Method and device for determining entrapment geological resource quantity, electronic equipment and storage medium

Abstract

The invention provides a method and a device for determining entrapment geological resource quantity, electronic equipment and a storage medium. The method comprises the following steps: determining entrapment data information of a to-be-determined item of a target entrapment in a preset entrapment knowledge graph based on multiple pieces of first entrapment data information; inputting the plurality of pieces of first trap data information and the trap data information of the to-be-determined item into a pre-trained trap geological resource quantity prediction model, and performing interactive item calculation processing on the plurality of pieces of first trap data information and the trap data information of the to-be-determined item, predicting the trap geological resource quantity of the target trap; wherein the trap geological resource quantity prediction model is obtained by training a linear regression model through interaction items of multiple pieces of sample trap data. According to the method, traps of different exploration degrees, trap types and oil and gas reservoir types can uniformly use the model to calculate the resource quantity, and the efficiency and accuracy of determining the geological resource quantity are improved.

Description

Technical Field

[0001] This application relates to the technical field of oil and gas exploration, and in particular to a method, device, electronic device and storage medium for determining the geological resources of a trap. Background Art

[0002] As the smallest geological unit for implementing drilling tasks in the process of oil and gas exploration, the research data of traps all come from the practical results of oil and gas exploration work. The prediction of trap resources is an important part of oil and gas exploration work, and the accuracy of trap resource results is directly related to the accuracy of oil and gas pre-exploration decisions. Currently, the most commonly used method for calculating trap resources is the probability method, and the two widely used methods are the Monte Carlo simulation method and the Swanson mean. The most important process in both algorithms is to first determine the distribution characteristics of each resource parameter, the probability distribution curve, and the three values of 10%, 50%, and 90% for each parameter. The trap resource estimation method generally adopts the volume method. This method first determines the resource calculation parameters (including oil and gas area, thickness, oil and gas saturation, volume coefficient, etc.) according to simple empirical methods or analogy methods, and then multiplies several parameters to obtain the resources. There are some deficiencies in this trap resource calculation method: First, some of the calculation parameters require the participation of expert experience and involve subjective judgment; second, the calculation formulas are different for traps with different exploration degrees and trap types; third, there are problems such as large randomness and large errors in parameter values. Its calculation accuracy and reliability depend on the selection of relevant parameter values, which may lead to large errors in the calculated resource results. Therefore, how to improve the accuracy and efficiency of determining trap geological resources has become a technical problem that cannot be underestimated. Summary of the Invention

[0003] In view of this, the purpose of this application is to provide a method, device, electronic device and storage medium for determining trap geological resources. By using the trap knowledge graph to determine the trap data information of the items to be determined that are relatively difficult to determine in the trap, it solves the problem of lack of demonstration of relevant parameters in some areas that are not yet clear in geological cognition. Using the trap geological resource prediction model to determine the trap geological resources of the trap, it realizes that traps with different exploration degrees, trap types, and oil and gas reservoir types can be uniformly calculated for resources using this model, improving the efficiency and accuracy of determining geological resources.

[0004] The embodiment of this application provides a method for determining trap geological resources, and the determination method includes:

[0005] Obtain multiple first trap data information of the target trap;

[0006] Based on the multiple first trap data information, determine the trap data information of the items to be determined of the target trap in a preset trap knowledge graph;

[0007] Input multiple first trap data information and the trap data information of the item to be determined into a pre-trained trap geological resource volume prediction model, perform interaction term calculation processing on the multiple first trap data information and the trap data information of the item to be determined, and predict the trap geological resource volume of the target trap; wherein, the trap geological resource volume prediction model is obtained by training a linear regression model with the interaction terms of multiple sample trap data.

[0008] In one possible implementation manner, the trap knowledge graph is determined through the following steps:

[0009] Obtain multiple reference trap data information of multiple reference traps, the ontology concepts of the preset reference trap data information, the attribute information of the reference trap data information, and the relationship information of the reference trap data information; wherein, the reference trap is a trap for which the trap geological resource volume has been determined.

[0010] Based on the ontology concepts of the reference trap data information, the attribute information of the reference trap data information, the relationship information of the reference trap data information, and the multiple reference trap data information of multiple reference traps, fill in the ontology information of the knowledge graph to construct an ontology knowledge graph.

[0011] Obtain the unstructured data information of multiple reference traps, perform data processing on the unstructured data information of multiple reference traps, and construct an entity knowledge graph.

[0012] Based on the ontology knowledge graph and the entity knowledge graph, determine the trap knowledge graph.

