Monitoring method and device for logging operation, electronic equipment and storage medium

Abstract

The invention provides a well logging operation supervision method and device, electronic equipment and a storage medium, and the method comprises the steps: determining an operation supervision workflow based on a pre-constructed well logging knowledge graph according to the operation characteristics of target well logging operation, determining a plurality of target operation nodes corresponding to target logging operation in the operation supervision workflow; for each target operation node, acquiring actual operation information of a target operation object expected to be supervised under the target operation node in the target logging operation; determining whether the target operation object meets the logging operation requirement or not by identifying the actual operation information; and if not, a rectification instruction for the target operation object is sent out according to the logging operation requirement. Therefore, whether the target operation object meets the logging operation requirement or not is determined based on the operation supervision workflow determined by the pre-constructed logging knowledge graph, the supervision timeliness of the logging operation is improved, and the labor cost is reduced.

Description

Technical Field

[0001] This application relates to the field of image recognition technology, and in particular to a supervision method, device, electronic device and storage medium for logging operations. Background Art

[0002] To strengthen safety management during logging operations and ensure the quality of logging operations, logging companies adopt the HSE system management standard for the logging operation workflow to ensure smooth construction and prevent safety accidents involving personnel casualties, radioactivity, and pyrotechnics. At present, the supervision work of logging operations mainly involves sending the company's own logging supervisors or hiring a third-party supervision company to the well site to collect logging operation information on-site and conduct supervision work in accordance with the HSE system standard, including whether equipment such as construction equipment, surface detection instruments, and downhole tools meet quality requirements; whether the installation of surface and downhole pulleys, the application of radioactive sources, and the application of pyrotechnics comply with technical specifications; whether operations such as the assembly of downhole instrument strings are reasonable and feasible, etc. After discovering problems that do not meet the HSE system standard, the logging team is ordered to rectify them in a timely manner, and the on-site supervision situation is reported to the relevant person in charge of the logging company.

[0003] When conducting on-site supervision of the HSE system standard for logging operations, there are three problems: First, it takes a long time and the work efficiency is low; for logging sites that are far away, it takes at least one day for supervisors to travel to and from the well site, slowing down the logging progress; second, relying solely on personal experience and knowledge accumulation to evaluate the implementation situation, due to differences in the sense of responsibility and technical level of supervisors, it is impossible to achieve standardized and consistent operation supervision; third, the problem of "too many wells and too few people", compared with the number of wells completed each year, the number of logging supervisors is seriously insufficient, resulting in a lack of HSE system standard supervision during the logging process of many development open-hole wells and cased wells, and there are potential safety risks. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a supervision method, device, electronic device and storage medium for logging operations, which can use the operation supervision workflow determined based on a pre-constructed logging knowledge graph to determine multiple target operation nodes involved in the target logging operation, and realize the supervision of whether the target operation object meets the logging operation requirements under each target operation node. Furthermore, it can improve the supervision timeliness of logging operations and reduce labor costs.

[0005] The embodiment of this application provides a supervision method for logging operations, and the supervision method includes:

[0006] Based on the operation supervision workflow determined by a pre-constructed well logging knowledge graph, according to the operation characteristics of the target well logging operation, determine multiple target operation nodes corresponding to the target well logging operation in the operation supervision workflow; wherein, the well logging knowledge graph is constructed based on the well logging operation requirements set under the HSE system;

[0007] For each target operation node, obtain the actual operation information of the target operation object expected to be supervised under this target operation node in the target well logging operation;

[0008] By identifying the actual operation information, determine whether the target operation object meets the well logging operation requirements;

[0009] If not, issue a rectification instruction for the target operation object according to the well logging operation requirements.

[0010] Furthermore, the supervision method further includes:

[0011] According to the number of completed operation nodes that have been identified among the multiple target operation nodes, determine the supervision progress of the supervision work for the target well logging operation;

[0012] Based on the identification results of the target operation objects expected to be supervised under each completed operation node, determine the operation quality level of the target well logging operation;

[0013] Generate a supervision report for the target well logging operation according to the supervision progress and the operation quality level.

[0014] Furthermore, determine the operation supervision workflow through the following steps:

[0015] Based on the well logging operation requirements set under the HSE system, establish a well logging knowledge graph;

[0016] Combined with the operation process information of the well logging operation, by searching the well logging knowledge graph, determine multiple well logging operation nodes in the well logging operation and the association relationships between the multiple well logging operation nodes;

[0017] According to the association relationships, combine the multiple well logging operation nodes to obtain the operation supervision workflow of the well logging operation.

[0018] Furthermore, the establishing a well logging knowledge graph based on the well logging operation requirements set under the HSE system includes:

[0019] Obtain well logging operation data samples that meet the well logging operation requirements;

[0020] By analyzing the well logging operation data samples, the operation type characteristics, operation process characteristics, wellbore attributes, operation requirements corresponding to the operation type characteristics, and operation requirements corresponding to the operation type characteristics, operation process characteristics, and wellbore attributes are determined;

[0021] Using the operation type characteristics, operation process characteristics, wellbore attributes, and operation requirements, an ontology model of the well logging knowledge graph is constructed;

[0022] Based on the ontology model, a plurality of supervised entities involved in the well logging operation, entity attributes of each supervised entity, and the association relationship between each supervised entity and its entity attributes are determined from the well logging operation data samples;

[0023] Based on the plurality of supervised entities, entity attributes of each supervised entity, and the association relationship between each supervised entity and its entity attributes, the well logging knowledge graph is established.

[0024] Further, the constructing an ontology model of the well logging knowledge graph using the operation type characteristics, operation process characteristics, wellbore attributes, and operation requirements includes:

[0025] Determining the well logging operation as the active subject of the ontology model;

[0026] Combining the primary-secondary relationship of the operation objects involved in the well logging operation during the well logging process, the wellbore is determined as the first well logging object of the ontology model;

[0027] Determining other operation objects except the wellbore among the operation objects involved in the well logging operation as the second well logging object of the ontology model;

[0028] Using the operation type characteristics, operation process characteristics, wellbore attributes, and operation requirements corresponding to the operation type characteristics, operation process characteristics, and wellbore attributes respectively, the well logging operation characteristics of the ontology model are determined;

[0029] According to the active subject, the first well logging object, the second well logging object, and the well logging operation characteristics, an ontology model of the well logging knowledge graph is constructed.

[0030] Further, for each target operation node, obtaining the actual operation information of the target operation object expected to be supervised under this target operation node in the target well logging operation includes:

[0031] For each target operation node, determining the target operation object expected to be supervised under this target operation node;

[0032] Obtain the initial operation image and actual operation data of the target operation object in the target logging operation;

[0033] Perform normalization processing on the initial operation image to obtain the actual operation image of the target operation object;

[0034] Integrate the actual operation data and the actual operation image to determine the actual operation information under each target operation node.

[0035] Further, the actual operation information includes the actual operation image and actual operation data of the target operation object; determining whether the target operation object meets the logging operation requirements by identifying the actual operation information includes:

[0036] Perform region division on the actual operation image in the actual operation information to determine the target recognition region of the target operation object in the actual operation image;

[0037] Extract keywords from the actual operation data in the actual operation information to determine the operation keywords for describing the target operation object;

[0038] Identify the target recognition region and the operation keywords to determine whether the target operation object meets the logging operation requirements.

