Oil and gas knowledge graph construction method and device, electronic equipment and storage medium

[0056] In order to make the purpose, technical solutions, and advantages of this application clearer, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the application, and not used to limit the application.

[0057] The method for constructing the oil and gas knowledge map provided in this application can be applied to figure 1 In the application environment shown. The user enters the entity nodes of the oil and gas knowledge graph to be constructed, the entity relationship corresponding to the entity nodes, oil and gas production data, and the preset oil and gas production nodes to the data processing terminal, and the data processing terminal obtains the entity nodes and entity nodes of the oil and gas knowledge graph to be constructed Corresponding entity relationships, oil and gas production data, and preset oil and gas production nodes; extract node data from oil and gas production data based on oil and gas production nodes to obtain oil and gas production node data; fill oil and gas production node data to the corresponding entity nodes to obtain oil and gas entities Node data: Based on the oil and gas entity node data and entity relationships, the oil and gas knowledge graph is obtained. Among them, the data processing terminal can be, but not limited to, various personal computers, notebook computers, smart phones, and tablet computers.

[0058] In one embodiment, such as figure 2 As shown, a method for constructing an oil and gas knowledge map is provided, and the method is applied to figure 1 Take the data processing terminal in as an example for description, including the following steps:

[0059] Step 202: Obtain entity nodes of the oil and gas knowledge graph to be constructed, entity relationships corresponding to the entity nodes, oil and gas production data, and preset oil and gas production nodes.

[0060] Knowledge graph refers to a structured semantic knowledge base, which is used to describe entities and relationships between entities. Its basic unit is entity-relation-entity triples, and entities are connected to each other through relationships. A bottom-up approach can be used to construct a knowledge map, including information extraction, knowledge fusion and knowledge processing. Among them, information extraction refers to extracting entities, attributes and relationships between entities from different data sources, and forming knowledge expression on this basis. Knowledge fusion refers to the integration of acquired knowledge to eliminate contradictions or ambiguities, such as certain entities corresponding to multiple expressions. Knowledge processing refers to the quality assessment of the knowledge that has been processed by knowledge fusion, and the qualified parts are added to the knowledge base to ensure the quality of the knowledge base.

[0061] The oil and gas knowledge map refers to a knowledge map based on oil and gas production data. The entity refers to something that is distinguishable and independent. The entity node can be a basin, oil and gas field, well, core, etc., more specifically, such as Sichuan Basin, Xingshugang Oilfield, Well Waiji 1, Jurassic cores of Well Waiji 1, etc. Oil and gas knowledge data includes oil and gas static data and oil and gas dynamic data. Static data refers to oil and gas knowledge data that does not change over time, such as the area of ​​the basin, the production horizon of the oil field, the reserves of the oil field, the author, unit, and research of the oil and gas knowledge achievement Subject etc. Oil and gas dynamic data refers to oil and gas production data that changes every year, every month, and every day. Oil and gas production data includes annual oil production, annual water production, annual gas production, annual water cut, annual decline rate, and the number of wells opened per year. And other dynamic data.

[0062] Oil and gas production node refers to the ontology library constructed according to the actual production needs of the oil field, such as oil fields, blocks, oil reservoirs, small layers, single wells, etc. as nodes, each node includes annual dynamics, monthly dynamics, daily dynamics, etc. Nodes, each node includes multiple attributes, such as dynamic attributes such as annual oil production, annual water production, annual gas production, annual water content, and annual decline rate. Specifically, the ontology database of the oil and gas knowledge map can be as image 3 Shown.

[0063] Step 204: Perform node data extraction on the oil and gas production data based on the oil and gas production node to obtain oil and gas production node data.

[0064] Oil and gas production node data refers to data corresponding to oil and gas production nodes. For example, oil field, annual oil production, cumulative oil production, annual fluid production, and cumulative fluid production are used as oil and gas production nodes, and 1979 is used as the time node. Specifically, Liaohe Huanxi In 1979, Ling Oilfield produced 1,371,200 tons of oil, 1.618 million tons of oil, 1,258,700 tons of liquid, and 1,258,700 tons of liquid. It can be seen that the oil and gas production node data includes the Liaohe Huanxiling Oilfield, the annual oil production data is 1,371,200 tons, the cumulative oil production data is 1.618 million tons, the annual fluid production data is 1,258,700 tons, and the cumulative fluid production data is 1,258,700. Ton.

