Equipment familial defect analysis method based on graph database, knowledge graph and equipment full life cycle

Abstract

The invention relates to an equipment familial defect analysis method based on a graph database, a knowledge graph and an equipment full life cycle. The method comprises the following steps: constructing a power equipment quality tracing model; the power equipment quality tracing model is configured with a power equipment knowledge graph and a power equipment graph database; determining a current power equipment quality event by adopting a community discovery algorithm matched with the power equipment knowledge graph; reasoning root information causing the occurrence of the current power equipment quality event in the power equipment knowledge base to obtain a power equipment quality event traceability result; according to the current power equipment quality event and the power equipment quality event traceability result, performing high-frequency sub-graph mining on the power equipment knowledge graph, and determining a defect analysis result; and according to a defect analysis result, screening out a station distribution condition of the power equipment associated with the suspected familial defect of the equipment. By adopting the method, the familial defect analysis effect of the power equipment can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to a method, apparatus, computer equipment, computer-readable storage medium and computer program product for analyzing family defects of equipment based on a graph database, a knowledge graph and the entire life cycle of the equipment. Background Art

[0002] The quality of equipment in the power grid directly affects the operating efficiency, safety and reliability of the power grid.

[0003] When quality problems occur in power equipment, it is often necessary to conduct a family defect analysis of the power equipment that has the quality problems. However, in the process of conducting family defect analysis of equipment, traditional technology is often determined based on the analyst's experience and subjective judgment, which makes the results of the family defect analysis of equipment easily affected by the analyst's experience and subjective judgment and has deviations, affecting the effect of the family defect analysis of equipment.

[0004] Therefore, there is a problem in that traditional technologies are not effective in analyzing family defects in power equipment. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for analyzing family defects of power equipment based on a graph database, knowledge graph and the entire life cycle of the equipment, which can improve the effect of family defect analysis of power equipment in response to the above-mentioned technical problems.

[0006] In a first aspect, the present application provides a method for analyzing family defects of equipment based on a graph database, a knowledge graph, and the entire life cycle of the equipment, the method comprising:

[0007] Constructing a power equipment quality tracing model; the power equipment quality tracing model is configured with a power equipment knowledge graph and a power equipment graph database;

[0008] Using a community discovery algorithm that matches the power equipment knowledge graph, the power equipment quality traceability model is used to identify quality problems and determine current power equipment quality events;

[0009] Taking the current power equipment quality event as the reasoning starting point and the preset reasoning end target as the reasoning guide, reasoning the root information that caused the current power equipment quality event to occur in the power equipment knowledge base, and obtaining the power equipment quality event tracing result;

[0010] According to the current power equipment quality event and the power equipment quality event tracing result, high-frequency subgraph mining is performed on the power equipment knowledge graph to determine the defect analysis result; the defect analysis result is used to characterize the suspected family defects of the current equipment;

[0011] According to the defect analysis results, the distribution of sites where power equipment associated with the suspected family defect of the equipment is located is screened out in relative geographic coordinates.

[0012] In one of the embodiments, the high-frequency subgraph mining is performed on the power equipment knowledge graph according to the current power equipment quality event and the power equipment quality event tracing result to determine the defect analysis result, including:

[0013] According to the current power equipment quality event and the power equipment quality event tracing result, a subgraph associated with the current power equipment quality event is determined from the power equipment knowledge graph; the subgraph records the relationship between the device node, the quality event node, and the tracing cause node associated with the current power equipment quality event;

[0014] According to the subgraph associated with the current power equipment quality event, high-frequency subgraph mining is performed on the power equipment knowledge graph to obtain a high-frequency subgraph; wherein the structure of the high-frequency subgraph matches the structure of the subgraph associated with the current power equipment quality event, and the number of the high-frequency subgraphs is greater than a preset number;

[0015] According to the subgraph pattern and subgraph relationship of the high-frequency subgraph, a comparison is made with known family defects of the equipment to determine whether the current power equipment quality event is a suspected family defect of the equipment.

[0016] In one of the embodiments, the high-frequency subgraph mining is performed on the power equipment knowledge graph according to the subgraph associated with the current power equipment quality event to obtain the high-frequency subgraph, including:

[0017] Perform feature extraction on the subgraph associated with the current power equipment quality event to obtain subgraph features of the current power equipment quality event; the subgraph features include at least one of the number of nodes, the number of edges, and the type of nodes of the subgraph associated with the current power equipment quality event;

[0018] According to the subgraph feature of the current power equipment quality event, searching the power equipment knowledge graph for a target subgraph whose structure matches the subgraph associated with the current power equipment quality event;

[0019] When the number of the target sub-graphs is greater than a preset number, the target sub-graphs are determined as the high-frequency sub-graphs.

