Work order process processing method based on power station operation and maintenance

Abstract

The present invention relates to the technical field of work order process management, and in particular to a work order process processing method based on power station operation and maintenance. The method comprises the following steps: receiving real-time monitoring data from sensors of power station equipment, generating work order application data through a communication module; classifying work order types according to the work order application data to obtain work order type classification data; prioritizing according to the work order type classification data to obtain work order priority sorting data; assisting work order operations according to the work order priority sorting data to obtain work order operation assistance data to perform work order assistance operations; obtaining work order status update data, and performing work order approval process management according to the work order status update data to obtain work order approval result data; evaluating work order operation and maintenance status according to the work order approval result data to obtain work order operation and maintenance status data. The present invention effectively improves the efficiency and safety of power station operation and maintenance through an intelligent and automated work order processing process.

Description

Technical Field

[0001] The present invention relates to the technical field of work order process management, and in particular to a work order process processing method based on power station operation and maintenance. Background Art

[0002] The work order management system is designed as a core component of facility management for the new energy industry (such as photovoltaic and wind power), and is mainly used to maintain, monitor and manage equipment operation and maintenance activities. With the continuous development of the power industry and the improvement of its intelligence level, the operation and maintenance management of power stations has gradually become more complex and diversified. The traditional work order processing process relies on manual records, task allocation and resource scheduling, and has problems such as low efficiency, untimely response, and high error rate. These problems are particularly prominent in large power stations. After a fault occurs, it is difficult to quickly identify and locate it. Irrational resource scheduling leads to delayed repairs, which in turn affects the overall operating efficiency and stability of the power station. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a work order process processing method based on power station operation and maintenance to solve at least one of the above technical problems.

[0004] The present application provides a work order process processing method based on power station operation and maintenance, the method comprising:

[0005] S1. Receive real-time monitoring data from sensors of power station equipment and generate work order application data through a communication module; classify work order types according to the work order application data to obtain work order type classification data; prioritize work order type classification data to obtain work order priority ranking data;

[0006] S2. Perform work order operation assistance processing according to the work order priority sorting data to obtain work order operation assistance data to perform work order assistance operations;

[0007] S3. Obtain the work order status update data, and manage the work order approval process according to the work order status update data to obtain the work order approval result data;

[0008] S4. Evaluate the work order operation and maintenance status based on the work order approval result data to obtain the work order operation and maintenance status data.

[0009] The automatic classification and sorting in the present invention can quickly determine the priority of the work order, reduce the time of manual judgment, and improve the response speed. By automatically allocating tasks and scheduling resources, the system can allocate operation and maintenance personnel and equipment more efficiently, reduce the problem of uneven distribution of human intervention, and improve resource utilization. Through systematic process control, the work order status update and approval process management can record the status update, approval process and related feedback data of each work order, improve the management quality of the work order, and all related operations can be traced. By evaluating the operation and maintenance situation of the work order approval result data, the system can perform scientific analysis based on multi-dimensional data, such as risk assessment, cost-benefit analysis, etc., to help decision makers make optimal choices for the processing priority, resource investment, etc. of the work order.

[0010] Optionally, S1 includes:

[0011] Receive real-time monitoring data from sensors of power station equipment and generate work order application data through the communication module;

[0012] Perform content analysis based on the work order application data to obtain work order content analysis data;

[0013] Perform event matching based on the work order content parsing data to obtain the work order content event data;

[0014] Subdivide and classify the work order content event data to obtain the work order type classification data;

[0015] Perform multi-dimensional evaluation based on the work order type classification data to obtain multi-dimensional evaluation data of the work order;

[0016] The work order type classification data is sorted according to the work order multi-dimensional evaluation data to obtain the work order priority sorting data.

[0017] In the present invention, the response device automatically initiates a work order application, reduces manual intervention, can detect abnormal conditions of the equipment more quickly and trigger the work order immediately. The automated process speeds up the fault response time and shortens the processing delay, especially for emergency problems, which can greatly improve the efficiency of equipment fault processing. By parsing the content of the work order, the system can accurately extract key information such as key fault information, equipment status, time, etc., avoiding the omission or inaccuracy of information in manual filling. Through event matching, the system can quickly locate the root cause of the current work order problem based on historical faults and predefined rules. Automated event matching shortens the problem location time and reduces the workload of manual troubleshooting. Through subdivision and classification, the system can intelligently classify work orders according to different event types to ensure that different types of work orders are processed according to the most appropriate process. Subdivision and classification enable the system to identify different scenarios such as routine maintenance and emergency repairs, and set corresponding processing priorities and resource requirements for each scenario, thereby improving the accuracy and efficiency of work order processing. Through multi-dimensional evaluation, the system can not only determine the importance of the work order, but also estimate possible risks and costs, provide data support for operation and maintenance decisions, and enhance the scientific nature of work order processing. Prioritization is based on the results of multi-dimensional evaluation to ensure that the most urgent and important work orders are handled first, thereby optimizing the allocation and scheduling of resources.

[0018] Optionally, the event matching includes:

[0019] Perform simple event matching based on the work order content parsing data to obtain the first work order content event data;

[0020] Perform event chain matching based on the work order content parsing data to obtain the work order content event chain data;

[0021] Perform knowledge graph event matching based on the work order content event chain data to obtain the second work order content event data;

[0022] The first work order content event data and the second work order content event data are integrated into the work order content event data.

[0023] In the present invention, by dividing event matching into multiple levels (simple event matching, event chain matching, knowledge graph matching), the system can gradually deepen its understanding of the work order content. Simple event matching quickly locates basic fault information, while event chain matching and knowledge graph matching further explore the association between events and complex fault modes. The multi-level matching structure can improve the accuracy of event matching and help the system more comprehensively identify the root causes of faults and potential risks.

[0024] Optionally, the event chain matching includes:

[0025] Use the preset work order event chain model to perform subgraph isomorphism matching and similarity calculation on the work order content event chain data, and obtain the work order event subgraph isomorphism data and work order event similarity data respectively;

[0026] The work order content event chain data is obtained by filtering and sorting the work order event subgraph isomorphic data and the work order event similarity data.

[0027] In the present invention, through the two-level event chain analysis of subgraph isomorphism matching and similarity calculation, the system can more accurately identify the potential fault mode in the work order event chain. Subgraph isomorphism matching can ensure that the structure of the current event chain is highly consistent with the historical event chain, while similarity calculation allows the identification of event chains that are not completely consistent but have similar characteristics. The multi-level matching mechanism greatly improves the accuracy of fault identification and reduces misjudgment. The use of subgraph isomorphism matching ensures the structural integrity of the event chain and can identify fault modes that are completely consistent with the preset event chain model. Similarity calculation introduces a certain degree of flexibility. Even if the current work order event chain is not completely consistent with the historical event chain, the system can still identify highly similar patterns. By combining subgraph isomorphism data and similarity data for screening and sorting, the system can give priority to the most critical and influential event chains. Screening and sorting can not only automatically select the best matching event chain, but also adjust the priority of fault handling according to the similarity of the events.

