Intelligent logging method and system for borehole cores

Abstract

This invention provides an intelligent borehole core logging method and system. The cloud-based system creates project records and borehole records using user-input project information and borehole design data from a web application. The web application retrieves these records from the cloud and stores them in association with the borehole design data. A mobile application retrieves corresponding target data from the cloud based on user-input geological identifier information and core attribute data. The cloud performs geological calculations using core parameter information input from the mobile application. The mobile application retrieves the geological calculation results from the cloud and stores them in association with the core parameter information. The cloud processes the original core box image to obtain a standard core box image. The mobile application retrieves the standard core box image from the cloud and stores the relevant data in association with the cloud. This invention ensures high-quality and efficient borehole core logging.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for intelligent logging of borehole cores. Background Technology

[0002] Rock cores are the most direct and practical data for studying and understanding underground geology and mineral resources. Through rock cores, we can understand the age, lithology, and sedimentary characteristics of strata; the physical and chemical properties of reservoirs and their oil, gas, and water content; the characteristics and oil-generating indicators of source layers; and the underground structural conditions. Borehole core logging is the process of systematically recording and describing the drilling process of rock cores.

[0003] The process of core logging under current technological conditions is as follows:

[0004] 1) Preparation: Determine the necessary tools (e.g., core box, measuring tools, ruler, magnifying glass, writing tools) and materials (e.g., logging forms, core box, notebook) for manually recording core information. 2) Filling out logging forms: Fill in the measurement results, observations, and descriptions in the recording forms (e.g., drill bit record form, soil record form, water level record form, dynamic exploration record form, SPT record form, etc.). 3) Core processing: Number the retrieved cores according to the drilling depth, perform preliminary processing (including removing soil, washing the core surface to remove drilling fluid, marking the start and end positions of each core run, etc.), and finally place them in the core box. 4) Core photography: Take photos of each box of cores using a camera. 5) Logging measurements: Use measuring tools (e.g., ruler or digital measuring instrument) to measure the length and diameter of the cores, and record the measurement results for each core segment. 6) Observation and Description: Use a magnifying glass to observe the details of the core (including the rock's color, structure, texture, mineral content, etc.) and describe them, recording any unusual structures, fractures, joints, or changes in the core. 7) Sampling: Select appropriate locations for sampling according to needs and sampling purposes, and record detailed sampling information. 8) Data Logging and Compilation: Compile and summarize all logged data and digitize it for subsequent analysis and application. 9) Data Archiving: Archive and store the logged data and core samples for future retrieval and research. 10) Report Compilation: Compile a detailed core logging report based on the logged data, including a detailed description of the core, measurement data, and image data.

[0005] The disadvantages of current borehole core logging methods under existing technological conditions are as follows: 1) Handwritten logging is labor-intensive and inefficient. 2) Handwritten logging has low standardization, requires high professional skills from loggers, and data quality cannot be guaranteed. 3) Paper storage leads to complex data maintenance and management, poor information security, inconvenient data retrieval and analysis, and difficulties in sharing and collaboration. Summary of the Invention

[0006] In view of this, the purpose of the present invention is to provide a method and system for intelligent logging of borehole cores, so as to alleviate the above-mentioned problems existing in the prior art.

[0007] In a first aspect, embodiments of the present invention provide a method for intelligent logging of borehole cores, applied to an intelligent logging system for borehole cores. The intelligent logging system includes a cloud terminal, a mobile terminal, and a web terminal, with the cloud terminal connected to both the mobile terminal and the web terminal. The method includes: the web terminal obtaining project records created by the cloud terminal using project information input by the user, and obtaining borehole records created by the cloud terminal using borehole design data input by the user; then, associating and storing the project records, the borehole records, and the borehole design data in the cloud terminal; the mobile terminal obtaining first target data from the cloud terminal based on geological identification information input by the user, and storing the geological identification information in the cloud terminal. The quality identification information and the first target data are associated and stored in the cloud; the mobile terminal obtains the geological calculation results calculated by the cloud using the core parameter information based on the core parameter information input by the user, and associates and stores the core parameter information and the geological calculation results in the cloud; wherein, the geological calculation results include at least one of the following: ROD, permeability coefficient, shape coefficient, Lurong value, PQ curve type, and formation continuity; the mobile terminal obtains the second target data from the cloud based on the core attribute data input by the user, and obtains the standard core box image obtained by the cloud after processing the original core box image, and then associates and stores the core attribute data, the second target data, and the standard core box image in the cloud.

[0008] Secondly, embodiments of the present invention also provide an intelligent borehole core logging system, comprising a cloud terminal, a mobile terminal, and a web terminal, wherein the cloud terminal is connected to the mobile terminal and the web terminal respectively; the web terminal is used to: obtain project records created by the cloud terminal using project information input by the user, and obtain borehole records created by the cloud terminal using borehole design data input by the user, and then associate and store the project records, the borehole records, and the borehole design data in the cloud terminal; the mobile terminal is used to: obtain first target data from the cloud terminal based on geological identification information input by the user, and associate the geological identification information and the first target data. The mobile terminal is used to: obtain geological calculation results calculated by the cloud using the core parameter information based on the core parameter information input by the user, and associate and store the core parameter information and the geological calculation results in the cloud; wherein, the geological calculation results include at least one of the following: ROD, permeability coefficient, shape coefficient, Lürson value, PQ curve type, and formation continuity; the mobile terminal is used to: obtain second target data from the cloud based on the core attribute data input by the user, and obtain a standard core box image obtained by the cloud after processing the original core box image, and then associate and store the core attribute data, the second target data, and the standard core box image in the cloud.

[0009] This invention provides an intelligent logging method and system for borehole cores. The cloud-based system creates project records using user-input project information from a web application and creates borehole records using user-input borehole design data from the web application. The web application retrieves the project records and borehole records from the cloud and stores them in association with the borehole design data. A mobile application retrieves first target data from the cloud based on user-input geological identification information and stores it in association with the geological identification information. The cloud-based system performs geological calculations using core parameter information input from the mobile application, and the mobile application retrieves the geological calculation results from the cloud and stores them in association with the core parameter information. The mobile application retrieves second target data from the cloud based on user-input core attribute data. The cloud-based system processes the original core box image to obtain a standard core box image, and the mobile application retrieves the standard core box image from the cloud and stores the core attribute data, the second target data, and the standard core box image in association with the cloud. Using the above technology, during the logging process, users only need to input project information and borehole design data on the web terminal to automatically create project records and borehole records in the cloud. Users only need to input geological identification information, core parameter information, and core attribute data on the mobile terminal to automatically obtain relevant data and perform geological calculations, image processing, and associated storage in the cloud. Borehole core logging can be carried out using the cloud, mobile terminal, and web terminal together, with a high degree of automation and standardization, which helps to ensure the quality and efficiency of borehole core logging.

