Fracture-vuggy carbonate reservoir reasoning method and device based on knowledge graph

Abstract

The invention discloses a fracture-vug type carbonate rock fracture-vug reservoir reasoning method and device based on a knowledge graph. The device comprises an ontology construction module, a knowledge extraction module, a knowledge fusion module, a business rule module, a reasoning model module and a reservoir comprehensive evaluation model. Wherein the business rules comprise an oil reservoir analysis rule, a reservoir physical property rule, a logging interpretation rule and the like, the calculation model is a carbonate reservoir comprehensive reasoning model, and comprehensive reasoning analysis is performed on each fracture-cavity reservoir by combining the business rules of the business rule module with a carbonate fracture-cavity reservoir comprehensive reasoning method. And generating a carbonate rock fracture-cavity reservoir optimization scheme. According to the method, the exploration target optimization working efficiency of the carbonate fractured-vuggy reservoir can be improved, the pertinence, accuracy and timeliness of exploration decision making are improved, the exploration risk is reduced, and the decision making efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the research field of seismic interpretation in oil and gas exploration in oil fields, and in particular to a fracture-cavity carbonate reservoir reasoning method and device based on a knowledge graph. Background Art

[0002] At present, against the backdrop of deteriorating quality of oil and gas resources, diversified exploration targets, and complex development objects, exploration and development technologies are not adaptable and the exploration and development business of the oil industry faces many technical challenges.

[0003] Reservoir inference technology for fracture-cavity carbonate reservoirs has always been a key research topic of concern at home and abroad. Carbonate fracture-cavity reservoirs are controlled by tectonic-karst action, with fractures and caves as the main reservoir types. The reservoirs are deeply buried, generally exceeding 5000m, with strong vertical and lateral heterogeneity, rapid lateral changes, and extremely complex oil-water relationships. Due to the strong heterogeneity of carbonate fracture-cavity reservoirs, reservoir inference faces great difficulties.

[0004] In current practical work, conventional fracture-vuggy reservoir prediction and inference generally use a single parameter for description and prediction. The comprehensive laws of high-quality reservoirs and knowledge of sedimentation, paleogeology, well logging, etc. are difficult to discover. It is urgent to introduce new methods and new applications to quickly realize the accurate evaluation of fracture-vuggy reservoirs. Summary of the invention

[0005] In view of the technical defects and technical drawbacks in the prior art, an embodiment of the present invention provides a method and device for applying knowledge graphs to perform carbonate fracture-vuggy reservoir reasoning, which overcomes the above problems or at least partially solves the above problems.

[0006] An embodiment of the present invention provides, on the one hand, a knowledge graph-based reasoning method for fracture-cavity carbonate fracture-cavity reservoirs, which includes:

[0007] Constructing the ontology of carbonate reservoir based on the pre-acquired interpretation result data and single well data;

[0008] Extracting knowledge based on the ontology;

[0009] Integrate the extracted knowledge;

[0010] Building business rules based on the integrated knowledge; and

[0011] Based on the business rules, an inference model of the carbonate fracture-vuggy reservoir is established and an inference result is obtained.

[0012] Another aspect of the present invention provides a knowledge graph-based reasoning device for fracture-cavity carbonate fracture-cavity reservoirs, which includes:

[0013] An ontology construction module, used to construct an ontology of carbonate reservoirs based on pre-acquired interpretation results data and single well data;

[0014] A knowledge extraction module, used for extracting knowledge based on the ontology;

[0015] Knowledge fusion module, used to fuse the extracted knowledge;

[0016] A business rules module, used to construct business rules based on the integrated knowledge; and

[0017] The inference model module is used to establish the inference model of the carbonate fracture-vuggy reservoir based on the business rules and obtain the inference results.

[0018] Another aspect of the embodiments of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the program implements the above method when executed by a processor.

[0019] Another aspect of an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the program.

[0020] The embodiment of the present invention applies the research on knowledge graph technology to the comprehensive reservoir reasoning analysis of carbonate oil reservoir well location demonstration, realizes the combination of knowledge graph and intelligent reasoning model, and conducts intelligent evaluation of fracture-cavity carbonate reservoirs, thereby improving the efficiency of optimizing exploration targets for carbonate fracture-cavity oil reservoirs, enhancing the pertinence, accuracy and timeliness of exploration decisions, reducing exploration risks and improving decision-making efficiency.

