Operation ticket automatic generation method, electronic device, storage medium, and program product

Abstract

Embodiments of the present application provide an operation ticket automatic generation method, an electronic device, a storage medium and a program product, and relate to the field of smart grids. The method comprises: obtaining an operation ticket generation request; generating a process operation ticket corresponding to a maintenance task based on a task type; updating the process operation ticket based on a historical operation ticket with the highest matching degree and the latest execution time obtained, a device association graph, an operation template and real-time state data; inputting the updated process operation ticket into an optimization model to obtain a target operation ticket; and outputting the target operation ticket. The method is used to improve the accuracy of generated operation tickets.

Description

Technical Field

[0001] This application relates to the field of smart grids, and in particular to a method for automatically generating operation tickets, electronic equipment, storage medium, and program products. Background Technology

[0002] Automatic operation ticket generation technology is an important research direction for improving operation and maintenance efficiency and operational safety in power systems. Its core lies in replacing the traditional manual creation of operation tickets with intelligent methods, ensuring the rigor of operational logic and the accuracy of execution through a systematic approach. This technology has broad application prospects, especially in the operation of complex systems, where it can significantly reduce the risk of human error.

[0003] Existing methods for generating operation tickets mainly rely on domain experts to build an operation rule base, combined with equipment topology models and real-time status data to generate operation tickets.

[0004] However, rule-based methods rely heavily on the completeness of expert experience and are difficult to cover boundary conditions such as extreme working conditions or equipment failures. Machine learning models are limited by the quality of training data and have insufficient generalization ability for abnormal states or new equipment operations that have not appeared in historical data. Therefore, existing technologies have the technical problem of poor accuracy in automatically generating operation tickets. Summary of the Invention

[0005] This application provides an automatic operation ticket generation method, electronic device, storage medium, and program product to improve the accuracy of operation ticket generation.

[0006] In a first aspect, embodiments of this application provide a method for automatically generating operation tickets, including:

[0007] Obtain the operation ticket generation request; the operation ticket generation request must include at least the maintenance task and the corresponding task type.

[0008] Based on the task type, generate a process operation ticket corresponding to the maintenance task; the process operation ticket shall at least include the operation time and operation method of the maintenance task.

[0009] Based on the historical operation tickets, equipment association diagrams, operation templates, and real-time status data that best match the maintenance task and have the latest execution time, update the process operation tickets;

[0010] Input the updated process operation ticket into the optimization model to obtain the target operation ticket;

[0011] Output the target operation ticket.

[0012] One possible implementation involves generating a process operation ticket corresponding to the maintenance task based on the task type, including:

[0013] When the task type is planned maintenance, based on the acquired real-time measurement data, a power grid knowledge graph and a matrix of five-prevention interlocking relationships between equipment entities are constructed using the historical operation tickets and order management system method sheets corresponding to the maintenance task.

[0014] Based on the power grid knowledge graph and the five-prevention interlocking relationship matrix, a process operation ticket is generated after performing time window overlay analysis on the maintenance task.

[0015] One possible implementation involves generating a process operation ticket corresponding to the maintenance task based on the task type, including:

[0016] When the task type is unplanned maintenance, obtain the processing scenario keywords corresponding to the maintenance task;

[0017] Based on the processing scenario keywords, process operation tickets are generated.

[0018] In one possible implementation, the optimization model is a mathematical model used to optimize the operation time and operation method in the process operation ticket. The training process of the optimization model includes:

[0019] Obtain device feature vectors and operational context;

[0020] The structural features of the power grid topology are determined based on the device feature vectors, and the operation sequence is determined based on the operation context.

[0021] Construct a multi-objective collaborative optimization loss function, which includes an order rationality loss function with different weight coefficients, a security constraint loss function, and a term matching loss function;

[0022] The optimization model is trained based on the multi-objective collaborative optimization loss function.