[0028] Optionally, the steps of constructing the preset work order event chain model include:

[0029] Obtain historical work order content data, and perform event representation and extraction based on the historical work order content data to obtain historical work order event data;

[0030] Perform Bayesian network causal reasoning on historical work order event data to obtain causal relationship data of historical work order events;

[0031] Sort the historical work order event data in time series and analyze the time series relationship to obtain the time series relationship data of historical work order events;

[0032] A work order event chain model is constructed for historical work order event data according to the causal relationship data of historical work order events and the temporal relationship data of historical work order events to obtain a work order event chain model.

[0033] In the present invention, by acquiring a large amount of historical work order content data, and performing event representation and extraction based on these data, the system can build a high-precision event chain model from the data accumulated in the actual operation and maintenance process. Through Bayesian network causal reasoning, the system can identify the causal relationship between events, rather than just a simple juxtaposition of events. The use of Bayesian networks can capture the complex dependencies between events and help the system understand which events lead to the occurrence of other events. Time series sorting and time series relationship analysis of historical work order event data can ensure that the events in the event chain model conform to the actual time sequence of occurrence. Time series analysis enables the model to simulate the development process of faults over time and identify possible time dependencies and periodic faults. The structured model can accelerate the event matching process, allowing the system to quickly identify the matching pattern between the current work order event and the model.

[0034] Optionally, the multidimensional assessment includes:

[0035] Perform fault impact scope assessment based on work order type classification data to obtain fault impact scope assessment data;

[0036] Perform cost-benefit evaluation based on the work order type classification data to obtain cost-benefit evaluation data;

[0037] The power plant equipment distribution data is obtained, and the power plant equipment distribution data is annotated according to the work order type classification data, fault impact range assessment data and cost-benefit assessment data to obtain multi-dimensional assessment data of the work order.

[0038] In the present invention, by integrating the scope of fault impact, cost-effectiveness and equipment distribution information, the system can comprehensively analyze the work order from multiple dimensions. By analyzing the scope of fault impact, the system can identify the potential impact of the current work order on other equipment and systems. For example, the failure of a certain equipment will have a chain reaction on the power generation efficiency of the entire power station or a key component. Cost-benefit evaluation provides an economic analysis for work order processing, and helps the system make the most economical and reasonable processing decisions by weighing the cost of repair or replacement and the benefits such as equipment downtime losses. Through automated cost-benefit calculations, the system can recommend the best resource allocation plan to avoid unnecessary waste of resources while maximizing operation and maintenance efficiency and cost-effectiveness. By combining the scope of fault impact and cost-effectiveness data with equipment distribution information for graphical annotation, the system can intuitively show which equipment is most severely affected by the fault and which areas are involved.

[0039] Optionally, S2 includes:

[0040] Work order tasks are assigned according to the work order priority sorting data to obtain work order task assignment data;

[0041] Perform resource scheduling based on the work order task allocation data to obtain the work order resource scheduling data;

[0042] According to the work order resource scheduling data, assist task decomposition is performed to obtain work order operation assistance data for performing work order assistance operations.

[0043] In the present invention, task allocation is performed through work order priority sorting data, and the system can automatically select the most suitable operation and maintenance personnel and resources for task allocation based on factors such as the urgency and importance of the work order. After the task allocation is completed, the system can perform accurate resource scheduling based on the work order task allocation data to ensure that various types of resources (such as manpower, equipment, materials, etc.) are used in the most optimized way. The system can dynamically adjust the resource scheduling plan based on real-time work order data to ensure that resources can adapt to changes in task requirements at any time. For example, if a work order task changes, the system can automatically reallocate resources to make it more flexible. Assisting in task decomposition automatically splits complex work order tasks into multiple subtasks and assigns them to different teams or individuals, reducing the complexity of a single task. Through clear task decomposition, operation and maintenance personnel can clearly understand their specific responsibilities, avoid unclear or confusing tasks, and reduce the possibility of errors.

[0044] Optionally, S3 includes:

[0045] Get work order status update data;

[0046] Update the data according to the work order status to trigger the approval task and obtain the approval task data;

[0047] Perform multi-level approval operations based on approval task data to obtain multi-level approval data;

[0048] Verify the approval rules based on the multi-level approval data to obtain the work order approval result data.

[0049] The system of the present invention can obtain the work order status update data in real time, ensuring that all relevant personnel and systems can synchronously understand the latest progress of the work order. The approval task is automatically triggered by the work order status update data, and the system can quickly start the approval process when the task meets the specified conditions. The multi-level approval process is hierarchical according to the type, priority and complexity of the work order, ensuring that the approval personnel at different levels can make decisions within their respective authority. Through the approval rule verification, the system can check whether each work order approval complies with the preset approval rules and process requirements. Approval rule verification ensures that each work order strictly follows the specifications of the enterprise or organization during the approval process, reducing erroneous operations or process deviations caused by human factors.

[0050] Optionally, S4 includes:

[0051] Perform work order operation and maintenance tracking operations based on the work order approval result data to obtain work order operation and maintenance data;

[0052] Multi-dimensional display is performed based on the work order operation and maintenance data to obtain the work order operation and maintenance status data.

[0053] After the work order approval in the present invention is completed, the system can continuously monitor the execution status of the work order through the operation and maintenance tracking operation of the work order. All work order processing activities, task progress, resource usage and other information can be automatically recorded by the system. Through the work order operation and maintenance tracking, the system can update the status of the work order in real time, including task completion, difficulties encountered and abnormal situations, etc. The system performs multi-dimensional display based on the work order operation and maintenance data, and converts complex operation and maintenance data into visual charts, reports, dashboards and other forms. Through intelligent multi-dimensional display, managers can see the processing of work orders more intuitively, information transmission is more efficient and clear, and the time cost of analyzing data is reduced.

[0054] Optionally, the multi-dimensional display includes:

[0055] Displaying the task progress through a preset first work order operation and maintenance display interface according to the work order operation and maintenance data, and obtaining the first work order operation and maintenance display data;

[0056] The equipment personnel are displayed through a preset second work order operation and maintenance display interface according to the work order operation and maintenance data to obtain the second work order operation and maintenance display data, wherein the first work order operation and maintenance display interface and the second work order operation and maintenance display interface are work order operation and maintenance display interfaces of different areas and different regions;

[0057] The first work order operation and maintenance display data and the second work order operation and maintenance display data are integrated to obtain work order operation and maintenance status data.