[0021] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structure described in the written description, claims, and drawings.

[0022] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0024] Figure 1 A flow chart of a fracture-cavity carbonate reservoir reasoning method provided in an embodiment of the present invention;

[0025] Figure 2Construct a schematic diagram for the carbonate reservoir itself;

[0026] Figure 3 This is a schematic diagram of the inference rules for carbonate reservoirs;

[0027] Figure 4 A structural diagram of a fracture-vuggy carbonate reservoir inference device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0029] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0030] During the research, the inventor found that with the continuous development of artificial intelligence cognitive computing technology, research on reservoir prediction methods based on new technical means has been carried out at home and abroad, and certain results have been achieved. However, to realize the deep application of artificial intelligence technology in China's petroleum industry, there are technical difficulties such as the lack of knowledge graph system in the field of oil and gas exploration and development, and the imperfect intelligent application technology and platform functions. Therefore, the present invention focuses on how to use knowledge graph technology, combined with knowledge rules in various aspects such as sedimentation and well logging, to innovate and form a knowledge graph-based fracture-cavity carbonate reservoir reasoning method, leading to changes in the way exploration and development decisions are made.

[0031] With the continuous deepening of the concepts of efficient exploration, profitable development, and scientific and technological innovation, carbonate fracture-vuggy reservoirs have become an extremely important oil and gas resource in China. In order to fully realize new oil and gas discoveries and support the strategic succession of resources in the western region, it is necessary to actively track forward-looking technologies, accelerate the application of knowledge graphs, and provide effective supply for upstream sustainable development.

[0032] Currently, carbonate fracture-vuggy reservoir prediction generally uses single seismic information for description and prediction. There is a lack of technical means to conduct comprehensive reasoning on reservoirs by combining multi-dimensional knowledge such as logging, sedimentation and expert experience, and the accuracy of identification and reasoning of high-quality reservoirs is poor.

[0033] In order to solve the problems existing in the prior art, the present invention takes into account the characteristics of carbonate fracture-vuggy oil reservoirs, combines knowledge of sedimentation, paleogeology, well logging and expert experience, establishes an inference method for high-quality carbonate reservoirs, and provides support for the formulation of well location demonstration plans.

[0034] This embodiment provides a fracture-cavity carbonate fracture-cavity reservoir reasoning method based on knowledge graph, such as Figure 1 As shown, the following steps are included:

[0035] Step 100, obtaining interpretation result data and single well data as input data.

[0036] The interpretation results data may include: seismic interpretation data of control layer and target layer, oil-water trend surface data, paleo-geomorphology data, fracture-cavity carving data; the single well data may include: logging curve, logging interpretation data, single well production data, well basic data and FMI imaging logging data, etc.;

[0037] Step 200: constructing the ontology of the carbonate reservoir based on the interpretation result data and the single well data.

[0038] Specifically, the scope and boundaries of the carbonate reservoir ontology are determined based on all the data in the interpretation results data and the single well data. Based on all the data to which reasoning can be applied, the business concepts of carbonate reservoir research are defined. A combination of top-down and bottom-up approaches are used to establish all the concepts required for the application of carbonate reservoir research business within the scope shown by the boundaries, including concepts such as wells, completed layers, production layers, oil fields, and blocks.

[0039] The attributes of the ontology refer to the related attributes of the entity corresponding to the ontology concept, such as: well number, well coordinates, core filling altitude, completed well depth, completion date and other attribute information. Attributes can include intrinsic attributes and extrinsic attributes. Intrinsic attributes such as well coordinates, core filling altitude, completed well depth, etc., and extrinsic attributes such as the block and oil and gas field where the well is located; Figure 2 shown.

[0040] Step 300: extract knowledge based on the ontology.

[0041] Specifically, the knowledge extraction can be divided into structured data knowledge extraction and unstructured data knowledge extraction.

[0042] The process of structured data knowledge extraction is as follows: mapping the structured data table in the input data to the concept of the ontology. The structured data table is, for example, the well logging interpretation data, single well production data, well basic data, etc. in the input data. Specifically, mapping the records of the structured data table to the entity of the concept, and mapping the values ​​in the structured data table to the URI (Uniform Resource Identifier) ​​of the entity or the attribute value of the entity;

[0043] The process of extracting knowledge from unstructured data is as follows: extracting entities and relationships based on statistical methods and natural language processing methods based on acquisition rules (such as regular expression rules or manually written rules) or dictionaries to obtain unstructured knowledge. Ontology refers to concepts, such as "well"; entities refer to specific values ​​under the concept, such as "well A"; relationships refer to the relationship between entities, such as "well A belongs to block A", and the key between the two is the relationship of "belonging to". Step 400: Integrate the extracted knowledge.

[0044] The specific fusion process may include: performing concept alignment and entity alignment on the knowledge. The concept alignment process is, for example, using manual or technical means to align the extracted knowledge with the concepts of the ontology; the entity alignment process is, for example, using manual or technical means to identify the same entity expressed in different names and perform entity alignment.

[0045] Step 500, construct business rules based on the fused knowledge. The ontology and attributes of the business rules include, for example, reservoir bottom boundary, oil-water trend surface, paleo-geomorphology, porosity, saturation and rule description. Specifically, the knowledge information of fracture-cavity carbonate reservoirs is extracted using statistical and natural language processing methods. For example, relationship extraction is performed based on the BERT model, and a large amount of language knowledge learned during BERT pre-training is used to perform relationship extraction. Comprehensive reasoning business rules are formulated using expert experience combined with knowledge information, and the formulated rules are stored in the knowledge graph; Figure 3 As shown, the business rules include, for example: oil reservoir evaluation rules, reservoir physical property rules, and well logging interpretation rules.

[0046] Step 600: Use the business rules in the graph to establish an inference model for carbonate fracture-vuggy reservoirs and obtain inference results.

[0047] Specifically, the seam hole carving data in the interpretation result data is imported as boundary data, the reasoning model is triggered and the rule indicators are used to perform reasoning calculations, and the reasoning result is output after the optimal reasoning scheme is obtained.

[0048] Step 700: Perform inference evaluation on the fracture-vuggy carbonate reservoir based on the inference result.

[0049] Specifically, through the reservoir reasoning model of step 600, the reasoning results are automatically generated, and the carbonate fracture-cave reservoirs are divided into Class I, Class II, and Class III reservoirs. Class I reservoirs have the best quality and are the best effective reservoirs for obtaining high-yield oil and gas flows.

[0050] The method described in this embodiment realizes intelligent evaluation of fracture-cavity carbonate reservoirs based on the knowledge graph fracture-cavity carbonate reservoir reasoning method, improves the accuracy of exploration target selection of carbonate fracture-cavity oil reservoirs, and provides support for the formulation of well location demonstration plans.

[0051] Specifically, the following technical effects are achieved:

[0052] 1. The present invention makes full use of the results of sedimentation, well logging, reservoir properties and other achievements in the oil and gas exploration and development research process and the knowledge and experience of experts to establish a carbonate fracture-vuggy reservoir reasoning model, comprehensively considers the business needs of seismic, geological, well logging and other aspects, and uses knowledge graph technology to establish a new automatic evaluation model for carbonate fracture-vuggy reservoirs, improve the efficiency of optimizing exploration targets for carbonate fracture-vuggy reservoirs, enhance the pertinence, accuracy and timeliness of exploration decisions, reduce exploration risks and improve decision-making efficiency;

[0053] 2. The present invention changes the previous mode of carbonate fracture-cave reservoir prediction, which generally only uses single seismic information for description and prediction, and constructs a comprehensive evaluation system that combines multiple business knowledge such as geology and well logging and expert experience, filling the gap in the field of reservoir evaluation based on knowledge graphs for oilfield enterprises;

[0054] 3. Under the premise of ensuring stable operation, the present invention comprehensively considers the realization of comprehensive reasoning of multiple professional businesses such as seismic, geology and well logging, further improves the scientificity and rationality of reservoir prediction, and achieves the goal of reducing exploration risks and improving decision-making efficiency;

[0055] 4. The present invention fully exploits the value of massive oilfield geology, logging and real-time production data, uses intelligent modeling technology to establish a carbonate fracture-vuggy reservoir inference model, and conducts beneficial exploration in the application scenarios of oilfield data and knowledge graphs;

[0056] 5. The present invention is based on seismic, oilfield geology, well logging and other data, and combines business rules (reservoir evaluation rules, reservoir physical property rules, well logging interpretation rules, etc.) to construct a carbonate fracture-cavity reservoir evaluation reasoning model, thereby realizing a new automatic evaluation model for carbonate fracture-cavity reservoirs. The entire method and process have better interpretation and generalization capabilities.

[0057] In order to verify the above effects, the following experimental examples are provided:

[0058] Step 1: First, screen and analyze the comprehensive reasoning indicators of carbonate fracture-vuggy reservoirs; based on the principle of effectively implementing high-quality reservoirs, construct comprehensive evaluation indicators for carbonate fracture-vuggy reservoirs, combine logging and production information, clarify the relationship between high-quality carbonate fracture-vuggy reservoirs and reservoir, oil reservoir and other characteristics, establish intelligent processing methods, extract sensitive attributes of carbonate fracture-vuggy reservoirs, such as oil-bottom interface, porosity, oil-source fracture distance, reservoir size, etc., and optimize these sensitive attributes through prior knowledge and expert experience.

[0059] Step 2: Based on professional books on petroleum exploration and development, petroleum dictionaries and other materials, and based on the technical specifications of exploration and development knowledge graphs, the ontology and relationships of carbonate fracture-cave reservoirs are constructed. By analyzing data such as seismic interpretation data of control layers and target layers, oil-water trend surface data, paleogeomorphic data, fracture-cave carving data, logging curves, logging interpretation data, single well production data, well basic data and FMI imaging logging data, the ontology and relationships are improved, and a corresponding graph database is established.

[0060] Step 3: Based on the above data, configure the data source. The data source is structured data (csv, excel) or a linked database. Fill in the database type, instance name, address, port number and related Sql statements for the linked database. At the same time, based on the data extraction in step 2, create the entities, attribute information and relationships of the graph, extract triples from the data source configured in the previous step. The triples are in the form of knowledge basis (subject-predicate-object), define the entity type as the data type, the data field as the extracted triple predicate, and the field function as the object from the source data. Based on the above steps, and through the quality inspection of the researchers, the corresponding triple data of the carbonate reservoir are obtained.

[0061] Step 4: Map the triples obtained in step 3 to entities and relationships through knowledge mapping. Edit the entity type field before mapping in the "Type Mapping" area under the corresponding entity, edit the data fields mapped to each attribute of the entity in the "Attribute Mapping" area under the corresponding entity, and edit the data fields and tail entity types mapped to each entity relationship in the "Relationship Mapping" area under the corresponding entity. Through knowledge fusion, merge the alignable entities introduced in the data, set the fusion identifier, add one or more attributes, configure each attribute similarity function and similarity threshold, and complete knowledge fusion.

[0062] Step 5: Establish business rule module (business rule description and definition)

[0063] Reservoir analysis rules: The low impedance below the Ordovician buried mountain is laterally continuously distributed and basically stable, with a thickness of 70 to 90 ms (180 to 220 m); according to the analysis of drilling data, the reservoirs encountered are concentrated within 180 m; according to the analysis of production data, the thickness of the oil layer is 160 m; the thickness of the Ordovician Eagle 1 oil layer in the A well area is comprehensively determined to be 155.5 m and is used as the bottom boundary of the reservoir calculation.

[0064] Reservoir physical property rules: Drilling, logging, core, cast thin section and other data show that the carbonate reservoir space types of the Ordovician Yingshan Formation in Well A are mainly pores, caves and fractures. The classification levels are shown in Table 1 below:

[0065] Table 1: Classification of pores, caves and fractures in carbonate rocks

[0066]

[0067] Well drilling confirmed that the Ordovician reservoirs in Well A and adjacent blocks are concentrated within 180m below the unconformity surface. Well logging interpretation rules:

[0068] The effective porosity of a single well is obtained by using thickness weighted average, and the effective porosity of the pore-type and fracture-type reservoirs of the calculation unit is obtained by three methods: arithmetic average, area trade-off, and contour area trade-off. The comprehensive values ​​are 8.1% and 0.14%, respectively. As shown in Table 2:

[0069] Table 2: Average effective porosity values ​​in well area A

[0070]

[0071] The Ordovician carbonate reservoir in Well A is a dual-porosity medium. The storage capacity of the reservoir is characterized by vug porosity and fracture porosity, and the oil content of the reservoir is characterized by hydrocarbon saturation. Therefore, the determination of the lower limit of effective thickness is to determine the vug porosity, fracture porosity and oil saturation. The lower limit of effective thickness of the reservoir in Well A is determined comprehensively: the lower limits of vug porosity and fracture porosity are 2.2% and 0.06% respectively, and the lower limit of saturation is 50%.