[0023] In one possible implementation, after optimizing the operation time and method of the maintenance task to obtain the target operation ticket, the method further includes:

[0024] The target operation ticket is simulated based on the digital twin system corresponding to the power grid, and the simulation results are obtained;

[0025] If the simulation results meet the preset verification system, the target operation ticket will be output;

[0026] If the simulation results do not conform to the preset verification system, process operation tickets corresponding to the maintenance tasks will be generated based on the task type until the simulation results conform to the preset verification system.

[0027] In one possible implementation, the verification dimensions of the pre-defined verification system include: grammatical compliance, topological security, and transient stability.

[0028] Secondly, embodiments of this application provide an automatic operation ticket generation device, comprising:

[0029] The acquisition module is used to acquire operation ticket generation requests; the operation ticket generation request must include at least the maintenance task and the task type corresponding to the maintenance task.

[0030] The generation module is used to generate process operation tickets corresponding to maintenance tasks based on task types; the process operation ticket shall include at least the operation time and operation method of the maintenance task.

[0031] The optimization module is used to update the process operation ticket based on the historical operation tickets, equipment association diagrams, operation templates, and real-time status data that have the highest matching degree with the maintenance task and the latest execution time.

[0032] The optimization module is also used to input the updated process operation ticket into the optimization model to obtain the target operation ticket;

[0033] The output module is used to output the target operation ticket.

[0034] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0035] The memory stores computer-executed instructions;

[0036] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0037] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0038] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0039] The operation ticket automatic generation method, electronic device, storage medium, and program product provided in this application receive operation ticket generation requests, intelligently analyze the maintenance tasks and corresponding task types in the requests, identify the task types and associated equipment objects, and based on the identified task types, automatically trigger the association rule base in the knowledge graph to dynamically generate a process operation ticket containing a complete operation chain. After generating the initial operation ticket, the operation time and method are intelligently adjusted to obtain the target operation ticket, which is then output to the user terminal. This method achieves the technical effect of improving the accuracy of operation ticket generation. Attached Figure Description

[0040] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0041] Figure 1 Flowchart of the method for automatically generating operation tickets provided in this application Figure 1 ;

[0042] Figure 2 Flowchart of the method for automatically generating operation tickets provided in this application Figure 2 ;

[0043] Figure 3 A schematic diagram of the automatic operation ticket generation device provided in this application;

[0044] Figure 4 A hardware schematic diagram of the automatic operation ticket generation device provided in this application.

[0045] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0046] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of methods and approaches consistent with some aspects of this application as detailed in the appended claims.

[0047] Based on the above scenarios, it can be seen that existing technologies for generating operation tickets mainly rely on two core elements: first, an operation rule base carefully constructed by domain experts, which is combined with equipment topology models and real-time status data; and second, the use of an inference engine to match rules and automatically generate operation tickets. In addition, machine learning methods are used to train and optimize the generated operation tickets. However, the rule-based approach has significant shortcomings. It heavily relies on the completeness and accuracy of expert experience; if expert experience is missing or biased, it is difficult to fully cover complex and special boundary conditions such as extreme operating conditions and equipment failures. On the other hand, while machine learning models possess a certain degree of intelligence, their performance is largely limited by the quality of the training data. When faced with abnormal states not seen in historical data or operating scenarios of new equipment, the generalization ability of machine learning models is insufficient, making it difficult to make accurate judgments and decisions. Therefore, existing automatic operation ticket generation technologies have significant accuracy issues.

[0048] Therefore, to address the technical problems existing in the prior art, this application provides an automatic operation ticket generation method, electronic device, storage medium, and program product. This method receives an operation ticket generation request, intelligently analyzes the maintenance task and corresponding task type in the request, identifies the task type and associated equipment objects, and based on the identified task type, automatically triggers the association rule base in the knowledge graph to dynamically generate a process operation ticket containing a complete operation chain. After generating the initial operation ticket, the operation time and method are intelligently adjusted to obtain the target operation ticket, which is then output to the user terminal. This method achieves the technical effect of improving the accuracy of operation ticket generation.

[0049] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0050] Figure 1 Flowchart of the method for automatically generating operation tickets provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0051] S101, Obtain the operation ticket generation request.

