Operation ticket generation method and device, equipment and storage medium

Abstract

The invention relates to the technical field of operation ticket processing, and discloses an operation ticket generation method and device, equipment and a storage medium, which are used for improving the adaptability of the operation ticket generation method to different substation operation scenes and improving the accuracy, safety and efficiency of the generated operation ticket. The operation order generation method comprises the steps of performing semantic analysis on a to-be-processed scheduling order to obtain structured scheduling order data; performing dynamic topology analysis on the structured scheduling order data according to the real-time equipment state data to obtain a real-time topology analysis result; matching in a preset operation ticket database according to the structured scheduling order data, and inputting the processed historical topology analysis result, the ticket forming template, the structured scheduling order data, the real-time topology analysis result, the self-defined ticket forming rule and the cue word template into a large language model for ticket forming to obtain an initial operation ticket; performing safety verification on the initial operation ticket to obtain a safety verification result; and generating a target operation ticket based on the interaction information of the security verification result.

Description

Technical Field

[0001] The present application relates to the technical field of operation ticket processing, and in particular to an operation ticket generation method, device, equipment and storage medium. Background Art

[0002] In the power industry, the operation ticket system is the most basic system to ensure that operators perform operations correctly and prevent misoperation. Among them, the operation items are the key content of the operation ticket. Accurate and standardized descriptions of operation items that conform to the operation logic are the prerequisite for ensuring correct operation. The intelligent switching operation ticket generation system has made certain progress in the automatic generation of operation tickets by extracting the logic and rules of historical operation tickets and typical operation tickets.

[0003] In the related technology, the traditional intelligent ticket generation system is based on the methods of neural networks, knowledge graphs and large language models. Among them, the operation ticket generation method based on neural networks is adopted to output the operation ticket by learning the ticket generation logic of the operation ticket sample; the construction and maintenance cost of constructing the knowledge graph based on the operation ticket sample is high; the method based on the large language model may have misunderstandings or errors when processing highly professional power operation instructions, especially when processing complex and non-standardized dispatching instructions; traditional solutions rely on a large number of operation ticket samples for training, however, substations in different regions have differences in equipment configuration and operating procedures. When the intelligent ticket generation system is applied to different operation scenarios or new equipment types are added, it will result in a large number of personnel for model training and adaptation adjustments, which is a huge workload and difficult to ensure quality. In addition, when there are errors in the operation ticket samples, the operation tickets generated by the traditional intelligent ticket generation system will also inherit these errors. Summary of the invention

[0004] The present application provides an operation ticket generation method, device, equipment and storage medium, which are used to solve the problem that traditional operation ticket generation cannot adapt to different substation operation scenarios, when new operating procedures, equipment and safety requirements emerge, knowledge cannot be effectively integrated, the generated operation tickets have low accuracy, and it is difficult to fully consider various safety dimensions of the operation.

[0005] The first aspect of the present application provides an operation ticket generation method, comprising: semantically parsing a dispatch order to be processed to obtain structured dispatch order data;

[0006] Performing dynamic topological analysis on the structured scheduling order data to obtain real-time topological analysis results;

[0007] According to the structured dispatch order data, historical dispatch orders and operation ticket samples of the same type are matched in a preset operation ticket database to obtain historical topology analysis results and ticket templates;

[0008] Input the structured dispatch order data, the real-time topology analysis result, the historical topology analysis result, the ticket template, the preset custom ticket rule and the preset prompt word template into a preset large language model for ticket generation to obtain an initial operation ticket;

[0009] Performing a security check on the initial operation ticket to obtain a security check result, wherein the security check result at least includes the checked initial operation ticket;

[0010] The security verification result is displayed, and a target operation ticket is generated based on the interactive information of the security verification result.

[0011] A second aspect of the present application provides an operation ticket generation device, comprising: a parsing module, for performing semantic parsing on a dispatch order to be processed to obtain structured dispatch order data;

[0012] A topology analysis module, used to perform dynamic topology analysis on the structured scheduling order data to obtain real-time topology analysis results;

[0013] A matching module, used to match historical dispatch orders and operation ticket samples of the same type in a preset operation ticket database according to the structured dispatch order data, to obtain historical topology analysis results and ticket templates;

[0014] A generation module, used for inputting the structured dispatch order data, the real-time topology analysis result, the historical topology analysis result, the ticket template and the preset prompt word template into a preset large language model to obtain an initial operation ticket;

[0015] A security verification module is used to perform a security verification on the initial operation ticket to obtain a security verification result;

[0016] The interactive module is used to display the security verification result and generate a target operation ticket based on the interactive information of the security verification result.

[0017] The third aspect of the present application provides an operation ticket generating device, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the operation ticket generating device executes the above-mentioned operation ticket generating method.

[0018] A fourth aspect of the present application provides a computer-readable storage medium, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the above-mentioned operation ticket generation method.

