Power equipment error prevention verification method, electronic equipment, storage medium and program product

Abstract

The present application provides a method for error-proofing of electric power equipment, an electronic device, a storage medium and a program product, and relates to the field of electric power dispatching technology. The method includes: obtaining an operation ticket to be verified and a dispatch error-proofing knowledge graph for electric power equipment; the dispatch error-proofing knowledge graph is generated based on the physical topology, status data and operating rules of the electric power equipment; performing event extraction on the operation ticket to be verified to obtain the task event to be verified; based on the dispatch error-proofing knowledge graph, determining the error-proofing rules corresponding to the task event, and performing error-proofing on the operation ticket. The embodiments of the present application can reduce the burden of manual review and improve the efficiency of error-proofing. The dispatch error-proofing knowledge graph is generated based on the physical topology, status data and operating rules of the electric power equipment, and can realize a multi-dimensional and refined description of the power grid, thereby improving the accuracy of error-proofing of the operation ticket.

Description

Technical Field

[0001] The present application relates to the technical field of electric power dispatching, and in particular to a method for preventing miscalibration of electric power equipment, electronic equipment, storage medium and program product. Background Art

[0002] The operation characteristics of the power grid are complex, and it is gradually developing towards a high proportion of new energy and high power electronic devices. The operation and regulation of the power grid are becoming more and more complex and difficult to control, which puts higher requirements on real-time operation and regulation. It is crucial to ensure the safe operation of power equipment and prevent electrical accidents caused by human errors.

[0003] The verification of operation tickets can be used to avoid misoperation of power equipment. The verification of operation tickets refers to the safety verification of the correctness of the operation instructions in the operation tickets. The correctness of the operation instructions is directly related to whether the power grid maintenance work can be carried out normally, and may even affect the safety of power grid operation and the personal safety of operators. Therefore, how to quickly and accurately verify the operation tickets in the power system to prevent misoperation has become a problem that needs to be solved. Summary of the invention

[0004] The embodiments of the present application provide a method for preventing error calibration of electric power equipment, an electronic device, a storage medium and a program product to achieve rapid and accurate prevention error calibration of electric power equipment.

[0005] In the first aspect, an embodiment of the present application provides a method for error prevention verification of power equipment, including: obtaining an operation ticket to be verified and a dispatch error prevention knowledge graph of the power equipment; the dispatch error prevention knowledge graph is generated based on the physical topology structure, status data and operation rules of the power equipment; performing event extraction on the operation ticket to be verified to obtain a task event to be verified; based on the dispatch error prevention knowledge graph, determining the error prevention verification rules corresponding to the task event; and performing error prevention verification on the operation ticket according to the error prevention verification rules.

[0006] In a second aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor implements any of the above methods when executing the computer program.

[0007] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, any of the above methods is implemented.

[0008] In a fourth aspect, an embodiment of the present application provides a computer program product, the computer program product including a computer program, and the computer program implements any of the above methods when executed by a processor.

[0009] Compared with the prior art, this application has the following advantages:

[0010] The present application provides a method for error prevention verification of electric equipment, an electronic device, a storage medium and a program product. First, the operation ticket to be verified and the dispatch error prevention knowledge graph of the electric equipment are obtained; the dispatch error prevention knowledge graph is generated based on the physical topology structure, state data and operation rules of the electric equipment; then, the operation ticket to be verified is subjected to event extraction to obtain the task event to be verified; based on the dispatch error prevention knowledge graph, the error prevention verification rule corresponding to the task event is determined; finally, according to the error prevention verification rule, the operation ticket is subjected to error prevention verification. In the embodiment of the present application, by extracting events from the operation ticket and determining the error prevention verification rule corresponding to the task event based on the dispatch error prevention knowledge graph for error prevention verification, the burden of manual review can be reduced and the efficiency of error prevention verification can be improved. Among them, the dispatch error prevention knowledge graph is generated based on the physical topology structure, state data and operation rules of the electric equipment, which can realize a multi-dimensional and refined description of the power grid, thereby improving the accuracy of error prevention verification of the operation ticket.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments according to the present application and should not be regarded as limiting the scope of the present application.

[0013] Figure 1 A schematic diagram of an application scenario of a method for preventing miscalibration of electric power equipment according to an embodiment of the present application.

[0014] Figure 2 This is a flow chart of a method for preventing miscalibration of electric power equipment according to an embodiment of the present application.

[0015] Figure 3 This is a flow chart of a method for preventing miscalibration of electric power equipment according to an embodiment of the present application.

[0016] Figure 4 This is a structural block diagram of a device for preventing miscalibration of electric power equipment according to an embodiment of the present application.

[0017] Figure 5 A block diagram of an electronic device used to implement an embodiment of the present application. DETAILED DESCRIPTION

[0018] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the concept or scope of the present application. Therefore, the drawings and descriptions are considered to be exemplary in nature and not restrictive.

[0019] To facilitate understanding of the technical solutions of the embodiments of the present application, the following describes the related technologies of the embodiments of the present application. The following related technologies can be combined with the technical solutions of the embodiments of the present application as optional solutions, and they all belong to the protection scope of the embodiments of the present application.

[0020] 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 the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0021] The power equipment anti-error verification method provided by the technical solution of the present application can be applied to the power equipment anti-error system, and specifically can be applied to power equipment verification scenarios such as line ticket verification, switch ticket verification, busbar ticket verification and transformer ticket verification. Among them, the power equipment anti-error system, the full name of which is the power system to prevent electrical misoperation system, is a set of technical measures and management systems designed in the power industry to ensure the safe operation of power equipment and prevent electrical accidents caused by human errors. The system can strictly control and supervise the operation process of power equipment through a combination of technical and management means to avoid operations that may lead to serious consequences, such as mistakenly pulling and closing switches, mistakenly entering live intervals, and mistakenly operating relay protection devices. The power equipment anti-error system is mainly used in power facilities such as substations and power plants, and is one of the important guarantees for safe production of electricity.

