Crude oil pipeline process map construction method and device, equipment and storage medium

Abstract

This application relates to the field of knowledge map construction technology, and more particularly to a method, apparatus, equipment, and storage medium for constructing a crude oil pipeline process map. The method includes: screening acquired multi-source knowledge of crude oil pipelines to obtain target unstructured knowledge and target structured knowledge; determining a knowledge unit set based on the target unstructured knowledge and the target structured knowledge; the knowledge unit set includes knowledge content corresponding to the target unstructured knowledge and the target structured knowledge, and metadata tags corresponding to each knowledge content; determining each knowledge entity in the knowledge unit set, and the entity relationships between the knowledge entities; and constructing a crude oil pipeline process map based on the knowledge entities and the entity relationships. This application facilitates improved retrieval efficiency and accuracy of crude oil pipeline process knowledge and reduces the information silo level of crude oil pipeline process knowledge.

Description

Technical Field

[0001] This application relates to the field of map construction technology, and in particular to a method, apparatus, equipment and storage medium for constructing a crude oil pipeline process map. Background Technology

[0002] Crude oil pipelines, especially pipeline systems that transport easily solidified and highly viscous crude oil over long distances, rely on complex process decisions for safe and efficient operation. These decisions cover temperature control settings, flow rate regulation, pump-boiler combinations, shutdown and restart, and emergency response. The core prerequisite for achieving autonomous and intelligent process decision-making is to build a corresponding process knowledge dataset.

[0003] Currently, the process knowledge dataset is constructed by using directly acquired unstructured knowledge (textual form) and structured knowledge (textual form) related to crude oil pipelines as the crude oil pipeline process knowledge dataset.

[0004] However, firstly, the aforementioned process knowledge dataset is massive in size, and users typically search by filename or keyword to retrieve multiple pieces of knowledge they need, resulting in poor search efficiency and accuracy. Secondly, the knowledge in the aforementioned process knowledge dataset is generally scattered across different departments or systems, making it difficult to access globally, leading to a high degree of information silos in the process knowledge dataset. Summary of the Invention

[0005] To improve the efficiency and accuracy of crude oil pipeline process knowledge retrieval and reduce the information silos of crude oil pipeline process knowledge, this application provides a method, apparatus, equipment, and storage medium for constructing crude oil pipeline process maps.

[0006] Firstly, this application provides a method for constructing a crude oil pipeline process map, including: The acquired multi-source knowledge of crude oil pipelines is filtered to obtain target unstructured knowledge and target structured knowledge; Based on the target unstructured knowledge and the target structured knowledge, a knowledge unit set is determined; the knowledge unit set includes the knowledge content corresponding to the target unstructured knowledge and the target structured knowledge respectively, and the metadata tags corresponding to each knowledge content respectively; Determine each knowledge entity in the knowledge unit set, and the entity relationships between each knowledge entity; Based on the knowledge entities and their relationships, a crude oil pipeline process map is constructed.

[0007] Secondly, this application provides a crude oil pipeline process map construction device, comprising: The knowledge filtering module is used to filter the acquired multi-source knowledge of crude oil pipelines to obtain target unstructured knowledge and target structured knowledge. The unit determination module is used to determine a knowledge unit set based on the target unstructured knowledge and the target structured knowledge; the knowledge unit set includes the knowledge content corresponding to the target unstructured knowledge and the target structured knowledge respectively, and the metadata tags corresponding to each knowledge content respectively; An entity recognition module is used to determine each knowledge entity in the knowledge unit set, as well as the entity relationships between the knowledge entities. The graph construction module is used to construct a crude oil pipeline process graph based on the knowledge entities and their relationships.

[0008] Thirdly, this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the method described above.

[0009] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described method.

[0010] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0011] The aforementioned method, apparatus, equipment, and storage medium for constructing crude oil pipeline process maps involve filtering acquired multi-source knowledge of crude oil pipelines to obtain target unstructured knowledge and target structured knowledge; determining a knowledge unit set based on the target unstructured knowledge and the target structured knowledge; the knowledge unit set includes the knowledge content corresponding to the target unstructured knowledge and the target structured knowledge, as well as the metadata tags corresponding to each knowledge content; determining each knowledge entity in the knowledge unit set, and the entity relationships between the knowledge entities; and constructing a crude oil pipeline process map based on the knowledge entities and the entity relationships. Through the above implementation, firstly, by processing the acquired multi-source knowledge of crude oil pipelines, a crude oil pipeline process map can be obtained, which facilitates users in obtaining the required process knowledge through retrieval, thus improving the retrieval efficiency and accuracy of crude oil pipeline process knowledge; secondly, the crude oil pipeline process map centralizes multi-source knowledge of crude oil pipelines in one place for user retrieval, effectively reducing the information silo level of crude oil pipeline process knowledge.

[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a flowchart of a crude oil pipeline process map construction method provided in the embodiments of this application; Figure 2 This is a schematic diagram of a crude oil pipeline process map construction device provided in the embodiments of this application; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application; Figure 4 This is an internal structural diagram of a computer-readable storage medium provided in an embodiment of this application. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of this disclosure clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this disclosure.

[0016] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings herein are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0017] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0018] Example 1 Figure 1 This is a flowchart of a crude oil pipeline process map construction method provided in Embodiment 1 of this application, with reference to... Figure 1 The method can be executed by a device that performs the method, which can be implemented in software and / or hardware, and the method includes: S110. Filter the acquired multi-source knowledge of crude oil pipelines to obtain target unstructured knowledge and target structured knowledge.

[0019] It should be noted that, in order to facilitate users to quickly, accurately, and comprehensively retrieve the crude oil pipeline process knowledge they need, this implementation intends to construct corresponding process diagrams based on the acquired crude oil pipeline process knowledge for users to search.

