Power two-ticket automatic generation and checking method, device and medium

Abstract

The application relates to the technical field of artificial intelligence, and discloses a power two-ticket automatic generation and checking method, equipment and medium. The method comprises the following steps: obtaining power distribution network power failure application forms, accessory text data and electrical drawing image data; based on the semantic analysis of the serial number of the accessory text, automatically splitting an unstructured operation process into multiple groups of independent operation task sequences, and generating an operation ticket draft in combination with power safety rules; using OCR technology to analyze the electrical drawing image data to extract device topology information, and performing cross-modal consistency checking on the device topology information and the device information in the operation ticket draft; generating a final operation ticket and a work ticket based on the checking result, and automatically backfilling the operation ticket and the work ticket to corresponding modules of a power grid management platform according to business types. The application realizes the automatic generation of an operation ticket and a work ticket from a power failure application form and the mutual checking and verification of drawings and numbers, significantly improves the two-ticket preparation efficiency and accuracy, reduces the risk of human errors, and guarantees the safety of power operation.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method, device and medium for automatic generation and verification of two-tickets for electricity. Background Technology

[0002] In the operation and maintenance of power transmission, transformation, and distribution, operation tickets and work tickets (collectively referred to as "two tickets") are core control tools for ensuring operational safety and preventing misoperation. According to the "Power Safety Work Regulations," any power outage maintenance work must be based on a power outage application form, with operation tickets prepared by maintenance personnel and work tickets prepared by the construction unit, and both must be reviewed and approved before execution. The accuracy of these two tickets is directly related to the safe operation of the power grid and the safety of the workers.

[0003] Currently, the preparation and verification of work orders mainly rely on manual labor. Existing technical solutions typically include: retrieving power outage application forms from the power grid management platform, reading the unstructured text attached to the application form, manually entering the work order content; filling out the work order based on the application form information; and comparing the work order with the application form and drawings word by word for consistency. This method has the following shortcomings: First, in the data acquisition stage, existing technologies require manual opening of each power outage application form and its attachments (power outage operation procedures, power restoration operation procedures, mode change orders, electrical drawings, etc.), and manual downloading or copying of text content, which cannot achieve automatic collection of multi-source heterogeneous data. This results in a long data preparation stage and an easy omission of attachments.

[0004] Second, in the operation ticket generation stage, existing technology cannot automatically parse the serial number markers (such as "(1)(2)(3)" or "1, 2, 3") in the attachment text, nor can it split the unstructured operation process into multiple independent operation tickets based on the serial number boundaries. After manually reading the attachments, it is necessary to determine how many operation tickets should be generated and then enter the operation steps one by one. This manual splitting method is extremely inefficient and prone to omissions or incorrect ordering, especially when an application form contains multiple tasks such as power outage, power restoration, and mode change, the human error rate increases significantly. In addition, existing technology lacks the ability to automatically generate a standardized sequence of operation steps in conjunction with power safety rules. For example, it cannot automatically insert mandatory steps such as "voltage testing" and "air pressure check", which may result in the generated operation tickets not meeting safety requirements.

[0005] Third, in the verification process, existing technologies lack effective cross-modal consistency verification methods. Verifiers must simultaneously compare the power outage application form text and electrical drawing images, meticulously checking equipment names, numbers, and the logical relationships of operational steps word by word. This process relies entirely on manual labor, which is not only inefficient but also highly susceptible to errors due to visual fatigue or lack of experience, such as missing typos (e.g., "F16" mistakenly written as "F1G") or logical conflicts (e.g., pulling the knife switch before disconnecting the circuit breaker). In particular, electrical drawings, as independent image modal data, never have their equipment topology information (connection relationships, equipment coordinates, etc.) automatically extracted and compared with the text document, resulting in a "separation of drawings and data," which prevents the drawings from fulfilling their role in verifying the document.

[0006] Fourth, in the process of filling in and backfilling application forms, the operation tickets and work tickets generated by existing technology need to be manually entered into the corresponding modules of the power grid management platform item by item. Different types of application forms (infrastructure, maintenance, user projects) correspond to different backfilling paths and forms. Operators need to be familiar with these differences and manually select them, which is tedious and prone to errors. The planned time of the work ticket also needs to be manually calculated based on the application time, further increasing the probability of errors.

[0007] In summary, existing technologies suffer from incomplete data collection, reliance on manual splitting of operation tickets, lack of cross-modal consistency verification, and low backfilling efficiency, failing to achieve efficient, accurate, and automated generation and verification of operation tickets. Therefore, there is an urgent need for a method that can automatically acquire multi-source data, semantically parse attachment sequence numbers to split multiple operation tickets, utilize OCR and topology diagrams for cross-validation of data and diagrams, and automatically backfill into different business modules to improve the efficiency and reliability of operation ticket preparation and ensure the safety of power operations. Summary of the Invention

[0008] This invention provides a method, device, and medium for automatic generation and verification of two-tickets for electricity, aiming to solve the technical problems of low efficiency and poor reliability in the preparation of two-tickets in the prior art.

[0009] To achieve the aforementioned objectives, the first aspect of this invention proposes a method for automatically generating and verifying two electricity tickets, comprising: Obtain the power outage application form and its attachments (text data) and electrical drawing image data; Based on the semantic parsing of the serial numbers in the attachment text, the unstructured operation process is automatically broken down into multiple independent operation task sequences, and a draft operation ticket is generated in conjunction with power safety rules. OCR technology is used to parse electrical drawing image data to extract equipment topology information, and the equipment topology information is then cross-modal consistency verification is performed with the equipment information in the draft operation ticket. Based on the verification results, the final operation ticket and work ticket are generated and automatically populated back into the corresponding module of the power grid management platform according to the business type.