[0052] In this embodiment, the system receives an operation ticket generation request from the user terminal. The operation ticket generation request includes at least the maintenance task and the corresponding task type. The maintenance task specifies the work to be performed, and the task type classifies the maintenance task. Different types of tasks may have different processing logic and requirements when generating operation tickets in the future.

[0053] S102. Based on the task type, generate the process operation ticket corresponding to the maintenance task.

[0054] In this embodiment, based on the acquired task type, the system generates a process operation ticket corresponding to the maintenance task according to predefined rules or templates. The process operation ticket includes at least the operation time and operation method of the maintenance task; the operation time specifies when each operation step should be performed, and the operation method describes the specific method for performing that step.

[0055] S103. Update the process operation ticket based on the historical operation ticket, equipment association map, operation template and real-time status data that have the highest matching degree with the maintenance task and the latest execution time.

[0056] In this embodiment, the generated process operation ticket may not be optimal, therefore, the operation time and method of the maintenance task need to be optimized. Operation time optimization can consider factors such as avoiding peak grid load periods and rationally arranging the operation sequence to reduce power outage time; operation method optimization can select more efficient and safer operation methods based on equipment status and personnel skill levels. Through optimization, a target operation ticket that better meets actual needs can be obtained. Further optimization of the process operation ticket can greatly improve the accuracy of operation ticket generation.

[0057] In this embodiment, the process operation ticket is optimized and updated by retrieving the historical operation ticket with the highest matching degree and whose execution time is the most recent time, in order to prevent the format of the historical operation ticket from not meeting the current requirements. By comparing with the historical operation ticket, the abnormal operation records and anti-accident drill handling plans of the historical operation ticket are learned, and the documents involving scheduling writing rules in the power grid system are constantly updated in a timely manner to make correction measures for the process operation ticket.

[0058] Furthermore, the system retrieves the equipment association map related to the process operation ticket, and corrects and updates the equipment relationships involved in the process operation ticket using the equipment association map. For example, it updates the electrical connection relationships, protection coordination relationships, and power grid topology of the same equipment. At the same time, based on the operation method of the process operation ticket, it retrieves relevant typical operation templates, and updates the operation method of the process operation ticket according to the content of the typical operation templates. This includes, but is not limited to, the voltage difference verification steps before the transformer parallel operation is retrieved when the main transformer is shut down; the rules for relay protection, safety automatic setting sheets, soft / hard pressure plate strategies, and ledgers corresponding to different operation modes; and it acquires real-time dynamic environmental data, which refers to the current environmental data corresponding to the generated operation ticket generation task. The environmental data includes, but is not limited to, the status of power grid equipment, natural conditions, power grid load status, and power grid operation status. Based on the real-time environmental data, the system verifies the content of the process operation ticket, including but not limited to verifying the real-time power flow distribution, identifying the relay protection setting sheets being executed, the safety automatic device switching strategy, and the standby automatic transfer string strategy.

[0059] S104. Input the updated process operation ticket into the optimization model to obtain the target operation ticket.

[0060] In this embodiment, a structured input dataset is constructed by combining historical operation ticket data with real-time equipment status, environmental parameters, and other dynamic information. This dataset is then trained using optimization models such as supervised learning, reinforcement learning, or graph neural networks. The model learns operational logic, safety rules, and efficiency constraints from massive amounts of data, and iteratively optimizes key elements of the updated process operation ticket, such as the step sequence, equipment selection, and time window, ultimately generating a safer, more efficient target operation ticket that adapts to dynamic environments. Optionally, in power systems, the model can combine real-time grid load and weather data to automatically adjust the power outage sequence or recommend redundant switching schemes in the power outage maintenance process, while mitigating the risk of human error. This process not only relies on the model's feature extraction and constraint embedding capabilities but also requires a closed-loop feedback loop formed through simulation testing and manual review to continuously improve the reliability of the generated results, thereby promoting the transformation from traditional experience-based operation modes to data-driven intelligent operation modes.

[0061] S105, Output target operation ticket.