[0013] In one possible implementation manner, the obtaining the unstructured data information of multiple reference traps, performing data processing on the unstructured data information of multiple reference traps, and constructing an entity knowledge graph includes:

[0014] Annotate the data information in the unstructured data information to determine each entity data information for constructing the entity knowledge graph in the unstructured data information.

[0015] Extract each entity data information, and determine the entity knowledge graph based on each entity data information.

[0016] In one possible implementation manner, the determining the trap data information of the item to be determined of the target trap based on the multiple first trap data information in the preset trap knowledge graph includes:

[0017] Determine the similarity values between each first trap data information and multiple second trap data information in the trap knowledge graph.

[0018] Determine the maximum similarity value among the multiple similarity values, and based on the second trap data information corresponding to the maximum similarity value, perform parameter analogy recommendation on the target trap to determine the trap data information of the item to be determined for the target trap.

[0019] In one possible implementation, the trap geological resource volume prediction model is trained through the following steps:

[0020] Perform data information preprocessing on the multiple sample trap data information of each sample trap to determine the multiple processed sample trap data information of each sample trap;

[0021] Input the multiple processed sample trap data information of each sample trap into the linear regression model, calculate the interaction terms of the multiple processed sample trap data information of each sample trap, and predict the trap predicted geological resource volume corresponding to each sample trap;

[0022] Based on the trap predicted geological resource volume corresponding to the multiple sample trap data information and the trap actual geological resource volume of each sample trap, determine the loss value of the linear regression model;

[0023] Based on the loss value and a preset loss threshold, perform iterative training on the linear regression model to determine the trap geological resource volume prediction model.

[0024] In one possible implementation, the performing iterative training on the linear regression model based on the loss value and a preset loss threshold to determine the trap geological resource volume prediction model includes:

[0025] Detect whether the loss value is less than the preset loss threshold;

[0026] If so, confirm the linear regression model as the trap geological resource volume prediction model;

[0027] If not, change the model parameters of the linear regression model, perform iterative training on the changed linear regression model until the iterative training of the linear regression model stops when the loss value is less than the preset loss threshold, and confirm the linear regression model as the trap geological resource volume prediction model.

[0028] In one possible implementation, the performing data information preprocessing on the multiple sample trap data information of each sample trap to determine the multiple processed sample trap data information of each sample trap includes:

[0029] Obtain the third trap data information of the block to which each of the sample traps belongs;

[0030] Interpolate the third trap data information of the block to which each of the sample traps belongs into the corresponding multiple sample trap data information based on the Hermite interpolation method, and determine multiple processed sample trap data information for each sample trap.

[0031] The embodiment of the present application also provides a device for determining the trap geological resource volume. The determining device includes:

[0032] An acquisition module, configured to acquire multiple first trap data information of a target trap;

[0033] A data recommendation module, configured to determine the trap data information of the item to be determined of the target trap in a preset trap knowledge graph based on the multiple first trap data information;

[0034] A resource volume prediction module, configured to input the multiple first trap data information and the trap data information of the item to be determined into a pre-trained trap geological resource volume prediction model, perform interaction term calculation processing on the multiple first trap data information and the trap data information of the item to be determined, and predict the trap geological resource volume of the target trap; wherein, the trap geological resource volume prediction model is obtained by training a linear regression model with interaction terms of multiple sample trap data.

[0035] The embodiment of the present application also provides an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the memory through the bus. When the machine-readable instructions are executed by the processor, the steps of the method for determining the trap geological resource volume as described above are executed.

[0036] The embodiment of the present application also provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is run by a processor, the steps of the method for determining the trap geological resource volume as described above are executed.

[0037] The method, device, electronic device and storage medium for determining the trap geological resource volume provided by the embodiments of the present application, the determination method includes: obtaining a plurality of first trap data information of a target trap; determining the trap data information of the item to be determined of the target trap in a preset trap knowledge graph based on the plurality of first trap data information; inputting the plurality of first trap data information and the trap data information of the item to be determined into a pre-trained trap geological resource volume prediction model, performing interactive term calculation processing on the plurality of first trap data information and the trap data information of the item to be determined, and predicting the trap geological resource volume of the target trap; wherein, the trap geological resource volume prediction model is obtained by training a linear regression model with the interactive terms of a plurality of sample trap data. By using the trap knowledge graph to determine the trap data information of the item to be determined that is relatively difficult to determine in the trap, the problem that the relevant parameters in some areas that are not yet clear in geological cognition lack demonstration is solved. By using the trap geological resource volume prediction model to determine the trap geological resource volume of the trap, it is realized that traps with different exploration degrees, trap types, and hydrocarbon reservoir types can be uniformly calculated for resource volume by using this model, improving the efficiency and accuracy of determining the geological resource volume.

