Smart park operation and maintenance information processing method and system applied to artificial intelligence

Abstract

The embodiment of the present application provides a method and system for processing operation and maintenance information of a smart park applied to artificial intelligence. According to the node incentive data of the first and second abnormal source nodes of the operation and maintenance abnormal event, the reference abnormal source node is intelligently selected through the concept of positive connection, which can ensure that the selection of the reference node is more accurate and reasonable. By selecting the target abnormal source node from the first and second reference abnormal source nodes, the scope of the abnormal root cause is further narrowed, which helps to more accurately locate the key nodes of the problem and conduct subsequent abnormal root cause analysis. In addition, based on the node incentive data of the target abnormal source node, the node incentive generated by the operation and maintenance abnormal event on the target abnormal source node is determined, and the corresponding target node incentive data is generated. The generated target node incentive data is used to annotate the abnormal root cause of the corresponding operation and maintenance abnormal event, which helps to identify, record and solve the root cause of the abnormal event, and improve the operation and maintenance efficiency and system reliability.

Description

Technical Field

[0001] The present application relates to the field of smart park operation and maintenance technology, and more specifically, to a smart park operation and maintenance information processing method and system applied to artificial intelligence. Background Art

[0002] The Smart Park Service Platform is a comprehensive platform developed to provide comprehensive management and operation support. The platform involves a large number of software service systems to collect, monitor and analyze various data to achieve efficient park management and services.

[0003] In traditional smart campus service platforms, there are usually many abnormal operation and maintenance events, which may cause equipment failure, service interruption or other problems. The process of handling these abnormal events usually requires manual intervention and investigation, which consumes time and resources and easily leads to response delays and difficulties in problem solving.

[0004] For example, when faced with complex operation and maintenance abnormal events, accurately identifying the root cause of the abnormality is often a challenge. Existing technologies may lack effective methods and indicators when determining the abnormal source nodes, making it difficult to locate the root cause of the abnormality.

[0005] Moreover, when dealing with abnormal operation and maintenance events, existing technologies may not fully utilize available data information and lack positive correlation analysis of node incentive data, which limits the accurate determination of truly critical nodes and the effectiveness of abnormal root cause analysis.

[0006] In addition, existing technologies may be subjective and inaccurate in abnormal root cause analysis. The lack of target node determination and abnormal root cause labeling methods based on node incentive data makes it difficult to handle and resolve abnormal operation and maintenance events, and easily leads to the recurrence of problems. Summary of the invention

[0007] In view of this, the purpose of this application is to provide a smart park operation and maintenance information processing method and system applied to artificial intelligence.

[0008] According to the first aspect of the present application, there is provided a method for processing smart park operation and maintenance information applied to artificial intelligence, which is applied to a smart park operation and maintenance system, and the method comprises:

[0009] For each operation and maintenance abnormal event in the smart park service platform, a first reference abnormal source node is selected from at least two first abnormal source nodes of the operation and maintenance abnormal event; the possibility of the first abnormal source node being selected is positively related to the node incentive data of the first abnormal source node;

[0010] Selecting a second reference abnormal source node from at least two second abnormal source nodes of the linkage operation and maintenance abnormal event of the operation and maintenance abnormal event; the possibility of the second abnormal source node being selected is positively related to the node incentive data of the second abnormal source node;

[0011] Selecting a target abnormal source node from the first reference abnormal source node and the second reference abnormal source node;

[0012] Based on the node incentive data of the target abnormal source node, determine the node incentive generated by the target abnormal source node of the operation and maintenance abnormal event to the operation and maintenance abnormal event, and generate the target node incentive data corresponding to the operation and maintenance abnormal event; the target abnormal source node includes the first abnormal source node and the second abnormal source node; the target node incentive data is used to mark the abnormal root cause of the corresponding operation and maintenance abnormal event.

[0013] In a possible implementation of the first aspect, for each operation and maintenance abnormal event in the smart park service platform, selecting a first reference abnormal source node from at least two first abnormal source nodes of the operation and maintenance abnormal event includes:

[0014] For each abnormal operation and maintenance event in the smart park service platform, the node tracing of the abnormal operation and maintenance event at the current stage is performed to obtain the first abnormal source node of the current stage tracing;

[0015] Determine an iterative first abnormal source node from the first abnormal source node traced in the current stage and the first abnormal source node selected in the forward stage, and determine the iterative first abnormal source node as the first abnormal source node selected in the current stage;

[0016] The backward stage is used as the current stage of iteration, and the operation of performing node tracing of the operation and maintenance abnormal event in the current stage to obtain the first abnormal source node of the current stage tracing is returned. When the tracing is completed, the first abnormal source node selected in the final stage is determined as the first reference abnormal source node.

