Electric power operation construction risk point mining method and device based on knowledge graph

Abstract

The invention relates to the technical field of building construction, and discloses a power operation construction risk point mining method and device based on a knowledge graph. Comprising the steps of constructing a power operation construction risk ontology, constructing a power operation construction risk scene knowledge graph, performing information extraction based on the power operation construction risk ontology, matching the extracted information with the knowledge graph, performing construction risk reasoning and early warning and the like. Carding electric power operation risk knowledge, and constructing an electric power operation construction risk ontology. And collecting historical data, determining a typical risk scene, and constructing a power operation typical risk scene knowledge graph based on the power operation risk ontology. And acquiring an electric power work ticket, performing information extraction based on the electric power work construction risk ontology, and matching the extracted information with related entities in the electric power work typical risk scene knowledge graph through semantic similarity. And constructing an inference rule, obtaining a power operation construction scheme risk point according to the typical risk scene knowledge graph in combination with the matching entity, and carrying out early warning pushing.

Description

Technical Field

[0001] The present invention relates to the technical field of building construction, and particularly relates to a method and device for mining risk points of electric power operation construction based on a knowledge graph. Background Technique

[0002] Data mining is a technology for finding rules from a large amount of data by analyzing each data, mainly including three steps: data preparation, rule finding, and rule representation. Data preparation is to select the required data from relevant data sources and integrate it into a data set for data mining; rule finding is to find out the rules contained in the data set by a certain method; rule representation is to represent the found rules in a way that is as understandable to users as possible (such as visualization). A knowledge graph describes concepts, entities, and their relationships in the objective world in a structured form, expresses unstructured information in a form closer to the human cognitive world, and provides an ability to better organize, manage, and understand structured information. Essentially, a knowledge graph is a semantic network. Its nodes represent entities or concepts, and the edges represent various semantic relationships between entities / concepts. As one of the bases for realizing machine cognitive intelligence, the knowledge graph is an important part of artificial intelligence, which helps to realize the automated and intelligent acquisition, mining, and application of knowledge, and has received extensive attention from the industrial and academic circles.

[0003] Currently, there is no solution for mining risk points of electric power operation construction in the fields of data mining and knowledge graphs. To fill this technical gap, the present invention designs a method and device for mining risk points of electric power operation construction based on a knowledge graph. Summary of the Invention

[0004] This part of the summary of the invention is used to briefly introduce the concepts, which will be described in detail in the following detailed implementation part. This part of the summary of the invention is not intended to identify the key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] The present invention proposes a method and device for mining risk points of electric power operation construction based on a knowledge graph to solve one or more of the technical problems mentioned in the above background technical part.

[0006] The present invention provides a method for mining risk points of electric power operation construction based on a knowledge graph, including:

[0007] Construct a risk ontology for electric power operation construction according to the historical electric power operation knowledge base. The risk ontology for electric power operation construction includes multiple constituent elements in the process of electric power operation construction. The multiple constituent elements include construction processes, construction tasks, risk accidents, risk causes, risk control measures, and violation events;

[0008] Construct a knowledge graph of typical risk scenarios for power operation based on the ontology of power operation construction risks;

[0009] Obtain a power operation ticket, and perform information extraction on the power operation ticket based on the ontology of power operation construction risks to obtain entities related to the ontology of power operation construction risks in the power operation ticket and use them as actual extracted entities;

[0010] Match the actual extracted entities with the entities in the knowledge graph of typical risk scenarios for power operation to obtain the entities in the knowledge graph of typical risk scenarios for power operation that match the actual extracted entities and denote them as matching entities;

[0011] Determine the risk points of the power operation construction plan according to the inference rules and the matching entities, and push the risk points of the power operation construction plan.

[0012] Optionally, construct a knowledge graph of typical risk scenarios for power operation based on the ontology of power operation construction risks, including:

[0013] Based on the ontology of power operation construction risks, perform information extraction and processing on the existing typical violation library and specifications of power operation to obtain the extracted information, and the extracted information includes entities, attributes, and relationships between entities;

[0014] Perform standardization processing on the extracted information to obtain the processed extracted information;

[0015] Construct a knowledge graph of typical risk scenarios for power operation based on the processed extracted information.

