Triple association-based oil and gas geology knowledge graph construction method and system, medium and equipment

Abstract

The invention relates to the field of oil and gas artificial intelligence and data management, and discloses an oil and gas geology knowledge graph construction method and system based on triple association, a medium and equipment, and the method comprises the steps: carrying out the entity extraction of an oil and gas geology text through employing a large language model, and recognizing and extracting an entity from the oil and gas geology text; associating the extracted and identified entities with authoritative documents through a semantic similarity algorithm to obtain a source of each entity; in combination with professional dictionaries and textbooks, corresponding accurate term definitions are distributed to each extracted and recognized entity, so that term definition integration is realized; and performing triple construction on the extracted and recognized entities, the sources of the entities and the term definitions of the entities, forming an entity-source-definition knowledge unit by the extracted and recognized entities, the sources of the entities and the term definitions of the entities, and further constructing a knowledge graph in the field of oil and gas geology. According to the invention, the information accuracy is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of oil and gas artificial intelligence and data management technology, and in particular to a method, system, medium and equipment for constructing an oil and gas geological knowledge graph based on triple association. Background Art

[0002] With the continuous accumulation of oil and gas geological data, knowledge management in oil and gas field development is becoming increasingly complex. This data covers every stage from exploration and development to production, and exists in a variety of forms, such as text records, laboratory reports, and charts. Traditional knowledge management methods are unable to efficiently extract, integrate, and query key information when faced with such a large and diverse data set.

[0003] In the field of oil and gas geology, information accuracy and source reliability are crucial. For example, key data such as reserve estimates and porosity and permeability measurements require not only high accuracy but also clear sources and authoritative definitions. However, existing data management methods often rely on unstructured text storage, making information retrieval difficult and making it difficult to guarantee information accuracy and source reliability. Summary of the Invention

[0004] In response to the above problems, the purpose of the present invention is to provide a method, system, medium and equipment for constructing an oil and gas geological knowledge graph based on triple association, which effectively improves the accuracy of information and provides a solid foundation for subsequent knowledge graph construction.

[0005] To achieve the above-mentioned objectives, in the first aspect, the technical solution adopted by the present invention is: a method for constructing an oil and gas geology knowledge graph based on triple association, which includes: using a large language model to extract entities from oil and gas geology texts, identifying and extracting entities from oil and gas geology texts; using a semantic similarity algorithm, associating the extracted and identified entities with authoritative documents to obtain the source of each entity; combining professional dictionaries and textbooks to assign corresponding precise term definitions to each extracted and identified entity to achieve term definition integration; constructing triples of the extracted and identified entities, the sources of the entities and the term definitions of the entities, and then constructing a knowledge graph in the field of oil and gas geology.

[0006] Furthermore, a large language model is used to extract entities from oil and gas geology texts, identifying and extracting entities from oil and gas geology texts, including: The large language model used is based on a pre-trained oil and gas geology knowledge base, performs natural language processing on oil and gas geology texts, and extracts domain-related entities; Segment and clean the input text to remove redundant content; Through natural language processing technology, key words and entities in the text are extracted, and the relationships between different entities are identified.

[0007] Furthermore, the extracted and identified entities are associated with authoritative literature through semantic similarity algorithms, including: The semantic similarity algorithm adopts a semantic matching method based on deep learning. By calculating the similarity between the entity and the authoritative literature, it automatically matches the relevant literature and completes the source link of the entity.

[0008] Furthermore, by combining professional dictionaries and textbooks, each extracted and identified entity is assigned a corresponding precise term definition, including: Extract key terms from professional dictionaries and textbooks through text analysis technology; Assign the most accurate terminology to each entity through key terms to ensure professionalism and consistency of terminology; For unstructured term descriptions, key information and feature points are extracted through text analysis technology and converted into structured definition representations.

[0009] Furthermore, the extracted and identified entities, their sources, and their terminology definitions are constructed into triples to construct a knowledge graph in the field of oil and gas geology, including: The extracted and identified entity, the source of the entity and the term definition of the entity constitute a triple of "entity-source-definition", and each triple is a knowledge unit; Integrate all knowledge units into a unified knowledge graph to form a multimodal knowledge representation framework; Format and optimize the knowledge graph.

[0010] Furthermore, after constructing the knowledge graph, it also includes: providing decision support for oil and gas exploration based on the constructed oil and gas geological knowledge graph.