[0019] In the technical solution provided by the present application, semantic parsing is performed on the dispatch order to be processed so that the large language model can accurately understand the context information of complex dispatch orders, thereby improving the versatility and adaptability of the system; dynamic topological analysis is performed on the structured dispatch order data based on real-time equipment data to achieve real-time update of equipment status and network topology, solving the problem that the traditional ticket model cannot adapt to the dynamic changes of the power grid. When new equipment is added to the power grid, it can also ensure that the generated operation ticket is consistent with the actual status of the current power grid. By inputting the real-time topological analysis results, the knowledge comprehension ability of the large language model can be improved; in order to provide a large language model solution that does not require training and improve the versatility and applicability of the large language model, a prompt word template is used. The large language model is provided with accurate guidance through the customized ticket-generating rules to meet the needs of generating operation tickets for different power plants; the large language model is provided with sufficient reference basis through the historical topology analysis results, ticket-generating templates, and preset customized ticket-generating rules; the large language model effectively integrates the reference data, real-time topology analysis results, and structured dispatch order data to comprehensively generate the initial operation ticket that meets the actual operation requirements; the reliability and security of the operation ticket are significantly improved through the security verification of the initial operation ticket; the security verification results are displayed, and the target operation ticket is generated based on the interactive information of the security verification results, allowing the user to review and modify the generated operation ticket, and the flexibility and accuracy of the generated operation ticket are guaranteed through manual interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of an embodiment of the method for generating an operation ticket in this application;

[0021] Figure 2 This is another schematic diagram of an embodiment of the method for generating an operation ticket in the present application;

[0022] Figure 3 A schematic diagram of an embodiment of an operation ticket generating device in the present application;

[0023] Figure 4 This is a schematic diagram of another embodiment of the operation ticket generating device in the present application;

[0024] Figure 5 This is a schematic diagram of an embodiment of an operation ticket generating device in the present application. DETAILED DESCRIPTION

[0025] The present application provides an operation ticket generation method, device, equipment and storage medium, which are used to improve the adaptability of the operation ticket generation method to different substation operation scenarios and improve the accuracy, safety and efficiency of the generated operation tickets.

[0026] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] For ease of understanding, the specific process of this application is described below. Figure 1 , an embodiment of the operation ticket generation method in the present application includes:

[0028] 101. Perform semantic analysis on the dispatch order to be processed to obtain structured dispatch order data.

[0029] It is understandable that the execution subject of the present application can be an operation ticket generation device, or an intelligent switching operation ticket generation system, and a terminal or server with corresponding operation logic, which is not limited here. This embodiment is described by taking the intelligent switching operation ticket generation system equipped with a large language model as the execution subject.

[0030] Among them, the Large Language Model (LLM) is based on learning technology and can capture implicit contextual information that may be contained in the dispatch order, avoiding parsing errors or omissions caused by the complexity and diversity of natural language expressions, such as the same operation described in different ways of expression, professional terms or abbreviations, which affects the accuracy of operation ticket generation. This embodiment uses a parser based on a large language model for semantic understanding, identifies key equipment, operating instructions, target status and other information in the dispatch order to be processed, so as to generate structured dispatch order data and improve the subsequent ticket generation efficiency.

[0031] 102. Perform dynamic topology analysis on the structured dispatch order data according to the current real-time device status data to obtain real-time topology analysis results.

[0032] The intelligent switching operation ticket generation system of this embodiment can obtain all the power grid equipment and their equipment status in the current substation, perform dynamic topology analysis on the structured dispatch order data, and obtain real-time topology analysis results.

[0033] The above-mentioned real-time topology analysis results include the target device, other devices associated with it, and the real-time status of the devices. In this embodiment, the real-time topology analysis results can fully grasp the association relationship between devices, can quickly respond to changes in device status, and update the power grid topology in real time to adapt to the current device changes in the substation.

[0034] Among them, the intelligent switching operation ticket generation system can continuously obtain real-time status information of power grid equipment by communicating with the Supervisory Control And Data Acquisition (SCADA) system or other data sources.

[0035] 103. According to the structured dispatch order data, historical dispatch orders and operation ticket samples of the same type are matched in a preset operation ticket database to obtain historical topology analysis results and ticket templates.

[0036] Optionally, the structured dispatch order data is matched in a preset operation ticket database to obtain historical dispatch orders of the same type and their corresponding operation ticket samples, and dynamic topological analysis is performed based on the historical dispatch orders of the same type to obtain historical topological analysis results; a ticket template is determined based on the operation ticket samples associated with the historical dispatch orders of the same type.

[0037] Optionally, if there are multiple historical dispatch orders of the same type in the matched operation ticket database, the latest historical dispatch order is selected for dynamic topology analysis to ensure that the subsequent large language model can generate operation tickets based on new knowledge.

[0038] In this embodiment, the operation ticket database includes multiple operation ticket samples, wherein each operation ticket sample is a typical operation ticket or a historical operation ticket of the current substation. The operation ticket database is formed by integrating the historical operation tickets and the typical operation tickets. The typical operation ticket is compiled according to the conventional operation process and standard operation procedure of the power system to indicate a representative and typical operation ticket, while the historical operation ticket data is an operation ticket that has been executed and records the operation items in the actual operation process. This embodiment enriches the samples of the operation ticket database through typical operation tickets and historical operation tickets, taking into account both the quality and quantity of the operation ticket samples.

