Method and device for constructing an oil and gas intelligent application platform oriented to task adaptive processing

Abstract

The present application provides a method and device for constructing an oil and gas intelligent application platform for task adaptive processing, which belongs to the field of intelligent technology in the oil and gas industry and is used to solve the problems of poor flexibility in task processing, inaccurate matching and incomplete optimization in related technologies. In this method and device, it can use intelligent agents, operators, and workflows to intelligently decompose tasks, match intelligent operators, and construct and select intelligent workflows, thereby realizing intelligent processing of tasks, which is conducive to realizing efficient and intelligent processing of tasks in the oil and gas industry, and solving the problems of poor flexibility in task processing, inaccurate matching and incomplete optimization in existing technologies.

Description

Technical Field

[0001] The present application relates to the field of intelligent technology in the oil and gas industry, and in particular to a method and device for constructing an oil and gas intelligent application platform oriented to task adaptive processing. Background Art

[0002] In actual operations within the oil and gas industry, task processing faces numerous challenges. On the one hand, oil and gas tasks are complex and diverse, involving knowledge from multiple fields, including geology, engineering, and management. Task execution requires comprehensive consideration of multiple constraints, including underlying characteristics, equipment performance, cost budgets, safety, and environmental protection. On the other hand, traditional task processing methods, which primarily rely on manual experience and simple rule-based systems, present the following problems:

[0003] Lack of flexibility in task decomposition: Existing methods mostly adopt a fixed task decomposition model, which is difficult to flexibly adjust according to the dynamic changes and complex constraints of actual tasks, and cannot fully adapt to the complex and changing operating environment of the oil and gas industry.

[0004] Insufficient operator matching accuracy: The operator matching process often only considers a single factor, such as functional matching, while ignoring important dimensions such as historical execution performance and resource consumption. This results in the matched operators being inefficient in actual execution or failing to meet task requirements.

[0005] Incomplete workflow optimization: Workflow generation usually only focuses on one aspect, either task execution efficiency or cost, and lacks comprehensive optimization of multiple objectives, making it difficult to achieve overall optimization of task processing.

[0006] With the in-depth application of artificial intelligence technology in the oil and gas industry, there is an urgent need for a method and system that can realize adaptive intelligent processing of tasks to improve the efficiency of oil and gas operations, reduce costs and ensure operational safety. Summary of the Invention

[0007] The present application provides a method and device for constructing an oil and gas intelligent application platform for task adaptive processing. It realizes efficient and intelligent processing of oil and gas industry tasks through intelligent decomposition of tasks, precise operator matching, and multi-objective optimization workflow generation, and solves the problems of poor task processing flexibility, inaccurate matching, and incomplete optimization in related technologies.

[0008] In a first aspect, the present application provides a method for constructing an oil and gas intelligent application platform oriented to task adaptive processing. The method comprises:

[0009] Based on the pre-built agent and pre-acquired task-related information, the task is broken down into multiple subtasks, and the task constraints and dependencies between subtasks are determined;

[0010] Based on the pre-built operator library and historical task processing records, the dimensional evaluation value of each operator relative to each subtask and the comprehensive historical execution effect score are determined, and the optional matching operators for each subtask are screened;

[0011] Based on the task constraint information and the dependencies between subtasks, a feasible workflow structure is formed by traversing the optional matching operators of all subtasks;

[0012] For each feasible workflow structure, the preference of the feasible workflow structure is determined based on the subtask adaptability between the subtask and the optional matching operator in the feasible workflow structure and the operator coupling degree of each group of adjacent coupled optional matching operators, as well as the pre-acquired execution efficiency data and execution risk data of the feasible workflow structure. The optional workflow structure with the highest preference is called as the selected workflow structure to generate task plan information, and the task plan information is used to guide the implementation of the task.

[0013] By adopting the above technical solution, it is possible to use intelligent agents, operators, and workflows to intelligently decompose tasks, match intelligent operators, and construct and select intelligent workflows, thereby realizing intelligent processing of tasks. This is conducive to the efficient and intelligent processing of tasks in the oil and gas industry, and solves the problems of poor task processing flexibility, inaccurate matching, and incomplete optimization in existing technologies.

[0014] Furthermore, the process of decomposing a task into multiple subtasks based on a pre-built agent and pre-acquired task-related information, and determining task constraint information and dependencies between subtasks includes:

[0015] The intelligent agent includes an oil and gas knowledge graph. Based on the pre-built oil and gas knowledge graph, the intelligent agent uses a recursive analysis method to decompose the task into subtasks according to task-related information, and determines the set of constraint conditions as the task constraint information, and determines the relationship between the subtasks as a dependency relationship, and the subtasks cannot be divided any further.