[0038] To make the above objects, features, and advantages of the present application more obvious and understandable, the following specifically gives preferred embodiments and, in conjunction with the accompanying drawings, detailed descriptions are as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] To more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other relevant drawings can also be obtained based on these drawings.

[0040] Figure 1 It is a flowchart of a method for determining the trap geological resource volume provided by the embodiments of the present application;

[0041] Figure 2 It is a schematic diagram of a method for determining the trap geological resource volume provided by the embodiments of the present application;

[0042] Figure 3 It is one of the structural schematic diagrams of a device for determining the trap geological resource volume provided by the embodiments of the present application;

[0043] Figure 4 It is the second structural schematic diagram of a device for determining the trap geological resource volume provided by the embodiments of the present application;

[0044] Figure 5Schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0045] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It should be understood that the accompanying drawings in the present application are only for the purposes of illustration and description, and are not used to limit the protection scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in the present application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical context relationships may be reversed or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart or remove one or more operations from the flowchart under the guidance of the content of the present application.

[0046] In addition, the described embodiments are only some embodiments of the present application, rather than all embodiments. The components of the embodiments of the present application usually described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application claimed, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present application.

[0047] To enable those skilled in the art to use the content of the present application, the following implementation manners are given in combination with a specific application scenario of "determining the trap geological resources". For those skilled in the art, without departing from the spirit and scope of the present application, the general principles defined here can be applied to other embodiments and application scenarios.

[0048] First, the application scenarios applicable to the present application are introduced. The present application can be applied to the field of oil and gas exploration technology.

[0049] It has been found through research that a trap, as the smallest geological unit in the implementation of drilling tasks during oil and gas exploration, its research data all come from the practical results of oil and gas exploration work. The prediction of trap resources is an important part of oil and gas exploration work, and the accuracy of trap resource results is directly related to the accuracy of oil and gas pre-exploration decisions. Currently, the most commonly used method for calculating trap resources is the probability method. The widely used ones are the Monte Carlo simulation method and the Swanson mean. The most important process in both algorithms is to first determine the distribution characteristics of each resource parameter, the probability distribution curve, and the three values of 10%, 50%, and 90% for each parameter. The method for estimating trap resources generally adopts the volume method. This method first determines the resource calculation parameters (including gas-bearing area, thickness, gas-bearing saturation, volume coefficient, etc.) according to simple empirical methods or analogy methods, and then multiplies several parameters to obtain the resources. There are some deficiencies in this method for calculating trap resources: First, some of the calculation parameters require the participation of expert experience and involve subjective judgment; second, the calculation formulas are different for traps with different exploration degrees and trap types; third, there are problems such as large randomness and large errors in parameter values. Its calculation accuracy and credibility depend on the selection of relevant parameter values, which may lead to large errors in the calculation results of resources. Therefore, how to improve the accuracy and efficiency of determining trap geological resources has become a technical problem that cannot be underestimated.

[0050] Based on this, the embodiment of the present application provides a method for determining trap geological resources. By using the trap knowledge graph, the trap data information of the undetermined items that are relatively difficult to determine in the trap is determined, solving the problem of lack of argumentation for relevant parameters in some areas that are not yet clear in geological cognition. Using the trap geological resource prediction model to determine the trap geological resources of the trap, it realizes that traps with different exploration degrees, trap types, and oil and gas reservoir types can be uniformly calculated for resources using this model, improving the efficiency and accuracy of determining geological resources.

[0051] Please refer to Figure 1 , Figure 1 which is a flowchart of a method for determining trap geological resources provided by the embodiment of the present application. As Figure 1 shown in

[0052] S101: Obtain multiple first trap data information of the target trap.

[0053] In this step, multiple first trap data information of the target trap is obtained, where the first trap data information includes other parameters such as gas-bearing area and average porosity.

[0054] S102: Based on the multiple first trap data information, determine the trap data information of the undetermined items of the target trap in the preset trap knowledge graph.

[0055] In this step, trap data information of the item to be determined for the target trap is determined in a preset trap knowledge graph according to multiple pieces of first closed-loop data information.

[0056] Among them, the trap data information of the item to be determined is the necessary trap data information that cannot be determined in the target trap. To improve the accuracy of determining the trap geological resource volume, it is necessary to determine the trap data information of this item.