[0020] In one embodiment, the reasoning of the root information that causes the current power equipment quality event to occur in the power equipment knowledge base to obtain the power equipment quality event tracing result includes:

[0021] Obtain a pre-built reasoning model; the reasoning model is built based on a quality event reasoning knowledge base; the quality event reasoning knowledge base uses a graph structure to represent a plurality of preset candidate power equipment quality events, cause reasoning rules of the candidate power equipment quality events, and rule priorities of the cause reasoning rules;

[0022] Acquire the initial facts of the current power equipment quality event, input the initial facts of the current power equipment quality event into the pre-built reasoning model, and obtain the power equipment quality event tracing result.

[0023] In one embodiment, inputting the initial facts of the current power equipment quality event into the pre-built reasoning model to obtain the power equipment quality event tracing result includes:

[0024] Acquire the initial fact of the current power equipment quality event as the current fact;

[0025] Inputting the current fact into the pre-built reasoning model, and outputting the fact of the previous step in response to the current fact through the pre-built reasoning model;

[0026] Acquire the fact of the previous step as the current fact, return to the step of inputting the current fact into the pre-built reasoning model, until the pre-built reasoning model cannot deduce new facts, and obtain a fact reasoning path;

[0027] According to the factual reasoning path, the tracing result of the power equipment quality event is determined.

[0028] In one embodiment, the community discovery algorithm matching the power equipment knowledge graph is used to identify quality problems of the power equipment quality traceability model and determine power equipment quality events, including:

[0029] Using a community discovery algorithm that matches the electric power equipment knowledge graph, community discovery is performed on the electric power equipment knowledge graph to obtain a plurality of electric power entity communities; each of the electric power entity communities includes at least two connected electric power entities;

[0030] The target power entity is identified by using the community characteristics of each power entity in the power entity community, and the current power equipment quality event is obtained; the difference between the community characteristics of the target power entity and the community characteristics of each power entity in the power entity community is greater than a preset difference.

[0031] In the second aspect, the present application also provides a power equipment quality tracing device based on a graph database, a knowledge graph and the entire life cycle of the equipment, the device comprising:

[0032] A construction module is used to construct a power equipment quality tracing model; the power equipment quality tracing model is configured with a power equipment knowledge graph and a power equipment graph database;

[0033] An identification module, configured to use a community discovery algorithm that matches the power equipment knowledge graph to identify quality problems in the power equipment quality traceability model and determine current power equipment quality events;

[0034] A tracing module is used to use the current power equipment quality event as the reasoning starting point and a preset reasoning end target as the reasoning guide to infer the root information that causes the current power equipment quality event in the power equipment knowledge base, and obtain the power equipment quality event tracing result;

[0035] An analysis module, used to mine high-frequency subgraphs of the power equipment knowledge graph according to the current power equipment quality event and the power equipment quality event tracing result, and determine a defect analysis result; the defect analysis result is used to characterize the suspected family defects of the currently existing equipment;

[0036] A screening module is used to screen out the distribution of sites where power equipment associated with the suspected family defect of the equipment is located in relative geographic coordinates according to the defect analysis results.

[0037] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0039] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0040] The above-mentioned equipment family defect analysis method, device, computer device, computer-readable storage medium and computer program product based on graph database, knowledge graph and equipment life cycle, constructs a power equipment quality tracing model, which is configured with a power equipment knowledge graph and a power equipment graph database; adopts a community discovery algorithm that matches the power equipment knowledge graph to identify quality problems in the power equipment quality tracing model and determine the current power equipment quality event; takes the current power equipment quality event as the reasoning starting point and the preset reasoning end goal as the reasoning guide, infers the root information that causes the current power equipment quality event in the power equipment knowledge base, and obtains the power equipment quality event tracing result; according to the current power equipment quality event and the power equipment quality event tracing result, the power equipment quality event is traced back to the power equipment quality traceability model. The power equipment knowledge graph is used to mine high-frequency subgraphs to determine the defect analysis results; the defect analysis results are used to characterize the suspected family defects of the equipment that currently exist; according to the defect analysis results, the distribution of sites where power equipment associated with the suspected family defects of the equipment are located is screened out in relative geographic coordinates; in this way, the power equipment knowledge graph and power equipment graph database configured based on the power equipment quality traceability model can be effectively used to quickly mine power equipment quality events and provide reasonable and accurate quality assessments; and the data features of power equipment quality events in the power equipment knowledge graph are used to quickly and intelligently perform equipment family defect analysis, so as to avoid as much as possible the deviation of the results of equipment family defect analysis due to the influence of analyst experience and subjective judgment, and effectively improve the efficiency and reliability of equipment family defect analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 An application environment diagram of a device family defect analysis method in an embodiment;