[0010] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained in accordance with the structures particularly pointed out in the description, claims and drawings.

[0011] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0012] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of the structure of a borehole core intelligent logging system according to an embodiment of the present invention;

[0014] Figure 2This is a flowchart illustrating an intelligent logging method for borehole cores according to an embodiment of the present invention.

[0015] Figure 3 This is an example diagram illustrating the implementation principle of intelligent logging of borehole cores in an embodiment of the present invention;

[0016] Figure 4 This is a diagram illustrating the effect of a mobile device accessing a geological knowledge retrieval service in an embodiment of the present invention.

[0017] Figure 5 This is a diagram illustrating the effect of a mobile terminal calling a geological calculation service in an embodiment of the present invention.

[0018] Figure 6 This is an example diagram of attribute data being entered on a mobile device in an embodiment of the present invention;

[0019] Figure 7 This is an example image of a mobile device capturing the original photo of a core box in an embodiment of the present invention;

[0020] Figure 8 This is an example of the effect of a mobile terminal calling an image processing service to identify a rock core box in an embodiment of the present invention.

[0021] Figure 9 This is a diagram showing the effect of perspective transformation after the mobile terminal calls the image processing service in an embodiment of the present invention.

[0022] Figure 10 This is a rendering of the mobile terminal associated attribute data and standard core box image in an embodiment of the present invention;

[0023] Figure 11 This is a rendering of a rock core photograph in an embodiment of the present invention that has not undergone image processing services.

[0024] Figure 12 This is a rendering of a core photograph processed by an image processing service in an embodiment of the present invention.

[0025] Figure 13 This is a diagram illustrating the effect of a mobile terminal calling an image processing service to stitch together core photos in an embodiment of the present invention.

[0026] Figure 14 This is a rendering of the web-based drill list in an embodiment of the present invention.

[0027] Figure 15 This is a rendering of a mobile device sharing core photos in an embodiment of the present invention;

[0028] Figure 16 This is a diagram showing the effect of loading boreholes onto a map in an embodiment of the present invention;

[0029] Figure 17 This is a rendering of a rock core model on a map and a display of rock core information in an embodiment of the present invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0031] Currently, the main drawbacks of existing borehole core logging methods under current technological conditions include: large workload and low efficiency of handwritten logging; low standardization of handwritten logging, high requirements for the professional skills of logging personnel, and unreliable data quality; paper storage, complex data maintenance and management, poor information security, inconvenient data retrieval and analysis, and difficulties in sharing and collaboration. Based on this, the present invention provides an intelligent borehole core logging method and system that can alleviate the above-mentioned problems existing in the prior art.

[0032] To facilitate understanding of this embodiment, a detailed description of the intelligent borehole core logging method disclosed in this embodiment of the invention will be provided first. This intelligent borehole core logging method can be applied to an intelligent borehole core logging system; see [link to previous section]. Figure 1 As shown, the intelligent borehole core logging system may include a cloud terminal 200, a mobile terminal 100, and a web terminal 300, with the cloud terminal 200 connected to both the mobile terminal 100 and the web terminal 300; see also Figure 2 As shown, the intelligent logging method for borehole cores may include the following steps:

[0033] In step S202, the WEB terminal 300 obtains the project record created by the cloud terminal 200 using the project information based on the project information input by the user, and obtains the drilling record created by the cloud terminal 200 using the drilling design data based on the drilling design data input by the user. Then, the project record, drilling record and drilling design data are associated and stored in the cloud terminal 200.

[0034] When creating a project, relevant personnel can manually input or import project details on the web client (300). The web client (300) then uploads the project details to the cloud client (200). The cloud client (200) automatically creates a project record in the project database using the project details and returns the created project record to the web client (300). After the project is successfully created, the drilling logger enters the drilling design data into a preset drilling template file and imports the template file into the web client (300). The web client (300) uploads the template file to the cloud client (200), which reads the drilling design data from the template file and uses the read data to create a drilling record in the database. The cloud client (200) then returns the created drilling record to the web client (300). After both the project and the drilling are successfully created, the web client (300) uploads the project record, drilling record, and drilling design data to the cloud client (200) database for linked storage in the form of a data table.

[0035] In step S204, the mobile terminal 100 obtains the first target data from the cloud 200 based on the geological identification information input by the user, and stores the geological identification information and the first target data together in the cloud 200.

[0036] Among them, geological identification information can refer to information that identifies the geological information of the borehole (such as geological age, geological time, geological genesis, rock and soil name, lithological description, etc.), such as stratigraphic number, etc., without limitation.

[0037] Users can enter geological identification information on mobile device 100. Mobile device 100 sends the geological identification information to cloud device 200. Cloud device 200 uses the geological identification information to perform data retrieval and returns the first target data retrieved to mobile device 100. Mobile device 100 uploads the geological identification information and the first target data to the database of cloud device 200 and stores them together in the form of a data table.

[0038] Step S206: The mobile terminal 100 obtains the geological calculation results calculated by the cloud terminal 200 using the core parameter information based on the core parameter information input by the user, and stores the core parameter information and the geological calculation results in the cloud terminal 200.

[0039] The geological calculation results may include ROD (Rock Quality Designation), permeability coefficient, shape factor, Lurong value, PQ curve type, stratigraphic continuity, etc., without limitation.

[0040] Users can input core parameters on mobile device 100. Mobile device 100 sends these values ​​to cloud device 200. Cloud device 200 uses these values ​​to calculate ROD, permeability coefficient, shape coefficient, Lurong value, PQ curve type, formation continuity, etc., and returns the calculation results to mobile device 100. Mobile device 100 then uploads these values ​​and calculation results to the database of cloud device 200 for associated storage in the form of a data table.

