A power distribution network automatic drawing method and device based on a knowledge graph

Abstract

The application discloses a power distribution network automatic drawing method and device based on a knowledge graph, and provides the power distribution network automatic drawing method based on the knowledge graph of the power distribution network, compares equipment data collected from the power distribution network system with entity attribute information in the power distribution network extracted from the knowledge graph, determines the correlation between the equipment data according to entity relationship information in the power distribution network extracted from the knowledge graph, and finally, based on the obtained correlation, visualizes the equipment and the equipment relationship in the power distribution network system in a graphical display mode through a graphical visualization tool, thereby forming the power distribution network diagram corresponding to the power distribution network system, realizing the automatic drawing of the power distribution network diagram, reducing the workload of manual drawing, and improving the drawing efficiency and accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power distribution network automation, and particularly relates to a power distribution network automatic mapping method and device based on a knowledge graph. BACKGROUND

[0002] In the power industry, a power distribution network is a very important infrastructure, which has a complex structure, contains a large number of devices and lines, and has a rapidly changing operating environment, and mapping is a main means for analyzing and optimizing the power distribution network. Traditionally, the mapping method for the power distribution network is manual mapping, but this method requires the mapping personnel to have a deep understanding of the power distribution network structure, and has problems such as low efficiency. SUMMARY

[0003] The present application provides a power distribution network automatic mapping method and device based on a knowledge graph, which is used to solve the technical problems of low efficiency and poor accuracy of the existing power distribution network mapping method.

[0004] To solve the above technical problems, the present application provides a power distribution network automatic mapping method based on a knowledge graph in the first aspect, comprising:

[0005] acquiring a power distribution network knowledge graph;

[0006] extracting entity attribute information and entity relationship information in the power distribution network according to the power distribution network knowledge graph;

[0007] collecting device data of a power distribution network system;

[0008] determining the association relationship between the device data according to the device data, combining the entity relationship information and the entity attribute information, and generating a power distribution network diagram corresponding to the power distribution network system based on the association relationship through a graphical visualization tool.

[0009] Preferably, the device data specifically includes device information and inter-device topology relationship information.

[0010] Preferably, the construction process of the power distribution network knowledge graph specifically includes:

[0011] acquiring a power distribution network data source;

[0012] extracting and classifying entity objects and entity relationships in the power distribution network data source through a preset natural language processing algorithm and a machine learning algorithm according to the power distribution network data source;

[0013] performing visual processing on the extracted entity objects and entity relationships according to an RDF graph framework to form a power distribution network knowledge graph.

[0014] Preferably, determining the correlation between the device data based on the device data, combined with the entity relationship information and entity attribute information, and generating the corresponding distribution network diagram of the distribution network system using a graphical visualization tool based on the correlation specifically includes:

[0015] The topology of the power distribution network system is determined based on the topology relationship information between the devices;

[0016] Based on the equipment information, determine the type of each node in the power distribution network system;

[0017] Based on the preset configuration information of node type and node layout position, the drawing position of each node in the power distribution network system is adjusted;

[0018] Based on the topology, the nodes of the power distribution network system are connected and drawn using a graphical visualization tool to obtain the power distribution network diagram corresponding to the power distribution network system.

[0019] Preferably, after obtaining the distribution network data source, the process further includes:

[0020] The data source of the power distribution network is cleaned and normalized to obtain a preprocessed power distribution network data source.

[0021] Meanwhile, a second aspect of this application provides a knowledge graph-based automatic distribution network mapping device, comprising:

[0022] The knowledge graph acquisition unit is used to acquire the knowledge graph of the power distribution network.

[0023] The graph knowledge extraction unit is used to extract entity attribute information and entity relationship information in the distribution network based on the distribution network knowledge graph.

[0024] Distribution network data acquisition unit, used to collect equipment data of the distribution network system;

[0025] The power distribution network diagram drawing unit is used to determine the correlation between the equipment data based on the equipment data, combined with the entity relationship information and entity attribute information, and generate the power distribution network diagram corresponding to the power distribution network system based on the correlation through a graphical visualization tool.

[0026] Preferably, the device data specifically includes: device information and topological relationship information between devices.