[0057] In a possible implementation manner, the trap knowledge graph is determined through the following steps:

[0058] A: Obtain multiple pieces of reference trap data information of multiple reference traps, the ontology concepts of the preset reference trap data information, the attribute information of the reference trap data information, and the relationship information of the reference trap data information; among them, the reference trap is a trap for which the trap geological resource volume has been determined.

[0059] Here, multiple pieces of reference trap data information of multiple reference traps, the ontology concepts of the preset reference trap data information, the attribute information of the reference trap data information, and the relationship information of the reference trap data information are obtained.

[0060] Among them, the ontology concepts of the reference trap data information can be ontology concepts of other data information such as calculation parameter determination, average porosity, gas-bearing area, etc., the relationship information of the reference trap data information can be other relationships such as parent-child relationship, output relationship, association relationship, etc., and the attribute information of the reference trap data information can be other information such as name information, value information, and trap type.

[0061] B: Based on the ontology concepts of the reference trap data information, the attribute information of the reference trap data information, the relationship information of the reference trap data information, and multiple pieces of reference trap data information of multiple reference traps, fill the ontology information of the knowledge graph to construct an ontology knowledge graph.

[0062] Here, according to the ontology concepts of the reference trap data information, the attribute information of the reference trap data information, the relationship information of the reference trap data information, and multiple pieces of reference trap data information of multiple reference traps, fill the ontology information of the knowledge graph to construct an ontology knowledge graph.

[0063] C: Obtain the unstructured data information of multiple reference traps, process the unstructured data information of multiple reference traps, and construct an entity knowledge graph.

[0064] Here, the unstructured data information of multiple reference traps is obtained, the unstructured data information of multiple reference traps is processed, and an entity knowledge graph is constructed.

[0065] Here, the unstructured data information of the reference trap is the text data of the reference trap, which can be from the trap research report document of the oilfield, and this part is not limited.

[0066] In a possible implementation manner, the obtaining of the unstructured data information of multiple reference traps, the data processing of the unstructured data information of multiple reference traps, and the construction of an entity knowledge graph include:

[0067] Annotate the data information in the unstructured data information to determine each entity data information for constructing the entity knowledge graph in the unstructured data information; extract each entity data information, and determine the entity knowledge graph based on each entity data information.

[0068] Here, annotate the data information in the unstructured data information to determine each entity data information for constructing the entity knowledge graph in the unstructured data information; extract each entity data information, and determine the entity knowledge graph according to each entity data information.

[0069] Here, the data information in the unstructured data information can be annotated by means of expert manual annotation, and this part is not limited.

[0070] Among them, the text and tables in the document can be annotated, the table names and tables are corresponded through regular rules, and rules are formulated according to the table format for extracting each entity data information.

[0071] In a possible implementation manner, the determining of the trap data information of the item to be determined of the target trap in the preset trap knowledge graph based on multiple pieces of the first trap data information includes:

[0072] a: Determine the similarity value between each piece of the first trap data information and multiple pieces of the second trap data information in the trap knowledge graph.

[0073] Here, determine the similarity value between each piece of the first trap data information and multiple pieces of the second trap data information in the trap knowledge graph.

[0074] b: Determine the maximum similarity value among the multiple similarity values, and based on the second trap data information corresponding to the maximum similarity value, perform parameter analogy recommendation on the target trap to determine the trap data information of the item to be determined of the target trap.

[0075] Here, the maximum similarity value is determined among multiple similarity values, and based on the second closed-loop data information corresponding to the maximum similarity value, parameter analogy recommendation is performed on the target trap, and the trap data information of the item to be determined of the target trap is determined. Thus, it is realized that the trap data information that is relatively difficult to determine can be selected by means of knowledge graph analogy recommendation, and the situation where relevant parameters in some areas with unclear geological understanding lack demonstration is solved.

[0076] Among them, the trap data information of the determined item corresponding to the second closed-loop data information of the maximum similarity value is used as the trap data information of the item to be determined of the target trap.

[0077] S103: Input multiple first trap data information and the trap data information of the item to be determined into a pre-trained trap geological resource volume prediction model, perform interaction term calculation processing on the multiple first trap data information and the trap data information of the item to be determined, and predict the trap geological resource volume of the target trap; among them, the trap geological resource volume prediction model is trained by using the interaction terms of multiple sample trap data on a linear regression model.

[0078] In this step, multiple first trap data information and the trap data information of the item to be determined are input into a pre-trained trap geological resource volume prediction model, interaction term calculation processing is performed on the multiple first trap data information and the trap data information of the item to be determined, and the trap geological resource volume of the target trap is predicted.