[0020] In this embodiment, the acquired crude oil pipeline process knowledge is referred to as crude oil pipeline multi-source knowledge. This crude oil pipeline multi-source knowledge includes: standard and specification knowledge, operating procedure knowledge, emergency plan knowledge, historical case knowledge, mechanism and rule knowledge, equipment and physical property data knowledge, etc., without any specific limitation.

[0021] The knowledge categories include: Standards and Specifications: Formal texts of national and industry standards, design specifications, and safety regulations such as SY / T 5536 "Operating Procedures for Crude Oil Pipelines" and SY / T 6893 "Process Safety Assessment of Crude Oil Pipelines"; Operating Procedures: Operating procedure manuals for specific stations and pipeline sections, standard temperature control curves, standardized procedures for flow rate regulation, start-up and shutdown operation instructions, and valve switching sequence tables; Emergency Response Plans: Emergency response plan documents, flowcharts, and instructions for handling emergency situations such as shutdowns, leaks, abnormal pressure, sudden temperature drops, and equipment failures; Historical Case Studies: Historical dispatch records, typical process schemes, successful emergency response cases, equipment failure review reports, and expert experience summaries; Mechanism and Rules: Collecting and explicitly defining the physical rules and safety constraints in process calculations, specifically including temperature drop calculation rules (such as the Sukhov temperature drop formula and its applicable boundary conditions), hydraulic calculation rules (such as the Repinzon hydraulic friction formula and its correction coefficient), and safety constraint rules (such as oil temperature above the pour point). The following are considered: pressure at each point in the pipeline does not exceed the design pressure, restart pressure does not exceed the pipeline strength limit; energy consumption calculation rules (such as the relationship between pump efficiency curve, furnace thermal efficiency curve and throughput); equipment and physical property data knowledge, including collecting characteristic parameters and performance curves of pumps, furnaces, and valves; collecting rheological data such as pour point, anomalous point, viscosity-temperature characteristic curves, and yield stress of different batches of oil.

[0022] It should be noted that the initially collected multi-source knowledge of crude oil pipelines can be divided into structured data and unstructured data according to their data format. Structured data has a fixed format, fixed fields, and a unified standardized structure. It can be neatly stored in a two-dimensional table (rows + columns), and the field meanings are clear, orderly, and can be directly read and parsed by machines. Unstructured data is the opposite. In order to further generate process diagrams based on structured and unstructured data, different processing strategies need to be applied to structured and unstructured data. Therefore, it is necessary to first divide the multi-source knowledge of crude oil pipelines into structured data and unstructured data.

[0023] Specifically, taking one crude oil pipeline knowledge from the multi-source knowledge of crude oil pipelines as an example, by identifying the data format of the crude oil pipeline knowledge, the crude oil pipeline knowledge is divided into structured data and unstructured data. The structured data is recorded as the target structured knowledge, and the unstructured data is recorded as the target unstructured knowledge.

[0024] For example, crude oil pipeline knowledge in one of the following data formats—.csv, .xls, .xlsx, and .sql (including create / insert)—is classified as target structured knowledge, while crude oil pipeline knowledge in one of the following data formats—.html, .docx, .pdf, .txt, .md, .jpg, .mp3, and .mp4—is classified as target unstructured knowledge.

[0025] S120. Based on the target unstructured knowledge and the target structured knowledge, determine a knowledge unit set; the knowledge unit set includes the knowledge content corresponding to the target unstructured knowledge and the target structured knowledge respectively, and the metadata tags corresponding to each knowledge content respectively.

[0026] It should be noted that this embodiment aims to convert both the target unstructured knowledge and the target structured knowledge into a unified structured expression form, so as to facilitate the subsequent construction of crude oil pipeline process maps.

[0027] In order to convert both target unstructured knowledge and target structured knowledge into a unified structured expression, this embodiment provides a first conversion strategy for target unstructured knowledge and a second conversion strategy for target structured knowledge; through the first conversion strategy and the second conversion strategy, both target unstructured knowledge and target structured knowledge can be converted into a unified structured expression.

[0028] In this example, the unified structured expression is denoted as a knowledge unit. For instance, this knowledge unit consists of two parts: the knowledge content corresponding to the target unstructured knowledge or target structured knowledge, and metadata tags matching that knowledge content. For instance, these metadata tags include at least knowledge type tags, applicable object tags, process scenario tags, and keyword tags. Specifically, knowledge type tags include standards, procedures, contingency plans, cases, and mechanism rules; applicable object tags include heating furnaces, oil pumps, pipeline segment chainage ranges, and specific oil products; and process scenario tags include normal transportation, start-up, shutdown, and emergency. The set of each target unstructured knowledge and each knowledge unit corresponding to each target structured knowledge is denoted as the knowledge unit set.

[0029] S130. Determine each knowledge entity in the knowledge unit set, and the entity relationships between each knowledge entity.

[0030] It should be noted that the crude oil pipeline process map is used to allow users to retrieve the knowledge they need. This knowledge includes corresponding entities, which are the key features of the knowledge, such as: pipeline, inclusions, pipe segments, etc. To facilitate user retrieval of this crude oil pipeline process map, in addition to providing users with the knowledge they can directly search for, this embodiment also provides users with hidden knowledge related to the retrieved knowledge. Therefore, this embodiment also needs to establish entity relationships between the various knowledge entities in the knowledge unit set.

[0031] Specifically, firstly, extract the corresponding entities from the knowledge content of each knowledge unit in the knowledge unit set and denot them as knowledge entities; then, define the entity relationships between each knowledge entity.

[0032] Examples of defined entity relationships include: “[Pipeline]-[Contains]->[Pipeline Segment]”, “[Station]-[Located at]->[Pipeline Segment]”, “[Station]-[Equipped with]->[Oil Pump] / [Heating Furnace]”, “[Process Scheme]-[Applicable to]->[Crude Oil]”, “[Process Scheme]-[Constrained]->[Temperature Control Threshold Rule]”, “[Risk Event]-[Trigger]->[Emergency Plan]”, etc.

