Power equipment risk control method, device and equipment based on knowledge graph

Abstract

The invention relates to a power equipment risk control method and device based on a knowledge graph, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: constructing an autonomous controllable knowledge graph based on equipment information related to the autonomous controllability of the power equipment, when the power equipment triggers updating, performing adaptive updating on the autonomous controllable knowledge graph based on updating information related to the autonomous controllability of the power equipment, and according to historical risk events of the power equipment, updating the autonomous controllable knowledge graph based on the updating information related to the autonomous controllability of the power equipment. Performing risk detection on nodes, edges and sub-graphs in the updated autonomous controllable knowledge graph to obtain risk parameters of the updated autonomous controllable knowledge graph, determining risk nodes with autonomous controllable risks from the updated autonomous controllable knowledge graph based on the risk parameters, and determining the risk nodes with the autonomous controllable risks from the updated autonomous controllable knowledge graph. And generating an autonomous controllable lifting scheme for carrying out risk control on the risk node. By adopting the method, the autonomous controllable risk of the power equipment can be reduced.

Description

Technical Field

[0001] The present application relates to the technical field of power equipment risk control, and in particular to a knowledge graph-based power equipment risk control method, device, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] At present, the evaluation and management of the autonomous controllability of power equipment mainly rely on a static indicator scoring system, traditional database information integration and manual risk identification. It also introduces supply chain management information systems and expert systems to assist decision-making and realize the archiving and classification of information such as equipment, components, suppliers, and technical patents.

[0003] However, the current control effect on the possible autonomous and controllable risks of power equipment is limited, and it is impossible to effectively reduce the autonomous and controllable risks of power equipment. Summary of the Invention

[0004] Based on this, it is necessary to provide a knowledge graph-based power equipment risk control method, device, computer equipment, computer-readable storage medium and computer program product that can reduce the autonomous and controllable risks of power equipment in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for risk control of power equipment based on a knowledge graph, comprising:

[0006] Obtaining equipment information related to the autonomous controllability of power equipment;

[0007] Based on the equipment information, an autonomous and controllable knowledge graph for power equipment is constructed. The autonomous and controllable knowledge graph includes nodes and edges connecting nodes. Nodes are used to represent entity information in the equipment information, and edges are used to represent the semantic relationship between connected nodes.

[0008] When the power equipment triggers an update, it obtains update information related to the autonomous controllability of the power equipment, and adaptively updates the autonomous controllable knowledge graph based on the update information to obtain an updated autonomous controllable knowledge graph;

[0009] Based on historical risk events of power equipment, risk detection is performed on the nodes, edges, and subgraphs in the updated autonomous and controllable knowledge graph to obtain risk parameters of the updated autonomous and controllable knowledge graph. The subgraph includes some nodes and some edges in the updated autonomous and controllable knowledge graph.

[0010] Based on the risk parameters, the risk nodes with autonomous controllability risks are determined from the updated autonomous controllability knowledge graph, and an autonomous controllability improvement plan is generated for risk control of the risk nodes.

[0011] In a second aspect, the present application also provides a knowledge graph-based power equipment risk control device, comprising:

[0012] A device information acquisition module is used to obtain device information related to the autonomous controllability of power equipment;

[0013] A knowledge graph construction module is used to construct an autonomous and controllable knowledge graph for power equipment based on equipment information. The autonomous and controllable knowledge graph includes nodes and edges connecting nodes. Nodes are used to represent entity information in equipment information, and edges are used to represent semantic relationships between connected nodes.

[0014] The knowledge graph update module is used to obtain update information related to the autonomous controllability of the power equipment when the power equipment triggers an update, and adaptively update the autonomous controllable knowledge graph based on the update information to obtain an updated autonomous controllable knowledge graph;

[0015] A risk detection module is used to perform risk detection on the nodes, edges, and subgraphs in the updated autonomous and controllable knowledge graph based on historical risk events of power equipment, and obtain risk parameters of the updated autonomous and controllable knowledge graph. The subgraph includes some nodes and some edges in the updated autonomous and controllable knowledge graph.

[0016] The improvement plan generation module is used to determine the risk nodes with autonomous controllable risks from the updated autonomous controllable knowledge graph based on risk parameters, and generate autonomous controllable improvement plans for risk control of the risk nodes.

[0017] In a third aspect, the present application also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements each step of the above-mentioned knowledge graph-based power equipment risk control method when executing the computer program.

[0018] In a fourth aspect, the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the various steps in the above-mentioned knowledge graph-based power equipment risk control method are implemented.

[0019] In a fifth aspect, the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the various steps in the above-mentioned knowledge graph-based power equipment risk control method.

[0020] The above-mentioned knowledge graph-based power equipment risk control method, device, computer equipment, computer-readable storage medium and computer program product construct an autonomous and controllable knowledge graph based on equipment information related to the autonomous controllability of the power equipment. When the power equipment triggers an update, the autonomous and controllable knowledge graph is adaptively updated based on the update information related to the autonomous controllability of the power equipment. According to the historical risk events of the power equipment, risk detection is performed on the nodes, edges and subgraphs in the updated autonomous and controllable knowledge graph to obtain the risk parameters of the updated autonomous and controllable knowledge graph. Based on the risk parameters, risk nodes with autonomous and controllable risks are determined from the updated autonomous and controllable knowledge graph, and an autonomous and controllable improvement plan for risk control of the risk nodes is generated. When the power equipment triggers an update, the autonomous and controllable knowledge graph is adaptively updated based on the updated information of the power equipment, and risk detection is performed on nodes, edges and subgraphs according to historical risk events. Based on the obtained risk parameters, risk nodes with autonomous and controllable risks are determined from the updated autonomous and controllable knowledge graph, and an autonomous and controllable improvement plan for risk control of the risk nodes is generated. In this way, the autonomous and controllable knowledge graph can be dynamically and adaptively updated, and the corresponding autonomous and controllable improvement plan can be generated after the risk nodes are determined based on the risk parameters of risk detection on nodes, edges and subgraphs. This can ensure the accuracy of risk identification, improve the pertinence of the autonomous and controllable improvement plan, and thus help reduce the autonomous and controllable risks of power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. 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 any creative work.

