Oil and gas pipeline standard system body completion method and system, medium and electronic equipment

Abstract

The invention relates to the technical field of oil and gas pipelines, and discloses an oil and gas pipeline standard system body completion method and system, a medium and electronic equipment. The method comprises the steps of obtaining text data of ontology knowledge to be extracted, and constructing a task prompt comprising a task instruction, a related case and the text data according to the text data; the task prompt is input into a large language model, and the large language model carries out ontology knowledge extraction on the text data based on the task instruction and the related case; and if the extracted ontology knowledge is new ontology knowledge, adding the new ontology knowledge into the existing oil and gas pipeline ontology library to update the oil and gas pipeline standard system. According to the method, a large language model is used as a domain expert to extract ontology knowledge from data, an existing oil and gas pipeline body is supplemented and perfected, and an oil and gas pipeline standard system is constructed and updated; management and maintenance of the oil and gas pipeline body are efficiently and economically achieved by means of automation.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas pipelines, and in particular to a method, system, medium and electronic equipment for completing an oil and gas pipeline standard system. Background Art

[0002] In the management of oil and gas pipelines, it is crucial to build a complete and accurate pipeline ontology. However, in actual management, due to various reasons, there are often problems with missing or incomplete ontology, which will affect the operation safety and maintenance efficiency of the pipeline.

[0003] Most of the existing pipeline ontology completion methods are based on manual filling. However, due to the complexity of pipeline concepts, including many technologies and complex processes, it is knowledge-intensive, with a lot of knowledge, miscellaneous, and highly professional. Asking staff to build a domain ontology is not only expensive, but also has the risk of missing a lot of ontology knowledge, low efficiency and prone to errors. The existing automation technology is based on the basic ontology built by domain experts, and extracts ontology knowledge from the collected data by formulating relevant rules, and then expands the original ontology. However, the formulated rules cannot cover all ontology knowledge, and the rule-based automation technology has the problem of error accumulation and propagation, which makes the accuracy of the extracted knowledge unable to be guaranteed. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method, system, medium and electronic equipment for completing the oil and gas pipeline standard system in view of the problems existing in the prior art.

[0005] In a first aspect, the present invention provides a method for completing an oil and gas pipeline standard system, comprising:

[0006] Obtain text data of the ontology knowledge to be extracted, and construct task prompts including task instructions, related cases and text data according to the text data;

[0007] The task prompts are input into the large language model, and the large speech model extracts ontological knowledge from the text data based on the task instructions and related cases;

[0008] If the extracted ontology knowledge is new ontology knowledge, the new ontology knowledge will be added to the existing oil and gas pipeline ontology library to update the oil and gas pipeline standard system.

[0009] In a second aspect, the present invention provides an oil and gas pipeline standard system ontology completion system, which is used to implement the oil and gas pipeline standard system ontology completion method provided by the above technical solution, and the system includes:

[0010] A task prompt construction module is used to obtain text data of ontology knowledge to be extracted, and to construct a task prompt including task instructions, related cases and text data according to the text data;

[0011] The ontology knowledge extraction module is used to input the task prompts into the large language model, and the large speech model extracts ontology knowledge from text data based on task instructions and related cases;

[0012] The standard system update module is used to add the new ontology knowledge to the existing oil and gas pipeline ontology library if the extracted ontology knowledge is new ontology knowledge, so as to update the oil and gas pipeline standard system.

[0013] In a third aspect, the present invention provides a computer-readable storage medium, comprising instructions, which, when executed on a computer, enable the computer to execute the method for completing the oil and gas pipeline standard system ontology as provided in the above technical solution.

[0014] In a fourth aspect, the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for completing the oil and gas pipeline standard system ontology as provided in the above technical solution is implemented.

[0015] In a fifth aspect, the present application also provides a computer program product, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the oil and gas pipeline standard system ontology completion method provided by the above solution.

[0016] The beneficial effects of the present invention are: constructing task prompts including task instructions, relevant cases and text data, using a large language model as a domain expert to extract ontology knowledge from the text data of the task prompts, supplementing and improving the existing oil and gas pipeline ontology, and constructing an updated oil and gas pipeline standard system; using automated means to efficiently and economically realize the management and maintenance of the oil and gas pipeline ontology.

