WO2021051909A1 - 油气数据处理方法及装置 - Google Patents

油气数据处理方法及装置 Download PDF

Info

Publication number
WO2021051909A1
WO2021051909A1 PCT/CN2020/097024 CN2020097024W WO2021051909A1 WO 2021051909 A1 WO2021051909 A1 WO 2021051909A1 CN 2020097024 W CN2020097024 W CN 2020097024W WO 2021051909 A1 WO2021051909 A1 WO 2021051909A1
Authority
WO
WIPO (PCT)
Prior art keywords
oil
data
entity
gas
knowledge graph
Prior art date
Application number
PCT/CN2020/097024
Other languages
English (en)
French (fr)
Inventor
葛婷
Original Assignee
北京国双科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京国双科技有限公司 filed Critical 北京国双科技有限公司
Publication of WO2021051909A1 publication Critical patent/WO2021051909A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G06F16/284—Relational databases
    • G06F16/288—Entity relationship models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri

Definitions

  • the invention relates to the field of oil and gas, and more specifically, to a method and device for processing oil and gas data.
  • the present invention provides an oil and gas data processing method and device that overcomes the above-mentioned problems or at least partially solves the above-mentioned problems.
  • An oil and gas data processing method including:
  • the ontology relationship graph includes the ontology of the oil and gas field and the association relationship between different ontology
  • the entities, and the entity information construct a knowledge graph in the oil and gas field;
  • the knowledge graph includes entities in the oil and gas field, and relationships between entities and entities;
  • the data fusion operation includes at least one of the following: entity alignment, entity conflict detection, and entity conflict resolution.
  • constructing a knowledge graph in the oil and gas field includes:
  • the corresponding ontology in the knowledge graph framework is replaced by entities, and the entity information is data integrated according to the knowledge graph framework to obtain the knowledge graph of the oil and gas field.
  • performing an operation corresponding to the user requirement based on the knowledge graph includes:
  • the modification instruction includes the modified content selected by the user in the knowledge graph and the modified target content;
  • the modified content stored in the database corresponding to the knowledge graph is modified to the target content.
  • performing an operation corresponding to the user requirement based on the knowledge graph includes:
  • the data search instruction includes the target object that needs to perform data query
  • the query result corresponding to the target object is searched from the knowledge graph and the link content related to the knowledge graph.
  • the method further includes:
  • performing an operation corresponding to the user demand includes:
  • the oil and gas reservoir analog query request includes attribute information of the oil and gas reservoir to be queried;
  • an entity whose similarity with the oil and gas reservoir to be queried is greater than a second preset threshold is determined, and the determined attribute information of the entity is output.
  • performing an operation corresponding to the user requirement based on the knowledge graph includes:
  • the data visualization instruction includes target data to be visualized
  • the target data to be visualized is displayed in a visual manner.
  • An oil and gas data processing device including:
  • the data acquisition module is used to acquire data related to the oil and gas field and the ontology relationship diagram of the oil and gas field;
  • the ontology relationship diagram includes the ontology of the oil and gas field and the association relationship between different ontologies;
  • a data extraction module for extracting entities in the oil and gas field and corresponding entity information from the data; the same ontology corresponds to at least one entity;
  • the graph building module is used to construct a knowledge graph in the oil and gas field based on the ontology relationship graph, the entities, and the entity information;
  • the knowledge graph includes entities in the oil and gas field, and relationships between entities and entities;
  • the demand processing module is used to perform operations corresponding to user demands based on the knowledge graph.
  • An oil and gas data processing device includes a storage medium and a processor, the storage medium stores a program, and the processor is used to run the program, wherein the above-mentioned oil and gas data processing method is executed when the program is running.
  • the present invention provides an oil and gas data processing method and device to obtain data related to the oil and gas field and an ontology relationship graph of the oil and gas field, and extract entities in the oil and gas field and corresponding entity information from the data , Based on the ontology relationship graph, the entity, and the entity information, construct a knowledge map of the oil and gas field. That is, through the present invention, a knowledge map of the oil and gas field can be constructed, and then the knowledge literature and expert experience can be gathered together to form a complete knowledge engine of oil and gas knowledge.
  • Fig. 1 shows a method flowchart of a method for processing oil and gas data according to an embodiment of the present invention
  • Figure 2 shows a schematic structural diagram of an ontology relationship diagram provided by an embodiment of the present invention
  • Figure 3 shows a schematic structural diagram of a knowledge graph provided by an embodiment of the present invention
  • Figure 4 shows a method flowchart of another oil and gas data processing method provided by an embodiment of the present invention.
  • FIG. 5 shows a method flowchart of still another oil and gas data processing method provided by an embodiment of the present invention
  • FIG. 6 shows a display diagram of a data query interface provided by an embodiment of the present invention
  • FIG. 7 shows a method flowchart of yet another oil and gas data processing method provided by an embodiment of the present invention.
  • FIG. 8 shows an interface diagram of an oil and gas reservoir analogy provided by an embodiment of the present invention.
  • FIG. 9 shows another interface diagram of an oil and gas reservoir analogy provided by an embodiment of the present invention.
  • FIG. 10 shows an interface diagram of a data visualization display provided by an embodiment of the present invention.
  • Fig. 11 shows a schematic structural diagram of an oil and gas data processing device provided by an embodiment of the present invention.
  • the embodiment of the present invention provides a method for processing oil and gas data.
  • the method may include:
  • the oil and gas field has accumulated many documents and materials for many years, the production data lasts for a long time, and the oil and gas field has a wide range of production operations, involving complex geological structures and detailed classification.
  • the real-time recording data of production data most of the knowledge and data exist in the paper materials of the report or in the brains of experts. These data are stored in an unstructured form in the industry research institutes and the data rooms of various local companies, where the above data needs to be collected.
  • the domain's knowledge graph framework that is, ontology relation graph.
  • the ontology relationship graph includes the ontology of the oil and gas field and the association relationship between different ontology.
  • the ontology refers to a formalized, clear and detailed description of the shared conceptual system.
  • the formal representation (the structure of the ontology design) is carried out according to a certain structure, so as to make the knowledge orderly.
  • the structure of the ontology is closely related to the industry.
  • the ontology relationship diagram refers to the relationship diagram between different wells, discovery wells, basins, etc. in the concept.
  • the knowledge map constructed in the later stage is an ontology relationship diagram of the actual scene that "landed". Refer to Figure 2 for the ontology relationship diagram.
  • the oil and gas field may further include:
  • the data fusion operation includes at least one of entity alignment, entity conflict detection, and entity conflict resolution.
  • Knowledge fusion is the unification of data belonging to the same entity but with different names.
  • Knowledge fusion involves entity alignment, entity conflict detection and entity conflict resolution.
  • entity alignment and entity conflict resolution we use complete matching and partial matching, and partial matching uses a method including the longest string subsequence and consistency calculation.
  • Entity Alignment is also called Entity Matching, which refers to finding the same entity in the real world for each entity in the knowledge base of heterogeneous data sources.
  • Entity conflict detection refers to the detection of a certain entity name corresponding to multiple named entity objects.
  • Entity conflict resolution is a technology specifically used to resolve the ambiguity of entities with the same name.
  • the entity may be represented by an entity name, and the entity information includes entity attributes, entity events, and association relationships between the entity and other entities.
  • Both the entity and the ontology are identified in the form of nodes, and the ontology includes the attribute list of all entities under the ontology, that is, the same ontology corresponds to at least one entity, and the entity includes 0 to more attributes.
  • Ontology supports ontology management, that is, supports custom ontology nodes and relationships according to industry knowledge and business needs, and the defined ontology is valid for all entities.
  • entity extraction and entity relationship extraction are performed from the data.
  • a combination of automatic extraction and manual extraction can be used.
  • the automatic extraction model is obtained by training in advance through domain rules defined for unstructured documents in the oil and gas field and a large number of domain-related documents as training data.