[0016] Optionally, the knowledge graph of typical risk scenarios for power operation includes a typical violation library sub-graph and a specification sub-graph.

[0017] Optionally, the typical violation library sub-graph includes multiple violation events; the typical violation library sub-graph is constructed through the following steps:

[0018] Extract the violation events during the construction process based on the construction materials, literature records, and construction specifications to form a violation event database;

[0019] Construct the relationships of different violation events, and the relationships include causal relationship, sequential relationship, time relationship, AND relationship, OR relationship;

[0020] Define the interface of the typical violation library sub-graph;

[0021] Construct the typical violation library sub-graph based on the violation event database, the relationships of different violation events, and the interface.

[0022] Optionally, the specification sub-graph is constructed through the following steps:

[0023] Extract information from existing construction specifications and industry specifications using natural language processing technology and deep learning technology to obtain item words.

[0024] Determine the valid information in the construction specifications and industry specifications by reviewing and classifying the item words;

[0025] Optionally, construct an ontology for construction risks in power operations based on the historical knowledge base of power operations, including:

[0026] Extract information from the historical knowledge base of power operations to obtain multiple constituent elements in the construction process of power operations, and each constituent element in the multiple constituent elements is implemented as a class;

[0027] Define multiple relationships between the multiple constituent elements, and the multiple relationships include inclusion relationships, sequential relationships, and participation relationships;

[0028] Generate an ontology for construction risks in power operations based on the classes corresponding to the multiple constituent elements and the multiple relationships between the multiple constituent elements.

[0029] Optionally, match the actually extracted entities with the entities in the knowledge graph of typical risk scenarios in power operations to obtain the entities in the knowledge graph of typical risk scenarios in power operations that match the actually extracted entities and denote them as matching entities, including:

[0030] Use semantic matching technology to determine the entity with the highest matching degree with the actually extracted entity in the knowledge graph of typical risk scenarios in power operations as the matching entity.

[0031] Optionally, determine the risk points of the construction plan for power operations and push the risk points of the construction plan for power operations according to the inference rules and the matching entities, including:

[0032] Determine the risk points of the construction plan for power operations according to the inference rules and the matching entities;

[0033] Perform risk warning operations according to the risk points of the construction plan for power operations.

[0034] Optionally, determine the valid information in the construction specifications and industry specifications by reviewing and classifying the item words, including:

[0035] Use expert experience information to review and classify the item words to determine the valid information in the construction specifications and industry specifications.

[0036] Some embodiments of the present invention propose a device for mining construction risk points in power operations based on a knowledge graph, including:

[0037] A risk ontology construction module, which is used to construct an ontology for power operation construction risks according to the historical power operation knowledge base. The ontology for power operation construction risks includes multiple constituent elements in the process of power operation construction, and the multiple constituent elements include construction processes, construction tasks, risk accidents, risk causes, risk control measures, and violation events;

[0038] A knowledge graph construction module, which is used to construct a knowledge graph of typical risk scenarios for power operations based on the ontology of power operation construction risks;

[0039] An information acquisition module, which is used to acquire power operation tickets and perform information extraction on the power operation tickets based on the ontology of power operation construction risks to obtain entities related to the ontology of power operation construction risks in the power operation tickets and use them as actual extracted entities;

[0040] A semantic similarity matching module, which is used to match the actual extracted entities with the entities in the knowledge graph of typical risk scenarios for power operations to obtain the entities in the knowledge graph of typical risk scenarios for power operations that match the actual extracted entities and denote them as matching entities;

[0041] A risk push module, which is used to determine the risk points of the power operation construction plan according to the inference rules and the matching entities and push the risk points of the power operation construction plan.

[0042] The present invention has the following beneficial effects: 1. The present invention proposes a method and device for mining risk points in power operation construction, which can automatically mine and identify construction risk points from power construction operation tickets, filling the technical gap;

[0043] 2. The present invention combines data mining technology and knowledge graph technology, matches the extracted power operation information with the knowledge graph of typical risk scenarios, and improves the quality and efficiency of mining construction risk points;

[0044] 3. The present invention extracts knowledge from power operation field specifications and typical power operation violation knowledge bases, constructs a unified knowledge ontology model, realizes the matching and alignment of power operation specifications and power operation violations, and then constructs a set of power operation construction risks, saving the mining process.