[0043] Figure 2 A schematic diagram of a process of analyzing a device family defect in an embodiment;

[0044] Figure 3 A schematic diagram of a process flow of a device family defect analysis method in another embodiment;

[0045] Figure 4 It is a structural block diagram of a device family defect analysis device in one embodiment;

[0046] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0048] The device family defect analysis method based on the graph database, knowledge graph and device life cycle provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The terminal 102 obtains the power equipment knowledge graph and the power equipment graph database from the server 104, and constructs a power equipment quality traceability model based on the power equipment knowledge graph and the power equipment graph database, so that the power equipment quality traceability model is configured with the power equipment knowledge graph and the power equipment graph database; the terminal 102 adopts a community discovery algorithm that matches the power equipment knowledge graph to identify quality problems in the power equipment quality traceability model and determine the current power equipment quality event; the terminal 102 uses the current power equipment quality event as the reasoning starting point and the preset reasoning end target as the reasoning guide to infer the root information that causes the current power equipment quality event in the power equipment knowledge base, and obtains the power equipment quality event tracing result; the terminal 102 mines high-frequency subgraphs on the power equipment knowledge graph based on the current power equipment quality event and the power equipment quality event tracing result to determine the defect analysis result; the defect analysis result is used to characterize the suspected family defects of the currently existing equipment; the terminal 102 screens out the distribution of sites where power equipment associated with the suspected family defects of the equipment is located in the relative geographic coordinates based on the defect analysis result. The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc. The server 104 may be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0049] In an exemplary embodiment, Figure 2As shown in the figure, a device family defect analysis method based on graph database, knowledge graph and the whole life cycle of the device is provided. Figure 1 The terminal in is taken as an example to illustrate, including the following steps S202 to S210. Among them:

[0050] Step S202, constructing a power equipment quality traceability model; the power equipment quality traceability model is configured with a power equipment knowledge graph and a power equipment graph database.

[0051] Among them, the basic constituent elements of the power equipment knowledge graph include concept dimension, attribute dimension and relationship dimension; among them, the concept dimension includes at least one of the main equipment entity, component entity, technical specification entity and source information entity associated with the power equipment; the attribute dimension includes at least one of the electrical parameter attribute, technical characteristic attribute, location information attribute and time information attribute; the relationship dimension includes at least one of the physical connection relationship, dependency relationship, influence relationship and compliance relationship.

[0052] In a specific implementation, the terminal can obtain the power equipment knowledge graph and the power equipment graph database from the server or local storage, and build a power equipment quality traceability model based on the power equipment knowledge graph and the power equipment graph database.

[0053] Step S204: Use a community discovery algorithm that matches the power equipment knowledge graph to identify quality problems in the power equipment quality traceability model and determine the current power equipment quality event.

[0054] The current power equipment quality event may refer to a power equipment quality event currently occurring in the power system.

[0055] In the specific implementation, the terminal can use a community discovery algorithm that matches the power equipment knowledge graph to identify quality problems in the power equipment quality traceability model and determine the current power equipment quality events.

[0056] Optionally, a community discovery algorithm that matches the power equipment knowledge graph is used to identify quality problems in the power equipment quality traceability model and determine power equipment quality events, including: using a community discovery algorithm that matches the power equipment knowledge graph to perform community discovery on the power equipment knowledge graph to obtain multiple power entity communities; using the community characteristics of each power entity in the power entity community to identify the target power entity and obtain the current power equipment quality event.

[0057] The difference between the community characteristics of the target power entity and the community characteristics of each power entity in the power entity community is greater than a preset difference.

[0058] Each power entity community includes at least two connected power entities.

[0059] In a specific implementation, when the terminal uses a community discovery algorithm that matches the knowledge graph of electric power equipment to identify quality problems in the quality traceability model of electric power equipment and determine the quality events of electric power equipment, the terminal can use a community discovery algorithm that matches the knowledge graph of electric power equipment, such as a community discovery algorithm based on graph partitioning, to perform community discovery on the knowledge graph of electric power equipment and obtain multiple electric power entity communities. Specifically, the terminal can use the Laplace matrix of the graph to perform feature decomposition and clustering on the electric power entity nodes in the knowledge graph of electric power equipment to obtain multiple electric power entity communities; each electric power entity community can include at least two connected electric power entity nodes.

[0060] Then, the terminal can extract the community characteristics of each power entity in the power entity community, and identify the target power entity in the power entity community whose community characteristics differ greatly from the community characteristics of each power entity in the power entity community by comparing the similarities and differences of the community characteristics of each power entity in the power entity community, and output the current power equipment quality event based on the characteristics or status of the target power entity.