[0065] Step 206: Fill the oil and gas production node data to the corresponding physical node to obtain the oil and gas physical node data.

[0066] The oil and gas entity node data includes the entity node and the data corresponding to the entity node. The oil and gas knowledge graph to be constructed is only the entity node, and the data corresponding to each entity node is blank. Fill the obtained oil and gas production node data to the corresponding entity node to obtain the oil and gas entity node data.

[0067] Step 208: Obtain an oil and gas knowledge map based on the oil and gas entity node data and entity relationships.

[0068] The knowledge graph is a graph-based data structure composed of nodes and edges. The nodes are entities, represented by a globally unique identifier, and the relationship is used to connect two nodes. The knowledge graph connects all different types of information together to obtain a relational network, which provides the ability to analyze problems from a relational perspective. The oil and gas knowledge graph can be constructed through Neo4j. Neo4j is a graph database, which belongs to NoSQL (Not Only SQL, non-relational database) and can be used to persist data. For example, you can write Cypher commands to create the relationship between nodes and nodes through Neo4j in the browser.

[0069] The method for constructing the above-mentioned oil and gas knowledge map is to obtain the oil and gas production data and preset oil and gas production nodes by obtaining the entity nodes of the oil and gas knowledge map to be constructed and the corresponding entity relationships, and perform node data extraction on the oil and gas production data based on the oil and gas production nodes. Obtain the oil and gas production node data; fill the oil and gas production node data to the corresponding entity node to obtain the oil and gas entity node data, and obtain the oil and gas knowledge map based on the oil and gas entity node data and the entity relationship, and conduct the oil and gas production data by constructing the oil and gas knowledge map After sorting out, the relationship between various oil and gas knowledge has been established, which can improve the management of oil and gas production data and reduce the difficulty of subsequent data retrieval.

[0070] In one embodiment, obtaining the entity node of the oil and gas knowledge graph to be constructed and the entity relationship corresponding to the entity node includes: obtaining a preset oil and gas knowledge system, extracting oil and gas data items in the oil and gas knowledge system; and creating time nodes for the oil and gas data items According to the oil and gas data items and time nodes, obtain the entity nodes of the oil and gas knowledge graph to be constructed; obtain the business relationship between the oil and gas data items according to the oil and gas knowledge system, and obtain the entity relationship of the oil and gas knowledge graph to be constructed according to the business relationship. Specifically, time nodes can be established on different oil and gas field units. The knowledge map generally only stores static data. By establishing time nodes on different oil and gas field units, the dynamic data storage function of the knowledge map can be realized. This changes the dynamic data storage structure based on the relational database single table, and realizes the data model based on the knowledge graph and graph data structure to store time series dynamic data. In addition, the concept of time node is introduced to link oil and gas production data to the time node of the oil and gas knowledge map to form an exploration and development knowledge base that integrates dynamic and static exploration and development data, laying a solid foundation for cognitive computing for oil and gas exploration and development. The application scope of the knowledge graph is expanded to extend to the dynamic data management based on time series, which increases the diversity and flexibility of data types in the knowledge graph. Using the time nodes of the knowledge graph to manage oil and gas production data greatly improves the efficiency of querying and analyzing dynamic data.

[0071] In one embodiment, the oil and gas production data includes structured oil and gas production data. Extracting node data from the oil and gas production data based on oil and gas production nodes to obtain oil and gas production node data includes: constructing a data table query statement based on the oil and gas production node; querying through the data table The sentence is searched in the structured oil and gas production data to obtain the oil and gas production node data. Structured oil and gas production data refers to oil and gas production data stored in structured databases, such as dynamic oil and gas production data stored in structured databases such as Oracle, MySQL, and SQL Server. By constructing different SQL (Structured Query Language, structured query language) statements, extract the dynamic data in the full table, part of the table and different tables, and then convert the extracted data into the entity-relationship in the knowledge graph through a preset program Entity triple form. For example, for Liaohe Huanxiling Oilfield, you can query the dynamic production data of the oilfield from the Oracle database through the SQL statement of SELECT*FROM FIELD_PROD_YEARLY. The query results are shown in the following table. Among them, annual oil production, cumulative oil production, and annual fluid production , The unit of cumulative liquid production is 10,000 tons, and the comprehensive water cut and oil production rate are percentages.