[0041] In step S208, the mobile terminal 100 obtains the second target data from the cloud 200 based on the core attribute data input by the user, and obtains the standard core box image obtained by the cloud 200 after processing the original core box image. Then, the core attribute data, the second target data and the standard core box image are associated and stored in the cloud 200.

[0042] Users can input necessary core attribute data (such as project, work site, borehole, depth, etc.) on mobile device 100. Mobile device 100 sends this core attribute information to cloud device 200. Cloud device 200 uses the core attribute information to perform data retrieval and returns the retrieved second target data to mobile device 100. Users can also use external camera equipment or the camera equipment built into mobile device 100 to take photos of the core box on-site and upload them to cloud device 200 via mobile device 100. Cloud device 200 processes the uploaded core box photos to obtain standard core box photos and returns the standard core box image to mobile device 100. Mobile device 100 uploads the core attribute data, second target data, and standard core box image to cloud device 200 for associated storage. In addition, cloud device 200 can also add annotation information to the standard core box image using the core attribute data and second target data associated with the standard core box image and return the annotated standard core box image to mobile device 100. Core box images (i.e., core box photos and / or standard core box images) can be stored simultaneously in the cloud (200) and on mobile devices (100) to prevent data loss.

[0043] This invention provides an intelligent borehole core logging method. During logging, users only need to input project information and borehole design data on the web terminal to automatically create project records and borehole records via the cloud. Users only need to input geological identification information, core parameter information, and core attribute data on the mobile terminal to automatically obtain relevant data and perform geological calculations, image processing, and associated storage via the cloud. Borehole core logging can be performed using the cloud, mobile terminal, and web terminal together, with a high degree of automation and standardization, which helps to ensure the quality and efficiency of borehole core logging.

[0044] As one possible implementation, the drilling design data may include the original drilling coordinate data; based on this, the steps of the cloud 200 in creating a drilling record using the drilling design data may include: the cloud 200 converting the original drilling coordinate data into drilling map coordinate data in a preset map coordinate system, and creating a drilling record using the drilling design data and the drilling map coordinate data.

[0045] For example, the cloud 200 can store multiple preset coordinate systems with known parameters (such as a general coordinate system, a local coordinate system, etc.) and a preset coordinate transformation library (i.e., a library that provides conversion methods between different coordinate systems, such as PROJ.4, etc.). The preset coordinate transformation library includes the coordinate transformation relationship between each preset coordinate system and the preset map coordinate system. Based on this, the step of converting the original borehole coordinate data into borehole map coordinate data in the preset map coordinate system by the cloud 200 can have the following two different operation methods depending on the situation:

[0046] Operation Method 1: If the original coordinate system of the borehole original coordinate data is a preset coordinate system, then Cloud 200 will use the preset coordinate transformation library to convert the original borehole coordinate data into borehole map coordinate data.

[0047] Operation Method 2: If the original coordinate system of the borehole original coordinate data is not the preset coordinate system, then Cloud 200 uses the Bursa seven-parameter model to convert the borehole original coordinate data into borehole map coordinate data; wherein, the Bursa seven-parameter model includes coordinate transformation parameters calculated using the reference coordinate values ​​of four or more control points corresponding to the original coordinate system and the preset map coordinate system respectively.

[0048] In practical applications, a coordinate transformation service can be pre-built for Cloud200: First, Cloud200's database contains known general and local coordinate systems for selection during project creation; then, a built-in coordinate transformation library is provided for use during coordinate transformation; if the original coordinates in the borehole design data use the database's built-in coordinate system, Cloud200 can directly utilize the built-in coordinate transformation library for coordinate transformation; if the original coordinates in the borehole design data use a local coordinate system and the parameters of that coordinate system are unknown, then at least four coordinate systems specific to the target coordinate system (i.e., the map used for borehole and core positioning and display) can be input into Cloud200. The control points for coordinates in the map coordinate system and the local coordinate system are used to calculate the seven parameters for coordinate transformation using the Bursa seven-parameter method. The Cloud 200 performs an accuracy evaluation on the calculated seven parameters and uses them as the coordinate transformation parameters if the accuracy evaluation result is qualified. The Cloud 200 then uses the Bursa model to transform the original coordinates to the target coordinate system. The above coordinate transformation process can be encoded into an API using programming languages ​​(such as Python), program frameworks (such as Flask), and coordinate transformation libraries (such as PROJ.4), and this API can be used as the coordinate transformation service of the Cloud 200 for invocation.

[0049] As one possible implementation, a pre-trained geological knowledge extraction model can be stored on the cloud 200; based on this, the above-mentioned intelligent logging method for borehole cores may also include: the cloud 200 acquiring geological text data, and using the geological knowledge extraction model to extract geological entities and geological entity relationships from the geological text data, and then using a preset map database to construct a geological knowledge graph using the extracted geological entities and geological entity relationships.

[0050] In practical applications, geological knowledge extraction models can include geological entity information extraction models and geological entity relationship information extraction models. These models extract geological entities and relationships from geological text data. A geological knowledge retrieval service can be pre-built for cloud-based systems: entity and relationship annotations are performed on geological-related text data to obtain annotated data with both entities and relationships. Then, the annotated data is used to train the geological entity information extraction model and the geological entity relationship information extraction model, respectively (for example, the annotated data is input into a deep learning model with a BERT+LSTM+CRF structure to train the geological entity information extraction model, and the annotated data is input into a BERT model to train the geological entity relationship information extraction model). The model extracts the geological entity information and the geological entity relationship information. Then, the text data to be processed (e.g., data scraped from the internet, data accumulated by geological exploration departments over the years) is input into the aforementioned geological entity information extraction model and geological entity relationship information extraction model, respectively. These two models then use natural language processing techniques to extract entities and relationships from the data, resulting in structured data of geological entity information and structured data of geological entity relationship information, respectively. The obtained structured data is then organized into a knowledge graph within a graph database (such as Neo4j), resulting in a geological knowledge graph. Cloud200 can use graph database query languages ​​(such as Cypher) to organize query statements to query the data in the graph database. The query results are then formatted and returned to the calling client. The geological information retrieval process can be encoded into an API using programming languages ​​(such as Python) and program frameworks (such as Flask), and this API can be used as a geological knowledge retrieval service for Cloud200. The geological knowledge retrieval service facilitates the retrieval and querying of geological information by constructing a relatively complete geological knowledge graph.