[0058] In the present invention, through the first work order operation and maintenance display interface, the system can intuitively display the progress of the work order task. The second work order operation and maintenance display interface focuses on displaying the equipment status and personnel scheduling. By real-time monitoring and displaying the equipment status, the manager can understand whether the equipment is operating normally, whether it needs maintenance, and other information, and can also view the allocation and working status of the operation and maintenance personnel. The task progress and equipment personnel information are displayed separately through display interfaces of different areas and regions to avoid the visual complexity caused by excessive concentration of information in one interface. The separated design of the interface not only improves the clarity of information display, but also enhances the sense of hierarchy of information. Through the specialized interface layout, the system can effectively reduce information overload, so that users of different roles (such as managers, technicians) can focus on the key data they care about, thereby improving data understanding and processing efficiency.

[0059] The purpose of the present invention is to quickly generate work orders by automatically responding to abnormal status of equipment or regular maintenance requests, thereby reducing the workload of manual monitoring and initiating work orders. Combined with a classification algorithm based on historical fault data, the system can automatically classify work orders into types such as routine maintenance, emergency repair or upgrade transformation. Based on this, automatic classification improves the efficiency of work order processing, shortening the overall work order processing time by about 30%. By analyzing 100 work orders, it was found that the automated resource scheduling system increased the efficiency of human resource scheduling by 25%, reduced equipment scheduling conflicts by 15%, and reduced the overall processing time by about 40%. Before using this method, the average time of the traditional approval process was 4 hours, and the error rate was about 5%. Through the present invention, the intelligent approval process shortens the approval time to 1 hour and reduces the error rate to 1%. The fast approval mechanism is particularly effective for emergency situations, and the approval time for emergency work orders is shortened by 75%. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting implementations made with reference to the following drawings:

[0061] Figure 1 A flowchart showing a method for processing a work order process based on power station operation and maintenance according to an embodiment of the present invention is provided;

[0062] Figure 2 A flowchart showing a method for prioritizing work orders according to an embodiment of the present invention is provided;

[0063] Figure 3 A flowchart showing a method for matching work order content events according to an embodiment of the present invention is shown;

[0064] Figure 4 A flowchart showing a method for assisting a work order operation according to an embodiment of the present invention is shown;

[0065] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0066] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0067] In addition, the drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0068] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0069] See also Figures 1 to 4 The present application provides a work order process processing method based on power station operation and maintenance, the method comprising:

[0070] S1. Receive real-time monitoring data from sensors of power station equipment and generate work order application data through a communication module; classify work order types according to the work order application data to obtain work order type classification data; prioritize work order type classification data to obtain work order priority ranking data;

[0071] The present invention provides an embodiment in which the sensor of the power station equipment monitors the operating status of the equipment in real time, and transmits the detected abnormal information or fault data to the work order management system through the communication module. The system first generates work order application data, which includes key data such as equipment ID, fault information, timestamp, etc. Subsequently, the system classifies the work order type according to the work order application data, analyzes the fault type, equipment level and possible impact range involved in the work order, and forms work order type classification data. Next, the system prioritizes various types of work orders according to the work order type classification data. The factors considered in the sorting include the importance of the equipment, the severity of the fault, the complexity of the repair, and the impact of the fault on the overall operation of the power station. In this way, the system generates work order priority sorting data to ensure that the most urgent faults or faults that have a greater impact on the power station can be handled first.

[0072] In one embodiment of the present invention, when a device initiates a work order application, the system receives device fault information and related operation data, and generates preliminary work order application data. Feature extraction is performed on the work order application data, and the work orders are classified according to information such as device type, fault description, and urgency, to generate work order type classification data. By analyzing the work order type classification data, priority factors of each type of work order (such as the impact range of the fault, the importance of the equipment, the duration of the fault, etc.) are extracted, and priority sorting is performed to obtain work order priority sorting data.

[0073] S2. Perform work order operation assistance processing according to the work order priority sorting data to obtain work order operation assistance data to perform work order assistance operations;

[0074] The present invention provides an embodiment in which resources and tasks are allocated according to work order priority sorting data, and a preliminary work order collaboration plan is generated. Based on the work order type classification data and work order priority sorting data, it is pushed to relevant operation and maintenance personnel or automation tools, and operation step suggestions are provided, such as equipment or parameters that should be checked. During the operation process, the work order execution data is obtained in real time, and the operation steps are dynamically adjusted through the data to improve work efficiency. Work order operation assistance data is generated to record the operation execution status and feedback.

[0075] S3. Obtain the work order status update data, and manage the work order approval process according to the work order status update data to obtain the work order approval result data;

[0076] The present invention provides an embodiment in which work order progress and status information is extracted from work order operation assistance data to generate work order status update data, including task completion, problems in job execution, and whether the specified steps are completed. Based on the work order status update data, it is automatically determined whether the work order meets the preset completion standard, and this information is pushed to the approval process for work order review. The approval process includes checking indicators such as equipment status, whether the fault is resolved, and operational stability, and generating work order approval result data. For work orders that do not meet the conditions, the system will feedback the unfinished steps and require re-operation.

[0077] S4. Evaluate the work order operation and maintenance status based on the work order approval result data to obtain the work order operation and maintenance status data.

[0078] In one embodiment provided by the present invention, the final status information of the work order is extracted from the work order approval result data, including the processing efficiency of the work order, the effectiveness of fault repair, and the performance of the operation and maintenance personnel. Based on the extracted information, the system automatically performs an operation and maintenance evaluation, including performance monitoring of the equipment after repair, whether new faults occur, etc., generates an operation and maintenance evaluation report, and obtains the operation and maintenance status data of the work order. Based on the operation and maintenance evaluation data, optimization suggestions are made for subsequent work order processing, such as improving the equipment maintenance cycle and improving the efficiency of personnel scheduling.

[0079] The automatic classification and sorting in the present invention can quickly determine the priority of the work order, reduce the time of manual judgment, and improve the response speed. By automatically allocating tasks and scheduling resources, the system can allocate operation and maintenance personnel and equipment more efficiently, reduce the problem of uneven distribution of human intervention, and improve resource utilization. Through systematic process control, the work order status update and approval process management can record the status update, approval process and related feedback data of each work order, improve the management quality of the work order, and all related operations can be traced. By evaluating the operation and maintenance situation of the work order approval result data, the system can perform scientific analysis based on multi-dimensional data, such as risk assessment, cost-benefit analysis, etc., to help decision makers make optimal choices for the processing priority, resource investment, etc. of the work order.