[0061] Optionally, before the step of identifying the target power entity by utilizing the community characteristics of each power entity in the power entity community, the method includes: determining, for a current power entity in any power entity community, connectivity information of the current power entity in the power entity community; and determining, based on the connectivity information of each current power entity in the power entity community, community characteristics of each power entity in the power entity community.

[0062] The current power entity is any power entity in the power entity community.

[0063] The connectivity information includes the number of connections between the current power entity and other power entities, and the number of connections between the current power entity outside the power entity community.

[0064] Among them, other power entities are power entities in the power entity community except the current power entity.

[0065] In a specific implementation, before the terminal uses the community characteristics of each power entity in the power entity community to identify the target power entity, the terminal can extract the community characteristics of each power entity in the power entity community; specifically, for the current power entity in any power entity community, the terminal can use the number of connections between the current power entity and other power entities, and the number of connections of the current power entity outside the power entity community; then, the terminal can determine the number of connections between the current power entity and other power entities, and the number of connections of the current power entity outside the power entity community as the community characteristics of the current power entity.

[0066] Step S206, taking the current power equipment quality event as the reasoning starting point and the preset reasoning end target as the reasoning guide, inferring the root information that caused the current power equipment quality event in the power equipment knowledge base, and obtaining the power equipment quality event tracing result.

[0067] Among them, the power equipment quality event tracing result can refer to the cause of the current power equipment quality event.

[0068] In the specific implementation, after the terminal identifies the current power equipment quality event, the terminal can use the current power equipment quality event as the reasoning starting point and the preset reasoning end target as the reasoning guide to infer the root cause information in the power equipment knowledge base that caused the current power equipment quality event to occur, and obtain the power equipment quality event tracing result.

[0069] Optionally, the root cause information that caused the current power equipment quality event to occur is inferred in the power equipment knowledge base to obtain the power equipment quality event tracing result, including: obtaining a pre-built reasoning model; the reasoning model is built based on the quality event reasoning knowledge base; obtaining the initial facts of the current power equipment quality event, inputting the initial facts of the current power equipment quality event into the pre-built reasoning model, and obtaining the power equipment quality event tracing result.

[0070] Among them, the initial facts of the current power equipment quality event are input into the pre-built reasoning model to obtain the power equipment quality event tracing results, including: obtaining the initial facts of the current power equipment quality event as the current facts; inputting the current facts into the pre-built reasoning model, responding to the current facts through the pre-built reasoning model, and outputting the facts of the previous step; obtaining the facts of the previous step as the current facts, returning to the step of inputting the current facts into the pre-built reasoning model, until the pre-built reasoning model cannot derive new facts, and obtaining the fact reasoning path; according to the fact reasoning path, determining the power equipment quality event tracing results.

[0071] Among them, the quality event reasoning knowledge base uses a graph structure to represent multiple preset candidate power equipment quality events, cause reasoning rules for candidate power equipment quality events, and rule priorities of cause reasoning rules.

[0072] In a specific implementation, when the terminal is inferring the root cause information that caused the current power equipment quality event in the power equipment knowledge base and obtaining the power equipment quality event tracing results, the terminal can obtain a pre-built reasoning model; wherein, the reasoning model is constructed based on the quality event reasoning knowledge base.

[0073] Specifically, the terminal can obtain the initial fact of the current power equipment quality event, and use the initial fact of the current power equipment quality event as the current fact; input the current fact into the pre-built reasoning model; after the pre-built reasoning model obtains the current fact, the pre-built reasoning model can respond to the current fact and determine the cause reasoning rule with the highest rule priority among multiple cause reasoning rules associated with the current power equipment quality event; then, the cause reasoning rule with the highest rule priority is used to map the current fact to the fact of the previous step;

[0074] The pre-built reasoning model can then take the facts of the previous step as the current facts, and return to the step of inputting the current facts into the pre-built reasoning model until the pre-built reasoning model cannot deduce new facts, thereby obtaining the fact reasoning path; the terminal can determine the tracing results of the power equipment quality event based on the fact reasoning path.

[0075] Step S208: Based on the current power equipment quality events and the power equipment quality event tracing results, high-frequency sub-graph mining is performed on the power equipment knowledge graph to determine the defect analysis results.

[0076] Among them, the defect analysis results are used to characterize the suspected family defects of the current equipment.

[0077] In the specific implementation, the terminal can perform high-frequency sub-graph mining on the power equipment knowledge graph based on the current power equipment quality events and the power equipment quality event tracing results, and determine the defect analysis results, that is, the suspected family defects of the current equipment.