[0011] Furthermore, based on the constructed oil and gas geological knowledge map, decision support is provided for oil and gas exploration, including: Input exploration data, clean the exploration data through data preprocessing, and convert the cleaned data into a format suitable for knowledge graph reasoning; Based on historical oil and gas reserves and porosity data, combined with current exploration data, and through reasoning analysis using knowledge graphs, oil and gas exploration reports are automatically generated. These reports include oil and gas field potential assessments and future development recommendations, providing data support for decision makers. The knowledge graph is dynamically updated based on new data to ensure that the knowledge graph can reflect the latest progress in oil and gas exploration in real time and provide continuous support for subsequent decision-making.

[0012] In the second aspect, the technical solution adopted by the present invention is: a system for constructing an oil and gas geology knowledge graph based on triple association, which includes: an entity extraction module, which uses a large language model to extract entities from oil and gas geology texts, and identifies and extracts entities from oil and gas geology texts; a source linking module, which uses a semantic similarity algorithm to associate the extracted and identified entities with authoritative documents to obtain the source of each entity; a term definition integration module, which combines professional dictionaries and textbooks to assign corresponding precise term definitions to each extracted and identified entity to achieve term definition integration; a knowledge graph construction module, which constructs triples of the extracted and identified entities, the sources of the entities and the term definitions of the entities, and then constructs a knowledge graph in the field of oil and gas geology.

[0013] In a third aspect, the technical solution adopted by the present invention is: a computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions, and when the instructions are executed by a computing device, the computing device executes any one of the above methods.

[0014] In a fourth aspect, the technical solution adopted by the present invention is: a computing device, comprising: one or more processors, a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the above methods.

[0015] The present invention has the following advantages due to the adoption of the above technical solution: 1. This invention utilizes natural language processing (NLP) technology, specifically large language models (LLMs), to identify and extract key entities from massive amounts of oil and gas geology text. These entities include, but are not limited to, geological parameters such as reserves, porosity, and permeability, as well as geological features such as geological structure and reservoir type.

[0016] 2. To ensure the accuracy and authority of the extracted entities, this paper introduces a semantic similarity algorithm. This algorithm associates the extracted entities with authoritative literature (such as API standards and drilling manuals), ensuring that each entity has a clear and reliable source. This step not only improves the accuracy of the information but also provides a solid foundation for subsequent knowledge graph construction.

[0017] 3. This invention aims to address existing challenges in oil and gas geological knowledge management. By leveraging NLP technology, semantic similarity algorithms, and the support of professional dictionaries and textbooks, it enables unified knowledge representation across data sources, forming a knowledge graph encompassing multi-level semantic relationships. This will provide strong support for knowledge management during oil and gas field development and facilitate the development of downstream products, such as intelligent question-answering systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of a method for constructing an oil and gas geological knowledge graph based on triple association in an embodiment of the present invention; Figure 2 This is a flowchart of oil and gas exploration decision support based on triple association in an embodiment of the present invention; Figure 3 It is a schematic diagram of the oil and gas geological knowledge graph structure based on triple association in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] To address the difficulty in uniformly representing and deeply linking multi-source, heterogeneous data in traditional oil and gas geology information processing, this invention provides a method, system, medium, and device for constructing an oil and gas geology knowledge graph based on triple associations. This method utilizes a large language model (LLM) for entity extraction, a semantic similarity algorithm for source linking, and the integration of professional dictionaries and textbooks for term definitions, forming a knowledge unit consisting of [entity-source-definition] to meet the knowledge management and application needs of the oil and gas geology field.

[0020] This invention constructs a precise and authoritative oil and gas geology knowledge graph by innovatively organizing domain data into "entity-source-definition" knowledge units. A large language model (LLM) is used to identify key entities in oil and gas geology texts (such as oilfield feasibility studies) and extract key field parameters such as reserves, porosity, and permeability. A semantic similarity algorithm is used to link the identified entities to authoritative references (such as API standards and drilling manuals) to ensure the accuracy and authority of the knowledge sources. Finally, combined with authoritative references (such as API standards and drilling manuals), precise term definitions are provided for each entity, forming a unified, multi-level semantically associated knowledge representation. This invention effectively integrates knowledge across data sources, providing fundamental support for oil and gas field development knowledge management and downstream applications (such as question-answering systems).

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the described embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of the present invention.