[0017] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flowchart of a method for completing an oil and gas pipeline standard system ontology is shown as an exemplary embodiment of the present application;

[0019] Figure 2 for Figure 1 A flowchart of step S1 in the illustrated embodiment in an exemplary embodiment;

[0020] Figure 3 A flowchart of a method for completing an oil and gas pipeline standard system ontology is shown as another exemplary embodiment of the present application;

[0021] Figure 4 A block diagram of an oil and gas pipeline standard system ontology completion system shown as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0022] The following describes the embodiments of the present disclosure through specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0023] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0024] In oil and gas pipeline management, it is crucial to build a complete and accurate pipeline ontology. However, in actual management, due to various reasons, there are often problems with missing or incomplete ontology, which will affect the operational safety and maintenance efficiency of the pipeline. Existing pipeline ontology completion methods are mostly based on manual filling, which is inefficient and prone to errors.

[0025] The embodiment of the present invention provides an oil and gas pipeline standard system ontology completion method, system, storage medium and computing device to solve the problem of pipeline ontology missing and incompleteness in the prior art and improve the accuracy and efficiency of oil and gas pipeline management. At the same time, the technology is also suitable for mining newly emerged entities and relationships to expand the pipeline ontology and maintain the advancement of the ontology.

[0026] The solution provided in the embodiment of the present invention can be executed by any electronic device, for example, a terminal device, or jointly executed by a terminal device and a server. The server can be an independent server, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, etc., and is not limited here.

[0027] Figure 1 The following is a flow chart of a method for completing the oil and gas pipeline standard system as an exemplary embodiment of the present application. Figure 1 As shown, in an exemplary embodiment, the oil and gas pipeline standard system ontology completion method may include steps S101 to S103, which are described in detail as follows:

[0028] S101, obtaining text data of ontology knowledge to be extracted, and constructing task prompts including task instructions, related cases and text data according to the text data.

[0029] It should be noted that ontology is a form of knowledge representation, which is used to define and describe concepts and their relationships in a field. In the field of oil and gas pipelines, building and maintaining high-quality ontology is conducive to the systematic management of knowledge.

[0030] The embodiment of the present invention establishes a task prompt including task instructions, relevant cases and text data (i.e., task prompt = task instruction + relevant case + text data) for the text data of the ontology knowledge to be extracted, guides the model to produce the expected output by constructing clear and instructive prompts; provides example input and output to help the model understand the task requirements; and continuously adjusts and optimizes the prompts according to the output effect of the model to improve the model performance, thereby optimizing the output of the large language model.

[0031] S102, inputting the task prompt into the large language model, and the large language model extracts ontology knowledge from the text data based on the task instructions and related cases.

[0032] It should be noted that large language models (LLMs, such as GPT-4) are natural language processing (NLP) models based on deep learning, which have powerful language generation and understanding capabilities. These models have mastered rich language knowledge and contextual understanding capabilities by training on large-scale text data. Large language models can be used for a variety of tasks, including text generation, translation, question answering, and text summarization.

[0033] In the embodiment of the present invention, the constructed task prompt is input into a closed-source large language model (such as GPT-4) or a fine-tuned open-source large language model (fine-tuned using oil and gas pipeline domain data). The large language model will act as a domain expert to identify and summarize the given text data and output the extracted ontology knowledge according to the task requirements.

[0034] It should be noted that instruction fine-tuning is a specialized model training technique that optimizes the performance of a large language model on a specific task by providing it with explicit instructions or task descriptions. Instruction fine-tuning usually involves the following steps:

[0035] Task definition: clarify the task objectives and requirements, such as text classification, entity recognition, etc.

[0036] Instruction design: Design specific instruction templates to guide the model to understand and execute tasks.

[0037] Fine-tuning training: Using predefined instructions and task examples, the model is further trained to improve its performance on a specific task.

[0038] S103, if the extracted ontology knowledge is new ontology knowledge, the new ontology knowledge is added to the existing oil and gas pipeline ontology library to update the oil and gas pipeline standard system.

[0039] The embodiment of the present invention matches the ontology knowledge extracted by the large language model with the existing ontology knowledge, and if new ontology knowledge is extracted, it is added to the existing pipeline ontology.

[0040] In the era of large language models, language models can store a large amount of domain knowledge. As the model size increases, its domain expertise is no less than that of domain experts. In addition, the development of prompt engineering and instruction learning technology has greatly enhanced the Few-Shot (Few-shot learning: few sample learning) capabilities of general large models (such as GPT-4), which can efficiently complete domain-specific tasks. It is a more effective and economical method to regard language models as domain experts and build domain ontology.