[0022] Figure 1 This is a diagram of an application environment of a knowledge graph-based power equipment risk control method in one embodiment;

[0023] Figure 2 1 is a flow chart of a method for risk control of power equipment based on a knowledge graph in one embodiment;

[0024] Figure 3 A schematic diagram of a flow chart of adaptive update processing in one embodiment;

[0025] Figure 4 Schematic diagram of an autonomous and controllable knowledge graph in one embodiment;

[0026] Figure 51 is a structural block diagram of a knowledge graph-based power equipment risk control device in one embodiment;

[0027] Figure 6 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0029] The power equipment risk control method based on knowledge graph provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104 or placed on the cloud or other network servers.

[0030] The terminal 102 can send device information related to the autonomous controllability of the power equipment to the server 104 through the network, and the server 104 can build an autonomous controllable knowledge graph based on the device information. When the power equipment triggers an update, the terminal 102 can send the update information related to the autonomous controllability of the power equipment to the server 104, and the server 104 can adaptively update the autonomous controllable knowledge graph based on the update information related to the autonomous controllability of the power equipment to obtain an updated autonomous controllable knowledge graph. The server 104 can perform risk detection on the nodes, edges and subgraphs in the updated autonomous controllable knowledge graph based on the historical risk events of the power equipment to obtain the risk parameters of the updated autonomous controllable knowledge graph. Based on the risk parameters, the server 104 can determine the risk nodes with autonomous controllable risks from the updated autonomous controllable knowledge graph, and generate an autonomous controllable improvement plan for risk control of the risk nodes. In addition, the server 104 can also send the autonomous controllable improvement plan to the terminal 102, so that the user of the terminal 102 can perform risk control on the entity information represented by the risk nodes in the power equipment. For example, the entity information such as components and manufacturers in the power equipment can be replaced, thereby reducing the autonomous controllable risk of the power equipment.

[0031] Terminal 102 may include, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices may include smart speakers, smart TVs, smart air conditioners, smart car devices, and projectors. Portable wearable devices may include smart watches, smart bracelets, and head-mounted devices. Head-mounted devices may include virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, and the like. Server 104 may be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server providing cloud computing services.

[0032] In an exemplary embodiment, Figure 2 As shown in the figure, a risk control method for power equipment based on knowledge graph is provided. Figure 1 The server in FIG. 1 is taken as an example to illustrate the method, including the following steps 202 to 210. Among them:

[0033] Step 202: Acquire device information related to the autonomous controllability of the power equipment.

[0034] Power equipment can include equipment used in power generation, transmission, distribution, conversion, and consumption, including but not limited to at least one of various types of equipment, such as generators, motors, transformers, and circuit breakers. Autonomy and controllability refers to the ability to independently conduct R&D, production, operation, and security assurance within a technology, industry, system, or supply chain, without relying on core resources (technology, patents, components, etc.) from external entities (such as other organizations or enterprises). Autonomy and controllability of power equipment refers to the ability to independently control the entire process of R&D, design, manufacturing, operation, and maintenance of key equipment in the power system (generation, transmission, transformation, distribution, and consumption), without relying on external core technologies, components, or supply chains. The core of autonomy and controllability of power equipment can include: mastering the core principles, design methods, and patents of the equipment, such as technological independence in chips, software algorithms, and material formulations; possessing the ability to domestically produce key components to avoid dependence on imported supply chains; and ensuring that the equipment's operation is immune to external manipulation or malicious attacks, ensuring the stability of the power system (such as the security of the grid dispatching system). Equipment information is information related to the autonomous controllability of power equipment, and may include but is not limited to at least one of various types of information including basic equipment information, component parameters, supplier information, intellectual property rights, technical patents, policies and regulations, historical risk events, operation and maintenance logs, etc.

[0035] For example, for power equipment requiring risk control, the server can obtain device information of the power equipment. This device information can be related to the autonomous controllability of the power equipment, and risk control can be performed based on the autonomous controllability of the power equipment. In some embodiments, the server can obtain multi-source heterogeneous data for the power equipment from multiple data sources, such as basic equipment information, component parameters, supplier information, intellectual property rights, technical patents, policies and regulations, historical risk events, and operation and maintenance logs. The server can perform data cleaning and standardization on the multi-source heterogeneous data to obtain device information.

[0036] Step 204: construct an autonomous and controllable knowledge graph for power equipment based on the equipment information. The autonomous and controllable knowledge graph includes nodes and edges connecting the nodes. The nodes are used to represent the entity information in the equipment information, and the edges are used to represent the semantic relationship between the connected nodes.

[0037] A knowledge graph is a form of knowledge representation that uses a graph structure (nodes + edges) to represent real-world entities and their relationships. The autonomous and controllable knowledge graph is a knowledge graph used to represent the equipment information of power equipment. Nodes in the autonomous and controllable knowledge graph can be used to represent entity information within the equipment information, such as at least one of various entity information types, such as technical patents, suppliers, equipment components, policies and regulations. Edges in the autonomous and controllable knowledge graph can represent semantic relationships between connected nodes, such as at least one of various semantic relationships, such as "dependency," "substitution," "control," and "associated risk."

[0038] Optionally, the server can construct an autonomous and controllable knowledge graph based on device information. For example, the server can determine entity information and the semantic relationships between these entities from the device information. For entity information, the server can construct corresponding nodes to represent it; for semantic relationships, the server can construct corresponding edges to represent them. The server can then connect the corresponding nodes through the constructed edges, thereby generating an autonomous and controllable knowledge graph for power equipment.

[0039] Step 206: When the power equipment triggers an update, update information related to the autonomous controllability of the power equipment is obtained, and the autonomous controllable knowledge graph is adaptively updated based on the update information to obtain an updated autonomous controllable knowledge graph.