[0051] As one possible implementation, the steps of the cloud 200 processing the original core box image may include: the cloud 200 converting the original core box image into a grayscale image, performing edge detection on the grayscale image to obtain the edge image of each object in the grayscale image, then converting each edge image into a corresponding binary image, and using the standard core box contour information and the binary image to determine the core box contour in the original core box image, then using the core box contour to crop the original core box image, and performing perspective transformation on the cropped image to obtain the standard core box image.

[0052] In practical applications, intelligent geological image processing services can be pre-built for cloud-based systems.

[0053] The intelligent geological image processing service mainly provides two functions: core box recognition and core box image stitching.

[0054] Core box identification: Cloud200 uses computer vision and machine learning software libraries (such as OpenCV) to read the original photos of the captured core boxes and convert them into grayscale images. Edge detection algorithms (such as the Canny algorithm) are used to find the edges of objects in the original photos, and a threshold is applied to convert the edge images into binary images. Then, the findContours function is used to find the contours of each object in the original photos. Finding contours returns the contours of multiple objects to obtain a contour list. Further identification and filtering of the core box contours are needed from this list. When identifying and filtering the core box contours, features of the core box contours (such as perimeter, area, and circumscribed rectangle) are used. Features such as (etc.) are filtered, identified, and processed to obtain the core box outline; finally, the original photo is cropped using the accurate core box outline to obtain the core box image; when taking the original photo of the core box on site, due to the limitations of factors such as the site environment, it is usually impossible to take a strictly standardized frontal photo of the core box, resulting in a distortion of the core box shape. Therefore, Cloud200 can use the principle of perspective transformation to perform perspective transformation on the cropped core box image to correct the core box image, change the perspective effect of the image, so that the core box images taken from different angles can all present a frontal view, making the core box image clearer and more beautiful, and thus a standard core box image is obtained after the core box image is corrected;

[0055] Core box stitching: Cloud200 queries all standard core box images of a certain core segment from the big data platform and reads the standard core box images. After scaling the read standard core box images to unify the size, the images are stitched together in order from shallow to deep to form a complete stitched core box image.

[0056] The geological image processing process of core box identification and core box stitching can be encoded into an API using programming languages ​​(such as Python), program frameworks (such as Flask), scientific computing libraries (such as Numpy), and computer vision and machine learning software libraries. This API can then be used as a cloud-based intelligent geological image processing service for invocation.

[0057] As one possible implementation, the above-mentioned intelligent logging method for borehole cores may further include:

[0058] Step A1: Cloud 200 stores the drilling design data and drilling map coordinate data together.

[0059] In step A2, the web terminal 300 obtains drilling design data and drilling map coordinate data from the cloud terminal 200, and uses the drilling design data and drilling map coordinate data to generate drilling information corresponding to each drilling hole on a preset map.

[0060] Step A3: The web terminal 300 retrieves the third target data from the borehole design data and the fourth target data from the borehole map coordinate data from the cloud terminal 200 based on the target borehole information selected by the user, and uses the third target data and the fourth target data to render and generate the target core model.

[0061] As one possible implementation, the target core model may include core segment models of each core segment of the corresponding borehole, with each core segment model bound to the borehole identifier and the depth information of the corresponding core segment. Based on this, the above-mentioned intelligent borehole core logging method may further include: the web terminal 300 obtaining target borehole logging data from the cloud 200 based on the target core segment model selected by the user, and displaying the target borehole logging data; wherein, the target borehole logging data may include the first target borehole identifier, target depth information, and target standard core box image corresponding to the target core segment model, etc., without limitation.

[0062] As one possible implementation, the above-mentioned intelligent logging method for borehole cores may further include: a mobile terminal 100 obtaining a first stitched image obtained by the cloud 200 after stitching together multiple first standard core box images corresponding to the first depth parameter information based on the first depth parameter information input by the user.

[0063] As one possible implementation, the above-mentioned intelligent logging method for borehole cores may further include:

[0064] Step a1: The WEB terminal 300 generates a borehole list using the borehole records; wherein, the borehole list may include the borehole identifier and second depth parameter information of each borehole.

[0065] Step a2: The web client obtains the second stitched image by stitching together multiple second standard core box images corresponding to 200 pairs of second depth parameter information from the cloud based on the second target borehole identifier selected by the user in the borehole list.

[0066] To facilitate understanding, the implementation principle of the above-mentioned intelligent logging method for borehole cores will be described exemplarily below using a specific application as an example.

[0067] See Figure 3 As shown, the above-mentioned intelligent logging method for borehole cores mainly includes the following steps:

[0068] Step 1: Build coordinate transformation service, geological knowledge retrieval service, geological calculation service, and geological image processing service (i.e., image processing service, also known as intelligent geological image processing service) on the cloud.

[0069] To build a coordinate transformation service: First, Cloud200 uses built-in general coordinate systems (such as Beijing 54, Xi'an 80, CGCS2000, etc.) and some local coordinate systems with known parameters (such as Guangzhou 2000, etc.) for selection when creating projects. Cloud200 also has built-in PROJ.4 as a coordinate transformation library. If the original coordinates use the built-in coordinate system of the database, the coordinate transformation is performed directly using PROJ.4. If the original coordinates use a local coordinate system and the coordinate system parameters are unknown, at least four control points with coordinates in both the target coordinate system (i.e., map coordinate system) and the local coordinate system are input. This allows the Bursa model to calculate the seven parameters of the coordinate transformation and use these parameters to transform the original coordinates into the target coordinate system. This enables the subsequent conversion of borehole, core model, etc., coordinates to be correctly positioned on mobile 100 and web 300 maps. The above coordinate transformation process can be encoded into an API providing coordinate transformation services using Python, the Flask framework, and the PROJ.4 coordinate transformation library for easy calling.

[0070] A geological knowledge retrieval service is constructed by annotating geological-related text with entities and entity relationships. The annotated data is then trained using a deep learning model (BERT+LSTM+CRF) and a BERT model to obtain geological entity information extraction and geological entity relationship information extraction models, respectively. Text data (e.g., unstructured data) is then obtained from online scraping and geological exploration departments and fed into the aforementioned two models for entity and entity relationship extraction. The resulting structured data, containing geological entity and relationship information, is then input into Neo4j for geological knowledge graph construction. When the geological knowledge retrieval service is invoked, a query is generated using Cypher to query the data in Neo4j. The query results are then formatted and returned to the calling client. By constructing a relatively complete geological knowledge graph, geological information retrieval and querying are facilitated. The geological information retrieval and querying process is encoded into an API (i.e., the geological knowledge retrieval service) using Python and the Flask framework for easy invocation.

