Oil and Gas Industry Chain Decision Optimization Methods and Devices

Abstract

This invention discloses a method and apparatus for optimizing decision-making in the oil and gas industry chain. The method includes: acquiring a task set, dependencies between tasks, real-time resource status, and a preset resource allocation function for the oil and gas industry chain; generating a task graph based on the task set and dependencies between tasks; decomposing the task graph according to the types of tasks in the task graph to generate multiple sub-task graphs; generating multiple candidate task sequences for each sub-task graph according to a preset prior probability algorithm; determining the posterior probability of each candidate task sequence according to a preset posterior probability algorithm; the preset posterior probability algorithm is set based on a Bayesian inference algorithm; comparing the posterior probabilities of multiple candidate task sequences corresponding to each sub-task graph to determine the final task sequence corresponding to the sub-task graph; and allocating real-time resources, which can improve the decision-making efficiency of the oil and gas industry chain and reduce resource consumption and operating costs.

Description

Technical Field

[0001] This invention relates to the field of decision optimization technology in the oil and gas industry chain, and in particular to a method and apparatus for decision optimization in the oil and gas industry chain. Background Technology

[0002] The oil and gas industry chain comprises multiple complex links, including exploration, development, production, transportation, processing, and sales, covering the upstream, midstream, and downstream sectors of the oil and gas industry. Each link involves significant resource allocation and task planning issues. The oil and gas industry chain is capital-intensive, technology-intensive, and labor-intensive, requiring multi-faceted collaboration to form a complete industry chain. Optimizing and integrating the oil and gas industry chain can improve industry efficiency, reduce costs, enhance energy security, and improve competitiveness.

[0003] Traditional decision-making methods in the oil and gas industry chain often overlook the importance of resource rationality and hierarchical task decomposition when dealing with complex decision-making problems, resulting in resource consumption, inefficiency, and high operating costs, which affect the overall competitiveness and economic benefits of oil and gas companies. Summary of the Invention

[0004] This invention provides a decision optimization method for the oil and gas industry chain, which aims to improve decision-making efficiency and reduce resource consumption and operating costs. The method includes:

[0005] Obtain the task set, dependencies between tasks, real-time resource status, and preset resource allocation functions for the oil and gas industry chain; the task set includes multiple tasks; a task is a business operation executed in the oil and gas industry chain.

[0006] Generate a task graph based on the task set and the dependencies between tasks;

[0007] Based on the type of task in the task graph, the task graph is decomposed to generate multiple sub-task graphs;

[0008] Based on the preset prior probability algorithm, multiple candidate task sequences are generated for each subtask graph. The preset prior probability algorithm is set according to the minimum description length criterion and the reuse bias prior algorithm. The reuse bias prior algorithm is used to filter tasks and / or determine the execution order of tasks in the candidate task sequence according to the execution frequency and execution success rate of the tasks.

[0009] The posterior probability of each candidate task sequence is determined according to the preset posterior probability algorithm; the preset posterior probability algorithm is set according to the Bayesian inference algorithm.

[0010] The posterior probabilities of multiple candidate task sequences corresponding to each subtask graph are compared, and the candidate task sequence with the highest posterior probability is determined as the final task sequence corresponding to the subtask graph.

[0011] Real-time resources are allocated based on the final task sequence, real-time resource status, and preset resource allocation functions.

[0012] This invention also provides an oil and gas industry chain decision optimization device to improve the decision-making efficiency of the oil and gas industry chain and reduce resource consumption and operating costs. The device includes:

[0013] The acquisition module is used to acquire the task set, dependencies between tasks, real-time resource status, and preset resource allocation functions of the oil and gas industry chain; the task set includes multiple tasks; and each task is a business operation executed in the oil and gas industry chain.

[0014] The task graph generation module is used to generate a task graph based on a set of tasks and the dependencies between tasks.

[0015] The subtask graph generation module is used to decompose the task graph according to the type of task in the task graph and generate multiple subtask graphs.