[0016] Furthermore, the method of determining the dimensional evaluation value of each operator relative to multiple dimensions of each subtask and the comprehensive historical execution effect score based on the pre-built operator library and historical task processing records, and screening the optional matching operators for each subtask includes:

[0017] Determine the description information of operators and subtasks based on the pre-built oil and gas knowledge graph model, and calculate the semantic similarity between the description information of operators and subtasks as the functional matching degree of operators to subtasks;

[0018] Calculate the dimensional evaluation values of the operator on multiple dimensions of the subtask based on the pre-acquired historical task processing records, and determine the historical execution effect score by combining all the dimensional evaluation values;

[0019] Filter the optional matching operators of the subtask based on the dimension evaluation value and the historical execution effect score, where the historical execution effect score of the optional matching operator is higher than the effect score threshold and the dimension evaluation value of the specified dimension is higher than the dimension evaluation threshold preset for the corresponding dimension;

[0020] The dimension evaluation value includes one or more of an execution accuracy evaluation value, an execution efficiency evaluation value, and a resource consumption evaluation value. The historical task processing record includes a historical selection of a workflow structure and a workflow operation record of a historical selection of the workflow structure. The workflow operation record of a historical selection of the workflow structure includes the operation time of each historical operator therein.

[0021] The method for determining the execution accuracy evaluation value includes: setting a characterization operator Subtask oriented The execution accuracy evaluation value is , the historical task processing records include A historical subtask with the same description information as the subtask, The historical operators corresponding to the historical subtasks in the historical task processing records are AND operator If the description information is the same, ;

[0022] The method for determining the execution efficiency evaluation value includes: setting a characterization operator Subtask oriented The execution efficiency evaluation value is , determine the historical task processing records and the operator The historical operator whose semantic similarity of the description information is higher than the first preset similarity threshold is the operator Similar operators, and determine the operators in the historical operators The average running time of similar operators is , determine the historical task processing information and the operator The historical operators with the same description information are operators Homogeneous operators, and determine the operators in the historical operators The average time taken by the homogeneous operator is ,but ;

[0023] The method for determining the resource consumption evaluation value includes: setting a representation operator Subtask oriented The resource consumption evaluation value is , operator The resource usage is , the default resource limit is ,but .

[0024] Furthermore, the determining of the preference of the feasible workflow structure based on the subtask adaptation degree between the subtask and the optional matching operator in the feasible workflow structure and the operator coupling degree of each group of adjacent coupled optional matching operators and the pre-acquired execution efficiency data and execution risk data of the feasible workflow structure includes:

[0025] Determining the subtask compatibility between the subtask and the optional matching operator in the feasible workflow structure and the operator coupling degree of each group of adjacent coupled optional matching operators, as well as pre-acquired execution efficiency data and execution risk data of the feasible workflow structure;

[0026] The preference is determined by comprehensively considering the subtask fitness of all subtasks in the feasible workflow structure and the optional matching operators, the operator coupling of all groups of adjacent coupled optional matching operators, and the pre-acquired execution efficiency data and execution risk data of the feasible workflow structure. The preference is positively correlated with the subtask fitness, operator coupling and execution efficiency data, and negatively correlated with the execution risk data.

[0027] Furthermore, a method for determining the compatibility between a subtask and a subtask of an optional matching operator includes:

[0028] ;

[0029] Where, For operator Subtask oriented The subtask fitness of For operator With subtasks Functional matching, For operator Subtask oriented The historical execution performance score of is the resource adaptability, which is equal to the pre-acquired operator resource occupancy value divided by the pre-acquired total available resources. All are preset calculation weights greater than zero;

[0030] Assume that the total subtask fitness of the feasible workflow structure is ,but , m is the number of subtasks, and the preference of the feasible workflow structure is positively correlated with the total subtask fitness.

[0031] Furthermore, a method for determining the operator coupling degree of the adjacent coupling optional matching operator includes:

[0032] Suppose the preceding operator in a set of adjacent coupled operators is , and the subsequent operator is , in front of the operator The output of Input, pre-acquire the data compatibility defined between adjacent coupling operators , process connectivity and synergy gain value , the comprehensive matching degree between adjacent coupling operators is ,but

[0033] ;

[0034] Where, All are preset calculation weights greater than zero;

[0035] The data compatibility is obtained based on a pre-configured operator compatibility comparison table;

[0036] The process connectivity is determined based on the dependency relationship between subtasks. When the subtask corresponding to the subsequent operator depends on the previous operator, the process connectivity is 1, otherwise the process connectivity is 0.