[0062] In this embodiment, the optimized target operation ticket needs to be output to the user terminal. The output method includes, but is not limited to, outputting in file form or in data interface form.

[0063] The automatic operation ticket generation method provided in this application receives an operation ticket generation request, intelligently analyzes the maintenance task and corresponding task type in the request, identifies the task type and associated equipment objects, and based on the identified task type, automatically triggers the association rule base in the knowledge graph to dynamically generate a process operation ticket containing a complete operation chain. After generating the initial operation ticket, the operation time and method are intelligently adjusted to obtain the target operation ticket, which is then output to the user terminal. This method achieves the technical effect of improving the accuracy of operation ticket generation.

[0064] Figure 2 Flowchart of the method for automatically generating operation tickets provided in this application Figure 2 ,like Figure 2 As shown, in this embodiment... Figure 1 Based on the embodiments, the automatic generation method of operation tickets is described in detail. Specifically, generating corresponding process operation tickets according to different task types can be achieved through steps S202 to S203; optimizing the process operation tickets can be achieved through step S204; and verifying the target operation ticket after obtaining it can be achieved through step S205. The method includes:

[0065] S201. Obtain the operation ticket generation request; the operation ticket generation request shall include at least the maintenance task and the task type corresponding to the maintenance task.

[0066] S202. Based on the task type, generate the process operation ticket corresponding to the maintenance task; when the task type is planned maintenance, based on the acquired real-time measurement data, construct the five-prevention interlocking relationship matrix between the power grid knowledge graph and equipment entities, and the historical operation tickets and order management system method sheets corresponding to the maintenance task; based on the power grid knowledge graph and the five-prevention interlocking relationship matrix, perform time window overlay analysis on the maintenance task, and then generate the process operation ticket.

[0067] In this embodiment, the real-time measurement data of the Operational Control System (OCS) refers to the real-time and accurate measurement of base sulfur using high-precision, portable analyzers or related technologies to obtain information such as its concentration and trend in the atmosphere, environment, or industrial processes. The real-time measurement data reflects the current operating status of the power grid, such as parameters like voltage, current, and power. The real-time measurement data is crucial for accurately assessing the impact of maintenance tasks on the power grid and determining the appropriate operation time.

[0068] In the Dispatching Command and Control System (DCCS), historical operation tickets, which record and execute operations in the past, contain information such as the operation process and operation time for similar maintenance tasks. By analyzing historical operation tickets, successful operation experiences can be learned from, recurring problems can be avoided, and the rationality and safety of new operation tickets can be improved.

[0069] The Operation Management System (OMS) generates order documents according to specific methods or formats. The OMS includes information such as the power grid's operating mode and equipment status, providing crucial reference for the planning and execution of maintenance tasks. By integrating real-time measurement data, historical operation tickets, and information from the OMS, a power grid knowledge graph based on a common information model is constructed, encompassing knowledge of equipment attributes, operating status, and connection relationships.

[0070] This power grid knowledge graph is a data structure that graphically represents various entities in a power grid and the relationships between them. It is a standard model in the power system field used to describe power grid equipment, systems, and their relationships. It provides a general and scalable information model for information exchange and sharing between different systems. Simultaneously, it constructs a five-prevention interlocking relationship matrix between equipment entities. The five-prevention interlocking refers to five measures to prevent electrical misoperation: preventing the opening and closing of disconnecting switches under load, preventing the accidental opening and closing of circuit breakers, preventing the connection of grounding wires while energized, preventing the closing of circuit breakers with grounding wires connected, and preventing accidental entry into energized compartments. The five-prevention interlocking relationship matrix between equipment entities describes the constraints between different devices in terms of these five preventions.

[0071] Furthermore, a spatiotemporal Petri net is used to perform time window overlay analysis on the maintenance tasks, derive the pre-issued command tasks in the feasible operation sequence space, identify the approved power outage operation start time, approved work start time, approved work end time, and approved power restoration operation end time of different maintenance orders under the same operation order, and group maintenance orders in the same time period into the same operation task.