[0010] Furthermore, the sequence number semantic parsing based on the attachment text automatically breaks down the unstructured operation process into multiple independent operation task sequences, including: Regular expression matching is performed on the attached text to identify preset format serial number markers used to identify task levels in the text; wherein, the preset format serial number markers include at least one of Arabic numeral serial numbers, Roman numeral serial numbers, letter serial numbers, Chinese numeral serial numbers, or serial numbers in parentheses; Based on the boundaries marked by the preset format sequence number, the overall operation process is divided into multiple independent operation task blocks, and each task block generates an independent operation ticket.

[0011] Furthermore, the process of generating a draft operation ticket by combining power safety rules includes: Establish a power equipment entity dictionary to perform named entity recognition for switches, disconnectors, and lines in the operation task block; Based on the electrical connection relationships of the equipment and the safety regulations, construct a dependency graph between the operation steps; If a step is detected to be missing or out of order, standard safety procedures will be automatically inserted to generate a sequence of standard operating procedures.

[0012] Furthermore, the step of using OCR technology to parse electrical drawing image data to extract equipment topology information includes: OCR can be used to identify equipment numbers, equipment names, and connection relationships in drawings. Convert the equipment coordinates and connection relationships in the drawings into a structured topology diagram.

[0013] Furthermore, the step of performing cross-modal consistency verification between the device topology information and the device information in the draft operation ticket includes: Compare the equipment names and numbers in the draft operation ticket with the equipment information in the structured topology diagram; If the draft operation ticket contains devices that are not present in the topology diagram, or if the device connection relationships conflict with the topology logic, the verification will fail and an alarm will be triggered.

[0014] Furthermore, the step of generating the final operation ticket and work ticket based on the verification results, and automatically backfilling them to the corresponding modules of the power grid management platform according to the business type, includes: A draft operation ticket is generated based on the standardized operation procedure sequence, and its completeness is compared with the key operation items of the original power outage application form. A unique work order is generated based on the same power outage application form. The work location and safety measures are automatically extracted. The start time of the power outage application form is shifted forward by a predetermined time, and the end time of the application is shifted backward by a predetermined time, so as to determine the planned start time and planned end time of the work order. The generated operation tickets and work tickets will be automatically populated back into the corresponding modules of the power grid management platform according to the business type.

[0015] Furthermore, the business types include infrastructure construction, maintenance, and user projects, and the corresponding backfilling modules are as follows: Backfilling for infrastructure projects should be moved to the safety management and construction operation plan module. Repair-related items are backfilled to the repair project workbench module; User engineering data is backfilled into the maintenance and repair plan execution module.

[0016] Furthermore, the method for automatically generating and verifying electricity tickets also includes: constructing a ticket knowledge management base, which includes a historical ticket database, a safety specification database, an operation specification database, a personnel qualification database, and a typical ticket database; When generating operation tickets or work tickets, the system automatically matches typical ticket templates, automatically calls safety regulations for compliance determination during verification, and associates and verifies personnel qualifications with work ticket permissions.

[0017] A second aspect of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the automatic generation and verification method for power tickets as described in any of the preceding claims.

[0018] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the steps of the automatic generation and verification method for power tickets as described in any of the preceding claims.

[0019] Compared with the prior art, the automatic generation and verification method, equipment, and medium for power tickets of the present invention have the following advantages: This invention enables the automatic acquisition of heterogeneous data from multiple sources, improving data preparation efficiency. Specifically, it first acquires the text data of power outage application forms and their attachments, along with electrical drawing image data, changing the traditional method of manually searching and downloading attachments one by one. By automatically filtering unexecuted application forms from the power grid management platform (defaulting to the next month) and acquiring all attachments (power outage procedures, power restoration procedures, method change orders, and electrical drawings), it ensures data integrity and timeliness. This step lays the data foundation for subsequent intelligent processing, avoids missing operation tickets due to missing attachments, and significantly reduces the time cost of manual retrieval and downloading.

[0020] This invention achieves automatic splitting of multiple operation tickets based on sequence number semantic parsing, significantly improving the efficiency and accuracy of ticket preparation. Specifically, based on the sequence number semantic parsing of the attachment text, this invention automatically splits unstructured operation processes into multiple independent operation task sequences, and generates draft operation tickets by combining them with power safety rules. Unlike existing technologies that rely on manual reading of sequence numbers and manual splitting, this invention can automatically identify various sequence number markers in the text (such as "(1)(2)(3)", "1, 2, 3", Chinese numerals, etc.), and use the sequence number boundaries as the dividing basis to split tasks such as power outage, power restoration, and mode change in an application form into multiple independent operation tickets. At the same time, combined with a preset power safety rule mapping table, the natural language operation steps are converted into a standard step sequence that meets the safety requirements (such as mapping "confirm xx switch" to "verify name number position is correct"). This technology reduces the manual splitting and input work that originally required tens of minutes to a second-level automatic completion, and avoids human errors such as omissions and misorders from the source, significantly improving the efficiency and compliance of operation ticket preparation.

[0021] This invention utilizes OCR and topology diagrams to achieve cross-modal consistency verification, constructing a multi-dimensional quality firewall. Specifically, this invention uses OCR technology to parse electrical drawing image data to extract equipment topology information, and then performs cross-modal consistency verification between this equipment topology information and the equipment information in the draft operation ticket. In existing technologies, electrical drawings are only used as static references, and the equipment names, numbers, and connection relationships contained therein are never automatically extracted and compared with the content of the ticket. This invention is the first to fuse the image modality (drawings) and the text modality (draft operation ticket), using OCR to identify the equipment and connection lines in the drawings, generating a structured topology diagram, and then automatically comparing whether the equipment names and numbers in the operation ticket exist in the topology diagram, and whether the operation sequence conflicts with the electrical connection logic (such as pulling the knife switch before disconnecting the circuit breaker). This cross-modal verification can effectively detect equipment name errors caused by typos or OCR recognition errors (such as "F16" mistakenly written as "F1G"), as well as operation sequences that violate safety regulations. It realizes automatic machine verification to replace manual word-by-word comparison, greatly improving the coverage and accuracy of verification, and constructing a multi-dimensional quality firewall for power operations.

