Oil and gas pipe network spatio-temporal data dynamic loading method, system and equipment and storage medium

Abstract

The invention discloses an oil and gas pipe network spatio-temporal data dynamic loading method, system and device and a storage medium, and relates to the technical field of oil and gas pipe network data processing.The method comprises the steps that an initial geometric network of an oil and gas pipe network is constructed according to a plurality of hard reference points selected from event data of the oil and gas pipe network; performing spatial data alignment analysis and spatial semantic alignment analysis on the target event data of the oil and gas pipe network; and automatically associating the target event data with the initial geometric network according to the spatial data alignment analysis result and the spatial semantic alignment analysis result by using a time-space association rule between the initial geometric network and the event data of the oil and gas pipe network. According to the method, the problems of data alignment and difficulty in automatic data loading and storage in linear engineering can be solved, and technical conditions are created for realizing the business management requirements of'operation, namely recording 'and'co-generation and co-growth' and the dual management requirements of data management.

Description

Background Art

[0002] With the development of intelligent pipeline network construction and digital technology, the digitization of physical assets of oil and gas pipeline networks has become increasingly important and urgent. At the same time, it has become an even more important need to accurately locate the various digitalized assets and event locations of oil and gas pipeline networks. On the one hand, the spatiotemporal data of pipeline network assets continue to change from the design, construction, and operation stages. The attribute data such as organizational management and logical association based on these spatiotemporal relationships have changed frequently due to organizational changes, resulting in the inability to accurately locate pipeline network assets and events; on the other hand, sensitive data such as the precise coordinates of the pipeline network direction cannot be directly transmitted and shared, and can only be displayed and used indirectly through relative reference. The lack of efficient and intuitive data loading and maintenance methods has seriously limited the timeliness and value of the spatiotemporal positioning data of pipeline network assets and events; secondly, the operation time cycle of the pipeline network is long, involving the collection of multi-source data at different stages. It needs to be collected in real time and automatically aligned before it can be efficiently loaded into the warehouse, truly realizing the dual management needs of business and data of "operation is record" and "co-growth". Limited by technical factors that prevent data from being automatically loaded and correlated for analysis, the spatiotemporal information in a large amount of sensor and manually recorded data during the operation of oil and gas pipeline assets is still being processed in a nearly abandoned manner. The three-dimensional models of a large number of physical asset objects under construction can only perform static display functions because they cannot automatically load data in real time, resulting in serious waste of spatiotemporal information value and resources. Summary of the invention

[0003] The technical problem to be solved by the present invention is to address the deficiencies of the prior art and specifically provide a method, system, device and storage medium for dynamic loading of spatiotemporal data of oil and gas pipeline networks, as follows:

[0004] 1) In the first aspect, the present invention provides a method for dynamically loading spatiotemporal data of an oil and gas pipeline network, and the specific technical solution is as follows:

[0005] Constructing an initial geometric network of the oil and gas pipeline network based on a plurality of hard reference points selected from event data of the oil and gas pipeline network;

[0006] Perform spatial data alignment analysis and spatial semantic alignment analysis on the target event data of the oil and gas pipeline network;

[0007] According to the results of spatial data alignment analysis and spatial semantic alignment analysis, and by using the spatiotemporal association rules between the initial geometric network and the event data of the oil and gas pipeline network, the target event data is automatically associated with the initial geometric network.

[0008] The beneficial effects of the method for dynamically loading spatiotemporal data of an oil and gas pipeline network provided by the present invention are as follows:

[0009] It can realize the automatic association between the event data of the oil and gas pipeline network and the initial geometric network, which can help solve the problems of data alignment and automatic data loading into the warehouse faced by linear engineering, and create technical conditions for realizing the dual management needs of business management and data management of "work is record" and "growth together".

[0010] On the basis of the above scheme, the method for dynamically loading spatiotemporal data of an oil and gas pipeline network of the present invention can also be improved as follows.

[0011] Furthermore, the method also includes: randomly extracting the spatial association relationship in the initial geometric network after associating the target event data, and verifying whether the randomly extracted spatial association relationship is correct.

[0012] Furthermore, it also includes:

[0013] Build a data warehouse for oil and gas pipeline networks;

[0014] When the randomly extracted spatial association relationship is verified to be correct, the initial geometric network after associating the target event data and the target event data are stored in the data warehouse, and the online boundary function interface is opened to allow users to edit the data warehouse online.

[0015] Furthermore, it also includes: using a GIS platform or a three-dimensional oil and gas pipeline network digital twin platform to visualize the initial geometric network associated with the target event data on a map base map.

[0016] 2) In the second aspect, the present invention also provides a system for dynamically loading spatiotemporal data of oil and gas pipeline networks, and the specific technical scheme is as follows:

[0017] It includes an initial geometric network building module, an alignment analysis module and an association module;

[0018] The initial geometric network construction module is used to: construct the initial geometric network of the oil and gas pipeline network according to a plurality of hard reference points selected from the event data of the oil and gas pipeline network;

[0019] The alignment analysis module is used to: perform spatial data alignment analysis and spatial semantic alignment analysis on the target event data of the oil and gas pipeline network;

[0020] The association module is used to automatically associate the target event data with the initial geometric network based on the spatial data alignment analysis results and the spatial semantic alignment analysis results, and by utilizing the spatiotemporal association rules between the initial geometric network and the event data of the oil and gas pipeline network.