[0039] The embodiment of the present application further provides a supervision device for logging operations, and the supervision device includes:

[0040] A node determination module, configured to determine, according to the operation characteristics of the target logging operation, multiple target operation nodes corresponding to the target logging operation in the operation supervision workflow determined based on a pre-constructed logging knowledge graph; wherein, the logging knowledge graph is constructed based on the logging operation requirements set under the HSE system;

[0041] An information acquisition module, configured to, for each target operation node, acquire the actual operation information of the target operation object expected to be supervised under the target operation node in the target logging operation;

[0042] An identification and judgment module, configured to determine whether the target operation object meets the logging operation requirements by identifying the actual operation information;

[0043] An instruction issuance module, configured to, if the target operation object does not meet the logging operation requirements, issue a rectification instruction for the target operation object according to the logging operation requirements.

[0044] Further, the supervision device further includes a supervision feedback module, and the supervision feedback module is used for:

[0045] Determine the supervision progress of the supervision work for the target logging operation according to the number of completed operation nodes among the multiple target operation nodes whose identification has been completed;

[0046] Based on the identification results of the target operation objects expected to be supervised under each completed operation node, determine the operation quality level of the target logging operation;

[0047] Generate a supervision report for the target logging operation according to the supervision progress and the operation quality level.

[0048] Further, when the node determination module is used to determine the operation supervision workflow, the node determination module is used to:

[0049] Based on the logging operation requirements set under the HSE system, establish a logging knowledge graph;

[0050] Combined with the operation process information of the logging operation, by searching the logging knowledge graph, determine multiple logging operation nodes in the logging operation and the association relationships between the multiple logging operation nodes;

[0051] According to the association relationships, combine the multiple logging operation nodes to obtain the operation supervision workflow of the logging operation.

[0052] Further, when the node determination module is used to establish a logging knowledge graph based on the logging operation requirements set under the HSE system, the node determination module is used to:

[0053] Obtain logging operation data samples that meet the logging operation requirements;

[0054] By analyzing the logging operation data samples, determine the operation type characteristics, operation process characteristics, wellbore attributes of the logging operation, and the operation requirements corresponding to the operation type characteristics, the operation process characteristics, and the wellbore attributes respectively;

[0055] Use the operation type characteristics, operation process characteristics, wellbore attributes, and the operation requirements corresponding to the operation type characteristics, the operation process characteristics, and the wellbore attributes respectively to construct the ontology model of the logging knowledge graph;

[0056] Based on the ontology model, determine multiple entities to be supervised involved in the logging operation, the attributes of each entity to be supervised, and the association relationships between the multiple entities to be supervised and the attributes of each entity to be supervised in the logging operation data samples;

[0057] Build a logging knowledge graph based on the multiple entities to be supervised, the attributes of each entity to be supervised, and the association relationships between the multiple entities to be supervised and the attributes of each entity to be supervised.

[0058] Further, when the node determination module is used to construct the ontology model of the logging knowledge graph by using the operation type features, operation process features, wellbore attributes, and operation requirements corresponding to the operation type features, the operation process features, and the wellbore attributes respectively, the node determination module is used to:

[0059] Determine the logging operation as the active subject of the ontology model;

[0060] Combine the subject-object relationship of the operation objects involved in the logging operation during the logging operation process, and determine the wellbore as the first logging object of the ontology model;

[0061] Determine the other operation objects except the wellbore among the operation objects involved in the logging operation as the second logging object of the ontology model;

[0062] Use the operation type features, operation process features, wellbore attributes, and operation requirements corresponding to the operation type features, the operation process features, and the wellbore attributes respectively to determine the logging operation features of the ontology model;

[0063] Construct the ontology model of the logging knowledge graph according to the active subject, the first logging object, the second logging object, and the logging operation features.

[0064] Further, when the information acquisition module is used to obtain the actual operation information of the target operation object expected to be supervised under each target operation node in the target logging operation for each target operation node, the information acquisition module is used to:

[0065] For each target operation node, determine the target operation object expected to be supervised under the target operation node;

[0066] Obtain the initial operation image and actual operation data of the target operation object in the target logging operation;

[0067] Perform normalization processing on the initial operation image to obtain the actual operation image of the target operation object;

[0068] Integrate the actual operation data and the actual operation image to determine the actual operation information under each target operation node.

[0069] Further, the actual operation information includes the actual operation image and actual operation data of the target operation object; when the recognition and judgment module is used to determine whether the target operation object meets the logging operation requirements by recognizing the actual operation information, the recognition and judgment module is configured to:

[0070] Divide the area of the actual operation image in the actual operation information to determine the target recognition area of the target operation object in the actual operation image;

[0071] Extract keywords from the actual operation data in the actual operation information to determine the operation keywords for describing the target operation object;

[0072] Recognize the target recognition area and the operation keywords to determine whether the target operation object meets the logging operation requirements.

[0073] An embodiment of the present application further provides an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the memory through the bus. When the machine-readable instructions are executed by the processor, the steps of the supervision method for logging operations as described above are executed.

[0074] An embodiment of the present application further provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is run by a processor, the steps of the supervision method for logging operations as described above are executed.

[0075] A supervision method, device, electronic device, and storage medium for logging operations provided by an embodiment of the present application. The supervision method includes: based on the operation supervision workflow determined by a pre-constructed logging knowledge graph, determining multiple target operation nodes corresponding to a target logging operation in the operation supervision workflow according to the operation characteristics of the target logging operation; wherein, the logging knowledge graph is constructed based on the logging operation requirements set under the HSE system; for each target operation node, obtaining the actual operation information of the target operation object expected to be supervised at the target operation node in the target logging operation; determining whether the target operation object meets the logging operation requirements by recognizing the actual operation information; if not, issuing a rectification instruction for the target operation object according to the logging operation requirements.

[0076] Compared with the method for supervising well logging operations on site in the prior art, by using the operation supervision workflow determined based on a pre-constructed well logging knowledge graph, multiple target operation nodes involved in the target well logging operation are determined, and the supervision of whether the target operation object meets the well logging operation requirements is implemented under each target operation node. Furthermore, the timeliness of well logging operation supervision can be improved, and the labor cost can be reduced.

[0077] To make the above objects, features, and advantages of the present application more obvious and understandable, the following specifically gives preferred embodiments and, in conjunction with the accompanying drawings, makes a detailed description as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other relevant drawings can also be obtained based on these drawings.

[0079] Figure 1 A flowchart of a method for supervising well logging operations provided by an embodiment of the present application;

[0080] Figure 2 A main model structure diagram of a well logging knowledge graph provided by an embodiment of the present application;

[0081] Figure 3 A construction process framework diagram of a well logging knowledge graph provided by an embodiment of the present application;

[0082] Figure 4 An effect diagram of a well logging knowledge graph provided by an embodiment of the present application;

[0083] Figure 5 A schematic structural diagram of a device for supervising well logging operations provided by an embodiment of the present application;

[0084] Figure 6 A schematic structural diagram of a device for supervising well logging operations provided by an embodiment of the present application;

[0085] Figure 7 A schematic structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0086] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Usually, the components of the embodiments of this application described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents the selected embodiments of this application. Based on the embodiments of this application, every other embodiment obtained by those skilled in the art without creative efforts belongs to the scope of protection of this application.