[0022] Figure 1 A schematic diagram of an application scenario of the method for preventing miscalibration of electric power equipment provided in this application. Figure 1 As shown, the implementation process of the power equipment anti-error verification method in this embodiment includes two parts: offline graph modeling and fusion, and online knowledge extraction and verification. The power equipment in this embodiment can be determined according to specific needs, for example, it can be a provincial 220kV equipment. The power equipment includes but is not limited to switches, capacitors, loads, lines, busbars, transformers, generators, etc.

[0023] The specific process of offline graph modeling and fusion includes:

[0024] The Common Information Model (CIM) of the power system is obtained, and the CIM is parsed to extract the schema-free graph structure, which represents the electrical connection relationship, voltage relationship, station and status attributes of the equipment in the power grid, that is, the physical topology of the power equipment. The physical topology includes the busbar topology hierarchy structure. The busbar topology hierarchy structure refers to a hierarchical network model used to describe the electrical connection relationship within a substation or between multiple substations in the power system. The busbar is an electrical connection point with the same voltage in the power system, which can be regarded as a node in the power network. Different power equipment such as generators, transformers, and lines are connected to each other through the busbar to realize the transmission and distribution of electric energy. In a complex power network, the busbar is organized into different levels according to its position in the power grid, voltage level, and the importance of the connected equipment. High-level busbars are usually connected to large power plants or high-voltage transmission lines, while low-level busbars may serve the power distribution needs of local areas. The busbars at each level are connected to the busbars at other levels through transformers, switchgear, etc., forming an electrical connection between the upper and lower levels. This inter-level connection relationship reflects the entire process of electricity production, transmission and distribution, and is the basis for the stable operation of the power system.

[0025] Generate a structural knowledge graph based on the physical topology structure. Optionally, construct multiple ontology object subgraphs (i.e., the "upper structure" in the physical topology graph, for example, the switch unit structure, including: ground switch-knife switch-switch-knife switch-ground switch) based on the wiring methods (e.g., single busbar wiring, double busbar wiring, bridge wiring, polygonal wiring, etc.) and equipment types (e.g., AC equipment types: generators, transformers, circuit breakers, disconnectors, etc.; DC equipment types: DC generators, DC motors, rectifiers, inverters, etc.) between different power equipment in the power system; use an improved graph isomorphism algorithm (e.g., VF2 algorithm) to perform a deep traversal in the physical topology graph, match multiple ontology object subgraphs in the physical topology graph, and determine successfully matched ontology object subgraphs; generate nodes corresponding to successfully matched ontology object subgraphs, for example, equipment attribute nodes, equipment wiring method nodes, etc., and determine the connection relationship between the nodes, and generate a structural knowledge graph with the nodes and connection relationships corresponding to multiple successfully matched ontology object subgraphs.

[0026] Generate a state knowledge graph using state data. Among them, state data includes historical state data and real-time state data in ticket data. Ticket data includes historical operation tickets and maintenance orders, etc. These unstructured data are structured and processed into a preset format, and then historical state data is obtained from them. Real-time state data includes telesignaling data and telemetry data, etc. Telesignaling data refers to the remote monitoring of state information, also known as remote state signals, usually represented by 1 or 2 binary bits, for example, the opening / closing state of a circuit breaker or disconnector, the action / reset of a protection signal, etc. Telemetry data transmits various measurement values ​​of the remote station to the master station, including electrical parameters such as voltage, current, and power, as well as other measurable physical quantities such as temperature and pressure. These measurement values ​​are used to monitor the operating status of the power system and ensure the safe and stable operation of the system. The real-time state data is processed in batches, that is, real-time stream batch data processing, and the processed historical state data and real-time state data are linked to the power equipment to generate a state knowledge graph.

[0027] The rule texts such as equipment operation specifications (e.g., dispatching operation specifications, equipment maintenance specifications) and error prevention regulations are processed by natural language processing, such as document splitting and knowledge extraction, to obtain operation rules. The operation rules mainly include basic state judgment rules for power grid operation and operation safety interlocking rules. The textual rules are converted into logical rules, and logical representation operators are defined, including complex combination logic such as AND, OR, NOT, and recursion, so as to be applicable to multiple scenarios such as AC equipment state rule verification, AC line state rule verification, AC equipment operation rule verification, and DC equipment state rule verification. The logical rules are linked to the power equipment to generate a rule knowledge graph. The rule knowledge graph can realize the structuring and electronicization of power equipment operation rules. Among them, the constructed error prevention rules have high versatility and expression ability, support complex logical combinations, and improve the breadth and depth of rule coverage.

[0028] The structural knowledge graph, state knowledge graph and rule knowledge graph are integrated to obtain the dispatch error prevention knowledge graph. The specific process of integration includes: first, identifying the common entities and attributes in the structural knowledge graph, state knowledge graph and rule knowledge graph, establishing the ontology mapping relationship across graphs, and ensuring the consistency of the same or similar concepts after integration. Then, based on the logical and physical connections between entities (for example, power equipment, state data, and operating rules), build or strengthen the links between cross-graph entities. For example, the power equipment in the structural knowledge graph is associated with the real-time state data in the state knowledge graph to integrate the static structure with the dynamic information. Finally, the graph database or knowledge graph reasoning engine is used to perform logical reasoning and consistency verification to solve the concept conflicts or data inconsistencies that may occur during the integration process.

[0029] The specific process of online knowledge extraction and verification includes:

[0030] Extracting operation ticket information means extracting events from the operation ticket to obtain task events to be verified.

[0031] The extraction process of task events includes: using the trigger word extraction model to obtain event trigger words from the operation ticket to be verified; using the argument extraction model, according to the operation ticket to be verified and the event trigger words, to obtain multiple event arguments (i.e., event constituent elements) corresponding to the operation ticket to be verified; combining multiple event arguments to obtain task events.