[0080] Optionally, S1 includes:

[0081] S11, receiving real-time monitoring data from sensors of power station equipment, and generating work order application data through a communication module;

[0082] In one embodiment of the present invention, when a device fails or detects an abnormality, a work order application is sent to the system, and the system receives raw data including device ID, fault information, timestamp, operating parameters, etc. The received raw data is preprocessed, such as removing redundant information, standardizing time format, unifying data format, etc., to generate preliminary work order application data.

[0083] S12, performing content analysis according to the work order application data to obtain work order content analysis data;

[0084] In one embodiment provided by the present invention, natural language processing is performed on work order application data to extract keywords, equipment failure causes, affected areas, urgency, and other information to generate work order content parsing data. Semantic analysis is performed on the parsed content to convert the natural language into a structured data form (such as tags, types, and levels) to further refine the work order content.

[0085] S13, performing event matching according to the work order content parsing data to obtain work order content event data;

[0086] The present invention provides an embodiment in which event matching is performed based on the equipment fault information, keywords and historical data in the work order content parsing data to find similar or related historical work orders, fault modes, and known fault repair methods. Through pattern recognition technology, the current fault is matched with the fault type in the historical event database to obtain the work order content event data, and the event type to which the fault may belong is identified.

[0087] S14, subdividing and classifying the work order content event data to obtain work order type classification data;

[0088] In one embodiment of the present invention, work orders are assigned to specific event types (such as hardware failure, software failure, network problem, etc.) and subdivided equipment modules or subsystems according to work order content event data. Work orders are subdivided and classified using decision trees or classification rules to generate work order type classification data to ensure that work orders are correctly classified into the most appropriate category.

[0089] S15. Perform multi-dimensional evaluation according to the work order type classification data to obtain multi-dimensional evaluation data of the work order;

[0090] In one embodiment of the present invention, dimensional data such as the impact range, fault urgency, and repair complexity of the work order are extracted from the work order type classification data. Multi-dimensional evaluation is performed in combination with real-time data (such as equipment operation status, work order backlog, and maintenance resources), and multi-dimensional scores (such as priority, expected completion time, resource requirements, etc.) are generated to form multi-dimensional evaluation data of the work order.

[0091] S16. Sort the work order type classification data according to the work order multi-dimensional evaluation data to obtain work order priority sorting data.

[0092] In one embodiment, the present invention provides a method for prioritizing work orders based on multi-dimensional evaluation data of work orders using multi-attribute decision analysis technology, taking into account factors such as impact scope, urgency, and availability of processing resources. Work order priority ranking data is generated, and work orders are ranked by priority to ensure that the most urgent and important work orders are processed first.

[0093] In the present invention, the response device automatically initiates a work order application, reduces manual intervention, can detect abnormal conditions of the equipment more quickly and trigger the work order immediately. The automated process speeds up the fault response time and shortens the processing delay, especially for emergency problems, which can greatly improve the efficiency of equipment fault processing. By parsing the content of the work order, the system can accurately extract key information such as key fault information, equipment status, time, etc., avoiding the omission or inaccuracy of information in manual filling. Through event matching, the system can quickly locate the root cause of the current work order problem based on historical faults and predefined rules. Automated event matching shortens the problem location time and reduces the workload of manual troubleshooting. Through subdivision and classification, the system can intelligently classify work orders according to different event types to ensure that different types of work orders are processed according to the most appropriate process. Subdivision and classification enable the system to identify different scenarios such as routine maintenance and emergency repairs, and set corresponding processing priorities and resource requirements for each scenario, thereby improving the accuracy and efficiency of work order processing. Through multi-dimensional evaluation, the system can not only determine the importance of the work order, but also estimate possible risks and costs, provide data support for operation and maintenance decisions, and enhance the scientific nature of work order processing. Prioritization is based on the results of multi-dimensional evaluation to ensure that the most urgent and important work orders are handled first, thereby optimizing the allocation and scheduling of resources.

[0094] Optionally, the event matching includes:

[0095] S131, performing simple event matching according to the work order content parsing data to obtain first work order content event data;

[0096] The present invention provides an embodiment in which key features (such as equipment type, fault type, fault description, etc.) are extracted from work order content parsing data, and these features are matched with event features in a historical event database. Using rule matching technology, the current work order content is quickly matched with similar historical events by comparing keywords or specific fields to generate first work order content event data. Simple matching event data is output, which represents a single historical event that is most relevant to the current work order content.

[0097] S132, performing event chain matching according to the work order content parsing data to obtain work order content event chain data;

[0098] In one embodiment, the present invention further analyzes the time series, device interaction relationship and event causal relationship in the work order content analysis data based on simple event matching. Through the event chain analysis technology, a chain containing multiple related events is constructed, and the time series relationship, triggering conditions and mutual influence between these events are analyzed to generate work order content event chain data. The event chain data shows the chain reaction caused by the current fault event or the complex connection with other events.

[0099] S133, performing knowledge graph event matching according to the work order content event chain data to obtain second work order content event data;

[0100] The present invention provides an embodiment that uses entities such as events, equipment, faults, and the relationships between them in the knowledge graph to further enrich and expand the work order content event chain data. Through entity relationship reasoning in the knowledge graph, possible related event nodes are identified, the work order content event chain data is matched with the knowledge graph, and supplementary event information related to the current work order content is extracted to obtain the second work order content event data.

[0101] S134. Integrate the first work order content event data and the second work order content event data into work order content event data.

[0102] The present invention provides an embodiment in which the first work order content event data is compared and merged with the second work order content event data to identify repeated or conflicting events and merge relevant information. Using event data integration technology, the information in the two data sets is deduplicated, filtered and weighted to generate the final work order content event data. The output work order content event data contains comprehensive event information after simple matching, event chain analysis and knowledge graph reasoning, providing a basis for subsequent classification and processing.

[0103] In the present invention, by dividing event matching into multiple levels (simple event matching, event chain matching, knowledge graph matching), the system can gradually deepen its understanding of the work order content. Simple event matching quickly locates basic fault information, while event chain matching and knowledge graph matching further explore the association between events and complex fault modes. The multi-level matching structure can improve the accuracy of event matching and help the system more comprehensively identify the root causes of faults and potential risks.