[0027] Preferably, it further includes:

[0028] The power distribution network knowledge graph construction unit is configured to acquire a power distribution network data source, extract and classify entity objects and entity relationships in the power distribution network data source according to a preset natural language processing algorithm and a machine learning algorithm, and perform visual processing on the extracted entity objects and entity relationships according to an RDF graph framework to form a power distribution network knowledge graph.

[0029] Preferably, the power distribution network mapping unit is specifically configured to:

[0030] determine a topology structure of the power distribution network system according to the inter-device topology relationship information;

[0031] determine types of each node of the power distribution network system according to the device information;

[0032] adjust mapping positions of each node of the power distribution network system according to preset configuration information of node types and node layout positions;

[0033] perform connection mapping of each node of the power distribution network system according to the topology structure by using a graph visualization tool to obtain a power distribution network diagram corresponding to the power distribution network system.

[0034] Preferably, the power distribution network mapping unit further comprises:

[0035] a preprocessing unit configured to perform data cleaning processing on the power distribution network data source and normalize the cleaned power distribution network data source to obtain a preprocessed power distribution network data source.

[0036] As can be seen from the above technical solutions, the present application has the following advantages:

[0037] The power distribution network automatic mapping method provided by the present application is based on a knowledge graph of a power distribution network. Entity attribute information in the power distribution network is extracted from the knowledge graph, and the extracted entity attribute information is compared with device data collected from the power distribution network system. Then, according to entity relationship information in the power distribution network extracted from the knowledge graph, an association relationship between the device data is determined. Finally, based on the obtained association relationship, the devices and device relationships in the power distribution network system are visualized by using a graph visualization tool in a graphical display manner, thereby forming a power distribution network diagram corresponding to the power distribution network system. The power distribution network diagram is automatically mapped, the workload of manual mapping is reduced, and the efficiency and accuracy of mapping are improved. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0039] Figure 1 The flowchart of a first embodiment of a power distribution network automatic drawing method based on a knowledge graph provided by the present application.

[0040] Figure 2 The flowchart of a second embodiment of a power distribution network automatic drawing method based on a knowledge graph provided by the present application.

[0041] Figure 3 The structural diagram of an embodiment of a power distribution network automatic drawing device based on a knowledge graph provided by the present application. DETAILED DESCRIPTION

[0042] The embodiments of the present application provide a power distribution network automatic drawing method and device based on a knowledge graph, which are used to solve the technical problems of low efficiency and poor accuracy of the existing power distribution network drawing method.

[0043] In order to make the purposes, characteristics and advantages of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the following described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0044] First, the detailed description of an embodiment of a power distribution network automatic drawing method based on a knowledge graph provided by the present application is as follows:

[0045] Please refer to Figure 1 The power distribution network automatic drawing method based on a knowledge graph provided by the present embodiment comprises:

[0046] Step S1, acquiring a power distribution network knowledge graph.

[0047] Step S2, extracting entity attribute information and entity relationship information in the power distribution network according to the power distribution network knowledge graph.

[0048] It should be noted that the knowledge graph is a form of expressing the relationship between entities and concepts in the form of a graph, which has the advantages of clear semantics, clear structure, strong scalability, etc. In the automatic drawing method of the power distribution network diagram, by constructing the power distribution network knowledge graph, the relationship between each power distribution device can be described more clearly, and the power distribution network diagram can be drawn more accurately.

[0049] Based on the obtained power distribution network knowledge graph, knowledge information is extracted, for example, the nodes in the constructed knowledge graph are classified, and the related attribute information is extracted. For example, in the knowledge graph of the power distribution network diagram, the nodes can be classified into transformer substations, distribution boxes, switches, etc., and then the position, model, voltage, etc. attribute information, i.e. entity attribute information, of them is extracted; the relationship between different nodes is identified and modeled into a directed graph. For example, in the knowledge graph of the power distribution network diagram, there is a "power supply" relationship between the transformer substation and the distribution box, which can be modeled into a directed edge. At the same time, there can be multiple relationships between different nodes, such as "connection", "power supply", "control", etc., which need to be modeled into corresponding directed edges, i.e. entity relationship information.

[0050] Step S3, collecting device data of the power distribution network system.

[0051] More specifically, the device data mentioned in the embodiment specifically includes: device information and inter-device topology relationship information, wherein the device information includes but is not limited to device identification information, voltage level, rated operating parameters, etc.