  • the automatic extraction result obtained by the automatic extraction model is used as a pre-annotation to detect some entities and relationships in the unstructured text.
  • manual supplementary annotation can be performed, and the automatically extracted pre-labeled results and the manually supplemented annotation results are used as the knowledge acquisition content of unstructured and semi-structured text.
  • the extracted entities include entity name, entity attribute and entity event.
  • entity name can be well 001.
  • entity attribute of the well can be well depth, well width, etc.
  • the physical properties of the oil and gas reservoir can be porosity, permeability, total thickness, net thickness, and density of underlying crude oil.
  • a physical event can be an event that occurred in the entity, such as a blowout in Well 001 in February 19 and another blowout in March.
  • the association relationship between the entity and the entity may be a hierarchical relationship of upper and lower levels, such as wells including well production, wellbore, mud logging, drilling, etc., operating company relationships, such as oil and gas field affiliated company A, location relationships, etc., such as well 001 Located in Sichuan area.
  • step S13 may include:
  • the ontology relationship graph represents the knowledge graph framework in the oil and gas field.
  • the ontology relationship graph can be used to form the knowledge graph framework.
  • the ontology relationship graph can be directly used as the knowledge graph framework, or the ontology relationship graph can be graphically beautified, such as Specify the color of each entity, etc. to get the knowledge graph framework.
  • the entity replaces the corresponding ontology, and the entity information is integrated according to the knowledge graph framework to obtain the knowledge graph.
  • Figure 3 for the structure of the knowledge graph. It should be noted that Figure 3 is only an example of a partial knowledge graph, not a complete knowledge graph.
  • user needs can be to change the knowledge map, content search, related content recommendation, oil and gas reservoir analog analysis, data visualization display, etc.
  • data related to the oil and gas field and an ontology relationship graph of the oil and gas field are acquired, and entities in the oil and gas field and corresponding entity information are extracted from the data, based on the ontology relationship graph, the entities, and the Entity information to build a knowledge map of the oil and gas field. That is, through the present invention, a knowledge map of the oil and gas field can be constructed, and then knowledge documents and expert experience can be aggregated together to form a complete knowledge engine for oil and gas knowledge.
  • step S14 when there are different user requirements, the specific implementation of step S14 is different, which will now be introduced separately.
  • step S14 may include:
  • the modification instruction includes the modified content selected by the user in the knowledge graph and the modified target content.
  • the knowledge management function of business personnel is opened, so that business personnel can import the map through annotations, and modify entity relationships, entity names, entity attributes, and entity events in the map. And other information. Specifically, all entities of the same type can be managed and adjusted through the ontology, and specific entity nodes or attributes can be added and deleted.
  • the business personnel can determine the content to be modified in the knowledge graph, and then modify the modified content into the target content, and then include the modified content selected in the knowledge graph and the modified target content
  • the modification instruction of the knowledge graph will be sent to the database corresponding to the knowledge graph through a specific data modification port, and the modified content stored in the database will be modified to the target content.
  • step S14 may include:
  • the data search instruction includes the target object to be data searched.
  • the knowledge graph in this embodiment supports the data query function, for example, the user enters the target object for data query in the query window.
  • the user enters the target object for data query in the query window.
  • enter Hongshanzui Oilfield in the text box which is a data query for Hongshanzui Oilfield.
  • semantic analysis can be performed based on the target object to obtain the query subject and the query range corresponding to the query subject.
  • the query subject is an entity that matches the target object in the knowledge map.
  • Hongshanzui Oilfield exists in the knowledge map
  • Hongshanzui Oilfield is the query subject.
  • the target object only includes the Hongshanzui Oilfield and does not include other content, so the query scope corresponding to the query subject here is the specific content of the Hongshanzui Oilfield.
  • the query subject is the Northwest Oilfield, and the query range corresponding to the query subject is all companies to which the Northwest Oilfield belongs.
  • the knowledge graph and the uniform resource locator URL link corresponding to the knowledge graph are searched for content corresponding to the query subject and the query scope.
  • the target object is Hongshanzui Oilfield
  • the query range corresponding to the query subject is the specific content of Hongshanzui Oilfield.
  • the query result is the query result interface based on the knowledge graph in Figure 6, and the query results include Altitude, address area, dimension, oil and gas field name, etc. If the query content is a company belonging to Northwest Oilfield, the query result can be Company A, that is, the specific company name.
  • step S33 it may further include:
  • the system can also implement knowledge recommendation on related topics based on the query subject and the data to be queried corresponding to the query subject.
  • the recommendation can include relevant cross-section diagrams, structural diagrams and other important pictures in the field. data.
  • step S14 may include:
  • the oil and gas reservoir analog query request includes the attribute information of the oil and gas reservoir to be queried.
  • this embodiment is an application of analogy of oil and gas reservoirs.
  • the application of analogy of oil and gas reservoirs is to calculate the similarity of each dimension of oil and gas reservoirs based on the knowledge map, and recommend the analogy results of each oil and gas reservoir according to the calculated scores for the deepening of oil and gas reservoirs. Analysis, and discovery of new oil and gas reservoirs.
  • this embodiment is applicable to two usage scenarios. One is to have a general understanding of the input-output ratio of the new oil and gas reservoir when a new oil and gas reservoir is discovered. The other is to conduct an in-depth analogy analysis of existing oil and gas reservoirs. This embodiment is mainly applicable to the first use scenario.
  • the new oil and gas reservoir obtained through measurement that is, the attribute information of the oil and gas reservoir to be queried, such as data such as porosity, permeability, and total thickness.
  • the preset oil and gas reservoir analysis dimensions include: porosity, permeability, and total thickness.
  • the analysis result is the analogy result in Figure 8.
  • the analogy result includes the normal, oversized, and undersized results and other information.
  • the similarity between the new oil and gas reservoir and the developed oil and gas reservoir can be calculated according to the analysis results, and the similarity is larger than the first one.
  • Target oil and gas reservoirs with preset thresholds Refer to Figure 9 for specific results. In Fig. 9, the similarities with the new oil and gas reservoirs from large to small are Xinglongtai and Kexia Formation in the Hong 032 well block respectively. At this time, the attribute information of each target oil and gas reservoir is output, such as oil and gas type, porosity, and permeability.
  • step S14 may include:
  • the data visualization instruction includes target data to be visualized
  • this embodiment supports the visualization of data.
  • a piece of data needs to be displayed visually, first determine the data that the user needs to display, that is, target data, and then perform the visual display through a chart or the like.
  • the visual display graph can be a bar graph like the permeability frequency distribution graph in FIG. 10.
  • another embodiment of the present invention provides an oil and gas data processing device. Referring to FIG. 11, it may include:
  • the data acquisition module 101 is configured to acquire data related to the oil and gas field and an ontology relationship diagram of the oil and gas field;
  • the ontology relationship diagram includes the ontology of the oil and gas field and the association relationship between different ontologies;
  • the data extraction module 102 is configured to extract entities in the oil and gas field and corresponding entity information from the data; the same ontology corresponds to at least one entity;
  • the graph construction module 103 is configured to construct a knowledge graph in the oil and gas field based on the ontology relationship graph, the entities, and the entity information; the knowledge graph includes entities in the oil and gas field, and relationships between entities and entities;
  • the demand processing module 104 is configured to perform operations corresponding to user demands based on the knowledge graph.
  • a data fusion module configured to perform a data fusion operation on data belonging to the same entity in the data; the data fusion operation includes at least one of the following: entity alignment, Entity conflict detection, entity conflict resolution.
  • the graph construction module 103 is configured to construct a knowledge graph in the oil and gas field based on the ontology relationship graph and the entity information, specifically for:
  • a knowledge graph framework is formed according to the ontology relationship graph, the corresponding ontology in the knowledge graph framework is replaced by entities, and the entity information is integrated according to the knowledge graph framework to obtain the knowledge graph in the oil and gas field .