[0022] Based on the verification results, the final tickets are automatically generated and backfilled according to the business type, achieving closed-loop automation. Specifically, this invention generates final operation tickets and work tickets based on the verification results and automatically backfills them to the corresponding modules of the power grid management platform according to the business type. In the prior art, after manually generating tickets, different business modules (infrastructure, maintenance, and user projects correspond to different paths) still need to be manually filled in, and the planned time of the work ticket needs to be manually offset and calculated. After the verification is passed, this invention automatically generates the final version of operation tickets (multiple tickets) and work tickets (one unique ticket), automatically extracts the work location and safety measures, and automatically offsets and determines the planned start and end times according to the application time (e.g., start time 2 hours earlier, end time 2 hours later). Subsequently, according to the business type of the application form, the corresponding module path and form of the power grid management platform are automatically selected to complete the data backfilling. Users only need to submit with one click to complete the entire process. This technology achieves full automation from application form to final archiving, eliminates manual copy and paste operations across systems and modules, significantly reduces the data entry error rate, and improves overall work efficiency.

[0023] In summary, this invention, through a complete technical chain of "automatic data acquisition—sequence number semantic decomposition—safety regulation generation—image and data mutual verification—automatic backfilling," solves the pain points of existing technologies, such as low efficiency, susceptibility to errors, difficulty in verification, and poor knowledge reuse. Compared with existing technologies, this invention reduces the time for two-ticket preparation from days to minutes, and improves the verification coverage from sampling to full automatic comparison, eliminating operational risks caused by incorrect equipment names or missing steps from the source. It significantly improves the safety and efficiency of power operation and maintenance, and has good prospects for widespread application. Attached Figure Description

[0024] Figure 1 A flowchart illustrating an embodiment of the invention for the automatic generation and verification of two electricity tickets; Figure 2 This is a schematic block diagram of a computer device according to an embodiment of the invention.

[0025] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0027] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of features, integers, steps, operations, elements, modules, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, modules, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any modules and all combinations of one or more associated listed items.

[0028] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0029] The technical solution of the present invention will be described in detail below with reference to a specific example. This example uses the "10kV F16 Ganghong Line Distribution Network Power Outage Maintenance Project of South District Bureau" as a scenario, but the scope of protection of the present invention is not limited to this example.

[0030] Reference Figure 1 This invention provides a method for automatically generating and verifying two power tickets, comprising the following steps: S101: Obtain the power outage application form and its attachments (text data) and electrical drawing image data.

[0031] A power outage application form is a formal document submitted by the operation and maintenance unit requesting a power outage for maintenance of a specific power line or equipment. It includes information such as the outage scope, working hours, and safety requirements. Attached text data refers to the operational procedure documents accompanying the power outage application form, including unstructured text such as "Power Outage Operation Procedures," "Power Restoration Operation Procedures," and "Mode Change Order." Electrical drawing image data refers to scanned copies or photographs of electrical wiring diagrams, primary system diagrams, and other drawings related to the outage equipment. In this step, the system retrieves unexecuted distribution network power outage applications from the South District Bureau from the power grid management platform (asset domain), filters out terminated applications, and defaults to querying data within the next month. Taking the "South District Bureau 10kV F16 Ganghong Line Distribution Network Power Outage Maintenance Project" as an example, the application form number obtained by the system is "DP-2025-00123", and its attachments include "Power Outage Operation Steps.docx" (containing "(1) Confirm that the Ganghong Line F16 switch is in the closed position; (2) Disconnect the Ganghong Line F16 switch; (3) Open the Ganghong Line F16 disconnector"), "Power Restoration Operation Steps.docx", "Mode Change Form.pdf", and a "Ganghong Line Primary Wiring Diagram.jpg". This step realizes the automatic collection of multi-source heterogeneous data, providing a complete data foundation for subsequent intelligent analysis and generation of two tickets, avoiding the tedious operation of manual searching and downloading.

[0032] S102: Based on the semantic parsing of the serial numbers in the attachment text, the unstructured operation process is automatically split into multiple independent operation task sequences, and a draft operation ticket is generated in combination with power safety rules.

[0033] Sequence semantic parsing refers to identifying sequence markers (such as "1.", "(1)", "一、", etc.) in text through algorithms like regular expressions, and splitting continuous text into independent operation task blocks according to the hierarchy and order of the sequences. The draft operation ticket refers to the content of the operation ticket that is initially generated and has not been verified, including basic information such as operation tasks, operation steps, and equipment names. Electrical safety rules include mandatory operation sequences, equipment operation logics (such as "disconnect the switch first, then open the disconnecting switch"), grounding wire installation requirements, etc. in the "Electrical Safety Work Regulations". In this step, the system scans each line of the attached text, identifies sequence boundaries, and splits multiple operation tasks in one attachment into multiple operation tickets. For example, if there are three sequences (1)(2)(3) in the power outage operation steps, three operation tickets are generated. Then, a standardized operation ticket step sequence is generated according to a preset safety regulation mapping table (such as mapping "confirm xx switch" to "check the name, number, and position of xx switch are correct"). In this example, the steps of operation ticket 1 generated after parsing "power outage operation steps.docx" include: "check the name, number, and position of Ganghong line F16 switch are correct"; "check the SF6 pressure gauge indication of F16 switch is normal; remove the 'Do not close, someone is working on the line!' sign; check the line-side charged indicator of F16 switch shows no power"; "open F16 disconnecting switch; check F16 disconnecting switch is in the open position". At the same time, the "power transfer operation task" and "restoration operation task" in the mode change form are split into independent operation tickets respectively. This step reduces the work of manually reading and splitting item by item for dozens of minutes to be automatically completed in seconds, and completely avoids missing items or incorrect sequences.