[0087] Through research, it is found that there are three problems in the on-site supervision of the HSE system standard for logging operations: First, it takes a long time and the work efficiency is low. For example, in Tarim Oilfield and Changqing Oilfield, it takes at least one day to travel back and forth to the well site, while the general logging operation time is also one day, resulting in low efficiency. Second, when evaluating the implementation of the HSE system standard in logging operations solely based on personal experience and knowledge accumulation, due to differences in the sense of responsibility and technical level of supervisors, it is difficult to achieve standardized and consistent operation supervision. Third, there is the problem of "more wells and fewer people". Compared with the number of wells drilled each year, the number of logging supervisors is seriously insufficient, resulting in a lack of supervision of the HSE system standard during the logging process of many development open-hole wells and cased wells, and there are potential safety risks.

[0088] Based on this, the embodiments of this application provide a method for supervising logging operations. By using the operation supervision workflow determined based on a pre-constructed logging knowledge graph, multiple target operation nodes involved in the target logging operation are determined, and the supervision of whether the target operation object meets the logging operation requirements is realized under each target operation node. Furthermore, the supervision timeliness of logging operations can be improved and the labor cost can be reduced.

[0089] Please refer to Figure 1 , Figure 1 which is a flowchart of a method for supervising logging operations provided by the embodiments of this application. As Figure 1 shown in, the method for supervising logging operations provided by the embodiments of this application includes:

[0090] S101. Based on the operation supervision workflow determined based on a pre-constructed logging knowledge graph, according to the operation characteristics of the target logging operation, determine multiple target operation nodes corresponding to the target logging operation in the operation supervision workflow; wherein, the logging knowledge graph is constructed based on the logging operation requirements set under the HSE system.

[0091] In this step, first, clarify the complete operation process information of the logging operation, including the logging operation objects, logging operation steps, logging operation specifications, etc. that need to be supervised in the logging operation process; then, based on the operation supervision workflow determined by the pre-constructed logging knowledge graph, clarify multiple logging operation nodes in the operation supervision workflow; finally, based on the operation supervision workflow determined by the pre-constructed logging knowledge graph, according to the complete operation process information of the logging operation, find the corresponding multiple target operation nodes of the current target logging operation in the operation supervision workflow.

[0092] It should be noted that the logging knowledge graph is constructed based on the logging operation requirements set under the HSE system, and is used to propose a comprehensive and standardized knowledge system for the all-round supervision of the logging operation process. It can not only clarify the operation objects and details in the operation process of the logging operation, but also calibrate the operation requirements for each link in each logging operation; the target logging operation is the specific logging operation currently being carried out. For example, the logging operation will have different operation processes and operation requirements for different wellbores or different operation locations. Then, for the current wellbore or operation location that is clear, the operation characteristics of the current target logging operation can be explored.

[0093] Furthermore, the operation supervision workflow is a computational program framework that calibrates the supervision workflow in the system program. It abstractly and generally describes the business rules between the workflow and its various operation steps. It represents the work logic and rules in the workflow in a proper model in the computer and implements calculations on it. Here, the main problem to be solved by the operation supervision workflow in the logging operation supervision is: to automatically transfer the workflow among multiple logging objects by using a computer according to the logging operation requirements under the HSE system to complete the collaborative work supported by the computer in order to achieve the business objectives of logging supervision.

[0094] Among them, the HSE system refers to a trinity management system of health, safety, and environment. It is an effective management method that identifies and evaluates in advance to determine the possible hazards and consequences severity in activities, and then takes effective preventive measures, control measures, and emergency plans to prevent accidents from occurring or reduce the risk level to the lowest, so as to reduce personal injuries, property losses, and environmental pollution. It is a management system commonly used in the international oil industry for the health, safety, and environment management of the oil and gas exploration and development and construction industries, and is also a management model generally recognized by current large international oil and petrochemical companies, with characteristics such as systematization, scientification, standardization, and institutionalization.

[0095] In an implementation manner of the present application, in specific implementation, the steps for determining the operation supervision workflow in step S101 may include:

[0096] S1011. Based on the logging operation requirements set under the HSE system, establish a logging knowledge graph.

[0097] In this step, first, obtain logging operation data samples that meet the logging operation requirements, and divide the data samples into structured data and unstructured data according to the data type; then, classify the logging operation data samples to determine the operation type characteristics, operation process characteristics, wellbore attributes of the logging operation, and the operation requirements corresponding to the operation type characteristics, the operation process characteristics, and the wellbore attributes respectively. Among them, the structured data can directly determine the above characteristics, attributes, and operation requirements; the unstructured data needs to perform event extraction, thesaurus annotation, and manual standard classification to determine the above characteristics, attributes, and operation requirements; then, according to the above characteristics, attributes, and operation requirements, construct the ontology model of the logging knowledge graph; then, determine multiple supervised entities involved in the logging operation, the attributes of each supervised entity, and the association relationships between the multiple supervised entities and the attributes of each supervised entity; finally, through the processing of unstructured data and knowledge fusion with structured data, establish a logging knowledge graph.

[0098] It should be noted that the logging knowledge graph is established around the logging operation requirements set in the HSE system. The logging knowledge graph has powerful advantages in big data analysis, intelligent recommendation, and interpretable artificial intelligence, etc. It can make full use of professional expert knowledge such as geology and logging, avoid robustness problems, and improve the accuracy of oil and gas layer identification. The logging knowledge graph is used in logging operation supervision to calibrate all business processes of the logging operation, and for each business process and the logging objects involved, carry out standardized limitations according to the logging operation requirements set in the HSE system.

[0099] In an implementation manner of the present application, in specific implementation, the steps of establishing a logging knowledge graph in step S1011 may include:

[0100] S10111. Obtain logging operation data samples that meet the logging operation requirements.

[0101] In this step, first, extract the data that meets the logging operation requirements through the stored historical data of the logging operation; then, combine the specific clauses of the logging operation requirements set under the HES system, and integrate the historical data and the logging operation clauses; finally, obtain the logging operation data samples that meet the logging operation requirements.

[0102] S10112. Determine the operation type characteristics, operation process characteristics, wellbore attributes, operation requirements corresponding to the operation type characteristics, operation requirements corresponding to the operation process characteristics, and operation requirements corresponding to the wellbore attributes of the logging operation by analyzing the logging operation data samples.