[0033] S140. Based on the knowledge entity and the entity relationship, construct a crude oil pipeline process map.

[0034] By storing the generated knowledge entities and entity relationships into a preset graph database (such as Neo4j), a crude oil pipeline process map can be obtained, which can be queried and reasoned by users.

[0035] It should be noted that this crude oil pipeline process map supports path query, for example: querying all associated "temperature control rules", "pressure constraints" and applicable "emergency plans" for "a certain pipeline section" under the current condition of "transporting a certain crude oil".

[0036] It should be noted that this embodiment filters the acquired multi-source knowledge of crude oil pipelines to obtain target unstructured knowledge and target structured knowledge; based on the target unstructured knowledge and target structured knowledge, a knowledge unit set is determined; the knowledge unit set includes the knowledge content corresponding to the target unstructured knowledge and the target structured knowledge, and the metadata tags corresponding to each knowledge content; each knowledge entity in the knowledge unit set is determined, and the entity relationships between the knowledge entities are determined; based on the knowledge entities and the entity relationships, a crude oil pipeline process map is constructed. Through the above implementation, firstly, since the acquired multi-source knowledge of crude oil pipelines is processed to obtain a crude oil pipeline process map, this map facilitates users to obtain the required process knowledge in the form of retrieval, thus improving the retrieval efficiency and accuracy of crude oil pipeline process knowledge; secondly, the crude oil pipeline process map centralizes multi-source knowledge of crude oil pipelines in one place for users to retrieve, effectively reducing the information silo level of crude oil pipeline process knowledge.

[0037] Example 2 This application provides a method for constructing a crude oil pipeline process map in Embodiment 2. This method optimizes the step in Embodiment 1 of "screening the acquired multi-source knowledge of crude oil pipelines to obtain target unstructured knowledge and target structured knowledge." It should be noted that for parts not detailed in this embodiment, please refer to the descriptions in other embodiments. This method includes: S211. Based on the preset knowledge data format, perform preliminary screening on the acquired multi-source knowledge of crude oil pipelines to obtain preliminary structured knowledge, preliminary unstructured knowledge, and preliminary pending knowledge.

[0038] It should be noted that each piece of knowledge in the multi-source knowledge of crude oil pipelines has a corresponding data format. Through the data format, structured knowledge and unstructured knowledge can be initially screened out from the multi-source knowledge of crude oil pipelines. After the initial screening of structured and unstructured knowledge, the remaining knowledge in the multi-source knowledge of crude oil pipelines is also known as pending knowledge. It is not yet clear whether the pending knowledge belongs to structured knowledge or unstructured knowledge, and further identification is required. The structured knowledge initially screened is recorded as preliminary screened structured knowledge, the unstructured knowledge initially screened is recorded as preliminary screened unstructured knowledge, and the pending knowledge is recorded as preliminary screened pending knowledge.

[0039] For example, if the data type of knowledge in the multi-source knowledge of crude oil pipelines is one of .csv, .xls, .xlsx, or .sql (including create / insert), then the knowledge is determined to be initially screened as structured knowledge; if the data type of knowledge in the multi-source knowledge of crude oil pipelines is one of .html, .docx, .pdf, .txt, .md, .jpg, .mp3, or .mp4, then the knowledge is determined to be initially screened as unstructured knowledge; then, knowledge in the multi-source knowledge of crude oil pipelines that is not initially screened as structured knowledge or unstructured knowledge is determined as pending knowledge in the initial screening.

[0040] S212. Based on a preset re-screening strategy, the initially screened undetermined knowledge is re-screened to obtain re-screened structured knowledge and re-screened unstructured knowledge.

[0041] It should be noted that, in order to further divide the initially screened knowledge into structured knowledge and unstructured knowledge, this embodiment has a pre-set re-screening strategy.

[0042] Among them, the structured knowledge that is screened by the re-screening strategy to identify the unstructured knowledge in the initial screening is called re-screened structured knowledge, and the unstructured knowledge that is screened by the re-screening strategy to identify the unstructured knowledge in the initial screening is called re-screened unstructured knowledge.

[0043] S213. Based on the initial screening structured knowledge, the initial screening unstructured knowledge, the rescreening structured knowledge, and the rescreening unstructured knowledge, target unstructured knowledge and target structured knowledge are obtained.

[0044] In this process, the initial screening of structured knowledge and the subsequent screening of structured knowledge are combined and denoted as target structured knowledge. The initial screening of unstructured knowledge and the subsequent screening of unstructured knowledge are also combined and denoted as target unstructured knowledge.

[0045] It should be noted that by further dividing the initially screened knowledge into structured and unstructured knowledge, instead of discarding it directly, we not only make full use of the multi-source knowledge of crude oil pipelines, but also increase the amount of knowledge in both the target unstructured and target structured knowledge.

[0046] S220. Based on the target unstructured knowledge and the target structured knowledge, determine a knowledge unit set; the knowledge unit set includes the knowledge content corresponding to the target unstructured knowledge and the target structured knowledge respectively, and the metadata tags corresponding to each knowledge content respectively.

[0047] S230. Determine each knowledge entity in the knowledge unit set, and the entity relationships between each knowledge entity.

[0048] S240. Based on the knowledge entity and the entity relationship, construct a crude oil pipeline process map.

[0049] Example 3 This application provides a method for constructing a crude oil pipeline process map in Embodiment 3. This method optimizes the step in Embodiment 2, which involves "re-screening the initially screened undetermined knowledge based on a preset re-screening strategy to obtain re-screened structured knowledge and re-screened unstructured knowledge." It should be noted that for parts not detailed in this embodiment, please refer to the descriptions in other embodiments. This method includes: S311. Based on the preset knowledge data format, perform preliminary screening on the acquired multi-source knowledge of crude oil pipelines to obtain preliminary structured knowledge, preliminary unstructured knowledge, and preliminary pending knowledge.