[0079] Among them, the trap geological resource volume prediction model is trained by using the interaction terms of multiple sample trap data on a linear regression model.

[0080] Here, in this solution, an interface for calculating the resource volume of the target trap is entered. This interface is divided into a calculation area and a resource volume prediction result area. The calculation area mainly includes the basic information of the trap and the input of calculation parameters, and supports multi-trap calculation and data import. Click the resource volume calculation button to run the trap geological resource volume prediction model, and the calculation result is displayed in the resource volume prediction result column.

[0081] In a possible implementation manner, the trap geological resource volume prediction model is trained through the following steps:

[0082] (1): Perform data information preprocessing on the multiple sample trap data information of each sample trap, and determine multiple processed sample trap data information of each sample trap.

[0083] Here, perform data information preprocessing on the multiple sample trap data information of each sample trap, and determine multiple processed sample trap data information of each sample trap.

[0084] In a possible implementation, the data information preprocessing of the multiple sample trap data information for each sample trap to determine multiple processed sample trap data information for each sample trap includes:

[0085] Obtain the third trap data information of the block to which each sample trap belongs; interpolate the third trap data information of the block to which each sample trap belongs into the corresponding multiple sample trap data information based on the Hermite interpolation method to determine multiple processed sample trap data information for each sample trap.

[0086] Here, obtain the third trap data information of the block to which each sample trap belongs, interpolate the third trap data information of the block to which each sample trap belongs into the corresponding multiple sample trap data information according to the Hermite interpolation method, and determine multiple processed sample trap data information for each sample trap.

[0087] Among them, since there are cases of partial data loss in the multiple sample trap data information of the sample trap, which will affect the training effect of the algorithm, it is necessary to perform data preprocessing on the sample trap data information.

[0088] (2): Input the multiple processed sample trap data information of each sample trap into the linear regression model, calculate the interaction terms of the multiple processed sample trap data information of each sample trap, and predict the trap predicted geological resource amount corresponding to each sample trap.

[0089] Here, input the multiple processed sample trap data information of each sample trap into the linear regression model, calculate the interaction terms of the multiple processed sample trap data information of each sample trap, and predict the trap predicted geological resource amount corresponding to each sample trap.

[0090] (3): Determine the loss value of the linear regression model based on the trap predicted geological resource amounts corresponding to the multiple sample trap data information and the trap actual geological resource amount of each sample trap.

[0091] Here, determine the loss value of the linear regression model according to the trap predicted geological resource amounts corresponding to the multiple sample trap data information and the trap actual geological resource amount of each sample trap.

[0092] (4): Perform iterative training on the linear regression model based on the loss value and a preset loss threshold to determine the trap geological resource amount prediction model.

[0093] Here, the linear regression model is iteratively trained according to the loss value and a preset loss threshold to determine the prediction model for the geological resources in the trap.

[0094] In a possible implementation manner, the iteratively training the linear regression model according to the loss value and the preset loss threshold to determine the prediction model for the geological resources in the trap includes:

[0095] Detect whether the loss value is less than the preset loss threshold; if so, determine the linear regression model as the prediction model for the geological resources in the trap; if not, modify the model parameters of the linear regression model, iteratively train the modified linear regression model until the loss value is less than the preset loss threshold, and then stop the iterative training of the linear regression model and determine the linear regression model as the prediction model for the geological resources in the trap.

[0096] Further, please refer to Figure 2 , Figure 2 , which is a schematic diagram of a method for determining the geological resources in the trap provided by an embodiment of the present application. As Figure 2 shown, an entity knowledge graph and an ontology knowledge graph are constructed. Multiple sample trap data information of each sample trap is selected from the ontology knowledge graph and the entity knowledge graph. Data interpolation processing is performed on the multiple sample trap data information of each sample trap to determine multiple processed sample trap data information of each sample trap. The multiple processed sample trap data information of each sample trap is input into the linear regression model for training to determine the prediction model for the geological resources in the trap. The multiple first trap data information of the target trap and the trap data information of the item to be determined are input into the prediction model for the geological resources in the trap to predict the geological resources in the target trap.