[0037] The synergy gain effect value is determined based on the pre-marked historical task processing records. The historical task processing records are pre-marked with the execution effect value and running time of each historical operator. The average execution effect value when executed separately is , average running time , statistics after the operator The average execution effect value when executed separately is The average running time is , statistics first operator Input operator and subsequent operator The average values of the execution effects during coupled execution are The average running time is ,but , where All are preset calculation weights greater than zero;

[0038] The sum of the coupling degrees between operators of a feasible workflow structure is ,but , where is the set of edges in the feasible workflow structure.

[0039] Furthermore, the method for obtaining the execution efficiency data includes:

[0040] The historical task processing records are pre-marked with the similarity between the content of the task plan and the historical implementation plan of the historical selected workflow structure, and the historical duration of the historical task implementation plan. The historical task processing records with the feasible workflow structure are screened. The historical duration of the same historical selected workflow structure and historical task implementation plan is determined based on the similarity of the plans to be the weighted average of the historical durations of all historical task implementation plans corresponding to the same selected workflow structure as the expected duration, and the result of dividing the preset benchmark duration by the expected duration is calculated as the execution efficiency data.

[0041] Furthermore, the method for acquiring execution risk data includes:

[0042] Determine the task risk value of each subtask based on the oil and gas knowledge graph;

[0043] The similarity between the task plan content pre-marked with the historical selected workflow structure in the historical task processing records and the historical implementation plan, and the historical risk frequency of each subtask in the historical task implementation plan, are calculated for each subtask based on the plan similarity. The weighted sum of the historical risk frequencies of the corresponding subtasks in all historical task implementation plans is the total risk frequency of the subtask;

[0044] For each operator, let the task risk value of the subtask corresponding to the operator in the feasible workflow structure be The total frequency of risk is , the operator risk score is ,but , where e is a natural constant, Calculate weights for the preset and ;

[0045] The execution risk data of the feasible workflow structure is ,but .

[0046] Furthermore, the preference is determined based on the subtask fitness of all subtasks and optional matching operators in the comprehensive feasible workflow structure, the operator coupling of all groups of adjacent coupled optional matching operators, and the pre-acquired execution efficiency data and execution risk data of the feasible workflow structure. The preference is positively correlated with the subtask fitness, operator coupling, and execution efficiency data, including:

[0047] Assume that the total subtask fitness of the feasible workflow structure is The sum of the coupling degrees between operators is , execution efficiency data is , execution risk data is , the preference is ,but

[0048] ;

[0049] Where, are all calculation coefficients greater than zero, is the pre-acquired calculated influence coefficient, e is a natural constant;

[0050] Calculate the influence coefficient The methods for obtaining include:

[0051] Define multiple adjacent time windows of the same width in the pre-marked historical task processing records, determine the historical task processing records in each time window with the same historical selected workflow structure and target feasible workflow structure as reference records, and determine the average execution efficiency of the reference records in each time window. and average execution risk , x represents the sequence number of the time window, and the ratio of the average execution efficiency and average execution risk of each time window is calculated as the reference value of the reference record. With the sequence number as the horizontal coordinate and the reference value as the vertical coordinate, a straight line is fitted to minimize the sum of the squares of the vertical distances from all coordinate points to the straight line. Let the slope of the straight line be ,but , where is the preset calculation weight and .

[0052] In a second aspect, the present application provides a device for constructing a task-adaptive processing-oriented, particularly intelligent application platform, wherein the device applies any of the methods described in the first aspect above.

[0053] In summary, this application has at least the following beneficial effects:

[0054] A method and device for constructing an oil and gas intelligent application platform for task adaptive processing is provided, which can realize intelligent decomposition of oil and gas industry tasks, accurate operator matching, and workflow generation for multi-objective optimization, thus achieving efficient and intelligent processing of oil and gas industry tasks.

[0055] The self-developed operator matching and multi-objective optimization workflow determination and evaluation selection model make operator matching more precise and workflow selection more accurate.

[0056] It should be understood that the contents described in the Summary of the Invention are not intended to limit the key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0058] Figure 1 A flowchart of a method for constructing an oil and gas intelligent application platform oriented to task adaptive processing in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0059] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0060] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0061] The present application provides a method and device for constructing an oil and gas intelligent application platform for task adaptive processing, which can realize intelligent disassembly of oil and gas industry tasks, precise operator matching, and multi-objective optimization workflow generation, thereby realizing efficient and intelligent processing of oil and gas industry tasks.

[0062] In a first aspect, embodiments of the present application disclose a method for constructing an oil and gas intelligent application platform for task-adaptive processing, which can be executed by a server.

[0063] Figure 1 A flowchart of a method for constructing an oil and gas intelligent application platform oriented to task adaptive processing in an embodiment of the present application is shown.

[0064] Reference Figure 1 , the method specifically comprises the following steps:

[0065] S110: Based on the pre-built intelligent agent and pre-acquired task-related information, the task is decomposed into multiple subtasks, and the task constraint information and the dependency relationship between the subtasks are determined.