[0016] The candidate task sequence generation module is used to generate multiple candidate task sequences for each subtask graph according to a preset prior probability algorithm. The preset prior probability algorithm is set according to the minimum description length criterion and the reuse bias prior algorithm. The reuse bias prior algorithm is used to filter tasks and / or determine the execution order of tasks in the candidate task sequence according to the execution frequency and execution success rate of the tasks.

[0017] The posterior probability determination module is used to determine the posterior probability of each candidate task sequence according to a preset posterior probability algorithm; the preset posterior probability algorithm is set according to the Bayesian inference algorithm.

[0018] The final task sequence determination module is used to compare the posterior probabilities of multiple candidate task sequences corresponding to each sub-task graph, and determine the candidate task sequence with the highest posterior probability as the final task sequence corresponding to the sub-task graph.

[0019] The resource allocation module is used to allocate real-time resources based on the final task sequence, real-time resource status, and preset resource allocation functions.

[0020] Compared with existing oil and gas industry chain decision optimization technologies, this invention obtains a task set, dependencies between tasks, real-time resource status, and a preset resource allocation function for the oil and gas industry chain. The task set includes multiple tasks; each task is a business operation performed within the oil and gas industry chain. A task graph is generated based on the task set and dependencies between tasks. The task graph is decomposed into multiple sub-task graphs based on the task types within it. Multiple candidate task sequences are generated for each sub-task graph according to a preset prior probability algorithm. The preset prior probability algorithm is set based on a minimum description length criterion and a reuse-biased prior algorithm. The prior algorithm is used to filter tasks and / or determine the execution order of tasks in the candidate task sequence according to the execution frequency and success rate of the tasks; the posterior probability of each candidate task sequence is determined according to the preset posterior probability algorithm, which is set according to the Bayesian inference algorithm; the posterior probabilities of multiple candidate task sequences corresponding to each sub-task graph are compared, and the candidate task sequence with the highest posterior probability is determined as the final task sequence corresponding to the sub-task graph; real-time resources are allocated according to the final task sequence, real-time resource status and preset resource allocation function, which can improve the decision-making efficiency of the oil and gas industry chain and reduce resource consumption and operating costs. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0022] Figure 1 This is a flowchart of an oil and gas industry chain decision optimization method provided in an embodiment of the present invention;

[0023] Figure 2 A flowchart illustrating a specific example of an oil and gas industry chain decision optimization method provided in this embodiment of the invention;

[0024] Figure 3 This is a schematic diagram of an oil and gas industry chain decision optimization device provided in an embodiment of the present invention;

[0025] Figure 4 This is a schematic diagram of a specific example of an oil and gas industry chain decision optimization device provided in an embodiment of the present invention;

[0026] Figure 5 This is a schematic diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0028] The acquisition, storage, use, and processing of data in this application comply with relevant laws and regulations.

[0029] In this document, the term "and / or" merely describes a relationship, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0030] In the description of this specification, the terms "comprising," "including," "having," and "containing" are open-ended terms, meaning that they include but are not limited to. The terms "an embodiment," "a specific embodiment," "some embodiments," and "for example," etc., refer to specific features, structures, or characteristics described in connection with that embodiment or example that are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. The order of steps involved in the various embodiments is used to illustrate the implementation of this application, and the order of steps is not limited and can be adjusted appropriately as needed.

[0031] To address the problems of existing technologies, this invention aims to optimize the decision-making process in the oil and gas industry chain, encompassing exploration, extraction, processing, and transportation, by introducing hierarchical programming and grammatical induction. This invention transforms complex decision-making problems into more manageable and solvable forms through an innovative method, thereby improving the efficiency and quality of decision-making in the oil and gas industry chain. By utilizing hierarchical programming, this invention decomposes massive decision-making tasks into multiple hierarchical sub-tasks, making each sub-task easier to handle and facilitating overall coordination and optimization.

[0032] Figure 1 This is a flowchart of an oil and gas industry chain decision optimization method provided in an embodiment of the present invention, such as... Figure 1 As shown, the method may include:

[0033] Step 101: Obtain the task set, dependencies between tasks, real-time resource status, and preset resource allocation functions for the oil and gas industry chain; the task set includes multiple tasks; a task is a business operation executed in the oil and gas industry chain.