[0045] 4. The present invention constructs a construction risk inference rule, combines the matching entities to perform risk inference and early warning, and realizes a risk early warning mechanism. Description of the Drawings

[0046] Combined with the drawings and referring to the following specific embodiments, the above and other features, advantages and aspects of the embodiments of the present invention will become more obvious. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the elements and elements are not necessarily drawn to scale.

[0047] Figure 1 is the flowchart of the method for mining risk points in power operation construction based on the knowledge graph of the present invention;

[0048] Figure 2 is the schematic diagram of the device for mining risk points in power operation construction based on the knowledge graph of the present invention. Detailed implementation manners

[0049] The present invention will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not used to limit the protection scope of the present invention.

[0050] In addition, it should be noted that only parts related to the relevant invention are shown in the drawings for the convenience of description. Without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0051] It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or mutual dependence relationship of the functions performed by these devices, modules or units.

[0052] It should be noted that the modifications of "one" and "multiple" mentioned in the present invention are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly specified in the context, it should be understood as "one or more".

[0053] The names of the messages or information exchanged between multiple devices of the present invention are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0054] The present invention will be described in detail below with reference to the drawings and in combination with the embodiments.

[0055] As Figure 1 shown, the flowchart of some embodiments of the method for mining risk points in power operation construction based on the knowledge graph of the present invention is shown, which specifically includes the following steps:

[0056] Step 101, construct a risk ontology for power operation construction according to the historical power operation knowledge base. The risk ontology for power operation construction includes multiple constituent elements in the power operation construction process. The multiple constituent elements include construction processes, construction tasks, risk accidents, risk causes, risk control measures, and violation events.

[0057] In some embodiments, the execution subject of the method for mining risk points in power operation construction based on a knowledge graph according to the present invention can be various electronic devices. On this basis, the execution subject sorts out the historical power operation knowledge base to obtain multiple constituent elements, where the historical power knowledge base includes, but is not limited to, power operation regulations, standards, and manuals issued by the state and the industry, employee manuals within power enterprises, as well as accumulated power operation cases and accident investigation reports over the years. According to the multiple constituent elements, a risk ontology for power operation construction is constructed, where the multiple constituent elements include construction processes, construction tasks, risk accidents, risk causes, risk control measures, and violation events.

[0058] Optionally, constructing a risk ontology for power operation construction according to the historical power operation knowledge base includes the following steps:

[0059] Step 1, extract information from the historical power operation knowledge base to obtain multiple constituent elements in the power operation construction process, and each constituent element in the multiple constituent elements is implemented as a class.

[0060] In some embodiments, the multiple constituent elements include construction processes, construction tasks, risk accidents, risk causes, risk control measures, and violation events. Each constituent element being implemented as a class includes a construction process class, a construction task class, a risk accident class, a risk cause class, a risk control measure class, and a violation event class.

[0061] Step 2, define multiple relationships between the multiple constituent elements, and the multiple relationships include an inclusion relationship, a sequential relationship, and a participation relationship.

[0062] In some embodiments, when defining multiple relationships between the multiple constituent elements, there is an inclusion relationship between the construction task and the construction process. As an example, the construction task of "substation expansion project" includes construction processes such as "electrical equipment installation" and "equipment commissioning". There is a sequential relationship between the risk cause and the risk accident. As an example, the risk cause of "unrepaired exposed wire" precedes the risk accident of "workers contacting the wire and getting electrocuted". There is a participation relationship between the construction personnel and the construction process. As an example, a certain construction worker is responsible for the construction process of "electrical equipment installation".

[0063] Step 3, generate a risk ontology for power operation construction based on the classes corresponding to the multiple constituent elements and the multiple relationships between the multiple constituent elements.

[0064] In some embodiments, according to the classes corresponding to each constituent element and the multiple relationships between the multiple constituent elements, use an ontology building tool to build a risk ontology for power operation construction.