[0078] Optionally, based on the current power equipment quality event and the power equipment quality event tracing results, high-frequency sub-graph mining is performed on the power equipment knowledge graph to determine the defect analysis results, including: based on the current power equipment quality event and the power equipment quality event tracing results, determining the sub-graph associated with the current power equipment quality event from the power equipment knowledge graph; based on the sub-graph associated with the current power equipment quality event, performing high-frequency sub-graph mining on the power equipment knowledge graph to obtain a high-frequency sub-graph; based on the sub-graph pattern and sub-graph relationship of the high-frequency sub-graph, comparing with the known familial defects of the equipment to determine whether the current power equipment quality event is a suspected familial defect of the equipment.

[0079] Among them, the subgraph records the relationship between the equipment node, quality event node, and traceability cause node associated with the current power equipment quality event.

[0080] The structure of the high-frequency subgraph matches the structure of the subgraph associated with the current power equipment quality event, and the number of the high-frequency subgraphs is greater than a preset number.

[0081] In the specific implementation, the terminal mines high-frequency subgraphs of the power equipment knowledge graph according to the current power equipment quality event and the power equipment quality event tracing results to determine the defect analysis results. The terminal can determine the subgraph associated with the current power equipment quality event from the power equipment knowledge graph according to the current power equipment quality event and the power equipment quality event tracing results.

[0082] Then, the terminal can mine high-frequency subgraphs of the power equipment knowledge graph based on the subgraphs associated with the current power equipment quality events to obtain high-frequency subgraphs;

[0083] Optionally, when the terminal mines high-frequency subgraphs on the power equipment knowledge graph based on the subgraph associated with the current power equipment quality event to obtain the high-frequency subgraphs: the terminal can perform feature extraction on the subgraph associated with the current power equipment quality event to obtain the subgraph features of the current power equipment quality event; wherein the subgraph features include at least one of the number of nodes, the number of edges, and the node type of the subgraph associated with the current power equipment quality event.

[0084] The terminal can search for a target subgraph whose structure matches the subgraph associated with the current power equipment quality event in the power equipment knowledge graph based on the subgraph features of the current power equipment quality event; when the number of target subgraphs is greater than a preset number, the terminal determines the target subgraph as a high-frequency subgraph.

[0085] Finally, the terminal can compare the subgraph patterns and subgraph relationships of the high-frequency subgraphs with the known family defects of the equipment to determine whether the current power equipment quality event is a suspected family defect of the equipment.

[0086] Specifically, the terminal can obtain high-frequency subgraphs of known familial defects of multiple devices, and then compare the high-frequency subgraphs of known familial defects of multiple devices with the high-frequency subgraphs associated with the current power equipment quality event, and analyze the subgraph patterns and subgraph relationships between the two; when the high-frequency subgraph associated with the current power equipment quality event is similar or consistent with the high-frequency subgraph of the known familial defects of any device, the terminal determines that the current equipment is suspected to have a familial defect and obtains the above-mentioned defect analysis result.

[0087] Step S210, based on the defect analysis result, the distribution of sites where power equipment associated with suspected family defects of the equipment is located is screened out in relative geographic coordinates.

[0088] In a specific implementation, after obtaining the defect analysis results, the terminal can filter out the distribution of sites where power equipment associated with suspected familial defects of the equipment is located in relative geographic coordinates based on the defect analysis results.

[0089] Specifically, the distribution of sites where power equipment associated with suspected familial defects of the equipment is located is screened out in the relative geographic coordinates, and then the terminal can display the distribution of sites where power equipment associated with suspected familial defects of the equipment is located in the power system map corresponding to the power system, so that users can intuitively view the location of the power equipment associated with the suspected familial defects of the equipment.

[0090] In the above-mentioned equipment family defect analysis method based on graph database, knowledge graph and equipment life cycle, a power equipment quality tracing model is constructed, and the power equipment quality tracing model is configured with a power equipment knowledge graph and a power equipment graph database; a community discovery algorithm matching the power equipment knowledge graph is used to identify quality problems in the power equipment quality tracing model and determine the current power equipment quality event; the current power equipment quality event is used as the reasoning starting point, and the preset reasoning end target is used as the reasoning guide to infer the root cause information that caused the current power equipment quality event in the power equipment knowledge base, and obtain the power equipment quality event tracing result; according to the current power equipment quality event and the power equipment quality event tracing result, the power equipment knowledge graph is subjected to high-frequency sub-graph tracing. Mining is performed to determine the defect analysis results; the defect analysis results are used to characterize the suspected family defects of the equipment that currently exist; according to the defect analysis results, the distribution of sites where power equipment associated with the suspected family defects of the equipment is located is screened out in relative geographic coordinates; in this way, the power equipment knowledge graph and power equipment graph database configured based on the power equipment quality traceability model can be effectively used to quickly mine power equipment quality events and provide reasonable and accurate quality assessments; and the data features of power equipment quality events in the power equipment knowledge graph are used to quickly and intelligently perform equipment family defect analysis, so as to avoid as much as possible the deviation of the results of the equipment family defect analysis due to the influence of the analyst's experience and subjective judgment, and effectively improve the efficiency and reliability of the equipment family defect analysis.