[0066] The method of this step specifically includes: the intelligent agent includes an oil and gas knowledge graph, and the intelligent agent uses a recursive analysis method based on a pre-built oil and gas knowledge graph to decompose the task into subtasks according to task-related information, and determines the set of constraint conditions as the task constraint information, determines the relationship between the subtasks as a dependency relationship, and the subtasks cannot be divided any further.

[0067] In one example, task-related information is a natural language description, which can be an input text document, collected conversations, or acquired text commands, specifically including some description of the task. The pre-built oil and gas knowledge graph includes various overall tasks for various scenarios, conventional decomposition methods for each overall task (generally, only one decomposition method is included for each typical task, but multiple decomposition methods are possible), descriptions of the overall task and its various subtasks, a tree-like relationship between the overall task and each subtask (including the smallest subtask, or atomic task), general constraints for each subtask, dependencies between subtasks (e.g., a subtask must be completed before another subtask, or a subtask must be completed within a specified time after another subtask), and subtask descriptions. Based on its interpretation of the task-related information, the agent uses the oil and gas knowledge graph and a recursive analysis model to decompose the task into a series of indivisible atomic tasks based on the knowledge graph. Subsequent subtasks are all based on this concept. The intelligent body contains a large model. The intelligent body uses the large model and oil and gas knowledge graph, and recursive analysis method to decompose and extract task-related information described in natural language. This is a general application method of the large model and proprietary knowledge graph. The specific working principle is not described here. It only needs to be able to clarify the task constraint information within the task and the dependency relationship between subtasks based on task-related information.

[0068] Here, we can model and define the disassembled tasks. Based on the subtasks, task constraints and dependencies between subtasks, we can build a directed acyclic graph of the tasks. The tasks are defined as triples. ,in, Represents the nodes corresponding to all subtasks, m is the number of subtasks, To represent the dependency between subtasks, express Need to Before completion, All constraints that represent task constraint information, Representing the task dependency matrix, If and only if .

[0069] S120: Determine the dimensional evaluation values of each operator relative to multiple dimensions of each subtask and the comprehensive historical execution effect score based on the pre-built operator library and historical task processing records, and screen the optional matching operators for each subtask.

[0070] The method of this step specifically includes: determining the description information of the operator and the subtask based on the pre-built oil and gas knowledge graph model, and calculating the semantic similarity between the description information of the operator and the subtask as the functional matching degree of the operator to the subtask;

[0071] Calculate the dimensional evaluation values of the operator on multiple dimensions of the subtask based on the pre-acquired historical task processing records, and determine the historical execution effect score by combining all the dimensional evaluation values;

[0072] The optional matching operator of the subtask is filtered based on the dimension evaluation value and the historical execution effect score, wherein the historical execution effect score of the optional matching operator is higher than the effect score threshold and the dimension evaluation value of the specified dimension is higher than the dimension evaluation threshold preset for the corresponding dimension.

[0073] Here, the operator description includes its function, processing methods, input requirements, output format, and so on. It is a natural language description and may be represented as a single statement or a series of labels. The subtask description is similar, including the subtask's general task objectives, general work content, general input data requirements, and general output data requirements. These can also be represented as a single statement or a series of labels, with the two forms of expression corresponding. If both descriptions are represented as a single statement, the overall semantic similarity is calculated as the semantic distance between the two. If both are represented as a series of labels, all of the labels are combined in a predetermined order, and the semantic similarity between the resulting combinations is calculated.

[0074] In the method of this step, the dimension evaluation value includes one or more of an execution accuracy evaluation value, an execution efficiency evaluation value, and a resource consumption evaluation value. The historical task processing record includes a historically selected workflow structure and a workflow operation record of a historically selected workflow structure. The workflow operation record of a historically selected workflow structure includes the operation time of each historical operator therein.

[0075] The method for determining the execution accuracy evaluation value includes: setting a characterization operator Subtask oriented The execution accuracy evaluation value is , the historical task processing records include A historical subtask with the same description information as the subtask, The historical operators corresponding to the historical subtasks in the historical task processing records are AND operator If the description information is the same, ;

[0076] The method for determining the execution efficiency evaluation value includes: setting a characterization operator Subtask oriented The execution efficiency evaluation value is , determine the historical task processing records and the operator The historical operator whose semantic similarity of the description information is higher than the first preset similarity threshold is the operator Similar operators, and determine the operators in the historical operators The average running time of similar operators is , determine the historical task processing information and the operator The historical operators with the same description information are operators Homogeneous operators, and determine the operators in the historical operators The average time taken by the homogeneous operator is ,but ;

[0077] The method for determining the resource consumption evaluation value includes: setting a representation operator Subtask oriented The resource consumption evaluation value is , operator The resource usage is , the default resource limit is ,but .