[0097] In this solution, based on the traditional calculation method for trap resources, ontology and entity knowledge graphs in the field of trap resource calculation are constructed using knowledge graph technology, a database of trap resource calculation parameters is established to realize analogical recommendation of calculation parameters, and a machine learning technology is used to construct an algorithm model for trap resource calculation. This algorithm model based on machine learning, on the one hand, solves the problem of different calculation formulas under different conditions. Traps with different exploration degrees, trap types, and oil and gas reservoir types can be uniformly calculated for resources using this algorithm model. On the other hand, calculation parameters can be selected through the analogical recommendation of the knowledge graph, solving the situation where relevant parameters in some areas with unclear geological understanding lack demonstration.

[0098] A method for determining the trap geological resource volume provided by an embodiment of the present application, the determination method includes: obtaining a plurality of first trap data information of a target trap; determining trap data information of an item to be determined of the target trap in a preset trap knowledge graph based on the plurality of first trap data information; inputting the plurality of first trap data information and the trap data information of the item to be determined into a pre-trained trap geological resource volume prediction model, performing interaction term calculation processing on the plurality of first trap data information and the trap data information of the item to be determined, and predicting the trap geological resource volume of the target trap; wherein, the trap geological resource volume prediction model is obtained by training a linear regression model with interaction terms of a plurality of sample trap data. By determining the trap data information of the item to be determined that is relatively difficult to determine in the trap through the trap knowledge graph, the problem that relevant parameters in some areas that are not yet clear in geological cognition lack demonstration is solved. Using the trap geological resource volume prediction model to determine the trap geological resource volume of the trap realizes that traps with different exploration degrees, trap types, and oil and gas reservoir types can be uniformly calculated for resource volume by this model, improving the efficiency and accuracy of determining geological resource volume.

[0099] Please refer to Figure 3 、 Figure 4 , Figure 3 which is one of the structural schematic diagrams of a device for determining the trap geological resource volume provided by an embodiment of the present application; Figure 4 which is the second structural schematic diagram of a device for determining the trap geological resource volume provided by an embodiment of the present application. As Figure 3 shown in

[0100] An acquisition module 310, configured to acquire a plurality of first trap data information of a target trap;

[0101] A data recommendation module 320, configured to determine trap data information of an item to be determined of the target trap in a preset trap knowledge graph based on the plurality of first trap data information;

[0102] A resource volume prediction module 330, configured to input the plurality of first trap data information and the trap data information of the item to be determined into a pre-trained trap geological resource volume prediction model, perform interaction term calculation processing on the plurality of first trap data information and the trap data information of the item to be determined, and predict the trap geological resource volume of the target trap; wherein, the trap geological resource volume prediction model is obtained by training a linear regression model with interaction terms of a plurality of sample trap data.

[0103] Further, as Figure 4As shown, the determination device 300 further includes a graph construction module 340, and the graph construction module 340 determines the trap knowledge graph through the following steps:

[0104] Obtain multiple reference trap data information of multiple reference traps, the ontology concepts of the preset reference trap data information, the attribute information of the reference trap data information, and the relationship information of the reference trap data information; wherein, the reference trap is a trap for which the trap geological resource volume has been determined;

[0105] Based on the ontology concepts of the reference trap data information, the attribute information of the reference trap data information, the relationship information of the reference trap data information, and the multiple reference trap data information of multiple reference traps, fill the ontology information of the knowledge graph to construct an ontology knowledge graph;

[0106] Obtain the unstructured data information of multiple reference traps, process the unstructured data information of multiple reference traps, and construct an entity knowledge graph;

[0107] Based on the ontology knowledge graph and the entity knowledge graph, determine the trap knowledge graph.

[0108] Further, when the graph construction module 340 is used to obtain the unstructured data information of multiple reference traps, process the unstructured data information of multiple reference traps, and construct an entity knowledge graph, the graph construction module 340 is specifically used for:

[0109] Annotate the data information in the unstructured data information to determine each entity data information for constructing the entity knowledge graph in the unstructured data information;

[0110] Extract each entity data information, and determine the entity knowledge graph based on each entity data information.

[0111] Further, the determining the trap data information of the to-be-determined item of the target trap among the preset trap knowledge graphs based on the multiple first trap data information includes:

[0112] Determine the similarity values between each first trap data information and multiple second trap data information in the trap knowledge graph;

[0113] Determine the maximum similarity value among the multiple similarity values, and based on the second trap data information corresponding to the maximum similarity value, perform parameter analogy recommendation on the target trap to determine the trap data information of the to-be-determined item of the target trap.