  • the requirement processing module 104 may include:
  • the modification instruction acquisition sub-module is used to acquire the user's knowledge graph modification instruction; the modification instruction includes the modified content selected by the user in the knowledge graph and the modified target content;
  • the data modification sub-module is configured to modify the modified content stored in the database corresponding to the knowledge graph to the target content according to the knowledge graph modification instruction.
  • the demand processing module 104 may include:
  • the query instruction acquisition sub-module is used to acquire the user's data query instruction;
  • the data search instruction includes the target object that needs to perform data query;
  • the query data analysis sub-module is used to determine an entity matching the target object in the knowledge graph of the oil and gas field as a query subject, and determine the query range corresponding to the query subject;
  • the data query sub-module is used to search for the query result corresponding to the target object from the knowledge graph and the link content related to the knowledge graph based on the query subject and the query scope.
  • the data push sub-module is used to obtain from the knowledge graph the corresponding entity attribute and the entity attribute in the query result whose similarity is greater than the first preset threshold value, and perform data processing on the entity information of the entity obtained Push.
  • the demand processing module 104 may include:
  • the analogy request receiving sub-module is used to obtain the oil and gas reservoir analogy query request input by the user; the oil and gas reservoir analogy query request includes the attribute information of the oil and gas reservoir to be queried;
  • the data analysis sub-module is used to compare the attribute information of each entity whose entity name belongs to the oil and gas reservoir in the knowledge map and the attribute information of the oil and gas reservoir to be queried respectively under the preset oil and gas reservoir analysis dimensions to obtain an analogy result;
  • the data determination sub-module is configured to determine an entity whose similarity to the oil and gas reservoir to be queried is greater than a second preset threshold according to the analogy result, and output the determined attribute information of the entity.
  • the demand processing module 104 may include:
  • the data visualization sub-module is used to obtain data visualization instructions, and display the target data to be visualized in a visual manner.
  • the data visualization instruction includes target data to be visualized.
  • data related to the oil and gas field and an ontology relationship graph of the oil and gas field are acquired, and entities in the oil and gas field and corresponding entity information are extracted from the data, based on the ontology relationship graph, the entities, and the Entity information to build a knowledge map of the oil and gas field. That is, through the present invention, a knowledge map of the oil and gas field can be constructed, and then the knowledge literature and expert experience can be gathered together to form a complete knowledge engine of oil and gas knowledge.
  • the oil and gas data processing device includes a processor and a memory.
  • the above-mentioned data acquisition module, data extraction module, atlas construction module, and demand processing module are all stored as program units in the memory, and the above program units stored in the memory are executed by the processor. To realize the corresponding function.
  • the processor contains the kernel, and the kernel calls the corresponding program unit from the memory.
  • One or more kernels can be set up. By adjusting kernel parameters, knowledge literature and expert experience can be aggregated to form a complete knowledge engine for oil and gas knowledge.
  • the memory may include non-permanent memory in computer-readable media, 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.
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash random access memory
  • the embodiment of the present invention provides a storage medium on which a program is stored, and when the program is executed by a processor, the oil and gas data processing method is realized.
  • the embodiment of the present invention provides a processor configured to run a program, wherein the oil and gas data processing method is executed when the program is running.
  • the embodiment of the present invention provides a device that includes a processor, a memory, and a program stored on the memory and capable of running on the processor, and the processor implements the following steps when the program is executed:
  • An oil and gas data processing method including:
  • the ontology relationship graph includes the ontology of the oil and gas field and the association relationship between different ontology
  • the entities, and the entity information construct a knowledge graph in the oil and gas field;
  • the knowledge graph includes entities in the oil and gas field, and relationships between entities and entities;
  • the data fusion operation includes at least one of the following: entity alignment, entity conflict detection, and entity conflict resolution.
  • constructing a knowledge graph in the oil and gas field includes:
  • the corresponding ontology in the knowledge graph framework is replaced by entities, and the entity information is data integrated according to the knowledge graph framework to obtain the knowledge graph of the oil and gas field.
  • performing operations corresponding to the user demand based on the knowledge graph includes:
  • the modification instruction includes the modified content selected by the user in the knowledge graph and the modified target content;
  • the modified content stored in the database corresponding to the knowledge graph is modified to the target content.
  • performing an operation corresponding to the user demand based on the knowledge graph includes:
  • the data search instruction includes the target object that needs to perform data query
  • the query result corresponding to the target object is searched from the knowledge graph and the link content related to the knowledge graph.
  • the method further includes:
  • performing an operation corresponding to the user demand includes:
  • the oil and gas reservoir analog query request includes attribute information of the oil and gas reservoir to be queried;
  • an entity whose similarity with the oil and gas reservoir to be queried is greater than a second preset threshold is determined, and the determined attribute information of the entity is output.
  • performing an operation corresponding to the user demand based on the knowledge graph includes:
  • the data visualization instruction includes target data to be visualized
  • the target data to be visualized is displayed in a visual manner.
  • the devices in this article can be servers, PCs, PADs, mobile phones, etc.
  • 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:
  • An oil and gas data processing method including:
  • the ontology relationship graph includes the ontology of the oil and gas field and the association relationship between different ontology
  • the entities, and the entity information construct a knowledge graph in the oil and gas field;
  • the knowledge graph includes entities in the oil and gas field, and relationships between entities and entities;
  • the data fusion operation includes at least one of the following: entity alignment, entity conflict detection, and entity conflict resolution.
  • constructing a knowledge graph in the oil and gas field includes:
  • the corresponding ontology in the knowledge graph framework is replaced by entities, and the entity information is data integrated according to the knowledge graph framework to obtain the knowledge graph of the oil and gas field.
  • performing operations corresponding to the user demand based on the knowledge graph includes:
  • the modification instruction includes the modified content selected by the user in the knowledge graph and the modified target content;
  • the modified content stored in the database corresponding to the knowledge graph is modified to the target content.
  • performing an operation corresponding to the user demand based on the knowledge graph includes:
  • the data search instruction includes the target object that needs to perform data query
  • the query result corresponding to the target object is searched from the knowledge graph and the link content related to the knowledge graph.
  • the method further includes:
  • performing an operation corresponding to the user demand includes:
  • the oil and gas reservoir analog query request includes attribute information of the oil and gas reservoir to be queried;
  • an entity whose similarity with the oil and gas reservoir to be queried is greater than a second preset threshold is determined, and the determined attribute information of the entity is output.
  • performing an operation corresponding to the user demand based on the knowledge graph includes:
  • the data visualization instruction includes target data to be visualized
  • the target data to be visualized is displayed in a visual manner.
  • this application can 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.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device.
  • the device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment.
  • the instructions provide steps for implementing the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • the computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • 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).
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash memory
  • 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.
  • this application can be provided as a method, a system, or a computer program product. 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.
  • a computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种油气数据处理方法及装置，所述方法包括：获取与油气领域相关的数据以及油气领域的本体关系图（S11），从所述数据中抽取得到油气领域的实体以及对应的实体信息（S12），基于所述本体关系图、所述实体以及所述实体信息，构建油气领域的知识图谱（S13），基于知识图谱，执行与用户需求对应的操作（S14）。所述方法可以构建油气领域的知识图谱，进而可以将知识文献和专家经验汇总到一起，形成完整的油气知识的知识引擎。