[0041] Therefore, based on the existing oil and gas pipeline ontology (regarded as a domain standard and accurate), the embodiment of the present invention studies how to use a large language model as a domain expert to complete the knowledge of the ontology, aiming at the possible lack of ontology knowledge in the ontology. At the same time, the technology is used to supplement the emerging ontology knowledge into the existing pipeline ontology to maintain the advancement of the pipeline ontology, so as to better perform downstream tasks in the domain.

[0042] The embodiment of the present invention uses a large language model as a domain expert to extract ontology knowledge from data, supplement and improve the existing oil and gas pipeline ontology, and build an updated oil and gas pipeline standard system; it uses automated means to efficiently and economically achieve the management and maintenance of the oil and gas pipeline ontology. That is, the embodiment of the present invention has the advantages of high automation, high data processing efficiency, dynamic data update, high efficiency and economy, strong flexibility, accuracy and intelligence.

[0043] It should be noted that, before extracting ontology knowledge, the embodiment of the present invention needs to pre-build a case library, and the specific process is as follows:

[0044] 1. Data collection. Obtain multi-source text data samples in the field of oil and gas pipelines. In the embodiments of the present invention, text data from multiple sources in the field of oil and gas pipelines can be collected, including but not limited to data collected during ontology construction, such as the latest system business data, journal and literature data, pipeline field-related data in web pages, etc.

[0045] 2. Data preprocessing: Preprocess the text data samples. In the embodiment of the present invention, data cleaning can be used to filter out irrelevant information such as irrelevant characters and symbols, and filter out text data that is irrelevant to the field.

[0046] 3. Data annotation. A preset number of text data samples are randomly selected for annotation, and the text data samples and the corresponding annotation results are stored as cases in the case library. In the embodiment of the present invention, the case library provides a wealth of cases for constructing task prompts.

[0047] For example, the example text data sample is "The diameter of the pipeline is 100 mm and it transports natural gas." Among them, the label "pipeline" is an equipment type entity, and the label "natural gas" is an energy type entity.

[0048] By constructing a case library, the embodiment of the present invention can provide rich case support when constructing task prompts, enhance the task execution effect of the large language model, and ensure that the extracted ontology knowledge is more in line with the actual needs and application scenarios of the field.

[0049] It should be noted that, before extracting the knowledge ontology, the embodiment of the present invention needs to establish a task instruction library in advance, and the specific process of constructing the task instruction library is as follows: obtaining the existing ontology knowledge in the existing oil and gas pipeline ontology library; analyzing the existing ontology knowledge and its structure to obtain the analysis results; and designing task instructions for activating the large language model to perform the ontology knowledge extraction task based on the analysis results.

[0050] The task instructions are task paradigm templates designed for experts, such as “Assuming that you are a professional engineer in the oil and gas pipeline field, please annotate the given data and extract the entities and relationships contained in the text.

[0051] The embodiment of the present invention summarizes the instruction template based on the existing oil and gas pipeline ontology and its structure as the task instruction for activating the large language model to process ontology extraction. A task may have multiple instruction templates. When constructing a task prompt, select the task instruction with the best effect.

[0052] See also Figure 2 , Figure 2 for Figure 1 The step S101 in the embodiment shown is a flow chart in an exemplary embodiment. Figure 2 As shown, step S101 may specifically include steps S201 to S204. The task prompt is obtained through the above steps, which are described in detail as follows:

[0053] S201, determining the task type of text data and the entities included in the text data. Specifically, the task type and the included entities may be determined by a named entity recognition algorithm.

[0054] S202, selecting a matching task instruction from a task instruction library based on the task type, wherein the task instruction in the task instruction library is used to activate the large language model to perform the ontology knowledge extraction task.

[0055] S203, selecting matching related cases from the case library based on the entities contained in the text data, wherein each case in the case library includes a text data sample and its annotation results.

[0056] S204, constructing a task prompt based on the task instruction, related cases and text data.

[0057] The following describes in detail the process of constructing a task prompt using a specific example.

[0058] Assume that the text data of the ontology knowledge to be extracted is "The pipeline was maintained in 2019 to ensure safety". Then the task type included in the text data is "entity extraction task", and the entity included is "pipeline".

[0059] Assume that the task instruction matched to the text data from the task instruction library is: Assuming that you are a professional engineer in the oil and gas pipeline field, please annotate the given data and extract the entities and relationships contained in the text.

[0060] Assume that the case matched by the text data from the case library is: input: 'the diameter of the pipeline is 100 mm, transporting natural gas', output: 'pipeline'-equipment entity, 'natural gas-energy entity'; xxx (indicates multiple cases).