[0034] Step 102: Generate a task graph based on the task set and the dependencies between tasks;

[0035] Step 103: Based on the type of task in the task graph, decompose the task graph to generate multiple sub-task graphs;

[0036] Step 104: Generate multiple candidate task sequences for each subtask graph according to the preset prior probability algorithm; the preset prior probability algorithm is set according to the minimum description length criterion and the reuse bias prior algorithm; the reuse bias prior algorithm is used to filter tasks and / or determine the execution order of tasks in the candidate task sequence according to the execution frequency and execution success rate of the tasks.

[0037] Step 105: Determine the posterior probability of each candidate task sequence according to the preset posterior probability algorithm; the preset posterior probability algorithm is set according to the Bayesian inference algorithm.

[0038] Step 106: Compare the posterior probabilities of multiple candidate task sequences corresponding to each subtask graph, and determine the candidate task sequence with the highest posterior probability as the final task sequence corresponding to the subtask graph.

[0039] Step 107: Allocate real-time resources according to the final task sequence, real-time resource status, and preset resource allocation function.

[0040] This invention provides a decision optimization method for the oil and gas industry chain based on hierarchical structure planning and grammatical induction. By decomposing complex decision problems into hierarchical subtasks and using a grammatical induction model to generate and optimize task sequences, this method achieves an efficient and low-cost decision-making process, improves the decision-making efficiency of the oil and gas industry chain, and reduces resource consumption and operating costs.

[0041] First, the defined oil and gas industry chain task map is decomposed hierarchically.

[0042] It is possible to obtain the task set T of the oil and gas industry chain. Among them, task t i It refers to a specific business operation (such as exploration, mining, etc.).

[0043] In one embodiment, the type of task includes one or any combination of exploration, extraction, processing, and transportation tasks. The oil and gas industry chain comprises multiple complex stages, such as exploration, extraction, processing, and transportation, each involving significant resource allocation and task planning issues.

[0044] In one embodiment, decomposing the task map according to the type of task in the task map to generate multiple sub-task maps may include: decomposing the task map according to the type of task in the task map to generate one or any combination of exploration sub-task maps, mining sub-task maps, processing sub-task maps, and transportation sub-task maps.

[0045] Construct a task graph G, where V is the set of nodes representing tasks, and E is the set of edges representing the dependencies between tasks. Decompose the task graph G into multiple sub-task graphs G1, G2, ..., G... i ... G k Each subtask graph represents an independent task module, such as an exploration module or a mining module.

[0046] In one embodiment, the exploration subtask diagram includes one or any combination of geological survey subtasks, drilling design subtasks, and sample analysis subtasks; the mining subtask diagram includes one or any combination of equipment deployment subtasks, production monitoring subtasks, and operation adjustment subtasks. Each subtask diagram G can be... i Further task decomposition yields a set of subtasks. .

[0047] The following section introduces the constructed Bayesian program inductive model and how to select the optimal task sequence based on the generated task sequence.

[0048] In one embodiment, the preset prior probability algorithm is as follows:

[0049] p(π) ∝ ;

[0050] p(ρ i ) ∝ ;

[0051] Where π is the task sequence; p(π) is the probability distribution of the task sequence, reflecting the priority and / or feasibility of the task plan; DL(π) represents the minimum description length of the task sequence π, and ∝ is proportional to; ρ i p(ρ) is the i-th task in the task sequence. i Let be the probability distribution of the i-th task; λ is the regularization parameter used to control the preference for reusing the i-th task. It is an exponential function used to calculate the probability of the i-th task.

[0052] Define a probability distribution p(π) for a task sequence, where π represents a task sequence. This distribution reflects the priority or probability of different task plans. Introduce a minimum description length (MDL) prior; the MDL principle favors selecting concise and efficient plans to reduce the overall description length. Define a reuse biased prior p(ρ).i ), where λ is a regularization parameter used to control the preference for reusing the i-th task; frequently used tasks have a higher probability of being reused. In short, p(ρ) i The design purpose of λ is to encourage the system to select and reuse tasks that have been proven effective and efficient, thereby improving the overall efficiency and effectiveness of the task sequence. The degree of this bias can be controlled by adjusting the value of λ to adapt to different application scenarios.