[0052] Step S4, according to the device data, combining the entity relationship information and the entity attribute information, determining the association relationship between the device data, and generating the corresponding power distribution network diagram of the power distribution network system based on the association relationship through a graphical visualization tool.

[0053] Then, according to the power distribution network system that needs to draw the power distribution network diagram, the device information of the power distribution network system is collected, and then according to the collected information, the entity relationship information and the entity attribute information obtained in the previous steps are combined to determine the node types corresponding to the devices and the association relationship between device data of different types, and a graphical visualization tool is used to generate the corresponding power distribution network diagram of the power distribution network system.

[0054] The above is a detailed description of a basic embodiment of a power distribution network automatic drawing method based on a knowledge graph provided by the present application, and the following is a detailed description of a further embodiment of a power distribution network automatic drawing method based on a knowledge graph provided by the present application based on the previous embodiment.

[0055] Please refer to Figure 2 Further, based on the previous embodiment, before step S1, it can also include:

[0056] Step S01, obtaining a power distribution network data source;

[0057] Step S02, according to the power distribution network data source, extracting and classifying the entity objects and entity relationships in the power distribution network data source through a preset natural language processing algorithm and a machine learning algorithm;

[0058] Step S03, according to the RDF graph framework, visualizing the extracted entity objects and entity relationships to form a power distribution network knowledge graph.

[0059] It should be noted that the steps S01 to 1003 of the embodiment provide a construction process of the power distribution network knowledge graph, which mainly includes the following content details:

[0060] Data source acquisition: obtaining original data from the power distribution network management system, including the topological structure of the power distribution line, the parameters and state information of the electrical equipment, etc.

[0061] Knowledge extraction: extracting entities and relationships related to the power distribution network from various data sources. The data sources can include technical literature of power distribution equipment, equipment list, equipment maintenance record, etc. The extracted entities include power distribution equipment, wires, disconnectors, etc., and the relationships include connection relationship, control relationship, etc.

[0062] Entity recognition and classification: recognizing and classifying the extracted entities and classifying them into specific types. This step needs to use natural language processing technology and machine learning algorithms, such as named entity recognition (NER) algorithm.

[0063] Relationship extraction and classification: identifying and classifying the extracted relationships and classifying them into specific types. This step also needs to use natural language processing technology and machine learning algorithms, such as dependency syntax analysis algorithm, relationship extraction algorithm, etc.

[0064] Knowledge representation: representing the extracted entities and relationships in the form of a graph. This step can use RDF (Resource Description Framework) and other knowledge representation languages to describe the entities and relationships in the knowledge graph.

[0065] In the process of constructing the knowledge graph, multiple links such as entity and relationship extraction, classification and representation need to be performed. Therefore, it is necessary to use natural language processing, machine learning and knowledge representation and other technologies to complete it. At the same time, the construction of the knowledge graph also needs to use professional knowledge and manual annotation and other means to assist. Through the construction of the knowledge graph, each entity and relationship in the power distribution network can be represented in the form of a graph, thereby providing more accurate basic information for the subsequent power distribution network graph automatic drawing method.

[0066] Further, step S01 can further include:

[0067] Step S001, data cleaning processing is performed on the power distribution network data source, and the cleaned power distribution network data source is normalized to obtain a preprocessed power distribution network data source.

[0068] It should be noted that the cleaning and conversion processing of the obtained data includes data deduplication, outlier processing, data format conversion, etc. For example, data mining techniques can be used to detect and process outliers to ensure the reliability and accuracy of the data. Then, the cleaned and converted data is normalized to facilitate subsequent processing and analysis. Normalization can use different methods, such as min-max normalization, Z-score normalization, etc. In this embodiment, the min-max normalization method is used to normalize the data, which maps the data to the interval [0, 1] to facilitate subsequent processing and analysis.

[0069] Further, the step S4 of the previous embodiment can specifically include:

[0070] Step S41, determining the topology structure of the power distribution network system according to the inter-device topology relationship information;

[0071] Step S42, determining the type of each node of the power distribution network system according to the device information;

[0072] Step S43, adjusting the drawing position of each node of the power distribution network system according to the preset node type and node layout position configuration information;

[0073] Step S44, connecting and drawing each node of the power distribution network system according to the topology structure using a graphical visualization tool to obtain a power distribution network diagram corresponding to the power distribution network system.