[0039] Optionally, pre-parse the typical operation tickets and / or historical operation tickets of the current plant, analyze the ticket generation logic and rules of different dispatch orders, and store the analyzed ticket generation logic and rules in the template library to form a basic template for operation ticket generation.

[0040] In this embodiment, the dispatch order is used to indicate instructions for dispatching power grid equipment in the substation, for example, switching a certain 282 switch from cold standby to operating state; and the operation ticket is used to indicate the specific operation content when executing the dispatch order. The operation ticket is composed of operation items, where the number of operation items can be one, two or more, each operation item corresponds to the operation content of a device, and the operation items are arranged in a strict operation order to ensure operation safety.

[0041] In this embodiment, the historical topology analysis results include the target device corresponding to the determined historical dispatch order and the set of devices associated therewith, which can be obtained by performing multi-level topology analysis on the target device based on the historical device data after the historical dispatch order is structured. In this embodiment, the historical topology analysis results are used to convert the same type of operation ticket samples into structured data that is easier to understand for the large language model. The historical topology analysis results and the real-time topology analysis results can intuitively present the differences between the two dispatch orders of the substation, so as to achieve targeted processing.

[0042] In this embodiment, the ticket template is used to indicate the style compiled by the ticket logic and rules of the same type of historical operation tickets or typical operation tickets, which can be generated by the historical operation tickets or typical operation tickets associated with the historical dispatch order. In this embodiment, the ticket template can standardize the ticket output form of the large language model.

[0043] 104. Input the structured dispatch order data, real-time topology analysis results, historical topology analysis results, ticket template, preset custom ticket rules and preset prompt word template into the preset large language model for ticket generation to obtain an initial operation ticket.

[0044] Specifically, the preset prompt word template is used to guide the large language model to perform the operation ticket generation task. The context learning ability of the large language model is used to refer to the historical topology analysis results, the ticket template, and the preset custom ticket rules to output the initial operation ticket that meets the actual operation requirements for the structured dispatch order data and the real-time topology analysis results. This embodiment integrates the dispatch order parsing results, real-time topology analysis data, and related historical operation ticket information through the multi-source information fusion mechanism of the large language model to improve the accuracy and applicability of the generation.

[0045] In this embodiment, the custom ticket generation rules are used to indicate the operation ticket generation rules set by the user in the substation. Each substation has differences in equipment configuration and operating procedures. Different operating environments and operators may have different needs. This embodiment adapts to the ticket generation needs of various scenarios by adding user-set custom ticket generation rules, improves the flexibility of the operation ticket generation method, meets the personalized needs of each substation, and can also adapt to various complex operating scenarios, such as normal operation, emergency response, inspection and maintenance, and other special requirements.

[0046] In this embodiment, the prompt word template is used to indicate the prompt words for guiding the large language model, so as to improve the large language model's ability to understand and parse complex dispatch orders, and guide the large language model to generate an operation ticket that meets the requirements.

[0047] 105. Perform security check on the initial operation ticket and obtain the security check result.

[0048] Specifically, the initial operation ticket is security-checked according to a plurality of preset verification rules to obtain a security-check result, which may include information such as the verified operation ticket and whether the verification is passed.

[0049] The above-mentioned safety verification may include safety analysis and risk assessment rules in multiple dimensions, including but not limited to verifying the rationality of the operation sequence in the operation ticket, the consistency of the equipment status, etc., to ensure the safety and feasibility of the operation ticket.

[0050] For example, the preset five-prevention logic formula is used to determine whether the operation ticket complies with the five-prevention operation rules, and the complete operation sequence of the operation ticket is subjected to error-proof logic verification to ensure the correctness of the operation sequence.

[0051] 106. Display the security verification result, and generate a target operation ticket based on the interactive information of the security verification result.

[0052] The intelligent switching operation ticket generation system can also provide a user-friendly visual interface to display the safety verification results, that is, present the verified operation ticket. The user can review the generated operation ticket online through the visual interface and generate interactive information through the corresponding functional components on the visual interface, such as modifying and annotating the operation ticket. The intelligent switching operation ticket generates the target operation ticket based on the interactive information of the safety verification results.

[0053] It can be understood that the interactive information may be approved, in which case the intelligent switching operation ticket directly uses the operation ticket as the target operation ticket; the interactive information may also be unapproved, in which case the interactive information includes user feedback. The intelligent switching operation ticket performs semantic analysis on the interactive information to modify the operation ticket to ensure the correctness of the target operation ticket.