[0072] This method integrates real-time measurement data, historical operation tickets, and operation management system mode sheets to construct a power grid knowledge graph and a five-prevention interlocking relationship matrix. It achieves deep fusion of multi-source data. By obtaining operation ticket generation requests, the connection relationship between equipment in the power grid can be determined according to the power grid knowledge graph and the five-prevention interlocking relationship matrix. At the same time, it ensures that the operation sequence complies with the five-prevention specifications during the operation ticket generation process and performs time window overlay analysis. It has achieved significant technical effects in many aspects such as data integration, safety assurance, operation process optimization, time scheduling, and resource utilization, and improved the scientificity, safety, and efficiency of maintenance task planning.

[0073] S203. When the task type is unplanned maintenance, obtain the processing scenario keywords corresponding to the maintenance task; generate a process operation ticket based on the processing scenario keywords.

[0074] In this embodiment, if the task type is unplanned maintenance, and the content of unplanned maintenance includes, but is not limited to, emergency maintenance, fault repair, and temporary maintenance, then the language generation model is activated to obtain the processing scenario keywords corresponding to the unplanned maintenance task, and a process operation ticket is generated based on the processing scenario keywords. This method broadens the scope of operation ticket generation, enabling the generation of operation tickets not only for planned inspections but also for expedited generation of operation tickets for unplanned temporary maintenance tasks, thus improving the efficiency and business scope of automatic operation ticket generation.

[0075] S204. Based on the historical operation tickets, equipment association diagrams, operation templates, and real-time status data that have the highest matching degree with the maintenance task and the latest execution time, update the process operation tickets; input the updated process operation tickets into the optimization model to obtain the target operation tickets.

[0076] In this embodiment, the updated process operation ticket is input into the optimization model for optimization training to obtain the target operation ticket. The optimization model is a mathematical model used to optimize the operation time and operation method in the process operation ticket. The training process of the optimization model includes: obtaining equipment feature vectors and operation context; determining the power grid topology structure features based on the equipment feature vectors and determining the operation sequence based on the operation context; constructing a multi-objective collaborative optimization loss function; and training the optimization model based on the multi-objective collaborative optimization loss function.

[0077] Optionally, the device feature vector uses a one-hot encoding to identify the discrete attributes of the device. For example, the device feature vector of a circuit breaker ["circuit breaker", "220kV"] can be changed to [1,0,0,...,0,1,0] through encoding. The operational context is described according to the ISON format state description. For example, {"topology":{"nodes":["busbar A","circuit breaker Q1"],"edges":[0,1]]},"State":{"circuit breaker Q1":"open","grounding switch":"closed"},"Environment":{"load rate":85%,"weather":"thunderstorm"}}, this data segment describes a portion of the topology and device status of a power system. In the topology, nodes represent key equipment or nodes in the power system, including bus A circuit breaker Q1. Edges represent the connection relationships between nodes. In this embodiment, [[0,1]] indicates that there is a connection between "bus A" (node ​​0) and "circuit breaker Q1" (node ​​1). In the State, circuit breaker Q1 is in the "open" state, meaning that the circuit breaker is currently open. Grounding switch is in the "closed" state, meaning that the grounding switch is currently closed. The Environment characterizes a load factor of 85%, indicating that the current load level of the power system is high. The weather condition is thunderstorm, indicating that the current weather conditions may affect the operation of the power system, such as causing equipment failure or requiring special operating measures.

[0078] Optionally, the power grid topology graph structure features are constructed based on GraphSAGE (Graph SAmple and aggreGatE). This inductive learning framework generates embedded representations of nodes by sampling and aggregating the features of node neighbors, thereby capturing the structural information in the graph and the dependencies between nodes. The power grid topology graph determined based on device vectors is essentially a graph structure, including nodes and edges. Nodes are equivalent to devices, and edges are equivalent to electrical connections between devices. By obtaining the neighboring nodes of each node device, neighbor features, such as the status of adjacent devices and voltage levels, are aggregated to generate node embeddings that represent the contextual role of devices in the graph.