[0065] Step 102, construct a knowledge graph of typical risk scenarios for power operation based on the risk ontology for power operation construction.

[0066] In some embodiments, according to the constructed ontology of power operation construction risks, a knowledge graph of typical risk scenarios for power operations is constructed.

[0067] Optionally, the knowledge graph of typical risk scenarios for power operations includes a sub-graph of a typical violation library and a sub-graph of norms.

[0068] In some embodiments, the knowledge graph of typical risk scenarios for power operations is divided into two parts: a sub-graph of a typical violation library and a sub-graph of norms.

[0069] Optionally, the sub-graph of the typical violation library includes various violation events; the sub-graph of the typical violation library is constructed through the following steps:

[0070] Step 1, extract violation events during the construction process based on construction materials, literature records, and construction specifications to form a violation event database.

[0071] In some embodiments, the construction materials include, but are not limited to, construction drawings, construction logs, accident investigation reports, and violation penalty records, etc. The literature records include, but are not limited to, power operation research reports, papers, and laws and regulations, etc. The violation events include, but are not limited to, violation behaviors, violators, violation times, and violation locations, etc., to form a violation event database.

[0072] Step 2, construct the relationships between different violation events. The relationships include causal relationships, sequential relationships, temporal relationships, AND relationships, and OR relationships.

[0073] In some embodiments, construct the causal relationship between different violation events. As an example, it is statistically found that in power operations, illegal command leads to risky operations by operators. As an example, the illegal command is the first violation event, and the risky operation is the second violation event.

[0074] Construct the sequential relationship between different violation events. As an example, it is statistically found that in power operations, after working without a ticket, the operator lacks a formal work instruction and may then make a mistake in the work scope. Among them, working without a ticket is the first violation event, and the mistake in the work scope is the second violation event. By adding time markers, the sequential relationship between different violation events is shown.

[0075] Construct the temporal relationship between different violation events. As an example, it is statistically found that in power operations, within the same time period, the frequency and duration of working without a ticket and not wearing protective equipment occurring simultaneously are counted. Among them, working without a ticket is the first violation event, and not wearing protective equipment is the second violation event.

[0076] Construct the AND relationship between different violation events. As an example, it is statistically found that in power operations, the situation where illegal operation and illegal command occur simultaneously is recorded. Among them, the illegal operation is the first violation event, and the illegal command is the second violation event.

[0077] Construct the OR relationship of different violation events. As an example, statistically analyze the possible correlations that may exist among personnel who do not perform voltage verification and grounding and those who do not correctly use personal protective equipment during electrical operations. Among them, not performing voltage verification and grounding is the first violation event, and not correctly using personal protective equipment is the second violation event.

[0078] Step three, define the interface of the typical violation library sub-graph.

[0079] In some embodiments, the association between different sub-graphs is realized through the interface.

[0080] Step four, construct the typical violation library sub-graph based on the violation event database, the relationships of different violation events, and the interface.

[0081] In some embodiments, the violation event database, the relationships of different violation events, and the interface are integrated to form the typical violation library sub-graph.

[0082] Optionally, the sub-graph is constructed through the following steps:

[0083] Step one, use natural language processing technology and deep learning technology to extract information from existing construction specifications and industry specifications to obtain item words.

[0084] In some embodiments, use natural language processing technology to parse construction specifications and industry specifications to extract relevant information, and use deep learning technology to perform semantic understanding on construction specifications and industry specifications to obtain item words.

[0085] Step two, determine the valid information in the construction specifications and industry specifications by reviewing and classifying the item words.

[0086] In some embodiments, relevant experts in the field of electrical operations conduct manual reviews on the obtained item words to obtain the required item words. Classify them according to the meaning and application scenarios of the item words. Obtain the valid information in the construction specifications and industry specifications.

[0087] Optionally, determining the valid information in the construction specifications and industry specifications by reviewing and classifying the item words includes:

[0088] Use expert experience information to review and classify the item words to determine the valid information in the construction specifications and industry specifications.

[0089] In some embodiments, relevant experts in electrical operations conduct manual reviews on the extracted item words to confirm accuracy and effectiveness, and eliminate incorrect, lengthy, or irrelevant item words.