[0034] S103: Use OCR technology to parse the electrical drawing image data to extract equipment topology information, and perform cross-modal consistency verification on the equipment topology information and the equipment information in the draft operation ticket.

[0035] OCR (Optical Character Recognition) is a technology that converts text in images into editable text. Equipment topology information includes equipment names, numbers, and electrical connections between equipment (such as the connection sequence of switches, disconnectors, and lines). Cross-modal consistency verification involves cross-comparing the equipment information in the text modality (draft operation ticket) with the image modality (electrical drawing topology diagram) to verify consistency. In this step, after the system uploads the electrical drawing image, OCR recognizes the equipment text in the image (such as "F16 switch" and "Ganghong line") and analyzes the line connections to form a structured topology diagram. Then, the equipment names and numbers appearing in the draft operation ticket are compared with the equipment list in the topology diagram. If any equipment in the operation ticket is found to be absent from the drawing, or if the connections between equipment conflict with the drawing, the verification fails and an alarm is triggered. In this example, after uploading "Ganghong line primary wiring diagram.jpg", OCR recognizes the equipment as: "F16 switch", "F16 disconnector", "Ganghong line", and "F17 tie switch". The draft operation ticket states "Disconnect switch F18," but switch F18 is not present in the topology diagram. The system determines the verification fails and displays an alarm: "Equipment F18 switch is not shown in the drawing; please check." This step provides a verification source independent of text from an image perspective, effectively identifying equipment name errors caused by typos or memory mistakes.

[0036] S104: Generate the final operation ticket and work ticket based on the verification results, and automatically fill them back into the corresponding modules of the power grid management platform according to the business type.

[0037] In this step, if the verification passes, the final operation ticket and work ticket are generated. A unique work ticket is generated based on the same power outage application form, with the planned start time shifted forward by 2 hours and the planned end time shifted backward by 2 hours. Backfilling refers to automatically filling the generated ticket data into the forms of the designated business modules on the power grid management platform. In this example, after verification, 3 operation tickets and 1 work ticket are generated. The application form type is "User Project." The system automatically opens the "Maintenance and Repair Management - Plan Management - Plan Execution - Fill in Associated Operation Tickets" page on the power grid management platform, filling in operation tickets 1, 2, and 3; then it opens the "Fill in Associated Work Tickets" page and fills in the work ticket. The user only needs to click "Submit" to complete the process. This step achieves one-click generation and automatic archiving from the application form to the final ticket, significantly reducing manual data entry.

[0038] In summary, compared with the prior art, the automatic generation and verification method for power tickets in this embodiment reduces the compilation time of the two tickets from days to minutes, and improves the verification coverage from random inspection to full automatic comparison, thus eliminating operational risks caused by incorrect equipment names or missing steps from the source.

[0039] In one embodiment, the above-mentioned semantic parsing of serial numbers based on attachment text automatically splits an unstructured operation process into multiple groups of independent operation task sequences, including the steps: S201: Perform regular matching on the attachment text to identify preset format serial number markers used to identify task levels in the text. Among them, the preset format serial number markers include at least one of Arabic numeral serial numbers, Roman numeral serial numbers, letter serial numbers, Chinese numeral serial numbers, or numbered serial numbers with parentheses.

[0040] Regular matching refers to using regular expressions to search for strings that conform to specific patterns in the text. The preset format serial number markers are a pre-defined set of serial number formats, such as "(1)", "1.", "一、", "A.", "①", etc. In this step, the system maintains a serial number pattern library containing regular expressions for various serial numbers. For example, "\d+." corresponds to "1.", "\d+" corresponds to "(1)", "[一二三四五]" corresponds to Chinese numerals, "[A-Z]." corresponds to letter serial numbers, etc. Match the attachment text line by line to identify the serial numbers and their levels. In this example, the content of the attachment text is: "1. Disconnect the F16 switch; 1.1 Check the SF6 gas pressure; 2. Open the F16 disconnecting switch." The regular expression "^\\d+." matches "1." and "2." as first-level serial numbers; "^\\d+\\.\\d+" matches "1.1" as a second-level serial number. This step can handle different serial number styles of various legacy documents and has high robustness.

[0041] Step 202: According to the boundaries of the preset format serial number markers, divide the overall operation process into multiple groups of independent operation task blocks, and generate an independent operation ticket for each group of task blocks.

[0042] In this step, the system uses the first-level serial numbers as boundaries to divide the text into multiple task blocks. Each task block contains all the content under that serial number (including second-level serial numbers). In this example, the above text is divided into two task blocks: Task block 1 (corresponding to operation ticket 1) content is "Disconnect the F16 switch; Check the SF6 gas pressure"; Task block 2 (corresponding to operation ticket 2) content is "Open the F16 disconnecting switch." This step ensures the accuracy and integrity of the splitting of multiple operation tickets.

[0043] In summary, this embodiment can handle different serial number styles of various legacy documents, has high robustness, and ensures the accuracy and integrity of the splitting of multiple operation tickets.

[0044] In one embodiment, the above-mentioned generation of an operation ticket draft in combination with power safety rules includes the steps: S301: Establish a power equipment entity dictionary and perform named entity recognition on switches, disconnecting switches, and lines in the operation task blocks.

