CN113220903A - Power accident visual analysis system and method based on knowledge graph - Google Patents
Power accident visual analysis system and method based on knowledge graph Download PDFInfo
- Publication number
- CN113220903A CN113220903A CN202110546698.7A CN202110546698A CN113220903A CN 113220903 A CN113220903 A CN 113220903A CN 202110546698 A CN202110546698 A CN 202110546698A CN 113220903 A CN113220903 A CN 113220903A
- Authority
- CN
- China
- Prior art keywords
- node
- result
- power accident
- preprocessing
- layer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000000007 visual effect Effects 0.000 title abstract description 10
- 230000003993 interaction Effects 0.000 claims abstract description 37
- 230000008569 process Effects 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 24
- 238000007781 pre-processing Methods 0.000 claims description 80
- 238000012800 visualization Methods 0.000 claims description 32
- 238000012217 deletion Methods 0.000 claims description 7
- 230000037430 deletion Effects 0.000 claims description 7
- 238000011161 development Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 238000013016 damping Methods 0.000 claims description 4
- 238000007794 visualization technique Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 230000001364 causal effect Effects 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000005065 mining Methods 0.000 description 4
- 238000009412 basement excavation Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000002146 bilateral effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012946 outsourcing Methods 0.000 description 2
- 238000001556 precipitation Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application discloses a power accident visual analysis system and method based on a knowledge graph, and the system and method comprises the following steps that firstly, a knowledge graph layer processes text data of a power accident event and constructs a graph database; the interface interaction layer acquires a data request and sends the data request to the data access layer; then, the data access layer processes the graph database according to the request and sends a processing result to the service logic layer, and the service logic layer respectively performs mode switching, node and relation editing and event process analysis according to the request and the processing result to determine a main responsible person and electric power equipment of the event; and finally, the interface interaction layer visually displays the processing result of the business logic layer. The method and the device solve the problem that people are difficult to find out the main responsible person or the main responsible power equipment when the power accident case happens because the condition of the power accident case is recorded in a traditional text mode and is not beneficial to analyzing the case, and make the visual content easier for people to understand.
Description
Technical Field
The application relates to the technical field of electric power, in particular to a power accident visualization analysis system and method based on a knowledge graph.
Background
In order to reduce the loss and reduce the occurrence of the power accident case, detailed analysis and tracing to the power accident case every time are needed, and the source of the accident and the main person responsible for the accident are found out, so that experience training is provided for the subsequent power safety production, the power production safety development is promoted, and meanwhile, the careful operation of power workers can be reminded.
At present, in the field of power technology, the situation of a power accident case is still recorded in a traditional text mode, text data is formed and analyzed, and because the mode is not favorable for analyzing the relevance of the power accident case and mining the causal relationship, people are difficult to help to accurately find out a main responsible person or a main responsible power device in the power accident case.
Therefore, a power accident visualization analysis system and method based on a knowledge graph are provided, which are used for solving the problem that it is difficult to help people to accurately find out a main responsible person or a main responsible power device in a power accident case because the fact that the power accident case is recorded in a traditional text mode is not beneficial to performing relevance analysis and cause-effect relationship mining on the power accident case.
Disclosure of Invention
In order to solve the problem that the situation of the power accident is recorded in a traditional text mode, which is not beneficial to the relevance analysis and the causal relationship mining of the situation, so that people are difficult to find out the main responsible person or the main responsible power equipment of the power accident situation accurately, the invention discloses a power accident visualized analysis system and method based on a knowledge graph through the following embodiments.
The application discloses in a first aspect an electric power accident visual analysis system based on knowledge graph, includes: the system comprises a knowledge map layer, a data access layer, a service logic layer and an interface interaction layer which are sequentially connected with one another;
the knowledge graph layer is used for acquiring text data of a power accident event, performing first preprocessing on the text data, and constructing a graph database according to a result of the first preprocessing, wherein the first preprocessing comprises data acquisition, knowledge extraction and knowledge updating, the graph database comprises a knowledge graph, the knowledge graph comprises nodes and relations, the nodes comprise operating personnel related to the power accident event, events related to the power accident event and power equipment related to the power accident event, and the relations are relations between any one node and other nodes;
the interface interaction layer is used for acquiring a data request of a user and sending the data request to the data access layer through the service logic layer;
the data access layer is used for carrying out second preprocessing on the nodes and the relations in the graph database according to the data request and feeding back the result of the second preprocessing to the service logic layer, wherein the second preprocessing comprises adding, deleting, modifying and inquiring;
the service logic layer comprises:
the mode switching module is used for switching between a responsible person view mode and an electric power equipment view mode according to the data request and the second preprocessing result, the responsible person view mode is used for showing the operation of each operator in the electric power accident event and the relation among the operations, and the electric power equipment view mode is used for showing the problem generated by each electric power equipment in the electric power accident event and the relation between the problem and the electric power accident event;
the node editing module is used for editing the node of the second preprocessing result according to the data request and sending the node editing result to the graph database through the data access layer for storage, wherein the node editing comprises node adding, node deleting and node attribute updating;
the relation editing module is used for carrying out relation editing on the second preprocessing result according to the data request and sending the relation editing result to the graph database through the data access layer for storage, wherein the relation editing comprises relation addition, relation deletion and relation attribute updating;
the auxiliary analysis module is used for analyzing the process of the power accident event according to the data request and the second preprocessing result and acquiring the influence of each node on the power accident event, wherein the node with the largest influence is a main responsible person or a main responsible power device of the power accident event;
the interface interaction layer is further configured to obtain a processing result of the service logic layer, and visually display the processing result according to the data request, where the processing result includes a switching result of the mode switching module, a result of the node editing module, a result of the relationship editing module, or an analysis result of the auxiliary analysis module.
