Oil and gas field report generation method and system based on plug-in knowledge base and large model

Abstract

The invention discloses an oil and gas field report generation method and system based on a plug-in knowledge base and a large model, and the method comprises the steps: collecting a plurality of historical oil and gas field reports, converting the text information in the historical oil and gas field reports into structured data through the large model, and storing the structured data into a plug-in database; in response to the oil and gas field report generation request, user input information is obtained, and the user input information comprises a well name and a report type demand; determining an oil and gas field report document template based on the user input information; matching well attribute information of related wells through the plug-in knowledge base; and filling the oil and gas field report document template with the well attribute information according to a preset rule, and performing format rendering to generate a final oil and gas field report. According to the technical scheme of the invention, the problem that unstructured data cannot be efficiently processed and a high-quality oil and gas field report cannot be automatically generated in the prior art can be solved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and system for generating oil and gas field reports based on an external knowledge base and a large model. Background Art

[0002] In the development process of oil and gas fields, report generation is an indispensable and important link. However, oil and gas field data include deep detection of strata during geological exploration, various types of fine operation data during drilling operations, and continuous monitoring information during production operations. Not only are the sources of oil and gas field data extremely wide and the data scale is huge, but there is no regularity at all, which greatly increases the difficulty and complexity of data processing, making report writing extremely inefficient and consuming a lot of manpower and time costs.

[0003] Geological reports and exploration records are mostly in the form of natural language, which contain a lot of key information that is crucial to oil and gas field development decisions, such as formation characteristics, reservoir parameters, etc. However, when faced with this unstructured information, traditional data processing technology can only perform shallow analysis and cannot deeply explore its complex semantic associations and logical contexts. It is difficult to accurately identify the detailed information of key elements, and it is even more difficult to reasonably integrate this information into the report, resulting in serious damage to the quality of the report and failure to provide strong support for decision-making.

[0004] Therefore, there is an urgent need for a method that can efficiently process unstructured data and automatically generate high-quality oil and gas field reports. Summary of the invention

[0005] In view of this, the present invention proposes a method and system for generating oil and gas field reports based on an external knowledge base and a large model, which can efficiently process unstructured data and automatically generate high-quality oil and gas field reports.

[0006] To achieve the above object, the present invention provides the following technical solutions: A method for generating an oil and gas field report based on an external knowledge base and a large model, comprising: Collect various historical oil and gas field reports, convert text information in the historical oil and gas field reports into structured data through a large model, and store the structured data in an external database; In response to a request for generating an oil and gas field report, obtaining user input information, wherein the user input information includes a well name and a report type requirement; Determine an oil and gas field report document template based on the user input information; Match the well attribute information of related wells through the external knowledge base; The well attribute information is filled into the oil and gas field report document template according to a predetermined rule, and formatted and rendered to generate a final oil and gas field report.

[0007] On the basis of the above technical solution, the present invention can also be improved as follows: Furthermore, the method of converting text information in the historical oil and gas field report into structured data through the large model and storing the structured data in the external database includes: In the stored procedure, a matching index is built based on historical user input information.

[0008] Further, in response to the oil and gas field report generation request, obtaining user input information includes: The key points of the user input information are extracted through a large model to obtain key information.

[0009] Further, determining the oil and gas field report document template based on the user input information includes: Determine whether the user uploads the oil and gas field report document template by himself. If so, use the oil and gas field report document template uploaded by the user.

[0010] Furthermore, the determining of the oil and gas field report document template based on the user input information further includes: When the user does not upload the document template by himself, the matching value between the historical oil and gas field report in the plug-in database and the user input information is calculated, and the historical oil and gas field report with the largest matching value is selected as the reference report; Dividing the structured data in the reference report into soft data and hard data by using a large model; The soft data is retained, the hard data is marked, and an oil and gas field report document template is generated.

[0011] Furthermore, the calculating of the matching value between the historical oil and gas field report in the plug-in database and the user input information includes: The matching value is calculated by formula (1); Formula (1); In the formula, is the matching value, is the weight of the well name matching degree, is the weight of the report type matching degree, is the weight of the matching degree of the target time period, is the well name matching degree, To report type matching, The target time period matching degree.