[0074] It should be noted that in power grid analysis, the topology structure of the power grid is very important, so in the process of automatically drawing the power distribution network diagram, the topology structure of the power grid is first determined, which can be inferred from the data information of the power grid.

[0075] After determining the topology structure of the power grid, the power grid nodes can be divided into different groups. This can better distinguish the different attributes of the nodes, such as substations, loads, power stations, etc.

[0076] When drawing the power grid topology diagram, the position of each node is also very important. Therefore, the implementation mode of the present application needs to determine the position of the node according to the attribute of the node, such as the substation which is generally located at the center position of the power grid, and the load which is located at the edge position.

[0077] After determining the positions of the nodes, the implementation of the present application needs to determine the connections between the nodes to reflect the power grid topology. The connections between the nodes should be determined according to the power grid data information to ensure the correctness and accuracy of the connections.

[0078] After determining the power grid topology, node grouping, node positions, and connections, the power grid topology diagram can be drawn by drawing software. When drawing, in order to improve the aesthetics, readability, and understandability of the graph, the spatial relationship between the nodes needs to be considered, and the positions of the nodes and connections in the graph can be adjusted by an automatic layout algorithm to ensure that the overall layout of the topology diagram is reasonable.

[0079] Overall, the visualization drawing technology in the implementation of the present application is realized on the basis of data preprocessing, knowledge graph construction, and knowledge graph analysis. By drawing a power grid topology diagram with good readability and understandability, the power grid manager can better understand the state and operation of the power grid. This can timely discover problems and make adjustments to ensure the normal operation of the power grid.

[0080] After obtaining the power distribution network diagram, the obtained data is output for users to view and analyze, and the data can also be stored for future use. For data output, the present application adopts an interactive power distribution network diagram drawing tool based on Web technology. The tool can display the processed data in the form of a graph, enabling users to more intuitively understand the structure and characteristics of the power distribution network. In addition, the tool is interactive, and users can zoom in, zoom out, pan, and other operations through the tool to better understand the details of the power distribution network.

[0081] In terms of data storage, the present application adopts a storage method based on a graph database. Specifically, the present application can use a Neo4j graph database to store the processed data in the database. Neo4j is a high-performance, embedded graph database that can very conveniently store and query graph data. Through the database, users can quickly query and analyze each node of the power distribution network to better understand the characteristics and performance of the power distribution network.

[0082] It should be noted that in data storage and output, the present application adopts some efficient algorithms and technologies to improve the efficiency and performance of data processing and application. For example, in the process of drawing the power distribution network diagram, the present application adopts a drawing method based on vector graphics, which can reduce the size of the graphic file while improving the clarity and readability of the graphics. In addition, the present application also utilizes some distributed computing-based technologies to improve the processing speed and concurrency performance of the data. The application of these algorithms and technologies provides strong support and guarantee for the implementation of the present application.

[0083] The above is a detailed description of an embodiment of the power distribution network automatic drawing method based on the knowledge graph provided in the present application. The following is a detailed description of an embodiment of a power distribution network automatic drawing device based on the knowledge graph provided in the present application.

[0084] Please refer to Figure 3 The embodiment provides a power distribution network automatic drawing device based on a knowledge graph, which comprises:

[0085] A knowledge graph acquisition unit M1 is configured to acquire a power distribution network knowledge graph.

[0086] A graph knowledge extraction unit M2 is configured to extract entity attribute information and entity relationship information in the power distribution network according to the power distribution network knowledge graph.

[0087] A power distribution network data acquisition unit M3 is configured to acquire device data of a power distribution network system.

[0088] A power distribution network drawing unit M4 is configured to determine the correlation between device data according to the device data, in combination with the entity relationship information and the entity attribute information, and generate a corresponding power distribution network diagram of the power distribution network system based on the correlation through a graphical visualization tool.

[0089] Further, the device data specifically comprises device information and topology relationship information between devices.

[0090] Further, the device data specifically comprises device information and topology relationship information between devices.

[0091] A power distribution network knowledge graph construction unit M01 is configured to acquire a power distribution network data source, extract and classify entity objects and entity relationships in the power distribution network data source through a preset natural language processing algorithm and a machine learning algorithm, and perform visual processing on the extracted entity objects and entity relationships according to an RDF graph framework to form a power distribution network knowledge graph.