[0071] Build geological calculation services: Using Python, the Flask framework, the scientific computing library NumPy, and common calculation formulas used in geological logging, the calculation processes such as RQD, permeability coefficient, shape coefficient, Lurong value, PQ curve type, and stratigraphic continuity judgment are encoded into APIs (geological calculation services) that can be called.

[0072] Intelligent geological image processing service: This includes the core box recognition function and the core box stitching function mentioned above. The core box recognition function uses OpenCV to read the original core box photo and convert it into a grayscale image. The Canny algorithm is used to find the edges of objects in the original photo, and a threshold is applied to convert the edge image into a binary image. Then, the findContours function is used to find the contour of objects in the original photo. Based on features such as the core box contour, perimeter, area, area-to-perimeter ratio, and aspect ratio of the circumscribed rectangle, the core box contour is filtered, identified, and processed to obtain the core box contour. The original photo is then cropped using the core box contour to obtain the core box image. A perspective transformation is then used to correct the cropped core box image to obtain a standard core box image. During the perspective transformation, at least four corresponding control points (such as the corner points, center points, and midpoints of the edges of a rectangle) need to be defined in both the source and target images. These control points are used to determine a perspective transformation matrix, which maps each pixel in the source image to a new pixel position in the target image. The core box stitching function retrieves all standard core box images of a single core segment from the big data platform, scales these images to a uniform size, and then stitches them together into a complete core box image by sequentially stitching the images from shallowest to deepest depth. The geological image processing process is encoded into an API (i.e., intelligent geological image processing service) using Python, the Flask framework, OpenCV, and NumPy for easy access.

[0073] Step 2: Create a project on the web client and import the drill bit to automatically complete the drill bit creation.

[0074] When creating a project, relevant personnel enter detailed project information on the web client (300) and select the coordinate system used. The cloud client (200) automatically creates a project record in the project database and returns it to the web client (300). After successful project creation, the borehole logging personnel enter the borehole design data (including original coordinate data) into a pre-prepared Excel file and import the Excel file into the web client (300). The cloud client (200) reads the borehole design data from the Excel file to create a borehole record in the database and returns it to the web client (300). During borehole creation, the web client (300) automatically calls the coordinate transformation service of the cloud client (200) to convert the original coordinates in the borehole design data into coordinates used in the map and returns these coordinates to the web client (300). The above project creation process and borehole creation process are encoded into APIs using Python and the Flask framework for easy access.

[0075] Step 3: The mobile terminal 100 calls the geological knowledge retrieval service and enters the core information by clicking the drop-down menu (i.e., the user clicks the drop-down button to bring up an option list and then clicks to select the corresponding option in the option list); the mobile terminal 100 calls the geological calculation service to automatically complete geological calculations such as RQD, permeability coefficient, shape coefficient, Lürson value, PQ curve type, and stratigraphic continuity judgment.

[0076] After the coordinate transformation service is called in step 2 to obtain the coordinate points in the map coordinate system, the mobile terminal 100 reads the drilling data from the cloud terminal 200. The drilling data can be loaded and displayed on the respective maps of the mobile terminal 100 and the web terminal 300.

[0077] See Figure 4 As shown, after a user clicks the drop-down button on mobile device 100, a list of options pops up. Selecting an option immediately invokes the geological knowledge retrieval service on cloud device 200. Cloud device 200 retrieves relevant geological information and returns it to mobile device 100, which then automatically writes the returned geological information into the corresponding attribute fields. For example... Figure 4 As shown, when a user clicks the drop-down button to the right of "Stratigraphic Number" on mobile device 100, a pop-up option list appears on mobile device 100. After selecting an option corresponding to a stratum (e.g., stratum number "1-3s") in the option list, mobile device 100 calls the geological knowledge retrieval service on cloud device 200 to retrieve the geological information associated with that stratum. Cloud device 200 returns the retrieved geological information to mobile device 100 in JSON format. Mobile device 100 uses the geological information to automatically complete the input of attributes such as "Geological Age", "Rock and Soil Name", and "Lithological Description" using a key-value matching method (e.g., using the attribute field name as the key and the attribute field value as the value). Users can also save the input information as a template description file on mobile device 100 and upload it to cloud device 200 for associated storage by clicking the corresponding button.

[0078] See Figure 5 As shown, after the user inputs the values ​​of relevant core parameters on mobile device 100, mobile device 100 automatically calls the geological calculation service on cloud device 200 to complete calculations such as RQD, permeability coefficient, shape coefficient, Lurong value, PQ curve type, and stratigraphic continuity judgment. Cloud device 200 returns the calculation results to mobile device 100, and mobile device 100 automatically writes the returned calculation results into the corresponding attribute fields. For example... Figure 5As shown, the user inputs the values ​​for "starting hole depth", "ending hole depth", "flow rate 1", "flow rate 2", "flow rate 3", "flow rate 4", "flow rate 5", "water level", "number of connecting pairs", and "total drill pipe length" on mobile device 100, and then selects "pressure stage". Mobile device 100 then uses the input values ​​to call the geological calculation service on cloud device 200 to calculate the values ​​for "test section length", "PQ curve type", and "Lü Rong value". Cloud device 200 returns the calculation results to mobile device 100 in JSON format. Mobile device 100 uses the calculation results to automatically complete the attribute entry for "test section length", "PQ curve type", and "Lü Rong value" using key-value matching. After the relevant data entry is complete, the user can also click the corresponding button on mobile device 100 (e.g., ...). Figure 5 The data is saved locally on the mobile device (100%) and uploaded to the cloud (200%) using the "Save and Add" button.

[0079] Step 4: The mobile device 100 takes a picture of the original core box, and calls the core box recognition function of the geological image intelligent processing service to intelligently recognize and process the original core box picture to obtain a standard core box image (i.e., a standard core box picture); the mobile device 100 or the WEB terminal 300 calls the core box stitching function of the geological image intelligent processing service to automatically stitch together the standard core box picture.