Optionally, the system further comprises a server;
and the server is connected with the data access layer and is used for backing up the result of the second preprocessing to realize data sharing.
Optionally, when the analysis result of the auxiliary analysis module is visually displayed according to the data request, the larger the influence, the larger the visualization radius of the node is.
The second aspect of the present application discloses a power accident visualization analysis method based on a knowledge graph, which is applied to the power accident visualization analysis system based on a knowledge graph of the first aspect of the present application, and includes:
acquiring text data of a power accident event, performing first preprocessing on the text data, and constructing a map database according to a first preprocessing result, wherein the first preprocessing comprises data acquisition, knowledge extraction and knowledge updating, the map database comprises a knowledge map, the knowledge map comprises nodes and relations, the nodes comprise operating personnel related to the power accident event, events related to the power accident event and power equipment related to the power accident event, and the relations are relations between any one node and other nodes;
acquiring a data request of a user, and sending the data request to a data access layer through a service logic layer;
according to the data request, performing second preprocessing on the nodes and the relations in the graph database, and feeding back the result of the second preprocessing to the service logic layer, wherein the second preprocessing comprises adding, deleting, modifying and inquiring;
switching between a responsible person view mode and an electric power equipment view mode according to the data request and the second preprocessing result, and acquiring a switching result, wherein the responsible person view mode is used for showing the operation of each operator in the electric power accident event and the relation among the operations, and the electric power equipment view mode is used for showing the problem generated by each electric power equipment in the electric power accident event and the relation between the problem and the electric power accident event;
node editing is carried out on the result of the second preprocessing according to the data request, and the node editing result is sent to the graph database of the knowledge graph layer through the data access layer to be stored, wherein the node editing comprises node adding, node deleting and node attribute updating;
according to the data request, performing relation editing on the second preprocessing result, and sending the relation editing result to the graph database of the knowledge graph layer through the data access layer for storage, wherein the relation editing comprises relation addition, relation deletion and relation attribute updating;
analyzing the process of the power accident event according to the data request and the second preprocessing result, and acquiring the influence of each node on the power accident event, wherein the node with the largest influence is a main responsible person or a main responsible power device of the power accident event;
and according to the data request, visually displaying the switching result, the node editing result, the relationship editing result or the analysis result of the process of the power accident event through an interface interaction layer.
Optionally, the knowledge graph layer is constructed in a crowdsourcing construction mode of a knowledge platform.
Optionally, after performing second preprocessing on the node and the relationship in the graph database according to the data request and feeding back a result of the second preprocessing to the service logic layer, the method further includes:
and backing up the result of the second preprocessing to realize data sharing.
Optionally, the interface development of the interface interaction layer is implemented by a JavaScript programming language.
Optionally, when the analysis result of the process of the power accident event is visually displayed according to the data request, the larger the influence is, the larger the visualization radius of the node is.
Optionally, the influence of any node on the power accident event is obtained through the following formula:
where x represents any node, pr (x) represents a web page rank value of any node x, pr (x) is larger, the larger the influence of any node x is, β is a damping coefficient between 0 and 1, and represents a random probability from any node x to the next node, Ai (i ═ 1, 2, 3.. multidot.n) represents the ith node pointing to any node x, c (Ai) is the number of nodes pointed outward by node Ai, and e (x) is a decay factor, and represents a certain vector of the corresponding node set.
The application discloses electric power accident visualization analysis system and method based on knowledge graph, including: the system comprises a knowledge map layer, a data access layer, a service logic layer and an interface interaction layer which are sequentially connected with one another; firstly, performing first preprocessing on text data of a power accident event by a knowledge graph layer, and constructing a graph database according to a processing result; the interface interaction layer acquires a data request of a user and sends the data request to the data access layer; then, the data access layer performs second preprocessing on the graph database according to the data request, and feeds back a processing result to the service logic layer, wherein the service logic layer comprises: the system comprises a mode switching module, a node editing module, a relation editing module and an auxiliary analysis module, wherein the mode switching module, the node editing module, the relation editing module and the auxiliary analysis module are respectively used for carrying out mode switching, node and relation editing and event process analysis according to a user request and a second preprocessing result so as to determine a main responsible person or a main responsible power device of the power accident event; and finally, the interface interaction layer visually displays the processing result of the service logic layer according to the user request.
The device for testing the bearing capacity of the medium-voltage block in the photovoltaic power station solves the problem that people are difficult to accurately find out main responsible persons or main responsible power equipment for the occurrence of the electric power accident case due to the fact that the situation of the electric power accident case is recorded in a traditional text mode and is not beneficial to the analysis of the relevance of the case and the excavation of the cause-effect relationship, helps the power grid company to confirm the incident responsibility by helping the power grid company to analyze the original cause of the electric power accident case and the relevance relationship and the influence factors among all entities in the incident, and simultaneously police the service personnel, reduces the occurrence of the electric power production accident, optimizes the traditional visualization technology by introducing the knowledge graph technology, and enables the visualized content to be easier to understand by people.