[0032] For task events, event arguments include: subject name, subject voltage level, sub-body name, start state, end state, location constraint, operation constraint, etc. Operation events include four types of objects. The event arguments of location objects include site name, line name, line voltage level, etc.; the event arguments of equipment objects include: equipment type, equipment number, equipment sub-type, equipment voltage level, etc.; the event arguments of action objects include: start state, end state, operation, etc.; the event arguments of constraint objects include: operation constraint, equipment constraint, location constraint, etc.

[0033] The specific process of linking the operation ticket information includes: determining the task entity corresponding to the task event in the node of the scheduling error prevention knowledge graph, and obtaining the target equipment subgraph corresponding to the task entity; obtaining the operating rules of the target power equipment based on the nodes of the target equipment subgraph as the error prevention verification rules corresponding to the task event.

[0034] Among them, by extracting task events from the operation ticket and linking them with task entities, intelligent understanding and rapid response to operation ticket instructions are achieved, which improves the automation and intelligence level of scheduling instruction processing.

[0035] The specific process of equipment rule verification and verification result return includes: recursively parsing the error prevention verification rules according to the target equipment sub-graph to obtain the status data and operation rules of the target power equipment corresponding to the task event; performing simulation deduction in the error prevention knowledge graph according to the status data and operation rules of the target power equipment to obtain the simulation deduction results; based on the simulation deduction results, determining the error prevention verification results of the operation ticket and returning them to the user.

[0036] In the online verification scenario, according to the input operation ticket, through event extraction-entity linking (determining the task entity in the dispatching error prevention knowledge graph)-equipment subgraph acquisition, the operating rules of the power equipment are recursively parsed based on the hierarchical topological structure information of the dispatching error prevention knowledge graph; finally, the real-time equipment status and the parsed rules are combined to perform verification and judgment, and the results are output.

[0037] Verification result display. Optionally, when the error prevention verification result indicates that the verification has not passed, the power equipment that has not passed the verification and the operating rules that have not passed the verification are determined; the power equipment that has not passed the verification and the operating rules that have not passed the verification are visualized to obtain a verification result knowledge graph. In response to a trigger operation on a node of the verification result knowledge graph, the description information of the verification failure corresponding to the node is displayed.

[0038] The graphical return and display technology of verification results has greatly improved the efficiency of fault identification and handling, allowing dispatchers to intuitively understand the root cause of the problem and take prompt action to ensure stable operation of the power grid.

[0039] In this embodiment, significant technical improvements have been achieved in multiple aspects, including the construction of a dispatching error prevention knowledge graph, rule processing, real-time information extraction, intelligent verification, and result visualization, providing strong technical support for the intelligent management and safe operation of the power system.

[0040] An embodiment of the present application provides a method for preventing miscalibration of power equipment. The method in this embodiment can be applied to servers, terminal devices, platforms, devices, etc. with computing and processing capabilities, wherein the server can be a server cluster or a single server, a server deployed in the cloud, or a local server.

[0041] like Figure 2 The flowchart of the method for preventing miscalibration of electric power equipment according to an embodiment of the present application is shown, comprising:

[0042] Step S201, obtaining the operation ticket to be verified and the dispatch error prevention knowledge graph of the power equipment; the dispatch error prevention knowledge graph is generated based on the physical topology structure, status data and operation rules of the power equipment.

[0043] The operation ticket refers to the document for electrical operation in the power system, including dispatching instruction ticket and substation operation ticket, etc. The operation ticket to be verified can be an operation ticket received online in real time, or a stored but unverified operation ticket.

[0044] Step S202, extracting events from the operation ticket to be checked to obtain the task events to be checked.

[0045] Among them, the task event corresponds to the operation task in the operation ticket, the task event contains multiple operation events, and the operation event corresponds to the operation details in the operation ticket. An operation ticket can correspond to one task event and multiple operation events, and the operation events are in a time sequence relationship.

[0046] Step S203, based on the scheduling error prevention knowledge graph, determine the error prevention verification rules corresponding to the task event.

[0047] The nodes of the dispatch error prevention knowledge graph are entities, such as power equipment, stations, etc. The edges of the dispatch error prevention knowledge graph are the relationships between entities, such as connection, dependency, trigger, etc. The error prevention verification rules are the operational constraints that need to be followed for the safe operation of equipment in the power grid.

[0048] Step S204, performing an anti-error check on the operation ticket according to the anti-error check rules.

[0049] The purpose of error-proof verification is to ensure the safe operation of the equipment and avoid operations that may lead to serious consequences, such as mistakenly opening and closing switches, mistakenly entering live intervals, and mistakenly operating relay protection devices.

[0050] The method for preventing errors in the verification of electric power equipment provided in the embodiment of the present application first obtains the operation ticket to be verified and the dispatching error prevention knowledge graph of the electric power equipment; the dispatching error prevention knowledge graph is generated based on the physical topology structure, state data and operation rules of the electric power equipment; then, the operation ticket to be verified is subjected to event extraction to obtain the task event to be verified; based on the dispatching error prevention knowledge graph, the error prevention verification rules corresponding to the task event are determined; finally, according to the error prevention verification rules, the operation ticket is subjected to error prevention verification. In the embodiment of the present application, by extracting events from the operation ticket and determining the error prevention verification rules corresponding to the task event based on the dispatching error prevention knowledge graph for error prevention verification, the burden of manual review can be reduced and the efficiency of error prevention verification can be improved. Among them, the dispatching error prevention knowledge graph is generated based on the physical topology structure, state data and operation rules of the electric power equipment, which can realize a multi-dimensional and refined description of the power grid, thereby improving the accuracy of the error prevention verification of the operation ticket.