[0090] According to the meaning and application scenario of the item words, classify each item word into different categories. This helps with the structured organization and efficient query of the sub-graph of the specification.

[0091] Optionally, based on the ontology of electric power operation construction risks, construct a knowledge graph of typical risk scenarios for electric power operations, including the following steps:

[0092] Step 1: Based on the ontology of electric power operation construction risks, perform information extraction and processing on the existing typical violation database and specifications of electric power operations to obtain the extracted information, which includes entities, attributes, and the relationships between entities.

[0093] In some embodiments, according to the established ontology of electric power operation construction risks, perform information extraction on the existing typical violation database of electric power operations, and extract violation events as entities. Among them, violation events include violation behaviors, violators, violation times, violation locations, etc.

[0094] On this basis, extract relevant attribute information for the entities. Among them, the attribute information includes violation types, violation consequences, violation causes, etc.

[0095] Based on the above violation entities and attributes, analyze the association relationships between entities and between entities and attributes. As an example, there is an execution relationship between the violator and the violation behavior, and a corresponding relationship between the violation behavior and the violation cause.

[0096] According to the established ontology of electric power operation construction risks, perform information extraction and processing on the existing electric power operation specifications, and extract the keys in the specifications as entities. Among them, the keys in the specifications include construction tasks, operation regulations, personnel qualifications, etc.

[0097] On this basis, extract relevant attribute information for the entities. As an example, the attributes of the construction task include objectives, requirements, and steps. The attributes of personnel qualifications include levels, majors, certificates, training records, etc.

[0098] Based on the above specification entities and attributes, analyze the association relationships between entities and between entities and attributes. As an example, there is a corresponding relationship between personnel qualifications and construction tasks, and a constraint relationship between construction tasks and operation regulations.

[0099] Step 2: Perform standardization processing on the extracted information to obtain the processed extracted information.

[0100] In some embodiments, perform standardization processing on the entities, attributes, and the relationships between entities to obtain the processed extracted information.

[0101] Step 103: Obtain the electric power operation ticket, and perform information extraction on the electric power operation ticket based on the ontology of electric power operation construction risks to obtain the entities related to the ontology of electric power operation construction risks in the electric power operation ticket and use them as the actual extracted entities.

[0102] In some embodiments, a power operation ticket is obtained. The content of the power operation ticket includes, but is not limited to, operation information, operation personnel, operation equipment, risk control measures, emergency rescue measures, etc. Using natural language processing technology and deep learning technology, information extraction is performed on the power operation ticket based on multiple constituent elements, and the entities related to the ontology of power operation construction risks in the obtained power operation ticket are used as actual extracted entities.

[0103] Step 104: Match the actual extracted entities with the entities in the knowledge graph of typical power operation risk scenarios to obtain the entities in the knowledge graph of typical power operation risk scenarios that match the actual extracted entities, and denote them as matching entities.

[0104] In some embodiments, the actual extracted entities are matched with the entities in the knowledge graph of typical power operation risk scenarios, and the entities obtained after matching are denoted as matching entities.

[0105] Optionally, matching the actual extracted entities with the entities in the knowledge graph of typical power operation risk scenarios to obtain the entities in the knowledge graph of typical power operation risk scenarios that match the actual extracted entities and denoting them as matching entities includes:

[0106] Using semantic matching technology, determine the entity with the highest matching degree with the actual extracted entities in the knowledge graph of typical power operation risk scenarios as the matching entity.

[0107] In some embodiments, the entities in the knowledge graph of typical power operation risk scenarios and the actual extracted entities are matched through semantic matching technology, the matching results are sorted by matching degree, and the entity with the highest matching degree is extracted as the matching entity.

[0108] Step 105: Determine the risk points of the power operation construction plan based on the inference rules and the matching entities, and push the risk points of the power operation construction plan.

[0109] In some embodiments, based on the inference rules and the matching entities, determine the risk points of the power operation construction plan and push the risk points of the power operation construction plan.

[0110] Optionally, determining the risk points of the power operation construction plan based on the inference rules and the matching entities and pushing the risk points of the power operation construction plan includes:

[0111] Step 1: Determine the risk points of the power operation construction plan based on the inference rules and the matching entities.