[0104] Optionally, the event chain matching includes:

[0105] Use the preset work order event chain model to perform subgraph isomorphism matching and similarity calculation on the work order content event chain data, and obtain the work order event subgraph isomorphism data and work order event similarity data respectively;

[0106] The present invention provides an embodiment in which, based on a preset work order event chain model, key nodes and edges in the work order content event chain data are extracted to construct a graph structure of an event chain. The extracted event chain graph is isomorphically matched with the subgraph in the work order event chain model, and the relationships between nodes and edges are compared to find a subgraph that is consistent with the structure in the model. Through a step-by-step traversal method, it is checked whether each subgraph in the current work order event chain graph is the same (isomorphic) as a subgraph in the preset model. The successfully matched subgraph will be marked as work order event subgraph isomorphic data. The output work order event subgraph isomorphic data contains subgraphs in the work order content event chain that are consistent with the model, and these subgraphs indicate a high degree of match between the current work order event chain and the known pattern.

[0107] For subgraphs that fail to fully match, the system uses similarity calculation technology to compare the similarity between the graph in the work order content event chain data and the preset event chain model. Similarity calculation can be based on the properties of nodes and edges (such as node type, edge weight, connection direction, etc.), using graph matching measurement methods (such as weighted scoring based on node similarity and edge structure) to calculate similarity scores. The similarity score of each subgraph represents the degree of similarity between the subgraph and the preset model, generating work order event similarity data.

[0108] The work order content event chain data is obtained by filtering and sorting the work order event subgraph isomorphic data and the work order event similarity data.

[0109] The present invention provides an embodiment in which, based on the subgraph isomorphic data and similarity data, the system first screens out the fully matched subgraphs (i.e., isomorphic data) and prioritizes them in front to ensure that the subgraphs that fully adapt to the model are processed first. The partially matched subgraphs are sorted according to the similarity scores, and the most similar subgraphs are ranked at higher priority positions. Based on the work order event subgraph isomorphic data and the work order event similarity data, a weighted calculation is performed to generate work order content event chain data, which shows the priority and matching degree of each event chain in the work order, providing a basis for subsequent analysis and decision-making.

[0110] In the present invention, through the two-level event chain analysis of subgraph isomorphism matching and similarity calculation, the system can more accurately identify the potential fault mode in the work order event chain. Subgraph isomorphism matching can ensure that the structure of the current event chain is highly consistent with the historical event chain, while similarity calculation allows the identification of event chains that are not completely consistent but have similar characteristics. The multi-level matching mechanism greatly improves the accuracy of fault identification and reduces misjudgment. The use of subgraph isomorphism matching ensures the structural integrity of the event chain and can identify fault modes that are completely consistent with the preset event chain model. Similarity calculation introduces a certain degree of flexibility. Even if the current work order event chain is not completely consistent with the historical event chain, the system can still identify highly similar patterns. By combining subgraph isomorphism data and similarity data for screening and sorting, the system can give priority to the most critical and influential event chains. Screening and sorting can not only automatically select the best matching event chain, but also adjust the priority of fault handling according to the similarity of the events.

[0111] Optionally, the steps of constructing the preset work order event chain model include:

[0112] Obtain historical work order content data, and perform event representation and extraction based on the historical work order content data to obtain historical work order event data;

[0113] In one embodiment, the present invention extracts work order content data from a historical work order database, including equipment information, fault description, solution, time information, etc. of the work order. Event representation is extracted from these historical work order content data to extract key event features, such as fault type, cause, impact range, equipment status, etc. Event representation uses natural language processing and feature engineering to generate structured historical work order event data. These event features are represented as a data structure with clear nodes and edges, which facilitates subsequent causal analysis and temporal relationship analysis.

[0114] Perform Bayesian network causal reasoning on historical work order event data to obtain causal relationship data of historical work order events;

[0115] The present invention provides an embodiment in which a causal relationship model between events is constructed based on historical work order event data. The Bayesian network reasoning technology is used to analyze the causal relationship between events and identify which events may be the direct or indirect cause of other events. The causal network structure of events is generated by modeling the probabilistic dependency relationship between events. The process involves constructing a causal reasoning graph, where nodes represent events, edges represent causal relationships, and parameters are estimated by the probability of event occurrence. Finally, the causal relationship data of historical work order events is output to clarify the causal relationship between events, providing a basis for subsequent temporal relationship analysis and model construction.

[0116] Sort the historical work order event data in time series and analyze the time series relationship to obtain the time series relationship data of historical work order events;

[0117] In one embodiment provided by the present invention, the timestamp of each event in the historical work order event data is extracted, and the events are sorted according to the time sequence of occurrence to generate preliminary time sequence sorting data. The time series relationship of the events is analyzed to identify the possible dependencies in the event chain (for example, whether the occurrence of a certain event will trigger the occurrence of subsequent events). The time interval and dependency of the event chain are modeled using the time series analysis method to generate the time series relationship data of the historical work order events, and capture the time correlation pattern between the events.

[0118] A work order event chain model is constructed for historical work order event data according to the causal relationship data of historical work order events and the temporal relationship data of historical work order events to obtain a work order event chain model.

[0119] The present invention provides an embodiment in which the causal relationship data of historical work order events are combined with the temporal relationship data, the causal chain and temporal chain between events are analyzed, and a comprehensive event chain model is constructed. Through the construction technology of the graph model, the historical work order events are represented as an event chain structure with causal and temporal relationships, the nodes represent the work order events, and the edges represent the causal or temporal associations between events. In this process, the probability of event occurrence, the regularity of time intervals, and the complexity of the causal chain are considered to generate a work order event chain model. This model can be used for event matching and fault prediction of future work orders.

[0120] In the present invention, by acquiring a large amount of historical work order content data, and performing event representation and extraction based on these data, the system can build a high-precision event chain model from the data accumulated in the actual operation and maintenance process. Through Bayesian network causal reasoning, the system can identify the causal relationship between events, rather than just a simple juxtaposition of events. The use of Bayesian networks can capture the complex dependencies between events and help the system understand which events lead to the occurrence of other events. Time series sorting and time series relationship analysis of historical work order event data can ensure that the events in the event chain model conform to the actual time sequence of occurrence. Time series analysis enables the model to simulate the development process of faults over time and identify possible time dependencies and periodic faults. The structured model can accelerate the event matching process, allowing the system to quickly identify the matching pattern between the current work order event and the model.