[0091] In another embodiment, Figure 3 As shown in the figure, a device family defect analysis method based on graph database, knowledge graph and the whole life cycle of the device is provided. Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0092] Step S302, constructing a power equipment quality traceability model; the power equipment quality traceability model is configured with a power equipment knowledge graph and a power equipment graph database.

[0093] Step S304: Use a community discovery algorithm that matches the power equipment knowledge graph to identify quality problems in the power equipment quality traceability model and determine the current power equipment quality events.

[0094] Step S306, taking the current power equipment quality event as the reasoning starting point and the preset reasoning end target as the reasoning guide, a pre-built reasoning model is obtained.

[0095] Step S308, obtaining the initial facts of the current power equipment quality event, inputting the initial facts of the current power equipment quality event into the pre-built reasoning model, and obtaining the power equipment quality event tracing result.

[0096] Step S310, based on the current power equipment quality event and the power equipment quality event tracing result, determine the subgraph associated with the current power equipment quality event from the power equipment knowledge graph.

[0097] Step S312: extract features of the subgraph associated with the current power equipment quality event to obtain subgraph features of the current power equipment quality event.

[0098] Step S314: Based on the subgraph features of the current power equipment quality event, a target subgraph whose structure matches the subgraph associated with the current power equipment quality event is searched in the power equipment knowledge graph.

[0099] Step S316, when the number of target subgraphs is greater than a preset number, the target subgraph is determined as a high-frequency subgraph; wherein the structure of the high-frequency subgraph matches the structure of the subgraph associated with the current power equipment quality event, and the number of high-frequency subgraphs is greater than a preset number.

[0100] Step S318, comparing the subgraph pattern and subgraph relationship of the high-frequency subgraph with the known family defects of the equipment, determining whether the current power equipment quality event is a suspected family defect of the equipment, and obtaining a defect analysis result.

[0101] Step S320, based on the defect analysis result, the distribution of sites where power equipment associated with suspected family defects of the equipment is located is screened out in relative geographic coordinates.

[0102] It should be noted that the specific limitations of the above steps can be found in the above-mentioned specific limitations of a method for analyzing equipment family defects based on a graph database, a knowledge graph and the entire life cycle of the equipment, which will not be repeated here.

[0103] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0104] Based on the same inventive concept, the embodiment of the present application also provides a device for analyzing device family defects based on a graph database, knowledge graph and the entire life cycle of the equipment, which is used to implement the device family defect analysis method based on a graph database, knowledge graph and the entire life cycle of the equipment involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the device family defect analysis device based on a graph database, knowledge graph and the entire life cycle of the equipment provided below can be found in the above limitations on the device family defect analysis method based on a graph database, knowledge graph and the entire life cycle of the equipment, and will not be repeated here.

[0105] In an exemplary embodiment, Figure 4 As shown, a device family defect analysis device based on a graph database, a knowledge graph and the entire life cycle of the device is provided, including:

[0106] A construction module 410 is used to construct a power equipment quality tracing model; the power equipment quality tracing model is configured with a power equipment knowledge graph and a power equipment graph database;

[0107] An identification module 420 is used to identify quality problems of the power equipment quality traceability model by using a community discovery algorithm that matches the power equipment knowledge graph, and determine the current power equipment quality event;

[0108] The tracing module 430 is used to use the current power equipment quality event as the reasoning starting point and the preset reasoning end target as the reasoning guide to infer the root information that causes the current power equipment quality event in the power equipment knowledge base, and obtain the power equipment quality event tracing result;

[0109] The analysis module 440 is used to perform high-frequency sub-graph mining on the power equipment knowledge graph according to the current power equipment quality event and the power equipment quality event tracing result to determine the defect analysis result; the defect analysis result is used to characterize the suspected family defects of the current equipment;

[0110] The screening module 450 is used to screen out the distribution of sites where the power equipment associated with the suspected family defect of the equipment is located in the relative geographic coordinates according to the defect analysis result.

[0111] In one of the embodiments, the analysis module 440 is specifically used to determine a subgraph associated with the current power equipment quality event from the power equipment knowledge graph based on the current power equipment quality event and the tracing result of the power equipment quality event; the subgraph records the relationship between the device nodes, quality event nodes, and tracing cause nodes associated with the current power equipment quality event; based on the subgraph associated with the current power equipment quality event, high-frequency subgraph mining is performed on the power equipment knowledge graph to obtain a high-frequency subgraph; wherein the structure of the high-frequency subgraph matches the structure of the subgraph associated with the current power equipment quality event, and the number of the high-frequency subgraphs is greater than a preset number; based on the subgraph pattern and subgraph relationship of the high-frequency subgraph, a comparison is performed with the known familial defects of the equipment to determine whether the current power equipment quality event is a suspected familial defect of the equipment.