[0053] Based on the task graph G and the prior distribution p(π), generate a sequence of candidate tasks. Each candidate task sequence is a feasible task execution order.

[0054] In one embodiment, the preset posterior probability algorithm is as follows:

[0055] ;

[0056] ;

[0057] in, π is a normalization constant; π' is a candidate task sequence; Π is the set of candidate task sequences. .

[0058] The posterior probability of each candidate task sequence is calculated. This step evaluates the effectiveness of each candidate task sequence through Bayesian inference, considering the success rate of the tasks and the prior distribution. π' represents any candidate task sequence used for comparison with other possible task sequences to determine which is the optimal execution plan. Here, p(π) can be defined by combining the minimum description length prior and the reuse bias prior. Specifically, for a task sequence π containing multiple tasks, its prior probability p(π) can be determined based on the probabilities p(ρ) of these tasks. i Adjust it using ).

[0059] In one embodiment, comparing the posterior probabilities of multiple candidate task sequences corresponding to each subtask graph and determining the candidate task sequence with the highest posterior probability as the final task sequence corresponding to the subtask graph may include: comparing the posterior probabilities of multiple candidate task sequences corresponding to each subtask graph and determining the candidate task sequence π* with the highest posterior probability as the final task sequence corresponding to the subtask graph.

[0060] ;

[0061] in, It makes Find the variable point corresponding to the maximum value.

[0062] The task sequence π* with the highest posterior probability is selected as the final execution plan. The optimal task execution order is found by comparing the posterior probabilities of all candidate sequences.

[0063] Figure 2 A flowchart illustrating a specific example of an oil and gas industry chain decision optimization method provided in this embodiment of the invention is shown below. Figure 2 As shown, in one embodiment, the oil and gas industry chain decision optimization method further includes: step 201, obtaining the task execution order;

[0064] The default resource allocation function is:

[0065] ;

[0066] in, S represents the real-time resource status, indicating the resource status at time t; S represents the task execution order, indicating the position of the task in the task sequence. This represents the real-time resource status after allocation; f is a resource allocation function that adjusts based on task requirements and real-time resource conditions.

[0067] In step 101, the real-time resource state R(t) is defined, which represents the resource state at time t. Resources may include manpower, equipment, funds, etc.

[0068] Define the task execution order in step 201. s j ∈T, representing the position of the task in the task sequence. Step 201 only needs to be executed before step 107 within the method.

[0069] Based on the task execution order S and the real-time resource status R(t), a preset resource allocation function is defined to dynamically adjust resource allocation. f is a resource allocation function that is adjusted according to task requirements and the current resource status. For example, if a task requires more manpower, the system will automatically allocate the corresponding manpower.

[0070] The specific steps to optimize the decision-making process for an oil and gas exploration project are as follows:

[0071] (1) In the data input interface, the user inputs the task diagram G of exploration tasks (geological survey, drilling design, sample analysis) and mining tasks (equipment deployment, production monitoring); verify the dependencies between tasks to ensure that the geological survey is completed before the drilling design.

[0072] (2) In the task decomposition section, the task map G is decomposed into the exploration module and the mining module. The geological survey task in the exploration module can be further decomposed into two tasks: data collection and data analysis.

[0073] (3) In the Bayesian program induction module, the system generates a sequence of candidate tasks.

[0074] Sequence 1: Geological survey data collection → Drilling design → Data sample analysis;

[0075] Sequence 2: Drilling design data collection → Geological survey → Data sample analysis.

[0076] Calculate the posterior probability of each candidate task sequence and select the optimal task sequence as sequence 1.

[0077] (4) Monitor the current resource status in real time, and increase the human resources for the geological survey stage to speed up the progress based on the task execution order and real-time resource status.

[0078] (5) Feedback and adjustment of task execution order and resource allocation based on actual situation, regenerate new task sequence and adjust resource allocation.