[0092] Further, the power distribution network drawing unit M4 is specifically configured to:

[0093] determine the topology structure of the power distribution network system according to the topology relationship information between devices;

[0094] determine the types of each node of the power distribution network system according to the device information;

[0095] adjust the drawing position of each node of the power distribution network system according to the configuration information of the preset node type and node layout position;

[0096] draw lines for each node of the power distribution network system using a graphical visualization tool according to the topology structure to obtain a corresponding power distribution network diagram of the power distribution network system.

[0097] Further, the device data specifically comprises device information and topology relationship information between devices.

[0098] The preprocessing unit M001 is configured to perform data cleaning on the power distribution network data source, and normalize the cleaned power distribution network data source to obtain a preprocessed power distribution network data source.

[0099] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the terminal, device and unit described above can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0100] In several embodiments provided in the present application, it should be understood that the disclosed terminal, device and method can be implemented by other manners. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0101] The terms "first", "second", "third", "fourth" and the like used in the description of the present application and the above drawings (if any) are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in other than the order shown or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0102] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e. they can be located in one place or distributed on multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiment scheme according to actual needs.

[0103] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0104] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the entire or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0105] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for automatic mapping of distribution networks based on knowledge graphs, characterized in that, include: Obtain the knowledge graph of the power distribution network; Based on the power distribution network knowledge graph, extract entity attribute information and entity relationship information in the power distribution network; Collect equipment data from the power distribution network system, wherein the equipment data specifically includes: equipment information and topological relationship information between equipment; The topology of the power distribution network system is determined based on the topology relationship information between the devices; Based on the equipment information, determine the type of each node in the power distribution network system; Based on the preset configuration information of node type and node layout position, the drawing position of each node in the power distribution network system is adjusted; Based on the topology, the nodes of the power distribution network system are connected and drawn using a graphical visualization tool to obtain the power distribution network diagram corresponding to the power distribution network system.

2. The method for automatic distribution network mapping based on knowledge graphs according to claim 1, characterized in that, The construction process of the distribution network knowledge graph specifically includes: Obtain data source from the power distribution network; Based on the power distribution network data source, the entity objects and entity relationships in the power distribution network data source are extracted and classified using preset natural language processing algorithms and machine learning algorithms; Based on the RDF graph framework, the extracted entity objects and entity relationships are visualized to form a power distribution network knowledge graph.

3. The method for automatic distribution network mapping based on knowledge graphs according to claim 2, characterized in that, After obtaining the distribution network data source, the following is also included: The data source of the power distribution network is cleaned and normalized to obtain a preprocessed power distribution network data source.

4. A knowledge graph-based automatic distribution network mapping device, characterized in that, include: The knowledge graph acquisition unit is used to acquire the knowledge graph of the power distribution network. The graph knowledge extraction unit is used to extract entity attribute information and entity relationship information in the distribution network based on the distribution network knowledge graph. The power distribution network data acquisition unit is used to acquire equipment data of the power distribution network system, wherein the equipment data specifically includes: equipment information and topology relationship information between equipment; The power distribution network diagram drawing unit is used to determine the topology of the power distribution network system based on the topology relationship information between the devices; determine the type of each node in the power distribution network system based on the device information; adjust the drawing position of each node in the power distribution network system according to the preset configuration information of node type and node layout position; and draw the connection between each node in the power distribution network system using a graphical visualization tool based on the topology to obtain the power distribution network diagram corresponding to the power distribution network system.

5. The automatic distribution network mapping device based on knowledge graphs according to claim 4, characterized in that, Also includes: The power distribution network knowledge graph construction unit is used to acquire power distribution network data sources, extract and classify entity objects and entity relationships in the power distribution network data sources through preset natural language processing algorithms and machine learning algorithms, and visualize the extracted entity objects and entity relationships according to the RDF graph framework to form a power distribution network knowledge graph.

6. The automatic distribution network mapping device based on knowledge graphs according to claim 5, characterized in that, Also includes: The preprocessing unit is used to clean the data from the power distribution network data source and normalize the cleaned data source to obtain the preprocessed power distribution network data source.

Images