[0051] The following introduces the specific implementation process of the above steps through multiple implementation methods:

[0052] In one implementation, obtaining a dispatch error prevention knowledge graph includes: calling a pre-generated dispatch error prevention knowledge graph; or generating a structural knowledge graph based on the physical topology of the power equipment; generating a state knowledge graph based on the state data of the power equipment; generating a rule knowledge graph based on the operation rules of the power equipment; and fusing the structural knowledge graph, the state knowledge graph, and the rule knowledge graph to obtain a dispatch error prevention knowledge graph.

[0053] Optionally, a dispatch error prevention knowledge graph may be generated offline in advance and stored, and when verifying the operation ticket, the pre-stored dispatch error prevention knowledge graph may be called for verification.

[0054] Optionally, a scheduling error prevention knowledge graph can also be generated in real time for use in operation ticket verification.

[0055] Among them, the structural knowledge graph focuses on the physical architecture, including but not limited to key components such as substations, transmission lines, busbars, transformers and their connections, providing a clear visual and logical framework for the static structure of the power network. For example, the triples that constitute the structural knowledge graph are: power equipment 1-connection relationship-power equipment 2. The rule knowledge graph focuses on specifications and standards, covering operating procedures, safety specifications, equipment operation rules, etc. These rules guide the daily operation and maintenance and exception handling of the power system to ensure that the system operates in accordance with national and industry standards. For example, the triples that constitute the rule knowledge graph are: power equipment-rule type-specific rules. The state knowledge graph involves real-time state information and historical state information, such as equipment health status, load level, fault records, etc., providing data support for state monitoring, performance evaluation and fault prediction of the power system. For example, the triples that constitute the state knowledge graph are: power equipment-equipment state-state value.

[0056] The process of integrating knowledge graphs from multiple sources or different types into a unified and coordinated graph system aims to improve the comprehensiveness, consistency and availability of information by integrating knowledge from different fields. In view of the complexity of the power system, the structural knowledge graph, rule knowledge graph and state knowledge graph constructed separately have different focuses, but they complement each other. The integration of these graphs can provide more comprehensive support for the operation, maintenance and optimization decision-making of the power system.

[0057] The fused dispatch error prevention knowledge graph can support multi-level and multi-dimensional query and analysis functions, such as joint analysis of grid vulnerability based on topological structure and status data, or prediction of potential fault points based on operating rules and status. Through the heterogeneous fusion of knowledge graphs, not only can a comprehensive and in-depth understanding and management of the power system be achieved, but also powerful data support can be provided for advanced applications such as intelligent decision support, fault prevention, and resource optimization and allocation, greatly improving the operating efficiency and safety of the power system.

[0058] In one implementation, a structural knowledge graph is generated based on the physical topology of the power equipment, including: determining multiple ontology object subgraphs based on the wiring methods and types of power equipment between different power equipment in the power system; matching the multiple ontology object subgraphs in the physical topology graph to determine successfully matched ontology object subgraphs; generating nodes corresponding to successfully matched ontology object subgraphs, and generating a structural knowledge graph based on the nodes corresponding to the multiple successfully matched ontology object subgraphs and the connection relationships between the nodes.

[0059] In practical applications, by parsing CIM, the schema-free graph structure is extracted to represent the electrical connection relationship, voltage relationship, site and status attributes of the devices in the power grid, that is, the physical topology of the power equipment.

[0060] The physical topology is used as the underlying structure, and the ontology object subgraph is used as the upper structure. The ontology object subgraph is determined according to the wiring modes and types of different power equipment in the power system, wherein the power equipment types include: AC equipment type, DC equipment type, etc. The ontology object subgraph can be a graph structure object, for example, it can include multiple objects associated with entities in the power system, for example, the ontology object subgraph can be a switch unit structure, specifically including: ground switch-switch-switch-switch-ground switch.

[0061] For example, the VF2 algorithm is used to perform hierarchical matching of the ontology object subgraph on the physical topology structure, determine all possible positions of the ontology object subgraph in the physical topology structure, update the successfully matched ontology object subgraph on the physical topology structure, generate nodes corresponding to the ontology object subgraph, and the nodes corresponding to the ontology object subgraph are upper-level nodes. Based on the upper-level nodes, the nodes of the next level are obtained, and the connection relationship between the nodes is determined according to the connection relationship in the physical topology structure. Through the accumulation of multi-level nodes, the structural knowledge graph is obtained. In the related art, when constructing the upper structure of the knowledge graph, direct matching and analysis are performed based on graph isomorphism. This type of method does not take into account the different wiring methods of power equipment or the existence of similar structures between power equipment types, which leads to matching confusion errors, and is not feasible in practical applications.

[0062] In this embodiment, when constructing the upper structure of the structural knowledge graph, the graph isomorphism algorithm is improved, and a set of common graph structure objects, namely, ontology object subgraphs, are designed for different wiring modes of power equipment, AC equipment types, DC equipment types, etc. A deep traversal is performed in the physical topology graph, and multiple ontology object subgraphs are matched in the physical topology graph. Fast and accurate matching is achieved based on the improved graph isomorphism algorithm (for example, the graph isomorphism algorithm VF2 algorithm is improved, and the ontology object subgraph is used for matching and analysis), which can quickly achieve expansion and generalization.

[0063] In one implementation, events are extracted from the operation ticket to be verified to obtain the task event to be verified, including: using a trigger word extraction model to obtain event trigger words from the operation ticket to be verified; using an argument extraction model to obtain multiple event component elements corresponding to the operation ticket to be verified based on the operation ticket to be verified and the event trigger words; and combining multiple event component elements to obtain the task event.

[0064] In practical applications, the pre-trained text extraction model is further trained using the operation ticket data in the power field as training samples to obtain a trained text extraction model that is more suitable for the task requirements of the power scene. The pre-trained text extraction model can be implemented using the bidirectional encoder representations from transformer (BERT) model.