[0079] Optionally, based on BERT+CRF, the operation sequence is determined based on the operation context, generating a text sequence that conforms to the power terminology specification, such as "open the bus side disconnect switch" instead of "close the bus section switch"; the BERT (Bidirectional Encoder Representations from Transformers) module encodes the operation context into a semantic vector, capturing the relevance of industry terminology; CRF (Conditional Random Field) is used to constrain the label transition probability of the output sequence to avoid illegal combinations, such as not "testing for electricity" immediately after "closing the switch".

[0080] Optionally, the multi-objective collaborative optimization loss function includes an order rationality loss function, a security constraint loss function, and a term matching loss function with different weight coefficients; the multi-objective collaborative optimization loss function is shown in the following equation:

[0081] L = α × L1 + β × L2 + γ × L3

[0082] Where α, β, and γ are weighting coefficients; L1 is the sequence rationality loss function, which is implemented by optimizing the model to predict the probability distribution of the next operation and calculating the cross-entropy loss to ensure that the operation conforms to the standard procedure; L2 is the safety constraint loss function, which optimizes the model to simulate whether the system still meets the stability requirements after removing any device; L3 is the terminology matching loss function, which compares the generated text in the operation ticket with the keyword weight vector of the standard terminology library to determine the similarity between the generated text and the standard terminology library.

[0083] In one possible implementation, the device feature vector of each device involved in the updated process operation ticket and the operation context instructions involved in that device are obtained. The power grid topology structure features are determined based on the device feature vectors, and operation sequence text is generated based on the context operation. Through multi-objective collaborative optimization of the loss function, the rationality of the updated operation ticket in terms of device connection relationship, device sequence, task operation and the rationality of the generated operation text is calculated for comprehensive training and optimization.

[0084] S205. Simulate the target operation ticket based on the digital twin system corresponding to the power grid and obtain the simulation results; if the simulation results meet the preset verification system, output the target operation ticket; if the simulation results do not meet the preset verification system, perform the process operation ticket generation based on the task type and corresponding to the maintenance task, until the simulation results meet the preset verification system.

[0085] In this embodiment, a visual operation interface is provided to the user terminal, displaying the optimized target operation ticket. Based on user input, the user terminal uses a digital twin system built on a software platform with powerful power system modeling and simulation capabilities, such as PowerWorld or PSASP, to model the target operation ticket, obtain simulation results, and determine whether the target operation ticket can perform the operation corresponding to the operation ticket generation request. If not, a new process operation ticket corresponding to the maintenance task is generated based on the task type. If it can be performed, the simulation results are pre-checked until they conform to the pre-check system, and the target operation ticket is output. Optionally, if the target operation ticket still does not meet the pre-check after a preset number of optimization training cycles, the user terminal can manually modify the target operation ticket. Modifications include, but are not limited to, the specific order of operation steps and the expression of operation syntax.

[0086] Optionally, the preset verification system includes the following verification dimensions: grammatical compliance, topological security, and transient stability, as shown in the table below.

[0087]

[0088] Optionally, for the text content of the target operation ticket, regular expression template matching can be used for grammatical compliance checks. This method can ensure that the terminology used in the operation ticket is standardized, conforms to industry standards and operating practices, and avoids misunderstandings or errors caused by inappropriate terminology. Simultaneously, by matching through a logical rule base, it can be checked whether the steps in the operation ticket are logically clear and logically ordered, and whether the opinions of various professional departments are consistent. For example, the opinions of departments such as mode, relay protection, safety automation, and dispatching need to be coordinated to ensure that the operation ticket will not cause problems due to inconsistencies between departments during actual execution. Furthermore, it is also necessary to verify whether the status of secondary equipment such as relay protection and safety automation is consistent with the corresponding setting sheets and operating modes; this is a crucial link in ensuring the safe and stable operation of the power system.