[0017] In a possible implementation manner of the first aspect, determining the iterative first abnormal source node from the first abnormal source node traced back in the current stage and the first abnormal source node selected in the forward stage includes:

[0018] Determine the significance weight of the first abnormal source node traced back in the current stage based on the node incentive data of the first abnormal source node traced back in the current stage;

[0019] Determine the significance weight of the first abnormal source node selected in the forward stage based on the node excitation data of the first abnormal source node selected in the forward stage;

[0020] Get the first selection hit parameter corresponding to the current stage;

[0021] Based on the first selection hit parameter, the significance weight of the first abnormal source node traced in the current stage, and the significance weight of the first abnormal source node selected in the forward stage, an iterative first abnormal source node is determined from the first abnormal source node traced in the current stage and the first abnormal source node selected in the forward stage.

[0022] In a possible implementation manner of the first aspect, the first abnormal source node selected in the forward phase is loaded into a node library corresponding to the operation and maintenance abnormal event;

[0023] The step of determining the iterative first abnormal source node as the first abnormal source node selected in the current stage includes:

[0024] The iterative first abnormal source node is determined as the first abnormal source node selected in the current stage, and the first abnormal source node selected in the forward stage in the node library corresponding to the operation and maintenance abnormal event is replaced with the first abnormal source node selected in the current stage.

[0025] In a possible implementation manner of the first aspect, the selecting a second reference abnormal source node from the at least two second abnormal source nodes of the linked operation and maintenance abnormal event of the operation and maintenance abnormal event includes:

[0026] For each linkage operation and maintenance abnormal event of the operation and maintenance abnormal event, performing node tracing at the current stage for the linkage operation and maintenance abnormal event to obtain a second abnormal source node traced at the current stage;

[0027] Determine the significance weight of the second abnormal source node traced back in the current stage based on the node incentive data of the second abnormal source node traced back in the current stage;

[0028] Determine the significance weight of the second abnormal source node selected in the forward stage based on the node excitation data of the second abnormal source node selected in the forward stage;

[0029] Get the second selection hit parameter corresponding to the current stage;

[0030] Based on the second selection hit parameter, the significance weight of the second abnormal source node traced in the current stage, and the significance weight of the second abnormal source node selected in the forward stage, an iterative second abnormal source node is determined from the second abnormal source node traced in the current stage and the second abnormal source node selected in the forward stage, and the iterative second abnormal source node is determined as the second abnormal source node selected in the current stage;

[0031] The backward stage is used as the current stage of iteration, and the operation of performing node tracing of the linkage operation and maintenance abnormal event in the current stage to obtain the second abnormal source node of the current stage tracing is returned. When the tracing is completed, the second abnormal source node selected in the final stage is determined as the second reference abnormal source node.

[0032] In a possible implementation of the first aspect, the method further includes:

[0033] For each operation and maintenance abnormal event in the smart park service platform, determine one or more basic linkage operation and maintenance abnormal events of the operation and maintenance abnormal event from the smart park service platform;

[0034] For each basic linkage operation and maintenance abnormal event, if there is no abnormal intersection position between the basic linkage operation and maintenance abnormal event and the cyclic operation and maintenance abnormal event, the basic linkage operation and maintenance abnormal event will be used as the linkage operation and maintenance abnormal event of the operation and maintenance abnormal event, and the cyclic operation and maintenance abnormal event is the operation and maintenance abnormal event that triggers a cycle on the first abnormal source node.

[0035] In a possible implementation manner of the first aspect, the first reference abnormal source node and the second reference abnormal source node form a reference abnormal source node sequence;

[0036] The selecting a target abnormal source node from the first reference abnormal source node and the second reference abnormal source node comprises:

[0037] A target abnormal source node is selected from the reference abnormal source node sequence, and the possibility of each reference abnormal source node in the reference abnormal source node sequence being selected is positively related to the node incentive data of the reference abnormal source node.

[0038] In a possible implementation of the first aspect, determining, based on the node incentive data of the target abnormal source node, the node incentive generated by the target abnormal source node of the operation and maintenance abnormal event for the operation and maintenance abnormal event, and generating the target node incentive data corresponding to the operation and maintenance abnormal event, includes:

[0039] According to the significance weight of the target abnormal source node, the excitation parameter depth data in the node excitation data of the target abnormal source node is updated to generate the excitation parameter attribute data of the target abnormal source node; the significance weight of the target abnormal source node reflects the depth of the excitation parameter in the node excitation data of the target abnormal source node;

[0040] The average significance weight of each target abnormal source node of the operation and maintenance abnormal event is weighted by the excitation parameter attribute data of the target abnormal source node to generate the target node excitation data corresponding to the operation and maintenance abnormal event. The average significance weight reflects the average depth of the excitation parameters in the node excitation data of each target abnormal source node.