[0078] In one example, historical execution performance scores , where The default calculation weights are all greater than zero, and can be selected in sequence. .

[0079] Theoretically, historical task processing records include the selected workflow structure obtained from historical task-related information according to this method, as well as the task plan content and task implementation plan determined based on the selected workflow structure (some content of the task plan information of the selected workflow structure may be adjusted during the implementation process). The task implementation plan is the plan executed during the actual implementation of the task, and its implementation process is recorded and marked in the historical task processing record, such as the adjusted plan parts during implementation, the duration of each subtask during implementation, risk events, etc. Of course, the process of calling the selected workflow structure to generate the task plan content is also recorded, such as the running time of each operator. Based on this, the dimension evaluation value of the established evaluation dimension can be determined, and the dimension evaluation value of each dimension can be analyzed.

[0080] The evaluation dimensions may also consider only one or two of the aforementioned, or other evaluation dimensions, which are not listed here. The mathematical model for determining the historical execution performance score based on the dimensional evaluation values of the evaluation dimension may also be other, as long as it conforms to the general evaluation logic of the evaluation dimension.

[0081] In one example, using the filter Filter the optional matching operators for each subtask in the operator library. It is an empirical threshold and can be determined and optimized based on empirical data.

[0082] The filtering conditions can also be determined as other ones. It is only necessary to filter out operators that are more suitable for subtasks in terms of the specified evaluation dimension and the historical execution effect score according to the general logic of the evaluation dimension.

[0083] S130: Based on the task constraint information and the dependency relationship between subtasks, a feasible workflow structure is formed according to the optional matching operators of all subtasks.

[0084] Since the dependency relationship between subtasks is determined, a directed acyclic graph of subtasks can be drawn under the constraint of the dependency relationship. Each node of the directed acyclic graph represents a subtask, and each node can be filled with an optional matching operator of the subtask. In this way, all possible directed acyclic graphs and the possibility of traversing each node to select each optional matching operator can be obtained to obtain all optional workflow structures.

[0085] Of course, other methods can also be used, such as Petri nets and path search.

[0086] S140: For each feasible workflow structure, the preference of the feasible workflow structure is determined based on the subtask adaptability between the subtask and the optional matching operator in the feasible workflow structure and the operator coupling degree of each group of adjacent coupled optional matching operators, as well as the pre-acquired execution efficiency data and execution risk data of the feasible workflow structure, and the optional workflow structure with the highest preference is called as the selected workflow structure to generate task plan information, and the task plan information is used to guide the implementation of the task.

[0087] The method of this step specifically includes: determining the subtask fitness of the subtask and the optional matching operator in the feasible workflow structure, the operator coupling degree of each group of adjacent coupled optional matching operators, and the pre-acquired execution efficiency data and execution risk data of the feasible workflow structure; comprehensively determining the preference by combining the subtask fitness of all subtasks and the optional matching operator in the feasible workflow structure, the operator coupling degree of all groups of adjacent coupled optional matching operators, and the pre-acquired execution efficiency data and execution risk data of the feasible workflow structure. The preference is positively correlated with the subtask fitness, operator coupling and execution efficiency data, and negatively correlated with the execution risk data.

[0088] In the method of this step, the method for determining the compatibility between the subtask and the subtask of the optional matching operator includes:

[0089] ;

[0090] Where, For operator Subtask oriented The subtask fitness of For operator With subtasks Functional matching, For operator Subtask oriented The historical execution performance score of is the resource adaptability, which is equal to the pre-acquired operator resource occupancy value divided by the pre-acquired total available resources. All are preset calculation weights greater than zero;

[0091] Assume that the total subtask fitness of the feasible workflow structure is ,but , m is the number of subtasks, and the preference of the feasible workflow structure is positively correlated with the total subtask fitness. Of course, the subtask fitness of a single operator can also be considered in the above One or two factors, or other factors can be considered, as long as they can meet the evaluation logic of operator and subtask adaptation. The higher the value, the more compatible the operator is with the subtask.

[0092] Methods for determining the operator coupling degree of adjacent coupled optional matching operators include:

[0093] Suppose the preceding operator in a set of adjacent coupled operators is , and the subsequent operator is , in front of the operator The output of Input, pre-acquire the data compatibility defined between adjacent coupling operators , process connectivity and synergy gain value , the comprehensive matching degree between adjacent coupling operators is ,but

[0094] ;

[0095] Where, All are preset calculation weights greater than zero;

[0096] The data compatibility is obtained based on a pre-configured operator compatibility comparison table;

[0097] The process connectivity is determined based on the dependency relationship between subtasks. When the subtask corresponding to the subsequent operator depends on the previous operator, the process connectivity is 1, otherwise the process connectivity is 0.