Description

油气数据处理方法及装置
本申请要求于2019年9月18日提交中国专利局、申请号为201910880997.7、发明名称为“油气数据处理方法及装置”的国内申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及油气领域，更具体的说，涉及一种油气数据处理方法及装置。
背景技术
人类在油气领域躬耕已久，在行业内也积累了大量的知识文献。同样，行业专家也积累了大量的行业经验知识。行业从业人员可以通过学习知识文献和专家经验，在油气行业中有所探索和创新。
但是现有技术中，油气行业的知识文献和专家经验相互分离，并没有一套包括完整的油气知识的知识引擎。
发明内容
鉴于上述问题，本发明提供一种克服上述问题或者至少部分地解决上述问题的一种油气数据处理方法及装置。
一种油气数据处理方法，包括：
获取与油气领域相关的数据以及油气领域的本体关系图；所述本体关系图包括油气领域的本体以及不同本体之间的关联关系；
从所述数据中抽取得到油气领域的实体以及对应的实体信息；同一本体对应至少一个实体；
基于所述本体关系图、所述实体以及所述实体信息，构建油气领域的知识图谱；所述知识图谱包括油气领域的实体、实体与实体之间的关系；
基于所述知识图谱，执行与用户需求对应的操作。
可选地，获取与油气领域相关的数据之后，还包括：
对所述数据中属于同一实体的数据进行数据融合操作；所述数据融合操作包括以下至少之一：实体对齐、实体冲突检测、实体冲突消解。
可选地，基于所述本体关系图、所述实体以及所述实体信息，构建油 气领域的知识图谱，包括：
根据所述本体关系图形成知识图谱框架；
通过实体对所述知识图谱框架中相应的本体进行替换，并将所述实体信息依据所述知识图谱框架进行数据整合，得到油气领域的所述知识图谱。
可选地，当所述用户需求为知识图谱修改需求时，基于所述知识图谱，执行与用户需求对应的操作，包括：
获取用户的知识图谱修改指令；所述修改指令包括用户在所述知识图谱中选取的被修改内容以及修改后的目标内容；
根据所述知识图谱修改指令，将所述知识图谱对应的数据库中存储的所述被修改内容修改为所述目标内容。
可选地，当所述用户需求为数据查询需求时，基于所述知识图谱，执行与用户需求对应的操作，包括：
获取用户的数据查询指令；所述数据查找指令包括需进行数据查询的目标对象；
将所述油气领域的知识图谱中与所述目标对象相匹配的实体确定为查询主题，并确定所述查询主题所对应的查询范围；
基于所述查询主题以及所述查询范围，从所述知识图谱以及与所述知识图谱相关的链接内容中查找与所述目标对象对应的查询结果。
可选地，在基于所述查询主题以及所述查询范围，从所述知识图谱以及与所述知识图谱相关的链接内容中查找与所述目标对象对应的查询结果之后，还包括：
从所述知识图谱中获取对应的实体属性与所述查询结果中的实体属性的相似度大于第一预设阈值的实体；
将获取的所述实体的实体信息进行数据推送。
可选地，当所述用户需求为油气藏类比查询需求时，基于所述知识图谱，执行与用户需求对应的操作，包括：
获取用户输入的油气藏类比查询请求；所述油气藏类比查询请求包括待查询油气藏的属性信息；
将所述知识图谱中实体名称属于油气藏的每一实体的属性信息分别与所述待查询油气藏的属性信息在预设油气藏分析维度下进行类比得到类比结果；
根据所述类比结果，确定与所述待查询油气藏的相似度大于第二预设阈值的实体，并将确定的所述实体的属性信息输出。
可选地，当所述用户需求为数据可视化需求时，基于所述知识图谱，执行与用户需求对应的操作，包括：
获取数据可视化指令；所述数据可视化指令包括待可视化的目标数据；
将所述待可视化的目标数据以可视化的方式进行数据展示。
一种油气数据处理装置，包括：
数据获取模块，用于获取与油气领域相关的数据以及油气领域的本体关系图；所述本体关系图包括油气领域的本体以及不同本体之间的关联关系；
数据抽取模块，用于从所述数据中抽取得到油气领域的实体以及对应的实体信息；同一本体对应至少一个实体；
图谱构建模块，用于基于所述本体关系图、所述实体以及所述实体信息，构建油气领域的知识图谱；所述知识图谱包括油气领域的实体、实体与实体之间的关系；
需求处理模块，用于基于所述知识图谱，执行与用户需求对应的操作。
一种油气数据处理设备，包括存储介质和处理器，所述存储介质存储有程序，所述处理器用于运行所述程序，其中，所述程序运行时执行上述的油气数据处理方法。
借由上述技术方案，本发明提供的一种油气数据处理方法及装置，获取与油气领域相关的数据以及油气领域的本体关系图，从所述数据中抽取得到油气领域的实体以及对应的实体信息，基于所述本体关系图、所述实体以及所述实体信息，构建油气领域的知识图谱。即通过本发明，可以构建油气领域的知识图谱，进而可以将知识文献和专家经验汇总到一起，形成完整的油气知识的知识引擎。
上述说明仅是本发明技术方案的概述，为了能够更清楚了解本发明的技术手段，而可依照说明书的内容予以实施，并且为了让本发明的上述和其它目的、特征和优点能够更明显易懂，以下特举本发明的具体实施方式。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1示出了本发明实施例提供的一种油气数据处理方法的方法流程图；
图2示出了本发明实施例提供的一种本体关系图的结构示意图；
图3示出了本发明实施例提供的一种知识图谱的结构示意图；
图4示出了本发明实施例提供的另一种油气数据处理方法的方法流程图；
图5示出了本发明实施例提供的再一种油气数据处理方法的方法流程图；
图6示出了本发明实施例提供的一种数据查询界面的展示图；
图7示出了本发明实施例提供的又一种油气数据处理方法的方法流程图；
图8示出了本发明实施例提供的一种油气藏类比的界面图；
图9示出了本发明实施例提供的另一种油气藏类比的界面图；
图10示出了本发明实施例提供的一种数据可视化展示的界面图；
图11示出了本发明实施例提供的一种油气数据处理装置的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的示例性实施例。虽然附图中显示了本公开的示例性实施例，然而应当理解，可以以各种形式实现本公开而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本公开，并且能够将本公开的范围完整的传达给本领域的技术人员。
本发明实施例提供了一种油气数据处理方法，参照图1，可以包括：
S11、获取与油气领域相关的数据以及油气领域的本体关系图。
具体的，收集油气领域内的应用需求及痛点，包括知识文献和专家经验。油气领域多年积累的文档材料多、生产数据持续时间长，并且油气领域生产作业覆盖范围广，涉及地质结构复杂，类别划分细致。并且除了生产数据的实时记录数据外，大多数知识和数据，存在于报告的纸质材料中，或专家的脑子中。这些数据以非结构化的形式存储在行业研究院、以及各地方公司的资料室里，此处需要对以上数据进行数据收集。
要利用这些数据，就必须理解这些非结构化形式的数据中蕴含的语义，分析各语义单元之间的关系，进而将这些数据结构化，而在结构化之前，首先就需要由行业专家构建油气领域的知识图谱框架，即本体关系图。所述本体关系图包括油气领域的本体以及不同本体之间的关联关系。其中，本体是指一种形式化的，对于共享概念体系的明确而又详细的说明。在对行业知识进行收集和整理的基础上，按照一定的结构进行形式化的表示(本体设计的结构)，从而使知识有序化。本体的结构与行业关系密切，在建立本体结构时，需要包含行业基础概念和类别，并包含各种概念之间的上下级关系。然后根据本体对实体进行扩充。举例来说，本体关系图是指在概念中不同井、发现井、盆地等之间的关系图，后期构建的知识图谱是一种“落地”的实际场景的本体关系图。本体关系图具体可以参照图2。
优选地，在获取与油气领域相关的数据之后，还可以包括：
对所述数据中属于同一实体的数据进行数据融合操作；所述数据融合操作包括实体对齐、实体冲突检测和实体冲突消解中的至少一个。
具体的，由于在油气领域的知识库本体部分是专家梳理，会涉及到例如属于同一油田，但是油田名称不同，或者是属于同一公司，但是公司名称不同的场景，此时需要进行知识融合。知识融合是将属于同一实体但是具有不同名称的数据进行统一。知识融合方面涉及实体对齐、实体冲突检测以及实体冲突消解。在实体对齐和实体冲突消解中，我们用到了完全匹配、部分匹配，其中部分匹配采用了包括最长字符串子序列和一致性计算的方法。其中，实体对齐(Entity Alignment)也被称作实体匹配(Entity Matching)，是指对于异构数据源知识库中的各个实体，找出属于现实世界中的同一实体。实体冲突检测是指检测出某个实体名称对应于多个命名实体对象的情况，实体冲突消解是专门用于解决同名实体产生歧义问题的技术。
S12、从所述数据中抽取得到油气领域的实体以及对应的实体信息。
其中，实体可以以实体名称表示，所述实体信息包括实体属性、实体事件、所述实体与其他实体之间的关联关系。实体和本体均是以节点形式标识，本体包括该本体下所有实体的属性列表，即同一本体对应至少一个实体，实体包括0个到多个属性。本体支持本体管理，即支持根据行业知识和业务需求，自定义本体节点和关系，定义的本体对所有实体有效。
具体的，从数据中进行实体抽取和实体关系抽取。对于非结构化和半结构化文本，在实体抽取和实体关系抽取的过程中，可以采用自动化抽取和人工抽取相结合的方式。在进行自动化抽取时，预先通过针对油气领域非结构化文档定义的领域规则和大量领域相关文档为训练数据，训练得到自动抽取模型。通过自动抽取模型得到的自动抽取结果作为预标注，可以检测出非结构化文本中的部分实体和关系。同时在此基础上，可以进行人工补充标注，将自动抽取的预标注结果和人工补充标注的结果一起作为非结构化和半结构化文本的知识获取内容。