[0041] In a possible implementation of the first aspect, the method further includes:

[0042] Mapping the excitation parameter depth data in the node excitation data of the target abnormal source node to the excitation parameter span data corresponding to the target abnormal source node;

[0043] Determining a significance weight of the target abnormal source node based on the excitation parameter span data corresponding to the target abnormal source node;

[0044] And for each target abnormal source node of the operation and maintenance abnormal event, mapping the excitation parameter depth data in the node excitation data of the target abnormal source node to the excitation parameter span data corresponding to the target abnormal source node;

[0045] Determining a significance weight of the target abnormal source node based on the excitation parameter span data corresponding to the target abnormal source node;

[0046] The significance weights of the target abnormal source nodes of the operation and maintenance abnormal event are averaged to generate the average significance weights of the target abnormal source nodes.

[0047] According to the second aspect of the present application, a smart park operation and maintenance system is provided, which includes a processor and a readable storage medium, wherein the readable storage medium stores a program, which, when executed by the processor, implements the aforementioned smart park operation and maintenance information processing method applied to artificial intelligence.

[0048] According to the third aspect of the present application, a computer-readable storage medium is provided, in which computer-executable instructions are stored. When the computer-executable instructions are monitored to be executed, the aforementioned smart park operation and maintenance information processing method applied to artificial intelligence is implemented.

[0049] According to any of the above aspects, in the present application, according to the node incentive data of the first and second abnormal source nodes of the operation and maintenance abnormal event, the reference abnormal source node is intelligently selected through the concept of positive connection. This can ensure that the selection of the reference node is more accurate and reasonable. And by selecting the target abnormal source node from the first and second reference abnormal source nodes, the scope of the abnormal root cause is further narrowed. This helps to locate the key nodes of the problem more accurately and conduct subsequent abnormal root cause analysis. In addition, based on the node incentive data of the target abnormal source node, the node incentive generated by the operation and maintenance abnormal event to the target abnormal source node is determined, and the corresponding target node incentive data is generated. The generated target node incentive data is used to annotate the abnormal root cause of the corresponding operation and maintenance abnormal event, which helps to identify, record and solve the root cause of the abnormal event, and improve the operation and maintenance efficiency and system reliability. That is, through the above technical solution, the reference abnormal source node can be selected more accurately and the target abnormal source node can be determined, and then the target node incentive data can be generated to support the abnormal root cause analysis and annotation of the operation and maintenance abnormal event, which helps to improve the operation and maintenance management capabilities and problem solving efficiency of the smart park service platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0051] Figure 1 A flow chart of a method for processing smart park operation and maintenance information applied to artificial intelligence provided by an embodiment of the present application;

[0052] Figure 2 A schematic diagram of the component structure of a smart park operation and maintenance system for implementing the above-mentioned smart park operation and maintenance information processing method applied to artificial intelligence provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0053] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0054] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0055] Figure 1 The flowchart of the method for processing operation and maintenance information of a smart park applied to artificial intelligence provided by the embodiment of the present application is shown. It should be understood that in other embodiments, the order of some steps in the method for processing operation and maintenance information of a smart park applied to artificial intelligence in this embodiment can be interchanged according to the need for annotation, or some steps can be omitted or deleted. The detailed steps of the method for processing operation and maintenance information of a smart park applied to artificial intelligence are described as follows.

[0056] Step S102, for each operation and maintenance abnormal event in the smart park service platform, select a first reference abnormal source node from at least two first abnormal source nodes of the operation and maintenance abnormal event; the possibility of the first abnormal source node being selected is positively related to the node incentive data of the first abnormal source node.

[0057] Among them, the first abnormal source node is the abnormal source node obtained by tracing the abnormal source node of the operation and maintenance abnormal event. The first reference abnormal source node is the abnormal source node selected from at least two first abnormal source nodes generated by tracing the abnormal source node of the operation and maintenance abnormal event. The possibility of the first abnormal source node being selected as the first reference abnormal source node is positively related to the node incentive data of the first abnormal source node. For each first abnormal source node, the greater the node incentive of the first abnormal source node for the operation and maintenance abnormal event, that is, the greater the influence weight of the first abnormal source node on the operation and maintenance abnormal event, the greater the possibility of the first abnormal source node being selected as the first reference abnormal source node. The node incentive data is the abnormal path data stimulated by the abnormal source node for the operation and maintenance abnormal event.