[0072] Table 1 The dynamic production data of the oil field obtained through a query statement

[0073]

[0074] In one embodiment, the oil and gas production data includes unstructured oil and gas production data, and node data extraction is performed on the oil and gas production data based on the oil and gas production node to obtain the oil and gas production node data including: marking the unstructured oil and gas production data based on the oil and gas production node , Get the labeled data; perform node data extraction on the unstructured oil and gas production data according to the labeled data to obtain the oil and gas production node data. Unstructured oil and gas production data refers to oil and gas production data stored in unstructured oil and gas production data, such as Word documents, ppt files, and PDF files. Unstructured oil and gas production data is extracted through technical means such as knowledge labeling and knowledge extraction, and connected to the knowledge map. Unstructured data is an important source of knowledge about oil and gas exploration and development. It can supplement and expand data in structured databases, expand data scale and coverage, and improve data governance and integration. Specifically, for example, extract a paragraph of "Huanxiling Oil Field History" from the book "China Oil and Gas Field Development History", business experts can mark the dynamic data with artificial knowledge, such as Figure 4 Shown. Supplement the knowledge in the existing structured database through the annotated knowledge, Figure 4 The documents in can expand the number of production days, number of production blocks, well spacing, well pattern type, etc. of Huanxiling Oilfield in 1979. In addition, according to the manually labeled corpus, the preset knowledge extraction system can train natural language processing, deep learning and other algorithms, and automatically extract the triple knowledge of subsequent new documents through the trained algorithm.

[0075] In one embodiment, filling the oil and gas production node data into the corresponding physical node, and before obtaining the oil and gas physical node data, further includes: when the oil and gas production node data does not have a corresponding physical node, the oil and gas production corresponding to the oil and gas production node data The node creates a new entity node; according to the created entity node, the entity node of the oil and gas knowledge graph to be constructed and the corresponding entity relationship are updated; the oil and gas production node data is filled into the corresponding entity node to obtain the oil and gas entity node data, based on the oil and gas entity Obtaining the oil and gas knowledge map based on the node data and entity relationships includes: filling the oil and gas production node data to the updated entity nodes correspondingly to obtain the oil and gas entity node data, and obtain the oil and gas knowledge map based on the oil and gas entity node data and the updated entity relationship. If the oil and gas production node does not exist in the pre-built knowledge graph ontology database, then it is necessary to create a new entity node in the ontology library based on the oil and gas production node, update or create a new time node in the pre-built knowledge graph, and add this The node is connected to the corresponding entity node of the knowledge graph. For example, there are two sources for the production performance data of Huanxiling Oilfield in 1979, one from the database, and the other from the book "China Oil and Gas Field Development History". Use Neo4j to create the relationship between nodes and nodes for oil and gas dynamic production data from the database, such as Figure 5 As shown; through Neo4j, the dynamic production data of oil and gas derived from "China Oil and Gas Field Development History" is used to create the relationship between nodes and nodes, such as Image 6 Shown. Perform knowledge fusion processing on oil and gas production data from two sources, and connect the fused time nodes to the relevant oilfield entities in the knowledge map, such as Figure 7 Shown.

[0076] In one embodiment, obtaining oil and gas production data includes: obtaining initial oil and gas production data; performing knowledge fusion processing on the initial oil and gas production data, eliminating duplicate data and abnormal data in the initial oil and gas production data, and obtaining oil and gas production data. Knowledge fusion of structured data and unstructured data, access the fused data to the knowledge map database, and carry out knowledge fusion of repeated data and conflicting and inconsistent oil and gas production dynamic data, specifically through existing open source tools and technologies achieve. The oil and gas production data after the knowledge fusion process is connected to the specific oil and gas production entity node in the knowledge map database to obtain the oil and gas knowledge map.