[0103] In this step, the knowledge system classification is the basis for constructing the knowledge graph and realizing knowledge management. Focusing on the logging operation, the above-mentioned logging operation data samples are divided into structured data and unstructured data according to the data type, which are used to determine the data that can be directly constructed and the data that needs to be processed during the construction of the knowledge graph. Among them, the structured data includes a large amount of data accumulated during the logging process that can directly reflect whether the logging operation meets the requirements of the logging operation under the HSE system, and the unstructured data includes digital data such as research reports, literature, and multimedia. For the structured data, the characteristics can be directly determined through the classification method of entity alignment. For the unstructured data, event extraction needs to be carried out first, and then according to the logging domain thesaurus and manual knowledge annotation, the unstructured data after event extraction is classified by entity alignment to determine the operation type characteristics, operation process characteristics, wellbore attributes, operation requirements corresponding to the operation type characteristics, operation requirements corresponding to the operation process characteristics, and operation requirements corresponding to the wellbore attributes of the logging operation.

[0104] Specifically, first, determine the operation type, operation process, and wellbore attributes of the logging operation. Here, the wellbore category mainly includes the category and type of the wellbore. Then, determine the characteristics of the operation type and operation process of the logging operation. Here, the characteristics of the operation type and operation process mainly include the main operation process of the logging operation and the core supervision operation points of each logging operation. Next, determine the operation requirements corresponding to the operation type characteristics, the operation process characteristics, and the wellbore attributes respectively. Finally, integrate the content of the knowledge system classification according to the above-classified knowledge.

[0105] Exemplarily, please refer to Table 1, which is the knowledge system classification table of the logging operation:

[0106] Table 1 Knowledge System Classification Table of Logging Operation

[0107]

[0108]

[0109] Among them, the first-level classification includes four aspects: well logging operation types, well logging operation processes, wellbore categories, and wellbore types. Each first-level type consists of several second-level types. For example, well logging operation types can be divided into open hole well logging, monitored well logging, production well logging, and logging while drilling. Each second-level type further corresponds to third-level types, including three third-level types: requirements in the early stage of the operation, requirements in the middle stage of the operation, and requirements in the later stage of the operation. Each third-level type is further subdivided into fourth-level types as needed, including the specific content of each well logging operation requirement.

[0110] S10113. Use the operation type characteristics, the operation process characteristics, the wellbore attributes, and the operation requirements to construct the ontology model of the well logging knowledge graph.

[0111] In this step, the construction of the ontology model is the basis for the construction of the well logging operation knowledge graph. It consists of three parts: objects, activities, and characteristics. Activities act on objects, and characteristics are used to describe activities and objects. First, clarify that the basic ontology model includes the well logging operation itself, the well logging operation objects corresponding to the well logging operation, and the characteristics corresponding to the well logging operation and the well logging operation objects. Then, use the principle of correspondence between objects and characteristics for construction. Finally, based on the business processes, data sets, and technical requirements involved in well logging operations, a knowledge graph ontology consisting of activity subjects, well logging objects, and well logging operation characteristics is constructed.

[0112] Exemplarily, please refer to Figure 2 , Figure 2 which is the main model structure diagram of a well logging knowledge graph provided by an embodiment of the present application. As Figure 2 shown, the well logging operation, as the activity subject, respectively corresponds to the well logging operation object and the well logging operation characteristics. The well logging operation objects are divided into the first well logging object and the second well logging object. Here, the first well logging object is the wellbore of the well logging operation, and the second well logging object is the well logging team, personnel, equipment, etc. The well logging operation characteristics correspond to the well logging operation activity ontology and the well logging object, including the operation type characteristics, the operation process characteristics, the wellbore attributes, and the well logging operation requirements corresponding to the operation type characteristics, the operation process characteristics, and the wellbore attributes respectively.

[0113] In an implementation manner of the present application, in specific implementation, the steps of constructing the ontology model of the well logging knowledge graph in step S1013 may include:

[0114] S101131. Determine the well logging operation as the activity subject of the ontology model.

[0115] In this step, since the purpose of establishing the ontology model of the knowledge graph is to supervise and manage the well logging operation activity, the well logging operation is determined as the activity subject of the ontology model of the well logging knowledge graph.

[0116] S101132. Combine the principal - object relationship of the operation objects involved in the logging operation during the logging operation process, and determine the wellbore as the first logging object of the ontology model.

[0117] In this step, around the logging operation which is the active subject of the ontology model, find the relevant objects of the logging operation activities. For example, the wellbore, logging personnel, logging equipment, etc. In addition, when conducting a logging operation, the operation process can be summarized as logging personnel using logging equipment to conduct logging operations on the wellbore. Thus, it can be analyzed that the wellbore is the object of the logging operation, and further determine that the wellbore is the first logging object of the ontology model.

[0118] S101133. Determine the other operation objects involved in the logging operation except the wellbore as the second logging object of the ontology model.

[0119] In this step, according to the analysis of the principal - object of the operation process, it can be determined that logging objects such as logging personnel, logging equipment, and logging teams are the subjects for conducting logging operations on the wellbore as the object, and further determine that logging objects such as logging personnel, logging equipment, and logging teams are the first logging objects of the ontology model.

[0120] S101134. Use the operation type characteristics, operation process characteristics, wellbore attributes, operation requirements corresponding to the operation type characteristics, operation requirements corresponding to the operation process characteristics, and operation requirements corresponding to the wellbore attributes respectively to determine the logging operation characteristics of the ontology model.

[0121] In this step, since the logging operation characteristics are oriented towards all activities and objects of the logging operation, the content obtained through the knowledge system classification above is an important basis for constructing the logging operation characteristics part of the ontology model. Here, determine the operation type characteristics, operation process characteristics, wellbore attributes, and operation requirements corresponding to the operation type characteristics, the operation process characteristics, and the wellbore attributes respectively as the logging operation characteristics of the ontology model.

[0122] S101135. Construct the ontology model of the logging knowledge graph according to the active subject, the first logging object, the second logging object, and the logging operation characteristics.

[0123] In this step, combined with the active subject, the first logging object, the second logging object, and the logging operation characteristics involved in the determined ontology model, by determining "logging operation" as the active subject, based on this active subject, determine the logging operation objects of the active subject and the characteristics of the active ontology, and then determine the characteristics of the logging operation objects, and then construct the ontology model of the logging knowledge graph.

[0124] S10114. Based on the ontology model, determine multiple entities to be supervised involved in the logging operation, the entity attributes of each entity to be supervised, and the association relationships between each entity to be supervised and the entity attributes of the entity to be supervised from the logging operation data samples.

[0125] It should be noted that constructing a knowledge graph is a process of deeply extracting and managing logging knowledge achievements, empirical understandings, and related data, specifically including named entity recognition, relationship extraction, and classification and extraction of attributes; in an implementable manner of this application, establishing a logging knowledge graph requires determining multiple entities to be supervised involved in the logging operation, the attributes of each entity to be supervised, and the association relationships between multiple entities to be supervised and the attributes of each entity to be supervised.

[0126] In this step, determining multiple entities to be supervised is the basis of information extraction. Its task is to find named entities from unstructured data such as field photos, video frames, or documents and mark their types; relationship extraction requires extracting the association relationships between two or more entities to be supervised from the text; attributes generally refer to the attributes of the entities to be supervised or the components that make up the entities to be supervised, and need to be extracted and classified according to the composition of knowledge and the purpose of the task.