[0054] In this embodiment, semantic parsing is performed on the dispatch order to be processed so that the large language model can accurately understand the context information of complex dispatch orders, thereby improving the versatility and adaptability of the system; dynamic topology analysis is performed on the structured dispatch order data based on real-time equipment data to achieve real-time update of equipment status and network topology, solving the problem that the traditional ticket model cannot adapt to the dynamic changes of the power grid. When new equipment is added to the power grid, it can also ensure that the generated operation ticket is consistent with the actual status of the current power grid. By inputting the real-time topology analysis results, the knowledge comprehension ability of the large language model can be improved; in order to provide a large language model solution that does not require training and improve the versatility and applicability of the large language model, prompt word templates and custom The Yichengti rules provide accurate guidance for the large language model to adapt to the operation ticket generation needs of different power plants; the historical topology analysis results, ticket templates, and preset custom ticket rules provide sufficient reference basis for the large language model. The large language model effectively integrates the reference data, real-time topology analysis results, and structured dispatch order data to comprehensively generate initial operation tickets that meet actual operation requirements; the reliability and security of the operation tickets are significantly improved through security verification of the initial operation tickets; the security verification results are displayed, and the target operation tickets are generated based on the interactive information of the security verification results, allowing users to review and modify the generated operation tickets, and ensuring the flexibility and accuracy of the generated operation tickets through manual interaction.

[0055] See also Figure 2 Another embodiment of the operation ticket generation method in the present application includes:

[0056] 201. Perform semantic analysis on the dispatch order to be processed to obtain structured dispatch order data.

[0057] Perform format analysis and conversion on the dispatch order to be processed to obtain the dispatch order information in the target format; analyze the dispatch order information by combining large language model technology and natural language processing technology to obtain the initial parsing result; verify and optimize the initial parsing result through the preset rule engine to obtain structured dispatch order data.

[0058] The intelligent switching operation ticket generation system of this embodiment supports dispatch order input in various formats, including text, voice, etc., to improve the applicability of the system; combines the semantic parsing of the large language model and natural language processing technology to perform named entity recognition and relationship extraction on the dispatch order information, and accurately identifies key equipment, operating instructions, target status and other information in the dispatch order; further combines with the power industry-specific rule engine to further verify and optimize the parsing results to ensure the accuracy of the parsing.

[0059] For example, the dispatch order to be processed is: Please switch the 121 switch of a 110kV line from cold standby to operation, or a non-standard dispatch order: Put the switch of Houjin Line 1 into operation. The intelligent switching operation ticket generation system can correctly parse similar structured dispatch order data through context understanding, as follows:

[0060] Equipment: 121 switch of a 110kV line;

[0061] Operation type: state transition;

[0062] Initial state: cold standby;

[0063] Target state: Running.

[0064] This embodiment uses a large language model that has been enhanced with professional knowledge in the power field to achieve semantic understanding of complex unstructured dispatch instructions. Compared with existing rule-based or simple neural network methods, the large language model significantly improves the system's ability to parse various professional instructions, and improves the system's versatility and adaptability.

[0065] 202. Perform dynamic topology analysis on the structured scheduling order data according to the current real-time device status data to obtain a real-time topology analysis result.

[0066] According to the current real-time device status data, a multi-level topological analysis is performed on the target device in the structured scheduling order data to obtain the associated device set corresponding to each level of the target device; according to the current real-time device status data, the real-time device status of the target device and its associated device set at each level is determined to obtain the real-time topological analysis result. The dynamic topological analysis of this embodiment ensures the real-time matching of the operation ticket with the actual device status, which improves the safety and reliability of the operation.

[0067] In this embodiment, the multi-level topology analysis includes device-level, bay-level and station-level analysis, etc., so as to fully grasp the relationship between devices. Continuing with step 201, the example is explained: for a 110kV line 121 switch, a dynamic topology analysis is performed, and the real-time topology analysis result can be output:

[0068] Equipment level: Identify associated circuit breakers, disconnect switches, voltage transformers, etc., as well as real-time equipment status.

[0069] Bay level: Determine the line bay where the switch is located and its connection status with the busbar.

[0070] Station level: Analyze the position of the line in the entire substation and its interaction with other lines.

[0071] Furthermore, the intelligent switching operation ticket generation system can also visualize the real-time topology analysis results to intuitively display the device connection status and the scope of operation impact.

[0072] 203. According to the structured dispatch order data, historical dispatch orders and operation ticket samples of the same type are matched in a preset operation ticket database to obtain historical topology analysis results and ticket templates.

[0073] Specifically, historical dispatch orders and operation ticket samples of the same type are screened in a preset operation ticket database according to the structured dispatch order data; dynamic topological analysis is performed on the historical dispatch orders to obtain historical topological analysis results; and a ticket template is determined according to the operation ticket samples.

[0074] Continuing with the example of the dispatch order for switching the switch 121 of a 110kV line from cold standby to operating state: search for the same type of operation tickets in the operation ticket database, and improve the approximation of the matching template by matching one or more structured parameters such as operation type, pre- and post-operation status, equipment type, etc., such as searching for the <cold standby to operating> operation ticket as a reference.

[0075] It is also possible to further select the historical dispatch order and its operation ticket sample with the highest similarity as a reference by means of similarity calculation.