[0112] In one of the embodiments, the analysis module 440 is specifically used to extract features from the subgraph associated with the current power equipment quality event to obtain the subgraph features of the current power equipment quality event; the subgraph features include at least one of the number of nodes, the number of edges, and the type of nodes in the subgraph associated with the current power equipment quality event; based on the subgraph features of the current power equipment quality event, a target subgraph whose structure matches the subgraph associated with the current power equipment quality event is searched in the power equipment knowledge graph; when the number of target subgraphs is greater than a preset number, the target subgraph is determined as the high-frequency subgraph.

[0113] In one of the embodiments, the tracing module 430 is specifically used to obtain a pre-constructed reasoning model; the reasoning model is constructed based on a quality event reasoning knowledge base; the quality event reasoning knowledge base uses a graph structure to represent multiple preset candidate power equipment quality events, the cause reasoning rules of the candidate power equipment quality events, and the rule priority of the cause reasoning rules; obtain the initial facts of the current power equipment quality event, input the initial facts of the current power equipment quality event into the pre-constructed reasoning model, and obtain the tracing results of the power equipment quality event.

[0114] In one embodiment, the tracing module 430 is specifically used to obtain the initial fact of the current power equipment quality event as the current fact; input the current fact into the pre-built reasoning model, respond to the current fact through the pre-built reasoning model, and output the fact of the previous step; obtain the fact of the previous step as the current fact, return to the step of inputting the current fact into the pre-built reasoning model until the pre-built reasoning model cannot derive new facts, and obtain the fact reasoning path; determine the tracing result of the power equipment quality event according to the fact reasoning path.

[0115] In one of the embodiments, the identification module 420 is specifically used to adopt a community discovery algorithm that matches the power equipment knowledge graph to perform community discovery on the power equipment knowledge graph to obtain multiple power entity communities; each of the power entity communities includes at least two connected power entities; the community characteristics of each power entity in the power entity community are used to identify the target power entity and obtain the current power equipment quality event; the difference between the community characteristics of the target power entity and the community characteristics of each power entity in the power entity community is greater than a preset difference.

[0116] Each module in the above-mentioned device family defect analysis device based on graph database, knowledge graph and device life cycle can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0117] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (Near Field Communication, NFC) or other technologies. When the computer program is executed by the processor, a method for analyzing family defects of equipment based on a graph database, a knowledge graph and the entire life cycle of the equipment is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0118] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0119] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above-mentioned method for analyzing device family defects based on a graph database, a knowledge graph, and the entire life cycle of the device. Here, the steps of the method for analyzing device family defects based on a graph database, a knowledge graph, and the entire life cycle of the device can be the steps of the method for analyzing device family defects based on a graph database, a knowledge graph, and the entire life cycle of the device in each of the above-mentioned embodiments.

[0120] In one embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the processor executes the steps of the above-mentioned method for analyzing device family defects based on a graph database, a knowledge graph, and the entire life cycle of the device. Here, the steps of the method for analyzing device family defects based on a graph database, a knowledge graph, and the entire life cycle of the device can be the steps of the method for analyzing device family defects based on a graph database, a knowledge graph, and the entire life cycle of the device in each of the above-mentioned embodiments.

[0121] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the processor executes the steps of the above-mentioned method for analyzing device family defects based on a graph database, a knowledge graph, and the entire life cycle of the device. Here, the steps of the method for analyzing device family defects based on a graph database, a knowledge graph, and the entire life cycle of the device can be the steps of the method for analyzing device family defects based on a graph database, a knowledge graph, and the entire life cycle of the device in each of the above-mentioned embodiments.

[0122] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0123] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magneto resistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0124] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0125] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for analyzing equipment family defects based on graph database, knowledge graph and equipment life cycle, characterized in that: The method comprises: Constructing a power equipment quality tracing model; the power equipment quality tracing model is configured with a power equipment knowledge graph and a power equipment graph database; Using a community discovery algorithm that matches the power equipment knowledge graph, the power equipment quality traceability model is used to identify quality problems and determine current power equipment quality events; Taking the current power equipment quality event as the reasoning starting point and the preset reasoning end target as the reasoning guide, reasoning the root information that caused the current power equipment quality event to occur in the power equipment knowledge base, and obtaining the power equipment quality event tracing result; According to the current power equipment quality event and the power equipment quality event tracing result, high-frequency subgraph mining is performed on the power equipment knowledge graph to determine the defect analysis result; the defect analysis result is used to characterize the suspected family defects of the current equipment; According to the defect analysis results, the distribution of sites where power equipment associated with the suspected family defect of the equipment is located is screened out in relative geographic coordinates.