[0012] Furthermore, the determining of the oil and gas field report document template based on the user input information further includes: A template library is constructed based on historical oil and gas field reports. When the user does not upload the oil and gas field report document template by himself, the corresponding oil and gas field report document template is matched from the template library based on the user input information.

[0013] An oil and gas field report generation system based on an external knowledge base and a large model, comprising: An external database construction module is used to collect various historical oil and gas field reports, convert text information in the historical oil and gas field reports into structured data through a large model, and store the structured data in the external database; An input information acquisition module, used to obtain user input information in response to an oil and gas field report generation request, wherein the user input information includes a well name and a report type requirement; A template determination module, used to determine an oil and gas field report document template based on the user input information; A matching module, used for matching well attribute information of related wells through an external knowledge base; The report generation module is used to fill the well attribute information into the oil and gas field report document template according to a predetermined rule, and perform format rendering to generate a final oil and gas field report.

[0014] An electronic device comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the method when executing the computer program.

[0015] A non-transitory computer-readable storage medium stores a computer program, which implements the steps of the method when executed by a processor.

[0016] The present invention has the following advantages: The oil and gas field report generation method based on the external knowledge base and the big model in the present invention realizes the effective integration of massive and messy oil and gas data by collecting various historical oil and gas field reports and converting them into structured data using the big model and storing them in the external database. It can quickly retrieve and call relevant data, avoids the tedious and time-consuming traditional methods in data query and organization, greatly improves data utilization efficiency, and lays a solid foundation for accurate report generation.

[0017] The oil and gas field report generation method based on the plug-in knowledge base and the large model in the present invention determines the document template according to the report type requirements input by the user, and then uses the plug-in knowledge base to match the well attribute information to fill in the template, so as to accurately generate an oil and gas field report that meets specific requirements. Whether it is an exploration report, a production report or other types, it can ensure that the content is highly targeted, meet the decision-making basis requirements in different scenarios, and reduce the risk of decision-making errors caused by inaccurate reports.

[0018] The oil and gas field report generation method based on the plug-in knowledge base and the large model in the present invention effectively solves the problems of non-standardized writing format and uneven content quality of traditional reports in the process of format rendering and report generation based on structured data and precise matching information. The report is professional, standardized, and well-organized, which facilitates information transmission and communication, and is conducive to improving the collaboration efficiency between the entire oil and gas field development team and related departments.

[0019] The oil and gas field report generation method based on the external knowledge base and the large model in the present invention can deeply mine the associations and trends behind the data by virtue of the powerful information processing capability of the large model and the rich data reserves of the external knowledge base. The generated high-quality reports can provide intelligent support for strategic planning, resource allocation, risk assessment and other decisions in the process of oil and gas field development, promote oil and gas field development to a more scientific, efficient and sustainable development path, and enhance the competitiveness and innovation ability of enterprises in the industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] For the purpose of illustration and not limitation, the present invention is now described in conjunction with the embodiments of the present invention and the accompanying drawings, in which: Figure 1 It is a flow chart of a method for generating an oil and gas field report based on an external knowledge base and a large model in an embodiment of the present invention; Figure 2 It is a schematic diagram of the main components of the oil and gas field report generation system based on the plug-in knowledge base and the large model in the embodiment of the present invention; Figure 3 This is a schematic diagram of the physical structure of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solution in the implementation of the present invention will be clearly and completely described below in conjunction with the drawings in the implementation of the present invention. Obviously, the described implementation is only a part of the implementation of the present invention, not all of the implementations. Based on the implementation of the present invention, all other implementations obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the specification of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so as to describe the embodiments of the present invention described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0024] Figure 1 FIG. 1 is a flow chart of a method for generating an oil and gas field report based on an external knowledge base and a large model in an embodiment of the present invention. Figure 1 As shown, the method for generating an oil and gas field report based on an external knowledge base and a large model provided by an embodiment of the present invention includes the following steps S101 to S105.