在自动化抽取和人工抽取中，抽取到的实体包括实体名称、实体属性和实体事件，实体名称可以是001号井，当实体为井时，井的实体属性可以是井深、井宽等，当实体为油气藏时，油气藏的实体属性可以是孔隙度、 渗透率、总厚度、净厚度、底层原油密度等。实体事件可以是该实体发生的事件，如001号井在19年2月份发生井喷，在3月份再次发生井喷等。
所述实体与实体之间的关联关系可以是上下级的等级关系，如井包括井生产、井筒、录井、钻井等，作业公司关系，如油气田所属A公司，位置关系等，如001号井位于四川地区。
S13、基于所述本体关系图、所述实体以及所述实体信息，构建油气领域的知识图谱；所述知识图谱包括油气领域的实体、实体与实体之间的关系。
可选的，步骤S13可以包括：
1)根据所述本体关系图形成知识图谱框架。
2)通过实体对所述知识图谱框架中相应的本体进行替换，并将所述实体信息依据所述知识图谱框架进行数据整合，得到油气领域的所述知识图谱。
具体的，本体关系图表征了油气领域的知识图谱框架，通过本体关系图可以行成知识图谱框架，具体可以直接将本体关系图作为知识图谱框架，或者将本体关系图进行一定的图形美化，如规定每一实体的颜色等，得到知识图谱框架。
得到知识图谱框架中，将实体替换了相应的本体，并且将实体信息按照知识图谱框架进行数据整合，得到知识图谱。知识图谱的结构可以参照图3。需要说明的是，图3仅是部分知识图谱示例，并不是完整的知识图谱。
S14、基于所述知识图谱，执行与用户需求对应的操作。
具体的，用户需求可以是更改知识图谱、内容查找、相关内容推荐、油气藏类比分析、数据可视化展示等。
本实施例中，获取与油气领域相关的数据以及油气领域的本体关系图，从所述数据中抽取得到油气领域的实体以及对应的实体信息，基于所述本体关系图、所述实体以及所述实体信息，构建油气领域的知识图谱。即通过本发明，可以构建油气领域的知识图谱，进而可以将知识文献和专家经 验汇总到一起，形成完整的油气知识的知识引擎。
可选的，在上述任一实施例的基础上，当存在不同的用户需求时，步骤S14的具体实现方式不同，现分别介绍。
1、当所述用户需求为知识图谱修改需求时，参照表图4，步骤S14可以包括：
S21、获取用户的知识图谱修改指令。
所述修改指令包括用户在所述知识图谱中选取的被修改内容以及修改后的目标内容。
S22、根据所述知识图谱修改指令，将所述知识图谱对应的数据库中存储的所述被修改内容修改为所述目标内容。
具体的，现有的一些知识图谱的产品都是针对知识图谱的应用进行的，而整个维护都是在后台由技术人员维护，这样会导致真正熟悉业务的使用人员无法直接对知识库进行调整各管理。
进而在本实施例中，形成了油气领域的知识图谱之后，开放业务人员的知识管理的功能，使业务人员能够通过标注导入图谱，并在图谱中修改实体关系、实体名称、实体属性、实体事件等信息。具体可以通过本体对全部同类型的实体进行管理和调整，也可以对具体的实体节点或属性进行添加和删除。
在进行知识图谱的修改时，业务人员可以在知识图谱中确定被修改的内容，然后将被修改内容修改成目标内容，然后包括在所述知识图谱中选取的被修改内容以及修改后的目标内容的知识图谱修改指令会通过特定的数据修改端口发送至知识图谱对应的数据库中，将数据库中的存储的所述被修改内容修改为所述目标内容。
需要说明的是，当需要进行删除操作时，不需要进行一数据到另一数据的修改，而是直接删除需要删除的数据。
2、当所述用户需求为数据查询需求时，参照图5，步骤S14可以包括：
S31、获取用户的数据查询指令。
其中，所述数据查找指令包括需进行数据查询的目标对象。
具体的，本实施例中的知识图谱支持数据查询功能，如用户在查询窗口输入需进行数据查询的目标对象即可。如图5中的查询入口，在文本框中输入红山嘴油田，即是对红山嘴油田的一个数据查询。
S32、将所述油气领域的知识图谱中与所述目标对象相匹配的实体确定为查询主题，并确定所述查询主题所对应的查询范围。
具体的，获取到目标对象之后，可以基于目标对象进行语义分析，得到查询主题和所述查询主题对应的查询范围。查询主题为知识图谱中与该目标对象相匹配的一实体，具体的，上述中的搜索红山嘴油田，红山嘴油田存在于知识图谱中，进而红山嘴油田即为查询主题，由于该目标对象仅包括红山嘴油田，不包括别的内容，所以此处查询主题对应的查询范围即为红山嘴油田的具体内容。
若目标对象为“西北油田所属公司”，则查询主题即为西北油田，所述查询主题对应的查询范围即为所有西北油田所属的公司。
S33、基于所述查询主题以及所述查询范围，从所述知识图谱以及与所述知识图谱相关的链接内容中查找与所述目标对象对应的查询结果。
具体的，当确定了所述查询主题以及所述查询主题对应的查询范围之后，从知识图谱以及知识图谱对应的统一资源定位符URL链接中查找与该查询主题以及查询范围对应的内容。举例来说，参照图6，目标对象为红山嘴油田，查询主题对应的查询范围即为红山嘴油田的具体内容，查询结果如图6中的基于知识图谱的查询结果界面，查询结果包括海拔、地址区域、维度、油气田名称等内容。若查询内容为西北油田所属公司，则查询结果可以为A公司，即具体的公司名称。
可选的，在本实施例的基础上，步骤S33之后，还可以包括：
从所述知识图谱中获取对应的实体属性与所述查询结果中的实体属性的相似度大于第一预设阈值的实体，将获取的所述实体的实体信息进行数据推送。
具体的，除了上述能够实现数据的精准查询之外，还能够实现根据查询主题和查询主题对应的待查询数据对相关主题进行知识推荐，推荐可以 有相关的剖面图、构造图等领域内重要图片数据。
在进行数据推荐时，首先获取查询结果中的实体属性，然后查找与该实体属性中的部分或全部的相似度较大的实体，即相似度大于第一预设阈值，并以剖面图、构造图等方式进行展示。
仍以待查询内容为红山嘴油田为例，参照图6中的相关图片推荐中的知识卡片中的内容，有构造剖面图、连井剖面图、构造位置图等。
3、当所述用户需求为油气藏类比查询需求时，参照图7，步骤S14可以包括：
S41、获取用户输入的油气藏类比查询请求。
其中，所述油气藏类比查询请求包括待查询油气藏的属性信息。
具体的，本实施例为油气藏类比应用，油气藏类比应用是根据知识图谱，对油气藏的各个维度进行相似性计算，根据计算分值推荐各个油气藏的类比结果，用于油气藏的深入分析，和新油气藏的发现。
具体的，本实施例适用于两种使用场景，一种是当发现新油气藏时，对新油气藏的投入产出比有一个大概的了解。另一种是对已有的油气藏进行深入的类比分析，本实施例主要适用于第一种使用场景。
当发现新油气藏时，首先获取通过测量得到的新油气藏，也就是待查询油气藏的属性信息，如孔隙度、渗透率和总厚度等数据。
S42、将所述知识图谱中实体名称属于油气藏的每一实体的属性信息分别与所述待查询油气藏的属性信息在预设油气藏分析维度下进行类比得到类比结果。
具体的，首先确定预设油气藏分析维度，预设油气藏分析维度包括：孔隙度、渗透率和总厚度等。
在已知预设油气藏分析维度之后，将新油气藏的属性信息与已开发的油气藏的属性信息在每一预设油气藏分析维度进行分析，得到每一预设油气藏分析维度下的分析结果。具体的分析结果可以参照图8。分析结果即为图8中的类比结果，类比结果包括正常、偏大和偏小三种结果其他信息。
S43、根据所述类比结果，确定与所述待查询油气藏的相似度大于第 二预设阈值的实体，并将确定的所述实体的属性信息输出。
具体的，当确定出每一所述预设油气藏分析维度下的分析结果之后，可以根据分析结果计算得到新油气藏与已开发油气藏的相似度，筛选出相似度较大，即大于第二预设阈值的目标油气藏。具体结果可以参照图9。图9中与该新油气藏的相似度由大到小的油气藏分别为兴隆台、红032井区克下组等。此时输出每一目标油气藏的属性信息，如油气类型、孔隙度和渗透率等。
4、当所述用户需求为数据可视化需求时，步骤S14可以包括：
获取数据可视化指令，将所述待可视化的目标数据以可视化的方式进行数据展示。所述数据可视化指令包括待可视化的目标数据；
具体的，本实施例支持数据可视化展示，当需要对一数据进行可视化展示时，首先确定用户需要展示的数据，即目标数据，然后通过图表等方式进行可视化展示即可。可视化展示图可以如图10中的渗透率频率分布图中的柱形图。
通过本实施例，实现了数据的管理和应用流程体系，方便了业务人员的知识图谱的修改和使用。
另外，将本实施例与上述实施例进行结合，形成了油气领域知识的收集、知识图谱的生成、管理和应用的一条闭环链路，实现对油气知识有效管理和应用的知识共享平台。
可选的，在上述油气数据处理方法的实施例的基础上，本发明的另一实施例提供了一种油气数据处理装置，参照图11，可以包括：
数据获取模块101，用于获取与油气领域相关的数据以及油气领域的本体关系图；所述本体关系图包括油气领域的本体以及不同本体之间的关联关系；
数据抽取模块102，用于从所述数据中抽取得到油气领域的实体以及对应的实体信息；同一本体对应至少一个实体；
图谱构建模块103，用于基于所述本体关系图、所述实体以及所述实体信息，构建油气领域的知识图谱；所述知识图谱包括油气领域的实体、 实体与实体之间的关系；
需求处理模块104，用于基于所述知识图谱，执行与用户需求对应的操作。
可选的，在本实施例的基础上，还包括：数据融合模块，用于对所述数据中属于同一实体的数据进行数据融合操作；所述数据融合操作包括以下至少之一：实体对齐、实体冲突检测、实体冲突消解。
可选的，在本实施例的基础上，图谱构建模块103用于基于所述本体关系图和所述实体信息，构建油气领域的知识图谱时，具体用于：
根据所述本体关系图形成知识图谱框架，通过实体对所述知识图谱框架中相应的本体进行替换，并将所述实体信息依据所述知识图谱框架进行数据整合，得到油气领域的所述知识图谱。
可选的，在本实施例的基础上，当所述用户需求为知识图谱修改需求时，需求处理模块104可以包括：