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a power accident visualization analysis system based on a knowledge graph according to an embodiment of the present application;
fig. 2 is a schematic workflow diagram of a power accident visualization analysis method based on a knowledge graph according to an embodiment of the present application;
fig. 3 is a schematic diagram illustrating a mode switching process of a power accident visualization analysis method based on a knowledge graph according to an embodiment of the present application;
fig. 4 is a schematic node editing flow diagram of a power accident visualization analysis method based on a knowledge graph according to an embodiment of the present application;
fig. 5 is a schematic diagram of a relationship editing process of a power accident visualization analysis method based on a knowledge graph according to an embodiment of the present application.
Detailed Description
In order to solve the problem that the situation of the power accident is recorded in a traditional text mode, which is not beneficial to the relevance analysis and the causal relationship mining of the situation, so that people are difficult to find out the main responsible person or the main responsible power equipment of the power accident situation accurately, the invention discloses a power accident visualized analysis system and method based on a knowledge graph through the following embodiments.
The first embodiment of the present application discloses a power accident visualization analysis system based on a knowledge graph, which refers to a schematic structural diagram shown in fig. 1, and includes: the system comprises a knowledge map layer, a data access layer, a service logic layer and an interface interaction layer which are sequentially connected with one another.
Specifically, the system adopts a four-layer architecture, and the functions of each layer adopt modular interaction, so that the dependence between layers is reduced, the system structure is clear, the expansibility and the independence of the system are stronger, and development and maintenance are facilitated for developers. The four-layer architecture comprises an interface interaction layer, a service logic layer, a data access layer and a knowledge map layer from top to bottom in sequence.
The knowledge graph layer is used for acquiring text data of an electric power accident event, performing first preprocessing on the text data, and constructing a graph database according to a result of the first preprocessing, wherein the first preprocessing comprises data acquisition, knowledge extraction and knowledge updating, the graph database comprises a knowledge graph, the knowledge graph comprises nodes and relations, the nodes comprise operating personnel related to the electric power accident event, events related to the electric power accident event and electric power equipment related to the electric power accident event, and the relations are relations between any one node and other nodes.
Specifically, the knowledge-graph layer provides data storage for the data access layer to match semantic queries, and meanwhile provides knowledge-graph-based reasoning to help clear event contexts. The knowledge graph is constructed in a knowledge platform crowdsourcing construction mode, crowdsourcing is a novel outsourcing model, a group of loose task contracting parties and task completers are connected, a series of operations such as task contracting, matching, completing and paying are achieved, and compared with the traditional outsourcing, crowdsourcing is better in terms of expenditure overhead, time, flexibility and the like. The knowledge graph consists of nodes (entities) and edges (relations), and the constructed knowledge graph is finally stored in a graph database, wherein the graph database adopts a high-performance Neo4j graph database, and the inference based on the knowledge graph helps to clear the context of an event, and can help people to accurately find out a main responsible person or a main responsible power equipment problem of a power accident case so as to perform responsibility pursuit.
And the interface interaction layer is used for acquiring a data request of a user and sending the data request to the data access layer through the service logic layer.
Specifically, the interface interaction layer directly interacts with the user, the main function is to understand the operation of the user, send the received data request to the service logic layer, and feed back the processing result to the interface interaction layer, the interface interaction layer does not involve the operation such as logic judgment, and the main function is realized by accessing the website through the browser. The interface development mainly uses the currently most popular JavaScript programming language, and the JavaScript programming language is used for operating a Document Object Model (DOM) to add interactive functions to a hypertext markup (HTML) webpage. The JavaScript programming language as a lightweight just-in-time compilation type programming language has the characteristics of portability, cross-platform performance and the like, and can run under most browsers. The method comprises the steps of optimizing hypertext markup (HTML) document operation, event processing and animation design by using a very fast quick (JQuery), wherein the very fast quick (JQuery) allows asynchronous JavaScript and XML (AJAX) to load data in the background and display the data on a global Wide Area Network (WAN) or a world wide web (web) page without reloading the whole page, and the use of the very fast quick (JQuery) is beneficial to reducing the code amount for agile development.
The interface interaction layer is rendered in a front-end rendering mode, and user experience is optimized by adopting technologies of selection interaction, filtering interaction and the like and simultaneously using a double-layer canvas. The visual channels used are mainly of shape, colour, orientation, size. There are various colors, in the visual editing page, as an example, red represents unselected nodes, green represents unselected relationships, bright blue represents nodes or relationships are selected, and the shapes are 3 types, namely, straight lines with arrows, and circles. Wherein circles represent nodes, undirected lines represent general relationships, and directed lines represent causal relationships. In the node influence analysis interface, the radius of the node is different from 20px to 60 px. The design of interface interaction layer makes this application when solving technical problem, still takes into account user's use and experiences, and the efficiency of further high solution technical problem.
And the data access layer is used for carrying out second preprocessing on the nodes and the relations in the graph database according to the data request and feeding back the result of the second preprocessing to the service logic layer, wherein the second preprocessing comprises addition, deletion, modification and query.
Further, the system also comprises a server.