[0112] In some embodiments, based on the preset inference rules, combined with the matching entities, conduct logical reasoning analysis, and through the reasoning analysis, identify the risk points of the operation construction plan.

[0113] Step 2, perform risk early warning operations according to the risk points of the electric power operation construction plan.

[0114] In some embodiments, the obtained risk points of the electric power operation construction plan are sent to the relevant persons in charge in a timely manner, such as the project manager, safety management personnel, etc., to complete the push of the risk points of the electric power operation construction plan.

[0115] For further reference Figure 2 , as an implementation of the methods shown in the above figures, the present invention provides some embodiments of a device for mining risk points of electric power operation construction based on a knowledge graph. These device embodiments correspond to Figure 1 the method embodiments shown, and the device can be specifically applied to various electronic devices.

[0116] As Figure 2 shown, some embodiments of the device for mining risk points of electric power operation construction based on a knowledge graph in this embodiment include: a risk ontology construction module 201, a knowledge graph construction module 202, an information acquisition module 203, a semantic similarity matching module 204, and a risk push module 205.

[0117] The risk ontology construction module 201 is used to construct a risk ontology for electric power operation construction according to the historical electric power operation knowledge base. The risk ontology for electric power operation construction includes multiple constituent elements in the process of electric power operation construction. The multiple constituent elements include construction procedures, construction tasks, risk accidents, risk causes, risk control measures, and violation events.

[0118] The knowledge graph construction module 202 is used to construct a knowledge graph of typical risk scenarios for electric power operation based on the risk ontology of electric power operation construction.

[0119] The information acquisition module 203 is used to obtain an electric power operation ticket and perform information extraction on the electric power operation ticket based on the risk ontology of electric power operation construction to obtain entities related to the risk ontology of electric power operation construction in the electric power operation ticket and use them as actual extracted entities.

[0120] The semantic similarity matching module 204 is used to match the actual extracted entities with the entities in the knowledge graph of typical risk scenarios for electric power operation to obtain the entities in the knowledge graph of typical risk scenarios for electric power operation that match the actual extracted entities and record them as matching entities.

[0121] The risk push module 205 is used to determine the risk points of the electric power operation construction plan according to the inference rules and the matching entities and push the risk points of the electric power operation construction plan.

[0122] It can be understood that the various units described in the device for mining risk points of electric power operation construction based on a knowledge graph correspond to the reference Figure 1Correspond to the respective steps in the described method. Thus, the operations, features, and beneficial effects described above for the method also apply to the apparatus and the units contained therein, and will not be elaborated herein.

[0123] The above description is only some preferred embodiments of the present invention and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the present invention is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the technical solutions formed by mutually replacing the above features with the (but not limited to) technical features having similar functions disclosed in the present invention.

Claims

1. A method for mining risk points in power operation construction based on knowledge graph, characterized in that: include: Based on the historical power operation knowledge base, construct the power operation construction risk ontology, which includes multiple components in the power operation construction process, including construction procedures, construction tasks, risk accidents, risk causes, risk control measures, and violations; Based on the power operation construction risk ontology, a knowledge graph of typical risk scenarios of power operations is constructed; Obtaining an electric power operation ticket, and extracting information from the electric power operation ticket based on the electric power operation construction risk ontology, obtaining entities in the electric power operation ticket related to the electric power operation construction risk ontology and using them as actual extracted entities; Matching the actually extracted entity with the entity in the knowledge graph of typical risk scenarios of electric power operations, obtaining the entity in the knowledge graph of typical risk scenarios of electric power operations that matches the actually extracted entity and recording it as a matching entity; According to the inference rules and the matching entities, the risk points of the electric power operation construction plan are determined and the risk points of the electric power operation construction plan are pushed.

2. The method for mining risk points of electric power construction based on knowledge graph according to claim 1 is characterized in that: The construction of a knowledge graph of typical risk scenarios of power operations based on the power operation construction risk ontology includes: Based on the power operation construction risk ontology, information extraction processing is performed on the existing typical violation database and specifications of power operations to obtain extracted information, wherein the extracted information includes entities, attributes and relationships between entities; Performing standardization processing on the extracted information to obtain processed extracted information; Based on the processed and extracted information, a knowledge graph of typical risk scenarios in power operations is constructed.