[0127] Specifically, for example, to complete the supervision of the logging operation, first, it is necessary to clarify the first logging object for supervising the logging operation, that is, the wellbore is the most important entity to be supervised; then, determine entities such as the logging team, logging operation personnel, and radiation source as the second logging objects as other entities to be supervised; then, the attributes of each entity to be supervised will be derived from the entities to be supervised, that is, the parameter requirements, operation requirements, and specification requirements that the entities to be supervised need to meet, etc., which are the contents that need to supervise the entities to be supervised to complete; finally, based on the ontology model, by analyzing the logging operation process that meets the logging operation requirements under the HSE system, determine the association relationships between multiple entities to be supervised and the attributes of each entity to be supervised.

[0128] S10115. Based on the multiple entities to be supervised, the entity attributes of each entity to be supervised, and the association relationships between each entity to be supervised and the entity attributes of the entity to be supervised, establish the logging knowledge graph.

[0129] It should be noted that in the process of constructing the logging knowledge graph, to reduce the ambiguity of the knowledge graph, referring to the China National Petroleum Exploration and Development Data Model (EPDM) standard, the integration of knowledge achievements and data is realized and deeply integrated. The integration of logging operation knowledge includes the integration of the concept layer and the entity layer. The integration of the concept layer is mainly based on the ontology model of the logging knowledge graph for knowledge expansion, and the integration of the entity layer uses the method of entity linking.

[0130] In this step, first, based on the well logging system knowledge formed by classifying the knowledge system, the determined entities to be supervised are applied to the supervised learning algorithm to obtain binary relation data. Then, the candidate entities to be supervised are trained by manually annotating and performing part-of-speech tagging on the unstructured data in the domain word library. The candidate entities to be supervised are sorted out and the binary relation data is screened out through a classifier. After that, through the supervised learning method, event extraction is performed on the unstructured data, and entity alignment is performed on the binary relation data. Finally, the extracted events and the binary relation data after entity alignment are fused through the entity similarity algorithm to construct a well logging knowledge graph.

[0131] Exemplarily, to establish a well logging knowledge graph, it is necessary to clarify the processing process of the knowledge graph for the system data flow. Please refer to Figure 3 , Figure 3 which is a framework diagram of the construction process of a well logging knowledge graph provided by an embodiment of the present application. As Figure 3 shown in, first, the data center divides the well logging operation data samples transmitted and meeting the well logging operation requirements into two categories: structured data and unstructured data. Here, the multi-source structured data includes a large amount of data accumulated during the well logging process that can directly reflect whether the well logging operation meets the well logging operation requirements under the HSE system, and the unstructured data includes digital data such as research reports, literature, and multimedia. Then, binary relation data processing is performed on the structured data and then entity alignment is performed to prepare for subsequent knowledge fusion into a graph. Next, event extraction is performed on the unstructured data, and the extracted events are descriptive data that can directly reflect the well logging operation process, and this event also prepares for subsequent knowledge fusion. Secondly, according to the well logging domain word library and manual knowledge annotation, the unstructured data after event extraction is classified, and the classified structured data is processed for binary relation data and then entity alignment is performed. Finally, the structured data obtained after binary relation data processing and then entity alignment and the extracted events are knowledge-fused to construct a well logging knowledge graph.

[0132] Furthermore, please refer to Figure 4 , Figure 4 which is an effect diagram of a well logging knowledge graph provided by an embodiment of the present application. As Figure 4 shown in, the entities to be supervised in the well logging knowledge graph are entity nodes with an attribute that can "diverge" outward; the attributes of each entity to be supervised are derived from the entity to be supervised; the association relationships between multiple entities to be supervised and the attributes of each entity to be supervised are represented by arrows indicating the relationship categories where the associations occur.

[0133] S1012. Combine the operation process information of the well logging operation, and determine multiple well logging operation nodes and the association relationships between the multiple well logging operation nodes by searching the well logging knowledge graph.

[0134] In this step, first, combine the operation process information of the logging operation that meets the requirements of the logging operation. For example, in the logging operation process, the relevant operations of the radiation source that need to be supervised key points, and each link of the operation process steps of the logging exploration needs to be supervised key points, etc.; then, by searching the established logging knowledge graph, according to the entities to be supervised and the attributes of the entities to be supervised in the logging knowledge graph, determine multiple logging operation nodes in the logging operation; finally, according to the association relationship between the multiple entities to be supervised and the attributes of each entity to be supervised in the logging knowledge graph, determine the association relationship between the multiple logging operation nodes.

[0135] S1013. According to the association relationship, combine the multiple logging operation nodes to obtain the operation supervision workflow of the logging operation.

[0136] In this step, through the determined multiple logging operation nodes, according to the association relationship between the multiple logging operation nodes determined in step S1012, combine them to obtain the operation supervision workflow of the logging operation.

[0137] Furthermore, after obtaining the operation supervision workflow of the logging operation, it is necessary to configure the environment before proceeding with the subsequent logging operation supervision work. Specifically, first, according to the business requirements, the system has set four types of user roles: system administrator, supervision administrator, logging supervisor, and logging operation engineer. Different roles correspond to the permissions of the system function modules. Here, the system configuration is mainly operated by the system administrator role to configure and manage various resources and permissions of the entire system; the supervision administrator role can configure and manage logging supervisors, teams, wells, and resource files to meet the differential configuration and information management of different oil and gas fields; then, through the environment configuration page, configure information such as logging supervisors, logging teams, logging projects, and wellbore data in the oilfield area; finally, the supervision administrator can realize the real-time control of the supervised logging information on the work dynamic management page, including task configuration and the supervised well dynamic function module; create a supervision task on the task configuration page and assign the supervision task to different logging supervisors.

[0138] S102. For each target operation node, obtain the actual operation information of the target operation object expected to be supervised under the target operation node in the target logging operation.

[0139] It should be noted that for each target operation node, the obtained actual operation information includes actual operation images and actual operation data. Here, the actual operation images and actual operation data are the relevant images and data of the target operation object expected to be supervised obtained under the target operation node.

[0140] In an implementation manner of the present application, in specific implementation, step S102 may include:

[0141] S1021. For each target job node, determine the target job object to be supervised under the target job node.

[0142] In this step, by searching the logging knowledge graph, for each target job node, the target job object to be supervised under the target job node can be found. Exemplarily, for the target job node of "marking a standard warning area at the radioactive source site during logging operations", the target job object that needs to be supervised for this target job node can be searched out in the logging knowledge graph as the radioactive source.

[0143] S1022. Obtain the initial operation image and actual operation data of the target job object in the target logging operation.

[0144] In this step, the user uploads the operation image and operation data corresponding to each target job node in the operation supervision workflow of the logging operation. Specifically, the operation image is the uploaded initial operation image, which is an operation image taken by the role of the logging supervision engineer among the users at the logging operation site, or an operation image taken by the camera set at the logging operation site; the operation data is the work document related to logging operation supervision uploaded by the logging supervision engineer at the logging operation site, and the work document includes text or digital data such as logging work process records, radioactive source usage records, and work records of logging personnel.

[0145] S1023. Perform normalization processing on the initial operation image to obtain the actual operation image of the target job object.