And the server is connected with the data access layer and is used for backing up the result of the second preprocessing to realize data sharing.
Specifically, the data access layer is mainly used for connecting the server and the graph database and directly performing operations such as adding, deleting, modifying, inquiring and the like on the graph database. The data access layer directly feeds back the processing result to the service logic layer, and simultaneously stores the calculation result of the service logic layer into the graph database.
The service logic layer comprises:
and the mode switching module is used for switching between a responsible person view mode and an electric power equipment view mode according to the data request and the second preprocessing result, wherein the responsible person view mode is used for showing the operation of each operator in the electric power accident event and the relation among the operations, and the electric power equipment view mode is used for showing the problem generated by each electric power equipment in the electric power accident event and the relation between the problem and the electric power accident event.
Specifically, the four modules of the business logic layer are independent from each other, the responsible person view mode mainly shows the operation of each operator in an event and the connection between the operators in the event, so as to help a power grid company to identify an event responsible person, the power equipment view mode mainly shows the problem generated by each power equipment in the event and the influence on the causal relationship of the event, and the mode is beneficial for the power grid company business personnel to perform subsequent quality evaluation on the power equipment. The design of mode switching enables the view to be clearer, the visual display is easier for workers to understand, and if various relationship hybrid systems are in the same view, the good visual effect is not achieved. Referring to the schematic diagram of the mode switching process shown in fig. 3, clicking a start button, the system starts to load nodes and edges in the graph database of the knowledge graph layer, and determines whether the current type is the power equipment view mode, if the current type is the power equipment view mode, a one-way edge is displayed, if the current type is not the power equipment view mode, it is determined whether switching is desired, if the current type is not the power equipment view mode, switching is directly crossed to whether selection is displayed at the front end, if switching is desired, switching is clicked, all edges are traversed, whether selection is displayed at the front end is selected, if selection is displayed at the front end, front end display is performed and ended, if not, front end hiding is performed and ended.
And the node editing module is used for editing the node of the second preprocessing result according to the data request and sending the node editing result to the graph database through the data access layer for storage, wherein the node editing comprises node adding, node deleting and node attribute updating.
Specifically, the node editing module mainly has three functions, namely, adding a node, deleting a node, updating a node attribute, wherein one node represents one entity (including people, events, equipment and the like) in an event, and since the tracing analysis process of the event is a continuous updating process, the information brought by the started information is not very accurate, the node and the attribute need to be modified.
The functions of adding, deleting and updating nodes can be realized through the operation of a Neo4j graphic database, referring to a schematic flow diagram of a node editing module shown in fig. 4, a start button is clicked, the name of a node is input, whether the node exists is judged, if the node exists, the node is updated or deleted, a delete update operation Cypher statement is generated, corresponding operation is performed in the Neo4j graphic database, if the node does not exist, the node is added, a create operation Cypher statement is generated, corresponding operation is performed in the Neo4j graphic database, the corresponding operation comprises the steps of adding the node, deleting the node and updating the node, and finally, the front end returns an operation result and ends.
And the relation editing module is used for editing the relation of the second preprocessing result according to the data request and sending the relation editing result to the graph database through the data access layer for storage, wherein the relation editing comprises the steps of adding a relation, deleting the relation and updating the relation attribute.
Specifically, the relationship editing module mainly has three functions of adding relationship, deleting relationship and updating relationship attributes, and is mainly used for editing the relationship between nodes, and the relationship between nodes in the graph database of the knowledge graph layer can be directly added, deleted or updated by using the neo4j graph database, so that the correctness and instantaneity of the knowledge graph are maintained. Referring to a flow diagram of a relationship editing module shown in fig. 5, a start button is clicked, a node is selected, node and relationship information thereof are obtained, relationship creation, relationship deletion and relationship updating are performed, the created relationship is judged, if the created relationship is bilateral, two edges are created in a neo4j graph database for the selected node, a neo4j graph database of corresponding operation is generated by Cypher statement operation, if the created relationship is not bilateral, an edge is created in a neo4j graph database for the selected node, and a neo4j graph database of corresponding operation is generated by Cypher statement operation; then, if one edge is displayed, the front end displays the oriented edge and ends, if the edge is measured, the front end displays the undirected edge and ends, the Cypher statement operation neo4j graph database of the deletion or update operation is carried out on the deleted relation and the updated relation, and the front end displays the operation result and ends.
And the auxiliary analysis module is used for analyzing the process of the power accident event according to the data request and the second preprocessing result, and acquiring the influence of each node on the power accident event, wherein the node with the largest influence is the main responsible person or the main responsible power equipment of the power accident event.
Specifically, the auxiliary analysis module mainly helps people to analyze the whole event process of the power accident and discover links (nodes) with large influence, so that the responsible person or equipment manufacturer can be subjected to main responsibility confirmation. And the service personnel select and input the starting node and the terminating node and use the causal relationship of the adjacent nodes as the weight to carry out the shortest path fast search. Meanwhile, business personnel can click corresponding buttons to analyze the influence of the nodes and visually display the influence according to the size of the influence, and the larger the visual radius of the node with large influence is. The module calculates the influence by using an improved PageRank algorithm, but if a certain node only points to the relation and does not point to the relation, the PageRank algorithm is easy to generate precipitation, in order to avoid the precipitation of the PageRank value, a decay factor is added into the original formula for improvement, the following formula is obtained, and the influence of any node on the power accident event is obtained through the following formula:
where x represents any node, pr (x) represents a web page rank value of any node x, pr (x) is larger, the larger the influence of any node x is, β is a damping coefficient between 0 and 1, and represents a random probability from any node x to the next node, Ai (i ═ 1, 2, 3.. multidot.n) represents the ith node pointing to any node x, c (Ai) is the number of nodes pointed outward by node Ai, and e (x) is a decay factor, and represents a certain vector of the corresponding node set.