[0058] For example, if the operation and maintenance abnormal event is that the data analysis module in the smart park service platform cannot operate normally, resulting in a delay in real-time data processing, then the first abnormal source node can be the data collection module A, data processing module B, ..., data processing module N, that is, there may be multiple modules involved in data collection and processing, and the data collection module A, data processing module B, ..., data processing module N are marked as the first abnormal source node because they are the most likely software failures or errors that cause the data analysis module to fail to operate normally.

[0059] For another example, if the operation and maintenance abnormal event is a failure in the user authentication module in the smart park service platform, which prevents users from successfully logging into the system, then the first abnormal source node can be the identity authentication service A, the user database B, etc., that is, there may be multiple components that constitute the user authentication module, and the identity authentication service A and the user database B are marked as the first abnormal source node because they are the software components most likely to cause user authentication failures.

[0060] For another example, if the operation and maintenance abnormal event is an error in the scheduling algorithm module in the smart park service platform, resulting in uneven task distribution, then the first abnormal source node can be scheduling algorithm A and task queue B. That is, there may be multiple modules responsible for task scheduling and distribution, and scheduling algorithm A and task queue B are marked as the first abnormal source node because they are the most likely software failures or errors to cause uneven task distribution.

[0061] The node incentive data of the first abnormal source node may refer to data or information related to the first abnormal source node, which is used to determine the positive connection between it and the operation and maintenance abnormal event.

[0062] For example, it may include real-time or historical monitoring data, log files or event records, fault reports or alarm notifications, system status information, etc. from the first abnormal source node. By analyzing and evaluating the node incentive data of the first abnormal source node, it can be determined whether the node has a positive connection with the operation and maintenance abnormal event. These data provide a basis for the subsequent selection of target abnormal source nodes, generation of target node incentive data, and abnormal root cause analysis. The specific node incentive data type and content will vary depending on the system and situation.

[0063] After obtaining at least two first abnormal source nodes of the operation and maintenance abnormal event, the first reference abnormal source node of the operation and maintenance abnormal event can be selected from the at least two first abnormal source nodes of the operation and maintenance abnormal event based on the node incentive data of each first abnormal source node. The possibility of the first abnormal source node being selected is positively related to the node incentive data of the first abnormal source node.

[0064] In some alternative implementations, for each first abnormal source node of an operation and maintenance abnormal event, the significance weight of the first abnormal source node can be determined based on the node incentive data of the first abnormal source node. Furthermore, the selection hit parameter selected for the first abnormal source node can be obtained, and based on the selection hit parameter selected for the first abnormal source node and the significance weight of each first abnormal source node, a first reference abnormal source node is selected from at least two first abnormal source nodes of the operation and maintenance abnormal event. Among them, the significance weight is positively related to the node incentive data. In this way, by referring to the selection hit parameter selected for the first abnormal source node, the first reference abnormal source node is selected from at least two first abnormal source nodes of the operation and maintenance abnormal event, which can ensure the comprehensiveness of the reference abnormal source node selected for each operation and maintenance abnormal event when marking the abnormal root cause of each operation and maintenance abnormal event in the smart park service platform.

[0065] In some alternative implementations, for each first abnormal source node of the operation and maintenance abnormal event, the incentive parameter depth data in the node incentive data of the first abnormal source node can be mapped to the incentive parameter span data corresponding to the first abnormal source node. Furthermore, the significance weight of the first abnormal source node can be determined based on the incentive parameter span data corresponding to the first abnormal source node. For example, the incentive parameter span data corresponding to the first abnormal source node, that is, the incentive parameter span value, can be directly used as the significance weight of the first abnormal source node. Alternatively, the incentive parameter span data corresponding to the first abnormal source node, that is, the incentive parameter span value, can also be fused to generate the significance weight of the first abnormal source node. Among them, the incentive parameter depth data is data reflecting the depth of the incentive parameter in the node incentive data. The incentive parameter span data reflects the span of the incentive parameter provided by the first abnormal source node for the operation and maintenance abnormal event.

[0066] In some alternative implementations, the excitation parameter depth data in the node excitation data of the first abnormal source node may be fused to generate the excitation parameter span data corresponding to the first abnormal source node.

[0067] In some alternative implementations, for each operation and maintenance abnormal event in the smart park service platform, the first abnormal source node with the largest node excitation can be selected from at least two first abnormal source nodes of the operation and maintenance abnormal event as the first reference abnormal source node of the operation and maintenance abnormal event.

[0068] Step S104, selecting a second reference abnormal source node from at least two second abnormal source nodes of the linked operation and maintenance abnormal event; the possibility of the second abnormal source node being selected is positively related to the node incentive data of the second abnormal source node.