[0146] In this step, since the obtained is the initial operation image of the target job object in the target logging operation, there will be a situation where the image standards are inconsistent, which will affect the subsequent steps of image recognition. Here, in this application, by performing normalization processing on the initial operation image, the initial operation image is standardized to obtain the actual operation image of the target job object.

[0147] Specifically, the Min - Max image normalization method is used to perform normalization processing on the initial operation image. First, it is determined to convert the initial operation image into a traversed image matrix; then, for each pixel in the traversed image matrix, the pixel maximum value and pixel minimum value are set; finally, the normalization processing of the image data is performed through the pixel conversion formula, and the specific formula is as follows.

[0148] x ′ =(x - min(x)) / (max(x) - min(x)).

[0149] where x ′The pixel obtained after normalization processing; x is the initial pixel; min(x) is the set minimum pixel value; max(x) is the set maximum pixel value.

[0150] S1024. Integrate the actual operation data and the actual operation image, and determine the actual operation information under each target operation node.

[0151] In this step, by integrating the obtained actual operation data and the actual operation image obtained through normalization processing, the integrated actual operation information is allocated to each target operation node in the operation supervision workflow.

[0152] S103. Determine whether the target operation object meets the logging operation requirements by identifying the actual operation information.

[0153] It should be noted that it is crucial for logging operation supervision to determine whether the target operation object corresponding to each target operation node meets the logging operation requirements under the HSE system by identifying the obtained actual operation information, that is, to judge whether the target operation object meets the operation requirements through information identification to achieve the purpose of logging operation supervision.

[0154] In an implementation manner of the present application, in specific implementation, step S103 may include:

[0155] S1031. Divide the area of the actual operation image in the actual operation information, and determine the target recognition area of the target operation object in the actual operation image.

[0156] In this step, in order to accurately find the target operation object expected to be supervised in the actual operation image, the actual operation image needs to be divided; specifically, it is divided along the contour of the target operation object in the actual operation image, and the area in the contour is determined as the target recognition area of the target operation object in the actual operation image.

[0157] Exemplarily, for example, if the current target operation node is to supervise the clothing of logging personnel and determine whether the clothing of logging personnel meets the logging operation requirements. First, determine the target operation object as logging personnel; then, find the contour of the logging personnel in the actual operation image; then divide the actual operation image along the contour of the logging personnel; finally, determine the area within the divided contour as the target recognition area of the target operation object in the actual operation image.

[0158] S1032. Extract keywords from the actual operation data in the actual operation information, and determine the operation keywords used to describe the target operation object.

[0159] In this step, the actual operation data is the work documents related to well logging operation supervision uploaded by the well logging supervision engineer at the well logging operation site. The specific well logging parameters and behaviors of the target operation object will be recorded in the work documents in the form of words and numbers. In order to accurately find out the attribute parameters and operation behaviors of the target operation object expected to be supervised in the actual operation data, keyword extraction needs to be performed on the actual operation data. Specifically, first, find out the description statements about the target operation object in the actual operation data; then determine the keywords such as the target operation object itself, the state or parameters of the target operation object, and the specific operation content of the target operation object in the description statements; finally, extract the above keywords to determine the operation keywords used to describe the target operation object for subsequent identification and judgment.

[0160] Exemplarily, for example, the current target operation node is to supervise the use of radioactive sources and judge whether the usage times and usage methods of radioactive sources meet the requirements of well logging operations. First, determine that the target operation object is the radioactive source; then, in the actual operation data, find out the statements describing the radioactive source; then find the keywords of the radioactive source itself, the state of the radioactive source, the usage records of the radioactive source, etc. in the statements describing the radioactive source; finally, extract the above keywords to determine the operation keywords used to describe the target operation object.

[0161] S1032. Identify the target recognition area and the operation keywords to determine whether the target operation object meets the well logging operation requirements.

[0162] In this step, identify the determined target recognition area and operation keywords, and judge whether the current target operation object meets the well logging operation requirements according to the specific content of the well logging operation requirements for the current target operation object in the well logging knowledge graph.

[0163] S104. If not, issue a rectification instruction for the target operation object according to the well logging operation requirements.

[0164] In this step, if the current target operation object does not meet the well logging operation requirements, first, for the current target operation object, find out the standard content of the well logging operation requirements corresponding to it in the well logging knowledge graph; then integrate the current target operation object that does not meet the well logging operation requirements and the found standard content of the well logging operation requirements into the rectification instruction; finally, issue the rectification instruction for this target operation object.

[0165] Exemplarily, for example, during the mid - stage of a logging operation, the surface and downhole pulleys in the logging equipment need to be installed. Then, the actual operation images of the target object, which is the surface and downhole pulley, obtained on - site are recognized to determine whether the installation of the surface and downhole pulley meets the standards set for its installation in the logging operation requirements. If the installation of the surface and downhole pulley does not meet the standards, for example, the fixing device of the pulley is used incorrectly, etc., a rectification instruction that meets the logging operation requirements for the target pulley is issued.

[0166] Further, if the current target operation object meets the logging operation requirements, then continue to identify and determine whether other target operation objects meet the logging operation requirements.

[0167] Optionally, in addition to the logging operation supervision method including the steps S101 to S104, it further includes steps S105 to S107. Specifically, steps S105 to S107 are used to illustrate the method of feeding back the logging operation supervision report according to the completion progress and operation quality of the supervision, which is beneficial for users to monitor the supervision situation of the logging operation in real - time.

[0168] Here, the specific steps of steps S101 to S104 are as described above and will not be elaborated here.

[0169] S105. Determine the supervision progress of the supervision work for the target logging operation according to the number of completed operation nodes that have been recognized among the multiple target operation nodes.

[0170] In this step, the proportion of the completed operation nodes that have been recognized among all the target operation nodes among the multiple target operation nodes is determined as the supervision progress of the supervision work for the target logging operation.

[0171] Specifically, in an implementation manner of the present application, for example, if there are 10 target operation nodes in the operation supervision workflow of the target logging operation, then according to the above - mentioned logging supervision method, if the recognition and judgment of 6 target operation nodes have been completed, it is determined that the supervision progress of the supervision work for the current target logging operation is 60%.

[0172] S106. Determine the operation quality level of the target logging operation based on the recognition results of the target operation objects expected to be supervised under each completed operation node.

[0173] In this step, the proportion of the number of nodes whose recognition results of the target operation objects expected to be supervised under each completed operation node meet the logging operation requirements among the number of nodes that have been recognized is used to determine the operation quality level of the target logging operation according to this proportion.

[0174] Exemplarily, the job quality level is divided into four levels, including excellent, good, medium, and poor. When the proportion of nodes meeting the logging operation requirements is 76% or more, the job quality level of the target logging operation is determined to be excellent; when the proportion of nodes meeting the logging operation requirements is 51%-75%, the job quality level of the target logging operation is determined to be good; when the proportion of nodes meeting the logging operation requirements is 26%-50%, the job quality level of the target logging operation is determined to be medium; when the proportion of nodes meeting the logging operation requirements is 25% or less, the job quality level of the target logging operation is determined to be poor.