[0065] The purpose of trigger word extraction is to predict the words that trigger the task event. The trigger word extraction model is used for multi-category classification tasks at the word level, and the classification label is the event type. Adding a multi-classifier to the trained text extraction model constitutes a trigger word extraction model. The input data of the trigger word extraction model is the text features extracted based on the text data in the operation ticket. In a specific embodiment, the specific form of the text features can be: the sum of tag embedding, position embedding and paragraph embedding. If there is only one sentence in the input, the paragraph number is set to 0, and the beginning and end of the sentence are the symbols [CLS] and [SEP] respectively. [CLS] indicates that the text feature is used for classification tasks, and [SEP] represents a sentence symbol used to separate two sentences in the input text.

[0066] The argument extraction model is used to extract event arguments (i.e., event components) related to the event corresponding to the trigger word, as well as the roles corresponding to these event arguments, for example, the role is an entity or a connection relationship, and the entity can be an electric device, etc. Similar to the trigger word extraction model, the argument extraction model also requires the sum of tag embedding, position embedding, and paragraph embedding as input data, but it is also necessary to know which words constitute the trigger word. Therefore, the position of the trigger word is set to a preset value, for example, set to 1. The argument extraction model can be specifically added to the trained text extraction model. Multiple groups of binary classifiers are used to judge the probability of each event argument belonging to all types of roles. Each group of binary classifiers serves a role to determine the start and end ranges of all event arguments belonging to the role. Different event arguments can be combined to obtain different task events.

[0067] In the related art, static text representation and fixed dictionaries are used to process the operation instructions in the operation ticket, which limits the adaptability to new vocabulary and expressions.

[0068] In the embodiment of the present application, by introducing a pre-trained text extraction model and training it with data from the power field, the flexibility and accuracy in processing power professional terms and understanding new operation commands are significantly improved, ensuring that the model can better understand the language characteristics of the power field. At the same time, a deep understanding and refined extraction of the operation ticket text is achieved, and the operation events and their arguments can be accurately identified, which improves the accuracy and generalization of information extraction. It supports a wider range of operation command sentences and expressions, reduces manual intervention, and improves processing efficiency and automation level.

[0069] In one implementation, based on the scheduling error prevention knowledge graph, the error prevention verification rules corresponding to the task event are determined, including: determining the task entity corresponding to the task event in the node of the scheduling error prevention knowledge graph, and obtaining the target equipment subgraph corresponding to the task entity; the scheduling error prevention knowledge graph includes the target equipment subgraph; based on the nodes of the target equipment subgraph, the operating rules of the target power equipment are obtained as the error prevention verification rules corresponding to the task event.

[0070] Among them, the target device subgraph refers to a part of the scheduling error prevention knowledge graph, which corresponds to the task entity corresponding to the task event.

[0071] For example, if the task event is "pull open the 5021 switch of AA station", the task entity corresponding to the task event is "AA station". Find "AA station" in the node of the scheduling error prevention knowledge graph, obtain the equipment subgraph corresponding to "AA station", that is, the target equipment subgraph, locate the 5021 switch in the node of the target equipment subgraph, and find the operational constraints behind the 2 / 3 wiring of the 5021 switch equipment structure, such as the need to follow "pull open the 5022 switch first, then pull open the 5021 switch".

[0072] In one implementation, the operation ticket is checked for errors according to the error-checking rules, including: recursively parsing the error-checking rules according to the target equipment sub-map to obtain the status data and operating rules of the target power equipment corresponding to the task event; and checking the operation ticket for errors according to the status data and operating rules of the target power equipment.

[0073] In actual applications, after obtaining the target equipment sub-map, a recursive algorithm is used to recursively parse the error-prevention verification rules corresponding to the task events to obtain the status data and operation rules of each target power equipment in the target equipment sub-map, and the task events in the operation ticket are verified against errors using the status data and operation rules.

[0074] It is understandable that the verification of the operation ticket needs to rely on error prevention rules, which are related to the wiring method and topology of the power grid.

[0075] In a related technology, the error prevention rules corresponding to each device are set by hard-coding. This method has problems such as non-replicability and promotion, large configuration workload, inability to automatically update the rules as the service develops, and difficulty in adapting to complex rule scenarios.

[0076] When parsing rules, a related technology relies on regular matching and template matching to parse the rules. This method is prone to omissions and false positives when faced with complex and changing rule scenarios, and has poor scalability.

[0077] In this embodiment, the scheduling error prevention knowledge graph based on the hierarchical topology structure is combined with the recursive algorithm for rule parsing, which can flexibly deal with the diversity and complexity of the rules. Through automatic parsing and verification, the workload of manually configuring rules is significantly reduced, the system's adaptive ability and real-time performance are enhanced, and the continuous effectiveness and accuracy of the rules are ensured as the service develops.

[0078] In one implementation, the operation ticket is checked for errors based on the status data and operating rules of the target power equipment, including: performing simulation and deduction in the error prevention knowledge graph according to the status data and operating rules of the target power equipment to obtain simulation and deduction results; and determining the error prevention and verification results of the operation ticket based on the simulation and deduction results.

[0079] In actual applications, according to the status data and operating rules of the target power equipment, the logical path of the operation ticket execution is simulated on the dispatch error prevention knowledge graph, and the simulation is performed in combination with the real-time status data, that is, the execution result of the operation ticket is inferred instead of the actual execution of the operation ticket, avoiding the risk of the actual execution of the operation ticket, realizing the intelligent upgrade of the operation ticket error prevention verification, and significantly reducing the operation risk. If the simulation result is safe, that is, the operation ticket verification is passed, the operation ticket can be actually executed.

[0080] In one implementation, the method for preventing miscalibration of power equipment also includes: when the miscalibration result indicates that the calibration has failed, determining the power equipment that has failed the calibration and the operating rules that have failed the calibration; visualizing the power equipment that has failed the calibration and the operating rules that have failed the calibration to obtain a knowledge graph of the calibration results.