[0098] The synergy gain effect value is determined based on the pre-marked historical task processing records. The historical task processing records are pre-marked with the execution effect value and running time of each historical operator. The average execution effect value when executed separately is , average running time , statistics after the operator The average execution effect value when executed separately is The average running time is , statistics first operator Input operator and subsequent operator The average values of the execution effects during coupled execution are The average running time is ,but , where All are preset calculation weights greater than zero;

[0099] The sum of the coupling degrees between operators of a feasible workflow structure is ,but , where is the set of edges in the feasible workflow structure.

[0100] The method for obtaining the execution efficiency data includes:

[0101] The historical task processing records are pre-marked with the similarity between the task plan content of the historical selected workflow structure (the optional workflow structure being called) and the historical implementation plan, and the historical duration of the historical task implementation plan. The historical task processing records are screened for tasks that are similar to the feasible workflow structure. The historical duration of the same historical selected workflow structure and historical task implementation plan is determined based on the similarity of the plans to be the weighted average of the historical durations of all historical task implementation plans corresponding to the same selected workflow structure as the expected duration, and the result of dividing the preset benchmark duration by the expected duration is calculated as the execution efficiency data.

[0102] Similarly, only one or two of the aforementioned data compatibility, process connectivity, and synergistic gain effect values may be considered, or other indicators that characterize the degree of operator coupling may be considered, without listing them one by one.

[0103] The method for acquiring execution risk data includes: determining a task risk value for each subtask based on an oil and gas knowledge graph, wherein the task risk value for the subtask is included in the description information of the subtask in the oil and gas knowledge graph;

[0104] The similarity between the task plan content pre-marked with the historical selected workflow structure in the historical task processing records and the historical implementation plan, and the historical risk frequency of each subtask in the historical task implementation plan, are calculated for each subtask based on the plan similarity. The weighted sum of the historical risk frequencies of the corresponding subtasks in all historical task implementation plans is the total risk frequency of the subtask;

[0105] For each operator, let the task risk value of the subtask corresponding to the operator in the feasible workflow structure be The total frequency of risk is , the operator risk score is ,but , where e is a natural constant, Calculate weights for the preset and ;

[0106] The execution risk data of the feasible workflow structure is ,but .

[0107] Based on the above content, the total subtask fitness of the feasible workflow structure is The sum of the coupling degrees between operators is , execution efficiency data is , execution risk data is , the preference is ,but

[0108] ;

[0109] Where, are all calculation coefficients greater than zero, is the pre-acquired computational influence coefficient, and e is a natural constant. Of course, the priority is determined by considering four factors: the subtask compatibility of all subtasks within the feasible workflow structure with the optional matching operators, the operator coupling degree of all groups of adjacent coupled optional matching operators, and the pre-acquired execution efficiency and execution risk data of the feasible workflow structure. Similarly, it is possible to determine the priority using only three, two, or one of these factors, or to consider additional factors, which are not listed here.

[0110] Here, the influence coefficient is calculated The methods for obtaining include:

[0111] Define multiple adjacent time windows of the same width in the pre-marked historical task processing records, determine the historical task processing records in each time window with the same historical selected workflow structure and target feasible workflow structure as reference records, and determine the average execution efficiency of the reference records in each time window. and average execution risk , x represents the sequence number of the time window, and the ratio of the average execution efficiency and average execution risk of each time window is calculated as the reference value of the reference record. With the sequence number as the horizontal coordinate and the reference value as the vertical coordinate, a straight line is fitted to minimize the sum of the squares of the vertical distances from all coordinate points to the straight line. Let the slope of the straight line be ,but , where is the preset calculation weight and .

[0112] In summary, this method intelligently decomposes tasks, intelligently and accurately matches operators to each subtask, constructs selectable workflow structures based on these operators, intelligently prioritizes these workflow structures, and uses these selected workflow structures to generate task solution information that can be implemented. This enables intelligent solution determination for oil and gas tasks, facilitating efficient and intelligent processing of these tasks.

[0113] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to the embodiments of this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required for this application.

[0114] In a second aspect, embodiments of the present application disclose a device for constructing a task-adaptive processing-oriented, particularly intelligent application platform. The device can be implemented as a server or included in a server. The device is used to execute the method disclosed in the first aspect above.

[0115] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described device can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0116] In summary, this application has at least the following beneficial effects:

[0117] A method and device for constructing an oil and gas intelligent application platform for task adaptive processing is provided, which can realize intelligent decomposition of oil and gas industry tasks, accurate operator matching, and workflow generation for multi-objective optimization, thus achieving efficient and intelligent processing of oil and gas industry tasks.