[0079] This invention also proposes an oil and gas industry chain decision optimization device, the principle of which is similar to the oil and gas industry chain decision optimization method, and will not be described in detail here.

[0080] Figure 3 This is a schematic diagram of an oil and gas industry chain decision optimization device provided in an embodiment of the present invention, such as... Figure 3 As shown, the decision optimization device for the oil and gas industry chain may include:

[0081] The acquisition module 301 is used to acquire the task set, the dependencies between tasks, the real-time resource status, and the preset resource allocation function of the oil and gas industry chain; the task set includes multiple tasks; the task is a business operation executed in the oil and gas industry chain;

[0082] The task graph generation module 302 is used to generate a task graph based on the task set and the dependencies between tasks;

[0083] The subtask graph generation module 303 is used to decompose the task graph according to the type of task in the task graph and generate multiple subtask graphs.

[0084] The candidate task sequence generation module 304 is used to generate multiple candidate task sequences for each subtask graph according to a preset prior probability algorithm. The preset prior probability algorithm is set according to the minimum description length criterion and the reuse bias prior algorithm. The reuse bias prior algorithm is used to filter tasks and / or determine the execution order of tasks in the candidate task sequence according to the execution frequency and execution success rate of the tasks.

[0085] The posterior probability determination module 305 is used to determine the posterior probability of each candidate task sequence according to a preset posterior probability algorithm; the preset posterior probability algorithm is set according to the Bayesian inference algorithm.

[0086] The final task sequence determination module 306 is used to compare the posterior probabilities of multiple candidate task sequences corresponding to each subtask graph, and determine the candidate task sequence with the highest posterior probability as the final task sequence corresponding to the subtask graph.

[0087] The resource allocation module 307 is used to allocate real-time resources based on the final task sequence, real-time resource status, and preset resource allocation functions.

[0088] In one embodiment, the type of task includes one or any combination of exploration tasks, mining tasks, processing tasks, and transportation tasks.

[0089] In one embodiment, the subtask graph generation module 303 is specifically used for:

[0090] Based on the type of task in the task map, the task map is decomposed to generate one or any combination of exploration sub-task maps, mining sub-task maps, processing sub-task maps, and transportation sub-task maps.

[0091] In one embodiment, the exploration subtask map includes one or any combination of geological survey subtasks, drilling design subtasks, and sample analysis subtasks;

[0092] The mining subtask diagram includes one or any combination of equipment deployment subtasks, production monitoring subtasks, and operation adjustment subtasks.

[0093] In one embodiment, the preset prior probability algorithm is as follows:

[0094] p(π) ∝ ;

[0095] p(ρ i ) ∝ ;

[0096] Where π is the task sequence; p(π) is the probability distribution of the task sequence, reflecting the priority and / or feasibility of the task plan; DL(π) represents the minimum description length of the task sequence π, and ∝ is proportional to; ρ i p(ρ) is the i-th task in the task sequence. i Let be the probability distribution of the i-th task; λ is the regularization parameter used to control the preference for reusing the i-th task. It is an exponential function used to calculate the probability of the i-th task.

[0097] In one embodiment, the preset posterior probability algorithm is as follows:

[0098] ;

[0099] ;

[0100] in, π is a normalization constant; π' is a candidate task sequence; Π is the set of candidate task sequences. .

[0101] In one embodiment, the final task sequence determination module 306 is specifically used for:

[0102] Compare the posterior probabilities of multiple candidate task sequences corresponding to each subtask graph, and select the candidate task sequence with the highest posterior probability. The final task sequence corresponding to the subtask graph is determined.

[0103] ;

[0104] in, It makes Find the variable point corresponding to the maximum value.

[0105] Figure 4 This is a schematic diagram of a specific example of an oil and gas industry chain decision optimization device provided in an embodiment of the present invention, such as... Figure 4 As shown, in one embodiment, the oil and gas industry chain decision optimization device further includes: a task execution order acquisition module 401, used to acquire the task execution order;

[0106] The default resource allocation function is:

[0107] ;

[0108] in, S represents the real-time resource status, indicating the resource status at time t; S represents the task execution order, indicating the position of the task in the task sequence. This represents the real-time resource status after allocation; f is a resource allocation function that adjusts based on task requirements and real-time resource conditions.