[0022] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0023] In one embodiment of the present invention, a method for constructing an oil and gas geology knowledge graph based on triple associations is provided. This method organizes oil and gas geology data into "entity-source-definition" knowledge units. By combining a large language model (LLM) with a semantic similarity algorithm, a unified knowledge representation across data sources is provided. This method can be widely applied to intelligent management of oil and gas geology data, knowledge graph construction, and downstream product development (such as question-answering systems and decision support systems). It is particularly suitable for oil and gas field development, oil and gas exploration, and geological knowledge management. It aims to improve the efficiency and accuracy of knowledge acquisition in the oil and gas geology field and support the intelligent decision-making and management required in oil and gas exploration, development, and production processes.

[0024] In this embodiment, Figure 1 As shown in FIG, the method for constructing an oil and gas geological knowledge graph based on triple association includes the following steps: 1) Use a large language model (LLM) to extract entities from oil and gas geology texts, identifying and extracting entities from them. Oil and gas geology texts include but are not limited to oilfield feasibility studies and geological exploration reports. 2) Using a semantic similarity algorithm, the extracted and identified entities are associated with authoritative literature to determine the source of each entity. Authoritative literature includes, but is not limited to, API standards, drilling manuals, and other field standards and literature. 3) Combine professional dictionaries and textbooks to assign corresponding precise term definitions to each extracted and identified entity to achieve term definition integration; professional dictionaries include but are not limited to petroleum technology dictionaries, and textbooks include but are not limited to drilling engineering, reservoir engineering, and other related textbooks; 4) The extracted and identified entities, their sources, and their terminology definitions are grouped into triplets, forming a knowledge unit of “entity-source-definition”, thereby constructing a knowledge graph in the field of oil and gas geology.

[0025] In step 1) above, a large language model is used to extract entities from the oil and gas geology text. Identifying and extracting entities from the oil and gas geology text includes the following steps: 1.1) The large language model used is based on a pre-trained oil and gas geology knowledge base. It performs natural language processing (NLP) on oil and gas geology text and extracts domain-related entities such as reserves, porosity, and permeability.

[0026] 1.2) Segment and clean the input text to remove redundant content; 1.3) Using natural language processing techniques, we extract key words and entities from the text and identify relationships between different entities, such as the relationship between exploration locations and oil and gas reservoirs, and the association between exploration results and experimental methods.

[0027] In step 2) above, the extracted and identified entities are associated with authoritative documents using a semantic similarity algorithm. Specifically, this algorithm uses a deep learning-based semantic matching method to automatically match relevant documents and complete the entity's source link by calculating the similarity between the entity and the authoritative document. Specifically, in this embodiment, a preset similarity threshold (for example, 0.8) is set. When the calculated semantic similarity between the entity and an authoritative document is greater than or equal to this threshold, the entity is automatically associated with the corresponding document. If multiple candidate documents meet the threshold, the document with the highest similarity is selected as the final source. This mechanism ensures the accuracy and authority of entity source matching.

[0028] In this embodiment, a semantic similarity algorithm is used to match the extracted entities with relevant entities and relationships in authoritative documents (such as API standards and drilling manuals) to ensure the authority and accuracy of the information source; through graph retrieval enhancement generation technology, nodes related to the entities in the query text are searched in the knowledge graph, and more potential matches are automatically inferred.

[0029] In step 3) above, combining professional dictionaries and textbooks, assigning corresponding precise term definitions to each extracted and identified entity includes the following steps: 3.1) Extract key terms from professional dictionaries (e.g., petroleum technology dictionaries) and textbooks (e.g., drilling engineering, reservoir engineering) using text analysis techniques; 3.2) Assign the most accurate terminology definition to each entity through key terms to ensure professionalism and consistency of terminology; 3.3) For unstructured term descriptions, key information and feature points are extracted through text analysis technology and converted into structured definition representations.

[0030] In step 4), the extracted and identified entities, their sources, and their terminology definitions are constructed into triples to construct a knowledge graph for the oil and gas geology field. This includes the following steps: 4.1) The extracted entity, the source of the entity, and the term definition of the entity form a triple of "entity-source-definition", and each triple is regarded as a knowledge unit; 4.2) Integrate all knowledge units into a unified knowledge graph to form a multimodal knowledge representation framework; 4.3) Format and optimize the knowledge graph to improve its readability and user experience in practical applications.

[0031] In the above embodiment, after constructing the knowledge graph, the process also includes providing decision support for oil and gas exploration based on the constructed oil and gas geology knowledge graph (step 5). By analyzing historical exploration data and geological reports, the system automatically extracts key entities and generates an exploration report based on factors such as oil and gas reserves and porosity, providing a scientific basis for decision makers.