[0114] Further, as Figure 4As shown, the determination device 300 further includes a training module 350, and the training module 350 trains the trap geological resource volume prediction model through the following steps:

[0115] Perform data information preprocessing on the multiple sample trap data information of each sample trap to determine the multiple processed sample trap data information of each sample trap;

[0116] Input the multiple processed sample trap data information of each sample trap into the linear regression model, calculate the interaction terms of the multiple processed sample trap data information of each sample trap, and predict the trap predicted geological resource volume corresponding to each sample trap;

[0117] Based on the trap predicted geological resource volume corresponding to the multiple sample trap data information and the trap actual geological resource volume of each sample trap, determine the loss value of the linear regression model;

[0118] Based on the loss value and a preset loss threshold, perform iterative training on the linear regression model to determine the trap geological resource volume prediction model.

[0119] Further, when the training module 350 is used to perform iterative training on the linear regression model based on the loss value and a preset loss threshold to determine the trap geological resource volume prediction model, the training module 350 specifically is used for:

[0120] Detect whether the loss value is less than the preset loss threshold;

[0121] If so, determine the linear regression model as the trap geological resource volume prediction model;

[0122] If not, change the model parameters of the linear regression model, perform iterative training on the changed linear regression model until the iterative training of the linear regression model stops when the loss value is less than the preset loss threshold, and determine the linear regression model as the trap geological resource volume prediction model.

[0123] Further, when the training module 350 is used to perform data information preprocessing on the multiple sample trap data information of each sample trap to determine the multiple processed sample trap data information of each sample trap, the training module 350 specifically is used for:

[0124] Obtain the third trap data information of the block to which each sample trap belongs;

[0125] Interpolate the third trap data information of each block to which the sample trap belongs into the corresponding multiple sample trap data information based on the Hermite interpolation method, and determine multiple processed sample trap data information for each sample trap.

[0126] A device for determining trap geological resources provided by an embodiment of the present application, the determining device includes: an acquisition module, configured to acquire multiple first trap data information of a target trap; a data recommendation module, configured to determine trap data information of an item to be determined of the target trap in a preset trap knowledge graph based on the multiple first trap data information; a resource quantity prediction module, configured to input the multiple first trap data information and the trap data information of the item to be determined into a pre-trained trap geological resource quantity prediction model, perform interaction term calculation processing on the multiple first trap data information and the trap data information of the item to be determined, and predict the trap geological resource quantity of the target trap; wherein, the trap geological resource quantity prediction model is obtained by training a linear regression model through interaction terms of multiple sample trap data. By determining the trap data information of the item to be determined that is relatively difficult to determine through the trap knowledge graph, the problem of lack of demonstration of relevant parameters in some areas that are not yet clear in geological cognition is solved. The trap geological resource quantity prediction model is used to determine the trap geological resource quantity of the trap, realizing that traps with different exploration degrees, trap types, and oil and gas reservoir types can be uniformly calculated for resource quantity using this model, improving the efficiency and accuracy of determining geological resources.

[0127] Please refer to Figure 5 , Figure 5 which is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 5 shown in, the electronic device 500 includes a processor 510, a memory 520, and a bus 530.

[0128] The memory 520 stores machine-readable instructions executable by the processor 510. When the electronic device 500 runs, the processor 510 communicates with the memory 520 through the bus 530. When the machine-readable instructions are executed by the processor 510, the steps of the method for determining trap geological resources in the method embodiment as shown above can be executed. The specific implementation manner can refer to the method embodiment and will not be elaborated here. Figure 1 shown, the steps of the method for determining trap geological resources in the method embodiment as shown above can be executed. The specific implementation manner can refer to the method embodiment and will not be elaborated here.

[0129] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, the steps of the method for determining trap geological resources in the method embodiment as shown above can be executed. The specific implementation manner can refer to the method embodiment and will not be elaborated here. Figure 1 shown, the steps of the method for determining trap geological resources in the method embodiment as shown above can be executed. The specific implementation manner can refer to the method embodiment and will not be elaborated here.

[0130] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0131] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some communication interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0132] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0134] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs that can store program codes.

[0135] Finally, it should be noted that the above-described embodiments are only specific implementation manners of the present application, used to illustrate the technical solutions of the present application, rather than limiting it. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that any person skilled in the technical field can still modify the technical solutions recorded in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for determining the trap geological resource volume, characterized in that, the determination method includes: obtaining a plurality of first trap data information of the target trap; determining the trap data information of the item to be determined of the target trap in a preset trap knowledge graph based on the plurality of first trap data information; inputting the plurality of first trap data information and the trap data information of the item to be determined into a pre-trained trap geological resource volume prediction model, performing interactive item calculation processing on the plurality of first trap data information and the trap data information of the item to be determined, and predicting the trap geological resource volume of the target trap; wherein, the trap geological resource volume prediction model is obtained by training a linear regression model with the interactive items of a plurality of sample trap data.