[0175] If there are 10 target job nodes in the job supervision workflow of the target logging operation and 6 completed job nodes have been completed, the recognition results of the 6 completed job nodes can be used to determine the job quality level of the target logging operation. If there are 3 completed job nodes meeting the logging operation requirements among the 6 completed job nodes, it can be determined that the number of completed job nodes meeting the logging operation requirements accounts for 50% of the total number of completed job nodes that have been recognized. Therefore, the current job quality level can be determined to be medium.

[0176] S107. Generate a supervision report for the target logging operation according to the supervision progress and the job quality level.

[0177] In this step, the supervision progress of the supervision work of the determined target logging operation and the job quality level of the target logging operation determined in step S106 are integrated to generate a supervision report for the target logging operation and feedback it to the user on the page, so as to facilitate the user to conduct real-time supervision of the entire logging operation and understand the supervision work situation at any time.

[0178] The supervision method for logging operations provided in the embodiments of the present application is based on the job supervision workflow determined by a pre-constructed logging knowledge graph. According to the job characteristics of the target logging operation, multiple target job nodes corresponding to the target logging operation in the job supervision workflow are determined; wherein, the logging knowledge graph is constructed based on the logging operation requirements set under the HSE system; for each target job node, the actual operation information of the target job object expected to be supervised under this target job node in the target logging operation is obtained; by identifying the actual operation information, it is determined whether the target job object meets the logging operation requirements; if not, a rectification instruction for the target job object is issued according to the logging operation requirements. In this way, by using the job supervision workflow determined by a pre-constructed logging knowledge graph, multiple target job nodes involved in the target logging operation are determined, and the supervision of whether the target job object meets the logging operation requirements is realized under each target job node. Furthermore, the supervision timeliness of logging operations can be improved and the labor cost can be reduced.

[0179] Please refer toFigure 5 , Figure 6 , Figure 5 is one of the structural schematic diagrams of a logging operation supervision device provided by an embodiment of the present application. Figure 6 is the second structural schematic diagram of a logging operation supervision device provided by an embodiment of the present application. As Figure 5 shown in, the supervision device 500 includes:

[0180] A node determination module 510, configured to determine multiple target operation nodes corresponding to a target logging operation in the operation supervision workflow based on the operation characteristics of the target logging operation according to the operation supervision workflow determined by a pre-constructed logging knowledge graph; wherein, the logging knowledge graph is constructed based on the logging operation requirements set under the HSE system;

[0181] An information acquisition module 520, configured to acquire the actual operation information of a target operation object expected to be supervised under each target operation node in the target logging operation for each target operation node;

[0182] An identification and judgment module 530, configured to determine whether the target operation object meets the logging operation requirements by identifying the actual operation information;

[0183] An instruction issuing module 540, configured to issue a rectification instruction for the target operation object according to the logging operation requirements if the target operation object does not meet the logging operation requirements.

[0184] Furthermore, as Figure 6 shown, the supervision device 500 further includes a supervision feedback module 550, and the supervision feedback module 550 is used for:

[0185] Determining the supervision progress of the supervision work for the target logging operation according to the number of completed operation nodes that have been identified among the multiple target operation nodes;

[0186] Determining the operation quality level of the target logging operation based on the identification results of the target operation objects expected to be supervised under each completed operation node;

[0187] Generating a supervision report for the target logging operation according to the supervision progress and the operation quality level.

[0188] Furthermore, when the node determination module 510 is used to determine the operation supervision workflow, the node determination module 510 is used for:

[0189] Establishing a logging knowledge graph based on the logging operation requirements set under the HSE system;

[0190] Combined with the operation process information of the logging operation, by searching the logging knowledge graph, determine multiple logging operation nodes in the logging operation and the association relationships between the multiple logging operation nodes;

[0191] According to the association relationships, combine the multiple logging operation nodes to obtain the operation supervision workflow of the logging operation.

[0192] Further, when the node determination module 510 is used to establish a logging knowledge graph based on the logging operation requirements set under the HSE system, the node determination module 510 is used for:

[0193] Obtain logging operation data samples that meet the logging operation requirements;

[0194] By analyzing the logging operation data samples, determine the operation type characteristics, operation process characteristics, wellbore attributes, operation requirements corresponding to the operation type characteristics, operation requirements corresponding to the operation process characteristics, and operation requirements corresponding to the wellbore attributes of the logging operation;

[0195] Use the operation type characteristics, the operation process characteristics, the wellbore attributes, and the operation requirements to construct the ontology model of the logging knowledge graph;

[0196] Based on the ontology model, determine multiple entities to be supervised involved in the logging operation, the entity attributes of each entity to be supervised, and the association relationships between each entity to be supervised and the entity attributes of the entity to be supervised from the logging operation data samples;

[0197] Based on the multiple entities to be supervised, the entity attributes of each entity to be supervised, and the association relationships between each entity to be supervised and the entity attributes of the entity to be supervised, establish the logging knowledge graph.

[0198] Further, when the node determination module 510 is used to construct the ontology model of the logging knowledge graph by using the operation type characteristics, the operation process characteristics, the wellbore attributes, and the operation requirements, the node determination module 510 is used for:

[0199] Determine the logging operation as the active subject of the ontology model;

[0200] Combined with the principal - object relationship of the operation objects involved in the logging operation during the logging operation process, determine the wellbore as the first logging object of the ontology model;

[0201] Determine the other operation objects except the wellbore among the operation objects involved in the logging operation as the second logging object of the ontology model;

[0202] Determine the logging operation characteristics of the ontology model by using the operation type characteristics, operation process characteristics, wellbore attributes, and the operation requirements corresponding to the operation type characteristics, the operation process characteristics, and the wellbore attributes respectively;

[0203] Construct the ontology model of the logging knowledge graph according to the active entity, the first logging object, the second logging object, and the logging operation characteristics.

[0204] Further, when the information acquisition module 520 is used to obtain the actual operation information of the target operation object expected to be supervised under each target operation node in the target logging operation for each target operation node, the information acquisition module 520 is used for:

[0205] For each target operation node, determine the target operation object expected to be supervised under the target operation node;

[0206] Obtain the initial operation image and actual operation data of the target operation object in the target logging operation;

[0207] Perform normalization processing on the initial operation image to obtain the actual operation image of the target operation object;

[0208] Integrate the actual operation data and the actual operation image to determine the actual operation information under each target operation node.

[0209] Further, the actual operation information includes the actual operation image and actual operation data of the target operation object; when the recognition and judgment module 530 is used to determine whether the target operation object meets the logging operation requirements by recognizing the actual operation information, the recognition and judgment module 530 is used for:

[0210] Perform regional division on the actual operation image in the actual operation information to determine the target recognition area of the target operation object in the actual operation image;

[0211] Extract keywords from the actual operation data in the actual operation information to determine the operation keywords for describing the target operation object;

[0212] Recognize the target recognition area and the operation keywords to determine whether the target operation object meets the logging operation requirements.