[0032] Specifically, in step 5), if Figure 2 As shown in the figure, based on the constructed oil and gas geological knowledge map, decision support is provided for oil and gas exploration, including the following steps: 5.1) Input exploration data, clean it through data preprocessing, and convert the cleaned data into a format suitable for knowledge graph reasoning; Among them, exploration data includes drilling depth, formation pressure, temperature, etc.

[0033] 5.2) Based on historical oil and gas reserves and porosity data, combined with current exploration data, and through reasoning and analysis using knowledge graphs, an oil and gas exploration report is automatically generated. This report includes an assessment of the oil and gas field's potential and recommendations for future development, providing data support for decision makers.

[0034] 5.3) As exploration progresses, the knowledge graph is dynamically updated based on newly added data. Through continuous data input and knowledge integration, the knowledge graph is ensured to reflect the latest progress in oil and gas exploration in real time, providing continuous support for subsequent decision-making.

[0035] In this example, a knowledge graph for oil and gas geology was constructed based on triple associations. The large language model (LLM) and semantic similarity algorithm were used to process and integrate multi-source data in the oil and gas geology field to construct an oil and gas geology knowledge graph. The specific operation process is as follows: (1) Collect raw data from various data sources in the field of oil and gas geology (such as oilfield feasibility study reports, reservoir assessment reports, oil and gas exploration data, technical literature, etc.). Clean and preprocess the data to remove redundant information, unify the format, and perform word segmentation on the text data.

[0036] (2) Use the Large Language Model (LLM) to perform entity recognition on the preprocessed text data and extract key entities in the field of oil and gas geology. These include but are not limited to geological parameters such as oil and gas reserves, porosity, permeability, lithology, pressure, and temperature. In specific implementation, the LLM is pre-trained on a specific dataset in the field of oil and gas geology to accurately identify and extract relevant domain entities.

[0037] (3) Using a semantic similarity algorithm, the extracted entities are matched with relevant authoritative literature. Literature sources include API standards, drilling manuals, and oil and gas geology textbooks. The semantic similarity calculation automatically assigns the appropriate source to the entity by comparing the vector representation of the extracted entity with the relevant terms in the literature. For example, the reserve entity will be linked to the relevant API standard literature on oil and gas reserves.

[0038] (4) Use professional dictionaries (e.g., petroleum technology dictionaries) and textbooks (e.g., drilling engineering, reservoir engineering) to provide accurate terminology definitions for each entity. This step ensures terminology consistency and accuracy by matching entities in the text with definitions in dictionaries or textbooks. For each entity, the system automatically assigns a precise term definition and integrates it.

[0039] Example: Reserves are defined as "the total amount of oil or natural gas that can be recovered from a reservoir."

[0040] Porosity is defined as "the ratio of pore volume to total volume of a rock."

[0041] (5) Construct triples of "entity-source-definition" and store them in the knowledge graph database. Each triple forms a knowledge unit. The knowledge graph forms a multi-level semantic network through the links between entities, relationships and attributes. This semantic network supports reasoning and retrieval of complex oil and gas geological problems. Figure 3 The figure shows the structure of the knowledge graph after construction. Taking the typical entity "DST test" as an example, it shows how the "entity-source-definition" triplet of the present invention is presented in the knowledge warehouse, where the "entity" is "DST test", which represents a formation testing method. The "source" is the original text corresponding to the entity extracted from the reservoir geological report, from which the text "Oil field formation temperature and pressure are obtained from DST test and formation pressure test data" is obtained. The "definition" is the term definition taken from the petroleum professional textbook and petroleum dictionary, specifically defined as "Drillstem formation test - DST (drillstem test) is an advanced technology that uses a drill pipe or oil tubing with a formation tester with a packer to test oil in the well. It can be tested in wells with casing or in open hole wells without casing..."

[0042] (6) The constructed oil and gas geological knowledge graph is used to support reasoning for specific queries. For example, when querying "the relationship between permeability and porosity of a certain oil and gas field," the system can retrieve relevant entities and perform reasoning based on the semantic associations in the knowledge graph to obtain the answer. At the same time, it supports deeper answers to queries through graph reasoning.