[0076] The above-mentioned dynamic topological analysis of historical dispatch orders obtains historical topological analysis results, including: semantic parsing of historical dispatch orders to obtain structured historical dispatch order data; multi-level topological analysis of target devices in the structured historical dispatch order data based on current real-time device status data to obtain a set of associated devices corresponding to each level of the target device; determining the historical device status of the target device and its associated device sets at each level based on the historical device status data to obtain historical topological analysis results.

[0077] 204. Input the structured dispatch order data, the real-time topology analysis results, the historical topology analysis results, the ticket template, the preset custom ticket rules and the preset prompt word template into the preset large language model for ticket generation to obtain an initial operation ticket.

[0078] This embodiment uses an advanced large language model with powerful information integration capabilities, which can process dispatch order analysis results, real-time topology data and historical operation ticket information, and comprehensively generate intelligent and flexible operation tickets. Through the preset prompt word engineering, the model is guided to generate operation tickets that meet actual operation requirements, and through the accumulation of historical tickets, continuous accumulation and updating of knowledge is achieved.

[0079] 205. Perform a security check on the initial operation ticket to obtain a security check result.

[0080] Specifically, the initial operation ticket is compared and analyzed with the operation ticket samples of the same type to obtain the comparison analysis results; the initial operation ticket is checked for equipment status consistency based on the equipment status in the real-time topology analysis results, and an anti-error verification is performed based on the anti-error verification logic to obtain an anti-error verification result; a safety verification result is generated based on the comparison analysis results and the anti-error verification results. In this embodiment, multiple verifications and real-time status analysis can simulate the operation execution process, predict potential risks, and provide warnings and suggestions, significantly improve the reliability and safety of the operation ticket, greatly reduce the risk of operation errors, and improve the safety of power grid operation.

[0081] The security verification results of this example may include verified operation tickets and optimization suggestions to facilitate further review and confirmation by users. By proactively providing optimization suggestions to users, the intelligence level of the system can be further improved.

[0082] The above-mentioned device status consistency check is performed on the initial operation ticket based on the device status in the real-time topology analysis result, and an anti-error check is performed based on the anti-error check logic to obtain an anti-error check result, including: combining the rule engine and the preset anti-error check logic, and performing a multi-dimensional security analysis on the initial operation ticket according to the real-time topology analysis result.

[0083] The above comparative analysis results may be the same or different. The different comparative analysis results may be due to the addition of new equipment between the two tickets, or the operation ticket sample is a historical ticket generated by other means, etc. The comparative analysis results mark the differences between the initial operation ticket and the same type of operation ticket samples, and analyze the reasons for the differences.

[0084] The above-mentioned error prevention check result can be a check pass or a check failure. When the error prevention check result is a check failure, the error prevention check result marks the operation that may cause risks and generates warning information and optimization suggestions. This embodiment simulates the operation execution process, predicts possible risks, and gives corresponding warnings and suggestions, thereby realizing multi-level security verification of the operation ticket and ensuring that each step of the operation complies with safety specifications and operation procedures.

[0085] 206. Display the security verification result, and generate a target operation ticket based on the interactive information of the security verification result.

[0086] Specifically, the verified operation ticket and optimization suggestions are presented through a visual interface, and the interactive information of the user after reviewing the initial operation ticket based on the optimization suggestions is obtained; the initial operation ticket is modified based on the interactive information, and the modified items are marked on the modified target operation ticket. This embodiment can automatically identify the differences between the operation ticket and the same type of operation ticket and the differences between manual modification and system generation through the differential comparison function, so that the user can quickly locate the difference points and confirm whether the modification has been correct.

[0087] 207. Feedback optimization is performed on a preset operation ticket generation rule and / or an operation ticket database based on the interactive information and the target operation ticket.

[0088] Optionally, extract interactive information and parse it to obtain new ticket rules from user feedback; update the preset operation ticket generation rules based on the new ticket rules; save the target operation ticket as a new historical ticket, and store the operation ticket database in association with the corresponding dispatch order. This embodiment allows users to review and modify generated operation tickets through an intelligent interactive feedback optimization mechanism. The system automatically analyzes the modification mode, extracts the modification rules, and converts them into executable knowledge. Through a feedback closed-loop mechanism, the system continuously learns and optimizes the knowledge base and model parameters, continuously improves performance, and adapts to the ever-changing operating environment.

[0089] Specifically, updating the preset operation ticket generation rules based on the new ticket generation rules includes: evaluating the new ticket generation rules to obtain evaluation results; if the evaluation results meet the preset rule update conditions, updating the custom ticket generation rules and / or the system built-in ticket generation rules according to the new ticket generation rules. For example, evaluating the modification frequency and importance of the new ticket generation rules, if it is found that the modification is high-frequency and high-importance, then generating update prompt information to prompt the user to optimize and improve the overall performance of the system.

[0090] Among them, the operation ticket generation rules can be custom rules, or they can be implicit ticket generation rules extracted by a large language model based on the dispatch order.

[0091] For example, suppose that when the user reviews the operation ticket on the visual interface, he requests to add a new operation item after step 5 through text interaction: "5a. Check whether the protection pressure plate of a 110kV line is correctly put into operation." The system parses the interactive information and marks the modification as "Increase of safety check steps." The feedback can be "Add the key step of <Check protection pressure plate> in the template of the <Cold standby to operation> type." The next time a similar operation ticket is generated, the system will automatically include the step of checking the protection pressure plate based on the new historical ticket.

[0092] In this embodiment, semantic parsing is performed on the dispatch order to be processed so that the large language model can accurately understand the context information of complex dispatch orders, thereby improving the versatility and adaptability of the system; dynamic topology analysis is performed on the structured dispatch order data based on real-time equipment data to achieve real-time update of equipment status and network topology, solving the problem that the traditional ticket model cannot adapt to the dynamic changes of the power grid. When new equipment is added to the power grid, it can also ensure that the generated operation ticket is consistent with the actual status of the current power grid. By inputting the real-time topology analysis results, the knowledge comprehension ability of the large language model can be improved; in order to provide a large language model solution that does not require training and improve the versatility and applicability of the large language model, prompt word templates and custom The Yichengticket rules provide accurate guidance to the large language model to meet the needs of generating operation tickets for different power plants; the historical topology analysis results, ticket templates, and preset custom ticket rules provide sufficient reference for the large language model. The large language model effectively integrates the reference data, real-time topology analysis results, and structured dispatch order data to comprehensively generate initial operation tickets that meet actual operation requirements; the reliability and security of the operation tickets are significantly improved by security verification of the initial operation tickets; the security verification results are displayed, and the target operation tickets are generated based on the interactive information of the security verification results, allowing users to review and modify the generated operation tickets, and ensuring the flexibility and accuracy of the generated operation tickets through manual interaction. Furthermore, new operation ticket generation rules and knowledge are extracted based on user modifications and feedback, and the template library, user-defined rules, and system built-in rules are updated and optimized to ensure the timeliness and accuracy of templates and rules, and to improve the system's adaptability and the quality of operation ticket generation.

[0093] The above describes the operation ticket generation method in this application. The following describes the operation ticket generation device in this application. Figure 3 , an embodiment of the operation ticket generating device in the present application includes:

[0094] The parsing module 301 is used to perform semantic parsing on the dispatch order to be processed to obtain structured dispatch order data;

[0095] A topology analysis module 302 is used to perform dynamic topology analysis on structured scheduling order data to obtain real-time topology analysis results;

[0096] A matching module 303 is used to match historical dispatch orders and operation ticket samples of the same type in a preset operation ticket database according to the structured dispatch order data to obtain historical topology analysis results and ticket templates;

[0097] The generating module 304 is used to input the structured dispatch order data, the real-time topology analysis results, the historical topology analysis results, the ticket template and the preset prompt word template into the preset large language model to obtain the initial operation ticket;

[0098] The security verification module 305 is used to perform security verification on the initial operation ticket and obtain a security verification result;

[0099] The interactive module 306 is used to display the security verification result and generate a target operation ticket based on the interactive information of the security verification result.

[0100] In this embodiment, semantic parsing is performed on the dispatch order to be processed so that the large language model can accurately understand the context information of complex dispatch orders, thereby improving the versatility and adaptability of the system; dynamic topology analysis is performed on the structured dispatch order data based on real-time equipment data to achieve real-time update of equipment status and network topology, solving the problem that the traditional ticket model cannot adapt to the dynamic changes of the power grid. When new equipment is added to the power grid, it can also ensure that the generated operation ticket is consistent with the actual status of the current power grid. By inputting the real-time topology analysis results, the knowledge comprehension ability of the large language model can be improved; in order to provide a large language model solution that does not require training and improve the versatility and applicability of the large language model, prompt word templates and custom The Yichengti rules provide accurate guidance for the large language model to adapt to the operation ticket generation needs of different power plants; the historical topology analysis results, ticket templates, and preset custom ticket rules provide sufficient reference basis for the large language model. The large language model effectively integrates the reference data, real-time topology analysis results, and structured dispatch order data to comprehensively generate initial operation tickets that meet actual operation requirements; the reliability and security of the operation tickets are significantly improved through security verification of the initial operation tickets; the security verification results are displayed, and the target operation tickets are generated based on the interactive information of the security verification results, allowing users to review and modify the generated operation tickets, and ensuring the flexibility and accuracy of the generated operation tickets through manual interaction.

[0101] See also Figure 4 Another embodiment of the operation ticket generating device in the present application includes:

[0102] The parsing module 301 is used to perform semantic parsing on the dispatch order to be processed to obtain structured dispatch order data;

[0103] A topology analysis module 302 is used to perform dynamic topology analysis on structured scheduling order data to obtain real-time topology analysis results;

[0104] A matching module 303 is used to match historical dispatch orders and operation ticket samples of the same type in a preset operation ticket database according to the structured dispatch order data to obtain historical topology analysis results and ticket templates;

[0105] The generating module 304 is used to input the structured dispatch order data, the real-time topology analysis results, the historical topology analysis results, the ticket template and the preset prompt word template into the preset large language model to obtain the initial operation ticket;

[0106] The security verification module 305 is used to perform security verification on the initial operation ticket and obtain a security verification result;

[0107] The interactive module 306 is used to display the security verification result and generate a target operation ticket based on the interactive information of the security verification result.