[0077] In one embodiment, the method for constructing an oil and gas knowledge map further includes: obtaining an oil and gas production data analysis request, parsing the oil and gas production data analysis request, and obtaining target oil and gas production data items; searching in the oil and gas knowledge map according to the target oil and gas production data items to obtain Target oil and gas production data corresponding to the target oil and gas production data item; analyze and process the target oil and gas production data to obtain analysis result data corresponding to the oil and gas production data analysis request. Based on the oil and gas dynamic data stored in the oil and gas knowledge map for data query, analysis, statistics and data mining, etc., the performance of oil and gas dynamic data query, analysis, statistics and data mining based on the oil and gas knowledge map is high, including a large number of oil and gas data The performance advantages of the oil and gas knowledge map are particularly obvious when the data tables of the data tables are connected to each other. The oil and gas knowledge map not only realizes the mixed storage of various dynamic data on oil and gas fields, blocks, small layers, and single wells, such as daily production data, monthly production data, annual production, and recoverable reserves, but also realizes the structure Hybrid storage of standardized and unstructured data. For example, based on the oil and gas production data stored in the oil and gas knowledge map, the degree of recovery is used as the abscissa, and the water cut is used as the ordinate, the obtained water flooding curve of the water injection oil field is as follows Figure 8 Shown. For another example, based on the oil and gas production data stored in the oil and gas knowledge map, the time is used as the abscissa and the production operation index is used as the ordinate, such as daily oil production, daily fluid production, daily water injection, and comprehensive water cut as the ordinate, the obtained oil field The daily output curve is as Picture 9 Shown.

[0078] It should be understood that although figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless specifically stated in this article, the execution of these steps is not strictly restricted in order, and these steps can be executed in other orders. and, figure 2 At least part of the steps in may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the order of execution of these sub-steps or stages is not necessarily It is performed sequentially, but may be performed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0079] In one embodiment, such as Picture 10 As shown, a device for constructing an oil and gas knowledge map is provided, including: a data acquisition module 1002, a first processing module 1004, a second processing module 1006, and a map generating module 1008. Among them, the data acquisition module 1002 is used to acquire the entity nodes of the oil and gas knowledge graph to be constructed, the entity relationships corresponding to the entity nodes, oil and gas production data, and preset oil and gas production nodes. The first processing module 1004 is used for node data extraction of oil and gas production data based on oil and gas production nodes to obtain oil and gas production node data. The second processing module 1006 is used for filling oil and gas production node data into corresponding physical nodes to obtain oil and gas physical node data. The map generation module 1008 is used to obtain an oil and gas knowledge map based on the oil and gas entity node data and entity relationships.

[0080] In one embodiment, the data acquisition module is also used to acquire a preset oil and gas knowledge system, extract oil and gas data items in the oil and gas knowledge system; create a time node for the oil and gas data item, and obtain the to-be-built according to the oil and gas data item and the time node The entity node of the oil and gas knowledge graph; obtain the business relationship between oil and gas data items according to the oil and gas knowledge system, and obtain the entity relationship of the oil and gas knowledge graph to be constructed according to the business relationship.

[0081] In an embodiment, the first processing module is also used to construct a data table query statement based on the oil and gas production node; search the structured oil and gas production data through the data table query statement to obtain the oil and gas production node data.

[0082] In one embodiment, the first processing module is further configured to annotate unstructured oil and gas production data based on oil and gas production nodes to obtain labeled data; and perform node data extraction on unstructured oil and gas production data based on the labeled data to obtain oil and gas production nodes data.

[0083] In one embodiment, the device for constructing an oil and gas knowledge graph further includes a node creation module, which is used to create a new entity node based on the oil and gas production node corresponding to the oil and gas production node data when there is no corresponding physical node in the oil and gas production node data; The created entity node updates the entity node of the oil and gas knowledge graph to be constructed and the corresponding entity relationship; the second processing module is also used to fill the oil and gas production node data into the updated entity node correspondingly to obtain the oil and gas entity node data; map generation The module is also used to obtain the oil and gas knowledge map based on the oil and gas entity node data and the updated entity relationship.

[0084] In one embodiment, the first processing module is also used to obtain initial oil and gas production data; perform knowledge fusion processing on the initial oil and gas production data, eliminate duplicate data and abnormal data in the initial oil and gas production data, and obtain oil and gas production data.

[0085] In one embodiment, the device for constructing an oil and gas knowledge map further includes a data analysis module for obtaining oil and gas production data analysis requests, analyzing oil and gas production data analysis requests, and obtaining target oil and gas production data items; according to the target oil and gas production data items in the oil and gas knowledge Search in the map to obtain the target oil and gas production data corresponding to the target oil and gas production data item; analyze and process the target oil and gas production data to obtain the analysis result data corresponding to the oil and gas production data analysis request.

[0086] The device for constructing an oil and gas knowledge map includes a processor and a memory. The above-mentioned data acquisition module, first processing module, second processing module, map generation module, node creation module, data analysis module, etc. are all stored in the memory as program modules, The processor executes the above-mentioned program modules stored in the memory to realize the corresponding functions.