[0121] Optionally, the multidimensional assessment includes:

[0122] Perform fault impact scope assessment based on work order type classification data to obtain fault impact scope assessment data;

[0123] The present invention provides an embodiment in which the fault type, equipment type and location corresponding to the work order are extracted from the work order type classification data, and the equipment and system scope that the fault may affect is analyzed in combination with the equipment operation history. By analyzing the connectivity between related equipment (such as the electrical network topology), the area that the fault may affect, the number of equipment, the role of key equipment and its importance are evaluated, and a preliminary fault impact range is generated. Combined with historical fault data, a fault propagation model or a network impact analysis method is used to further simulate the potential impact of the fault on surrounding equipment and generate fault impact range assessment data. This data includes a list of affected equipment, the degree of impact and the repair priority.

[0124] Perform cost-benefit evaluation based on the work order type classification data to obtain cost-benefit evaluation data;

[0125] The present invention provides an embodiment in which relevant data such as historical repair costs, equipment replacement costs, and downtime costs are extracted based on the fault types and equipment conditions provided in the work order type classification data. Cost evaluation is performed by analyzing the average repair time, required resources (such as personnel, materials), and possible downtime losses of each fault, and the direct and indirect costs of each fault are calculated. In combination with the revenue model (such as reduced downtime, restored power plant output, etc.), a benefit evaluation is performed to calculate the benefits brought to the power plant after the fault is repaired. Cost-benefit evaluation data is generated, including quantitative indicators of cost and benefit.

[0126] The power plant equipment distribution data is obtained, and the power plant equipment distribution data is annotated according to the work order type classification data, fault impact range assessment data and cost-benefit assessment data to obtain multi-dimensional assessment data of the work order.

[0127] The present invention provides an embodiment in which power station equipment distribution data is obtained, a geographical distribution map or a system topology map of the power station equipment is constructed, and the specific location, function, associated equipment and its current status of each device are marked. The power station equipment distribution map is annotated according to the work order type classification data, fault impact range assessment data and cost-benefit assessment data. The map annotation process includes annotating information such as faulty equipment, affected equipment and its priority, cost-benefit situation on the equipment distribution map, and using colors, symbols or numbers to represent data of each dimension. Combined with the map annotation results, multi-dimensional evaluation data of the work order is generated. The data integrates multi-dimensional information such as equipment distribution, fault impact range, cost-benefit, etc., which is used to assist decision-making and priority sorting.

[0128] In the present invention, by integrating the scope of fault impact, cost-effectiveness and equipment distribution information, the system can comprehensively analyze the work order from multiple dimensions. By analyzing the scope of fault impact, the system can identify the potential impact of the current work order on other equipment and systems. For example, the failure of a certain equipment will have a chain reaction on the power generation efficiency of the entire power station or a key component. Cost-benefit evaluation provides an economic analysis for work order processing, and helps the system make the most economical and reasonable processing decisions by weighing the cost of repair or replacement and the benefits such as equipment downtime losses. Through automated cost-benefit calculations, the system can recommend the best resource allocation plan to avoid unnecessary waste of resources while maximizing operation and maintenance efficiency and cost-effectiveness. By combining the scope of fault impact and cost-effectiveness data with equipment distribution information for graphical annotation, the system can intuitively show which equipment is most severely affected by the fault and which areas are involved.

[0129] Optionally, S2 includes:

[0130] S21, assigning work order tasks according to the work order priority sorting data to obtain work order task assignment data;

[0131] The present invention provides an embodiment in which the priority, fault type, required skill set and processing time limit of each work order are extracted from the work order priority ranking data. Based on the work order priority ranking and factors such as the available personnel, equipment skills, geographical location, current workload, etc., a task allocation strategy (such as based on a heuristic algorithm or a task allocation model) is used to automatically allocate work order tasks. Work order task allocation data is generated to clarify the executor of the task, the task start time and the expected completion time. This data ensures that task priority processing meets business needs and optimizes the efficiency of task allocation.

[0132] S22, performing resource scheduling according to the work order task allocation data to obtain work order resource scheduling data;

[0133] The present invention provides an embodiment in which, according to the work order task allocation data, the resources (including manpower, equipment, materials, etc.) required for each work order task are extracted, and the available resources are counted. Based on the urgency of the work order task, resource availability, geographical location, etc., resource scheduling optimization technology (such as linear programming or scheduling algorithm based on resource conflict minimization) is used to generate the best resource allocation plan. Work order resource scheduling data is generated to clearly specify the specific resources allocated for each task, including personnel scheduling arrangements, equipment allocation, material transportation time, etc., to ensure that resource utilization is maximized and no conflicts occur.

[0134] S23. Decompose the assistance task according to the work order resource scheduling data to obtain the work order operation assistance data to perform the work order assistance operation.

[0135] The present invention provides an embodiment in which, based on the work order resource scheduling data, complex tasks or multi-step tasks that need to be assisted are identified and task decomposed. Based on the complexity of the task, the required resources, the time limit, etc., the complex task is broken down into multiple executable small tasks using task decomposition technology, and each small task is assigned an assistant or an automated tool to generate work order operation assistance data. The output work order operation assistance data includes detailed collaboration steps, executors, execution tools, and time arrangements, which are used for the execution and monitoring of subsequent work order assistance operations.

[0136] In the present invention, task allocation is performed through work order priority sorting data, and the system can automatically select the most suitable operation and maintenance personnel and resources for task allocation based on factors such as the urgency and importance of the work order. After the task allocation is completed, the system can perform accurate resource scheduling based on the work order task allocation data to ensure that various types of resources (such as manpower, equipment, materials, etc.) are used in the most optimized way. The system can dynamically adjust the resource scheduling plan based on real-time work order data to ensure that resources can adapt to changes in task requirements at any time. For example, if a work order task changes, the system can automatically reallocate resources to make it more flexible. Assisting in task decomposition automatically splits complex work order tasks into multiple subtasks and assigns them to different teams or individuals, reducing the complexity of a single task. Through clear task decomposition, operation and maintenance personnel can clearly understand their specific responsibilities, avoid unclear or confusing tasks, and reduce the possibility of errors.

[0137] Optionally, S3 includes:

[0138] Get work order status update data;

[0139] The present invention provides an embodiment in which real-time data is collected from each execution node in the work order operation process, including task progress, completion status, problem report, work log, etc. These status update data are sorted and aggregated to form unified work order status update data, ensuring that the execution status and time node of each step are accurately recorded. The work order status update data is generated, including information such as the completion status of each task, whether it meets the predetermined requirements, and whether additional processing is required.

[0140] Update the data according to the work order status to trigger the approval task and obtain the approval task data;

[0141] In one embodiment of the present invention, based on the task completion status in the work order status update data, the system automatically determines whether the conditions for triggering approval are met (such as whether the task is completed on time, whether the quality standards are met, etc.). When the approval trigger conditions are met, approval task data is automatically generated. The approval task data includes the work order information that needs to be approved, the summary of the task completion status, and the specific content that needs to be approved (such as the fault repair status, cost expenditure, etc.). The approval task trigger ensures that the approval process is started in time, so that the task status quickly enters the review stage.