[0089] Optionally, a real-time topology analysis engine can be used to perform a security analysis on the topological relationships involved in the template operation ticket. Topology analysis can reveal the connection status and interactions between devices in the power system, thereby identifying potential safety hazards. Topology analysis can check for the formation of electrical islands, i.e., a part of the system is isolated from other parts due to faults or operations, resulting in abnormal power transmission. It can also perform safety verification and alarms on status, topology, and hazardous points, promptly identifying and addressing issues that may endanger system security.

[0090] Optionally, verifying the transient stability of the target operation ticket through simulation interface calls is an important means of ensuring the feasibility of the operation ticket. Transient stability analysis can simulate the dynamic response of the system during the execution of the operation ticket, check for any failures in OCS verification and power flow verification, and whether signal alarms or current anomalies occur before and after the simulated operation. These verifications can comprehensively assess the impact of the operation ticket on the stability of the power system, ensuring that serious consequences such as system crashes or equipment damage will not occur during actual execution.

[0091] The automatic operation ticket generation method provided in this application offers multiple generation methods for the user during the operation ticket generation process. It can obtain process operation tickets based on two generation formats: unplanned maintenance and planned maintenance. The method then updates and optimizes the process operation tickets from multiple dimensions, including historical operation tickets, equipment association diagrams, and real-time dynamic environments. Simultaneously, it strengthens the training of the process operation tickets through optimization models, comprehensively optimizing the operation methods and operation times to obtain more accurate operation tickets with reasonable text and accurate equipment relationships. The generated target operation ticket undergoes simulation and verification multiple checks to verify its feasibility. This method performs multi-dimensional optimization at different stages of operation ticket generation, optimization, and verification, thereby achieving the technical effect of improving the accuracy of operation ticket generation.

[0092] Figure 3 A schematic diagram of the automatic operation ticket generation device provided in this application is shown below. Figure 3 As shown, the automatic operation ticket generation device 30 provided in this embodiment includes:

[0093] The acquisition module 301 is used to acquire the operation ticket generation request; the operation ticket generation request includes at least the maintenance task and the task type corresponding to the maintenance task.

[0094] The generation module 302 is used to generate a process operation ticket corresponding to the maintenance task based on the task type; the process operation ticket shall include at least the operation time and operation method of the maintenance task.

[0095] The optimization module 303 is used to update the process operation ticket based on the historical operation ticket, equipment association map, operation template and real-time status data that have the highest matching degree with the maintenance task and the latest execution time.

[0096] The optimization module 303 is also used to input the updated process operation ticket into the optimization model to obtain the target operation ticket;

[0097] Output module 304 is used to output the target operation ticket.

[0098] In one possible implementation, the generation module 302 is further used for:

[0099] When the task type is planned maintenance, based on the acquired real-time measurement data, a power grid knowledge graph and a matrix of five-prevention interlocking relationships between equipment entities are constructed using the historical operation tickets and order management system method sheets corresponding to the maintenance task.

[0100] Based on the power grid knowledge graph and the five-prevention interlocking relationship matrix, a process operation ticket is generated after performing time window overlay analysis on the maintenance task.

[0101] In one possible implementation, the generation module 302 is further used for:

[0102] When the task type is unplanned maintenance, obtain the processing scenario keywords corresponding to the maintenance task.

[0103] Based on the processing scenario keywords, process operation tickets are generated.

[0104] In one possible implementation, the training process of the optimization module 303 is as follows:

[0105] Obtain the device feature vector and operation context.

[0106] The structural features of the power grid topology are determined based on the device feature vectors, and the operation sequence is determined based on the operation context.

[0107] A multi-objective collaborative optimization loss function is constructed, which includes a sequence rationality loss function with different weight coefficients, a security constraint loss function, and a term matching loss function.

[0108] The optimization model is trained based on the multi-objective collaborative optimization loss function.

[0109] In one possible implementation, the output module 304 is also used for:

[0110] The target operation ticket is simulated based on the digital twin system corresponding to the power grid, and the simulation results are obtained.

[0111] If the simulation results meet the preset verification system, the target operation ticket will be output.

[0112] If the simulation results do not conform to the preset verification system, process operation tickets corresponding to the maintenance tasks will be generated based on the task type until the simulation results conform to the preset verification system.