[0043] In one embodiment of the present invention, a system for constructing an oil and gas geological knowledge graph based on triple association is provided, which includes: The entity extraction module uses a large language model to extract entities from oil and gas geology texts, identifying and extracting entities from oil and gas geology texts; The source linking module uses a semantic similarity algorithm to associate the extracted and identified entities with authoritative documents to obtain the source of each entity; The term definition integration module combines professional dictionaries and textbooks to assign corresponding precise term definitions to each extracted and identified entity to achieve term definition integration; The knowledge graph construction module constructs triples of the extracted and identified entities, the sources of the entities, and the term definitions of the entities, and then constructs a knowledge graph in the field of oil and gas geology.

[0044] In the above embodiment, a large language model is used to extract entities from the oil and gas geology text, and entities are identified and extracted from the oil and gas geology text, including: The large language model used is based on a pre-trained oil and gas geology knowledge base, performs natural language processing on oil and gas geology texts, and extracts domain-related entities; Segment and clean the input text to remove redundant content; Through natural language processing technology, key words and entities in the text are extracted, and the relationships between different entities are identified.

[0045] In the above embodiment, the extracted and identified entities are associated with authoritative documents through a semantic similarity algorithm, including: The semantic similarity algorithm adopts a semantic matching method based on deep learning. By calculating the similarity between the entity and the authoritative literature, it automatically matches the relevant literature and completes the source link of the entity.

[0046] In the above embodiment, a corresponding precise term definition is assigned to each extracted and identified entity in combination with professional dictionaries and teaching materials, including: Extract key terms from professional dictionaries and textbooks through text analysis technology; Assign the most accurate terminology to each entity through key terms to ensure professionalism and consistency of terminology; For unstructured term descriptions, key information and feature points are extracted through text analysis technology and converted into structured definition representations.

[0047] In the above embodiment, the extracted and identified entities, the sources of the entities, and the term definitions of the entities are constructed into triples to construct a knowledge graph in the field of oil and gas geology, including: The extracted and identified entity, the source of the entity and the term definition of the entity constitute a triple of "entity-source-definition", and each triple is a knowledge unit; Integrate all knowledge units into a unified knowledge graph to form a multimodal knowledge representation framework; Format and optimize the knowledge graph.

[0048] In the above embodiment, after the knowledge graph is constructed, it also includes: providing decision support for oil and gas exploration based on the constructed oil and gas geological knowledge graph.

[0049] In this embodiment, based on the constructed oil and gas geological knowledge graph, decision support is provided for oil and gas exploration, including: Input exploration data, clean the exploration data through data preprocessing, and convert the cleaned data into a format suitable for knowledge graph reasoning; Based on historical oil and gas reserves and porosity data, combined with current exploration data, and through reasoning analysis using knowledge graphs, oil and gas exploration reports are automatically generated. These reports include oil and gas field potential assessments and future development recommendations, providing data support for decision makers. The knowledge graph is dynamically updated based on new data to ensure that the knowledge graph can reflect the latest progress in oil and gas exploration in real time and provide continuous support for subsequent decision-making.

[0050] The system provided in this embodiment is used to execute the above-mentioned method embodiments. Please refer to the above-mentioned embodiments for specific processes and detailed contents, which will not be repeated here.

[0051] In one embodiment of the present invention, a computing device is provided. The computing device may be a terminal and may include: a processor, a communications interface, a memory, a display screen, and an input device. The processor, communications interface, and memory communicate with each other via a communications bus. The processor is configured to provide computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. When executed by the processor, the computer program implements the methods described in the above embodiments. The internal memory provides an environment for the operating system and computer program in the non-volatile storage medium to run. The communications interface is configured to communicate with an external terminal via wired or wireless communication. The wireless communication may be achieved via Wi-Fi, a network management service provider, NFC (near field communication), or other technologies. The display screen may be a liquid crystal display or an electronic ink display. The input device may be a touchscreen layer covering the display screen, or may be buttons, a trackball, or a touchpad provided on the computing device housing, or may be an external keyboard, touchpad, or mouse. The processor may invoke logic instructions stored in the memory.

[0052] In addition, the logical instructions in the above-mentioned memory can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0053] In one embodiment of the present invention, a computer program product is provided, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the methods provided by the above-mentioned method embodiments.

[0054] In one embodiment of the present invention, a non-transitory computer-readable storage medium is provided. The non-transitory computer-readable storage medium stores server instructions. The computer instructions enable a computer to execute the methods provided in the above embodiments.