[0142] Perform multi-level approval operations based on approval task data to obtain multi-level approval data;

[0143] The present invention provides an embodiment in which, based on the approval task data, situations requiring multi-level approval (such as different levels of approval personnel, and review contents with different permissions) are determined. Using the approval process control technology, the approval tasks are assigned to different approval levels, and each level of approval personnel reviews the tasks according to their authority, involving the review of repair results, resource usage, overall work efficiency, etc. The system generates multi-level approval data, and the approval results of each level are recorded and passed to the next approval level until all approval processes are completed. This data contains the approval results, review opinions, and records of approval at each level.

[0144] Verify the approval rules based on the multi-level approval data to obtain the work order approval result data.

[0145] The present invention provides an embodiment in which the system automatically performs approval rule verification based on multi-level approval data to check whether all approval steps comply with preset approval rules (such as the integrity of the approval process, authority verification, result consistency, etc.). The rule engine verifies each approval link one by one to ensure the legality and compliance of the approval process. Any illegal or non-compliant operation will trigger an alarm or re-approval. The system generates work order approval result data to clarify whether the work order has been approved and whether it needs further modification or resubmission. The approval result data will serve as the final approval result of the work order process to determine the subsequent processing steps.

[0146] The system of the present invention can obtain the work order status update data in real time, ensuring that all relevant personnel and systems can synchronously understand the latest progress of the work order. The approval task is automatically triggered by the work order status update data, and the system can quickly start the approval process when the task meets the specified conditions. The multi-level approval process is hierarchical according to the type, priority and complexity of the work order, ensuring that the approval personnel at different levels can make decisions within their respective authority. Through the approval rule verification, the system can check whether each work order approval complies with the preset approval rules and process requirements. Approval rule verification ensures that each work order strictly follows the specifications of the enterprise or organization during the approval process, reducing erroneous operations or process deviations caused by human factors.

[0147] Optionally, S4 includes:

[0148] Perform work order operation and maintenance tracking operations based on the work order approval result data to obtain work order operation and maintenance data;

[0149] The present invention provides an embodiment in which, based on the work order approval result data, the approved work order information (including the equipment to be tracked, repair steps, execution personnel, etc.) is extracted, and a detailed operation and maintenance tracking plan is formulated. During the work order execution process, various data generated during the operation and maintenance process are continuously collected, including equipment operation status, operation and maintenance progress, operation and maintenance quality feedback, etc., to form real-time work order operation and maintenance data. The monitoring system is used to automatically track the operating status and operation and maintenance operations of key equipment, record any abnormal conditions, and update the work order operation and maintenance data in real time to ensure the stability of the equipment after operation and maintenance and the reduction of failure rate.

[0150] Multi-dimensional display is performed based on the work order operation and maintenance data to obtain the work order operation and maintenance status data.

[0151] The present invention provides an embodiment in which the work order operation and maintenance data is sorted and classified, and data of different dimensions (such as equipment status, task completion time, personnel efficiency, repair cost, etc.) are prepared for multi-dimensional display. Visualization technology is used to build a multi-dimensional display chart based on the operation and maintenance data, including timeline display, equipment status display, operation and maintenance results and cost analysis, efficiency comparison, etc., to display the work order operation and maintenance data in a graphical manner. The multi-dimensional display data can be dynamically interactively operated, and the operation and maintenance personnel can switch views between different dimensions to gain an in-depth understanding of different aspects of operation and maintenance (such as analysis by dimensions such as equipment, personnel, and time), so as to more comprehensively grasp the work order operation and maintenance situation.

[0152] After the work order approval in the present invention is completed, the system can continuously monitor the execution status of the work order through the operation and maintenance tracking operation of the work order. All work order processing activities, task progress, resource usage and other information can be automatically recorded by the system. Through the work order operation and maintenance tracking, the system can update the status of the work order in real time, including task completion, difficulties encountered and abnormal situations, etc. The system performs multi-dimensional display based on the work order operation and maintenance data, and converts complex operation and maintenance data into visual charts, reports, dashboards and other forms. Through intelligent multi-dimensional display, managers can see the processing of work orders more intuitively, information transmission is more efficient and clear, and the time cost of analyzing data is reduced.

[0153] Optionally, the multi-dimensional display includes:

[0154] Displaying the task progress through a preset first work order operation and maintenance display interface according to the work order operation and maintenance data, and obtaining the first work order operation and maintenance display data;

[0155] The present invention provides an embodiment in which real-time status information of a task is extracted from work order operation and maintenance data, including task start time, current progress, completion time prediction, etc. These data are standardized to ensure that the progress information of each task can be used for unified display. In the preset first work order operation and maintenance display interface, the task progress is visualized in the form of a chart, a progress bar or a timeline. The task progress display can be dynamically updated so that the interface reflects the latest progress of the task in real time. The system generates the first work order operation and maintenance display data, which contains the detailed progress of each task, possible delays and completion time predictions. The progress display helps operation and maintenance personnel and managers to quickly understand the current status of the task.

[0156] The equipment personnel are displayed through a preset second work order operation and maintenance display interface according to the work order operation and maintenance data to obtain the second work order operation and maintenance display data, wherein the first work order operation and maintenance display interface and the second work order operation and maintenance display interface are work order operation and maintenance display interfaces of different areas and different regions;

[0157] The present invention provides an embodiment in which equipment and personnel related information is extracted from work order operation and maintenance data, including the operating status of the equipment, maintenance records, current personnel task allocation, etc. These data are aggregated to form an equipment and personnel status table. In the preset second work order operation and maintenance display interface, the current status of the equipment and personnel is displayed through topological maps, status marks, personnel distribution maps, etc. Different graphics and symbols are used to distinguish the operating status of the equipment (such as normal, under maintenance, downtime, etc.) and the task status of the personnel (such as in execution, to be assigned, etc.). The system generates the second work order operation and maintenance display data to clarify the health status of the equipment and the scheduling of the personnel. This display interface and the task progress display interface are distributed in different regions and areas to ensure the hierarchy and clarity of information display.

[0158] The first work order operation and maintenance display data and the second work order operation and maintenance display data are integrated to obtain work order operation and maintenance status data.