修改指令获取子模块，用于获取用户的知识图谱修改指令；所述修改指令包括用户在所述知识图谱中选取的被修改内容以及修改后的目标内容；
数据修改子模块，用于根据所述知识图谱修改指令，将所述知识图谱对应的数据库中存储的所述被修改内容修改为所述目标内容。
可选的，在本实施例的基础上，当所述用户需求为数据查询需求时，需求处理模块104可以包括：
查询指令获取子模块，用于获取用户的数据查询指令；所述数据查找指令包括需进行数据查询的目标对象；
查询数据分析子模块，用于将所述油气领域的知识图谱中与所述目标对象相匹配的实体确定为查询主题，并确定所述查询主题所对应的查询范围；
数据查询子模块，用于基于所述查询主题以及所述查询范围，从所述知识图谱以及与所述知识图谱相关的链接内容中查找与所述目标对象对应的查询结果。
可选的，在本实施例的基础上，还包括：
数据推送子模块，用于从所述知识图谱中获取对应的实体属性与所述查询结果中的实体属性的相似度大于第一预设阈值的实体，将获取的所述实体的实体信息进行数据推送。
可选的，在本实施例的基础上，当所述用户需求为油气藏类比查询需求时，需求处理模块104可以包括：
类比请求接收子模块，用于获取用户输入的油气藏类比查询请求；所述油气藏类比查询请求包括待查询油气藏的属性信息；
数据分析子模块，用于将所述知识图谱中实体名称属于油气藏的每一实体的属性信息分别与所述待查询油气藏的属性信息在预设油气藏分析维度下进行类比得到类比结果；
数据确定子模块，用于根据所述类比结果，确定与所述待查询油气藏的相似度大于第二预设阈值的实体，并将确定的所述实体的属性信息输出。
可选的，在本实施例的基础上，当所述用户需求为数据可视化需求时，需求处理模块104可以包括：
数据可视化子模块，用于获取数据可视化指令，将所述待可视化的目标数据以可视化的方式进行数据展示。
所述数据可视化指令包括待可视化的目标数据。
本实施例中，获取与油气领域相关的数据以及油气领域的本体关系图，从所述数据中抽取得到油气领域的实体以及对应的实体信息，基于所述本体关系图、所述实体以及所述实体信息，构建油气领域的知识图谱。即通过本发明，可以构建油气领域的知识图谱，进而可以将知识文献和专家经验汇总到一起，形成完整的油气知识的知识引擎。
需要说明的是，本实施例中的各个模块和子模块的工作过程，请参照上述实施例中的相应说明，在此不再赘述。
所述油气数据处理装置包括处理器和存储器，上述数据获取模块、数据抽取模块、图谱构建模块和需求处理模块等均作为程序单元存储在存储器中，由处理器执行存储在存储器中的上述程序单元来实现相应的功能。
处理器中包含内核，由内核去存储器中调取相应的程序单元。内核可以设置一个或以上，通过调整内核参数来实现将知识文献和专家经验汇总到一起，形成完整的油气知识的知识引擎。
存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)，存储器包括至少一个存储芯片。
本发明实施例提供了一种存储介质，其上存储有程序，该程序被处理器执行时实现所述油气数据处理方法。
本发明实施例提供了一种处理器，所述处理器用于运行程序，其中，所述程序运行时执行所述油气数据处理方法。
本发明实施例提供了一种设备，设备包括处理器、存储器及存储在存储器上并可在处理器上运行的程序，处理器执行程序时实现以下步骤：
一种油气数据处理方法，包括：
获取与油气领域相关的数据以及油气领域的本体关系图；所述本体关系图包括油气领域的本体以及不同本体之间的关联关系；
从所述数据中抽取得到油气领域的实体以及对应的实体信息；同一本体对应至少一个实体；
基于所述本体关系图、所述实体以及所述实体信息，构建油气领域的知识图谱；所述知识图谱包括油气领域的实体、实体与实体之间的关系；
基于所述知识图谱，执行与用户需求对应的操作。
进一步，获取与油气领域相关的数据之后，还包括：
对所述数据中属于同一实体的数据进行数据融合操作；所述数据融合操作包括以下至少之一：实体对齐、实体冲突检测、实体冲突消解。
进一步，基于所述本体关系图、所述实体以及所述实体信息，构建油气领域的知识图谱，包括：
根据所述本体关系图形成知识图谱框架；
通过实体对所述知识图谱框架中相应的本体进行替换，并将所述实体信息依据所述知识图谱框架进行数据整合，得到油气领域的所述知识图谱。
进一步，当所述用户需求为知识图谱修改需求时，基于所述知识图谱，执行与用户需求对应的操作，包括：
获取用户的知识图谱修改指令；所述修改指令包括用户在所述知识图谱中选取的被修改内容以及修改后的目标内容；
根据所述知识图谱修改指令，将所述知识图谱对应的数据库中存储的所述被修改内容修改为所述目标内容。
进一步，当所述用户需求为数据查询需求时，基于所述知识图谱，执行与用户需求对应的操作，包括：
获取用户的数据查询指令；所述数据查找指令包括需进行数据查询的目标对象；
将所述油气领域的知识图谱中与所述目标对象相匹配的实体确定为查询主题，并确定所述查询主题所对应的查询范围；
基于所述查询主题以及所述查询范围，从所述知识图谱以及与所述知识图谱相关的链接内容中查找与所述目标对象对应的查询结果。
进一步，在基于所述查询主题以及所述查询范围，从所述知识图谱以及与所述知识图谱相关的链接内容中查找与所述目标对象对应的查询结果之后，还包括：
从所述知识图谱中获取对应的实体属性与所述查询结果中的实体属性的相似度大于第一预设阈值的实体；
将获取的所述实体的实体信息进行数据推送。
进一步，当所述用户需求为油气藏类比查询需求时，基于所述知识图谱，执行与用户需求对应的操作，包括：
获取用户输入的油气藏类比查询请求；所述油气藏类比查询请求包括待查询油气藏的属性信息；
将所述知识图谱中实体名称属于油气藏的每一实体的属性信息分别与所述待查询油气藏的属性信息在预设油气藏分析维度下进行类比得到类比结果；
根据所述类比结果，确定与所述待查询油气藏的相似度大于第二预设 阈值的实体，并将确定的所述实体的属性信息输出。
进一步，当所述用户需求为数据可视化需求时，基于所述知识图谱，执行与用户需求对应的操作，包括：
获取数据可视化指令；所述数据可视化指令包括待可视化的目标数据；
将所述待可视化的目标数据以可视化的方式进行数据展示。
本文中的设备可以是服务器、PC、PAD、手机等。
本申请还提供了一种计算机程序产品，当在数据处理设备上执行时，适于执行初始化有如下方法步骤的程序：
一种油气数据处理方法，包括：
获取与油气领域相关的数据以及油气领域的本体关系图；所述本体关系图包括油气领域的本体以及不同本体之间的关联关系；
从所述数据中抽取得到油气领域的实体以及对应的实体信息；同一本体对应至少一个实体；
基于所述本体关系图、所述实体以及所述实体信息，构建油气领域的知识图谱；所述知识图谱包括油气领域的实体、实体与实体之间的关系；
基于所述知识图谱，执行与用户需求对应的操作。
进一步，获取与油气领域相关的数据之后，还包括：
对所述数据中属于同一实体的数据进行数据融合操作；所述数据融合操作包括以下至少之一：实体对齐、实体冲突检测、实体冲突消解。
进一步，基于所述本体关系图、所述实体以及所述实体信息，构建油气领域的知识图谱，包括：
根据所述本体关系图形成知识图谱框架；
通过实体对所述知识图谱框架中相应的本体进行替换，并将所述实体信息依据所述知识图谱框架进行数据整合，得到油气领域的所述知识图谱。
进一步，当所述用户需求为知识图谱修改需求时，基于所述知识图谱，执行与用户需求对应的操作，包括：
获取用户的知识图谱修改指令；所述修改指令包括用户在所述知识图谱中选取的被修改内容以及修改后的目标内容；
根据所述知识图谱修改指令，将所述知识图谱对应的数据库中存储的所述被修改内容修改为所述目标内容。
进一步，当所述用户需求为数据查询需求时，基于所述知识图谱，执行与用户需求对应的操作，包括：
获取用户的数据查询指令；所述数据查找指令包括需进行数据查询的目标对象；
将所述油气领域的知识图谱中与所述目标对象相匹配的实体确定为查询主题，并确定所述查询主题所对应的查询范围；
基于所述查询主题以及所述查询范围，从所述知识图谱以及与所述知识图谱相关的链接内容中查找与所述目标对象对应的查询结果。
进一步，在基于所述查询主题以及所述查询范围，从所述知识图谱以及与所述知识图谱相关的链接内容中查找与所述目标对象对应的查询结果之后，还包括：
从所述知识图谱中获取对应的实体属性与所述查询结果中的实体属性的相似度大于第一预设阈值的实体；
将获取的所述实体的实体信息进行数据推送。
进一步，当所述用户需求为油气藏类比查询需求时，基于所述知识图谱，执行与用户需求对应的操作，包括：
获取用户输入的油气藏类比查询请求；所述油气藏类比查询请求包括待查询油气藏的属性信息；
将所述知识图谱中实体名称属于油气藏的每一实体的属性信息分别与所述待查询油气藏的属性信息在预设油气藏分析维度下进行类比得到类比结果；
根据所述类比结果，确定与所述待查询油气藏的相似度大于第二预设阈值的实体，并将确定的所述实体的属性信息输出。
进一步，当所述用户需求为数据可视化需求时，基于所述知识图谱，执行与用户需求对应的操作，包括：
获取数据可视化指令；所述数据可视化指令包括待可视化的目标数据；
将所述待可视化的目标数据以可视化的方式进行数据展示。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash  RAM)。存储器是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白，本申请的实施例可提供为方法、系统或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
以上仅为本申请的实施例而已，并不用于限制本申请。对于本领域技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本申请的权利要求范围之内。