[0080] See Figure 6 As shown, before taking photos of the core box on the mobile device, users need to enter necessary attribute data, such as start depth, end depth, recording time, logger, project name, etc.

[0081] See Figures 7 to 10 As shown, mobile terminal 100 uses the mobile device's camera to capture the original photo of the core box (e.g., Figure 7 As shown), after the photo is taken, the mobile device 100 immediately and automatically calls the geological image processing service (core box recognition) on the cloud 200, and simultaneously uploads the original photo of the core box to the cloud 200; when the mobile device 100 uploads the core box photo to the cloud 200, it will also simultaneously upload the attribute data entered by the user (e.g., Figure 6 The start depth, end depth, recording time, logger, and project name are uploaded to Cloud200 for storage. Cloud200 then processes the uploaded original photos using the core box recognition function of the geological image processing service, automatically identifying the core boxes in the original photos to obtain core box images (e.g., Figure 8 The image within the blue box in the middle), the core box image is further corrected by perspective transformation (e.g., using...). Figure 8The perspective transformation matrix is ​​calculated using the four corner points and the midpoints of the four sides of the blue box as eight control points. This matrix is ​​then used to perform a perspective transformation on the core box image, resulting in a clear and aesthetically pleasing standard core box image (e.g., ...). Figure 9 (As shown); the mobile terminal 100 can also associate and save standard core box images with user-entered attribute data (such as...). Figure 10 (As shown). In addition, the mobile device 100 can also upload images of standard core boxes to the cloud 200 for storage.

[0082] The cloud-based 200 system can also retrieve related core data (such as project, work site, borehole, depth, etc.) based on user-entered attribute data, and selectively annotate this attribute data and the retrieved core data onto a standard core box image. The annotated standard core box image is then returned to the mobile 100 system. See also... Figure 11 and Figure 12 As shown, a comparison was made between core images that had not undergone image processing services (i.e., geological image processing services) and core images that had undergone image processing services. It can be seen that... Figure 11 The core box in the middle is deformed, and Figure 12 The core box in the image is a standard rectangle, and the necessary core information (e.g., information about the core itself) is marked within a white border around the core box (e.g., top and bottom). Figure 12 The project name "XXXXXXX Project" is located at the top of the core box, while the site information "Dam Site Area", borehole number "BPZK27", and depth information "42-48" are located at the bottom of the core box.

[0083] See Figure 13 As shown, after the user inputs depth parameters (i.e., start depth and end depth) on mobile device 100, mobile device 100 calls the geological image processing service (core box stitching) on ​​cloud device 200. Cloud device 200 automatically finds standard core box images with necessary core information within the corresponding depth range based on the depth parameters, and stitches these standard core box images into a complete image according to a uniform size and format (e.g., ...). Figure 13 (As shown), and then the image is returned to the mobile device 100 for display.

[0084] The web-based 300 interface can also display and manage drill holes through a drill hole list (e.g., ...). Figure 14 As shown, after a user selects a borehole from the borehole list on the web client 300, the web client 300 can also call the cloud client 200 to automatically find standard core box images with necessary core information marked within the corresponding depth range of the borehole, and call the geological image processing service of the cloud client 200 to stitch the core boxes together (not described in detail here). The web client 300 then downloads the stitched image from the cloud client 200 to the local machine for display and saving.

[0085] Core box images can be stored simultaneously in the cloud (200%) and on mobile devices (100%) to ensure data security and prevent loss.

[0086] In practical applications, the images obtained after stitching together core boxes using the geological image processing service on the cloud (200) do not need to be stored, as the geological image processing service can be invoked at any time for core box stitching. Once the mobile device (100) receives the image stitched together from the cloud (200), the user can share it on the mobile device (e.g., via WeChat, WeChat Work, etc.). Figure 15 As shown, users can trigger the sharing of the stitched image by clicking the "Share" button displayed on the mobile device 100.

[0087] Since physical core boxes are inconvenient to preserve and transport for extended periods, images of core boxes become crucial data for geological problem analysis when physical core boxes are unavailable. The core box stitching function allows users to easily select and view standard core box images within a specified depth range, facilitating targeted geological problem analysis.

[0088] Step 5: The web client reads the core data from the cloud client and displays and manages it in a comprehensive, three-dimensional visualization on the map.

[0089] See Figure 3 and Figure 16 As shown, the web client 300 reads drilling data from the cloud 200 and loads it onto the map. When loading the drilling data onto the map, the web client 300 adds corresponding drilling icons (e.g., ...) to the preset map. Figure 16 The map shows circular icons, each with a corresponding borehole number marked nearby, and the status of each borehole is distinguished by the color of the circular icon. Each borehole icon is associated with its own borehole data.

[0090] See Figure 3 , Figure 16 and Figure 17 As shown, when a user clicks the borehole icon on the map on the web client (300), a pop-up menu appears on the web client (300). The user then clicks the "Core Model" button in the menu. The web client (300) then reads the core data from the cloud (200) and renders a three-dimensional core model based on the core data using a 3D visualization framework (such as Cesium or other WebGIS frameworks). Figure 17(As shown). When rendering a core model on the Web 300, it is necessary to first obtain the location (i.e., coordinates) of the core and the starting depth, ending depth, lithology, and size of each core segment. For example, the Web 300 renders a core model at coordinates (112, 26), with a core size (i.e., length) of 6 meters. The core has a 0-2 meter limestone segment and a 2-6 meter silty claystone segment from top to bottom. The core model is rendered using Cesium, and the core model size (i.e., diameter) is 20 cm.

[0091] See Figure 17 As shown, the core model uses color to distinguish the lithology of strata, and can also display labels to annotate relevant information (such as stratum depth and lithology) for each core segment. When a user clicks on a core segment in the core model on the web interface, the web interface will display detailed information about that core segment in a pop-up window, including attribute descriptions (e.g., Figure 17 (layer top depth, layer bottom depth), images (e.g.) Figure 17 The system displays information such as standard core box images, project information, work site information, borehole information, latitude and longitude information, soil and rock name, and diameter. The implementation of displaying detailed core information for a specific segment on the web-based 300 platform mainly involves: pre-establishing the correspondence between core segments and related information; when a user selects a segment of a core model, the web-based 300 platform first retrieves all borehole logging data corresponding to that borehole from the cloud based on the borehole ID; then, the web-based 300 platform retrieves borehole logging data at the corresponding depth from the cloud based on the depth information of that core segment, and selectively displays this portion of the borehole logging data.

[0092] After performing coordinate transformation using the coordinate transformation service in step 2 to obtain the coordinate points in the map coordinate system, the borehole and core models can be located and displayed on the map via mobile terminal 100 and web terminal 300. The operation method for locating and displaying borehole and core models on mobile terminal 100 is similar to that on web terminal 300, and will not be described in detail here. In addition to being used to locate borehole and core models on the map, the coordinate points in the map coordinate system can also be used for range queries (for example, first draw a rectangle on the map to define a geographical range, and select boreholes and cores whose coordinates are within that geographical range).

[0093] See Figure 3 As shown, the above-mentioned intelligent borehole core logging method can also query, manage, statistically analyze, and visualize various types of core logging data, such as borehole opening records, borehole closing records, borehole sealing records, template descriptions, soil and rock records, water level records, hydrogeological data, dynamic exploration records, sampling records, standard penetration test records, borehole diameter and structure, integrity, water injection test, water pressure test, core photography, and on-site photography, through mobile terminals 100 and WEB terminals 300.

[0094] The above-mentioned intelligent logging method for borehole cores utilizes cloud, mobile, and web terminals to jointly complete the logging and data management of borehole cores. The cloud provides geological knowledge retrieval services, geological calculation services, and intelligent geological image processing services, while storing the core data in big data. The mobile terminal calls the services provided by the cloud for intelligent core logging, and the web terminal reads the core data from the cloud and performs comprehensive, three-dimensional visualization and management.

[0095] The advantages of the aforementioned intelligent borehole core logging method mainly include: utilizing mobile devices for borehole core logging, resulting in a high degree of automation, standardization, and work efficiency; by calling geological knowledge retrieval services, core information can be entered simply by selecting list items and manually inputting a small amount of text; by calling geological calculation services, loggers can perform relevant geological data calculation and analysis without on-site manual calculations; by calling geological image intelligent processing services, core boxes are automatically identified and perspective transformation corrections are performed to obtain clear and aesthetically pleasing standard core box images, which are then automatically stitched together, resulting in high-quality images without post-processing. Furthermore, by constructing a coordinate transformation service, core data in any coordinate system can be loaded and displayed on a map; simultaneously, the three-dimensional model of the core, core information, and core photos are centrally and uniformly displayed, making the viewing of core-related information more comprehensive, three-dimensional, and complete.

[0096] Based on the above-described intelligent borehole core logging method, this invention also provides an intelligent borehole core logging system, see [link to relevant documentation]. Figure 1 and Figure 2 As shown, the intelligent logging system for borehole cores may include a cloud terminal 200, a mobile terminal 100, and a web terminal 300, wherein the cloud terminal 200 is connected to the mobile terminal 100 and the web terminal 300 respectively.

[0097] The WEB terminal 300 can be used to: obtain project records created by the cloud terminal 200 using the project information based on user input project information, and obtain drilling records created by the cloud terminal 200 using the drilling design data based on user input drilling design data, and then associate and store the project records, the drilling records and the drilling design data in the cloud terminal 200.

[0098] The mobile terminal 100 can be used to: obtain first target data from the cloud 200 based on geological identification information input by the user, and associate and store the geological identification information and the first target data in the cloud 200;

[0099] The mobile terminal 100 can be used to: obtain the geological calculation results calculated by the cloud 200 using the core parameter information based on the core parameter information input by the user, and associate and store the core parameter information and the geological calculation results in the cloud 200; wherein, the geological calculation results include at least one of the following: ROD, permeability coefficient, shape coefficient, Lürson value, PQ curve type, and formation continuity;

[0100] The mobile terminal 100 can be used to: obtain second target data from the cloud 200 based on the core attribute data input by the user, and obtain a standard core box image obtained by the cloud 200 after processing the original core box image, and then associate and store the core attribute data, the second target data and the standard core box image in the cloud 200.

[0101] Using the aforementioned intelligent borehole core logging system, during logging, users only need to input project information and borehole design data on the web terminal to automatically create project records and borehole records via the cloud. Users only need to input geological identification information, core parameter information, and core attribute data on the mobile terminal to automatically obtain relevant data and perform geological calculations, image processing, and associated storage via the cloud. Borehole core logging can be performed using the cloud, mobile terminal, and web terminal together, with a high degree of automation and standardization, which helps to ensure the quality and efficiency of borehole core logging.

[0102] The intelligent core logging system provided in this embodiment of the invention has the same implementation principle and technical effects as the aforementioned intelligent core logging method embodiment. For the sake of brevity, any parts not mentioned in the intelligent core logging system embodiment can be referred to the corresponding content in the aforementioned intelligent core logging method embodiment.

[0103] Unless otherwise specifically stated, the relative steps, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of the invention.

[0104] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0105] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0106] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for intelligent logging of borehole cores, characterized in that, An intelligent borehole core logging system is applied, comprising a cloud platform, a mobile terminal, and a web terminal, wherein the cloud platform is connected to both the mobile terminal and the web terminal; the intelligent borehole core logging method includes: The web client obtains the project record created by the cloud using the project information based on the project information input by the user, and obtains the drilling record created by the cloud using the drilling design data based on the drilling design data input by the user. Then, the project record, the drilling record and the drilling design data are associated and stored in the cloud. The mobile device sends the geological identification information input by the user to the cloud. The cloud uses the geological identification information to perform data retrieval and returns the retrieved first target data to the mobile device. The mobile device uploads the geological identification information and the first target data to the cloud's database for associated storage in the form of a data table. The mobile device sends the core parameter information input by the user to the cloud. The cloud uses the core parameter information to calculate the geological calculation results and returns the geological calculation results to the mobile device. The mobile device uploads the core parameter information and the geological calculation results to the cloud's database for associated storage in the form of a data table. The geological calculation results include ROD, permeability coefficient, shape coefficient, Llurong value, PQ curve type, and stratigraphic continuity. The mobile device sends the core attribute data input by the user to the cloud. The cloud uses the core attribute data to perform data retrieval and returns the retrieved second target data to the mobile device. The mobile device uploads the original core box image to the cloud. The cloud processes the original core box image to obtain a standard core box image and returns the standard core box image to the mobile device. The mobile device uploads the core attribute data, the second target data, and the standard core box image to the cloud for associated storage. The drilling design data includes the original coordinate data of the borehole; the cloud uses the drilling design data to create the drilling record, including: the cloud converts the original coordinate data of the borehole into borehole map coordinate data under a preset map coordinate system, and uses the drilling design data and the borehole map coordinate data to create the drilling record; The intelligent logging method for borehole cores further includes: the cloud storing the borehole design data and the borehole map coordinate data in association; the web client obtaining the borehole design data and the borehole map coordinate data from the cloud, and generating borehole information corresponding to each borehole on a preset map using the borehole design data and the borehole map coordinate data; the web client obtaining third target data from the borehole design data and fourth target data from the borehole map coordinate data based on the target borehole information selected by the user, and rendering using the third target data and the fourth target data to generate a target core model; the target core model includes core segment models of each core segment of the corresponding borehole, and each core segment model is bound to the borehole identifier of the corresponding borehole and the depth information of the corresponding core segment.