[0108] Optionally, the interaction module 306 is specifically used to: obtain interaction information after the user reviews the initial operation ticket based on the optimization suggestion;

[0109] The initial operation ticket is modified based on the interactive information, and the modified items are marked on the modified target operation ticket.

[0110] Optionally, the parsing module 301 is specifically used to: perform format analysis and conversion on the dispatch order to be processed to obtain dispatch order information in a target format;

[0111] Combine large language model technology and natural language processing technology to analyze the dispatch order information and obtain the initial parsing results;

[0112] The initial parsing results are verified and optimized through the preset rule engine to obtain structured dispatch order data.

[0113] Optionally, the topology analysis module 302 is specifically used to: perform multi-level topology analysis on the target device in the structured scheduling order data according to the current real-time device status data, and obtain a set of associated devices corresponding to each level of the target device;

[0114] The real-time device status of the target device and its associated device sets at each level is determined based on the current real-time device status data to obtain the real-time topology analysis results.

[0115] Optionally, the security verification module 305 is specifically used to: compare and analyze the initial operation ticket with a sample of the same type of operation ticket to obtain a comparison analysis result;

[0116] Performing a device status consistency check on the initial operation ticket based on the device status in the real-time topology analysis result, and performing an anti-error check based on the anti-error check logic to obtain an anti-error check result;

[0117] Generate safety verification results based on comparative analysis results and anti-error verification results.

[0118] Optionally, historical dispatch orders and operation ticket samples of the same type are filtered in a preset operation ticket database according to the structured dispatch order data;

[0119] Perform dynamic topological analysis on historical dispatch orders to obtain historical topological analysis results;

[0120] Determine the ticket template based on the operation ticket sample.

[0121] Optionally, the matching module 303 is specifically used to filter historical dispatch orders and operation ticket samples of the same type in a preset operation ticket database according to the structured dispatch order data;

[0122] Perform dynamic topological analysis on historical dispatch orders to obtain historical topological analysis results;

[0123] Determine the ticket template based on the operation ticket sample.

[0124] Optionally, the operation ticket generating device further includes an optimization module 307 for performing feedback optimization on a preset operation ticket generating rule and / or an operation ticket database based on the interactive information and the target operation ticket.

[0125] In this embodiment, semantic parsing is performed on the dispatch order to be processed so that the large language model can accurately understand the context information of complex dispatch orders, thereby improving the versatility and adaptability of the system; dynamic topology analysis is performed on the structured dispatch order data based on real-time equipment data to achieve real-time update of equipment status and network topology, solving the problem that the traditional ticket model cannot adapt to the dynamic changes of the power grid. When new equipment is added to the power grid, it can also ensure that the generated operation ticket is consistent with the actual status of the current power grid. By inputting the real-time topology analysis results, the knowledge comprehension ability of the large language model can be improved; in order to provide a large language model solution that does not require training and improve the versatility and applicability of the large language model, prompt word templates and custom The Yichengticket rules provide accurate guidance to the large language model to meet the needs of generating operation tickets for different power plants; the historical topology analysis results, ticket templates, and preset custom ticket rules provide sufficient reference for the large language model. The large language model effectively integrates the reference data, real-time topology analysis results, and structured dispatch order data to comprehensively generate initial operation tickets that meet actual operation requirements; the reliability and security of the operation tickets are significantly improved by security verification of the initial operation tickets; the security verification results are displayed, and the target operation tickets are generated based on the interactive information of the security verification results, allowing users to review and modify the generated operation tickets, and ensuring the flexibility and accuracy of the generated operation tickets through manual interaction. Furthermore, new operation ticket generation rules and knowledge are extracted based on user modifications and feedback, and the template library, user-defined rules, and system built-in rules are updated and optimized to ensure the timeliness and accuracy of templates and rules, and to improve the system's adaptability and the quality of operation ticket generation.

[0126] above Figure 3 and Figure 4 The operation ticket generating device in the present application is described in detail from the perspective of modular functional entities, and the operation ticket generating device in the present application is described in detail from the perspective of hardware processing.

[0127] See also Figure 5As shown, the operation ticket generating device includes a processor 500 and a memory 501, wherein the memory 501 stores machine executable instructions that can be executed by the processor 500, and the processor 500 executes the machine executable instructions to implement the above-mentioned inverter circuit self-test method.

[0128] Further, Figure 5 The operation ticket generating device shown also includes a bus 502 and a communication interface 503 , and the processor 500 , the communication interface 503 and the memory 501 are connected via the bus 502 .