[0213] The supervision device for logging operations provided by the embodiments of the present application determines multiple target operation nodes corresponding to a target logging operation in the operation supervision workflow based on the operation supervision workflow determined by a pre-constructed logging knowledge graph, according to the operation characteristics of the target logging operation; wherein, the logging knowledge graph is constructed based on the logging operation requirements set under the HSE system; for each target operation node, actual operation information of a target operation object to be supervised under the target operation node in the target logging operation is obtained; by identifying the actual operation information, it is determined whether the target operation object meets the logging operation requirements; if not, a rectification instruction for the target operation object is issued according to the logging operation requirements. In this way, by using the operation supervision workflow determined by a pre-constructed logging knowledge graph, multiple target operation nodes involved in the target logging operation are determined, and the supervision of whether the target operation object meets the logging operation requirements is realized under each target operation node. Furthermore, the supervision timeliness of logging operations can be improved and the labor cost can be reduced.

[0214] Please refer to Figure 7 , Figure 7 which is a schematic structural diagram of an electronic device provided by the embodiments of the present application. As Figure 7 shown in

[0215] The memory 720 stores machine-readable instructions executable by the processor 710. When the electronic device 700 runs, the processor 710 communicates with the memory 720 through the bus 730. When the machine-readable instructions are executed by the processor 710, the steps of the supervision method for logging operations in the method embodiment as shown above Figure 1 can be executed. The specific implementation manner can refer to the method embodiment and will not be elaborated here.

[0216] The embodiments of the present application also provide a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is run by a processor, the steps of the supervision method for logging operations in the method embodiment as shown above Figure 1 can be executed. The specific implementation manner can refer to the method embodiment and will not be elaborated here.

[0217] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0218] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some communication interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0219] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0220] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0221] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or this part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0222] Finally, it should be noted that the above-described embodiments are only specific implementation manners of the present application, used to illustrate the technical solutions of the present application, rather than limiting it. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that any person skilled in the technical field of the present application can still modify the technical solutions described in the foregoing embodiments or easily conceive of changes, or perform equivalent replacements for some of the technical features; and these modifications, changes or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A supervision method for logging operations, characterized in that, the supervision method includes: Based on the operation supervision workflow determined by the pre-constructed logging knowledge graph, according to the operation characteristics of the target logging operation, determining multiple target operation nodes corresponding to the target logging operation in the operation supervision workflow; wherein, the logging knowledge graph is constructed based on the logging operation requirements set under the HSE system; For each target operation node, obtaining the actual operation information of the target operation object expected to be supervised under this target operation node in the target logging operation; By identifying the actual operation information, determining whether the target operation object meets the logging operation requirements; If not, then according to the logging operation requirements, issuing a rectification instruction for the target operation object.

2. The method according to claim 1, characterized in that, the supervision method further includes: According to the number of completed operation nodes that have been identified among the multiple target operation nodes, determining the supervision progress of the supervision work for the target logging operation; Based on the identification results of the target operation objects expected to be supervised under each completed operation node, determining the operation quality level of the target logging operation; According to the supervision progress and the operation quality level, generating a supervision report for the target logging operation.

3. The method according to claim 1, characterized in that, The operation supervision workflow is determined through the following steps: Based on the logging operation requirements set under the HSE system, establishing a logging knowledge graph; Combining the operation process information of the logging operation, by searching the logging knowledge graph, determining multiple logging operation nodes in the logging operation and the association relationships between the multiple logging operation nodes; According to the association relationships, combining the multiple logging operation nodes to obtain the operation supervision workflow of the logging operation.

4. The method according to claim 3, characterized in that, The establishing a logging knowledge graph based on the logging operation requirements set under the HSE system includes: Obtaining logging operation data samples that meet the logging operation requirements; By analyzing the logging operation data samples, determining the operation type characteristics, operation process characteristics, wellbore attributes, operation requirements corresponding to the operation type characteristics, operation requirements corresponding to the operation process characteristics, and operation requirements corresponding to the wellbore attributes of the logging operation; Using the operation type characteristics, the operation process characteristics, the wellbore attributes, and the operation requirements to construct the ontology model of the logging knowledge graph; Based on the ontology model, determining multiple entities to be supervised involved in the logging operation, the entity attributes of each entity to be supervised, and the association relationships between each entity to be supervised and the entity attributes of this entity to be supervised from the logging operation data samples; Based on the multiple entities to be supervised, the entity attributes of each entity to be supervised, and the association relationships between each entity to be supervised and the entity attributes of this entity to be supervised, establishing the logging knowledge graph.

5. The method according to claim 4, characterized in that, Constructing the ontology model of the logging knowledge graph by using the operation type feature, the operation process feature, the wellbore attribute, and the operation requirement includes: Determining the logging operation as the active entity of the ontology model; Combining the primary and secondary relationships of the operation objects involved in the logging operation during the logging operation process, and determining the wellbore as the first logging object of the ontology model; Determining the other operation objects except the wellbore among the operation objects involved in the logging operation as the second logging object of the ontology model; Using the operation type feature, the operation process feature, the wellbore attribute, and the operation requirements corresponding to the operation type feature, the operation process feature, and the wellbore attribute respectively, to determine the logging operation feature of the ontology model; Constructing the ontology model of the logging knowledge graph according to the active entity, the first logging object, the second logging object, and the logging operation feature.

6. The method according to claim 1, wherein, For each target operation node, obtaining the actual operation information of the target operation object to be supervised under the target operation node in the target logging operation, including: For each target operation node, determining the target operation object to be supervised under the target operation node; Obtaining the initial operation image and the actual operation data of the target operation object in the target logging operation; Performing normalization processing on the initial operation image to obtain the actual operation image of the target operation object; Integrating the actual operation data and the actual operation image to determine the actual operation information under each target operation node.

7. The method according to claim 1, wherein, The actual operation information includes the actual operation image and the actual operation data of the target operation object; Determining whether the target operation object meets the logging operation requirements by identifying the actual operation information, including: Performing region division on the actual operation image in the actual operation information to determine the target recognition region of the target operation object in the actual operation image; Performing keyword extraction on the actual operation data in the actual operation information to determine the operation keywords for describing the target operation object; Identifying the target recognition region and the operation keywords to determine whether the target operation object meets the logging operation requirements.

8. A supervision device for logging operations, wherein, The supervision device includes: A node determination module, configured to determine a plurality of target operation nodes corresponding to the target logging operation in the operation supervision workflow according to the operation characteristics of the target logging operation based on the operation supervision workflow determined by the pre-constructed logging knowledge graph; wherein, the logging knowledge graph is constructed based on the logging operation requirements set under the HSE system; An information acquisition module, configured to obtain the actual operation information of the target operation object to be supervised under each target operation node in the target logging operation; An identification and judgment module, configured to determine whether the target operation object meets the logging operation requirements by identifying the actual operation information; An instruction issuing module, configured to issue a rectification instruction for the target operation object according to the logging operation requirements if the target operation object does not meet the logging operation requirements.

9. An electronic device, characterized in that, it includes: a processor, a memory and a bus, the memory stores machine-readable instructions executable by the processor, when the electronic device runs, the processor communicates with the memory through the bus, and when the machine-readable instructions are run by the processor, the steps of the logging operation supervision method according to any one of claims 1 to 7 are executed.

10. A computer-readable storage medium, characterized in that, a computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, the steps of the logging operation supervision method according to any one of claims 1 to 7 are executed.

Images