[0118] 2. Self-developed operator matching and multi-objective optimization workflow determination and evaluation selection models make operator matching more precise and workflow selection more accurate.

[0119] The above description is merely a preferred embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the aforementioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for constructing an oil and gas intelligent application platform for task adaptive processing, characterized in that: include: Based on the pre-built agent and pre-acquired task-related information, the task is broken down into multiple subtasks, and the task constraints and dependencies between subtasks are determined; Based on the pre-built operator library and historical task processing records, the dimensional evaluation value of each operator relative to each subtask and the comprehensive historical execution effect score are determined, and the optional matching operators for each subtask are screened; Based on the task constraint information and the dependencies between subtasks, a feasible workflow structure is formed by traversing the optional matching operators of all subtasks; For each feasible workflow structure, the preference of the feasible workflow structure is determined based on the subtask fitness between the subtasks in the feasible workflow structure and the subtasks of the optional matching operators and the operator coupling degree of each group of adjacent coupled optional matching operators, as well as the pre-acquired execution efficiency data and execution risk data of the feasible workflow structure. The optional workflow structure with the highest preference is called as the selected workflow structure to generate task solution information, and the task solution information is used to guide the implementation of the task; The method of determining the dimensional evaluation value of each operator relative to multiple dimensions of each subtask and the comprehensive historical execution effect score based on the pre-built operator library and historical task processing records, and screening the optional matching operators for each subtask includes: Determine the description information of operators and subtasks based on the pre-built oil and gas knowledge graph model, and calculate the semantic similarity between the description information of operators and subtasks as the functional matching degree of operators to subtasks; Calculate the dimensional evaluation values of the operator on multiple dimensions of the subtask based on the pre-acquired historical task processing records, and determine the historical execution effect score by combining all the dimensional evaluation values; Filter the optional matching operators of the subtask based on the dimension evaluation value and the historical execution effect score, where the historical execution effect score of the optional matching operator is higher than the effect score threshold and the dimension evaluation value of the specified dimension is higher than the dimension evaluation threshold preset for the corresponding dimension; The dimension evaluation value includes one or more of an execution accuracy evaluation value, an execution efficiency evaluation value, and a resource consumption evaluation value. The historical task processing record includes a historical selection of a workflow structure and a workflow operation record of a historical selection of the workflow structure. The workflow operation record of a historical selection of the workflow structure includes the operation time of each historical operator therein. The method for determining the execution accuracy evaluation value includes: setting a characterization operator Subtask oriented The execution accuracy evaluation value is , the historical task processing records include A historical subtask with the same description information as the subtask, The historical operators corresponding to the historical subtasks in the historical task processing records are AND operator If the description information is the same, ; The method for determining the execution efficiency evaluation value includes: setting a characterization operator Subtask oriented The execution efficiency evaluation value is , determine the historical task processing records and the operator The historical operator whose semantic similarity of the description information is higher than the first preset similarity threshold is the operator Similar operators, and determine the operators in the historical operators The average running time of similar operators is , determine the historical task processing information and the operator The historical operators with the same description information are operators Homogeneous operators, and determine the operators in the historical operators The average time taken by the homogeneous operator is ,but ; The method for determining the resource consumption evaluation value includes: setting a representation operator Subtask oriented The resource consumption evaluation value is , operator The resource usage is , the default resource limit is ,but ; The determining of the preference of the feasible workflow structure based on the subtask adaptation degree between the subtask and the optional matching operator in the feasible workflow structure and the operator coupling degree of each group of adjacent coupled optional matching operators and the pre-acquired execution efficiency data and execution risk data of the feasible workflow structure includes: Determining the subtask compatibility between the subtask and the optional matching operator in the feasible workflow structure and the operator coupling degree of each group of adjacent coupled optional matching operators, as well as pre-acquired execution efficiency data and execution risk data of the feasible workflow structure; The preference is determined by comprehensively considering the subtask fitness of all subtasks in the feasible workflow structure and the optional matching operators, the operator coupling of all groups of adjacent coupled optional matching operators, and the pre-acquired execution efficiency data and execution risk data of the feasible workflow structure. The preference is positively correlated with the subtask fitness, operator coupling and execution efficiency data, and negatively correlated with the execution risk data.

2. The method according to claim 1, characterized in that The process of decomposing a task into multiple subtasks based on a pre-built agent and pre-acquired task-related information, and determining task constraint information and dependencies between subtasks includes: The intelligent agent includes an oil and gas knowledge graph. Based on the pre-built oil and gas knowledge graph, the intelligent agent uses a recursive analysis method to decompose the task into subtasks according to task-related information, and determines the set of constraint conditions as the task constraint information, and determines the relationship between the subtasks as a dependency relationship, and the subtasks cannot be divided any further.