[0021] On the basis of the above scheme, the oil and gas pipeline network spatiotemporal data dynamic loading system of the present invention can also be improved as follows.

[0022] Furthermore, a verification module is included, and the verification module is used to:

[0023] Randomly extract the spatial association relationships in the initial geometric network after associating the target event data, and verify whether the randomly extracted spatial association relationships are correct.

[0024] Further, it also includes a data warehouse construction module and a storage editing module;

[0025] The data warehouse construction module is used to: construct the data warehouse of the oil and gas pipeline network;

[0026] The storage and editing module is used to: when the randomly extracted spatial association relationship is verified to be correct, the initial geometric network and target event data after associating the target event data are stored in the data warehouse, and the online boundary function interface is opened to allow users to edit the data warehouse online.

[0027] Furthermore, it also includes a visual display module, which is used to:

[0028] Using the GIS platform or the three-dimensional oil and gas pipeline network digital twin platform, the initial geometric network after associating the target event data can be visualized on the map base map.

[0029] 3) In a third aspect, the present invention further provides an electronic device, comprising a processor, the processor being coupled to a memory, the memory storing at least one computer program, the at least one computer program being loaded and executed by the processor, so that the electronic device implements any of the above-mentioned methods for dynamically loading spatiotemporal data of an oil and gas pipeline network.

[0030] 4) In a fourth aspect, the present invention further provides a computer-readable storage medium, in which at least one computer program is stored, and at least one computer program is loaded and executed by a processor so that a computer implements any of the above-mentioned methods for dynamically loading spatiotemporal data of an oil and gas pipeline network.

[0031] It should be noted that the beneficial effects achieved by the technical solutions of the second to fourth aspects of the present invention and the corresponding possible implementation methods can be found in the above-mentioned technical effects of the first aspect and its corresponding possible implementation methods, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0033] Figure 1 This is one of the flow diagrams of a method for dynamically loading spatiotemporal data of an oil and gas pipeline network according to an embodiment of the present invention;

[0034] Figure 2This is a second flow chart of a method for dynamically loading spatiotemporal data of an oil and gas pipeline network according to an embodiment of the present invention;

[0035] Figure 3 This is one of the structural schematic diagrams of a system for dynamically loading spatiotemporal data of an oil and gas pipeline network according to an embodiment of the present invention;

[0036] Figure 4 This is a second structural schematic diagram of a system for dynamically loading spatiotemporal data of an oil and gas pipeline network according to an embodiment of the present invention;

[0037] Figure 5 The figure is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0039] like Figure 1 As shown, a method for dynamically loading spatiotemporal data of an oil and gas pipeline network according to an embodiment of the present invention comprises the following steps:

[0040] S1. constructing an initial geometric network of the oil and gas pipeline network based on a plurality of hard reference points selected from event data of the oil and gas pipeline network;

[0041] Among them, hard reference points specifically refer to: relatively fixed events or asset deployment space points during pipeline operation, similar to static space points in a relative time period. By establishing hard reference points as the reference positions for subsequent loading of oil and gas pipeline network asset event data in the oil and gas pipeline network asset geometry network.

[0042] Usually, hard reference points are defined using data labeling technology. The location of hard reference points on the map is relatively fixed and has obvious identifiable features or attribute values. The data label of a defined hard reference point can be one attribute value or multiple attribute values. Usually, in combination with the concept of knowledge graph, a triple (i.e., a group of three attributes) can be defined. In order to ensure the spatiotemporal attributes of hard reference points, the time attribute value of asset digitization is usually added. Therefore, the database also needs to have the ability to store a geometric database of spatiotemporal multidimensional data, as follows:

[0043] ① Ground feature identification: including three piles and one sign, hydraulic facilities, monitoring points and other identifiable ground features; record data information: map-based coordinate information, ground feature attribute information, and time tags.

[0044] ② Pipeline ancillary facilities: including valves, spans, above-ground pipelines, B-type sleeves, repair locations, venting points and other identifiable features; record data information: map-based coordinate information, ancillary facility attribute information, and time tags.

[0045] ③ Boundary points of management units: including the locations where management authority is divided between regional companies, management offices, work areas and work areas; record data information: map-based coordinate information, boundary point management attribute information, and time tags.

[0046] ④ Construction weld number: including construction weld number, upstream steel pipe number, downstream steel pipe number and other information; record data information: map-based coordinate information, weld number, weld numbering rules, and time tags.

[0047] ⑤ Internal inspection weld number: including internal inspection weld number, upstream intersection clock position, downstream intersection clock position and other information; record data information: map-based coordinate information, weld number, weld numbering rule, upstream intersection clock position, downstream intersection clock position, time label.

[0048] Furthermore, based on the pipeline directions and hard reference points, the initial geometric network of the oil and gas pipeline network is constructed as the core master data for the subsequent spatiotemporal data maintenance of the spatiotemporal data warehouse.

[0049] The collected data can be automatically loaded into the appropriate location of the database to achieve accurate linear relative coordinate position information of the pipeline.

[0050] The key components of building a spatial geometric network include:

[0051] 1) Edges: Represent linear features such as pipelines, roads, and rivers in the network.

[0052] 2) Points: represent the connection points in the network, such as the reference points selected above, as well as the intersection of pipelines or the confluence of rivers. They can be the starting point, end point or branch point of pipelines, or online points of other facility elements, valves, joints (connections of pipelines of different diameters or different pressure levels), pumping stations, metering stations, branch points, terminals (starting point or end point of oil and gas pipelines), and other hard reference points.