[0069] Among them, for each operation and maintenance abnormal event in the smart park service platform, the linkage operation and maintenance abnormal event of the operation and maintenance abnormal event is other secondary abnormal events associated with the operation and maintenance abnormal event in the smart park service platform, which may be caused by the influence or triggering of the main abnormal event and have a certain correlation with the operation and maintenance abnormal event. For example, the linkage operation and maintenance abnormal event may include the following situations:

[0070] Cascading failures: A major abnormal event triggers failures or errors in other devices or systems. For example, a server crash causes the database to be inaccessible, which in turn affects the normal operation of the application.

[0071] Triggering events: Major abnormal events trigger the occurrence of other events. For example, a network outage causes the automated monitoring system to send an alarm message, notifying the operation and maintenance personnel to check the network connection.

[0072] Similar problems: The main abnormal event caused similar abnormal events. For example, in different floors of a smart park, multiple air-conditioning equipments simultaneously experienced cooling effect degradation, and these problems were all related to the main abnormal event.

[0073] Correlation and interaction: When handling major abnormal events, it is necessary to interact, collaborate, or share information with other abnormal events. For example, when solving network failures, it is necessary to correlate with other abnormal events such as network device configuration errors and abnormal firewall settings.

[0074] The second abnormal source node is an abnormal source node generated by tracing the abnormal source node for the linkage operation and maintenance abnormal event. The second reference abnormal source node is an abnormal source node selected from at least two second abnormal source nodes generated by tracing the abnormal source node for the linkage operation and maintenance abnormal event. The possibility of the second abnormal source node being selected as the second reference abnormal source node is positively related to the node incentive data of the second abnormal source node. It can be understood that for each second abnormal source node, the greater the node incentive of the second abnormal source node for the linkage operation and maintenance abnormal event, that is, the greater the influence weight of the second abnormal source node on the linkage operation and maintenance abnormal event, the greater the possibility of the second abnormal source node being selected as the second reference abnormal source node.

[0075] For example, for each operation and maintenance abnormal event in the smart park service platform, the number of linkage operation and maintenance abnormal events of the operation and maintenance abnormal event can be one or more. After obtaining at least two second abnormal source nodes of the linkage operation and maintenance abnormal event, the second reference abnormal source node of the linkage operation and maintenance abnormal event can be selected from the at least two second abnormal source nodes of the linkage operation and maintenance abnormal event based on the node incentive data of each second abnormal source node. The possibility of the second abnormal source node being selected is positively related to the node incentive data of the second abnormal source node.

[0076] In some alternative implementations, for each second abnormal source node of the linkage operation and maintenance abnormal event, the significance weight of the second abnormal source node can be determined based on the node incentive data of the second abnormal source node. Furthermore, the selection hit parameter selected for the second abnormal source node can be obtained, and based on the selection hit parameter selected for the second abnormal source node and the significance weight of each second abnormal source node, a second reference abnormal source node is selected from at least two second abnormal source nodes of the linkage operation and maintenance abnormal event. Among them, the significance weight is positively related to the node incentive data. In this way, by referring to the selection hit parameter selected for the second abnormal source node, a second reference abnormal source node is selected from at least two second abnormal source nodes of the linkage operation and maintenance abnormal event, it can be ensured that when the abnormal root cause of each operation and maintenance abnormal event in the smart park service platform is marked, the comprehensiveness of the reference abnormal source node selected corresponding to each linkage operation and maintenance abnormal event of the operation and maintenance abnormal event can be ensured.

[0077] In some alternative implementations, for each second abnormal source node of the linkage operation and maintenance abnormal event, the excitation parameter depth data in the node excitation data of the second abnormal source node can be mapped to the excitation parameter span data corresponding to the second abnormal source node. Furthermore, the significance weight of the second abnormal source node can be determined based on the excitation parameter span data corresponding to the second abnormal source node. For example, the excitation parameter span data corresponding to the second abnormal source node, that is, the excitation parameter span value, can be directly used as the significance weight of the second abnormal source node. Alternatively, the excitation parameter span data corresponding to the second abnormal source node, that is, the excitation parameter span value, can also be fused to generate the significance weight of the second abnormal source node. Among them, the excitation parameter depth data is data reflecting the depth of the excitation parameter in the node excitation data.

[0078] In some alternative implementations, the excitation parameter depth data in the node excitation data of the second abnormal source node may be fused to generate the excitation parameter span data corresponding to the second abnormal source node.

[0079] In some alternative implementations, for each linked operation and maintenance abnormal event of the operation and maintenance abnormal event in the smart park service platform, the second abnormal source node with the largest node excitation can be selected from at least two second abnormal source nodes of the linked operation and maintenance abnormal event as the second reference abnormal source node of the linked operation and maintenance abnormal event.