[0050] S312A: In response to the fact that the data format of the preliminary screening pending knowledge is JSON format, the knowledge records in the preliminary screening pending knowledge are read in batches. In response that each of the knowledge records corresponds to the same key value, the preliminary screening pending knowledge is determined as structured knowledge for further screening; otherwise, it is determined as unstructured knowledge for further screening.

[0051] In this process, the initial screening of undetermined knowledge contains multiple pieces of knowledge, and each piece of knowledge is recorded as a knowledge record. A re-screening strategy is as follows: if the multiple knowledge records contained in the initial screening of undetermined knowledge are all in JSON format, and a batch of knowledge records randomly read from the initial screening of undetermined knowledge all correspond to the same key (corresponding to the same key means that the data has a unified and predictable schema, which is the core feature of structured data), then the initial screening of undetermined knowledge has a very high probability of being structured knowledge, and the initial screening of undetermined knowledge will be determined as re-screened structured knowledge; otherwise, it will be determined as re-screened unstructured knowledge.

[0052] S312B. In response to the fact that the data format of the preliminary screening undetermined knowledge is XML format, determine whether the preliminary screening undetermined knowledge can be parsed to obtain the corresponding document definition. If so, determine the preliminary screening undetermined knowledge as structured knowledge for further screening; otherwise, determine it as unstructured knowledge for further screening.

[0053] Another re-screening strategy is as follows: if the data format of the initially screened undetermined knowledge is all in XML format, and the corresponding document definition can be parsed out from the initially screened undetermined knowledge, then the initially screened undetermined knowledge has a very high probability of being structured knowledge. At this time, the initially screened undetermined knowledge is determined to be re-screened structured knowledge; otherwise, it is determined to be re-screened unstructured knowledge.

[0054] Among them, a document is defined as which elements are allowed to appear in the data, the order and nesting relationship between the elements, and the type of attributes; if the preliminary screening of undetermined knowledge in XML format has a related document definition, it means that the knowledge has a clearly defined data structure rule, and this kind of knowledge is generally structured knowledge.

[0055] S313. Based on the initial screening structured knowledge, the initial screening unstructured knowledge, the rescreening structured knowledge, and the rescreening unstructured knowledge, target unstructured knowledge and target structured knowledge are obtained.

[0056] S320. Based on the target unstructured knowledge and the target structured knowledge, determine a knowledge unit set; the knowledge unit set includes the knowledge content corresponding to the target unstructured knowledge and the target structured knowledge respectively, and the metadata tags corresponding to each knowledge content respectively.

[0057] S330. Determine each knowledge entity in the knowledge unit set, and the entity relationships between each knowledge entity.

[0058] S340. Based on the knowledge entity and the entity relationship, construct a crude oil pipeline process map.

[0059] Example 4 This application provides a method for constructing a crude oil pipeline process map in Embodiment 4. This method optimizes the "determining a knowledge unit set based on the target unstructured knowledge and the target structured knowledge" in Embodiment 1. It should be noted that for parts not detailed in this embodiment, please refer to the descriptions in other embodiments. The method includes: S410. Filter the acquired multi-source knowledge of crude oil pipelines to obtain target unstructured knowledge and target structured knowledge.

[0060] S421. The target unstructured knowledge is parsed to obtain plain text table data, and the plain text table data is semantically segmented to obtain knowledge blocks.

[0061] It should be noted that, based on the obtained target unstructured knowledge and target structured knowledge, this embodiment intends to process the target unstructured knowledge and target structured knowledge into corresponding knowledge units respectively.

[0062] In order to process the target unstructured knowledge into corresponding knowledge units, it is necessary to first perform document parsing on the target unstructured knowledge to obtain the plain text and / or plain table data. This embodiment has a pre-set document parsing tool for parsing the target unstructured knowledge, and the parsed plain text and / or plain table data is denoted as plain text table data.

[0063] It should be noted that the plain text table data itself is large in volume and may contain multiple knowledge items. This embodiment aims to establish a corresponding knowledge unit for each knowledge item. To this end, it is also necessary to perform semantic segmentation on the plain text table data to obtain multiple knowledge blocks, each of which belongs to one knowledge item. Specifically, the semantic segmentation is implemented by intelligently segmenting the plain text table data according to the heading level and paragraph semantics to obtain multiple knowledge blocks. This segmentation method helps to ensure the integrity and independence of each knowledge block.

[0064] S422, Match the first metadata tag to the knowledge block.

[0065] The first metadata tags include knowledge type tags, applicable object tags, process scenario tags, keyword tags, etc., without any specific limitations.

[0066] For example, the first metadata tag of the knowledge block "Emergency Response Plan for Condensation Pipeline" is specifically "[Knowledge Type: Plan] [Process Scenario: Shutdown] [Keywords: Condensation Pipeline, Restart]".

[0067] S423. In response to the target structured knowledge being mechanistic rule-based knowledge, the target structured knowledge is explicitly encoded to obtain condition-conclusion rule pairs.

[0068] It should be noted that although the target structured knowledge is already a type of structured knowledge, it is still further processed in order to generate the corresponding knowledge units.

[0069] Among them, the target structured knowledge can be divided into mechanism rule knowledge (collecting and explicitly defining physical rules and safety constraints in process calculations). The reprocessing strategy for this mechanism rule knowledge is to explicitly encode it, thereby processing it into condition-conclusion rule pairs.

[0070] For example, one condition-conclusion rule pair is: IF Outlet temperature ≤ Pour point + 3℃ THEN Risk level = "High risk in condensation pipe"; another example is: IF Pipeline pressure > Design pressure × 1.0 THEN Status = "Overpressure".

[0071] S424, Match the second metadata tag for the condition-conclusion rule pair.

[0072] Among them, as mentioned above, the first metadata tag, the second metadata tag also includes knowledge type tags, applicable object tags, process scenario tags, keyword tags, etc., without any specific limitations.

[0073] S425. In response to the target structured knowledge being equipment performance knowledge or item property knowledge, the target structured knowledge is tabulated to obtain tabular knowledge.

[0074] Among them, the target structured knowledge can be further divided into equipment performance knowledge or item property knowledge. If the target structured knowledge is equipment performance knowledge or item property knowledge, then the target structured knowledge is organized into a standardized table structure and associated with specific equipment IDs and oil batches, thereby realizing the tabulation of the target structured knowledge. The tabulated target structured knowledge is recorded as table knowledge.

[0075] S426. Match the third metadata tag to the knowledge in the table.

[0076] In addition to the first and second metadata tags mentioned above, the third metadata tag also includes knowledge type tags, applicable object tags, process scenario tags, keyword tags, etc., without any specific limitations.

[0077] S427. Based on the knowledge block, the first metadata tag, the condition-conclusion rule pair, the second metadata tag, the tabular knowledge, and the third metadata tag, determine the knowledge unit set.

[0078] In this embodiment, a knowledge unit comprises two components: knowledge content and metadata tags.

[0079] Among them, the knowledge content in the knowledge unit corresponding to the target unstructured knowledge is a knowledge block, and the metadata tag is the first metadata tag; the knowledge content in the knowledge unit corresponding to the target structured knowledge of the type of mechanism rule knowledge is a condition-conclusion rule pair, and the metadata tag is the second metadata tag; the knowledge content in the knowledge unit corresponding to the target structured knowledge of the type of equipment performance knowledge or item property knowledge is tabular knowledge, and the metadata tag is the third metadata tag.

[0080] In an optional embodiment, in addition to the two components mentioned above, each knowledge unit may also include a knowledge unit ID and one or more of the source files as new components; wherein, the knowledge unit ID is used to identify the corresponding knowledge unit, and the source file is used to represent the original source file of the corresponding knowledge unit.

[0081] S430. Determine each knowledge entity in the knowledge unit set, and the entity relationships between each knowledge entity.

[0082] S440. Based on the knowledge entity and the entity relationship, construct a crude oil pipeline process map.

[0083] Example 5 This application provides a method for constructing a crude oil pipeline process map in Embodiment 5, which supplements the method shown in Embodiment 1. It should be noted that for parts not detailed in this embodiment, please refer to the descriptions in other embodiments. The method includes: S510. Filter the acquired multi-source knowledge of crude oil pipelines to obtain target unstructured knowledge and target structured knowledge.

[0084] S520. Based on the target unstructured knowledge and the target structured knowledge, determine a knowledge unit set; the knowledge unit set includes the knowledge content corresponding to the target unstructured knowledge and the target structured knowledge respectively, and the metadata tags corresponding to each knowledge content respectively.

[0085] S530. Determine each knowledge entity in the knowledge unit set, and the entity relationships between each knowledge entity.

[0086] S540. Based on the knowledge entity and the entity relationship, construct a crude oil pipeline process map.

[0087] S550. Vectorize the knowledge units in the knowledge unit set to obtain unit vectors.

[0088] It should be noted that while users can retrieve knowledge from the crude oil pipeline process diagram using custom search terms, the retrieval results are unsatisfactory, specifically in terms of low retrieval efficiency and a limited number of knowledge results related to the search terms. However, if each knowledge unit is vectorized and the vectorized results are added to the corresponding knowledge unit, the deep semantic information of the knowledge unit can be captured during the retrieval process. This allows semantically similar queries and knowledge to be closer together in the vector space, thereby improving retrieval efficiency and increasing the number of knowledge results related to the search terms.

[0089] This implementation includes a pre-defined text embedding model optimized for the industrial and technological fields (such as the BGE (BAAI General Embedding) series of models optimized for industrial corpora). This model is used to vectorize the knowledge units in the input and record the vectorization results as unit vectors.

[0090] S560. Based on the unit vector and the knowledge unit set, determine the knowledge expansion unit set.

[0091] Each unit vector corresponds to a knowledge unit in the knowledge unit set. Taking one of the unit vectors as an example, by adding the unit vector as a new component to the corresponding knowledge unit, a new knowledge unit can be obtained, which is denoted as the knowledge extension unit. The set of knowledge extension units corresponding to each unit vector is also denoted as the knowledge extension unit set.

[0092] S570. Based on the knowledge expansion unit set, construct a target process knowledge graph.

[0093] Among them, a new knowledge graph can be constructed through this knowledge expansion unit set. The construction process is the same as steps S530-S540 above, and will not be repeated here. The new knowledge graph constructed through the knowledge expansion unit set is denoted as the target process knowledge graph.

[0094] It should be noted that, since the target process knowledge graph contains unit vectors corresponding to each knowledge unit, it enables the target process knowledge graph to support efficient approximate nearest neighbor retrieval, and can recall and query the most relevant knowledge from hundreds of thousands of knowledge blocks in milliseconds.

[0095] Example 6 This application provides a method for constructing a crude oil pipeline process map in Embodiment Six, which supplements the method shown in Embodiment Five. It should be noted that for parts not detailed in this embodiment, please refer to the descriptions in other embodiments. The method includes: S610. Filter the acquired multi-source knowledge of crude oil pipelines to obtain target unstructured knowledge and target structured knowledge.

[0096] S620. Based on the target unstructured knowledge and the target structured knowledge, determine a knowledge unit set; the knowledge unit set includes the knowledge content corresponding to the target unstructured knowledge and the target structured knowledge respectively, and the metadata tags corresponding to each knowledge content respectively.

[0097] S630. Determine each knowledge entity in the knowledge unit set, and the entity relationships between each knowledge entity.

[0098] S640. Based on the knowledge entity and the entity relationship, construct a crude oil pipeline process map.

[0099] S650. Vectorize the knowledge units in the knowledge unit set to obtain unit vectors.

[0100] S660. Based on the unit vector and the knowledge unit set, determine the knowledge expansion unit set.

[0101] S670. Based on the knowledge expansion unit set, construct a target process knowledge graph.

[0102] S680. In response to the existence of new multi-source knowledge of crude oil pipelines, the target process knowledge graph is updated based on the new multi-source knowledge of crude oil pipelines to obtain a process knowledge update graph.

[0103] It should be noted that after the target process knowledge graph is finalized, new multi-source knowledge about crude oil pipelines will emerge over time. If the target process knowledge graph cannot be updated in a timely manner, the accuracy of the knowledge retrieved through the target process knowledge graph will decrease significantly. Therefore, it is necessary to periodically check whether new multi-source knowledge about crude oil pipelines has emerged.

[0104] For example, with a 15-day cycle, it is periodically checked whether there is new crude oil pipeline multi-source knowledge. If so, the new crude oil pipeline multi-source knowledge and the original crude oil pipeline multi-source knowledge are combined to form the current crude oil pipeline multi-source knowledge. According to steps S610-S670, a new target process knowledge graph is constructed, which is denoted as the process knowledge update graph.

[0105] S690. Record the update information corresponding to the process knowledge update map.

[0106] The update information includes the time, content, and operator of the update.

[0107] In an optional embodiment, to evaluate the retrieval performance of the process knowledge update graph, the analysis also examines cases where user adoption rates are low or reports are inaccurate in the RAG recall results.

[0108] Example 7 This application provides a method for constructing a crude oil pipeline process map in Embodiment 7, which supplements the method shown in Embodiment 5. It should be noted that for parts not detailed in this embodiment, please refer to the descriptions in other embodiments. The method includes: S710. Filter the acquired multi-source knowledge of crude oil pipelines to obtain target unstructured knowledge and target structured knowledge.

[0109] S720. Based on the target unstructured knowledge and the target structured knowledge, determine a knowledge unit set; the knowledge unit set includes the knowledge content corresponding to the target unstructured knowledge and the target structured knowledge respectively, and the metadata tags corresponding to each knowledge content respectively.

[0110] S730. Determine each knowledge entity in the knowledge unit set, and the entity relationships between each knowledge entity.

[0111] S740. Based on the knowledge entity and the entity relationship, construct a crude oil pipeline process map.

[0112] S750. Vectorize the knowledge units in the knowledge unit set to obtain unit vectors.

[0113] S760. Based on the unit vector and the knowledge unit set, determine the knowledge expansion unit set.

[0114] S770. Based on the knowledge extension unit set, construct a target process knowledge graph.

[0115] S780. The target process knowledge graph is encapsulated to obtain a unified service interface; the unified service interface includes: a retrieval service interface, a graph query interface, and a knowledge verification interface.

[0116] It should be noted that, in order to make the generated target process knowledge graph available for use by the upper-level decision-making agent (RAG module), this embodiment also encapsulates the target process knowledge graph into a unified service interface; in this embodiment, the encapsulated unified service interface includes: a retrieval service interface, a graph query interface, and a knowledge verification interface.

[0117] For example, the input to the retrieval service interface is: a process query statement generated by the user or intelligent agent (e.g., "The current oil temperature is close to the pour point, give all relevant warning rules and handling cases"); the output of the retrieval service interface is: the Top-N relevant knowledge units after mixed retrieval and sorting, including complete knowledge content, source, and relevant graph node information.

[0118] For example, the input to the graph query interface is one or more entity IDs (e.g., pipe segment ID, device ID); the output of the graph query interface is to return the neighborhood information of the entity in the graph in JSON format, including associated devices, rules, and plans.

[0119] For example, the input to the knowledge verification interface is: preliminary process suggestions generated by the large model (e.g., "It is recommended to set the outlet temperature to XX degrees"); the output of the knowledge verification interface is: the corresponding constraints retrieved from the knowledge base (e.g., "The standard stipulates that the outlet temperature of this oil product should not be lower than XX degrees"), which are used for subsequent compliance verification.

[0120] It should be noted that the above-described method embodiments have the following effects: 1. Systematize knowledge: Integrate scattered and heterogeneous process knowledge into a unified, standardized, and interconnected knowledge base to eliminate information silos.

[0121] 2. Intelligent retrieval: Upgraded from keyword search to semantic understanding, the precision and recall of knowledge queries are greatly improved, and the intelligent agent can obtain the required information faster and more accurately.

[0122] 3. Services are callable; through standardized API interfaces, the knowledge base can be flexibly called by various upper-layer applications such as decision-making agents, simulation systems, and operator portals, and the knowledge is highly reusable.

[0123] 4. Reasoning is supported; the process knowledge graph provides a data foundation for the agent's associative reasoning, enabling it to have the analytical ability of "reasoning from cause to effect" and "drawing inferences from similar cases".

[0124] 5. Decisions are based on evidence; every suggestion generated by the intelligent agent can be traced back to specific standards, procedures or cases in the knowledge base, making the decision-making process explainable, traceable and auditable.

[0125] 6. Knowledge can evolve; an automated knowledge update mechanism has been established, and new cases and procedures can be quickly added to the database and take effect. The knowledge base becomes more and more complete and accurate as the system runs for a long time.

[0126] 7. Safety is guaranteed; through a knowledge verification mechanism, process safety constraints are explicitly injected into the decision-making process of the intelligent agent, effectively avoiding erroneous suggestions that violate physical laws or safety standards.

[0127] 8. Low implementation cost; adopting the RAG architecture that eliminates the need for fine-tuning of large models, only the knowledge base needs to be built to empower general large models, without the need to invest high computing power for domain model fine-tuning, making deployment simple and cost-effective.

[0128] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0129] Example 8 Based on the same inventive concept, this embodiment also provides a crude oil pipeline process map construction device for implementing the crude oil pipeline process map construction method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the crude oil pipeline process map construction device provided below can be found in the limitations of the crude oil pipeline process map construction method described above, and will not be repeated here.

[0130] In this embodiment, as Figure 2 As shown, a crude oil pipeline process map construction device is provided, comprising: The knowledge filtering module is used to filter the acquired multi-source knowledge of crude oil pipelines to obtain target unstructured knowledge and target structured knowledge. The unit determination module is used to determine a knowledge unit set based on the target unstructured knowledge and the target structured knowledge; the knowledge unit set includes the knowledge content corresponding to the target unstructured knowledge and the target structured knowledge respectively, and the metadata tags corresponding to each knowledge content respectively; An entity recognition module is used to determine each knowledge entity in the knowledge unit set, as well as the entity relationships between the knowledge entities. The graph construction module is used to construct a crude oil pipeline process graph based on the knowledge entities and their relationships.

[0131] Each module in the aforementioned crude oil pipeline process diagram construction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor within the electronic device in hardware form, or stored in the memory of the electronic device in software form, so that the processor can call and execute the corresponding operations of each module.

[0132] It should be noted that this embodiment filters the acquired multi-source knowledge of crude oil pipelines to obtain target unstructured knowledge and target structured knowledge; based on the target unstructured knowledge and target structured knowledge, a knowledge unit set is determined; the knowledge unit set includes the knowledge content corresponding to the target unstructured knowledge and the target structured knowledge, and the metadata tags corresponding to each knowledge content; each knowledge entity in the knowledge unit set is determined, and the entity relationships between the knowledge entities are determined; based on the knowledge entities and the entity relationships, a crude oil pipeline process map is constructed. Through the above implementation, firstly, since the acquired multi-source knowledge of crude oil pipelines is processed to obtain a crude oil pipeline process map, this map facilitates users to obtain the required process knowledge in the form of retrieval, thus improving the retrieval efficiency and accuracy of crude oil pipeline process knowledge; secondly, the crude oil pipeline process map centralizes multi-source knowledge of crude oil pipelines in one place for users to retrieve, effectively reducing the information silo level of crude oil pipeline process knowledge.

[0133] In an optional embodiment, the step of filtering the acquired multi-source knowledge of crude oil pipelines to obtain target unstructured knowledge and target structured knowledge includes: Based on a preset knowledge data format, the acquired multi-source knowledge of crude oil pipelines is initially screened to obtain initially screened structured knowledge, initially screened unstructured knowledge, and initially screened pending knowledge. The initially screened undetermined knowledge is re-screened based on a preset re-screening strategy to obtain re-screened structured knowledge and re-screened unstructured knowledge. Based on the initial screening structured knowledge, the initial screening unstructured knowledge, the rescreening structured knowledge, and the rescreening unstructured knowledge, target unstructured knowledge and target structured knowledge are obtained.

[0134] In an optional embodiment, the re-screening of the initially screened undetermined knowledge based on a preset re-screening strategy to obtain re-screened structured knowledge and re-screened unstructured knowledge includes: In response to the fact that the data format of the initially screened undetermined knowledge is JSON format, knowledge records in the initially screened undetermined knowledge are read in batches. In response that each of the knowledge records corresponds to the same key value, the initially screened undetermined knowledge is determined to be structured knowledge for further screening; otherwise, it is determined to be unstructured knowledge for further screening. In response to the fact that the data format of the initially screened undetermined knowledge is XML, it is determined whether the corresponding document definition can be parsed from the initially screened undetermined knowledge. If so, the initially screened undetermined knowledge is determined to be structured knowledge for further screening; otherwise, it is determined to be unstructured knowledge for further screening.

[0135] In an optional embodiment, determining the knowledge unit set based on the target unstructured knowledge and the target structured knowledge includes: The target unstructured knowledge is parsed to obtain plain text table data, and the plain text table data is semantically segmented to obtain knowledge blocks; Match the first metadata tag to the knowledge block; In response to the fact that the target structured knowledge is mechanistic rule-based knowledge, the target structured knowledge is explicitly encoded to obtain condition-conclusion rule pairs; The condition-conclusion rule is used to match the second metadata tag; In response to the fact that the target structured knowledge is equipment performance knowledge or item property knowledge, the target structured knowledge is tabulated to obtain tabular knowledge; Match third-party metadata tags to the knowledge in the table; Based on the knowledge block, the first metadata tag, the condition-conclusion rule pair, the second metadata tag, the tabular knowledge, and the third metadata tag, a knowledge unit set is determined.

[0136] In an optional embodiment, the crude oil pipeline process mapping device further includes: The vector calculation module is used to vectorize the knowledge units in the knowledge unit set to obtain unit vectors; The unit expansion module is used to determine the knowledge expansion unit set based on the unit vector and the knowledge unit set; The knowledge graph creation module is used to construct a target process knowledge graph based on the knowledge expansion unit set.

[0137] In an optional embodiment, the crude oil pipeline process mapping device further includes: The graph update module is used to update the target process knowledge graph based on the new crude oil pipeline multi-source knowledge in response to the existence of new crude oil pipeline multi-source knowledge, so as to obtain a process knowledge update graph. The information recording module is used to record the update information corresponding to the updated process knowledge map.

[0138] In an optional embodiment, the crude oil pipeline process mapping device further includes: An interface encapsulation module is used to encapsulate the target process knowledge graph to obtain a unified service interface; the unified service interface includes: a retrieval service interface, a graph query interface, and a knowledge verification interface.

[0139] Example 9 Figure 3 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0140] like Figure 3 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0141] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0142] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the method for determining the microcirculation resistance index.

[0143] In some embodiments, the method for determining the microcirculation resistance index may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for determining the microcirculation resistance index described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method for determining the microcirculation resistance index by any other suitable means (e.g., by means of firmware).

[0144] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0145] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0146] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0147] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0148] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0149] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0150] Example 10 In this embodiment, a computer-readable storage medium is provided, such as... Figure 4 As shown, a computer program is stored thereon, and when the computer program is executed by the processor, it implements the steps in the above-described method embodiments.

[0151] Example 11 In this embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0152] It should be noted that the information collected is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with the relevant laws, regulations and standards of the relevant countries and regions, necessary confidentiality measures have been taken, and it does not violate public order and good morals. Corresponding operation portals are provided for users to choose to authorize or refuse.

[0153] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this disclosure can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this disclosure may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this disclosure may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0154] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0155] The embodiments described above are merely illustrative of several implementations of this disclosure, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent disclosure. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this disclosure, and these all fall within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the appended claims.

Claims

1. A method for constructing a crude oil pipeline process map, characterized in that, include: The acquired multi-source knowledge of crude oil pipelines is filtered to obtain target unstructured knowledge and target structured knowledge; Based on the target unstructured knowledge and the target structured knowledge, a knowledge unit set is determined; The knowledge unit set includes the knowledge content corresponding to the target unstructured knowledge and the target structured knowledge, respectively, and the metadata tags corresponding to each knowledge content; Determine each knowledge entity in the knowledge unit set, and the entity relationships between each knowledge entity; Based on the knowledge entities and their relationships, a crude oil pipeline process map is constructed.

2. The method according to claim 1, characterized in that, The process of filtering the acquired multi-source knowledge of crude oil pipelines yields target unstructured knowledge and target structured knowledge, including: Based on a preset knowledge data format, the acquired multi-source knowledge of crude oil pipelines is initially screened to obtain initially screened structured knowledge, initially screened unstructured knowledge, and initially screened pending knowledge. The initially screened undetermined knowledge is re-screened based on a preset re-screening strategy to obtain re-screened structured knowledge and re-screened unstructured knowledge. Based on the initial screening structured knowledge, the initial screening unstructured knowledge, the rescreening structured knowledge, and the rescreening unstructured knowledge, target unstructured knowledge and target structured knowledge are obtained.

3. The method according to claim 2, characterized in that, The pre-set re-screening strategy is used to re-screen the initially screened undetermined knowledge to obtain re-screened structured knowledge and re-screened unstructured knowledge, including: In response to the fact that the data format of the initially screened undetermined knowledge is JSON format, knowledge records in the initially screened undetermined knowledge are read in batches. In response that each of the knowledge records corresponds to the same key value, the initially screened undetermined knowledge is determined to be structured knowledge for further screening; otherwise, it is determined to be unstructured knowledge for further screening. In response to the fact that the data format of the initially screened undetermined knowledge is XML, it is determined whether the corresponding document definition can be parsed from the initially screened undetermined knowledge. If so, the initially screened undetermined knowledge is determined to be structured knowledge for further screening; otherwise, it is determined to be unstructured knowledge for further screening.

4. The method according to claim 1, characterized in that, The step of determining a knowledge unit set based on the target unstructured knowledge and the target structured knowledge includes: The target unstructured knowledge is parsed to obtain plain text table data, and the plain text table data is semantically segmented to obtain knowledge blocks; Match the first metadata tag to the knowledge block; In response to the fact that the target structured knowledge is mechanistic rule-based knowledge, the target structured knowledge is explicitly encoded to obtain condition-conclusion rule pairs; The condition-conclusion rule is used to match the second metadata tag; In response to the fact that the target structured knowledge is equipment performance knowledge or item property knowledge, the target structured knowledge is tabulated to obtain tabular knowledge; Match third-party metadata tags to the knowledge in the table; Based on the knowledge block, the first metadata tag, the condition-conclusion rule pair, the second metadata tag, the tabular knowledge, and the third metadata tag, a knowledge unit set is determined.

5. The method according to claim 1, characterized in that, Also includes: Vectorize the knowledge units in the knowledge unit set to obtain unit vectors; Based on the unit vector and the knowledge unit set, determine the knowledge expansion unit set; Based on the aforementioned knowledge extension unit set, a target process knowledge graph is constructed.

6. The method according to claim 5, characterized in that, Also includes: In response to the existence of new multi-source knowledge about crude oil pipelines, the target process knowledge graph is updated based on the new multi-source knowledge about crude oil pipelines to obtain an updated process knowledge graph. Record the update information corresponding to the updated process knowledge map.

7. The method according to claim 5, characterized in that, Also includes: The target process knowledge graph is encapsulated into a unified service interface. The unified service interface includes: retrieval service interface, graph query interface, and knowledge verification interface.

8. A crude oil pipeline process map construction device, characterized in that, The device includes: The knowledge filtering module is used to filter the acquired multi-source knowledge of crude oil pipelines to obtain target unstructured knowledge and target structured knowledge. The unit determination module is used to determine a knowledge unit set based on the target unstructured knowledge and the target structured knowledge; the knowledge unit set includes the knowledge content corresponding to the target unstructured knowledge and the target structured knowledge respectively, and the metadata tags corresponding to each knowledge content respectively; An entity recognition module is used to determine each knowledge entity in the knowledge unit set, as well as the entity relationships between the knowledge entities. The graph construction module is used to construct a crude oil pipeline process graph based on the knowledge entities and their relationships.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the target box grasping method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the target box grasping method according to any one of claims 1-7.

Images