In order to enable the algorithm to be applied visually, the system of the application calls a Neo4j graphic database PageRank algorithm, returns PR values of different nodes, and performs differentiated presentation at the front end according to the PR values. When a user clicks an influence analysis button, an onPageRankClick event is triggered, a separate window is popped up, a showPageRank function is called at the same time, a Cypher statement runs in a neo4j graph database, then a PageRank algorithm is used for calculation, influence scores of all nodes are returned, the larger the numerical value is, the larger the influence of the node is, the smaller the minimum value and the maximum value of the PR value of the node are selected, and if the two values are equal, the sizes of all the nodes are equal, so that the influence of all the nodes is the same; and if the two values are not equal, the PR value difference is mapped to an interval with the radius of 20px to 60px, the radius of each node is set according to the proportion, and the larger the influence is, the larger the node is.
The key code for calling the PageRank algorithm is as follows:
String query="CALL algo.PageRank.stream(\n"+"\"MATCH(p)RETURN id(p)AS id\",\n"+"\"MATCH(p1)-[r]->(p2)RETURN id(p1)AS source,id(p2)AS target,r.weight as weight\",\n"+"{graph:\"Cypher\",weightProperty:\"weight\"})\n"+"YIELD node id,score\n"+
"RETURN algo.get Node By id(node id)AS node,score\n"+"ORDER BY score DESC\n"+"LIMIT10";
the interface interaction layer is further configured to obtain a processing result of the service logic layer, and visually display the processing result according to the data request, where the processing result includes a switching result of the mode switching module, a result of the node editing module, a result of the relationship editing module, or an analysis result of the auxiliary analysis module.
The application discloses electric power accident visualization analysis system and method based on knowledge graph, including: the system comprises a knowledge map layer, a data access layer, a service logic layer and an interface interaction layer which are sequentially connected with one another. Firstly, the knowledge graph layer carries out first preprocessing on text data of the power accident event, and a graph database is constructed according to a processing result. The interface interaction layer acquires a data request of a user and sends the data request to the data access layer. Then, the data access layer performs second preprocessing on the graph database according to the data request, and feeds back a processing result to the service logic layer, wherein the service logic layer comprises: and the mode switching module, the node editing module, the relationship editing module and the auxiliary analysis module are respectively used for carrying out mode switching, node and relationship editing and event process analysis according to the user request and the second preprocessing result so as to determine a main responsible person or a main responsible power device of the power accident event. And finally, the interface interaction layer visually displays the processing result of the service logic layer according to the user request.
The device for testing the bearing capacity of the medium-voltage block in the photovoltaic power station solves the problem that people are difficult to accurately find out main responsible persons or main responsible power equipment for the occurrence of the electric power accident case due to the fact that the situation of the electric power accident case is recorded in a traditional text mode and is not beneficial to the analysis of the relevance of the case and the excavation of the cause-effect relationship, helps the power grid company to confirm the incident responsibility by helping the power grid company to analyze the original cause of the electric power accident case and the relevance relationship and the influence factors among all entities in the incident, and simultaneously police the service personnel, reduces the occurrence of the electric power production accident, optimizes the traditional visualization technology by introducing the knowledge graph technology, and enables the visualized content to be easier to understand by people.
Further, the interface interaction layer visually displays the analysis result of the auxiliary analysis module according to the data request, and the larger the influence is, the larger the visualization radius of the node is.
The following are embodiments of the method disclosed in the present application, which are used to implement the above-mentioned embodiments of the system, and refer to the embodiments of the system for details not disclosed in the embodiments of the method.
A second embodiment of the present application discloses a power accident visualization analysis method based on a knowledge graph, which is applied to a power accident visualization analysis system based on a knowledge graph disclosed in the first embodiment, referring to a workflow diagram shown in fig. 2, and includes:
step S1, acquiring text data of the power accident event, performing first preprocessing on the text data, and constructing a graph database according to a result of the first preprocessing, wherein the first preprocessing comprises data acquisition, knowledge extraction and knowledge updating, the graph database comprises a knowledge graph, the knowledge graph comprises nodes and relations, the nodes comprise operators related to the power accident event, events related to the power accident event and power equipment related to the power accident event, and the relations are relations between any one node and other nodes.
Furthermore, the knowledge graph layer is constructed in a crowdsourcing construction mode of a knowledge platform.
Specifically, step S1 is implemented in the knowledge-graph layer.
And step S2, acquiring the data request of the user, and sending the data request to the data access layer through the service logic layer.
Step S3, according to the data request, performing a second preprocessing on the nodes and the relationships in the graph database, and feeding back a result of the second preprocessing to the service logic layer, where the second preprocessing includes adding, deleting, modifying, and querying.
Further, after step S3, the method further includes:
and backing up the result of the second preprocessing to realize data sharing.