[0109] Compared with existing oil and gas industry chain decision optimization technologies, this invention obtains a task set, dependencies between tasks, real-time resource status, and a preset resource allocation function for the oil and gas industry chain. The task set includes multiple tasks; each task is a business operation performed within the oil and gas industry chain. A task graph is generated based on the task set and dependencies between tasks. The task graph is decomposed into multiple sub-task graphs based on the task types within it. Multiple candidate task sequences are generated for each sub-task graph according to a preset prior probability algorithm. The preset prior probability algorithm is set based on a minimum description length criterion and a reuse-biased prior algorithm. The prior algorithm is used to filter tasks and / or determine the execution order of tasks in the candidate task sequence according to the execution frequency and success rate of the tasks; the posterior probability of each candidate task sequence is determined according to the preset posterior probability algorithm, which is set according to the Bayesian inference algorithm; the posterior probabilities of multiple candidate task sequences corresponding to each sub-task graph are compared, and the candidate task sequence with the highest posterior probability is determined as the final task sequence corresponding to the sub-task graph; real-time resources are allocated according to the final task sequence, real-time resource status and preset resource allocation function, which can improve the decision-making efficiency of the oil and gas industry chain and reduce resource consumption and operating costs.

[0110] This invention provides a decision optimization method for the oil and gas industry chain based on hierarchical programming and grammatical induction, which can effectively improve the decision-making efficiency of the oil and gas industry chain and reduce resource consumption and operating costs. By decomposing complex decision problems into hierarchical subtasks, and using a grammatical induction model to generate and optimize task sequences, an efficient and low-cost decision-making process is achieved. The system architecture design makes this method easily applicable to real-world scenarios, enhancing the overall competitiveness and economic benefits of oil and gas enterprises.

[0111] This invention also provides a computer device. Figure 5 This is a schematic diagram of a computer device in an embodiment of the present invention. The computer device 500 includes a memory 510, a processor 520, and a computer program 530 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 530, it implements the above-mentioned oil and gas industry chain decision optimization method.

[0112] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described oil and gas industry chain decision optimization method.

[0113] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-mentioned oil and gas industry chain decision optimization method.

[0114] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0115] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0116] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0117] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0118] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A decision optimization method for the oil and gas industry chain, characterized in that, include: The task set, dependencies between tasks, real-time resource status, and preset resource allocation functions of the oil and gas industry chain are obtained; the task set includes multiple tasks. The task refers to business operations performed within the oil and gas industry chain; Based on the task set and the dependencies between tasks, a task graph is generated; Based on the type of task in the task graph, the task graph is decomposed to generate multiple sub-task graphs; According to the preset prior probability algorithm, multiple candidate task sequences are generated for each subtask graph; the preset prior probability algorithm is set according to the minimum description length criterion and the reuse bias prior algorithm; the reuse bias prior algorithm is used to filter tasks and / or determine the execution order of tasks in the candidate task sequence according to the execution frequency and execution success rate of the tasks. The posterior probability of each candidate task sequence is determined according to a preset posterior probability algorithm; the preset posterior probability algorithm is set according to the Bayesian inference algorithm. The posterior probabilities of multiple candidate task sequences corresponding to each subtask graph are compared, and the candidate task sequence with the highest posterior probability is determined as the final task sequence corresponding to the subtask graph. Real-time resources are allocated based on the final task sequence, real-time resource status, and preset resource allocation function; The preset prior probability algorithm is as follows: p ( π ) ∝ ； p ( ρ i ) ∝ ； in, π For task sequence; p ( π ) represents the probability distribution of the task sequence, reflecting the priority and / or feasibility of the task plan; DL ( π ) represents a task sequence π The minimum description length, ∝ is proportional to; ρ i For the first task in the sequence i One task; p ( ρ i ) is the first i The probability distribution of the i-th task; λ is a regularization parameter used to control the probability distribution of the i-th task. i A preference for reusing individual tasks; It is an exponential function used to calculate the first exponential function. i The probability of each task; The preset posterior probability algorithm is as follows: ； ； in, π is a normalization constant; π' is a candidate task sequence; Π is the set of candidate task sequences. .