[0072] According to the determined lower limit standard of effective thickness, 7 wells in the oil-bearing area were uniformly processed and interpreted to obtain the effective thickness, porosity and oil saturation of different reservoir spaces in each well. The average effective thickness was calculated by arithmetic mean, well point area weighing and contour area weighing respectively; the comprehensive value: the effective thickness of the pore-type and fracture reservoirs were 13.3m and 15.9m respectively.

[0073] Step 6: Establishment of inference model for carbonate fracture-vuggy reservoir

[0074] The carbonate fracture-vuggy reservoir reasoning is based on the carbonate reservoir knowledge graph, extracts the carbonate fracture-vuggy reservoir reasoning business rules, establishes the carbonate fracture-vuggy reservoir reasoning model through knowledge reasoning technology, and realizes the intelligent evaluation of carbonate fracture-vuggy reservoirs.

[0075] Specifically, the knowledge reasoning model refers to the establishment of business rules applicable to carbonate fracture-vuggy reservoir reasoning by combing and analyzing the properties of carbonate fracture-vuggy reservoirs. Here, a rule-based knowledge reasoning algorithm is used to establish a carbonate fracture-vuggy reservoir reasoning model to perform intelligent optimization reasoning on the carbonate fracture-vuggy reservoir prediction results. As shown in Table 3:

[0076] Table 3: Reservoir attribute information

[0077]

[0078] It is preferred to determine whether there is leakage and emptying. If so, it corresponds to Class I reservoir; if there is no leakage and emptying, and there is acid fracturing and production, it corresponds to Class II reservoir. For other cases, the subsequent conditions are determined;

[0079] 1. R(C==leakage and emptying)=>(C==type I reservoir)

[0080] 2. R(C==acid fracturing production)=>(C==Class II reservoir)

[0081] If the distance from the oil source fracture is 1 km, it is a Class I reservoir, 1-2 km is a Class II reservoir, and if it is greater than 2 km, the subsequent conditions are determined;

[0082] 3.R(C.DIS<1)=>(C==Class I reservoir)

[0083] 4.R(C.DIS>=1&&C.DIS<=2)=>(C==Class II reservoir)

[0084] If the distance from the oil bottom is less than 70m, it is a Class I reservoir, 70m-155.5m is a Class II reservoir, and if it is below the oil bottom interface, the subsequent conditions are determined.

[0085] 5.R(C.YD<70)=>(C==Class I reservoir)

[0086] 6.R(C.YD>=70&&C.YD<=155.5)=>(C==Class II reservoir)

[0087] If the wave impedance value is less than 15500, it is a Class I reservoir, and the wave impedance range is 15500-16600, it is a Class II reservoir. For other cases, the subsequent conditions are determined;

[0088] 7. R(C.BZK <15500)=> (C==Class I reservoir)

[0089] 8.R(C.BZK>=15500&&C.BZK<=16600)=>(C==Class II reservoir)

[0090] If the pore size is greater than 20 mm, it is a Class I reservoir, 2 mm-20 mm is a Class II reservoir, and other cases determine subsequent conditions;

[0091] 9.R(C.KJ>20)=>(C==Class I reservoir)

[0092] 10.R(C.KJ>=2&&C.KJ<=20)=>(C==Class II reservoir)

[0093] Well logging interpretation shows that the effective porosity is ≥4.5% and the fracture porosity is ≥0.1%, which is a Class I reservoir; well logging interpretation shows that the effective porosity is 1.8-4.5% and the fracture porosity is 0.04-0.1%, which is a Class II reservoir; the others are Class III reservoirs;

[0094] 11.R(C.KXD>=4.5&&C.LF>=0.1)=>(C==Class I reservoir)

[0095] 12.R((C.KXD<4.5&&C.KXD>=1.8)&&(C.LF<0.1&&C.LF>=0.04))=>(C=Class II reservoir)

[0096] 13.R(C.KXD<1.8||C.LF<0.04)=>(C=three types of reservoirs)

[0097] Step 7: Comprehensive reasoning and evaluation of fracture-cavity carbonate reservoirs

[0098] Rules 1-13 that can be used for knowledge reasoning are formed according to business rules. Based on the entities and attributes of the reservoir stored in the knowledge graph, logical reasoning is performed in the order of rules 1-13 to obtain automatic reasoning results of the reservoir type.