[0080] Step S106: Select a target abnormal source node from the first reference abnormal source node and the second reference abnormal source node.

[0081] For example, for each operation and maintenance abnormal event in the smart park service platform, the target abnormal source node of the operation and maintenance abnormal event can be selected from the first reference abnormal source node of the operation and maintenance abnormal event and the second reference abnormal source nodes corresponding to each linked operation and maintenance abnormal event of the operation and maintenance abnormal event.

[0082] In some alternative implementations, for each operation and maintenance abnormal event in the smart park service platform, the first reference abnormal source node and each second reference abnormal source node of the operation and maintenance abnormal event can form a reference abnormal source node sequence corresponding to the operation and maintenance abnormal event. From the reference abnormal source node sequence corresponding to the operation and maintenance abnormal event, a reference abnormal source node can be randomly selected to be determined as the target abnormal source node of the operation and maintenance abnormal event. The probability of each reference abnormal source node in the reference abnormal source node sequence being selected as the target abnormal source node is the same.

[0083] Step S108, in combination with the node incentive data of the target abnormal source node, determine the node incentive generated by the target abnormal source node of the operation and maintenance abnormal event to the operation and maintenance abnormal event, and generate the target node incentive data corresponding to the operation and maintenance abnormal event; the target abnormal source node includes the first abnormal source node and the second abnormal source node; the target node incentive data is used to mark the abnormal root cause of the corresponding operation and maintenance abnormal event.

[0084] For example, for each operation and maintenance abnormal event in the smart park service platform, the first abnormal source node and the second abnormal source node of the operation and maintenance abnormal event may constitute the target abnormal source node of the operation and maintenance abnormal event. The node incentive data generated by the target abnormal source node of the operation and maintenance abnormal event for the operation and maintenance abnormal event may be combined to determine the node incentive generated by the target abnormal source node of the operation and maintenance abnormal event for the operation and maintenance abnormal event, and generate the target node incentive data of the operation and maintenance abnormal event. Furthermore, based on the target node incentive data of the operation and maintenance abnormal event, the abnormal root cause of the operation and maintenance abnormal event may be marked.

[0085] For example, the abnormal root cause features related to the abnormal root cause are extracted from the target node incentive data. The abnormal root cause features may be indicators, state parameters or abnormal patterns directly related to the abnormal event. Then, an abnormal root cause annotation model is constructed, for example, a training model is constructed using machine learning or statistical methods, which can associate the target node incentive data with the known abnormal root cause. This can be a classification model, a clustering model or other related models. The constructed abnormal root cause annotation model is then trained and verified using the known abnormal root cause data. This usually involves using a portion of the data for training the model and then using another portion of the data for verification and evaluation of the model performance. Thus, the trained abnormal root cause annotation model can be used to annotate the root causes of new operation and maintenance abnormal events. The target node incentive data is input into the abnormal root cause annotation model, and the abnormal root cause annotation model will output a label or probability score related to the abnormal root cause.

[0086] Through the above steps, the process of associating the target node incentive data with the root cause of the anomaly can be realized. This helps to automatically identify the root cause of the anomaly and provide guidance to the operation and maintenance team on locating and resolving abnormal events. It should be noted that the accuracy and effect of the model depend on factors such as the quality of the data used, feature selection, and model training, so sufficient data analysis and verification are required during the implementation process.

[0087] In some alternative implementations, the excitation parameter depth data in the node excitation data of the target abnormal source node can be mapped to the excitation parameter span data corresponding to the target abnormal source node, and the significance weight of the target abnormal source node can be determined based on the excitation parameter span data corresponding to the target abnormal source node. The significance weight of the target abnormal source node reflects the depth of the excitation parameter in the node excitation data of the target abnormal source node. Furthermore, the excitation parameter depth data in the node excitation data of the target abnormal source node can be updated according to the significance weight of the target abnormal source node to generate the excitation parameter attribute data of the target abnormal source node. For each target abnormal source node of the operation and maintenance abnormal event, the excitation parameter depth data in the node excitation data of the target abnormal source node can be mapped to the excitation parameter span data corresponding to the target abnormal source node, and the significance weight of the target abnormal source node can be determined based on the excitation parameter span data corresponding to the target abnormal source node. Furthermore, the significance weight with the largest significance weight can be selected from the significance weights of each target abnormal source node of the operation and maintenance abnormal event, and the excitation parameter attribute data of the target abnormal source node with the selected largest significance weight can be weighted to generate the target node excitation data of the operation and maintenance abnormal event. The excitation parameter span data may refer to the variation range or value range of a certain excitation parameter. The excitation parameter depth data may indicate the importance or influence of the excitation parameter on the target abnormal source node.