[0025] S101, collecting various historical oil and gas field reports, converting text information in the historical oil and gas field reports into structured data through a large model, and storing the structured data in an external database.

[0026] Specifically: First, collect historical oil and gas field reports from different oil and gas fields, different periods and different operation links, including geological exploration reports, drilling reports, completion reports, fracturing reports, production reports, etc.; then, with the help of advanced big model technology, such as pre-trained big models, conduct deep semantic understanding and analysis of text information in the report, accurately identify key contents such as stratigraphic structure description, reservoir parameters, operation process and results, and convert them into structured data forms, such as tables, data fields, etc., stored in a specially constructed plug-in database; in the conversion process, the big model can accurately distinguish professional terms, data values ​​and descriptive statements based on its powerful language understanding ability, so as to efficiently build a clear, easy to retrieve and call structured data system, so as to provide sufficient and orderly data resource reserves for subsequent report generation work.

[0027] During the storage process, a matching index is built based on historical user input information. First, all historical user input information is comprehensively and carefully sorted and classified. This information covers a variety of well name expressions, rich and diverse report type requirements, and other related specific requirements or keywords. Then, advanced data analysis algorithms and data mining techniques are used to deeply analyze the internal connections, frequency of occurrence, and distribution of importance of these historical user input information.

[0028] Based on the analysis results, we select those information elements that are representative, appear frequently and have a key impact on report generation, such as typical well names in specific areas, commonly used report type keywords, etc., and set them as the core basis for index construction; then, we use an efficient index creation algorithm to build a multi-level, multi-dimensional matching index system for these core information elements.

[0029] In this indexing system, not only can accurate and rapid positioning based on well names be achieved, but also the corresponding historical data resources can be quickly screened out according to the report type requirements; for example, when a user enters a specific well name or report type keyword, the system can locate the highly relevant structured data in the external database in a very short time through matching indexes, greatly improving the efficiency of data retrieval and call, providing strong technical support for the subsequent rapid generation of oil and gas field reports that meet user needs, and significantly optimizing the operating speed and accuracy of the entire oil and gas field report generation process.

[0030] S102, in response to the oil and gas field report generation request, obtaining user input information.

[0031] Specifically, the user input information includes the well name and report type requirements. When receiving a request to generate an oil and gas field report, the system will prompt the user to enter relevant information through a friendly user interface. The well name entered by the user will serve as a key identifier for accurately locating data related to a specific oil and gas well, and the report type requirement clarifies the purpose and focus of this report, such as an exploration report focusing on geological analysis, a production report focusing on production efficiency and output, or a special report for a specific operation link. Through this clear information input, the system can specifically determine the direction and scope for subsequent report generation steps to ensure that the generated report can closely fit the user's actual needs and application scenarios.

[0032] The key points of the user input information are extracted through a large model to obtain key information.

[0033] First, the user's input information is completely and accurately entered into a large model that has been fully trained and optimized specifically for the oil and gas field. With its powerful natural language processing capabilities and deep learning algorithms, this large model is able to conduct in-depth analysis and understanding of the input information word by word.

[0034] During the processing, the big model uses semantic analysis technology to accurately identify the core concepts, key terms and descriptive sentences with decisive significance in the information. For example, for well name information, the big model can quickly extract key elements such as the well number, the region where it is located, and the name of the oil and gas field to which it belongs, and mark them as important points. For report type requirements, the big model can accurately determine whether it is a geological exploration report, production and operation report, reserve assessment report or other specific types. At the same time, it can further analyze the specific aspects that should be covered in the report, such as the key focus areas of the stratigraphic structure in the geological exploration report and the key periods of production fluctuations in the production and operation report.

[0035] The large model comprehensively considers the semantic associations, grammatical structures and contextual contexts between words in the user input information, filters out redundant, ambiguous or irrelevant information content, and finally accurately extracts and refines the most critical and valuable information points for generating oil and gas field reports, laying a solid foundation for subsequently determining the report document template based on these key information, matching well attribute information and generating high-quality reports, thereby effectively improving the accuracy and efficiency of the entire oil and gas field report generation process.