2. The method according to claim 1, characterized in that According to the current power equipment quality event and the power equipment quality event tracing result, high-frequency subgraph mining is performed on the power equipment knowledge graph to determine the defect analysis result, including: According to the current power equipment quality event and the power equipment quality event tracing result, a subgraph associated with the current power equipment quality event is determined from the power equipment knowledge graph; the subgraph records the relationship between the device node, the quality event node, and the tracing cause node associated with the current power equipment quality event; According to the subgraph associated with the current power equipment quality event, high-frequency subgraph mining is performed on the power equipment knowledge graph to obtain a high-frequency subgraph; wherein the structure of the high-frequency subgraph matches the structure of the subgraph associated with the current power equipment quality event, and the number of the high-frequency subgraphs is greater than a preset number; According to the subgraph pattern and subgraph relationship of the high-frequency subgraph, a comparison is made with known family defects of the equipment to determine whether the current power equipment quality event is a suspected family defect of the equipment.

3. The method according to claim 2, characterized in that The step of mining high-frequency subgraphs on the power equipment knowledge graph according to the subgraphs associated with the current power equipment quality events to obtain high-frequency subgraphs includes: Perform feature extraction on the subgraph associated with the current power equipment quality event to obtain subgraph features of the current power equipment quality event; the subgraph features include at least one of the number of nodes, the number of edges, and the type of nodes of the subgraph associated with the current power equipment quality event; According to the subgraph feature of the current power equipment quality event, searching the power equipment knowledge graph for a target subgraph whose structure matches the subgraph associated with the current power equipment quality event; When the number of the target sub-graphs is greater than a preset number, the target sub-graphs are determined as the high-frequency sub-graphs.

4. The method according to claim 1, characterized in that: The reasoning of the root cause information of the current power equipment quality event in the power equipment knowledge base to obtain the power equipment quality event tracing result includes: Obtain a pre-built reasoning model; the reasoning model is built based on a quality event reasoning knowledge base; the quality event reasoning knowledge base uses a graph structure to represent a plurality of preset candidate power equipment quality events, cause reasoning rules of the candidate power equipment quality events, and rule priorities of the cause reasoning rules; Acquire the initial facts of the current power equipment quality event, input the initial facts of the current power equipment quality event into the pre-built reasoning model, and obtain the power equipment quality event tracing result.

5. The method according to claim 4, characterized in that The inputting the initial facts of the current power equipment quality event into the pre-built reasoning model to obtain the power equipment quality event tracing result includes: Acquire the initial fact of the current power equipment quality event as the current fact; Inputting the current fact into the pre-built reasoning model, and outputting the fact of the previous step in response to the current fact through the pre-built reasoning model; Acquire the fact of the previous step as the current fact, return to the step of inputting the current fact into the pre-built reasoning model, until the pre-built reasoning model cannot deduce new facts, and obtain a fact reasoning path; According to the factual reasoning path, the tracing result of the power equipment quality event is determined.

6. The method according to claim 1, characterized in that The method adopts a community discovery algorithm that matches the power equipment knowledge graph to identify quality problems of the power equipment quality traceability model and determine power equipment quality events, including: Using a community discovery algorithm that matches the electric power equipment knowledge graph, community discovery is performed on the electric power equipment knowledge graph to obtain a plurality of electric power entity communities; each of the electric power entity communities includes at least two connected electric power entities; The target power entity is identified by using the community characteristics of each power entity in the power entity community, and the current power equipment quality event is obtained; the difference between the community characteristics of the target power entity and the community characteristics of each power entity in the power entity community is greater than a preset difference.

7. A device for analyzing equipment family defects based on a graph database, a knowledge graph, and the entire life cycle of the equipment, characterized in that: The device comprises: A construction module is used to construct a power equipment quality tracing model; the power equipment quality tracing model is configured with a power equipment knowledge graph and a power equipment graph database; An identification module, configured to use a community discovery algorithm that matches the power equipment knowledge graph to identify quality problems in the power equipment quality traceability model and determine current power equipment quality events; A tracing module is used to use the current power equipment quality event as the reasoning starting point and a preset reasoning end target as the reasoning guide to infer the root information that causes the current power equipment quality event in the power equipment knowledge base, and obtain the power equipment quality event tracing result; An analysis module, used to mine high-frequency subgraphs of the power equipment knowledge graph according to the current power equipment quality event and the power equipment quality event tracing result, and determine a defect analysis result; the defect analysis result is used to characterize the suspected family defects of the currently existing equipment; A screening module is used to screen out the distribution of sites where power equipment associated with the suspected family defect of the equipment is located in relative geographic coordinates according to the defect analysis results.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images