[0055] The above embodiment provides a computer-readable storage medium, whose implementation principle and technical effects are similar to those of the above method embodiment, and will not be repeated here.

[0056] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0057] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0058] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0059] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for constructing an oil and gas geological knowledge graph based on triple association, characterized in that: include: A large language model is used to extract entities from oil and gas geology texts to identify and extract entities from oil and gas geology texts; Through the semantic similarity algorithm, the extracted and identified entities are associated with authoritative documents to obtain the source of each entity; Combine professional dictionaries and textbooks to assign corresponding precise term definitions to each extracted and identified entity to achieve term definition integration; The extracted and identified entities, their sources, and their terminological definitions are constructed into triples to build a knowledge graph in the field of oil and gas geology.

2. The method for constructing an oil and gas geological knowledge graph based on triple association according to claim 1, characterized in that: A large language model is used to extract entities from oil and gas geology texts. Entities are identified and extracted from oil and gas geology texts, including: The large language model used is based on a pre-trained oil and gas geology knowledge base, performs natural language processing on oil and gas geology texts, and extracts domain-related entities; Segment and clean the input text to remove redundant content; Through natural language processing technology, key words and entities in the text are extracted, and the relationships between different entities are identified.

3. The method for constructing an oil and gas geological knowledge graph based on triple association according to claim 1, characterized in that: The extracted and identified entities are associated with authoritative literature through semantic similarity algorithms, including: The semantic similarity algorithm adopts a semantic matching method based on deep learning. By calculating the similarity between the entity and the authoritative literature, it automatically matches the relevant literature and completes the source link of the entity.

4. The method for constructing an oil and gas geological knowledge graph based on triple association according to claim 1, characterized in that: Combining professional dictionaries and textbooks, each extracted and identified entity is assigned a corresponding precise term definition, including: Extract key terms from professional dictionaries and textbooks through text analysis technology; Assign the most accurate terminology to each entity through key terms to ensure professionalism and consistency of terminology; For unstructured term descriptions, key information and feature points are extracted through text analysis technology and converted into structured definition representations.

5. The method for constructing an oil and gas geological knowledge graph based on triple association according to claim 1, characterized in that: The extracted and identified entities, their sources, and their terminology definitions are grouped into triplets to construct a knowledge graph for the oil and gas geology field, including: The extracted and identified entity, the source of the entity, and the term definition of the entity constitute a triple of "entity-source-definition", and each triple is regarded as a knowledge unit; Integrate all knowledge units into a unified knowledge graph to form a multimodal knowledge representation framework; Format and optimize the knowledge graph.

6. The method for constructing an oil and gas geological knowledge graph based on triple association according to claim 1, characterized in that: After constructing the knowledge graph, it also includes: providing decision support for oil and gas exploration based on the constructed oil and gas geological knowledge graph.

7. The method for constructing an oil and gas geological knowledge graph based on triple association according to claim 6, characterized in that: Based on the constructed oil and gas geological knowledge map, it provides decision support for oil and gas exploration, including: Input exploration data, clean the exploration data through data preprocessing, and convert the cleaned data into a format suitable for knowledge graph reasoning; Based on historical oil and gas reserves and porosity data, combined with current exploration data, and through reasoning analysis using knowledge graphs, oil and gas exploration reports are automatically generated. These reports include oil and gas field potential assessments and future development recommendations, providing data support for decision makers. The knowledge graph is dynamically updated based on new data to ensure that the knowledge graph can reflect the latest progress in oil and gas exploration in real time and provide continuous support for subsequent decision-making.

8. A system for constructing an oil and gas geological knowledge graph based on triple association, characterized in that: include: The entity extraction module uses a large language model to extract entities from oil and gas geology texts, identifying and extracting entities from oil and gas geology texts; The source linking module uses a semantic similarity algorithm to associate the extracted and identified entities with authoritative documents to obtain the source of each entity; The term definition integration module combines professional dictionaries and textbooks to assign corresponding precise term definitions to each extracted and identified entity to achieve term definition integration; The knowledge graph construction module constructs triples of the extracted and identified entities, the sources of the entities, and the term definitions of the entities, and then constructs a knowledge graph in the field of oil and gas geology.

9. A computer-readable storage medium storing one or more programs, characterized in that: The one or more programs include instructions that, when executed by a computing device, cause the computing device to perform any one of the methods of claims 1 to 7 .

10. A computing device, characterized in that include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any one of the methods according to claims 1 to 7.

Images