[0045] The power equipment entity dictionary is a database containing equipment types (switches, disconnectors, lines, transformers, etc.) and their standard names. Named Entity Recognition (NER) extracts specific types of entities, such as equipment names, from text. In this step, the system uses a pre-trained power domain NER model to extract equipment names and operation verbs from operation task blocks. In this example, the task block text "Disconnect F16 switch" is identified by NER as the equipment entity "F16 switch" and the operation verb "disconnect". This step transforms unstructured text into structured data, laying the foundation for subsequent logical verification.

[0046] S302: Based on the electrical connection relationship of the equipment and the safety logic, construct a dependency relationship diagram between operation steps and calculate the dependency missing risk index.

[0047] A dependency graph is a directed graph with operation steps as nodes and the order and logical dependencies between steps as edges. Safety regulations refer to mandatory rules such as "the switch must be turned off before the disconnector can be opened" or "voltage must be tested before the grounding wire can be installed".

[0048] This embodiment introduces an original dependency missing risk index formula. The sequence of operation steps is defined as S = {s1, s2, ..., s...}. n The standard dependency edge set required by safety regulations is E. std Steps i Dependency Loss Risk Index R(s) i )for:

[0049] in: Pred(s i ) is the s specified in the safety regulations. i The set of prerequisite steps; δ(s j ,s i ) is an indicator function; if s in the actual sequence j Appeared in s i The value is 1 if it is not present, and 0 otherwise. w j,i The weights are based on the value of 0 to 1 (e.g., 0.9 between disconnecting the switch and opening the knife switch, and 1.0 between voltage testing and grounding).

[0050] Decision rule: When R(s) i When the value is greater than 0.5, it is determined that the step is missing or the order is incorrect, and automatic insertion is triggered.

[0051] The unique features and advantages of this formula include: traditional methods rely solely on fixed rules (such as "insert if a prerequisite step is missing"), which are prone to missed or false positives due to improper rule threshold settings. This formula, for the first time, integrates the size of the prerequisite step set, the degree to which the actual order is satisfied, and the dependency weights into a continuous risk index. Specifically, this is achieved by introducing dependency weight w. j,i This method can distinguish the importance of different preceding steps (for example, "disconnecting the switch" is far more dependent on "opening the knife switch" than "checking the air pressure"), making risk quantification more precise. The formula has advantages such as strong interpretability, adjustable thresholds, and applicability to complex operation sequences.

[0052] In this example, the draft operation ticket only includes "open the F16 disconnect switch" but not "disconnect the F16 switch". The standard pre-step Pred(open disconnect switch) = {disconnect switch}, δ=0, w=0.9, therefore R=0.9>0.5, and the system determines it is missing. This step, through quantitative risk assessment, accurately identifies the missing step, avoiding missed judgments caused by mechanical rule matching.

[0053] S303: If a step is detected to be missing or out of order, standard safety procedures will be automatically inserted to generate a sequence of standard operating procedures.

[0054] In this step, the system automatically inserts the required safety procedure at the missing location. In this example, the inserted sequence is: "Disconnect switch F16; Check SF6 gas pressure at switch F16; Remove the 'Do Not Close' sign; Check that there is no power on the line side; Open switch F16; Check that switch F16 is indeed in the open position." This step ensures that every generated operation ticket complies with mandatory safety requirements, preventing the omission of critical steps due to human negligence from the outset.

[0055] In summary, this embodiment accurately identifies missing steps through quantitative risk assessment, ensuring that every generated operation ticket complies with mandatory safety regulations, thus preventing the omission of critical steps due to human negligence from the source.

[0056] In one embodiment, the above-mentioned use of OCR technology to parse electrical drawing image data to extract equipment topology information includes: S401: Identify equipment numbers, equipment names, and connection relationships in drawings using OCR.

[0057] In this step, OCR not only recognizes text but also uses image processing algorithms to detect the start and end points of lines, establishing the connection relationships between devices. In this example, the drawing contains the text "F16 switch" within a rectangle and "F16 disconnector" within another rectangle, connected by lines. OCR identifies the devices "F16 switch" and "F16 disconnector" and records the connection relationship. This step automatically extracts the topology from the image, eliminating the need for manual redrawing.

[0058] S402: Convert the equipment coordinates and connection relationships in the drawings into a structured topology diagram.

[0059] A structured topology graph is a graph data structure represented by nodes (devices) and edges (connections), which can be stored in a database. In this step, the system stores the device coordinates, names, numbers, and connection relationships into the graph database, forming a queryable topology graph. In this example, a topology graph in JSON format is generated: {"nodes":[{"id":"F16 switch","type":"breaker"},{"id":"F16 disconnector","type":"disconnector"}],"edges":[{"from":"F16 switch","to":"F16 disconnector"}]}. This step provides machine-readable standardized input for subsequent cross-modal verification.

[0060] In summary, this embodiment automatically extracts the topology from the image without requiring manual redrawing, providing machine-readable standardized input for subsequent cross-modal verification.

[0061] In one embodiment, the above-mentioned cross-modal consistency verification of the device topology information and the device information in the draft operation ticket includes the following steps: S501: Compare the equipment names and numbers in the draft operation ticket with the equipment information in the structured topology diagram, and use the fuzzy matching similarity formula.