Claims (10)

  1. 一种油气数据处理方法，其特征在于，包括：
    获取与油气领域相关的数据以及油气领域的本体关系图；所述本体关系图包括油气领域的本体以及不同本体之间的关联关系；
    从所述数据中抽取得到油气领域的实体以及对应的实体信息；同一本体对应至少一个实体；
    基于所述本体关系图、所述实体以及所述实体信息，构建油气领域的知识图谱；所述知识图谱包括油气领域的实体、实体与实体之间的关系；
    基于所述知识图谱，执行与用户需求对应的操作。
  2. 根据权利要求1所述的油气数据处理方法，其特征在于，获取与油气领域相关的数据之后，还包括：
    对所述数据中属于同一实体的数据进行数据融合操作；所述数据融合操作包括以下至少之一：实体对齐、实体冲突检测、实体冲突消解。
  3. 根据权利要求1所述的油气数据处理方法，其特征在于，基于所述本体关系图、所述实体以及所述实体信息，构建油气领域的知识图谱，包括：
    根据所述本体关系图形成知识图谱框架；
    通过实体对所述知识图谱框架中相应的本体进行替换，并将所述实体信息依据所述知识图谱框架进行数据整合，得到油气领域的所述知识图谱。
  4. 根据权利要求1所述的油气数据处理方法，其特征在于，当所述用户需求为知识图谱修改需求时，基于所述知识图谱，执行与用户需求对应的操作，包括：
    获取用户的知识图谱修改指令；所述修改指令包括用户在所述知识图谱中选取的被修改内容以及修改后的目标内容；
    根据所述知识图谱修改指令，将所述知识图谱对应的数据库中存储的所述被修改内容修改为所述目标内容。
  5. 根据权利要求1所述的油气数据处理方法，其特征在于，当所述用户需求为数据查询需求时，基于所述知识图谱，执行与用户需求对应的操 作，包括：
    获取用户的数据查询指令；所述数据查找指令包括需进行数据查询的目标对象；
    将所述油气领域的知识图谱中与所述目标对象相匹配的实体确定为查询主题，并确定所述查询主题所对应的查询范围；
    基于所述查询主题以及所述查询范围，从所述知识图谱以及与所述知识图谱相关的链接内容中查找与所述目标对象对应的查询结果。
  6. 根据权利要求5所述的油气数据处理方法，其特征在于，在基于所述查询主题以及所述查询范围，从所述知识图谱以及与所述知识图谱相关的链接内容中查找与所述目标对象对应的查询结果之后，还包括：
    从所述知识图谱中获取对应的实体属性与所述查询结果中的实体属性的相似度大于第一预设阈值的实体；
    将获取的所述实体的实体信息进行数据推送。
  7. 根据权利要求1所述的油气数据处理方法，其特征在于，当所述用户需求为油气藏类比查询需求时，基于所述知识图谱，执行与用户需求对应的操作，包括：
    获取用户输入的油气藏类比查询请求；所述油气藏类比查询请求包括待查询油气藏的属性信息；
    将所述知识图谱中实体名称属于油气藏的每一实体的属性信息分别与所述待查询油气藏的属性信息在预设油气藏分析维度下进行类比得到类比结果；
    根据所述类比结果，确定与所述待查询油气藏的相似度大于第二预设阈值的实体，并将确定的所述实体的属性信息输出。
  8. 根据权利要求1所述的油气数据处理方法，其特征在于，当所述用户需求为数据可视化需求时，基于所述知识图谱，执行与用户需求对应的操作，包括：
    获取数据可视化指令；所述数据可视化指令包括待可视化的目标数据；
    将所述待可视化的目标数据以可视化的方式进行数据展示。
  9. 一种油气数据处理装置，其特征在于，包括：
    数据获取模块，用于获取与油气领域相关的数据以及油气领域的本体关系图；所述本体关系图包括油气领域的本体以及不同本体之间的关联关系；
    数据抽取模块，用于从所述数据中抽取得到油气领域的实体以及对应的实体信息；同一本体对应至少一个实体；
    图谱构建模块，用于基于所述本体关系图、所述实体以及所述实体信息，构建油气领域的知识图谱；所述知识图谱包括油气领域的实体、实体与实体之间的关系；
    需求处理模块，用于基于所述知识图谱，执行与用户需求对应的操作。
  10. 一种油气数据处理设备，其特征在于，包括存储介质和处理器，所述存储介质存储有程序，所述处理器用于运行所述程序，其中，所述程序运行时执行如权利要求1-8中任一所述的油气数据处理方法。
PCT/CN2020/097024 2019-09-18 2020-06-19 油气数据处理方法及装置 WO2021051909A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910880997.7A CN112528032A (zh) 2019-09-18 2019-09-18 油气数据处理方法及装置
CN201910880997.7 2019-09-18