2. The determination method according to claim 1, characterized in that, the trap knowledge graph is determined through the following steps: obtaining a plurality of reference trap data information of a plurality of reference traps, the ontology concepts of the preset reference trap data information, the attribute information of the reference trap data information, and the relationship information of the reference trap data information; wherein, the reference trap is a trap for which the trap geological resource volume has been determined; performing ontology information filling of the knowledge graph based on the ontology concepts of the reference trap data information, the attribute information of the reference trap data information, the relationship information of the reference trap data information, and the plurality of reference trap data information of the plurality of reference traps, and constructing an ontology knowledge graph; obtaining the unstructured data information of a plurality of reference traps, processing the unstructured data information of the plurality of reference traps, and constructing an entity knowledge graph; determining the trap knowledge graph based on the ontology knowledge graph and the entity knowledge graph.

3. The determination method according to claim 2, characterized in that, the obtaining the unstructured data information of a plurality of reference traps, processing the unstructured data information of the plurality of reference traps, and constructing an entity knowledge graph includes: annotating the data information in the unstructured data information to determine each entity data information for constructing the entity knowledge graph in the unstructured data information; extracting each entity data information, and determining the entity knowledge graph based on each entity data information.

4. The determination method according to claim 1, characterized in that, the determining the trap data information of the item to be determined of the target trap in a preset trap knowledge graph based on the plurality of first trap data information includes: determining the similarity values between each of the first trap data information and a plurality of second trap data information in the trap knowledge graph; determining the maximum similarity value among the plurality of similarity values, and performing parameter analogy recommendation on the target trap based on the second trap data information corresponding to the maximum similarity value, to determine the trap data information of the item to be determined of the target trap.

5. The determination method according to claim 1, characterized in that, the trap geological resource volume prediction model is trained through the following steps: Perform data information preprocessing on the multiple sample trap data information of each sample trap to determine multiple processed sample trap data information of each sample trap; Input the multiple processed sample trap data information of each sample trap into the linear regression model, calculate the interaction terms of the multiple processed sample trap data information of each sample trap, and predict the trap predicted geological resource volume corresponding to each sample trap; Based on the trap predicted geological resource volume corresponding to the multiple sample trap data information and the trap actual geological resource volume of each sample trap, determine the loss value of the linear regression model; Based on the loss value and a preset loss threshold, perform iterative training on the linear regression model to determine the trap geological resource volume prediction model.

6. The determination method according to claim 5, wherein, the performing iterative training on the linear regression model based on the loss value and a preset loss threshold to determine the trap geological resource volume prediction model includes: detecting whether the loss value is less than the preset loss threshold; if so, determining the linear regression model as the trap geological resource volume prediction model; if not, changing the model parameters of the linear regression model, performing iterative training on the changed linear regression model until the loss value is less than the preset loss threshold, and then stopping the iterative training of the linear regression model and determining the linear regression model as the trap geological resource volume prediction model.

7. The determination method according to claim 4, wherein, the performing data information preprocessing on the multiple sample trap data information of each sample trap to determine multiple processed sample trap data information of each sample trap includes: obtaining the third trap data information of the block to which each sample trap belongs; interpolating the third trap data information of the block to which each sample trap belongs into the corresponding multiple sample trap data information based on the Hermite interpolation method to determine multiple processed sample trap data information of each sample trap.

8. A determination device for trap geological resource volume, wherein, the determination device includes: an acquisition module, configured to acquire multiple first trap data information of a target trap; a data recommendation module, configured to determine the trap data information of the item to be determined of the target trap in a preset trap knowledge graph based on the multiple first trap data information; a resource volume prediction module, configured to input the multiple first trap data information and the trap data information of the item to be determined into a pre-trained trap geological resource volume prediction model, perform interaction term calculation processing on the multiple first trap data information and the trap data information of the item to be determined, and predict the trap geological resource volume of the target trap; wherein, the trap geological resource volume prediction model is obtained by training a linear regression model through the interaction terms of multiple sample trap data.

9. An electronic device, wherein, it includes: A processor, a memory, and a bus, where the memory stores machine-readable instructions executable by the processor. When the electronic device operates, the processor communicates with the memory through the bus. When the machine-readable instructions are run by the processor, the steps of the method for determining the trapped geological resource volume according to any one of claims 1 to 7 are executed.

10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, the steps of the method for determining the trapped geological resource volume according to any one of claims 1 to 7 are executed.

Images