[0053] 3) Spatial network (table): A spatial coordinate system and reference position grid, where all points and edges exist. It can also be roughly considered as a spatial background grid, where the exact spatial position point can be found through any set of spatial coordinates. Based on the spatial network, spatial analysis and calculations such as spatial distance, shortest path calculation, network loop search, flow direction determination, upstream or downstream element tracking can be performed.

[0054] 4) Attribute label (table): stores the attribute and characteristic information of each geometric network element to facilitate classification query and retrieval selection.

[0055] 5) Relationship: Corresponding to the spatial network, it stores the relationship between each element, including time-space relationship, organizational management relationship, technical causal relationship, etc. For oil and gas pipelines, the more important relationships include flow direction (defining the direction of flow in the network) and weight (indicating the resistance or other attributes of the edge in the network during flow, such as pipeline diameter).

[0056] 6) Verification rules: define the rules and verification of how different elements in the network are connected to each other, ensuring that the spatial relationships and attributes of the feature classes involved in the construction of the geometric network are logically reasonable and consistent.

[0057] 7) Connectivity rules define how different elements in the network are connected to each other:

[0058] ① Define rules: Based on the operating rules of the pipeline system and actual engineering requirements, create rules to define which pipeline or facility element segments can be connected and the connection conditions between them.

[0059] ② Set restrictions: You can set restrictions on the number of connections of a specific type. For example, some pipe segments may only have one connection point, while other pipe segments may allow multiple connections.

[0060] At the beginning of geometric network design, the subsequent update and maintenance of spatial data and a large amount of associated attribute data should be considered. A good pipeline basic data model is designed, and database mechanisms such as foreign keys and triggers are used to maintain data consistency.

[0061] Optionally, a geographic spatiotemporal database is established first, and then a spatiotemporal graph database is constructed based on it. They correspond to the real geographic spatiotemporal view and the logical semantic view respectively:

[0062] 1) Geographic spatiotemporal view: Use relational GIS spatial database to store and display real geographic spatial data and attribute data.

[0063] 2) Logical space view: Use graph database to store and display logical semantic relationships in geometric network space such as points and edges.

[0064] S2, performing spatial data alignment analysis and spatial semantic alignment analysis on the target event data of the oil and gas pipeline network;

[0065] S3. According to the results of spatial data alignment analysis and spatial semantic alignment analysis, and by using the spatiotemporal association rules between the initial geometric network and the event data of the oil and gas pipeline network, the target event data is automatically associated with the initial geometric network.

[0066] Optionally, in the above technical solution, it also includes:

[0067] S4. Randomly extract the spatial association relationship in the initial geometric network after associating the target event data, and verify whether the randomly extracted spatial association relationship is correct.

[0068] S2, S3 and S4 are explained as follows:

[0069] The initial geometric network is constructed when each pipeline is put into operation. As the pipeline enters operation, the geometric network also enters the update and maintenance period. During the operation period, a large number of data, text, images, signals, voice, and data recorded by manual inspection observations obtained by oil and gas pipeline network sensors all contain time and space locations. Considering each recorded data as an oil and gas pipeline network asset event and associating it with the constructed oil and gas pipeline network asset geometric network in time and space can better realize event location and decision analysis.

[0070] Temporal association can be directly associated through timestamp and event time attributes. Spatial association can be associated based on geographic location data and spatial features.

[0071] Specifically, the association ideas can be divided into three categories: direct association based on timestamp and spatial coordinate data pairs, semantic association based on event time-space semantic space vector distance, and computational association based on conversion of time-space relative distance. Specifically:

[0072] 1) Direct association: Directly perform spatiotemporal association through the absolute time and spatial coordinates of the event record. The association is based on the spatiotemporal query of the initial geometric network and is associated with the matched query object. If there is no matching object, the event object feature is newly created in the spatial grid according to its spatiotemporal coordinates, and the geometric network update rule check is performed.

[0073] 2) Semantic association: Through the semantics of time and space features in event metadata or description records, spatial association is performed in the semantic vector space. For multi-source heterogeneous data such as images, videos, and electronic documents, metadata or labels of the data can be first constructed based on technologies such as OCR, image, and speech recognition, and then spatiotemporal semantic association analysis of multi-source heterogeneous data can be achieved based on the space, time, and content in its metadata or labels.

[0074] 3) Calculate association: Based on the relative distance description between the event location and the hard reference point, perform conversion calculations and then perform time-space association. For example, the pipeline linear reference system can be converted to obtain the time-space position between the hard reference point. This will automatically associate or create.

[0075] The above associations are only for static events. Optionally, for spatiotemporal dynamic events, spatiotemporal flow analysis is also required to record the spatiotemporal changes and associated interactions of the events.

[0076] Based on the above association rules, set up automatic association scripts and stored procedures that are automatically updated after the association operation is triggered, and actually perform automatic association regularly or irregularly.

[0077] Optionally, an algorithm is developed based on the above spatiotemporal association ideas to extract spatial, temporal and content features from the input data in an automated or semi-automated manner, and an attempt is made to use machine learning methods to determine the weights of indicators in each dimension to reduce the subjectivity of human participation.

[0078] The automatic association rules and algorithms are verified on experimental data sets to check the effectiveness of the above automatic association methods, and the performance of the association models on actual data sets is comprehensively analyzed to continuously optimize and improve the models.

[0079] The spatiotemporal automatic association embodiment is as follows:

[0080] ① Establish a basic indicator system for spatial semantic association:

[0081] According to the spatiotemporal data characteristics of the oil and gas pipeline network, a spatiotemporal semantic association index library containing three dimensions of space, time and content is constructed. The index library can be constructed by integrating the spatiotemporal ontology dictionary of the pipeline network based on the public time description dictionary and the place name dictionary. The spatiotemporal ontology of the pipeline network provides the spatiotemporal relationship between the conceptual system of the oil and gas pipeline network and the concepts, and helps to identify and associate the spatiotemporal ontologies of the pipeline network with the same or similar semantics.

[0082] ②Construct a spatial segmentation index system for oil and gas pipeline networks:

[0083] It can be aligned with the idea of ​​building a data warehouse, and the related indicators can be further subdivided according to the levels of the above three dimensions. For example, according to the trunk and branches of the oil and gas pipeline network, combined with the operation stage, affiliation, administrative and geographical boundaries, the oil and gas pipeline network business space semantic indicator system can be constructed. It can be attached to the smallest spatial basic unit data item such as the pipe segment number.

[0084] ③Preprocessing such as data cleaning and alignment:

[0085] The collected data is stored in real time in the buffer data pool. After passing through the data pool, it is retrieved and matched in the geometric database and loaded between the attribute values ​​of the two nearest hard reference points to achieve automatic alignment and loading into the database.

[0086] ④ Perform spatiotemporal semantic association calculation:

[0087] a. Spatial correlation calculation extracts spatial semantic information from the input data, such as coordinate values, relative distance values, administrative divisions, business locations, pipe sections, etc., and matches them with the spatial data indicators in the initial oil and gas pipeline network geometric network data warehouse to calculate spatial topological relationships and metric relationships, such as spatial overlap ratio and spatial distance.

[0088] b. Time correlation calculation:

[0089] Using the temporal information in the input data, including the time of event occurrence or acquisition, the temporal topological relationships and metric relationships, such as temporal overlap ratio and temporal distance, are calculated.

[0090] c. Content relevance calculation:

[0091] The spatial semantic relevance is calculated by using spatial ontology dictionary or knowledge base rule method and statistical method based on large-scale corpus. The semantic similarity of keywords in geospatial metadata content is calculated.

[0092] d. Comprehensive semantic relevance calculation model:

[0093] The semantic relevance of the three dimensions of space, time and content is integrated to obtain the comprehensive semantic relevance between geospatial data through weighted summation.

[0094] ⑤Automated feature extraction and weight determination:

[0095] Based on the above ideas of spatiotemporal correlation, an algorithm is developed to extract spatial, temporal and content features from the input data in an automated or semi-automated manner, and an attempt is made to use machine learning methods to determine the weights of indicators in each dimension to reduce the subjectivity of human participation.

[0096] ⑥Verification and optimization:

[0097] The automatic association rules and algorithms are verified on experimental data sets to check the effectiveness of the above automatic association methods, and the performance of the association models on actual data sets is comprehensively analyzed to continuously optimize and improve the models.

[0098] Optionally, in the above technical solution, it also includes:

[0099] Build a data warehouse for oil and gas pipeline networks;

[0100] When the randomly extracted spatial association relationship is verified to be correct, the initial geometric network after associating the target event data and the target event data are stored in the data warehouse, and the online boundary function interface is opened to allow users to edit the data warehouse online.

[0101] Optionally, the above technical solution also includes: using a GIS platform or a three-dimensional oil and gas pipeline network digital twin platform to visualize the initial geometric network associated with the target event data on a map base map.

[0102] Among them, the basic data of in-service pipelines and newly built pipelines are integrated to establish the asset space data warehouse of the oil and gas pipeline network, as described in detail as follows:

[0103] Each oil and gas pipeline has three stages: design and construction, operation and maintenance, and decommissioning and storage. According to the time stage dimension of the pipeline, the centerline direction coordinate spatial data of each oil and gas pipeline, as well as the spatial and attribute data of online and offline key ancillary facilities, are integrated to establish an oil and gas pipeline network spatial data warehouse.

[0104] Among them, basic data refers to the pipeline centerline, pipeline facilities, third-party facilities, inspection and maintenance, basic geography, operation and maintenance, pipeline risks, emergency management, intelligent perception and other data submitted online when the pipeline is put into operation.

[0105] Each record in the spatial data warehouse should have at least three fields: absolute geographic coordinates, timestamp, and belonging phase. Other optional fields include relative coordinates, coordinate system type, encrypted coordinates, encryption method, etc.

[0106] Data integration focuses on in-service pipelines and newly built pipelines. Retired pipelines can be imported as a whole to provide support for subsequent design and related queries.

[0107] For existing pipelines in service, we can choose to restore historical data digitally and integrate the data by combining it with re-digital collection based on actual conditions.

[0108] The quality of the core data of the oil and gas pipeline network determines the quality of the subsequent initial geometric network and dynamic loading. Quality inspection rules should be set for the imported data, and data cleaning and data quality repair and improvement should be performed.

[0109] Optionally, based on the above-mentioned oil and gas pipeline network asset spatial data warehouse, other structured data such as attributes, operation records, and unstructured data such as videos, images, and documents can also be organized into the lake to establish an oil and gas pipeline network asset integrity management spatiotemporal data lake or an integrated design of spatiotemporal related data lake and warehouse, and perform spatiotemporal association of data records with the spatiotemporal core records in the above-mentioned spatial data warehouse.

[0110] Optionally, the scope of constructing the above asset space data warehouse may include the following three aspects:

[0111] Internal enterprise: historical data of construction and completion acceptance, production and operation period ledgers and inspection records, etc.

[0112] Industry service providers: service data such as design procurement, renovation, testing and maintenance provided by third-party service providers;

[0113] Public channels: Internet oil and gas pipeline network public opinion event data, operator / statistical yearbook / literature database and other data.

[0114] Optionally, based on the above-mentioned oil and gas pipeline network asset spatial data warehouse, the intermediate derivative data and result data / data sets generated based on intelligent algorithms and decision model rules can also be stored in the warehouse / lake as events, laying the foundation for the subsequent provision of auxiliary decision-making services such as intelligent question and answer for the construction of spatiotemporal knowledge graphs.

[0115] The online boundary function interface is opened to enable users to edit the asset space data warehouse online, as described below:

[0116] The initial geometric network database uses the GIS platform or the 3D oil and gas pipeline network digital twin platform to visualize the oil and gas pipeline network geometry on the map base map, publish map services, and open the online boundary function interface to support the pipeline network operation and maintenance personnel to edit and maintain the real-time event data online. The editing is mainly divided into two ways:

[0117] 1) Spatial network data editing: including operations such as adding, deleting, and modifying the initial geometric network data, as well as online marking and editing of event points and edge data during runtime.

[0118] 2) Attribute data editing: editing operations such as adding, deleting, and modifying related attribute data.

[0119] It should be noted that for each geometric network edit that triggers local or global changes in the geometric network, permission review and version control should be carried out, and the associated attribute data should be updated according to the technical implementation plan. For the update of attribute data, it should be updated and improved according to the set automatic association and update scripts, and an update procedure should be established to ensure that any update of the geometric network is correctly reflected in the attribute data.

[0120] Optionally, the method further includes: designing a spatial data encryption conversion algorithm to perform coordinate system deflection.

[0121] Given that the high-precision coordinate data of some companies' original oil and gas pipeline assets are relatively sensitive, it is impossible to directly provide spatial query services on the Internet, and automatic loading, updating and maintenance of spatiotemporal data cannot be achieved.

[0122] In order to meet the data security supervision requirements of the oil and gas pipeline industry, an oil and gas pipeline network geospatial data deflection encryption algorithm is established through nonlinear projection transformation, commercial cryptographic encryption and decryption technologies, a unified spatial reference benchmark after deflection is established, and the original spatial data is desensitized or the coordinate system is deflected and converted.

[0123] It should be noted that the encryption deflection of geographic coordinate spatial data mainly affects the spatial network part of the above-mentioned oil and gas pipeline network geometric network. The deflected geometric network database can provide spatial data query and association services based on the deflected spatial reference benchmark.

[0124] On-site operation and maintenance personnel of oil and gas pipeline networks can use software and hardware developed based on the deflected spatial reference benchmark, such as encrypted inspection terminals, to perform spatiotemporal editing and maintenance updates of online event data.

[0125] Through Figure 2 The embodiments shown further illustrate the invention:

[0126] 0. New real-time events: collect and record data for events that need to be recorded.

[0127] The data, text, images, signals, voice, and manual inspection observation records obtained by a large number of oil and gas pipeline network sensors during the operation period all contain spatial locations. Considering each recorded data as an oil and gas pipeline network asset event and spatially associating it with the constructed oil and gas pipeline network asset geometric network can better realize event location and decision analysis.

[0128] In addition to recording event information, each event record should also have three fields: absolute / relative geographic coordinates or spatial location description, timestamp, and subordinate stage. When recording relative coordinates, fields such as coordinate system type, encrypted coordinates, and encryption method should also be given.

[0129] 1. Interactive editing of spatial network data:

[0130] Through the spatial network data interactive editing interface or tools, newly generated real-time events can be imported, edited online, and inputted. Based on the initial geometric network database, the geometric network of the oil and gas pipeline network is visualized on the map base map with the help of the GIS platform or the three-dimensional oil and gas pipeline network digital twin platform, and map services are published. The online boundary function interface is opened to support the online editing and maintenance of real-time event data by pipeline network operation and maintenance personnel.

[0131] For streaming event data, such as key equipment monitoring information, real-time access can be achieved through the database interface; for discrete event data, such as abnormal alarm event data, batch import or manual import can be selected according to the quantity for access; the processing of some spatial network update events can be directly updated and maintained through online GIS tools by dragging and dropping or entering geographic coordinates.

[0132] 2. Automatic spatial data alignment: For the accessed event data, spatial data alignment analysis is performed. According to the alignment analysis method, it can be divided into two types, specifically:

[0133] 2.1. Spatial data analysis (spatial data alignment analysis):

[0134] The spatial coordinates of the initial geometric network are queried through the absolute spatial coordinates of the event record, and spatial association is performed with the matched query object. If there is no matching object, the event object element is newly created in the spatial grid according to its spatiotemporal coordinates. Further, the spatial distance conversion calculation can be performed based on the relative distance description between the event location and the hard reference point, and then spatial association can be performed. For example, the linear reference system of the pipeline can be converted to obtain the spatiotemporal position between the hard reference point.

[0135] This part should rely on the spatial network association rule library ( Figure 2 The spatial geometric network association rules in the label 2.3) are calculated.