[0099] Another embodiment of the present invention provides a fracture-cavity carbonate reservoir reasoning device based on a knowledge graph, such as Figure 4 As shown, the device includes: ontology construction module 10, knowledge extraction module 20, knowledge fusion module 30, business rule module 40, reasoning model module 50, reservoir comprehensive evaluation model 60. Its working principle is as follows:

[0100] The ontology construction module 10 constructs the ontology of carbonate reservoirs based on the pre-acquired interpretation results data and single well data; the knowledge extraction module 20 extracts knowledge based on the ontology; the knowledge fusion module 30 fuses the extracted knowledge; the business rule module 40 constructs business rules based on the fused knowledge, and the business rules include, for example, oil reservoir analysis rules, reservoir physical property rules, and well logging interpretation rules; the reasoning model module 50 establishes the reasoning model of the carbonate fracture-cavity reservoir based on the business rules and obtains the reasoning results. The calculation model is a comprehensive reasoning model of carbonate reservoirs. The business rules of the business rule module are combined with the comprehensive reasoning method of carbonate fracture-cavity reservoirs to perform comprehensive analysis and reasoning on each fracture-cavity reservoir, and generate a carbonate fracture-cavity reservoir optimization plan. The reservoir comprehensive evaluation module 60 performs reasoning evaluation on the fracture-cavity carbonate reservoir based on the reasoning results.

[0101] The technical effects and technical details of the device described in this embodiment can be found in the relevant contents of the above method embodiment, which will not be repeated here.

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

[0103] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as 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 a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0104] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0105] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A knowledge graph-based reasoning method for fracture-cavity carbonate reservoirs, characterized in that: include: Constructing the ontology of carbonate reservoir based on the pre-acquired interpretation result data and single well data; Extracting knowledge based on the ontology; Integrate the extracted knowledge; Build business rules based on the integrated knowledge; as well as Based on the business rules, an inference model of the carbonate fracture-vuggy reservoir is established and an inference result is obtained.

2. The method according to claim 1, characterized in that The process of constructing the ontology includes: Determining the boundary of the entity based on the interpretation result data and the single well data; Within the scope shown by the boundary, all concepts required for the business application of the carbonate reservoir research are established as the ontology.

3. The method according to claim 1, characterized in that The process of knowledge extraction includes: structured data knowledge extraction and unstructured data knowledge extraction.

4. The method according to claim 3, characterized in that The structured data knowledge extraction includes: mapping the structured data tables in the interpretation result data and the single well data to the concepts of the ontology.

5. The method according to claim 3, characterized in that: The unstructured data knowledge extraction includes: jointly extracting entities and relationships based on statistics and natural language processing to obtain unstructured knowledge.

6. The method according to claim 1, characterized in that The process of fusing the extracted knowledge includes: performing concept alignment and entity alignment on the knowledge.

7. The method according to claim 1, characterized in that The business rules include, for example: oil reservoir evaluation rules, reservoir physical property rules, and well logging interpretation rules.

8. The method according to claim 1, characterized in that The process of obtaining the inference result includes: Importing the seam and hole carving data in the interpretation result data as boundary data; triggering the inference model and performing inference calculation using rule indicators; The obtained optimal reasoning solution is output as the reasoning result.

9. The method according to claim 1, characterized in that: Also includes: Based on the inference results, the fracture-vuggy carbonate reservoir is inferred and evaluated.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

11. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 9 is implemented.

12. A knowledge graph-based fracture-cavity carbonate fracture-cavity reservoir reasoning device, characterized in that: include: An ontology construction module is used to construct an ontology of carbonate reservoirs based on pre-acquired interpretation results data and single well data; A knowledge extraction module, used for extracting knowledge based on the ontology; Knowledge fusion module, used to fuse the extracted knowledge; Business rule module, used to build business rules based on the integrated knowledge; as well as The inference model module is used to establish the inference model of the carbonate fracture-vuggy reservoir based on the business rules and obtain the inference results.

13. The device according to claim 12, characterized in that Also includes: A reservoir comprehensive evaluation module is used to perform reasoning evaluation on the fracture-vuggy carbonate reservoir based on the reasoning result.

Images