Specifically, the server backs up the result of the second preprocessing, so as to realize data sharing.
Step S4, according to the data request and the result of the second preprocessing, performing switching between a responsible person view mode and an electrical equipment view mode, and obtaining a switching result, where the responsible person view mode is used to show operations of each operator in the electrical accident event and the relation between the operations, and the electrical equipment view mode is used to show problems generated by each electrical equipment in the electrical accident event and the relation between the problems and the electrical accident event.
And step S5, node editing is carried out on the result of the second preprocessing according to the data request, and the node editing result is sent to the graph database of the knowledge graph layer through the data access layer to be stored, wherein the node editing comprises adding nodes, deleting nodes and updating node attributes.
And step S6, performing relation editing on the second preprocessing result according to the data request, and sending the relation editing result to the map database of the knowledge map layer through the data access layer for storage, wherein the relation editing comprises adding relations, deleting relations and updating relation attributes.
Step S7, analyzing the process of the power accident event according to the data request and the result of the second preprocessing, and obtaining an influence of each node on the power accident event, where the node with the largest influence is a main responsible person or a main responsible power device of the power accident event.
Further, when the analysis result of the process of the power accident event is visually displayed according to the data request, the larger the influence is, the larger the visualization radius of the node is.
Further, the influence of any node on the electric power accident event is obtained through the following formula:
where x represents any node, pr (x) represents a web page rank value of any node x, pr (x) is larger, the larger the influence of any node x is, β is a damping coefficient between 0 and 1, and represents a random probability from any node x to the next node, Ai (i ═ 1, 2, 3.. multidot.n) represents the ith node pointing to any node x, c (Ai) is the number of nodes pointed outward by node Ai, and e (x) is a decay factor, and represents a certain vector of the corresponding node set.
And step S8, visually displaying the switching result, the node editing result, the relationship editing result or the analysis result of the process of the power accident event through an interface interaction layer according to the data request.
Furthermore, the interface development of the interface interaction layer is realized through a JavaScript programming language.
The application discloses electric power accident visualization analysis system and method based on knowledge graph, including: the system comprises a knowledge map layer, a data access layer, a service logic layer and an interface interaction layer which are sequentially connected with one another. Firstly, the knowledge graph layer carries out first preprocessing on text data of the power accident event, and a graph database is constructed according to a processing result. The interface interaction layer acquires a data request of a user and sends the data request to the data access layer. Then, the data access layer performs second preprocessing on the graph database according to the data request, and feeds back a processing result to the service logic layer, wherein the service logic layer comprises: and the mode switching module, the node editing module, the relationship editing module and the auxiliary analysis module are respectively used for carrying out mode switching, node and relationship editing and event process analysis according to the user request and the second preprocessing result so as to determine a main responsible person or a main responsible power device of the power accident event. And finally, the interface interaction layer visually displays the processing result of the service logic layer according to the user request.
The device for testing the bearing capacity of the medium-voltage block in the photovoltaic power station solves the problem that people are difficult to accurately find out main responsible persons or main responsible power equipment for the occurrence of the electric power accident case due to the fact that the situation of the electric power accident case is recorded in a traditional text mode and is not beneficial to the analysis of the relevance of the case and the excavation of the cause-effect relationship, helps the power grid company to confirm the incident responsibility by helping the power grid company to analyze the original cause of the electric power accident case and the relevance relationship and the influence factors among all entities in the incident, and simultaneously police the service personnel, reduces the occurrence of the electric power production accident, optimizes the traditional visualization technology by introducing the knowledge graph technology, and enables the visualized content to be easier to understand by people.
The present application has been described in detail with reference to specific embodiments and illustrative examples, but the description is not intended to limit the application. Those skilled in the art will appreciate that various equivalent substitutions, modifications or improvements may be made to the presently disclosed embodiments and implementations thereof without departing from the spirit and scope of the present disclosure, and these fall within the scope of the present disclosure. The protection scope of this application is subject to the appended claims.
Claims (9)
1. A power accident visualization analysis system based on knowledge graph, comprising: the system comprises a knowledge map layer, a data access layer, a service logic layer and an interface interaction layer which are sequentially connected with one another;
the knowledge graph layer is used for acquiring text data of a power accident event, performing first preprocessing on the text data, and constructing a graph database according to a result of the first preprocessing, wherein the first preprocessing comprises data acquisition, knowledge extraction and knowledge updating, the graph database comprises a knowledge graph, the knowledge graph comprises nodes and relations, the nodes comprise operating personnel related to the power accident event, events related to the power accident event and power equipment related to the power accident event, and the relations are relations between any one node and other nodes;
the interface interaction layer is used for acquiring a data request of a user and sending the data request to the data access layer through the service logic layer;
the data access layer is used for carrying out second preprocessing on the nodes and the relations in the graph database according to the data request and feeding back the result of the second preprocessing to the service logic layer, wherein the second preprocessing comprises adding, deleting, modifying and inquiring;
the service logic layer comprises:
the mode switching module is used for switching between a responsible person view mode and an electric power equipment view mode according to the data request and the second preprocessing result, the responsible person view mode is used for showing the operation of each operator in the electric power accident event and the relation among the operations, and the electric power equipment view mode is used for showing the problem generated by each electric power equipment in the electric power accident event and the relation between the problem and the electric power accident event;
the node editing module is used for editing the node of the second preprocessing result according to the data request and sending the node editing result to the graph database through the data access layer for storage, wherein the node editing comprises node adding, node deleting and node attribute updating;
the relation editing module is used for carrying out relation editing on the second preprocessing result according to the data request and sending the relation editing result to the graph database through the data access layer for storage, wherein the relation editing comprises relation addition, relation deletion and relation attribute updating;
the auxiliary analysis module is used for analyzing the process of the power accident event according to the data request and the second preprocessing result and acquiring the influence of each node on the power accident event, wherein the node with the largest influence is a main responsible person or a main responsible power device of the power accident event;
the interface interaction layer is further configured to obtain a processing result of the service logic layer, and visually display the processing result according to the data request, where the processing result includes a switching result of the mode switching module, a result of the node editing module, a result of the relationship editing module, or an analysis result of the auxiliary analysis module.