[0036] S103, determining an oil and gas field report document template based on user input information.

[0037] Specifically, the first method is to determine whether the user uploads the oil and gas field report document template by himself, and if so, use the oil and gas field report document template uploaded by the user.

[0038] The second method: when the user does not upload the document template by himself, the matching value between the historical oil and gas field report in the plug-in database and the user input information is calculated, and the historical oil and gas field report with the largest matching value is selected as the reference report; Dividing the structured data in the reference report into soft data and hard data by using a large model; The soft data is retained, the hard data is marked, and an oil and gas field report document template is generated.

[0039] The matching value is calculated by formula (1); Formula (1); In the formula, is the matching value, is the weight of the well name matching degree, is the weight of the report type matching degree, is the weight of the matching degree of the target time period, is the well name matching degree, To report type matching, The target time period matching degree.

[0040] An example: User input information: Well name: A-001 well; Report type requirements: production operation report; Target period: January 2022 - December 2022; Historical oil and gas field reports in the plug-in database: Report 1 Well name: A-001 well; Report type: Production operation report; Time period: January 2022 - December 2022; Report 2 Well name: A-002 well; Report type: Production operation report; Time period: January 2022 - December 2022; Report 3 Well name: A-001 well; Report Type: Exploration Report; Time period: January 2022 - December 2022; Calculate the matching value: (Well name matching weight) = 0.4; (Report Type Match Weight) = 0.3; (target time period matching weight) = 0.3; For Report 1: =1 (well name matches exactly); =1 (report type exact match); =1 (target time period fully matches); ; For Report 2: =0 (well name does not match); =1 (report type exact match); =1 (target time period fully matches); ; For report 3: =1 (well name matches exactly); =0 (report type mismatch); =1 (target time period fully matches); ; Calculation shows that report 1 has the largest matching value ( ), so select Report 1 as the reference report.

[0041] Taking the old well reference report as an example, the report content is first parsed. After the analysis is completed, the content is stored in the database, and the spatial vector relationship is used to retrieve similar content; then, the content in the big model is judged, and the soft data (that is, data that does not need to be changed) is retained, and the hard data (that is, data that will change due to different reports) is handed over to the big model for tagging and processing, and then the document template is generated.

[0042] When extracting data through large model judgment, a few-shot prompt word construction method is adopted. Specifically, the oil and gas data in the report content is systematically analyzed to construct the required prompt words (Prompt); for each input sentence, a corresponding prompt is constructed. For a given input sentence X, Prompt (X) is used to represent the prompt constructed for it. The construction of the prompt word consists of three parts: task description, a small number of sample demonstrations, and input sentences; The following are some examples: Task description: As a good linguist, you need to mark the oil and gas reservoir noun entity and data type in the given sentence; A few sample demonstrations: Example 1: Input: The first drilling was carried out using a Φ311.1mm drill bit, and the initial well depth was 516.000m.

[0043] Output: The first drilling was carried out using the 〈〈Φ311.1mm〉〉 drill bit, and the first well depth was ##〈〈516.000m〉〉.

[0044] Example 2: Input: Well A is a development well of YC Petroleum Oil and Gas Exploration Company, and the actual completed well depth is 3235.00m.

[0045] Output: Well A is a development well of YC Petroleum Oil and Gas Exploration Company, with the actual completed well depth of ##〈〈3235.00m〉〉.

[0046] Example 3: Input: The maximum dogleg angle of the vertical section of this well is 0.9° / 30m.

[0047] Output: The maximum dogleg angle of the vertical section of this well is ##〈〈0.9° / 30m〉〉.

[0048] Input sentence: In wellbore trajectory control, the appropriate wellbore curvature should be controlled between 3° / 30m - 8° / 30m.

[0049] Output: In the control of ##wellbore trajectory##, the appropriate ##wellbore curvature## should be controlled within 〈〈3° / 30m- 8° / 30m〉〉.

[0050] In this example, the “〈〈” and “〉〉” symbols mark the data entity of the wellbore curvature range “3° / 30m - 8° / 30m”.