[0062] In this step, the system extracts all device names and numbers from the draft operation ticket and matches them with the node set in the topology diagram. Since OCR recognition may contain errors (e.g., "F16" is recognized as "F1G"), and manual input of the operation ticket may also contain typos, a fuzzy matching similarity formula is introduced to reduce these errors: Let 's' be the device name string in the operation ticket, and 't' be the device name string in the topology graph. The similarity Sim(s,t) is: Sim(s,t)=α Lev(s,t)+β LCS(s,t)+γ ED(s,t) in: Lev(s,t)=1-(edit distance(s,t) / max(∣s∣,∣t∣)) LCS(s,t) = 2 × |Longest Common Subsequence(s,t)| / (|s| + |t|); ED(s,t) is the device type matching factor (1.0 for the same type, 0.8 for semantically similar "switch" and "circuit breaker", otherwise 0). α+β+γ=1. In this embodiment, α=0.4, β=0.4, γ=0.2, α=0.4, β=0.4, and γ=0.2.

[0063] Judgment rules: Sim≥0.85: Match passed; 0.6≤Sim<0.85: Fuzzy matching, triggering manual confirmation; Sim<0.6: Mismatch, triggering an alarm.

[0064] The unique advantage of this formula lies in its ability to handle OCR recognition errors and synonymous device names (such as "circuit breaker" and "switch"), as traditional string comparison methods rely on exact matching or single edit distance. This innovative formula integrates three dimensions: edit distance, longest common subsequence, and semantic type matching, assigning different weights to each. The longest common subsequence factor tolerates insertion or deletion errors while maintaining character order, while the device type matching factor addresses the normalization issue of synonyms in the power industry. This formula maintains high accuracy while significantly reducing the false alarm rate caused by minor errors.

[0065] In this example, the draft operation ticket states "F1G switch" (which should be F16 switch), and the topology diagram shows "F16 switch". Calculating Lev = 1 - 1 / 3 = 0.667, LCS = 2 × 2 / (3 + 3) = 0.667, and ED = 1.0, we get Sim = 0.4 × 0.667 + 0.4 × 0.667 + 0.2 × 1.0 = 0.7336, which falls within the interval [0.6, 0.85). The system triggers manual confirmation: "Should F1G switch be F16 switch?" The system automatically corrects the value after user confirmation.

[0066] This step uses fuzzy matching to automatically correct OCR recognition errors or human typos, reducing false alarms.

[0067] S502: Check whether the device connection relationship in the draft operation ticket conflicts with the topology logic, and calculate the topology logic conflict coefficient.

[0068] To quantify the degree of conflict, this step introduces a conflict coefficient formula. The sequence of operation steps in the operation ticket is defined as O = {o1, o2, ..., o}. m}, where each operation o i Involves a device d i Extract the device connection matrix C from the topology graph, where Cp,q=1 indicates that device p and device q have a direct electrical connection. The conflict coefficient Φ is:

[0069] in: I(Operation Type Conflict) is an indicator function; it is 1 if the operation order violates the safety rules, and 0 otherwise. λ is the attenuation coefficient, and in this embodiment, λ = 0.5; e λ(j i) The time weights are used, and the more adjacent the steps are, the higher the conflict weight.

[0070] If Φ>0, a logical conflict is determined, and an alarm is triggered.

[0071] The unique feature and advantage of this formula lies in the fact that existing technologies can only detect the presence of equipment, but cannot determine whether the operation sequence is consistent with the electrical topology logic. This formula, for the first time, integrates the operation sequence, electrical connection relationship, and temporal proximity into a conflict coefficient. In particular, it introduces an exponentially decaying weight e. λ(j i) This allows conflicts between adjacent steps to have a higher alarm priority, as incorrect sequences of adjacent steps are often the most dangerous operational errors. The formula quantitatively assesses the degree of conflict, rather than using a simple binary judgment, thus providing a more refined alarm classification.

[0072] In this example, the operation ticket steps are: o1 = "Open F16 disconnect switch", o2 = "Disconnect F16 switch". The topology diagram shows that the F16 disconnect switch and the F16 switch are directly connected, C=1. There is an operation type conflict: opening the disconnect switch before disconnecting the switch violates safety regulations, I=1. ji=1, e 0.5 If Φ = 0.6065, then Φ = 0.6065 > 0, triggering the alarm "Operation sequence error: Switch F16 should be disconnected first, then the F16 disconnector should be opened." This step quantifies the degree of conflict and prioritizes the nearest erroneous step, helping users quickly locate and correct the error.

[0073] In summary, compared with the simple string comparison in the prior art, this invention can tolerate OCR errors and typos, while automatically detecting electrical logic conflicts, thus building a smarter and more secure quality firewall.

[0074] In one embodiment, the process of generating the final operation ticket and work ticket based on the verification results and automatically backfilling them to the corresponding module of the power grid management platform according to the business type includes the following steps: S601: Generate a draft operation ticket based on the standardized operation procedure sequence and compare its completeness with the key operation items of the original power outage application form.

[0075] Critical operation items refer to mandatory operations explicitly required in the power outage request, such as "the F16 switch must be disconnected." In this step, the system compares the steps on the generated operation ticket with the critical operation items in the request to ensure nothing is omitted. In this example, the request requires "disconnecting the F16 switch," and the generated operation ticket includes this step, thus passing the completeness comparison. This step ensures that the requirements of the request are fully implemented in the operation ticket.

[0076] S602: Generate a unique work order based on the same power outage application form, automatically extract the work location and safety measures, and shift the application start time of the power outage application form forward by a predetermined time and the application end time backward by a predetermined time to determine the planned start time and planned end time of the work order.

[0077] In this step, the planned start time = application start time - 2 hours, and the planned end time = application end time + 2 hours. In this example, the "Application Start Time" on the application form is 09:00 on December 15, 2025, and the "Application End Time" is 17:00 on December 15, 2025. Therefore, the planned start time for the work order is 07:00 on December 15, 2025, and the planned end time is 19:00 on December 15, 2025. This step allows sufficient preparation and wrap-up time for on-site operations, which aligns with actual work practices.