2. The system according to claim 1, further comprising a server;
and the server is connected with the data access layer and is used for backing up the result of the second preprocessing to realize data sharing.
3. The power accident visualization analysis system based on a knowledge graph as claimed in claim 2, wherein the interface interaction layer is configured to visually display the analysis result of the auxiliary analysis module according to the data request, and the visualization radius of the node with larger influence is larger.
4. A power accident visualization analysis method based on a knowledge graph, which is applied to a power accident visualization analysis system based on a knowledge graph according to any one of claims 1 to 3, and comprises:
acquiring text data of a power accident event, performing first preprocessing on the text data, and constructing a map database according to a first preprocessing result, wherein the first preprocessing comprises data acquisition, knowledge extraction and knowledge updating, the map database comprises a knowledge map, the knowledge map comprises nodes and relations, the nodes comprise operating personnel related to the power accident event, events related to the power accident event and power equipment related to the power accident event, and the relations are relations between any one node and other nodes;
acquiring a data request of a user, and sending the data request to a data access layer through a service logic layer;
according to the data request, performing second preprocessing on the nodes and the relations in the graph database, and feeding back the result of the second preprocessing to the service logic layer, wherein the second preprocessing comprises adding, deleting, modifying and inquiring;
switching between a responsible person view mode and an electric power equipment view mode according to the data request and the second preprocessing result, and acquiring a switching result, wherein the responsible person view mode is used for showing the operation of each operator in the electric power accident event and the relation among the operations, and the electric power equipment view mode is used for showing the problem generated by each electric power equipment in the electric power accident event and the relation between the problem and the electric power accident event;
node editing is carried out on the result of the second preprocessing according to the data request, and the node editing result is sent to the graph database of the knowledge graph layer through the data access layer to be stored, wherein the node editing comprises node adding, node deleting and node attribute updating;
according to the data request, performing relation editing on the second preprocessing result, and sending the relation editing result to the graph database of the knowledge graph layer through the data access layer for storage, wherein the relation editing comprises relation addition, relation deletion and relation attribute updating;
analyzing the process of the power accident event according to the data request and the second preprocessing result, and acquiring the influence of each node on the power accident event, wherein the node with the largest influence is a main responsible person or a main responsible power device of the power accident event;
and according to the data request, visually displaying the switching result, the node editing result, the relationship editing result or the analysis result of the process of the power accident event through an interface interaction layer.
5. The power accident visualization analysis method based on the knowledge-graph as claimed in claim 4, wherein the knowledge-graph layer is constructed by adopting a crowd-sourced construction mode of a knowledge platform.
6. The method for power accident visualization analysis based on knowledge-graph according to claim 4, wherein after the second preprocessing of the nodes and the relationships in the graph database according to the data request and the feedback of the result of the second preprocessing to the business logic layer, the method further comprises:
and backing up the result of the second preprocessing to realize data sharing.
7. The power accident visualization analysis method based on knowledge graph as claimed in claim 4, wherein the interface development of the interface interaction layer is implemented by JavaScript programming language.
8. The power accident visualization analysis method based on the knowledge graph as claimed in claim 4, wherein, when the analysis result of the process of the power accident event is visually displayed according to the data request, the visualization radius of the node with larger influence is larger.