[0113] In one possible implementation, the verification dimensions of the preset verification system in the output module 304 include: syntax compliance, topology security, and transient stability.

[0114] The method provided in this embodiment can execute the method provided in the above-described method embodiments, and its implementation principle and technical effect are similar, so it will not be described in detail here.

[0115] Figure 4 A hardware schematic diagram of the operation ticket generation device provided in this application. Figure 4 As shown, the electronic device 40 provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the device 40 further includes a communication component 403. The processor 401, memory 402, and communication component 403 are connected via a bus 404.

[0116] In a specific implementation, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to perform the above-described method.

[0117] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0118] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0119] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0120] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0121] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0122] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0123] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0124] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0125] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, methods, or units, and may be electrical, mechanical, or other forms.

[0126] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0127] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0128] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0129] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0130] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for automatically generating operation tickets, characterized in that, The method includes: Obtain an operation ticket generation request; the operation ticket generation request includes at least the maintenance task and the task type corresponding to the maintenance task. Based on the task type, a process operation ticket corresponding to the maintenance task is generated; the process operation ticket includes at least the operation time and operation method of the maintenance task. Based on the historical operation tickets, equipment association diagrams, operation templates, and real-time status data that have the highest matching degree with the maintenance task and the latest execution time, the process operation ticket is updated; Input the updated process operation ticket into the optimization model to obtain the target operation ticket; Output the target operation ticket.

2. The method according to claim 1, characterized in that, The step of generating a process operation ticket corresponding to the maintenance task based on the task type includes: When the task type is planned maintenance, based on the acquired real-time measurement data, a power grid knowledge graph and a five-prevention interlocking relationship matrix between equipment entities are constructed using the historical operation tickets and order management system method sheets corresponding to the maintenance task. Based on the power grid knowledge graph and the five-prevention interlocking relationship matrix, the maintenance task is analyzed by time window overlay to generate the process operation ticket.

3. The method according to claim 1, characterized in that, The step of generating a process operation ticket corresponding to the maintenance task based on the task type includes: When the task type is unplanned maintenance, obtain the processing scenario keywords corresponding to the maintenance task; Based on the processing scenario keywords, the process operation ticket is generated.

4. The method according to claim 1, characterized in that, The optimization model is a mathematical model used to optimize the operation time and operation method in the process operation ticket. The training process of the optimization model includes: Obtain device feature vectors and operational context; The power grid topology structure features are determined based on the device feature vectors, and the operation sequence is determined based on the operation context. Construct a multi-objective collaborative optimization loss function, which includes an order rationality loss function, a security constraint loss function, and a term matching loss function with different weight coefficients; The optimization model is trained based on the multi-objective collaborative optimization loss function.

5. The method according to claim 1, characterized in that, After optimizing the operation time and operation method of the maintenance task to obtain the target operation ticket, the method further includes: The target operation ticket is simulated based on the digital twin system corresponding to the power grid, and the simulation results are obtained; If the simulation results conform to the preset verification system, the target operation ticket is output; If the simulation result does not conform to the preset verification system, the process of generating a process operation ticket corresponding to the maintenance task based on the task type is executed until the simulation result conforms to the preset verification system.

6. The method according to claim 5, characterized in that, The verification dimensions of the preset verification system include: grammatical compliance, topological security, and transient stability.

7. An automatic ticket generation device, characterized in that, include: The acquisition module is used to acquire operation ticket generation requests; The operation ticket generation request includes at least the maintenance task and the task type corresponding to the maintenance task. The generation module is used to generate a process operation ticket corresponding to the maintenance task based on the task type; the process operation ticket includes at least the operation time and operation method of the maintenance task. The optimization module is used to update the process operation ticket based on the historical operation tickets, equipment association diagrams, operation templates, and real-time status data that have the highest matching degree with the maintenance task and the latest execution time. The optimization module is also used to input the updated process operation ticket into the optimization model to obtain the target operation ticket; The output module outputs the target operation ticket.

8. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images