[0078] S603: Automatically populate the generated operation tickets and work tickets back to the corresponding modules of the power grid management platform according to the business type.

[0079] In this step, the system selects different backfill paths based on the classification of the power outage application form. In this example, the business type is "User Project," and the system automatically opens the "Maintenance and Repair Management - Plan Management - Plan Execution - Fill in Related Operation Ticket" page of the power grid management platform and fills in the data. This step can adapt to the process differences of different business lines to achieve accurate backfilling.

[0080] In summary, this embodiment achieves a closed loop in invoice generation, seamlessly integrating the automatically generated results into the existing business system without requiring manual secondary data entry.

[0081] Furthermore, the above-mentioned business types include infrastructure construction, maintenance, and user projects, and the corresponding backfilling modules are as follows: infrastructure construction is backfilled to the safety management and construction operation plan module; maintenance is backfilled to the repair project workbench module; and user projects are backfilled to the maintenance and repair plan execution module.

[0082] In this example, if the type is "infrastructure", the API of the power grid management platform is called: / security / construction-plan / weekly-plan / {id} / edit-work-ticket; If the type is "Repair", then call: / repair-project / workbench / single-project / {id} / weekly-plan-detail / edit-work-ticket; If the type is "User Project", then call: / maintenance / plan-execution / fill-related-work-ticket.

[0083] This embodiment can be fully adapted to the existing multi-entry architecture of the power grid management platform. The invention can be used without modifying the platform, which improves practicality and deployment compatibility.

[0084] In one embodiment, the method for automatically generating and verifying two electricity tickets further includes the following steps: S801: Construct a knowledge management database for two types of tickets, including a historical ticket database, a safety specification database, an operational specification database, a personnel qualification database, and a typical ticket database.

[0085] The historical ticket database stores archived historical operation tickets and work tickets; the safety specification database stores structured texts of the "Safety Regulations" clauses; the operation specification database stores standardized operation instructions; the personnel qualification database stores qualification certificate information of construction personnel and work supervisors; and the typical ticket database stores standard operation ticket and work ticket templates for typical scenarios, each template containing a fixed step framework and replaceable placeholders (such as {line name}, {switch number}). In this step, the system imports or synchronizes the above data in batches or in real time from the data center and operation and maintenance database, supporting batch import of Excel and CSV formats. In this example, 1000 historical operation tickets are imported and indexed; the full text of the "Power Safety Work Regulations" is imported and the clause numbers are marked; the construction personnel qualification table, including name, certificate number, and validity period, is imported; and the typical ticket template database is imported. This step provides a knowledge base for intelligent generation and verification.

[0086] S802: When generating operation tickets or work tickets, it automatically matches typical ticket templates and uses a multi-feature weighted matching scoring formula.

[0087] Let the feature vector of the current application form be F=(f1,f2,…,f n The eigenvector of a typical ticket template T is G. T =(g1,g2,…,g n The matching score Match(T) is:

[0088] in: w kFor feature weights, ∑w k =1; The features in this embodiment include: equipment voltage level (w1=0.25), operation type (power outage / power restoration, w2=0.3, equipment type (line / transformer / switch cabinet, w3=0.2), working environment (indoor / outdoor / high altitude, w4=0.15), and applicant (w5=0.1). Sim k (f k ,g k ) is the similarity function for the k-th feature (1 for categorical matching and 0 otherwise, and Gaussian kernel for numerical matching); Freq T Let T be the number of times template T has been used in the past year, and N be the total number of times all templates have been used. Age T Let T be the number of days since the last update of template T, and μ be the decay coefficient. In this example, μ = 0.01.

[0089] The system selects the template with the highest Match(T) as the recommended template. If the score is lower than the threshold of 0.6, the system prompts the user to select a template manually.

[0090] The unique feature and advantage of this formula lies in the fact that traditional template matching relies solely on keyword co-occurrence or simple similarity, failing to distinguish between the maturity and timeliness of templates. This formula innovatively introduces two dynamic factors: one is the frequency factor. This results in high-frequency, mature templates receiving bonus points, reflecting an "experience preference"; secondly, the time decay factor e μ AgeT This reduces the score of outdated templates that haven't been updated in a long time, encouraging the use of the latest standardized templates. Furthermore, the multi-feature weighted structure allows for flexible adjustment of weights based on different regions and business scenarios, offering strong configurability.

[0091] In this example, the current application has the following characteristics: voltage level 10kV, operation type power outage, equipment type line, operating environment outdoor, and applicant unit South District Bureau. The typical ticket database contains template A (general template) and template B (South District Bureau specific template). The calculated Match(B) = 0.515 > Match(A) = 0.463, so the system recommends template B and replaces the placeholder {line name} with "Ganghong Line" and {switch number} with "F16". This step automatically selects the most suitable, mature, and up-to-date typical ticket template through a comprehensive scoring system that considers multiple feature weights, frequency preferences, and time decay.

[0092] Step 803: Automatically invoke safety regulations during verification to determine compliance.

[0093] In this step, the system compares each step of the operation ticket with the corresponding clause in the safety regulation library. If a clause is violated, an alarm is triggered. In this example, for the operation ticket step "Install grounding wire," the system matches the safety regulation clause "3.4.2" to check if the prerequisite step "Verification of electricity" is present. If not, an alarm is triggered. This step automates the safety regulation compliance check, replacing manual review of safety regulations.

[0094] Step 804: Verify the association between personnel qualifications and work order permissions.