2. The intelligent logging method for borehole cores according to claim 1, characterized in that, The intelligent logging method for borehole cores also includes: The web client retrieves target borehole logging data from the cloud based on the target core segment model selected by the user, and displays the target borehole logging data; wherein, the target borehole logging data includes the first target borehole identifier, target depth information and target standard core box image corresponding to the target core segment model.

3. The intelligent logging method for borehole cores according to claim 1, characterized in that, The intelligent logging method for borehole cores also includes: The mobile device obtains a first stitched image based on the first depth parameter information input by the user, which is obtained by stitching together multiple first standard core box images corresponding to the first depth parameter information from the cloud.

4. The intelligent logging method for borehole cores according to claim 1, characterized in that, The intelligent logging method for borehole cores also includes: The web application uses the drilling records to generate a drilling list; wherein, the drilling list includes the drilling identifier and second depth parameter information of each drilling hole; The web client obtains a second stitched image based on the second target borehole identifier selected by the user for the borehole list, which is obtained by stitching together multiple second standard core box images corresponding to the second depth parameter information in the cloud.

5. The intelligent logging method for borehole cores according to claim 1, characterized in that, The cloud storage contains multiple preset coordinate systems with known parameters and a preset coordinate transformation library. The preset coordinate transformation library includes the coordinate transformation relationship between each preset coordinate system and the preset map coordinate system. The cloud platform converts the original borehole coordinate data into borehole map coordinate data in a preset map coordinate system, including: If the original coordinate system of the borehole original coordinate data is a preset coordinate system, the cloud uses the preset coordinate transformation library to convert the borehole original coordinate data into the borehole map coordinate data. If the original coordinate system of the borehole original coordinate data is not a preset coordinate system, the cloud platform uses the Bursa seven-parameter model to convert the borehole original coordinate data into the borehole map coordinate data; wherein, the Bursa seven-parameter model includes coordinate transformation parameters calculated using reference coordinate values ​​of four or more control points corresponding to the original coordinate system and the preset map coordinate system respectively.

6. The intelligent logging method for borehole cores according to claim 1, characterized in that, The cloud storage contains pre-trained geological knowledge extraction models; the intelligent logging method for borehole cores also includes: The geological text data is acquired from the cloud, and the geological knowledge extraction model is used to extract geological entities and relationships from the geological text data. Then, a geological knowledge graph is constructed using a preset graph database with the extracted geological entities and relationships.

7. The intelligent logging method for borehole cores according to claim 1, characterized in that, The cloud-based processing of the original core box images includes: The cloud platform converts the original core box image into a grayscale image and performs edge detection on the grayscale image to obtain the edge image of each object in the grayscale image. Then, each edge image is converted into a corresponding binary image, and the core box contour information and the binary image are used to determine the core box contour in the original core box image. Then, the original core box image is cropped using the core box contour, and the cropped image is subjected to perspective transformation to obtain the standard core box image.

8. A borehole core intelligent logging system, characterized in that, The intelligent borehole core logging system includes a cloud platform, a mobile terminal, and a web terminal, with the cloud platform connected to both the mobile terminal and the web terminal. The web interface is used to: obtain project records created by the cloud using the project information based on user input, and obtain drilling records created by the cloud using the drilling design data based on user input, and then associate and store the project records, the drilling records, and the drilling design data in the cloud. The mobile terminal is used to: send the geological identification information input by the user to the cloud, receive the first target data retrieved and returned by the cloud after using the geological identification information to perform data retrieval, and upload the geological identification information and the first target data to the database of the cloud for associated storage in the form of a data table; The mobile terminal is used to: send the core parameter information input by the user to the cloud, receive the geological calculation results obtained and returned by the cloud after using the core parameter information, and upload the core parameter information and the geological calculation results to the database of the cloud for associated storage in the form of a data table; wherein, the geological calculation results include ROD, permeability coefficient, shape coefficient, Lürson value, PQ curve type and stratigraphic continuity; The mobile terminal is used to: send core attribute data input by the user to the cloud; receive second target data retrieved and returned by the cloud after performing data retrieval using the core attribute data; upload the original core box image to the cloud; receive the standard core box image obtained and returned by the cloud after processing the original core box image; and upload the core attribute data, the second target data, and the standard core box image to the cloud for associated storage. The drilling design data includes the original coordinate data of the borehole; the cloud uses the drilling design data to create the drilling record, including: the cloud converts the original coordinate data of the borehole into borehole map coordinate data under a preset map coordinate system, and uses the drilling design data and the borehole map coordinate data to create the drilling record; The cloud platform is used to associate and store the borehole design data and the borehole map coordinate data; the web platform is also used to: obtain the borehole design data and the borehole map coordinate data from the cloud platform, and generate borehole information corresponding to each borehole on a preset map using the borehole design data and the borehole map coordinate data; obtain third target data from the borehole design data and fourth target data from the borehole map coordinate data from the cloud platform based on the target borehole information selected by the user, and render the third target data and fourth target data to generate a target core model; the target core model includes core segment models of each core segment of the corresponding borehole, and each core segment model is bound to the borehole identifier of the corresponding borehole and the depth information of the corresponding core segment.

Images