[0081] In actual applications, for devices that fail the verification, the operating rules that they violated will be returned. Using knowledge graph technology, the failed entities and relationships are presented in the form of nodes and edges to obtain the verification result knowledge graph. Each node represents an entity (such as equipment, code module, data record, etc.), and the edge represents the relationship between them, such as dependency, influence, trigger, etc. In the verification result knowledge graph, the problem nodes can be marked with different colors, size changes or special icons to intuitively indicate the error location and severity.

[0082] In this embodiment, the verification result mapping technology is used to convert complex error prevention verification results into intuitive graphical representations, which is extremely valuable when verifying large-scale systems or data sets. When the error prevention verification fails, the problem can be displayed intuitively, and the full picture and root cause of the error can be displayed through highly correlated graphs, greatly improving the efficiency of problem diagnosis and resolution.

[0083] In one implementation, the method for preventing miscalibration of electric power equipment further includes: in response to a trigger operation on a node of the calibration result knowledge graph, displaying descriptive information of the node corresponding to the failed calibration.

[0084] The trigger operation can be a click operation, including but not limited to: single click, double click, right click, etc. Users can interactively browse the verification result knowledge graph, click any node to obtain a detailed error description, locate the root cause of the problem, and check whether it is an error operation. This method can not only speed up the error identification speed, but also improve the efficiency of the dispatcher in diagnosing problems and intuitively locate the problem. The verification result knowledge graph greatly enhances the accuracy and timeliness of troubleshooting by converting abstract verification feedback into an intuitive graphical view.

[0085] An embodiment of the present application provides a method for preventing miscalibration of power equipment. The method in this embodiment can be applied to servers, terminal devices, platforms, devices, etc. with computing and processing capabilities, wherein the server can be a server cluster or a single server, a server deployed in the cloud, or a local server.

[0086] like Figure 3 The flowchart of the method for preventing miscalibration of electric power equipment according to an embodiment of the present application is shown, comprising:

[0087] Step S301, obtaining the operation ticket of the power equipment to be verified.

[0088] The operation ticket refers to the document for electrical operation in the power system, including dispatching instruction ticket and substation operation ticket, etc. The operation ticket to be verified can be an operation ticket received online in real time, or a stored but unverified operation ticket.

[0089] Step S302, obtaining a scheduling error prevention knowledge graph.

[0090] Specifically, a structural knowledge graph is generated based on the physical topological structure of the power equipment; a state knowledge graph is generated based on the state data of the power equipment; a rule knowledge graph is generated based on the operation rules of the power equipment; the structural knowledge graph, the state knowledge graph and the rule knowledge graph are integrated to obtain a scheduling error prevention knowledge graph.

[0091] Among them, a structural knowledge graph is generated according to the physical topological structure of the power equipment, specifically including: determining multiple ontology object subgraphs according to the equipment wiring method type and equipment type in the power system; matching the multiple ontology object subgraphs in the physical topological graph to determine the successfully matched ontology object subgraph; generating device attribute nodes and device wiring method nodes corresponding to the successfully matched ontology object subgraph, and generating a structural knowledge graph according to the device attribute nodes and device wiring method nodes corresponding to the multiple successfully matched ontology object subgraphs.

[0092] Step S303: using a trigger word extraction model to obtain event trigger words from the operation ticket to be checked.

[0093] The purpose of trigger word extraction is to predict the words that trigger the task event. The trigger word extraction model is used for multi-category classification tasks at the word level, and the classification label is the event type. Adding a multi-classifier to the trained text extraction model constitutes the trigger word extraction model.

[0094] Step S304, using the argument extraction model, according to the operation ticket to be checked and the event trigger word, obtain multiple event arguments corresponding to the operation ticket to be checked.

[0095] The argument extraction model is used to extract event arguments (i.e. event components) related to the event corresponding to the trigger word, as well as the roles corresponding to these event arguments. For example, the role is an entity or a connection relationship, and the entity can be an electric device, etc. Similar to the trigger word extraction model, the argument extraction model also requires the sum of tag embedding, position embedding, and paragraph embedding as input data, but it is also necessary to know which words constitute the trigger word. Therefore, the position of the trigger word is set to a preset value, for example, set to 1. The argument extraction model can be specifically a trained text extraction model with multiple groups of binary classifiers added to it, and the binary classifiers are used to judge the probability of each event argument belonging to all types of roles. Each group of binary classifiers serves a role to determine the start and end ranges of all event arguments belonging to the role.

[0096] Step S305, combining multiple event arguments to obtain a task event.

[0097] Step S306, determine the task entity corresponding to the task event in the node of the scheduling error prevention knowledge graph, and obtain the target equipment subgraph corresponding to the task entity; obtain the operation rules of the target power equipment based on the nodes of the target equipment subgraph as the error prevention verification rules corresponding to the task event.

[0098] Step S307 , recursively parse the error prevention check rule according to the target equipment sub-graph to obtain the state data and operation rules of the target power equipment corresponding to the task event.

[0099] Among them, the target device subgraph refers to a part of the scheduling error prevention knowledge graph, which corresponds to the task entity corresponding to the task event.

[0100] In actual applications, after obtaining the target equipment sub-map, a recursive algorithm is used to recursively parse the error-prevention verification rules corresponding to the task events to obtain the status data and operation rules of each target power equipment in the target equipment sub-map, and the task events in the operation ticket are verified against errors using the status data and operation rules.

[0101] Step S308, according to the state data and operation rules of the target power equipment, simulation is performed in the error prevention knowledge graph to obtain the simulation result; based on the simulation result, the error prevention verification result of the operation ticket is determined.

[0102] In actual applications, based on the status data and operating rules of the target power equipment, by simulating the logical path of the operation ticket execution on the dispatching error prevention knowledge graph and combining it with real-time status data for simulation and deduction, the intelligent upgrade of the operation ticket error prevention verification is realized, which significantly reduces the operational risks.