[0061] Based on the above assumptions, the task prompt corresponding to the text data is: Assuming that you are a professional engineer in the field of oil and gas pipelines, please annotate the given data and extract the entities and relationships contained in the text. For example, the input is: 'The diameter of the pipeline is 100 mm and it transports natural gas', and the output is: 'Pipeline'-equipment entity, 'Natural gas-energy entity'; xxx (multiple cases). Now, please perform the entity extraction task, the input is: 'The pipeline was maintained in 2019 to ensure safety', and the output is: ".

[0062] In an embodiment of the present invention, for the text data of the ontology to be extracted, the task type and the entities included in the text data are preliminarily determined, the most relevant cases are retrieved from the case library according to the entities, and the task instructions are matched from the task instruction library according to the task type. Then, the task instructions, relevant cases and text data together constitute the task prompts of the large language model, thereby better optimizing the output of the large language model.

[0063] Optionally, in an exemplary embodiment of the present invention, Figure 1 After the ontology knowledge is extracted through step S2, the illustrated embodiment further includes: adding the current text data and the extracted ontology knowledge as new cases to the case library to automatically update the case library.

[0064] Figure 3 This is a flow chart of another exemplary embodiment of the present application showing a method for completing the oil and gas pipeline standard system. Figure 3 This embodiment of the present invention is described in detail.

[0065] S301, obtaining text data of the field where the oil and gas pipeline is located;

[0066] S302, preprocessing the acquired text data (including preprocessing methods such as data cleaning), and randomly selecting a number of text data for expression to construct a case library;

[0067] S303, determining the task type for the text data of the ontology knowledge to be extracted, and selecting a task instruction from an instruction template according to the task type;

[0068] S304, for the text data from which ontology knowledge is to be extracted, similar cases are retrieved from the case library, and the similar cases are combined with the task instructions selected in S303 to form a task prompt of the large voice model;

[0069] S305, inputting the task prompt into the large speech model, and the large speech model, as a domain expert, extracts the ontology knowledge contained in the text data;

[0070] S306, adding the text data and the corresponding extracted ontology knowledge as new cases to the case library;

[0071] S307, filter out existing ontology knowledge and identify emerging ontologies in the field;

[0072] S308, updating the emerging ontology into the existing ontology library;

[0073] S309, output the oil and gas pipeline body.

[0074] Compared with the prior art, the oil and gas pipeline standard system ontology completion method provided by the embodiment of the present invention has the following advantages:

[0075] 1) High degree of automation: Traditional ontology construction and completion methods often rely on manual participation, which is time-consuming and labor-intensive. However, the embodiments of the present invention use a large language model as a domain expert to achieve automated ontology knowledge extraction and completion, greatly reducing human input and improving work efficiency.

[0076] 2) High data processing efficiency: Through preprocessing and filtering steps, the present invention can effectively process a large amount of text data, eliminate irrelevant information, ensure the quality of input data, and thus improve the accuracy and efficiency of ontology knowledge extraction.

[0077] 3) Dynamic update. The present invention not only relies on the data collected when constructing the ontology, but also includes the latest system business data, journal literature data, web page data, etc., to achieve dynamic update and supplement of ontology knowledge, ensuring that the ontology always reflects the latest knowledge and development in the field.

[0078] 4) Efficient and economical: Using large language models to complete and improve the ontology can significantly reduce labor costs and time costs and improve economic benefits. In addition, the automated processing method based on large language models can respond to knowledge updates and changes more quickly and maintain the timeliness and accuracy of the ontology.

[0079] 5) Strong flexibility. The present invention supports the use of closed-source large language models (such as GPT-4) or fine-tuned open-source large language models. It has strong flexibility and adaptability and can select the most suitable model for extracting and completing ontology knowledge according to actual needs.

[0080] 6) Accuracy and intelligence. By learning a large amount of domain-related data, the large language model has a high level of semantic understanding and reasoning capabilities. It can more accurately extract and summarize the ontology knowledge in the text and improve the intelligence level of ontology construction and completion.

[0081] 7) Case library support. By building a case library, the present invention can provide relevant case support when task prompts are given, enhance the task execution effect of the large language model, and ensure that the extracted ontology knowledge is more in line with the actual needs and application scenarios of the field.