2. The method as described in claim 1, characterized in that, The types of tasks include one or any combination of exploration tasks, mining tasks, processing tasks, and transportation tasks.

3. The method as described in claim 2, characterized in that, Based on the types of tasks in the task graph, the task graph is decomposed to generate multiple sub-task graphs, including: Based on the type of task in the task map, the task map is decomposed to generate one or any combination of exploration sub-task maps, mining sub-task maps, processing sub-task maps, and transportation sub-task maps.

4. The method as described in claim 3, characterized in that, The exploration subtask diagram includes one or any combination of geological survey subtasks, drilling design subtasks, and sample analysis subtasks; The mining subtask diagram includes one or any combination of equipment deployment subtasks, production monitoring subtasks, and operation adjustment subtasks.

5. The method as described in claim 1, characterized in that, The posterior probabilities of multiple candidate task sequences corresponding to each subtask graph are compared, and the candidate task sequence with the highest posterior probability is determined as the final task sequence corresponding to the subtask graph, including: Compare the posterior probabilities of multiple candidate task sequences corresponding to each subtask graph, and select the candidate task sequence with the highest posterior probability. The final task sequence corresponding to the subtask graph is determined. ； in, It makes Find the variable point corresponding to the maximum value.

6. The method as described in claim 1, characterized in that, Also includes: Obtain the task execution order; The preset resource allocation function is: ； in, This represents the real-time resource status, indicating the resource status at time t. S This indicates the task execution order and the position of the task in the task sequence. This refers to the real-time status of the allocated resources. f It is a resource allocation function that adjusts based on task requirements and real-time resource status.

7. A decision optimization device for the oil and gas industry chain, characterized in that, include: The acquisition module is used to acquire the task set, dependencies between tasks, real-time resource status, and preset resource allocation functions of the oil and gas industry chain; the task set includes multiple tasks; the tasks are business operations executed in the oil and gas industry chain. The task graph generation module is used to generate a task graph based on the task set and the dependencies between tasks; The subtask graph generation module is used to decompose the task graph according to the type of task in the task graph and generate multiple subtask graphs. The candidate task sequence generation module is used to generate multiple candidate task sequences for each subtask graph according to a preset prior probability algorithm. The preset prior probability algorithm is set according to the minimum description length criterion and the reuse biased prior algorithm. The reuse biased prior algorithm is used to filter tasks and / or determine the execution order of tasks in the candidate task sequence according to the execution frequency and execution success rate of the tasks. The posterior probability determination module is used to determine the posterior probability of each candidate task sequence according to a preset posterior probability algorithm; the preset posterior probability algorithm is set according to the Bayesian inference algorithm. The final task sequence determination module is used to compare the posterior probabilities of multiple candidate task sequences corresponding to each sub-task graph, and determine the candidate task sequence with the highest posterior probability as the final task sequence corresponding to the sub-task graph. The resource allocation module is used to allocate real-time resources based on the final task sequence, real-time resource status, and preset resource allocation functions. The preset prior probability algorithm is as follows: p ( π ) ∝ ； p ( ρ i ) ∝ ； in, π For task sequence; p ( π ) represents the probability distribution of the task sequence, reflecting the priority and / or feasibility of the task plan; DL ( π ) represents a task sequence π The minimum description length, ∝ is proportional to; ρ i For the first task in the sequence i One task; p ( ρ i ) is the first i The probability distribution of the i-th task; λ is a regularization parameter used to control the probability distribution of the i-th task. i A preference for reusing individual tasks; It is an exponential function used to calculate the first exponential function. i The probability of each task; The preset posterior probability algorithm is as follows: ； ； in, π is a normalization constant; π' is a candidate task sequence; Π is the set of candidate task sequences. .

8. 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 computer program, it implements the method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.

Images