9. The power accident visualization and analysis method based on knowledge-graph according to claim 4, characterized in that,
obtaining the influence of any node on the electric power accident event through the following formula:
where x represents any node, pr (x) represents a web page rank value of any node x, pr (x) is larger, the larger the influence of any node x is, β is a damping coefficient between 0 and 1, and represents a random probability from any node x to the next node, Ai (i ═ 1, 2, 3.. multidot.n) represents the ith node pointing to any node x, c (Ai) is the number of nodes pointed outward by node Ai, and e (x) is a decay factor, and represents a certain vector of the corresponding node set.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110546698.7A CN113220903B (en) | 2021-05-19 | 2021-05-19 | Power accident visual analysis system and method based on knowledge graph |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110546698.7A CN113220903B (en) | 2021-05-19 | 2021-05-19 | Power accident visual analysis system and method based on knowledge graph |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113220903A true CN113220903A (en) | 2021-08-06 |
CN113220903B CN113220903B (en) | 2023-01-20 |
Family
ID=77093131
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110546698.7A Active CN113220903B (en) | 2021-05-19 | 2021-05-19 | Power accident visual analysis system and method based on knowledge graph |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113220903B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114328977A (en) * | 2022-03-09 | 2022-04-12 | 北京有生博大软件股份有限公司 | Personnel migration map spectrum construction method based on map database |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180367549A1 (en) * | 2017-06-14 | 2018-12-20 | International Business Machines Corporation | Feedback-based prioritized cognitive analysis |
CN110955782A (en) * | 2019-11-15 | 2020-04-03 | 国网甘肃省电力公司 | Scheduling control knowledge representation method based on knowledge graph |
CN111339316A (en) * | 2020-02-27 | 2020-06-26 | 河海大学 | Method and system architecture for realizing visual editing and persistence of knowledge graph |
CN111898040A (en) * | 2020-07-20 | 2020-11-06 | 电子科技大学 | Circle layer user influence evaluation method combined with social network |
CN111930784A (en) * | 2020-07-23 | 2020-11-13 | 南京南瑞信息通信科技有限公司 | Power grid knowledge graph construction method and system |
CN112182242A (en) * | 2020-09-27 | 2021-01-05 | 武汉大学 | Safety control knowledge graph construction method for whole process of electric power operation |
CN112597105A (en) * | 2020-12-26 | 2021-04-02 | 中国农业银行股份有限公司 | Processing method of file associated object, server side equipment and storage medium |
CN112632288A (en) * | 2020-12-15 | 2021-04-09 | 深圳供电局有限公司 | Power dispatching system and method based on knowledge graph |
-
2021
- 2021-05-19 CN CN202110546698.7A patent/CN113220903B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180367549A1 (en) * | 2017-06-14 | 2018-12-20 | International Business Machines Corporation | Feedback-based prioritized cognitive analysis |
CN110955782A (en) * | 2019-11-15 | 2020-04-03 | 国网甘肃省电力公司 | Scheduling control knowledge representation method based on knowledge graph |
CN111339316A (en) * | 2020-02-27 | 2020-06-26 | 河海大学 | Method and system architecture for realizing visual editing and persistence of knowledge graph |
CN111898040A (en) * | 2020-07-20 | 2020-11-06 | 电子科技大学 | Circle layer user influence evaluation method combined with social network |
CN111930784A (en) * | 2020-07-23 | 2020-11-13 | 南京南瑞信息通信科技有限公司 | Power grid knowledge graph construction method and system |
CN112182242A (en) * | 2020-09-27 | 2021-01-05 | 武汉大学 | Safety control knowledge graph construction method for whole process of electric power operation |
CN112632288A (en) * | 2020-12-15 | 2021-04-09 | 深圳供电局有限公司 | Power dispatching system and method based on knowledge graph |
CN112597105A (en) * | 2020-12-26 | 2021-04-02 | 中国农业银行股份有限公司 | Processing method of file associated object, server side equipment and storage medium |
Non-Patent Citations (2)
Title |
---|
刘鑫: "面向故障分析的知识图谱构建技术研究", 《中国优秀硕士学位论文全文数据库(信息科技辑)》 * |
王杰 等: "航空安全事件知识图谱构建", 《中国科技信息》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114328977A (en) * | 2022-03-09 | 2022-04-12 | 北京有生博大软件股份有限公司 | Personnel migration map spectrum construction method based on map database |
Also Published As
Publication number | Publication date |
---|---|
CN113220903B (en) | 2023-01-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8006187B1 (en) | Checkpoint sequence fallout metrics management during path analysis | |
US8793266B2 (en) | Graphical user interface for a search query | |
US11194456B1 (en) | Webpage testing tool | |
US10354002B2 (en) | Interaction relationship building and explorer for dashboard | |
CN106599039B (en) | Statistical representation method supporting free combination nesting of relational database data | |
US20090216808A1 (en) | Data exploration system | |
ZA200608228B (en) | Product selection expert system | |
CN112612908A (en) | Natural resource knowledge graph construction method and device, server and readable memory | |
CN109976735A (en) | One kind being based on the visual knowledge mapping algorithm application platform of web | |
CN105045583B (en) | A kind of IETM failure classes data module composition apparatus and its creative method based on visible process | |
CN112765159A (en) | Report generation method, system, computer equipment and storage medium | |
US20230169116A1 (en) | Ontology-based time series visualization and analysis | |
CN110222251A (en) | A kind of Service encapsulating method based on Web-page segmentation and searching algorithm | |
CN113220903B (en) | Power accident visual analysis system and method based on knowledge graph | |
CN109032937B (en) | Data selection method and system based on webpage | |
CN114647735A (en) | Relation graph display method, medium and display device | |
CN110309239B (en) | Visual map editing method and device | |
US9483852B2 (en) | Method for displaying and manipulating genealogical data using a full family graph | |
CN117010198A (en) | Multi-user multi-view model modeling interaction method based on SysML | |
CN116610558A (en) | Code detection method, device, electronic equipment and computer readable storage medium | |
CN110941749A (en) | Visualization method for government affair big data full life cycle governance | |
JP2012194876A (en) | Module analysis system, module analysis method, and module analysis program | |
CN113407678B (en) | Knowledge graph construction method, device and equipment | |
CN114596070A (en) | Product optimization design platform construction method based on knowledge graph | |
CN111782823A (en) | Application of knowledge graph in analysis of violation big data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |