A knowledge graph construction method and device for power operation and inspection

Abstract

The embodiment of the present invention provides a method and device for constructing a knowledge graph specifically related to electric power operation and inspection, which solves the problem that it is difficult to ensure the accuracy of knowledge graph construction in the field of electric power operation and inspection without the support of professional and technical personnel. The method for constructing a knowledge graph for electric power operation and inspection includes: obtaining data information; selecting a data dump in the data information, and determining the dump type, and constructing corresponding nodes and newly added nodes according to the dump type; obtaining the relationship between the node and the newly added node based on the node and the newly added node; and constructing a knowledge graph database based on the node, the newly added node, and the relationship between the node and the newly added node.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a method and device for constructing a knowledge graph for electric power operation and maintenance. Background Art

[0002] As an important branch of artificial intelligence technology, knowledge graph (KG) has been successfully applied in the big data environment. It combines big data in intelligent search, intelligent question and answer, intelligent recommendation and intelligent decision-making, and has shown great power in many fields such as medical care and finance. As a power production and consumption system with complex assets and intensive knowledge, the power system has complex concepts, entities, events and relationships, involving a systematic knowledge system in multiple fields such as generation, transmission, transformation, distribution and use. Based on business needs, power companies have proposed a variety of technical routes and application cases in the knowledge graph of the power field to achieve data connectivity and support the development of power grid business and new business. The knowledge entities in the open, flat and weakly bounded power field knowledge system are difficult to semantically expand. The knowledge in the power operation and inspection field is widely derived from structured data such as power knowledge engineering system and expert knowledge, and semi- / unstructured data such as power standards, experience of experts and technicians. The knowledge and data in the operation and inspection field have many situations such as aliases, abbreviations, and colloquialisms, which are difficult to identify through general word segmentation tools, and it is difficult to ensure accuracy without expert supervised learning and strong rule definition. At the same time, since programmers do not understand this professional field knowledge, it is difficult to realize subsequent functions such as dynamic knowledge fusion, knowledge update and graph query after adding new operation and inspection data without the support of field professionals. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a method and device for constructing a knowledge graph specifically related to electric power operation and maintenance, which solves the problem that it is difficult to ensure the accuracy of knowledge graph construction in the field of electric power operation and maintenance without the support of professional and technical personnel.

[0004] A method for constructing a knowledge graph for electric power operation and inspection provided by an embodiment of the present invention includes: acquiring data information; selecting a data dump from the data information and determining the dump type, and constructing corresponding nodes and newly added nodes according to the dump type; obtaining the relationship between the node and the newly added node based on the node and the newly added node; and constructing a knowledge graph database based on the node, the newly added node, and the relationship between the node and the newly added node.

[0005] In one embodiment, the step of constructing a knowledge graph database based on the nodes, the newly added nodes, and the relationships between the nodes and the newly added nodes includes: checking the standardization of the nodes, and determining whether to discard the nodes, the newly added nodes, and the relationships between the nodes and the newly added nodes based on the standardization of the nodes.

[0006] In one embodiment, the step of obtaining the relationship between the node and the newly added node includes: constructing a work order node, extracting non-work order attribute columns as new nodes, and filling the remaining columns as attributes of the work order node, and obtaining the relationship between the newly added node and the work order node after the row data is read.

[0007] In one embodiment, the step of obtaining the relationship between the node and the newly added node includes: constructing a device node, extracting non-device attribute columns as new nodes, and filling the remaining columns as attributes of the device node, and after the row data is read, the relationship between the newly added node and the device single node.

[0008] In one embodiment, the step of obtaining the relationship between the node and the newly added node includes: constructing a node of a corresponding type, and determining through rules whether the node of the corresponding type is associated with a work order or equipment; if so, obtaining a newly added node based on the node, and then constructing the relationship between the node and the newly added node; if not, discarding the node of the corresponding type.

[0009] In one embodiment, after the step of constructing a knowledge graph database based on the nodes, the newly added nodes, and the relationship between the nodes and the newly added nodes, it also includes: acquiring newly added information data, and adding the newly added data to the knowledge graph database; enabling a stop word list, performing word segmentation and part-of-speech tagging on the operation and inspection task description text, identifying terminology nouns outside the stop word list and adding them to the collection; performing encyclopedia precision search and fuzzy search on entity nouns, crawling the entity nouns and discarding the entity nouns with non-standard descriptions, taking the entity or the crawled entity noun to form a key-value pair and storing it in a first mapping table; extracting the entity introduction keywords to obtain the inverted index of the entity keywords, and storing the inverted index and the entity in a second mapping table; persisting the first mapping table and the second mapping table.

[0010] In one embodiment, the step of adding the newly added information data to the knowledge graph database includes: determining whether the newly added data already exists in the database; if so, updating the existing attribute values ​​of the existing nodes and aligning and filling the new attributes; if not, adding a new node to the knowledge graph database.

[0011] In one embodiment, the step of adding a new node to the knowledge graph database includes: taking the attribute labels of existing work order nodes to construct a set, and taking the attribute values ​​of existing work order nodes to construct a reverse mapping; if the node attribute of the newly added data is in the set, the node attribute of the newly added data and the attribute value of the newly added data are stored in the newly added node; if the node attribute of the newly added data is not in the set, the attribute value of the newly added data is matched with each key in the reverse mapping for similarity, and among the attribute values ​​of the newly added data that exceed the threshold, the attribute name of the attribute value of the newly added data with the highest similarity is selected as the new name of the node attribute of the newly added data to complete the alignment.

[0012] A knowledge graph construction device for electric power operation and inspection, comprising: an initialization unit, used to initialize the knowledge graph database environment and obtain data information; a selection and judgment unit, used to select a data dump and judge the dump type; a construction unit, used to construct corresponding nodes and newly added nodes according to the dump type; based on the nodes and the newly added nodes, obtain the relationship between the nodes and the newly added nodes; and construct a knowledge graph database based on the nodes, the newly added nodes, and the relationship between the nodes and the newly added nodes.

[0013] Optionally, it also includes:

[0014] An acquisition unit is used to acquire new information data and add the new data to the knowledge graph database;

[0015] A set construction unit is used to enable a stop word list, perform word segmentation and part-of-speech tagging on the operation and inspection task description text, identify term nouns outside the stop word list, and group the term nouns outside the stop word list into a set;

[0016] A crawling unit, used for performing encyclopedia precise search and fuzzy search on the entity nouns in the set, crawling the entity nouns and discarding the entity nouns with non-standard descriptions;

[0017] A first mapping table building unit, used to form a key-value pair from an entity and the crawled entity introduction and store it in a first mapping table;

[0018] A second mapping table construction unit extracts the entity introduction keyword to obtain an inverted index of the entity keyword, and stores the inverted index and the entity in a second mapping table;

[0019] A persistence unit is used to persist the first mapping table and the second mapping table.

[0020] The embodiment of the present invention provides a method and device for constructing a knowledge graph for electric power operation and inspection. The method for constructing a knowledge graph for electric power operation and inspection includes initializing a knowledge graph database environment and obtaining data information; selecting a data dump and determining the dump type, and constructing corresponding nodes and newly added nodes according to the dump type; obtaining the relationship between the nodes and the newly added nodes based on the nodes and the newly added nodes; and constructing a knowledge graph database based on the nodes, the newly added nodes, and the relationship between the nodes and the newly added nodes. The present invention aims at the original data automatically generated and manually recorded during the electric power operation and inspection process, obtains the relationship between the nodes and the newly added nodes through the nodes and the newly added nodes, analyzes the connection between data and knowledge, and provides a more reasonable solution for automatically constructing a knowledge graph and knowledge fusion and updating in an unsupervised manner. In this way, graph construction does not need to rely on expert supervision, does not require an industry terminology knowledge base as corpus, and does not need to strictly construct ontological knowledge in a top-down manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 The figure is a flow chart of a method for constructing a knowledge graph for electric power operation and inspection provided by one embodiment of the present invention;

[0022] Figure 2 The figure is a flow chart of a method for constructing a knowledge graph for electric power operation and inspection provided by another embodiment of the present invention;

[0023] Figure 3 The figure is a schematic diagram of the structure of a knowledge graph construction device for electric power operation and inspection provided by an embodiment of the present invention;

[0024] Figure 4 Shown is a structural schematic diagram of a knowledge graph construction device for power operation and inspection provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] The embodiment of the present invention provides a method for constructing a knowledge graph for power operation and inspection, referring to Figure 1 As shown, the method for constructing the knowledge graph of power operation and inspection includes:

[0027] Step 01: Initialize the knowledge graph database environment and obtain data information. Optionally, the knowledge graph database is initialized as a Neo 4j environment. Optionally, the data information can be as shown in Table 1 below.

[0028] Table 1, some data information

[0029]

[0030]

[0031] Step 02: Select a data dump in the data information and determine the dump type. Optionally, the dump type may be a work order or equipment ledger.

[0032] Step 03: Construct corresponding nodes and newly added nodes according to the dump type, and obtain the relationship between the nodes and the newly added nodes based on the nodes and the newly added nodes.

[0033] According to the dump type, corresponding nodes and newly added nodes are constructed, and the step of obtaining the relationship between the nodes and the newly added nodes based on the nodes and the newly added nodes may include: constructing new nodes, extracting non-work order attribute items (such as compiler, power station line, affiliated city, etc.) as new nodes, filling <attribute, attribute value> as node content into the node, and after processing is completed, connecting the task node with other extracted nodes to form an (entity-relationship-entity) structure (such as task-preparer-employee).

[0034] Corresponding nodes and newly added nodes are constructed according to the dump type, and the step of obtaining the relationship between the nodes and the newly added nodes based on the nodes and the newly added nodes may also include: constructing new nodes, extracting non-device items (such as device owners, manufacturers, etc.) as new nodes, filling <attributes, attribute values> as node content into the nodes, and after processing is completed, connecting the task nodes with other extracted nodes to form an (entity-relationship-entity) structure (such as device-manufacturer-manufacturer).

[0035] According to the dump type, the corresponding node and the newly added node are constructed, and the step of obtaining the relationship between the node and the newly added node based on the node and the newly added node may also include: constructing other types of nodes, judging by rules whether the corresponding type of node is associated with a work order or equipment; if so, obtaining a newly added node based on the node, and then constructing the relationship between the node and the newly added node; if not, discarding the corresponding type of node. For example: if it is determined that the modified record type data describes the equipment maintenance information, a node is constructed for the modified record data entry, and this node is connected to the corresponding equipment node. Some data types that are not determined according to the rules will be directly discarded.

[0036] Step 04: Construct a knowledge graph database based on the node, the newly added node, and the relationship between the node and the newly added node. Submit the node, the newly added node, and the relationship between the node and the newly added node to the knowledge graph database, the transaction is submitted, the database connection is closed, and the graph construction process ends.

[0037] In one embodiment of the present invention, in the step of constructing a knowledge graph database based on the node, the newly added node, and the relationship between the node and the newly added node in step 03, the incomplete node produced in step 02 will be checked for standardization, and whether to discard the node, the newly added node, and the relationship between the node and the newly added node will be determined based on the standardization of the node. If there are too many null values ​​for attributes or duplicate entries (duplicate id, duplicate description, etc.) in a node, such nodes and the relationships connected to them will be deleted.

[0038] In one embodiment of the present invention, after the initial graph is constructed, the automated knowledge fusion and update tasks are completed through the following steps for the description text of the inspection task in the work order, referring to Figure 2 As shown:

[0039] Step 21: Obtain new information data and add the new data to the knowledge graph database. If you want to add work order data, determine the work order type and process it separately:

[0040] If the work order information (determination id) already exists, the existing attribute values ​​of the existing nodes are updated and the new attributes are aligned and filled;

[0041] If the work order information does not exist, a new work order node is created, and each attribute and attribute value in the existing work order node in the graph is taken to construct a set (that is, attribute name setP and attribute value setV). The attribute value constructs a map<attribute value, attribute name> as a reverse mapping. If Pi is in the set, Pi and Vi are stored in the newly added node, otherwise Vi is matched with each key in the map for similarity, and a variety of short text similarity matching methods are used for fusion scoring. 0.8 is used as the similarity threshold to add attribute names that exceed the threshold to the priority queue pq, and finally the first element of pq is taken as the final selected attribute alignment name.

[0042] The final generated nodes are stored in the graph database.

[0043] Step 22: Enable the stop word list, perform word segmentation and part-of-speech tagging on the operation and maintenance task description text, identify term nouns outside the stop word list, and group the term nouns outside the stop word list into a set. Start the stop word list (Baidu stop words), perform word segmentation and part-of-speech tagging on the operation and maintenance task description text. Taking the text "Eliminate the defect of [QX20161229012 Caozili 750 switch cabinet 10-5 busbar porcelain column discharge abnormal sound. 2016-12-2810:34:24]" as an example, segment the words and tag all the nouns with part-of-speech, and you can extract the two term nouns of switch cabinet and busbar porcelain column, and then add these two term nouns to the set S. After processing the entire task description text, a set containing all the term nouns can be obtained.

[0044] Step 23: Perform encyclopedia precise search and fuzzy search on the entity nouns in the set, crawl the entity nouns and discard the entity nouns with non-standard descriptions, and store the entity and the crawled entity introduction into a key-value pair in a first mapping table;

[0045] Step 24: extract the keywords that introduce the entity to obtain the inverted index of the entity keywords, and store the inverted index and the entity in a second mapping table.

[0046] For each noun entity e in the set S (taking ADSS as an example):

[0047] Perform precise encyclopedia search and fuzzy search on e, crawl terminology knowledge, eliminate aliases, abbreviations and other non-standard descriptions, and discard entity e if no results are found. Perform precise encyclopedia search and fuzzy search on the term ADSS, crawl out the terminology knowledge entity optical cable behind ADSS, and obtain the entire ADSS alias set (ADSS, optical cable, optical fiber cable, high-voltage transmission line) and the specific introduction of the term entity content. Some entities that cannot obtain knowledge content will be deleted.

[0048] The entity and the crawled entity introduction are formed into a key-value pair <entity, introduction> and stored in the first mapping table. The ADSS and the crawled ADSS introduction are formed into a key-value pair <ADSS, ADSS knowledge introduction> and stored in the first mapping table.

[0049] Use TF-IDF and TextRank to extract introduction keywords, and the top five with the highest similarity are used as entity keywords to make an inverted index <keyword, entity> and stored in the second mapping table; use word segmentation to segment the ADSS introduction text, and then use TF-IDF and TextRank fusion scoring to extract keywords in the ADSS introduction text. Text keywords that exceed the threshold of 0.5 are used as keywords for the introduction text. In this example, the words "optical cable" and "optical fiber" are extracted from the introduction. At this time, these two keywords are used as keywords for the ADSS description to make an inverted index <keyword, ADSS> and stored in the second mapping table.

[0050] Step 25: Persist the first mapping table and the second mapping table. Persist the first mapping table and the second mapping table for use in subsequent functions.

[0051] After the task is completed, the overall structure of the terminology knowledge and the search keywords can be obtained. The newly added knowledge can be integrated and updated in this way. After persisting the backend service, the hot update of the graph knowledge can be realized.

[0052] The present invention targets the original data automatically generated and manually recorded in the process of power operation and inspection, obtains the relationship between nodes and newly added nodes through nodes and newly added nodes, analyzes the connection between data and knowledge, and provides a more reasonable solution for automatically constructing knowledge graphs and knowledge fusion and updating in an unsupervised manner. In this way, graph construction does not need to rely on expert supervision, does not require industry terminology knowledge base as corpus, and does not need to strictly construct ontology knowledge in a top-down manner.

[0053] In one embodiment, a knowledge graph system for power operation and inspection is provided, wherein the knowledge graph system obtains data information by initializing a knowledge graph database environment; selects a data dump and determines the dump type, and constructs corresponding nodes and newly added nodes according to the dump type; obtains the relationship between the node and the newly added node based on the node and the newly added node; and constructs a knowledge graph database based on a construction method of the node, the newly added node, and the relationship between the node and the newly added node.

[0054] The present invention targets the original data automatically generated and manually recorded in the process of power operation and inspection, obtains the relationship between nodes and newly added nodes through nodes and newly added nodes, analyzes the connection between data and knowledge, and provides a more reasonable solution for automatically constructing knowledge graphs and knowledge fusion and updating in an unsupervised manner. In this way, graph construction does not need to rely on expert supervision, does not require industry terminology knowledge base as corpus, and does not need to strictly construct ontology knowledge in a top-down manner.

[0055] An embodiment of the present invention provides a knowledge graph construction device 100 for power operation and inspection, referring to Figure 3As shown, the knowledge graph construction device 100 includes:

[0056] The acquisition unit 101 is used to initialize the knowledge graph database environment and acquire data information.

[0057] The selection and determination unit 102 is used to select a data dump from the data information and determine the dump type.

[0058] The construction unit 103 is used to construct corresponding nodes and newly added nodes according to the dump type; obtain the relationship between the nodes and the newly added nodes based on the nodes and the newly added nodes; and construct a knowledge graph database based on the nodes, the newly added nodes, and the relationship between the nodes and the newly added nodes.

[0059] The initialization unit initializes the knowledge graph database environment and obtains data information; then the selection judgment unit 20 selects the data dump and determines the dump type; the construction unit 30 constructs corresponding nodes and newly added nodes according to the dump type; based on the nodes and the newly added nodes, the relationship between the nodes and the newly added nodes is obtained; based on the nodes, the newly added nodes, and the relationship between the nodes and the newly added nodes, the knowledge graph database is constructed.

[0060] The knowledge graph construction device in the present invention targets the original data automatically generated and manually recorded in the process of power operation and inspection, obtains the relationship between nodes and newly added nodes through nodes and newly added nodes, analyzes the connection between data and knowledge, and provides a more reasonable solution for automatically constructing knowledge graphs and knowledge fusion and updating in an unsupervised manner. In this way, graph construction does not need to rely on expert supervision, does not require industry terminology knowledge base as corpus, and does not need to strictly construct ontology knowledge in a top-down manner.

[0061] An embodiment of the present invention provides a knowledge graph construction device 200 for power operation and inspection. After the initial graph construction is completed, the following units are used to complete the automatic knowledge fusion and update tasks for the operation and inspection task description text in the work order. Figure 4 As shown, it also includes,

[0062] An acquisition unit 201 is used to acquire new information data and add the new data to the knowledge graph database;

[0063] A set construction unit 202 is used to enable a stop word list, perform word segmentation and part-of-speech tagging on the operation and inspection task description text, identify term nouns outside the stop word list, and group the term nouns outside the stop word list into a set;

[0064] A crawling unit 203 is used to perform an encyclopedia precise search and a fuzzy search on the entity nouns in the set, crawl the entity nouns and discard the entity nouns with non-standard descriptions;

[0065] A first mapping table building unit 204, configured to form a key-value pair of an entity and the crawled entity introduction and store it in a first mapping table;

[0066] A second mapping table construction unit 205 extracts the entity introduction keyword to obtain an inverted index of the entity keyword, and stores the inverted index and the entity in a second mapping table;

[0067] The persistence unit 206 is used to persist the first mapping table and the second mapping table.

[0068] This embodiment provides an electronic device, which may include a memory and a processor, wherein a computer program is stored on the memory, and when the computer program is executed by the processor, the knowledge graph construction method for power operation and inspection as described in Embodiment 1 is implemented. It is understood that the electronic device may also include an input / output (I / O) interface and a communication component.

[0069] The processor is used to execute all or part of the steps in the knowledge graph construction method for power operation and inspection in the first embodiment. The memory is used to store various types of data, which may include instructions of any application or method in the electronic device, and data related to the application.

[0070] The processor can be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components, and is used to execute the knowledge graph construction method for power operation and inspection in the above-mentioned embodiment one.

[0071] The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0072] This embodiment also provides a computer-readable storage medium. Each functional unit in each embodiment of the present invention may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. If the function is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium.

[0073] Based on such understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0074] The aforementioned storage media include: flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, server, APP application mall, etc. Various media that can store program check codes, on which a computer program is stored, and when the computer program is executed by a processor, the following method steps can be implemented:

[0075] Step S01: Initialize the knowledge graph database environment and obtain data information.

[0076] Step S02: select a data dump, determine the dump type, and construct corresponding nodes and newly added nodes according to the dump type.

[0077] Step S03: obtaining a relationship between the node and the newly added node based on the node and the newly added node.

[0078] Step S04: Construct a knowledge graph database based on the nodes, the newly added nodes, and the relationships between the nodes and the newly added nodes.

[0079] The specific implementation methods and the effects produced can be referred to the above embodiments, and the present invention will not be described in detail here.

[0080] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0081] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0082] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0083] The block diagrams of devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems may be connected, arranged, or configured in any manner.

[0084] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0085] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0086] In the description of the application, the meaning of "multiple" is at least two, for example, two, three, etc., unless otherwise clearly and specifically limited. In the embodiment of the present application, all directional indications (such as up, down, left, right, front, back, top, bottom ...) are only used to explain the relative position relationship, motion conditions, etc. between the components under a certain specific posture (as shown in the drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their deformations are intended to cover non-exclusive inclusions. For example, the process, method, system, product or equipment comprising a series of steps or units are not limited to the steps or units listed, but optionally also include the steps or units not listed, or optionally also include other steps or units inherent to these processes, methods, products or equipment.

[0087] In addition, the reference to "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0088] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims. The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention. The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0089] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for constructing a knowledge graph for power operation and inspection, characterized in that: include: Get data information; Selecting a data dump from the data information and determining the dump type; Construct corresponding nodes and newly added nodes according to the dump type, and obtain the relationship between the nodes and the newly added nodes based on the nodes and the newly added nodes; Construct a knowledge graph database based on the nodes, the newly added nodes, and the relationships between the nodes and the newly added nodes; The step of obtaining the relationship between the node and the newly added node includes: Build a work order node, extract non-work order attribute columns as new nodes, and fill the remaining columns as attributes of the work order node. After the row data is read, the relationship between the new node and the work order node is obtained; The step of obtaining the relationship between the node and the newly added node includes: Build the device node, extract the non-device attribute columns as the new node, and fill the remaining columns as the attributes of the device node. After the row data is read, the relationship between the new node and the single device node is added; The step of obtaining the relationship between the node and the newly added node includes: Construct a node of the corresponding type, and determine whether the node of the corresponding type is associated with a work order or a device through a rule; if so, obtain a new node based on the node, and then construct a relationship between the node and the new node; if not, discard the node of the corresponding type; The step of constructing a knowledge graph database based on the nodes, the newly added nodes, and the relationships between the nodes and the newly added nodes includes: Checking the data accuracy of the node to determine whether the data accuracy is lower than a preset accuracy; If so, discard the node, the newly added node, and the relationship between the node and the newly added node; After the step of constructing a knowledge graph database based on the nodes, the newly added nodes, and the relationships between the nodes and the newly added nodes, the step further includes: Acquire new information data, and add the new information data to the knowledge graph database; Enable the stop word list, perform word segmentation and part-of-speech tagging on the operation and inspection task description text, identify term nouns outside the stop word list, and group the term nouns outside the stop word list into a set; Performing encyclopedia precise search and fuzzy search on the entity nouns in the set, crawling the entity nouns and discarding the entity nouns with non-standard descriptions; The entity and the crawled entity introduction are formed into a key-value pair and stored in a first mapping table; Extracting the keywords of the entity introduction to obtain the inverted index of the entity keywords, and storing the inverted index and the entity in a second mapping table; The first mapping table and the second mapping table are persisted.