[0136] 2.2. Spatial semantic relevance calculation (spatial semantic alignment analysis):

[0137] Through the spatial feature semantics in event metadata or description records, the spatial distance calculation of semantic vector space is performed, and association analysis is performed. For multi-source heterogeneous data such as images, videos, and electronic documents, the metadata or labels of the data can be first constructed based on technologies such as OCR, image, and speech recognition, and then the spatial semantic association analysis of multi-source heterogeneous data can be realized based on the space, time, and content in its metadata or labels.

[0138] This part should rely on the spatiotemporal semantic association index library ( Figure 2 The spatial and temporal semantic association indicators in the label 2.4) are calculated.

[0139] 3. Automatic association of spatial network data:

[0140] Based on the results of the above spatial data analysis and calculation, automatic association is performed in the geometric network. The steps for implementing spatial automatic association are as follows:

[0141] ① Establish a basic indicator system for spatial semantic association:

[0142] According to the characteristics of oil and gas pipeline network spatial data, a spatial semantic association index library containing spatial and content dimensions is constructed. The index library can be constructed by integrating the pipeline network spatial ontology dictionary based on the public place name dictionary. The pipeline network spatial ontology provides the spatial location relationship between the oil and gas pipeline network concept system and concepts, and helps to identify and associate pipeline network spatial ontologies with the same or similar semantics.

[0143] ②Construct a spatial segmentation index system for oil and gas pipeline networks:

[0144] It can be aligned with the idea of ​​building a data warehouse, and the related indicators can be further subdivided according to the levels of the above two dimensions. For example, according to the trunk and branches of the oil and gas pipeline network, combined with the operation stage, affiliation, administrative and geographical boundaries, the oil and gas pipeline network business space semantic indicator system can be constructed. It can be attached to the smallest spatial basic unit data item such as the pipe segment number.

[0145] ③Preprocessing such as data cleaning and alignment:

[0146] The collected data is stored in real time in the buffer data pool. After passing through the data pool, it is retrieved and matched in the geometric database and loaded between the attribute values ​​of the two nearest hard reference points to achieve automatic alignment and loading into the database.

[0147] ④ Perform spatiotemporal semantic association calculation:

[0148] Spatial relevance calculation extracts spatial semantic information from the input data, such as coordinate values, relative distance values, administrative divisions, business locations, pipe sections, etc., and matches the coordinates with the spatial data indicators in the initial oil and gas pipeline network geometric network data warehouse to calculate spatial topological relationships and metric relationships, such as spatial overlap ratios and spatial distances. Content relevance calculation uses spatial ontology dictionary or knowledge base rule methods and statistical methods based on large-scale corpora to calculate spatial semantic relevance. Calculate the semantic similarity of keywords in geospatial metadata content. Comprehensive semantic relevance calculation model: The semantic relevance of the comprehensive space and content dimensions is combined to obtain the comprehensive semantic relevance between geospatial data by weighted summation.

[0149] ⑤Automated feature extraction and weight determination:

[0150] Based on the above ideas of spatiotemporal correlation, an algorithm is developed to extract spatial and content features from the input data in an automated or semi-automated manner, and an attempt is made to use machine learning methods to determine the weights of indicators in each dimension to reduce the subjectivity of human participation.

[0151] 4. Spatial association verification check:

[0152] By randomly extracting spatial association relationships, the automatic association rules and algorithms are verified on the data set to check whether the above automatic association results have errors in spatial topology, logical semantics, etc.

[0153] Then confirm the validity of the spatial association relationship, comprehensively analyze the impact of automatic association on the historical database, and ensure the consistency and compatibility of the association relationship in the geometric network.

[0154] For problems found during the verification process, rules are created and updated to the rule knowledge base to continuously optimize and improve the automatic association model.

[0155] 5. Real-time data update of geometric network:

[0156] After the verification of the automatic spatial association event data is completed, the geometric network can be updated in real time through automated scripts or tools.

[0157] 6. Update to spatiotemporal data warehouse:

[0158] For each real-time update event that updates the geometric network, detailed version records should be kept and updated in the data warehouse.

[0159] After the data is uploaded to the database, it is dynamically published and the results are fed back to the application interface to inform the real-time event data submitter to query.

[0160] Establish a version control mechanism, and for exceptions after the update is completed, it should also support reverse operation tools such as version rollback and associated automatic recovery.

[0161] The beneficial effects of the present invention are as follows:

[0162] 1) Based on the construction of the initial geometric network database of the oil and gas pipeline network in combination with hard reference points, the present invention calculates association rules through spatiotemporal analysis, establishes dynamic spatiotemporal positioning associations for in-service pipeline operation and maintenance events, and supports tracing back to historical events. Furthermore, online spatiotemporal editing can be provided for historical spatiotemporal data, and real-time spatiotemporal feedback correction of in-service pipelines can be achieved, which better reflects the value of spatiotemporal data and provides rapid response and decision support for spatiotemporal analysis of oil and gas pipeline network events.

[0163] 2) The present invention proposes for the first time a data labeling technology for defining spatiotemporal hard reference points, which can help solve the problems of data alignment and automatic data loading into the warehouse faced by linear engineering, and creates technical conditions for achieving the dual management needs of business management and data management of "work as record" and "growing together".

[0164] 3) It can release the spatiotemporal value of data: the original spatiotemporal data of oil and gas pipeline networks is difficult to realize due to the lack of real-time dynamic association, which leads to the silence of data value. The present invention fully pays attention to the spatiotemporal attribute information of events, and can realize accurate spatiotemporal positioning and association analysis of events.