[0040] Among them, the update information is related to the autonomous controllability of the power equipment, and belongs to the updated device information in the device information of the power equipment, such as the policy and regulations in the device information are updated, then the update information may include the updated policy and regulations. Exemplarily, the server can monitor the power equipment to determine whether the device information of the power equipment is updated. When it is determined that the power equipment triggers an update, the server can obtain the updated information of the power equipment and adaptively update the autonomous controllable knowledge graph through the updated information. For example, the server can update at least one of the nodes or edges in the autonomous controllable knowledge graph to obtain an updated autonomous controllable knowledge graph. In some embodiments, the adaptive update of the autonomous controllable knowledge graph may include at least one of various operations such as replacement, addition, and deletion of nodes and / or edges.

[0041] Step 208: Based on the historical risk events of the power equipment, risk detection is performed on the nodes, edges and subgraphs in the updated autonomous and controllable knowledge graph to obtain the risk parameters of the updated autonomous and controllable knowledge graph. The subgraph includes some nodes and some edges in the updated autonomous and controllable knowledge graph.

[0042] Among them, historical risk events are risk events related to autonomous controllability that have occurred in the history of power equipment, and may include historical risk accidents, specifically including various information such as the accident time, fault type, and loss of historical risk accidents. The subgraph includes some nodes and some edges in the updated autonomous controllable knowledge graph, that is, the subgraph can be regarded as a small network composed of several nodes and edges. Risk detection is a detection related to autonomous controllability, specifically detecting whether there are autonomous controllable risks in the nodes, edges, and subgraphs in the autonomous controllable knowledge graph. The risk parameters can be the detection results obtained by risk detection of the nodes, edges, and subgraphs in the updated autonomous controllable knowledge graph. The risk parameters can be obtained based on the risk detection results of the nodes, edges, and subgraphs, thereby comprehensively representing the risk detection results of the autonomous controllable knowledge graph as a whole.

[0043] Exemplarily, the server can obtain historical risk events of power equipment and perform risk detection on the nodes, edges and subgraphs in the updated autonomous and controllable knowledge graph based on the historical risk events. For example, the server can perform risk detection on the nodes, edges and subgraphs based on the historical risk events, thereby obtaining the risk parameters of the updated autonomous and controllable knowledge graph. In some embodiments, the server can perform risk detection on the nodes, edges and subgraphs in the updated autonomous and controllable knowledge graph based on the historical risk events, thereby obtaining the risk quantification values ​​corresponding to the nodes, edges and subgraphs. The server can obtain the overall risk value based on the risk quantification values ​​corresponding to the nodes, edges and subgraphs, and obtain the risk parameters of the updated autonomous and controllable knowledge graph based on the overall risk value. In some embodiments, for the risk quantification values ​​corresponding to the nodes, edges and subgraphs, the server can perform weighted fusion according to the weights corresponding to the nodes, edges and subgraphs, thereby obtaining the risk parameters of the updated autonomous and controllable knowledge graph.

[0044] Step 210: Based on the risk parameters, determine the risk nodes with autonomous controllability risks from the updated autonomous controllability knowledge graph, and generate an autonomous controllability improvement plan for risk control of the risk nodes.

[0045] Among them, the risk node is a node with autonomous controllable risk determined from the updated autonomous controllable knowledge graph, and the autonomous controllable improvement plan is an implementation plan for risk control of the risk node, such as an implementation plan for replacing the entity information represented by the risk node. Optionally, the server can determine the risk node from the updated autonomous controllable knowledge graph based on risk parameters. For example, when the risk parameters include an overall risk value, the server can compare the overall risk value with the risk value threshold. When the overall risk value is greater than the risk value threshold, the server can determine the risk node with autonomous controllable risk from the updated autonomous controllable knowledge graph. For example, the server can determine the node with a risk quantification value exceeding the threshold as a risk node with autonomous controllable risk. For the risk node, a risk control method for risk control is determined, and an autonomous controllable improvement plan for the risk node is obtained according to the risk control method, so that the user can perform risk control on the risk node according to the autonomous controllable improvement plan.

[0046] In the above-mentioned knowledge graph-based power equipment risk control method, an autonomous and controllable knowledge graph is constructed based on equipment information related to the autonomous controllability of the power equipment. When the power equipment triggers an update, the autonomous and controllable knowledge graph is adaptively updated based on the update information related to the autonomous controllability of the power equipment. According to the historical risk events of the power equipment, risk detection is performed on the nodes, edges and subgraphs in the updated autonomous and controllable knowledge graph to obtain the risk parameters of the updated autonomous and controllable knowledge graph. Based on the risk parameters, risk nodes with autonomous and controllable risks are determined from the updated autonomous and controllable knowledge graph, and an autonomous and controllable improvement plan for risk control of the risk nodes is generated. When the power equipment triggers an update, the autonomous and controllable knowledge graph is adaptively updated based on the updated information of the power equipment, and risk detection is performed on nodes, edges and subgraphs according to historical risk events. Based on the obtained risk parameters, risk nodes with autonomous and controllable risks are determined from the updated autonomous and controllable knowledge graph, and an autonomous and controllable improvement plan for risk control of the risk nodes is generated. In this way, the autonomous and controllable knowledge graph can be dynamically and adaptively updated, and the corresponding autonomous and controllable improvement plan is generated after the risk nodes are determined based on the risk parameters of risk detection on nodes, edges and subgraphs. This can ensure the accuracy of risk identification, improve the pertinence of the autonomous and controllable improvement plan, and thus help reduce the autonomous and controllable risks of power equipment.

[0047] In an exemplary embodiment, based on historical risk events of power equipment, risk detection is performed on the nodes, edges and subgraphs in the updated autonomous and controllable knowledge graph to obtain risk parameters of the updated autonomous and controllable knowledge graph, including: obtaining risk detection data based on historical risk events of power equipment; performing risk detection on the nodes, edges and subgraphs in the updated autonomous and controllable knowledge graph respectively through the risk detection data to obtain node layer detection results, edge layer detection results and sublayer detection results; obtaining risk parameters of the updated autonomous and controllable knowledge graph based on the node layer detection results, edge layer detection results and sublayer detection results.