Publications (1)

Publication Number Publication Date
WO2021051909A1 true WO2021051909A1 (zh) 2021-03-25

Family

ID=74883921

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/097024 WO2021051909A1 (zh) 2019-09-18 2020-06-19 油气数据处理方法及装置

Country Status (2)

Country Link
CN (1) CN112528032A (zh)
WO (1) WO2021051909A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107491555A (zh) * 2017-09-01 2017-12-19 北京纽伦智能科技有限公司 知识图谱构建方法和系统
CN108549731A (zh) * 2018-07-11 2018-09-18 中国电子科技集团公司第二十八研究所 一种基于本体模型的知识图谱构建方法
CN109508381A (zh) * 2018-09-29 2019-03-22 北京国双科技有限公司 知识图谱的处理方法及装置
CN110019842A (zh) * 2018-09-30 2019-07-16 北京国双科技有限公司 一种建立知识图谱的方法及装置
CN110222199A (zh) * 2019-06-20 2019-09-10 青岛大学 一种基于本体和多种神经网络集成的人物关系图谱构建方法

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9779141B2 (en) * 2013-12-14 2017-10-03 Microsoft Technology Licensing, Llc Query techniques and ranking results for knowledge-based matching
CN109145122A (zh) * 2018-08-02 2019-01-04 北京仿真中心 一种产品知识图谱构建和查询方法及系统
CN109492077B (zh) * 2018-09-29 2020-09-29 北京智通云联科技有限公司 基于知识图谱的石化领域问答方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107491555A (zh) * 2017-09-01 2017-12-19 北京纽伦智能科技有限公司 知识图谱构建方法和系统
CN108549731A (zh) * 2018-07-11 2018-09-18 中国电子科技集团公司第二十八研究所 一种基于本体模型的知识图谱构建方法
CN109508381A (zh) * 2018-09-29 2019-03-22 北京国双科技有限公司 知识图谱的处理方法及装置
CN110019842A (zh) * 2018-09-30 2019-07-16 北京国双科技有限公司 一种建立知识图谱的方法及装置
CN110222199A (zh) * 2019-06-20 2019-09-10 青岛大学 一种基于本体和多种神经网络集成的人物关系图谱构建方法

Also Published As

Publication number Publication date
CN112528032A (zh) 2021-03-19

Similar Documents

Publication Publication Date Title
CN107609052B (zh) 一种基于语义三角的领域知识图谱的生成方法及装置
US11734233B2 (en) Method for classifying an unmanaged dataset
US8533152B2 (en) System and method for data provenance management
US8898104B2 (en) Auto-mapping between source and target models using statistical and ontology techniques
CN113779261B (zh) 知识图谱的质量评价方法、装置、计算机设备及存储介质
US20130232158A1 (en) Data subscription
CN116049379A (zh) 知识推荐方法、装置、电子设备和存储介质
CN111475604A (zh) 数据处理方法及装置
Polpinij et al. Internet usage patterns mining from firewall event logs
Rao et al. Role of exploratory data analysis in data science
Nimmagadda et al. Big-data integration methodologies for effective management and data mining of petroleum digital ecosystems
US20110258007A1 (en) Data subscription
Bernard et al. Theseus: A framework for managing knowledge graphs about geographical divisions and their evolution
WO2021051909A1 (zh) 油气数据处理方法及装置
Maynard et al. Change management for metadata evolution
Jabeen et al. Divided we stand out! forging cohorts for numeric outlier detection in large scale knowledge graphs (conod)
Margitus et al. RDF versus attributed graphs: The war for the best graph representation
Kim et al. Construction of disaster knowledge graphs to enhance disaster resilience
CN109101656B (zh) 一种基于本体的关联数据质量评估方法
Gunasundari et al. Removing non-informative blocks from the web pages
Lanasri et al. Crumbs4Cube: Turning Breadcrumbs into Smart Enriched Data Cubes.
Shah et al. Unleashing the Potential of Relative Permeability Using Artificial Intelligence
KR101526312B1 (ko) 현안 키워드 대응 연구개발 정보 서비스 시스템 및 방법
CN115687623B (zh) 一种工业数字孪生数据空间构建方法及系统
EP3683759A1 (en) Resource exploitation management system, method and program product

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20865159

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20865159

Country of ref document: EP

Kind code of ref document: A1