[0165] 4) Geometric network construction and association rule design based on hard reference points. A method is proposed to construct an initial geometric network database based on hard reference points, and to associate subsequent events in time and space based on distance and semantics. This method can support automatic dynamic association and online editing and maintenance of time and space data, and realize dynamic loading and maintenance of pipe network time and space data.

[0166] 5) Good security and scalability. Optional methods such as coordinate data encryption deflection and spatial network (view) semantic network (view) separation provide technical guarantees for the secure release and convenient maintenance of spatiotemporal data, and support customization in scenarios with high security requirements and high user friendliness.

[0167] In the above embodiments, although the steps are numbered S1, S2, etc., these are only specific embodiments given by the present invention. Those skilled in the art may adjust the execution order of S1, S2, etc. according to actual conditions, which is also within the protection scope of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.

[0168] like Figure 3 As shown, a system 200 for dynamically loading spatiotemporal data of an oil and gas pipeline network according to an embodiment of the present invention comprises an initial geometric network construction module 201, an alignment analysis module 202 and an association module 203;

[0169] The initial geometric network construction module 201 is used to: construct an initial geometric network of the oil and gas pipeline network according to a plurality of hard reference points selected from the event data of the oil and gas pipeline network;

[0170] The alignment analysis module 202 is used to: perform spatial data alignment analysis and spatial semantic alignment analysis on the target event data of the oil and gas pipeline network;

[0171] The association module 203 is used to automatically associate the target event data with the initial geometric network according to the spatial data alignment analysis results and the spatial semantic alignment analysis results, and by using the spatiotemporal association rules between the initial geometric network and the event data of the oil and gas pipeline network.

[0172] Optionally, the above technical solution further includes a verification module, which is used to randomly extract spatial association relationships in the initial geometric network after associating the target event data, and verify whether the randomly extracted spatial association relationships are correct.

[0173] Optionally, in the above technical solution, a data warehouse construction module and a storage editing module are also included;

[0174] The data warehouse construction module is used to: construct the data warehouse of the oil and gas pipeline network;

[0175] The storage and editing module is used to: when the randomly extracted spatial association relationship is verified to be correct, the initial geometric network and target event data after associating the target event data are stored in the data warehouse, and the online boundary function interface is opened to allow users to edit the data warehouse online.

[0176] Optionally, the above technical solution also includes a visualization display module, which is used to: use a GIS platform or a three-dimensional oil and gas pipeline network digital twin platform to visualize the initial geometric network associated with the target event data on a map base map.

[0177] By another embodiment, Figure 4 As shown, the present invention is described:

[0178] A system for dynamically loading spatiotemporal data of an oil and gas pipeline network according to an embodiment of the present invention is divided into five layers: an interactive service layer, a security control layer, a computing and analysis layer, an associated execution layer, and a data storage layer. Specifically:

[0179] 1) The interactive service layer includes an online query and editing module for spatiotemporal data of oil and gas pipeline networks, which provides an interactive interface for online query and editing of spatiotemporal data of oil and gas pipeline networks. The editing objects include business attribute information and spatiotemporal information. Data editing of geometric networks is only open to management and maintenance personnel.

[0180] 2) Security control layer: including the following functional modules:

[0181] ① System control module: provides allocation and control management of security permissions for users, data, and functional modules.

[0182] ②Data quality control module: used to verify, clean, trace, and provide control and version maintenance for data quality.

[0183] ③ Spatial data encryption conversion module: It is used to encrypt and decrypt data, especially spatial data, to meet the sharing and circulation of spatial data under the premise of security. The spatial data encryption conversion module is an optional module.

[0184] 3) Computational analysis layer: the implementation layer for dynamic maintenance of spatiotemporal data. It includes the following functional modules:

[0185] ① Time analysis and calculation module: provides data alignment, analysis, calculation, update and processing in the time dimension.

[0186] ②Spatial analysis and calculation module: provides data alignment, analysis, calculation, update and processing in spatial dimension.

[0187] ③Semantic analysis and calculation module: provides data association, disambiguation, calculation, update and processing of semantic dimensions.

[0188] 4) Association execution layer: including the following functional modules:

[0189] ① Association rules and knowledge base module: manage and maintain the rules, algorithms and other knowledge for spatiotemporal alignment analysis, and provide knowledge support for various spatiotemporal data computation and analysis for the computational analysis layer.

[0190] ② Spatiotemporal data automatic loading and association module: It interacts with the computational analysis layer to input and output, and performs the execution and result confirmation of spatiotemporal data automatic loading and dynamic association.

[0191] 5) Data storage layer: provides storage and management of various data. It mainly includes two parts of data:

[0192] ① Oil and gas pipeline network geometry network: It is the benchmark data for the entire data alignment and automatic loading, and lays a reference foundation for the automatic alignment of all spatiotemporal data. This part of the data should be managed and maintained by a dedicated person.

[0193] ② Oil and gas pipeline network spatiotemporal data warehouse: manage and store data snapshots in multiple versions for all spatiotemporal related data, and support data traceability query and correlation analysis.

[0194] It should be noted that the beneficial effects of the oil and gas pipeline network spatiotemporal data dynamic loading system 200 provided in the above embodiment are the same as the beneficial effects of the oil and gas pipeline network spatiotemporal data dynamic loading method described above, which will not be described in detail here. In addition, when the system provided in the above embodiment realizes its functions, it only uses the division of the above-mentioned functional modules as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to actual conditions to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be described in detail here.