[0103] Step S309, when the anti-miscalibration result indicates that the calibration has failed, determine the power equipment that has failed the calibration and the operating rules that have failed the calibration; visualize the power equipment that has failed the calibration and the operating rules that have failed the calibration to obtain a calibration result knowledge graph.

[0104] In actual applications, for devices that fail the verification, the operating rules that they violated will be returned. Using knowledge graph technology, the failed entities and relationships are presented in the form of nodes and edges to obtain the verification result knowledge graph. Each node represents an entity (such as equipment, code module, data record, etc.), and the edge represents the relationship between them, such as dependency, influence, trigger, etc. In the verification result knowledge graph, the problem nodes can be marked with different colors, size changes or special icons to intuitively indicate the error location and severity.

[0105] Step S310, in response to a trigger operation on a node of the verification result knowledge graph, display the description information of the node corresponding to the node that failed the verification.

[0106] The trigger operation can be a click operation, including but not limited to: single click, double click, right click, etc. Users can interactively browse the verification result knowledge graph, click any node to obtain a detailed error description, locate the root cause of the problem, and check whether it is an error operation. This method can not only speed up the error identification speed, but also improve the efficiency of the dispatcher in diagnosing problems and intuitively locate the problem. The verification result knowledge graph greatly enhances the accuracy and timeliness of troubleshooting by converting abstract verification feedback into an intuitive graphical view.

[0107] Corresponding to the application scenario and method of the method provided in the embodiment of the present application, the embodiment of the present application also provides an anti-error calibration device for electric power equipment. Figure 4 The figure is a structural block diagram of a device for preventing miscalibration of electric power equipment according to an embodiment of the present application, the device comprising:

[0108] The acquisition module 401 is used to obtain the operation ticket to be verified and the dispatch error prevention knowledge graph of the power equipment; the dispatch error prevention knowledge graph is generated based on the physical topology structure, status data and operation rules of the power equipment.

[0109] The extraction module 402 is used to extract events from the operation ticket to be checked to obtain the task events to be checked.

[0110] The determination module 403 is used to determine the error prevention verification rules corresponding to the task event based on the scheduling error prevention knowledge graph.

[0111] The verification module 404 is used to perform error-proof verification on the operation ticket according to error-proof verification rules.

[0112] The anti-error verification device for electric power equipment provided in the embodiment of the present application first obtains the operation ticket to be verified and the dispatching anti-error knowledge graph of the electric power equipment; the dispatching anti-error knowledge graph is generated based on the physical topology structure, state data and operation rules of the electric power equipment; then, the operation ticket to be verified is subjected to event extraction to obtain the task event to be verified; based on the dispatching anti-error knowledge graph, the anti-error verification rule corresponding to the task event is determined; finally, according to the anti-error verification rule, the operation ticket is subjected to anti-error verification. In the embodiment of the present application, by extracting events from the operation ticket and determining the anti-error verification rule corresponding to the task event based on the dispatching anti-error knowledge graph for anti-error verification, the burden of manual review can be reduced and the efficiency of anti-error verification can be improved. Among them, the dispatching anti-error knowledge graph is generated based on the physical topology structure, state data and operation rules of the electric power equipment, which can realize a multi-dimensional and refined description of the power grid, thereby improving the accuracy of the anti-error verification of the operation ticket.

[0113] In one implementation, the acquisition module 401 is specifically used to: call a pre-generated scheduling error prevention knowledge graph; or generate a structural knowledge graph based on the physical topology of the power equipment; generate a state knowledge graph based on the state data of the power equipment; generate a rule knowledge graph based on the operating rules of the power equipment; and fuse the structural knowledge graph, the state knowledge graph, and the rule knowledge graph to obtain a scheduling error prevention knowledge graph.

[0114] In one implementation, when the acquisition module 401 generates a structural knowledge graph based on the physical topology of the power equipment, it is used to: determine multiple ontology object subgraphs based on the wiring methods and power equipment types between different power equipment in the power system; match the multiple ontology object subgraphs in the physical topology graph to determine the successfully matched ontology object subgraphs; generate nodes corresponding to the successfully matched ontology object subgraphs, and generate a structural knowledge graph based on the nodes corresponding to the multiple successfully matched ontology object subgraphs and the connection relationship between the nodes.

[0115] In one implementation, the extraction module 402 is used to: use a trigger word extraction model to obtain event trigger words from the operation ticket to be verified; use an argument extraction model to obtain multiple event component elements corresponding to the operation ticket to be verified based on the operation ticket to be verified and the event trigger words; combine multiple event component elements to obtain a task event.

[0116] In one implementation, the determination module 403 is used to: determine the task entity corresponding to the task event in the node of the scheduling error prevention knowledge graph, and obtain the target equipment subgraph corresponding to the task entity; the scheduling error prevention knowledge graph includes the target equipment subgraph; based on the nodes of the target equipment subgraph, obtain the operating rules of the target power equipment as the error prevention verification rules corresponding to the task event.

[0117] In one implementation, the verification module 404 is used to: recursively parse the error prevention verification rules according to the target equipment sub-map to obtain the status data and operation rules of the target power equipment corresponding to the task event; and perform error prevention verification on the operation ticket according to the status data and operation rules of the target power equipment.

[0118] In one implementation, when the verification module 404 performs error prevention verification on the operation ticket according to the status data and operating rules of the target power equipment, it is used to: perform simulation deduction in the error prevention knowledge graph according to the status data and operating rules of the target power equipment to obtain simulation deduction results; and determine the error prevention verification results of the operation ticket based on the simulation deduction results.

[0119] In one implementation, the power equipment anti-miscalibration device is also used to: when the anti-miscalibration result indicates that the calibration has failed, determine the power equipment that has failed the calibration and the operating rules that have failed the calibration; visualize the power equipment that has failed the calibration and the operating rules that have failed the calibration to obtain a knowledge graph of the calibration results.