[0051] The “##” symbol marks the two data types “well trajectory” and “well curvature”.

[0052] The third method is to build a template library based on historical oil and gas field reports. When the user does not upload the oil and gas field report document template by himself, the corresponding oil and gas field report document template is matched from the template library based on the user input information.

[0053] S104, matching well attribute information of related wells through an external knowledge base.

[0054] Specifically, the plug-in knowledge base integrates a large amount of professional knowledge, industry standards, and past successful case data in the oil and gas field. After determining the specific well name, the system uses efficient retrieval and matching algorithms to comprehensively search for well attribute information related to the well in the plug-in knowledge base. These well attribute information covers the well's geographical location coordinates, formation depth range, reservoir characteristics (such as permeability, porosity, etc.), surrounding geological structure characteristics, previous production or exploration history data and other aspects. By matching and correlating with the rich data in the knowledge base, the unique attributes and potential laws of the well in the entire oil and gas field development system can be excavated, providing key data support for accurately and comprehensively filling in the report content, so that the report is not limited to the presentation of surface data, but can also deeply analyze the intrinsic characteristics and development potential of the well.

[0055] S105, filling the well attribute information into the oil and gas field report document template according to the predetermined rules, and performing format rendering to generate the final oil and gas field report.

[0056] Specifically, after obtaining the matching well attribute information, according to the pre-set filling rules, this information is accurately filled into the corresponding position in the selected oil and gas field report document template. For example, the geographical location information of the well is filled into the basic information part of the report, the reservoir characteristic data is filled into the data table of the geological analysis chapter, and the production history data is displayed in the production operation section in the form of charts. After the filling is completed, the format rendering operation is performed. According to industry specifications and aesthetic requirements, the text font, font size, and paragraph format in the report are uniformly adjusted, and the data charts are optimized and beautified to ensure that the overall layout of the report is reasonable, the visual effect is good, and the reading experience is smooth. Finally, an oil and gas field report with detailed content, accurate data, standardized format and strong professionalism is generated, which can be directly used for decision-making reference, technical exchange, and results reporting in the process of oil and gas field development. It effectively improves the efficiency and quality of oil and gas field report generation and promotes the intelligent and standardized process of oil and gas field development.

[0057] Figure 2 FIG. 1 is a schematic diagram of the main components of the oil and gas field report generation system based on the plug-in knowledge base and the large model in the embodiment of the present invention. Figure 2 As shown, the oil and gas field report generation system 1 based on the external knowledge base and the large model provided by the embodiment of the present invention includes an external database construction module 10, an input information acquisition module 20, a template determination module 30, a matching module 40, and a report generation module 50.

[0058] The external database construction module 10 is used to collect various historical oil and gas field reports, convert the text information in the historical oil and gas field reports into structured data through a large model, and store the structured data in the external database; The input information acquisition module 20 is used to respond to the oil and gas field report generation request and acquire user input information, wherein the user input information includes the well name and the report type requirement; The template determination module 30 is used to determine the oil and gas field report document template based on the above user input information; The matching module 40 is used to match the well attribute information of the relevant wells through the external knowledge base; The report generation module 50 is used to fill the well attribute information into the oil and gas field report document template according to a predetermined rule, and perform format rendering to generate a final oil and gas field report.

[0059] Figure 3 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, the electronic device 60 includes: a processor 601 (processor), a memory 602 (memory) and a bus 603; The processor 601 and the memory 602 communicate with each other via the bus 603; The processor 601 is used to call the program instructions in the memory 602 to execute the methods provided by the above-mentioned method embodiments, for example, including: collecting a variety of historical oil and gas field reports, converting the text information in the historical oil and gas field reports into structured data through a large model, and storing the structured data in an external database; in response to an oil and gas field report generation request, obtaining user input information, wherein the user input information includes a well name and a report type requirement; determining an oil and gas field report document template based on the user input information; matching the well attribute information of related wells through an external knowledge base; filling the well attribute information into the oil and gas field report document template according to predetermined rules, and performing format rendering to generate a final oil and gas field report.