[0087] The processor contains the kernel, which calls the corresponding program module from the memory. The kernel can be set to one or more, and the management of oil and gas production data can be improved by adjusting the kernel parameters, and the difficulty of subsequent data retrieval can be reduced.

[0088] The embodiment of the present invention provides a storage medium on which a program is stored, and the method for constructing the oil and gas knowledge graph is realized when the program is executed by a processor.

[0089] The embodiment of the present invention provides a processor configured to run a program, wherein the method for constructing the oil and gas knowledge graph is executed when the program is running.

[0090] The embodiment of the present invention provides a device that includes at least one processor, and at least one memory and a bus connected to the processor; wherein the processor and the memory communicate with each other through the bus; the processor is used to call Program instructions to execute the above-mentioned construction method of the oil and gas knowledge map. The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0091] This application also provides a computer program product, which when executed on a data processing device, is suitable for executing a program that initializes the following method steps: obtaining the entity node of the oil and gas knowledge graph to be constructed, the entity relationship corresponding to the entity node, and the oil and gas knowledge graph. Production data and preset oil and gas production nodes; extract oil and gas production data based on oil and gas production nodes to obtain oil and gas production node data; fill oil and gas production node data to corresponding physical nodes to obtain oil and gas entity node data; based on oil and gas entities Node data and entity relationships are used to obtain an oil and gas knowledge map.

[0092] This application also provides a computer program product, which when executed on a data processing device, is suitable for executing a program that initializes the following method steps: obtaining a preset oil and gas knowledge system, and extracting oil and gas data items in the oil and gas knowledge system; creating The time node of the oil and gas data item, according to the oil and gas data item and the time node, obtain the entity node of the oil and gas knowledge graph to be constructed; obtain the business relationship between oil and gas data items according to the oil and gas knowledge system, and obtain the oil and gas knowledge graph to be constructed according to the business relationship Entity relationship.

[0093] This application also provides a computer program product, which when executed on a data processing device, is suitable for executing a program that initializes the following method steps: constructing data table query statements based on oil and gas production nodes; Search in the production data to get the oil and gas production node data.

[0094] This application also provides a computer program product, which when executed on a data processing device, is suitable for executing a program that initializes the following method steps: based on the oil and gas production node, unstructured oil and gas production data is annotated to obtain the annotation data; The labeled data extracts node data from unstructured oil and gas production data to obtain oil and gas production node data.

[0095] This application also provides a computer program product, which when executed on a data processing device, is suitable for executing a program that initializes the following method steps: when there is no corresponding physical node in the oil and gas production node data, corresponding to the oil and gas production node data Create a new entity node for the oil and gas production node; update the entity node of the oil and gas knowledge graph to be constructed and the corresponding entity relationship according to the created entity node; fill the oil and gas production node data correspondingly to the updated entity node to obtain the oil and gas entity node Data, based on the oil and gas entity node data and the updated entity relationship, obtain the oil and gas knowledge map.

[0096] This application also provides a computer program product, which when executed on a data processing device, is suitable for executing a program that initializes the following method steps: acquiring initial oil and gas production data; performing knowledge fusion processing on the initial oil and gas production data, and eliminating initial oil and gas Repetitive data and abnormal data in the production data to obtain oil and gas production data.

[0097] This application is described with reference to flowcharts and/or block diagrams of methods, devices, and computer program products according to embodiments of this application. It should be understood that each process and/or block in the flowchart and/or block diagram, and the combination of processes and/or blocks in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing equipment are generated for use In the process Figure one Process or multiple processes and/or boxes Figure one A device with functions specified in a block or multiple blocks.

[0098] In a typical configuration, such as Picture 11 As shown, the device includes one or more processors (CPU), memory, and buses. The device may also include input/output interfaces, network interfaces, and so on.

[0099] The memory may include non-permanent memory in a computer readable medium, random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM), and the memory includes at least one Memory chip. The memory is an example of a computer-readable medium.

[0100] Computer-readable media include permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

[0101] It should also be noted that the terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or equipment including a series of elements not only includes those elements, but also includes Other elements that are not explicitly listed, or include elements inherent to the process, method, commodity, or equipment. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, method, commodity or equipment that includes the element.

[0102] Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, this application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0103] The above are only examples of this application, and are not used to limit this application. For those skilled in the art, this application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included in the scope of the claims of this application.