[0088] Based on the above steps, according to the node incentive data of the first and second abnormal source nodes of the operation and maintenance abnormal event, the reference abnormal source node is intelligently selected through the concept of positive connection. This ensures that the selection of the reference node is more accurate and reasonable. And by selecting the target abnormal source node from the first and second reference abnormal source nodes, the scope of the abnormal root cause is further narrowed. This helps to locate the key nodes of the problem more accurately and conduct subsequent abnormal root cause analysis. In addition, based on the node incentive data of the target abnormal source node, the node incentive generated by the operation and maintenance abnormal event on the target abnormal source node is determined, and the corresponding target node incentive data is generated. The generated target node incentive data is used to annotate the abnormal root cause of the corresponding operation and maintenance abnormal event, which helps to identify, record and solve the root cause of the abnormal event, and improve the operation and maintenance efficiency and system reliability. That is, through the above technical solution, the reference abnormal source node can be selected more accurately and the target abnormal source node can be determined, and then the target node incentive data can be generated to support the abnormal root cause analysis and annotation of the operation and maintenance abnormal event, which helps to improve the operation and maintenance management capabilities and problem solving efficiency of the smart park service platform.

[0089] In some alternative implementations, for each operation and maintenance abnormal event in the smart campus service platform, a first reference abnormal source node is selected from at least two first abnormal source nodes of the operation and maintenance abnormal event, including: for each operation and maintenance abnormal event in the smart campus service platform, performing node tracing of the current stage for the operation and maintenance abnormal event to obtain the first abnormal source node traced in the current stage; determining the iterative first abnormal source node from the first abnormal source node traced in the current stage and the first abnormal source node selected in the forward stage, and determining the iterative first abnormal source node as the first abnormal source node selected in the current stage; taking the backward stage as the iterative current stage, returning to the operation of performing node tracing of the current stage for the operation and maintenance abnormal event to obtain the first abnormal source node traced in the current stage, until the tracing is ended, and determining the first abnormal source node selected in the final stage as the first reference abnormal source node.

[0090] For example, for each operation and maintenance abnormal event in the smart park service platform, the node tracing of the current stage can be performed for the operation and maintenance abnormal event to generate the first abnormal source node of the current stage tracing. The first abnormal source node selected after the forward stage tracing of the current stage tracing can be obtained, and the iterative first abnormal source node can be determined from the first abnormal source node of the current stage tracing and the first abnormal source node selected in the forward stage, and the iterative first abnormal source node is determined as the first abnormal source node selected in the current stage. Furthermore, the backward stage tracing of the current stage tracing can be used as the iterative current stage tracing, and the operation of performing the node tracing of the current stage and generating the first abnormal source node of the current stage tracing can be returned for each operation and maintenance abnormal event in the smart park service platform, until the tracing is ended, and the first abnormal source node selected in the final stage is determined as the first reference abnormal source node of the operation and maintenance abnormal event.

[0091] In some alternative implementations, the abnormal source node with the largest node excitation can be selected from the first abnormal source node traced in the current stage and the first abnormal source node selected in the forward stage and determined as the iterative first abnormal source node, and the iterative first abnormal source node can be determined as the first abnormal source node selected in the current stage.

[0092] In some alternative implementations, determining an iterative first abnormal source node from the first abnormal source node traced in the current stage and the first abnormal source node selected in the forward stage includes: determining the significance weight of the first abnormal source node traced in the current stage based on the node excitation data of the first abnormal source node traced in the current stage; determining the significance weight of the first abnormal source node selected in the forward stage based on the node excitation data of the first abnormal source node selected in the forward stage; obtaining the first selection hit parameter corresponding to the current stage; determining the iterative first abnormal source node from the first abnormal source node traced in the current stage and the first abnormal source node selected in the forward stage based on the first selection hit parameter, the significance weight of the first abnormal source node traced in the current stage, and the significance weight of the first abnormal source node selected in the forward stage.

[0093] In some alternative implementations, the significance weight of the first abnormal source node traced in the current stage can be determined based on the node excitation data of the first abnormal source node traced in the current stage, and the significance weight of the first abnormal source node selected in the forward stage can be determined based on the node excitation data of the first abnormal source node selected in the forward stage. Furthermore, the first selection hit parameter corresponding to the current stage can be obtained, and based on the first selection hit parameter, the significance weight of the first abnormal source node traced in the current stage, and the significance weight of the first abnormal source node selected in the forward stage, the iterative first abnormal source node is determined from the first abnormal source node traced in the current stage and the first abnormal source node selected in the forward stage.