2. The method for constructing a knowledge graph for power operation and inspection according to claim 1, characterized in that: The step of adding the newly added information data to the knowledge graph database includes: Determine whether the newly added information data already exists in the database; If yes, update the existing attribute values ​​of the existing nodes and align and fill the new attributes; If not, a new node is added to the knowledge graph database.

3. The method for constructing a knowledge graph for power operation and inspection according to claim 2, characterized in that: The step of adding a new node to the knowledge graph database includes: Take the attribute labels of existing work order nodes to build a set, and take the attribute values ​​of existing work order nodes to build a reverse mapping; If the node attribute of the newly added information data is in the set, storing the node attribute of the newly added information data and the attribute value of the newly added information data in the newly added node; If the node attribute of the newly added information data is not in the set, the attribute value of the newly added information data is matched with each key in the reverse mapping for similarity, and among the attribute values ​​of the newly added information data that exceed the threshold, the attribute name of the attribute value of the newly added information data with the highest similarity is selected as the new name of the node attribute of the newly added information data to complete the alignment.

4. A knowledge graph construction device for power operation and inspection, characterized in that: include: An acquisition unit, used for acquiring data information; A selection and judgment unit, used for selecting a data dump from the data information and judging a dump type; A construction unit, configured to construct corresponding nodes and newly added nodes according to the dump type; and obtain a relationship between the nodes and the newly added nodes based on the nodes and the newly added nodes; Construct a knowledge graph database based on the nodes, the newly added nodes, and the relationships between the nodes and the newly added nodes; The step of obtaining the relationship between the node and the newly added node includes: Build a work order node, extract non-work order attribute columns as new nodes, and fill the remaining columns as attributes of the work order node. After the row data is read, the relationship between the new node and the work order node is obtained; The step of obtaining the relationship between the node and the newly added node includes: Build the device node, extract the non-device attribute columns as the new node, and fill the remaining columns as the attributes of the device node. After the row data is read, the relationship between the new node and the single device node is added; The step of obtaining the relationship between the node and the newly added node includes: Construct a node of the corresponding type, and determine whether the node of the corresponding type is associated with a work order or a device through a rule; if so, obtain a new node based on the node, and then construct a relationship between the node and the new node; if not, discard the node of the corresponding type; The step of constructing a knowledge graph database based on the nodes, the newly added nodes, and the relationships between the nodes and the newly added nodes includes: Checking the data accuracy of the node to determine whether the data accuracy is lower than a preset accuracy; If so, discard the node, the newly added node, and the relationship between the node and the newly added node; After the step of constructing a knowledge graph database based on the nodes, the newly added nodes, and the relationships between the nodes and the newly added nodes, the step further includes: Acquire new information data, and add the new information data to the knowledge graph database; Enable the stop word list, perform word segmentation and part-of-speech tagging on the operation and inspection task description text, identify term nouns outside the stop word list, and group the term nouns outside the stop word list into a set; Performing encyclopedia precise search and fuzzy search on the entity nouns in the set, crawling the entity nouns and discarding the entity nouns with non-standard descriptions; The entity and the crawled entity introduction are formed into a key-value pair and stored in a first mapping table; Extracting the keywords of the entity introduction to obtain the inverted index of the entity keywords, and storing the inverted index and the entity in a second mapping table; The first mapping table and the second mapping table are persisted.

5. The knowledge graph construction device for electric power operation and inspection according to claim 4 is characterized in that: Also includes: An acquisition unit is used to acquire new information data and add the new information data to the knowledge graph database; A set construction unit is used to enable a stop word list, perform word segmentation and part-of-speech tagging on the operation and inspection task description text, identify term nouns outside the stop word list, and group the term nouns outside the stop word list into a set; A crawling unit, used for performing encyclopedia precise search and fuzzy search on the entity nouns in the set, crawling the entity nouns and discarding the entity nouns with non-standard descriptions; A first mapping table building unit, used to form a key-value pair from an entity and the crawled entity introduction and store it in a first mapping table; A second mapping table construction unit extracts the entity introduction keyword to obtain an inverted index of the entity keyword, and stores the inverted index and the entity in a second mapping table; A persistence unit is used to persist the first mapping table and the second mapping table.

Images