[0048] The risk detection data is reference data for performing risk detection on nodes, edges, and subgraphs in the autonomous and controllable knowledge graph. The risk detection data can be obtained based on at least historical risk events of power equipment. Node-level detection results are the results of node-level risk detection on nodes, edge-level detection results are the results of edge-level risk detection on edges, and subgraph-level detection results are the results of subgraph-level risk detection on subgraphs.

[0049] For example, the server can obtain historical risk events for power equipment and obtain risk detection data based on these historical risk events. For example, the server can perform mapping processing based on the historical risk events, mapping them into triples (equipment → risk occurrence → event), and determine data such as the accident time, fault type, and loss. The risk detection data can be obtained by integrating the triples, accident time, fault type, and loss data. The server can perform risk detection on nodes, edges, and subgraphs in the autonomous and controllable knowledge graph that has been updated based on the risk detection data, thereby obtaining node-level detection results for node risk detection, edge-level detection results for edge risk detection, and subgraph-level detection results for subgraph risk detection. The server can integrate the node-level detection results, edge-level detection results, and subgraph-level detection results. For example, the server can perform weighted fusion of the node-level detection results, edge-level detection results, and subgraph-level detection results according to their respective weights to obtain risk parameters for the updated autonomous and controllable knowledge graph.

[0050] In some embodiments, as shown in Table 1 below, three perspectives may be included when performing risk detection based on risk detection data, specifically including three risk detection perspectives of nodes, edges, and subgraphs.

[0051] Table 1

[0052]

[0053] Therefore, when performing risk detection on the updated autonomous and controllable knowledge graph, risk detection can be performed separately on the three perspectives of nodes, edges and subgraphs in the updated autonomous and controllable knowledge graph to obtain node layer detection results, edge layer detection results and subgraph layer detection results.

[0054] Furthermore, for risk detection at the node layer, the number and intensity of reliance on each node can be counted to obtain "dependency centrality" and "controllability" can be calculated. If a component has no domestic alternatives and relies entirely on foreign patents, it is considered to have a high degree of control. Nodes with high dependency centrality and high degree of control are marked as potentially high-risk nodes. For risk detection at the edge layer, indicators such as delivery cycle, price, and failure rate can be tracked in real time. Once a sharp jump occurs compared to the long-term average, it means that the dependency chain has begun to become unstable, which is marked as a weak link. For risk detection at the sub-layer layer, the same supplier and its upstream and downstream equipment can be extracted into a subnet. If the subnet shows "one supply and multiple demands" and has no backup path, or has an abnormally sparse structure, it is considered a high-concentration risk cluster.

[0055] For the same power equipment, the risk score of the node where it is located, the abnormality of the associated edges, and the concentration of the subgraph where it is located can be integrated to obtain the overall risk value. Based on the overall risk value, the risk parameters of the updated autonomous and controllable knowledge graph can be obtained.

[0056] In some embodiments, if the overall risk value of the power equipment exceeds a set threshold, then:

[0057] 1. Mark the electrical equipment in red;

[0058] 2. Automatically find the longest or most vulnerable path along the "dependency → supplier → patent" chain and present it to operation and maintenance / decision-makers as a weak link.

[0059] By starting from the three levels of "node-edge-subgraph", using simple statistics and mutation detection methods, we can quickly identify key components or supply chains that are susceptible to external constraints, and highlight the most vulnerable dependency chains for users, thereby automatically marking the autonomous and controllable shortcomings in the knowledge graph.

[0060] In some embodiments, as shown in Table 2 below, risk control processing is performed for switch cabinets.

[0061] Table 2

[0062]

[0063] In this embodiment, the server performs risk detection on nodes, edges and subgraphs respectively through risk detection data obtained based on historical risk events of power equipment, and obtains the risk parameters of the updated autonomous and controllable knowledge graph based on the obtained node layer detection results, edge layer detection results and subgraph layer detection results, which can ensure the accuracy of the risk parameters.

[0064] In an exemplary embodiment, risk detection data is obtained based on historical risk events of power equipment, including: obtaining periodic data streams of power equipment and historical risk events related to the autonomous controllability of power equipment; and obtaining risk detection data based on the periodic data streams and historical risk events.

[0065] The periodic data stream may be periodically acquired device data from the power equipment, such as log data from the power equipment. Alternatively, the server may acquire the periodic data stream from the power equipment, which may be device data acquired at a preset period, such as real-time data streams from the power equipment. The server may acquire historical risk events related to the autonomous controllability of the power equipment and generate risk detection data based on the periodic data stream and the historical risk events.

[0066] In some embodiments, as shown in Table 3 below, historical risk events of the power equipment may be used as offline data, and periodic data streams of the power equipment may be used as real-time data, and risk detection data may be obtained based on the offline data and the real-time data.

[0067] Table 3

[0068]

[0069] In some embodiments, when the power equipment is a transformer, as shown in Table 4 below, risk detection processing can be performed based on the risk detection data of transformer #T-1101.

[0070] Table 4

[0071]

[0072] In this embodiment, the server can integrate the periodic data stream of the power equipment and historical risk events to obtain risk detection data, which can ensure the comprehensiveness of the risk detection data and help improve the accuracy and reliability of risk detection.

[0073] In an exemplary embodiment, Figure 3 As shown, the adaptive update process, i.e., adaptively updating the autonomous and controllable knowledge graph based on the update information to obtain the updated autonomous and controllable knowledge graph, includes steps 302 to 306. Among them:

[0074] Step 302: Generate an update node based on the update information through the incremental graph model.

[0075] An incremental graph model, such as an incremental GraphSAGE model, is capable of processing dynamic changes to graph structured data (nodes, edges, and attributes) in real time or in batches. Alternatively, the server can generate update nodes based on update information using the incremental graph model. For example, the incremental graph model can be used to input update information into the incremental graph model, which then generates the updated nodes.