[0129] The memory 501 may include a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), for example, at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 503 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used. The bus 502 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0130] The processor 500 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 500. The above processor 500 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as a hardware decoding processor to be executed, or a combination of hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 501 , and the processor 500 reads the information in the memory 501 and completes the method steps of the above-mentioned embodiment in combination with its hardware.

[0131] The present application also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the operation ticket generation method.

[0132] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0133] If the integrated unit is implemented in the form of 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 the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., and other media that can store program codes.

[0134] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for generating an operation ticket, characterized in that: The operation ticket generation method comprises: Perform semantic analysis on the dispatch order to be processed to obtain structured dispatch order data; Performing dynamic topology analysis on the structured dispatch order data according to the current real-time device status data to obtain a real-time topology analysis result; According to the structured dispatch order data, historical dispatch orders and operation ticket samples of the same type are matched in a preset operation ticket database to obtain historical topology analysis results and ticket templates; Input the structured dispatch order data, the real-time topology analysis result, the historical topology analysis result, the ticket template, the preset custom ticket rule and the preset prompt word template into a preset large language model for ticket generation to obtain an initial operation ticket; Performing a security check on the initial operation ticket to obtain a security check result, wherein the security check result at least includes the checked initial operation ticket; The security verification result is displayed, and a target operation ticket is generated based on the interactive information of the security verification result.

2. The operation ticket generation method according to claim 1, characterized in that: The safety verification results also include optimization suggestions; The generating of a target operation ticket based on the interactive information of the security verification result includes: Obtaining interaction information after the user reviews the initial operation ticket based on the optimization suggestion; The initial operation ticket is modified based on the interactive information, and the modified items are marked on the modified target operation ticket.

3. The operation ticket generation method according to claim 1, characterized in that: After displaying the security verification result and generating a target operation ticket based on the interactive information of the security verification result, the method further includes: Feedback optimization is performed on the preset operation ticket generation rules and / or the operation ticket database based on the interactive information and the target operation ticket.

4. The operation ticket generation method according to claim 1, characterized in that: The method of performing dynamic topology analysis on the structured dispatch order data according to the current real-time device status data to obtain a real-time topology analysis result includes: Performing a multi-level topological analysis on the target device in the structured scheduling order data according to the current real-time device status data to obtain a set of associated devices corresponding to each level of the target device; The real-time device status of the target device and its associated device sets at each level is determined according to the current real-time device status data to obtain a real-time topology analysis result.

5. The operation ticket generation method according to claim 1, characterized in that: The method of matching the same type of historical dispatch orders and operation ticket samples in a preset operation ticket database according to the structured dispatch order data to obtain historical topology analysis results and ticket templates includes: Filtering historical dispatch orders and operation ticket samples of the same type in a preset operation ticket database according to the structured dispatch order data; Performing dynamic topological analysis on the historical dispatch order to obtain a historical topological analysis result; A ticket template is determined based on the operation ticket sample.

6. The operation ticket generation method according to claim 1, characterized in that: The performing of security verification on the initial operation ticket to obtain a security verification result includes: Comparing and analyzing the initial operation ticket with operation ticket samples of the same type to obtain a comparative analysis result; Performing a device status consistency check on the initial operation ticket based on the device status in the real-time topology analysis result, and performing an anti-error check based on an anti-error check logic to obtain an anti-error check result; A safety verification result is generated according to the comparison analysis result and the anti-mistake verification result.

7. The operation ticket generation method according to claim 1, characterized in that: The semantic analysis of the dispatch order to be processed is performed to obtain structured dispatch order data, including: Performing format analysis and conversion on the pending dispatch order to obtain dispatch order information in a target format; Analyze the dispatch order information by combining large language model technology and natural language processing technology to obtain an initial parsing result; The initial parsing result is verified and optimized through a preset rule engine to obtain structured dispatch order data.

8. An operation ticket generating device, characterized in that: The operation ticket generating device comprises: A parsing module, used for semantically parsing the dispatch order to be processed to obtain structured dispatch order data; A topology analysis module, used to perform dynamic topology analysis on the structured scheduling order data to obtain real-time topology analysis results; A matching module, used to match historical dispatch orders and operation ticket samples of the same type in a preset operation ticket database according to the structured dispatch order data, to obtain historical topology analysis results and ticket templates; A generation module, used for inputting the structured dispatch order data, the real-time topology analysis result, the historical topology analysis result, the ticket template and the preset prompt word template into a preset large language model to obtain an initial operation ticket; A security verification module is used to perform a security verification on the initial operation ticket to obtain a security verification result; The interactive module is used to display the security verification result and generate a target operation ticket based on the interactive information of the security verification result.

9. An operation ticket generating device, characterized in that: The operation ticket generating device comprises: a memory and at least one processor, wherein the memory stores instructions; The at least one processor calls the instructions in the memory to enable the operation ticket generating device to execute the operation ticket generating method according to any one of claims 1 to 7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instruction is read and executed, the operation ticket generation method as described in any one of claims 1-7 is executed.

Images