[0120] In one implementation, the device for preventing miscalibration of electric power equipment is also used to: in response to a trigger operation on a node of the calibration result knowledge graph, display descriptive information of the node corresponding to the failed calibration.

[0121] The functions of each module in the embodiment of the present application can be referred to the corresponding description in the above method, and have corresponding beneficial effects, which will not be repeated here.

[0122] Figure 5 FIG. 1 is a block diagram of an electronic device used to implement an embodiment of the present application. Figure 5 As shown, the electronic device includes: a memory 510 and a processor 520. The memory 510 stores a computer program that can be run on the processor 520. When the processor 520 executes the computer program, the method in the above embodiment is implemented. The number of the memory 510 and the processor 520 can be one or more.

[0123] The electronic device also includes:

[0124] The communication interface 530 is used to communicate with external devices and perform data exchange transmission.

[0125] If the memory 510, the processor 520 and the communication interface 530 are implemented independently, the memory 510, the processor 520 and the communication interface 530 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0126] Optionally, in a specific implementation, if the memory 510, the processor 520 and the communication interface 530 are integrated on a chip, the memory 510, the processor 520 and the communication interface 530 can communicate with each other through an internal interface.

[0127] An embodiment of the present application provides a computer-readable storage medium storing a computer program, which implements the method provided in the embodiment of the present application when the program is executed by a processor.

[0128] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method provided in the embodiment of the present application is implemented.

[0129] An embodiment of the present application also provides a chip, which includes a processor for calling and executing instructions stored in the memory from the memory, so that a communication device equipped with the chip executes the method provided by the embodiment of the present application.

[0130] An embodiment of the present application also provides a chip, including: an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected via an internal connection path, and the processor is used to execute the code in the memory. When the code is executed, the processor is used to execute the method provided in the embodiment of the application.

[0131] It should be understood that the above processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor that supports the Advanced RISC Machines (ARM) architecture.

[0132] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of exemplary but not limiting description, many forms of RAM are available. For example, static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (DR RAM).

[0133] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0134] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0135] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0136] Any process or method described in the flow chart or otherwise described herein can be understood as a module, fragment or portion of a code representing one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0137] The logic and / or steps described in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0138] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0139] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.

[0140] The above is only an exemplary embodiment of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope recorded in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for preventing miscalibration of electric power equipment, characterized in that: include: Obtain the operation tickets to be verified and the knowledge graph for preventing scheduling errors of power equipment; The scheduling error prevention knowledge graph is generated based on the physical topology, status data and operation rules of the power equipment; Extracting events from the operation ticket to be verified to obtain task events to be verified; Determine the error prevention verification rule corresponding to the task event based on the scheduling error prevention knowledge graph; According to the error-proofing check rule, the operation ticket is checked for errors; The step of extracting events from the operation ticket to be verified to obtain the task event to be verified includes: Using a trigger word extraction model to obtain event trigger words from the operation ticket to be checked; Using an argument extraction model, according to the operation ticket to be checked and the event trigger word, a plurality of event component elements corresponding to the operation ticket to be checked are obtained; The multiple event constituent elements are combined to obtain the task event.

2. The method according to claim 1, characterized in that The step of obtaining a scheduling error prevention knowledge graph includes: Calling the pre-generated scheduling error prevention knowledge graph; or Generate a structural knowledge graph based on the physical topology of the power equipment; Generate a state knowledge graph based on the state data of the power equipment; Generate rule knowledge graph based on the operation rules of power equipment; The structure knowledge graph, the state knowledge graph and the rule knowledge graph are integrated to obtain the scheduling error prevention knowledge graph.

3. The method according to claim 2, characterized in that The generating of a structural knowledge graph according to the physical topological structure of the power equipment includes: According to the wiring mode and the type of power equipment between different power equipment in the power system, a plurality of ontology object subgraphs are determined; Matching the multiple ontology object subgraphs in the physical topology graph to determine a successfully matched ontology object subgraph; Generate the nodes corresponding to the successfully matched ontology object subgraphs, and generate the structural knowledge graph according to the nodes corresponding to the multiple successfully matched ontology object subgraphs and the connection relationships between the nodes.

4. The method according to any one of claims 1 to 3, characterized in that: The step of determining the error prevention verification rule corresponding to the task event based on the scheduling error prevention knowledge graph includes: Determine the task entity corresponding to the task event in the node of the scheduling error prevention knowledge graph, and obtain the target device subgraph corresponding to the task entity; the scheduling error prevention knowledge graph includes the target device subgraph; Based on the nodes of the target device subgraph, the operation rules of the target power equipment are obtained as the error prevention verification rules corresponding to the task event.

5. The method according to claim 4, characterized in that The step of performing error-proofing on the operation ticket according to the error-proofing checking rule comprises: Recursively parsing the error prevention check rule according to the target device subgraph to obtain the state data and operation rules of the target power device corresponding to the task event; The operation ticket is checked to prevent errors according to the status data of the target power equipment and the operation rules.

6. The method according to claim 5, characterized in that The step of performing error prevention check on the operation ticket according to the status data of the target power equipment and the operation rules comprises: According to the state data of the target power equipment and the operation rules, simulation deduction is performed in the error prevention knowledge graph to obtain simulation deduction results; Based on the simulation results, the error-proof verification result of the operation ticket is determined.

7. The method according to claim 6, characterized in that The method further comprises: When the error prevention check result indicates that the check has not passed, determining the power equipment that has not passed the check and the operation rules that have not passed the check; The power equipment that failed the verification and the operating rules that failed the verification are visualized to obtain a verification result knowledge graph.

8. The method according to claim 7, characterized in that The method further comprises: In response to a trigger operation on a node of the verification result knowledge graph, descriptive information of the node corresponding to the failed verification is displayed.

9. An electronic device, characterized in that: The electronic device comprises a memory, a processor and a computer program stored in the memory, and the processor implements the method according to any one of claims 1 to 8 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

11. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images