[0076] Step 304: Determine edges associated with the updated nodes based on the updated information and entity alignment.

[0077] Entity alignment refers to matching the updated node with the entity information of the power equipment. This entity alignment can determine the edges connecting the updated node with other nodes. For example, the server can determine the edges associated with the updated node based on the updated information and entity alignment. For example, the server can perform entity alignment on the updated node with each node in the updated autonomous and controllable knowledge graph based on the updated information to determine the nodes connected to the updated node by edges, thereby determining the edges associated with the updated node.

[0078] In step 306 , when the update node and the edge associated with the update node pass the update verification, the autonomous and controllable knowledge graph is adaptively updated through the update node and the edge associated with the update node to obtain an updated autonomous and controllable knowledge graph.

[0079] The server can adaptively update the autonomous and controllable knowledge graph by updating the nodes and the edges associated with the updated nodes. Optionally, the server can perform an update check on the updated nodes and the edges associated with the updated nodes to determine whether the updated nodes and the edges associated with the updated nodes meet the update conditions. For example, the server can perform a confidence determination on the updated nodes and the edges associated with the updated nodes. When the confidence determination result indicates that the update verification has been passed, the server can adaptively update the autonomous and controllable knowledge graph by updating the nodes and the edges associated with the updated nodes to obtain an updated autonomous and controllable knowledge graph.

[0080] In some embodiments, when adaptively updating an autonomous and controllable knowledge graph, the server can employ a six-stage pipeline: "data stream - extraction - embedding - prediction - verification - writing" to achieve automatic expansion and adaptive updating of the knowledge graph. First, Kafka streams and the CDC (Change Data Capture Interface) interface automatically access heterogeneous information from multiple sources, such as device time series data, operation and maintenance logs, and policy documents, and cleanse and standardize it within the data lake. Subsequently, using BERT-CRF (Bidirectional Encoder Representations from Transformers-Conditional Random Field) text extraction and CV (Computer Vision) object detection, structured and unstructured information are uniformly abstracted into incremental triples. Next, node embedding vectors are learned online based on the incremental GraphSAGE model. Entity alignment and new relationship prediction are achieved through vector retrieval and attribute matching, dynamically completing semantic edges such as "dependency," "substitution," and "association risk." New knowledge is verified using SHACL (Shapes Constraint Language) rules and evaluated using LightGBM (Light Gradient Boosting Machine) confidence assessment before being transactionally written to the graph database and versioned. The system's built-in drift monitoring mechanism triggers model retraining upon detection of distribution changes, ensuring the graph adapts in real time as business evolves. Ultimately, the graph provides the latest dependency paths and confidence scores for risk warnings and domestic substitution recommendations, achieving a closed-loop knowledge update and continuous value-added.

[0081] In this embodiment, the server can determine the update nodes and the edges associated with the update nodes based on the update information, and when the update nodes and the edges associated with the update nodes pass the update verification, the server can adaptively update the autonomous and controllable knowledge graph through the update nodes and the edges associated with the update nodes, thereby ensuring the accuracy of the update nodes and the edges associated with the update nodes, thereby ensuring the reliability of the updated autonomous and controllable knowledge graph.

[0082] In an exemplary embodiment, based on risk parameters, risk nodes with autonomous controllable risks are determined from an updated autonomous controllable knowledge graph, and an autonomous controllability improvement plan for risk control of the risk nodes is generated, including: when the risk parameters meet preset conditions, risk nodes with autonomous controllable risks are determined from the updated autonomous controllable knowledge graph; at least one risk control method for risk control of the risk nodes is determined; and an autonomous controllability improvement plan is generated based on at least one risk control method.

[0083] Pre-set conditions can be configured based on actual needs to determine whether risk control should be triggered for a risk node based on risk parameters. For example, if the risk parameters include a risk value, the pre-set condition could be that the risk value is greater than a risk threshold. Risk control methods refer to the risk control approach for risk nodes, such as replacing risk nodes and the path within which they reside.

[0084] For example, the server may determine a preset condition and, if it determines that the risk parameter satisfies the preset condition, identify a risk node in the updated autonomous and controllable knowledge graph that has an autonomous and controllable risk. For example, the server may identify a node whose risk detection result exceeds a risk threshold as a risk node that has an autonomous and controllable risk. For each risk node, the server may determine at least one risk control method for risk control, which may include various risk control methods such as replacement and warning. The server may generate an autonomous and controllable improvement plan based on the risk control method for the risk node, so that risk control can be performed on the risk node using the autonomous and controllable improvement plan.

[0085] In this embodiment, when the risk parameters meet the preset conditions, the server can generate a corresponding autonomous and controllable improvement plan based on at least one risk control method for the risk node, which can improve the targetedness of the autonomous and controllable improvement plan, thereby helping to reduce the autonomous and controllable risks of power equipment.

[0086] In an exemplary embodiment, an autonomous and controllable knowledge graph for power equipment is constructed based on device information, including: determining entity information associated with the power equipment from the device information, and constructing nodes representing the entity information; determining semantic relationships between different entity information from the device information, and constructing edges representing the semantic relationships; connecting each node and each edge according to the entity information and semantic relationships to obtain an autonomous and controllable knowledge graph for the power equipment.

[0087] Optionally, the server can determine entity information associated with the power equipment from the device information and construct nodes representing the corresponding entity information, with a one-to-one correspondence between nodes and entity information. The server can also determine semantic relationships between different entity information from the device information and construct edges representing these semantic relationships. The server can connect each node and each edge based on the entity information and the phonetic relationships between each entity information, thereby obtaining an autonomous and controllable knowledge graph for power equipment.

[0088] In this embodiment, the server determines entity information and semantic relationships based on device information, and generates an autonomous and controllable knowledge graph for power equipment by constructing nodes and edges, thereby ensuring the reliability of the autonomous and controllable knowledge graph.