[0082] Figure 4The following is a block diagram of an oil and gas pipeline standard system ontology completion system shown in an exemplary embodiment of the present application. Figure 4 As shown, in an exemplary embodiment, the oil and gas pipeline standard system ontology completion system may include a task prompt construction module, an ontology knowledge extraction module and a standard system update module, which are described in detail as follows:

[0083] A task prompt construction module is used to obtain text data of ontology knowledge to be extracted, and to construct a task prompt including task instructions, related cases and text data according to the text data;

[0084] The ontology knowledge extraction module is used to input the task prompts into the large language model, and the large speech model extracts ontology knowledge from text data based on task instructions and related cases;

[0085] The standard system update module is used to add the new ontology knowledge to the existing oil and gas pipeline ontology library if the extracted ontology knowledge is new ontology knowledge, so as to update the oil and gas pipeline standard system.

[0086] An embodiment of the present invention further provides a computer-readable storage medium, comprising instructions, which, when executed on a computer, enable the computer to execute the method for completing the oil and gas pipeline standard system ontology as provided in any of the above embodiments.

[0087] An embodiment of the present invention further provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for completing the oil and gas pipeline standard system ontology as provided in any of the above embodiments is implemented.

[0088] The embodiment of the present invention also provides a computer program product, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the oil and gas pipeline standard system ontology completion method provided in the above various optional embodiments.

[0089] The oil and gas pipeline field standard system ontology completion method and related equipment provided by the embodiment of the present invention are designed to use a large language model as a domain expert to extract ontology knowledge from data to supplement and improve the existing ontology. By means of automation, the management and maintenance of the oil and gas pipeline ontology is realized efficiently and economically.

[0090] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0091] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0092] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0093] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0094] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0095] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for completing the oil and gas pipeline standard system, characterized in that: include: Acquire text data of ontology knowledge to be extracted, and construct task prompts including task instructions, related cases and text data according to the text data; Inputting the task prompt into a large language model, the large language model extracting ontology knowledge from the text data based on the task instruction and related cases; If the extracted ontology knowledge is new ontology knowledge, the new ontology knowledge is added to the existing oil and gas pipeline ontology library to update the oil and gas pipeline standard system.

2. The method according to claim 1, characterized in that The step of constructing a task prompt including a task instruction, related cases and text data according to the text data includes: Determining a task type of the text data and entities included in the text data; Selecting a matching task instruction from a task instruction library based on the task type; wherein the task instruction in the task instruction library is used to activate a large language model to perform an ontology knowledge extraction task; Selecting matching related cases from a case library based on entities contained in the text data; wherein each case in the case library includes a text data sample and its annotation results; A task prompt is constructed based on the task instruction, the related cases and the text data.

3. The method according to claim 2, characterized in that The construction process of the case library includes the following contents: Acquire multi-source text data samples in the field of oil and gas pipelines, and preprocess the text data samples; A preset number of the text data samples are randomly selected for annotation, and the text data samples and the corresponding annotation results are stored as cases in a case library.

4. The method according to claim 3, characterized in that The preprocessing of the text data sample comprises: The text data samples are preprocessed by data cleaning.

5. The method according to claim 2, characterized in that: The construction process of the task instruction library includes the following contents: Acquire existing ontology knowledge in the existing oil and gas pipeline ontology library; Analyze the existing ontology knowledge and its structure to obtain analysis results; According to the analysis results, task instructions for activating the large language model to perform the ontology knowledge extraction task are designed.

6. The method according to any one of claims 2 to 5, characterized in that: After extracting ontology knowledge, it also includes: The current text data and the extracted ontology knowledge are added as new cases to the case library to update the case library.

7. The method according to claim 6, characterized in that The large speech model adopts a closed-source large language model or a fine-tuned open-source large language model.

8. An oil and gas pipeline standard system body completion system, characterized in that: The system is used to implement the method for completing the oil and gas pipeline standard system as described in any one of claims 1 to 7, and comprises: A task prompt construction module is used to obtain text data of the ontology knowledge to be extracted, and construct a task prompt including task instructions, related cases and text data according to the text data; An ontology knowledge extraction module, used for inputting the task prompt into a large language model, and the large language model extracts ontology knowledge from the text data based on the task instruction and related cases; The standard system updating module is used to add the new ontology knowledge to the existing oil and gas pipeline ontology library if the extracted ontology knowledge is new ontology knowledge, so as to update the oil and gas pipeline standard system.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a computer, the computer is caused to execute the method for completing the oil and gas pipeline standard system ontology as described in any one of claims 1 to 7.

10. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for completing the oil and gas pipeline standard system ontology as described in any one of claims 1 to 7 is implemented.

Images