[0159] The present invention provides an embodiment in which the first work order operation and maintenance display data and the second work order operation and maintenance display data are integrated, and an algorithm is used to perform correlation analysis on the task progress and the equipment and personnel status. For example, whether the delay of the task is related to equipment failure or insufficient personnel, the system automatically generates related data. The integrated data forms a global operation and maintenance status data set, which can display the comprehensive situation of the work order, including multi-dimensional information such as task completion, equipment operating status, and personnel scheduling efficiency. The system generates work order operation and maintenance status data, and the system can dynamically update and display the integrated operation and maintenance status through a unified visualization platform to ensure that the operation and maintenance personnel can fully control the execution of the work order and the operating status of the equipment.

[0160] In the present invention, through the first work order operation and maintenance display interface, the system can intuitively display the progress of the work order task. The second work order operation and maintenance display interface focuses on displaying the equipment status and personnel scheduling. By real-time monitoring and displaying the equipment status, the manager can understand whether the equipment is operating normally, whether it needs maintenance, and other information, and can also view the allocation and working status of the operation and maintenance personnel. The task progress and equipment personnel information are displayed separately through display interfaces of different areas and regions to avoid the visual complexity caused by excessive concentration of information in one interface. The separated design of the interface not only improves the clarity of information display, but also enhances the sense of hierarchy of information. Through the specialized interface layout, the system can effectively reduce information overload, so that users of different roles (such as managers, technicians) can focus on the key data they care about, thereby improving data understanding and processing efficiency.

[0161] The purpose of the present invention is to quickly generate work orders by automatically responding to abnormal status of equipment or regular maintenance requests, thereby reducing the workload of manual monitoring and initiating work orders. Combined with a classification algorithm based on historical fault data, the system can automatically classify work orders into types such as routine maintenance, emergency repair or upgrade transformation. Based on this, automatic classification improves the efficiency of work order processing, shortening the overall work order processing time by about 30%. By analyzing 100 work orders, it was found that the automated resource scheduling system increased the efficiency of human resource scheduling by 25%, reduced equipment scheduling conflicts by 15%, and reduced the overall processing time by about 40%. Before using this method, the average time of the traditional approval process was 4 hours, and the error rate was about 5%. Through the present invention, the intelligent approval process shortens the approval time to 1 hour and reduces the error rate to 1%. The fast approval mechanism is particularly effective for emergency situations, and the approval time for emergency work orders is shortened by 75%.

[0162] Therefore, from any point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the attached application documents rather than the above description, and it is intended that all changes falling within the meaning and scope of equivalent elements of the application documents are included in the present invention.

[0163] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A work order process processing method based on power station operation and maintenance, characterized in that: The method comprises: S1. Receive real-time monitoring data from sensors of power station equipment and generate work order application data through a communication module; classify work order types according to the work order application data to obtain work order type classification data; prioritize work order type classification data to obtain work order priority ranking data; S2. Perform work order operation assistance processing according to the work order priority sorting data to obtain work order operation assistance data to perform work order assistance operations; S3. Obtain the work order status update data, and manage the work order approval process according to the work order status update data to obtain the work order approval result data; S4. Evaluate the work order operation and maintenance status based on the work order approval result data to obtain the work order operation and maintenance status data; S1 includes: Receive real-time monitoring data from sensors of power station equipment and generate work order application data through the communication module; Perform content analysis based on the work order application data to obtain work order content analysis data; Perform event matching based on the work order content analysis data to obtain the work order content event data; Subdivide and classify the work order content event data to obtain the work order type classification data; Perform multi-dimensional evaluation based on the work order type classification data to obtain multi-dimensional evaluation data of the work order; Sort the work order type classification data according to the work order multi-dimensional evaluation data to obtain the work order priority sorting data; Event matching includes: Perform simple event matching based on the work order content parsing data to obtain the first work order content event data; Perform event chain matching based on the work order content parsing data to obtain the work order content event chain data; Perform knowledge graph event matching based on the work order content event chain data to obtain the second work order content event data; Integrate the first work order content event data and the second work order content event data into work order content event data; The event chain matching includes: Use the preset work order event chain model to perform subgraph isomorphism matching and similarity calculation on the work order content event chain data, and obtain the work order event subgraph isomorphism data and work order event similarity data respectively; Filter and sort the work order event subgraph isomorphic data and work order event similarity data to obtain the work order content event chain data; The steps for building the preset work order event chain model include: Obtain historical work order content data, and perform event representation and extraction based on the historical work order content data to obtain historical work order event data; Perform Bayesian network causal reasoning on historical work order event data to obtain causal relationship data of historical work order events; Sort the historical work order event data in time series and analyze the time series relationship to obtain the time series relationship data of historical work order events; A work order event chain model is constructed for historical work order event data according to the causal relationship data of historical work order events and the temporal relationship data of historical work order events to obtain a work order event chain model.

2. The method according to claim 1, characterized in that The multi-dimensional assessment includes: Perform fault impact scope assessment based on work order type classification data to obtain fault impact scope assessment data; Perform cost-benefit evaluation based on the work order type classification data to obtain cost-benefit evaluation data; The power plant equipment distribution data is obtained, and the power plant equipment distribution data is annotated according to the work order type classification data, fault impact range assessment data and cost-benefit assessment data to obtain multi-dimensional assessment data of the work order.

3. The method according to claim 1, characterized in that S2 include: Work order tasks are assigned according to the work order priority sorting data to obtain work order task assignment data; Perform resource scheduling based on the work order task allocation data to obtain the work order resource scheduling data; According to the work order resource scheduling data, assist task decomposition is performed to obtain work order operation assistance data for performing work order assistance operations.

4. The method according to claim 1, characterized in that S3 include: Get work order status update data; Update the data according to the work order status to trigger the approval task and obtain the approval task data; Perform multi-level approval operations based on approval task data to obtain multi-level approval data; Verify the approval rules based on the multi-level approval data to obtain the work order approval result data.

5. The method according to claim 1, characterized in that S4 includes: Perform work order operation and maintenance tracking operations based on the work order approval result data to obtain work order operation and maintenance data; Multi-dimensional display is performed based on the work order operation and maintenance data to obtain the work order operation and maintenance status data.

6. The method according to claim 5, characterized in that The multi-dimensional display includes: Displaying the task progress through a preset first work order operation and maintenance display interface according to the work order operation and maintenance data, and obtaining the first work order operation and maintenance display data; The equipment personnel are displayed through a preset second work order operation and maintenance display interface according to the work order operation and maintenance data to obtain the second work order operation and maintenance display data, wherein the first work order operation and maintenance display interface and the second work order operation and maintenance display interface are work order operation and maintenance display interfaces of different areas and different regions; The first work order operation and maintenance display data and the second work order operation and maintenance display data are integrated to obtain work order operation and maintenance status data.

Images