[0089] In an exemplary embodiment, the knowledge graph-based power equipment risk control method further includes: generating risk warning information associated with the risk node; and displaying the risk warning information in a perceptible manner in the updated autonomous and controllable knowledge graph.

[0090] Risk warning information is used to indicate autonomous and controllable risks within the equipment information of power equipment, allowing users to promptly implement risk control measures. For example, for risk nodes, the server can generate corresponding risk warning information and display it in a perceptible manner within the updated autonomous and controllable knowledge graph. For example, the server can highlight the risk warning information within the updated autonomous and controllable knowledge graph.

[0091] In this embodiment, the server displays the risk warning information associated with the risk node in a perceptible manner in the updated autonomous and controllable knowledge graph, and can provide targeted and intuitive prompts through the risk warning information to prompt risk control, which is conducive to reducing the autonomous and controllable risks of power equipment.

[0092] This application also provides an application scenario, which applies the above-mentioned power equipment risk control method based on knowledge graph. Specifically, the application of the power equipment risk control method based on knowledge graph in this application scenario is as follows:

[0093] Currently, the evaluation and management of the autonomous controllability of power equipment primarily relies on static indicator scoring systems, traditional database information integration, and manual risk identification. Some new approaches incorporate supply chain management information systems and expert systems to aid decision-making, enabling the archiving and classification of information on equipment, components, suppliers, and technical patents. Some research is beginning to utilize knowledge graph technology to link heterogeneous information such as power equipment, key components, suppliers, and technical standards, supporting information retrieval and visualization, and improving data utilization efficiency.

[0094] Despite the initial adoption of emerging technologies such as knowledge graphs, existing methods generally have the following shortcomings: (1) The knowledge graph structure is static and cannot be adaptively learned and updated based on actual operations, external changes, risk dynamics and other factors, resulting in limited recommendation and identification capabilities; (2) There is a lack of multi-dimensional correlation mining of equipment, supply chain, patents, policies, risk events, etc., and it cannot effectively identify the "shortcomings" and improvement paths of autonomous control; (3) There is a lack of intelligent decision-making recommendation functions, and there is a lack of active recommendation capabilities for autonomous control improvement and risk avoidance in complex situations; (4) The identification and response speed of new external risk events is slow, and real-time automatic labeling and alarm of key risks cannot be achieved.

[0095] Based on this, the knowledge graph-based power equipment risk control method provided in this application, by constructing an adaptively updated knowledge graph of autonomous and controllable power equipment, realizes the intelligent fusion, dynamic association, risk identification and automatic recommendation of autonomous and controllable improvement paths for the entire life cycle of the equipment. The knowledge graph-based power equipment risk control method provided in this application can realize the automatic learning and adaptive update mechanism of the knowledge graph, intelligently mine the deep correlation of multi-source information such as equipment, supply chain, technology, policy, risk, etc., actively identify high-risk points and links that are prone to loss of control, and automatically recommend alternative solutions and localization paths to improve the level of autonomous control, ultimately realizing risk-driven intelligent decision support.

[0096] The knowledge graph-based power equipment risk control method provided in this application involves the automatic construction and adaptive learning processing of the autonomous and controllable knowledge graph of power equipment with full life cycle and multi-dimensional information, multi-source heterogeneous data fusion based on the knowledge graph, incremental update of graph relationships and risk path reasoning mechanism, high-risk nodes combined with historical risk event mining and real-time monitoring, intelligent identification and dynamic labeling algorithm of weak links, and intelligent recommendation engine for improving autonomous control, including automatic generation and processing of personalized suggestions such as domestic substitution, patent bypass, and supply chain optimization path, as well as intelligent graph visualization and dynamic alarm linkage mechanism.

[0097] Specifically, the implementation steps of the knowledge graph-based power equipment risk control method provided in this application include data collection → data cleaning and standardization → knowledge graph construction → graph adaptive learning and updating → intelligent risk identification and recommendation → visual display and alarm output, specifically including:

[0098] 1. Data collection and fusion:

[0099] Through interfaces, the system automatically collects multi-source heterogeneous data throughout the life cycle of power equipment, including basic equipment information, component parameters, supplier information, intellectual property rights, technical patents, policies and regulations, historical risk events, and operation and maintenance logs. It uses data cleaning and standardization to integrate multiple types of structured and unstructured data.

[0100] Specifically, as shown in Table 5 below, multi-source heterogeneous data includes structured data (data sets with fixed field definitions, such as equipment basic information tables, component parameter tables, and supplier performance tables) as well as unstructured data, such as free-text inspection logs, full-text patents in PDF (Portable Document Format), and infrared video streams. Through ETL (Extract, Transform, Load) + NLP (Natural Language Processing) / CV processing, the system parses unstructured content into computable features and aligns these features with structured tables in a unified knowledge graph, achieving efficient integration of data across the entire lifecycle.

[0101] Table 5

[0102]

[0103] Furthermore, unstructured data lacks standardized fields or formats and requires techniques such as NLP, optical character recognition (OCR), and knowledge extraction to be included in analysis. This data typically accounts for over 70% of the total data volume. Table 6 below illustrates the processing of unstructured data.

[0104] Table 6

[0105]

[0106] Structured data is stored in a fixed schema with defined field names and data types, allowing for direct query and statistics using SQL or graph databases. Table 7 below illustrates the processing of structured data.

[0107] Table 7

[0108]

[0109] 2. Knowledge graph construction and adaptive learning:

[0110] The above information is constructed into a multi-level, multi-dimensional knowledge graph of autonomous and controllable power equipment. With equipment, components, supply chain companies, patents, technical specifications, policies, events, etc. as nodes, multiple semantic relationships between entities (such as "dependency", "substitution", "controlled", "associated risk", etc.) are established. Machine learning algorithms, graph embedding and incremental knowledge discovery mechanisms are introduced to support automatic expansion and adaptive updating of knowledge graphs, and can automatically learn node attributes and relationship changes based on new data or risk events. In some embodiments, such as Figure 4 As shown in FIG, a schematic diagram of the knowledge graph constructed for a 220 kV main transformer is shown.