[0060] The present embodiment provides a non-transitory computer-readable storage medium, which stores computer instructions. The computer instructions enable a computer to execute the methods provided by the above-mentioned method embodiments, for example, including: collecting a variety of historical oil and gas field reports, converting the text information in the historical oil and gas field reports into structured data through a large model, and storing the structured data in an external database; in response to an oil and gas field report generation request, obtaining user input information, wherein the user input information includes a well name and a report type requirement; determining an oil and gas field report document template based on the user input information; matching well attribute information of related wells through an external knowledge base; filling the well attribute information into the oil and gas field report document template according to predetermined rules, and performing format rendering to generate a final oil and gas field report.

[0061] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various storage media that can store program codes.

[0062] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for generating oil and gas field reports based on an external knowledge base and a large model, characterized in that: include: Collect various historical oil and gas field reports, convert text information in the historical oil and gas field reports into structured data through a large model, and store the structured data in an external database; In response to a request for generating an oil and gas field report, obtaining user input information, wherein the user input information includes a well name and a report type requirement; Determine an oil and gas field report document template based on the user input information; Match the well attribute information of related wells through the external knowledge base; The well attribute information is filled into the oil and gas field report document template according to a predetermined rule, and formatted and rendered to generate a final oil and gas field report.

2. The method for generating oil and gas field reports based on an external knowledge base and a large model according to claim 1, characterized in that: The method of converting text information in the historical oil and gas field report into structured data by using a large model, and storing the structured data in an external database, includes: In the stored procedure, a matching index is built based on historical user input information.

3. The method for generating oil and gas field reports based on an external knowledge base and a large model according to claim 1 is characterized in that: The step of obtaining user input information in response to the oil and gas field report generation request includes: The key points of the user input information are extracted through a large model to obtain key information.

4. The method for generating oil and gas field reports based on an external knowledge base and a large model according to claim 1, characterized in that: The step of determining the oil and gas field report document template based on the user input information includes: Determine whether the user uploads the oil and gas field report document template by himself. If so, use the oil and gas field report document template uploaded by the user.

5. The method for generating oil and gas field reports based on an external knowledge base and a large model according to claim 1 is characterized in that: The step of determining the oil and gas field report document template based on the user input information further includes: When the user does not upload the document template by himself, the matching value between the historical oil and gas field report in the plug-in database and the user input information is calculated, and the historical oil and gas field report with the largest matching value is selected as the reference report; Dividing the structured data in the reference report into soft data and hard data by using a large model; The soft data is retained, the hard data is marked, and an oil and gas field report document template is generated.

6. The method for generating oil and gas field reports based on an external knowledge base and a large model according to claim 5 is characterized in that: The calculating of the matching value between the historical oil and gas field report in the plug-in database and the user input information includes: The matching value is calculated by formula (1); Formula (1): In the formula, is the matching value, is the weight of the well name matching degree, is the weight of the report type matching degree, is the weight of the matching degree of the target time period, is the well name matching degree, To report type matching, The target time period matching degree.

7. The method for generating oil and gas field reports based on an external knowledge base and a large model according to claim 1 is characterized in that: The step of determining the oil and gas field report document template based on the user input information further includes: A template library is constructed based on historical oil and gas field reports. When the user does not upload the oil and gas field report document template by himself, the corresponding oil and gas field report document template is matched from the template library based on the user input information.

8. A system for generating oil and gas field reports based on an external knowledge base and a large model, characterized in that: include: An external database construction module is used to collect various historical oil and gas field reports, convert text information in the historical oil and gas field reports into structured data through a large model, and store the structured data in the external database; An input information acquisition module, used to obtain user input information in response to an oil and gas field report generation request, wherein the user input information includes a well name and a report type requirement; A template determination module, used to determine an oil and gas field report document template based on the user input information; A matching module, used for matching well attribute information of related wells through an external knowledge base; The report generation module is used to fill the well attribute information into the oil and gas field report document template according to a predetermined rule, and perform format rendering to generate a final oil and gas field report.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A non-transitory computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images