[0095] In this step, the system checks whether the person in charge of the work, the supervisor, and the operator listed on the work order are in the personnel qualification database and whether their certificates are valid. In this example, the person in charge of the work is "Li Si," and the qualification database shows that his high-voltage electrician certificate is valid until December 20, 2025. The current date is December 15, 2025, so it is valid and passes the check. This step ensures that the qualifications of the workers are compliant and improves the level of construction safety management.

[0096] In summary, compared with the prior art of manually selecting templates or simple keyword matching, this invention can dynamically evaluate the applicability, maturity and timeliness of templates, significantly improve the standardization level and efficiency of two-ticket generation, and at the same time ensure the compliance of the qualifications of the operators.

[0097] Reference Figure 2 The present invention also provides a computer device, the internal structure of which can be as follows: Figure 2 As shown. The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor is designed to provide computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores operating devices, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores data such as power outage application forms and their attachments (text data) and electrical drawing images. The network interface is used to communicate with external terminals via a network connection. Furthermore, the computer device may also include input devices and a display screen. When the computer program is executed by the processor, it implements the automatic generation and verification method for power tickets as described in any of the above embodiments. Those skilled in the art will understand that... Figure 2 The structures shown are merely block diagrams of some structures related to the present invention and do not constitute a limitation on the computer devices on which the present invention is applied.

[0098] An embodiment of the present invention also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the automatic generation and verification method for power tickets as described in any of the above embodiments. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0099] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the present invention and embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual-rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0100] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0101] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for automatically generating and verifying two electricity tickets, characterized in that, include: Obtain the power outage application form and its attachments (text data) and electrical drawing image data; Based on the semantic parsing of the serial numbers in the attachment text, the unstructured operation process is automatically broken down into multiple independent operation task sequences, and a draft operation ticket is generated in conjunction with power safety rules. OCR technology is used to parse electrical drawing image data to extract equipment topology information, and the equipment topology information is then cross-modal consistency verification is performed with the equipment information in the draft operation ticket. Based on the verification results, the final operation ticket and work ticket are generated and automatically populated back into the corresponding module of the power grid management platform according to the business type; The process of generating a draft operation ticket by combining power safety rules includes: Establish a power equipment entity dictionary to perform named entity recognition for switches, disconnectors, and lines in the operation task block; Based on the electrical connection relationships of the equipment and the safety regulations, a dependency graph is constructed among the operation steps, and the dependency missing risk index is calculated; where, the sequence of operation steps is defined as S={s1,s2,…,s…} n The standard dependency edge set required by safety regulations is E. std Steps i Dependency Loss Risk Index R(s) i )for: Pred(s i ) is the s specified in the safety regulations. i The set of prerequisite steps; δ(s) j ,s i ) is an indicator function; if s in the actual sequence j Appeared in s i The value is 1 if it is not present, and 0 otherwise; w j,i For dependent weights; when R(s) i If the value is greater than 0.5, it is determined that a step is missing or the order is incorrect; If a step is detected to be missing or out of order, standard safety procedures will be automatically inserted to generate a sequence of standard operating procedures.

2. The method according to claim 1, characterized in that, The sequence number semantic parsing based on the attachment text automatically breaks down the unstructured operation process into multiple independent operation task sequences, including: Regular expression matching is performed on the attached text to identify preset format serial number markers used to identify task levels in the text; wherein, the preset format serial number markers include at least one of Arabic numeral serial numbers, Roman numeral serial numbers, letter serial numbers, Chinese numeral serial numbers, or serial numbers in parentheses; Based on the boundaries marked by the preset format sequence number, the overall operation process is divided into multiple independent operation task blocks, and each task block generates an independent operation ticket.

3. The method according to claim 1, characterized in that, The method of using OCR technology to parse electrical drawing image data to extract equipment topology information includes: OCR can be used to identify equipment numbers, equipment names, and connection relationships in drawings. Convert the equipment coordinates and connection relationships in the drawings into a structured topology diagram.

4. The method according to claim 1, characterized in that, The step of performing cross-modal consistency verification between the device topology information and the device information in the draft operation ticket includes: Compare the equipment names and numbers in the draft operation ticket with the equipment information in the structured topology diagram; If the draft operation ticket contains devices that are not present in the topology diagram, or if the device connection relationships conflict with the topology logic, the verification will fail and an alarm will be triggered.

5. The method according to claim 1, characterized in that, The process of generating final operation tickets and work tickets based on verification results, and automatically backfilling them into the corresponding modules of the power grid management platform according to business type, includes: A draft operation ticket is generated based on the standardized operation procedure sequence, and its completeness is compared with the key operation items of the original power outage application form. A unique work order is generated based on the same power outage application form. The work location and safety measures are automatically extracted. The start time of the power outage application form is shifted forward by a predetermined time, and the end time of the application form is shifted backward by a predetermined time, so as to determine the planned start time and planned end time of the work order. The generated operation tickets and work tickets will be automatically populated back into the corresponding modules of the power grid management platform according to the business type.

6. The method according to claim 5, characterized in that, The business types include infrastructure construction, maintenance, and user projects, and the corresponding backfilling modules are as follows: Backfilling for infrastructure projects should be moved to the safety management and construction operation plan module. Repair-related items are backfilled to the repair project workbench module; User engineering data is backfilled into the maintenance and repair plan execution module.

7. The method according to claim 1, characterized in that, It also includes building a two-ticket knowledge management library, which includes a historical ticket library, a safety specification library, an operation specification library, a personnel qualification library, and a typical ticket library; When generating operation tickets or work tickets, the system automatically matches typical ticket templates, automatically calls safety regulations for compliance determination during verification, and associates and verifies personnel qualifications with work ticket permissions.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the automatic generation and verification method for two power tickets as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the automatic generation and verification method for two power tickets as described in any one of claims 1 to 7.

Images