[0195] like Figure 5 As shown, an electronic device 300 of an embodiment of the present invention includes a processor 320, the processor 320 is coupled to a memory 310, and the memory 310 stores at least one computer program 330, and the at least one computer program 330 is loaded and executed by the processor 320, so that the electronic device 300 implements any of the above-mentioned methods for dynamically loading spatiotemporal data of oil and gas pipeline networks, specifically:

[0196] The electronic device 300 may have relatively large differences due to different configurations or performances, and may include one or more processors 320 (Central Processing Units, CPU) and one or more memories 310, wherein the one or more memories 310 store at least one computer program 330, and the at least one computer program 330 is loaded and executed by the one or more processors 320, so that the electronic device 300 implements any of the oil and gas pipeline network spatiotemporal data dynamic loading methods provided in the above embodiments. Of course, the electronic device 300 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output. The electronic device 300 may also include other components for realizing device functions, which will not be described in detail here. The electronic device may specifically be a computer, etc.

[0197] A computer-readable storage medium according to an embodiment of the present invention stores at least one computer program, and the at least one computer program is loaded and executed by a processor so that a computer implements any of the above-mentioned methods for dynamically loading spatiotemporal data of an oil and gas pipeline network.

[0198] Optionally, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0199] In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes any of the above-mentioned methods for dynamically loading spatiotemporal data of an oil and gas pipeline network.

[0200] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects and represent the definition of a specific order or sequence. The order of use of similar objects can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than the order shown or described.

[0201] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.

[0202] Any combination of one or more computer-readable media can be used. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0203] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for dynamically loading spatiotemporal data of an oil and gas pipeline network, characterized in that: include: Constructing an initial geometric network of the oil and gas pipeline network based on a plurality of hard reference points selected from event data of the oil and gas pipeline network; Perform spatial data alignment analysis and spatial semantic alignment analysis on the target event data of the oil and gas pipeline network; According to the spatial data alignment analysis results and the spatial semantic alignment analysis results, and by utilizing the spatiotemporal association rules between the initial geometric network and the event data of the oil and gas pipeline network, the target event data is automatically associated with the initial geometric network.

2. The method for dynamically loading spatiotemporal data of an oil and gas pipeline network according to claim 1, characterized in that: Also includes: The spatial association relationship in the initial geometric network after associating the target event data is randomly extracted, and whether the randomly extracted spatial association relationship is correct is verified.

3. The method for dynamically loading spatiotemporal data of an oil and gas pipeline network according to claim 2 is characterized in that: Also includes: Build a data warehouse for oil and gas pipeline networks; When the randomly extracted spatial association relationship is verified to be correct, the initial geometric network associated with the target event data and the target event data are stored in the data warehouse, and an online boundary function interface is opened to allow users to edit the data warehouse online.

4. A method for dynamically loading spatiotemporal data of an oil and gas pipeline network according to any one of claims 1 to 3, characterized in that: Also includes: Using a GIS platform or a three-dimensional oil and gas pipeline network digital twin platform, the initial geometric network associated with the target event data is visualized on a map base map.

5. A dynamic loading system for spatiotemporal data of oil and gas pipeline network, characterized in that: It includes an initial geometric network building module, an alignment analysis module and an association module; The initial geometric network construction module is used to: construct an initial geometric network of the oil and gas pipeline network based on a plurality of hard reference points selected from event data of the oil and gas pipeline network; The alignment analysis module is used to: perform spatial data alignment analysis and spatial semantic alignment analysis on the target event data of the oil and gas pipeline network; The association module is used to automatically associate the target event data with the initial geometric network according to the spatial data alignment analysis results and the spatial semantic alignment analysis results, and by utilizing the spatiotemporal association rules between the initial geometric network and the event data of the oil and gas pipeline network.

6. The oil and gas pipeline network spatiotemporal data dynamic loading system according to claim 5 is characterized in that: Also included is a verification module, the verification module is used to: The spatial association relationship in the initial geometric network after associating the target event data is randomly extracted, and whether the randomly extracted spatial association relationship is correct is verified.

7. The oil and gas pipeline network spatiotemporal data dynamic loading system according to claim 6 is characterized in that: It also includes a data warehouse building module and a storage editing module; The data warehouse construction module is used to: construct a data warehouse for the oil and gas pipeline network; The storage and editing module is used to: when verifying that the randomly extracted spatial association relationship is correct, store the initial geometric network and the target event data associated with the target event data in the data warehouse, and open an online boundary function interface to allow users to edit the data warehouse online.

8. The oil and gas pipeline network spatiotemporal data dynamic loading system according to any one of claims 5 to 7, characterized in that: It also includes a visual display module, which is used to: Using a GIS platform or a three-dimensional oil and gas pipeline network digital twin platform, the initial geometric network associated with the target event data is visualized on a map base map.

9. An electronic device, characterized in that: The electronic device includes a processor, the processor is coupled to a memory, at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor so that the electronic device implements a method for dynamically loading spatiotemporal data of an oil and gas pipeline network as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: At least one computer program is stored in the computer-readable storage medium, and the at least one computer program is loaded and executed by the processor so that the computer implements the method for dynamically loading spatiotemporal data of an oil and gas pipeline network as described in any one of claims 1 to 4.

Images