3. The method for mining risk points of electric power construction based on knowledge graph according to claim 2 is characterized in that: The knowledge graph of typical risk scenarios in power operations includes a typical violation library sub-graph and a specification sub-graph.

4. The method for mining risk points of electric power construction based on knowledge graph according to claim 3 is characterized in that: The typical violation library sub-map includes a variety of violation events; the typical violation library sub-map is constructed by the following steps: Extract violations during the construction process based on construction data, literature records, and construction specifications to form a violation database; Constructing relationships between different violation events, wherein the relationships include causal relationships, sequential relationships, time relationships, and relationships, or relationships; An interface for defining the typical violation library sub-map; Based on the traffic violation event database, the relationship between the different traffic violation events and the interface, the typical traffic violation database sub-graph is constructed.

5. The method for mining risk points of electric power construction based on knowledge graph according to claim 4 is characterized in that: The canonical subgraph is constructed by the following steps: Use natural language processing technology and deep learning technology to extract information from existing construction specifications and industry specifications to obtain entries; By reviewing and classifying the entries, valid information in the construction specifications and industry specifications is determined.

6. The method for mining risk points of electric power construction based on knowledge graph according to claim 1 is characterized in that: The construction of the risk ontology of power operation construction based on the historical power operation knowledge base includes: Extracting information from a historical power operation knowledge base to obtain multiple components in the power operation construction process, wherein each component in the multiple components is implemented as a class; defining a plurality of relationships between the plurality of components, the plurality of relationships comprising relationship, sequence relationship and participation relationship; The power operation construction risk ontology is generated based on the classes corresponding to the multiple components and the multiple relationships between the multiple components.

7. The method for mining risk points of electric power construction based on knowledge graph according to claim 1 is characterized in that: The matching of the actually extracted entity with the entity in the knowledge graph of typical risk scenarios of electric power operations to obtain the entity in the knowledge graph of typical risk scenarios of electric power operations that matches the actually extracted entity and record it as a matching entity includes: By using semantic matching technology, the entity in the knowledge graph of typical risk scenarios of power operations that has the highest matching degree with the actually extracted entity is determined as the matching entity.

8. The method for mining risk points of electric power construction based on knowledge graph according to claim 1 is characterized in that: The step of determining risk points of the electric power operation construction plan according to the inference rule and the matching entity and pushing the risk points of the electric power operation construction plan includes: Determine risk points of the power operation construction plan according to the inference rules and the matching entities; Perform risk warning operations based on the risk points of the power operation construction plan.

9. The method for mining risk points of electric power construction based on knowledge graph according to claim 5 is characterized in that: The valid information in the construction specifications and industry specifications is determined by reviewing and classifying the items, including: Using expert experience information, the entries are reviewed and classified to determine valid information in the construction specifications and industry specifications.

10. A device for mining risk points in power operation construction based on knowledge graph, characterized in that: include: A risk ontology construction module is used to construct a risk ontology of power operation construction based on a historical power operation knowledge base. The risk ontology of power operation construction includes multiple components in the power operation construction process, including construction procedures, construction tasks, risk accidents, risk causes, risk control measures, and violations; A knowledge graph construction module, used to construct a knowledge graph of typical risk scenarios of power operations based on the power operation construction risk ontology; An information acquisition module, used to acquire an electric power operation ticket, and extract information from the electric power operation ticket based on the electric power operation construction risk ontology, and obtain entities in the electric power operation ticket related to the electric power operation construction risk ontology as actual extracted entities; A semantic similarity matching module, used for matching the actually extracted entity with the entity in the knowledge graph of typical risk scenarios of electric power operations, obtaining the entity in the knowledge graph of typical risk scenarios of electric power operations that matches the actually extracted entity and recording it as a matching entity; The risk push module is used to determine the risk points of the power operation construction plan according to the inference rules and the matching entities and push the risk points of the power operation construction plan.

Images