[0111] 3. Intelligent risk identification and weak link positioning:

[0112] Combining historical risk event mining with real-time data streams, the system automatically detects and identifies high-risk nodes and nodes with low autonomy and controllability within the knowledge graph, along with their impact paths. Through graph mining and anomaly detection algorithms (e.g., based on node centrality, edge weight variation, and subgraph anomalies), it identifies weaknesses in the equipment's autonomy and controllability in areas such as supply chain, patent dependency, and technological processes, automatically marking high-risk points.

[0113] 4. Intelligent recommendation and autonomous and controllable improvement path generation:

[0114] A knowledge graph-based reasoning engine automatically searches for feasible domestic substitution paths, patent circumvention solutions, supply chain optimization suggestions, and key technology advancements for identified risk nodes and weak links. This provides intelligent, personalized path recommendations and decision-making insights for enhancing equipment's independent and controllable capabilities. Recommendations may include: alternative components, potential partners, patent application suggestions, and recommendations for adapting to new policies.

[0115] 5. Intelligent visualization and dynamic alarm:

[0116] The graphical visualization interface displays the full range of autonomous and controllable equipment in real time, supporting risk heat maps, high-risk node marking, and dynamic display of improvement paths. It also supports automatic alerts for risk events, assisting operations and decision-makers in responding promptly and locating issues quickly.

[0117] The knowledge graph-based power equipment risk control method provided in this application has strong adaptability, supporting the automatic expansion and updating of the knowledge graph based on new data and risk events. It can continuously reflect the actual operating environment and technological dynamics, identify new risk points, and recommend the latest improvement paths. Secondly, it achieves multi-dimensional intelligent fusion. By integrating full-dimensional information such as equipment, supply chain, patents, policies, and events, it automatically infers complex relationships, improving the accuracy and depth of risk identification. Moreover, it implements proactive intelligent recommendations, providing personalized recommendations for autonomous and controllable improvement paths, alternative resources, key patents / technical solutions, etc. for actual scenarios, enhancing decision-making support capabilities. In addition, it can quickly locate weak links, intelligently identify autonomous and controllable shortcomings and weak nodes, and provide specific and feasible optimization suggestions. Finally, the knowledge graph-based power equipment risk control method provided in this application has a fast response speed and strong visualization. It can visualize risk points and improvement paths in real time, support dynamic early warning and intelligent alarms, and greatly improve risk response and management efficiency.

[0118] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed 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 portion of steps or stages in other steps.

[0119] Based on the same inventive concept, the embodiments of the present application also provide a knowledge graph-based power equipment risk control device for implementing the above-mentioned knowledge graph-based power equipment risk control method. The implementation solution provided by the device is similar to the implementation solution described in the above-mentioned method. Therefore, the specific limitations of one or more embodiments of the knowledge graph-based power equipment risk control device provided below can be found in the above-mentioned limitations of the knowledge graph-based power equipment risk control method, and will not be repeated here.

[0120] In an exemplary embodiment, Figure 5 As shown, a knowledge graph-based power equipment risk control device 500 is provided, comprising: an equipment information acquisition module 502, a knowledge graph construction module 504, a knowledge graph update module 506, a risk detection module 508, and an improvement plan generation module 510, wherein:

[0121] The device information acquisition module 502 is used to acquire device information related to the autonomous controllability of the power equipment;

[0122] A knowledge graph construction module 504 is used to construct an autonomous and controllable knowledge graph for power equipment based on the equipment information. The autonomous and controllable knowledge graph includes nodes and edges connecting the nodes. The nodes are used to represent entity information in the equipment information, and the edges are used to represent the semantic relationship between the connected nodes.

[0123] The knowledge graph update module 506 is configured to obtain update information related to the autonomous controllability of the power equipment when the power equipment triggers an update, and adaptively update the autonomous controllability knowledge graph based on the update information to obtain an updated autonomous controllability knowledge graph;

[0124] The risk detection module 508 is used to perform risk detection on the nodes, edges, and subgraphs in the updated autonomous and controllable knowledge graph based on historical risk events of the power equipment, and obtain risk parameters of the updated autonomous and controllable knowledge graph, where the subgraph includes some nodes and some edges in the updated autonomous and controllable knowledge graph;

[0125] The improvement plan generation module 510 is used to determine risk nodes with autonomous controllable risks from the updated autonomous controllable knowledge graph based on risk parameters, and generate autonomous controllable improvement plans for risk control of the risk nodes.

[0126] In some embodiments, the risk detection module 508 is also used to obtain risk detection data based on historical risk events of power equipment; through the risk detection data, risk detection is performed on the nodes, edges and subgraphs in the updated autonomous and controllable knowledge graph respectively to obtain node layer detection results, edge layer detection results and subgraph layer detection results; based on the node layer detection results, edge layer detection results and subgraph layer detection results, the risk parameters of the updated autonomous and controllable knowledge graph are obtained.

[0127] In some embodiments, the risk detection module 508 is further configured to obtain periodic data streams of the power equipment and historical risk events related to the autonomous controllability of the power equipment; and obtain risk detection data based on the periodic data streams and historical risk events.

[0128] In some embodiments, the knowledge graph update module 506 is also used to generate an update node based on the update information through an incremental graph model; determine the edges associated with the update node based on the update information and entity alignment; when the update node and the edge associated with the update node pass the update verification, the autonomous and controllable knowledge graph is adaptively updated through the update node and the edge associated with the update node to obtain an updated autonomous and controllable knowledge graph.

[0129] In some embodiments, the improvement plan generation module 510 is also used to determine the risk nodes with autonomous controllable risks from the updated autonomous controllable knowledge graph when the risk parameters meet the preset conditions; determine at least one risk control method for risk control of the risk nodes; and generate an autonomous controllable improvement plan based on at least one risk control method.