3. The method according to claim 1, characterized in that Methods for determining the compatibility of a subtask with an optional matching operator include: ； Where, For operator Subtask oriented The subtask fitness of For operator With subtasks Functional matching, For operator Subtask oriented The historical execution performance score of is the resource adaptability, which is equal to the pre-acquired operator resource occupancy value divided by the pre-acquired total available resources. 、 、 All are preset calculation weights greater than zero; Assume that the total subtask fitness of the feasible workflow structure is ,but , m is the number of subtasks, and the preference of the feasible workflow structure is positively correlated with the total subtask fitness.

4. The method according to claim 1, wherein Methods for determining the operator coupling degree of adjacent coupled optional matching operators include: Suppose the preceding operator in a set of adjacent coupled operators is , and the subsequent operator is , in front of the operator The output of Input, pre-acquire the data compatibility defined between adjacent coupling operators , process connectivity and synergy gain value , the comprehensive matching degree between adjacent coupling operators is ,but ； Where, 、 、 All are preset calculation weights greater than zero; The data compatibility is obtained based on a pre-configured operator compatibility comparison table; The process connectivity is determined based on the dependency relationship between subtasks. When the subtask corresponding to the subsequent operator depends on the previous operator, the process connectivity is 1, otherwise the process connectivity is 0. The synergy gain effect value is determined based on the pre-marked historical task processing records. The historical task processing records are pre-marked with the execution effect value and running time of each historical operator. The average execution effect value when executed separately is , average running time , statistics after the operator The average execution effect value when executed separately is The average running time is , statistics first operator Input operator and subsequent operator The average values of the execution effects during coupled execution are 、 The average running time is 、 ,but , where and All are preset calculation weights greater than zero; The sum of the coupling degrees between operators of a feasible workflow structure is ,but , where is the set of edges in the feasible workflow structure.

5. The method according to claim 1, wherein The method for obtaining the execution efficiency data includes: The historical task processing records are pre-marked with the similarity between the content of the task plan and the historical implementation plan of the historical selected workflow structure, and the historical duration of the historical task implementation plan. The historical task processing records with the feasible workflow structure are screened. The historical duration of the same historical selected workflow structure and historical task implementation plan is determined based on the similarity of the plans to be the weighted average of the historical durations of all historical task implementation plans corresponding to the same selected workflow structure as the expected duration, and the result of dividing the preset benchmark duration by the expected duration is calculated as the execution efficiency data.

6. The method according to claim 1, characterized in that The method for acquiring execution risk data includes: Determine the task risk value of each subtask based on the oil and gas knowledge graph; The similarity between the task plan content pre-marked with the historical selected workflow structure in the historical task processing records and the historical implementation plan, and the historical risk frequency of each subtask in the historical task implementation plan, are calculated for each subtask based on the plan similarity. The weighted sum of the historical risk frequencies of the corresponding subtasks in all historical task implementation plans is the total risk frequency of the subtask; For each operator, let the task risk value of the subtask corresponding to the operator in the feasible workflow structure be The total frequency of risk is , the operator risk score is ,but , where e is a natural constant, Calculate weights for the preset and ; The execution risk data of the feasible workflow structure is ,but .

7. The method according to claim 1, wherein: The preference is determined by comprehensively considering the subtask fitness of all subtasks in the feasible workflow structure and the subtask fitness of the optional matching operators, the operator coupling of all groups of adjacent coupled optional matching operators, and the pre-acquired execution efficiency data and execution risk data of the feasible workflow structure. The preference is positively correlated with the subtask fitness, operator coupling, and execution efficiency data, including: Assume that the total subtask fitness of the feasible workflow structure is The sum of the coupling degrees between operators is , execution efficiency data is , execution risk data is , the priority is Priority ,but ； Where, 、 、 、 are all calculation coefficients greater than zero, is the pre-acquired calculated influence coefficient, e is a natural constant; Calculate the influence coefficient The methods for obtaining include: Define multiple adjacent time windows of the same width in the pre-marked historical task processing records, determine the historical task processing records in each time window with the same historical selected workflow structure and target feasible workflow structure as reference records, and determine the average execution efficiency of the reference records in each time window. and average execution risk , x represents the sequence number of the time window, and the ratio of the average execution efficiency and average execution risk of each time window is calculated as the reference value of the reference record. With the sequence number as the horizontal coordinate and the reference value as the vertical coordinate, a straight line is fitted to minimize the sum of the squares of the vertical distances from all coordinate points to the straight line. Let the slope of the straight line be ,but , where is the preset calculation weight and .

8. A device for constructing an oil and gas intelligent application platform for task adaptive processing, characterized in that: The device applies the method according to any one of claims 1 to 7.

Images