[0130] In some embodiments, the knowledge graph construction module 504 is also used to determine entity information associated with the power equipment from the device information and construct nodes representing the entity information; determine the semantic relationship between different entity information from the device information and construct edges representing the semantic relationship; connect each node and each edge according to the entity information and semantic relationship to obtain an autonomous and controllable knowledge graph for the power equipment.

[0131] In some embodiments, a risk warning module is also included, which is used to generate risk warning information associated with risk nodes; in the updated autonomous and controllable knowledge graph, the risk warning information is displayed in a perceptible manner.

[0132] Each module in the aforementioned knowledge graph-based power equipment risk control device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0133] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, memory and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. 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, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store various data involved in the knowledge graph-based power equipment risk control method. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a knowledge graph-based power equipment risk control method is implemented.

[0134] Those skilled in the art will understand that Figure 6The 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 shown in the figure, or combine certain components, or have a different component arrangement.

[0135] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0136] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above-mentioned method embodiments when executed by a processor.

[0137] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0138] 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.

[0139] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. 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. In particular, any reference to memory, database, or other media used in the embodiments provided in this 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), magnetic 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. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0140] The technical features of the above embodiments can be combined arbitrarily. In order 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.

[0141] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for controlling power equipment risk based on knowledge graph, characterized in that: The method comprises: Obtaining equipment information related to the autonomous controllability of power equipment; Constructing an autonomous and controllable knowledge graph for the power equipment based on the equipment information, wherein the autonomous and controllable knowledge graph includes nodes and edges connecting the nodes, wherein the nodes are used to represent entity information in the equipment information, and the edges are used to represent semantic relationships between the connected nodes; When the power device triggers an update, update information related to the autonomous controllability of the power device is obtained, and based on the update information, the autonomous controllable knowledge graph is adaptively updated to obtain an updated autonomous controllable knowledge graph; Based on historical risk events of the power equipment, risk detection is performed on nodes, edges, and subgraphs in the updated autonomous and controllable knowledge graph to obtain risk parameters of the updated autonomous and controllable knowledge graph, wherein the subgraph includes some nodes and some edges in the updated autonomous and controllable knowledge graph; Based on the risk parameters, risk nodes with autonomous controllability risks are determined from the updated autonomous controllability knowledge graph, and an autonomous controllability improvement plan for performing risk control on the risk nodes is generated.

2. The method according to claim 1, characterized in that The step of performing risk detection on nodes, edges, and subgraphs in the updated autonomous and controllable knowledge graph based on historical risk events of the power equipment to obtain risk parameters of the updated autonomous and controllable knowledge graph includes: Obtaining risk detection data based on historical risk events of the power equipment; Using the risk detection data, risk detection is performed on the nodes, edges, and subgraphs in the updated autonomous and controllable knowledge graph, respectively, to obtain node layer detection results, edge layer detection results, and subgraph layer detection results; Based on the node layer detection results, the edge layer detection results and the sublayer layer detection results, the risk parameters of the updated autonomous and controllable knowledge graph are obtained.

3. The method according to claim 2, characterized in that The obtaining of risk detection data based on historical risk events of the power equipment includes: Acquiring a periodic data stream of the power equipment and historical risk events related to autonomous controllability of the power equipment; Risk detection data is obtained based on the periodic data stream and the historical risk events.

4. The method according to claim 1, wherein Adaptively updating the autonomous and controllable knowledge graph based on the update information to obtain an updated autonomous and controllable knowledge graph includes: Generate an update node based on the update information through an incremental graph model; Determining an edge associated with the updated node based on the updated information and entity alignment; When the update node and the edge associated with the update node pass the update verification, the autonomous and controllable knowledge graph is adaptively updated through the update node and the edge associated with the update node to obtain an updated autonomous and controllable knowledge graph.

5. The method according to claim 1, wherein The step of determining risk nodes with autonomous controllability risks from the updated autonomous controllability knowledge graph based on the risk parameters and generating an autonomous controllability improvement plan for risk control of the risk nodes includes: When the risk parameter meets the preset conditions, determining the risk nodes with autonomous controllable risks from the updated autonomous controllable knowledge graph; Determining at least one risk control method for performing risk control on the risk node; An autonomous and controllable improvement plan is generated based on the at least one risk control method.

6. The method according to claim 1, characterized in that The constructing of an autonomous and controllable knowledge graph for the power equipment based on the equipment information includes: Determining entity information associated with the power equipment from the equipment information, and constructing a node representing the entity information; Determining semantic relationships between different entity information from the device information, and constructing edges representing the semantic relationships; According to the entity information and the semantic relationship, each of the nodes and each of the edges are connected to obtain an autonomous and controllable knowledge graph for the power equipment.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Generating risk warning information associated with the risk node; In the updated autonomous and controllable knowledge graph, the risk warning information is displayed in a perceptible manner.

8. A power equipment risk control device based on knowledge graph, characterized in that: The device comprises: A device information acquisition module is used to obtain device information related to the autonomous controllability of power equipment; a knowledge graph construction module, configured to construct an autonomous and controllable knowledge graph for the power equipment based on the equipment information, wherein the autonomous and controllable knowledge graph includes nodes and edges connecting the nodes, wherein the nodes are used to represent entity information in the equipment information, and the edges are used to represent semantic relationships between the connected nodes; A knowledge graph updating module is configured to, when the power device triggers an update, obtain update information related to the autonomous controllability of the power device, and adaptively update the autonomous controllable knowledge graph based on the update information to obtain an updated autonomous controllable knowledge graph; a risk detection module, configured to perform risk detection on nodes, edges, and subgraphs in the updated autonomous and controllable knowledge graph based on historical risk events of the power equipment, and obtain risk parameters of the updated autonomous and controllable knowledge graph, wherein the subgraph includes some nodes and some edges in the updated autonomous and controllable knowledge graph; An improvement plan generation module is used to determine risk nodes with autonomous controllable risks from the updated autonomous controllable knowledge graph based on the risk parameters, and generate an autonomous controllable improvement plan for risk control of the risk nodes.

9. 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 7 are implemented.

10. 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 7 are implemented.

Images