[0094] In some alternative implementations, the excitation parameter depth data in the node excitation data of the first abnormal source node traced at the current stage can be mapped to the excitation parameter span data corresponding to the first abnormal source node traced at the current stage. Furthermore, the significance weight of the first abnormal source node traced at the current stage can be determined based on the excitation parameter span data corresponding to the first abnormal source node traced at the current stage. For example, the excitation parameter span data corresponding to the first abnormal source node traced at the current stage, that is, the excitation parameter span value, can be directly used as the significance weight of the first abnormal source node traced at the current stage. Alternatively, the excitation parameter span data corresponding to the first abnormal source node traced at the current stage, that is, the excitation parameter span value, can also be fused to generate the significance weight of the first abnormal source node traced at the current stage.

[0095] In some alternative implementations, the excitation parameter depth data in the node excitation data of the first abnormal source node selected in the forward stage can be mapped to the excitation parameter span data corresponding to the first abnormal source node selected in the forward stage. Furthermore, the significance weight of the first abnormal source node selected in the forward stage can be determined based on the excitation parameter span data corresponding to the first abnormal source node selected in the forward stage. For example, the excitation parameter span data corresponding to the first abnormal source node selected in the forward stage, that is, the excitation parameter span value, can be directly used as the significance weight of the first abnormal source node selected in the forward stage. Alternatively, the excitation parameter span data corresponding to the first abnormal source node selected in the forward stage, that is, the excitation parameter span value, can also be fused to generate the significance weight of the first abnormal source node selected in the forward stage.

[0096] Therefore, in the selection process of each stage, the iterative first abnormal source node is determined from the first abnormal source node traced in the current stage and the first abnormal source node selected in the forward stage through the first selection hit parameter of the current stage, the significance weight of the first abnormal source node traced in the current stage, and the significance weight of the first abnormal source node selected in the forward stage. This can improve the reliability of the first abnormal source node selected in the current stage, so as to ensure the comprehensiveness of the reference abnormal source nodes selected corresponding to each operation and maintenance abnormal event when marking the abnormal root cause of each operation and maintenance abnormal event in the smart park service platform.

[0097] In some alternative implementations, the first abnormal source node selected in the forward stage is loaded into the node library corresponding to the operation and maintenance abnormal event; the iterative first abnormal source node is determined as the first abnormal source node selected in the current stage, including: determining the iterative first abnormal source node as the first abnormal source node selected in the current stage, and replacing the first abnormal source node selected in the forward stage in the node library corresponding to the operation and maintenance abnormal event with the first abnormal source node selected in the current stage.

[0098] For example, the iterative first abnormal source node can be determined as the first abnormal source node selected in the current stage, and the first abnormal source node selected in the forward stage stored in the node library corresponding to the operation and maintenance abnormal event can be replaced with the first abnormal source node selected in the current stage. It can be understood that the abnormal source nodes loaded in the node library corresponding to the operation and maintenance abnormal event will be updated as the abnormal source nodes are traced and selected in each stage, until the tracing is completed, and the first abnormal source node stored in the node library corresponding to the operation and maintenance abnormal event can be used as the first reference abnormal source node of the operation and maintenance abnormal event.

[0099] In some alternative implementations, a second reference abnormal source node is selected from at least two second abnormal source nodes of the linked operation and maintenance abnormal events of the operation and maintenance abnormal events, including: for each linked operation and maintenance abnormal event of the operation and maintenance abnormal event, tracing the nodes of the linked operation and maintenance abnormal event at the current stage to obtain the second abnormal source node traced at the current stage; determining the iterative second abnormal source node from the second abnormal source node traced at the current stage and the second abnormal source node selected in the forward stage, and determining the iterative second abnormal source node as the second abnormal source node selected at the current stage; taking the backward stage as the iterative current stage, returning to the operation of tracing the nodes of the linked operation and maintenance abnormal event at the current stage to obtain the second abnormal source node traced at the current stage, until the tracing is ended, and determining the second abnormal source node selected in the final stage as the second reference abnormal source node.

[0100] For example, for each linkage operation and maintenance abnormal event of the operation and maintenance abnormal event in the smart park service platform, the node tracing of the current stage can be performed for the linkage operation and maintenance abnormal event to generate the second abnormal source node of the current stage tracing. The second abnormal source node selected after the forward stage tracing of the current stage tracing can be obtained, and the iterative second abnormal source node can be determined from the second abnormal source node of the current stage tracing and the second abnormal source node selected in the forward stage, and the iterative second abnormal source node is determined as the second abnormal source node selected in the current stage. Furthermore, the backward stage tracing of the current stage tracing can be used as the iterative current stage tracing to return to each linkage operation and maintenance abnormal event of the operation and maintenance abnormal event in the smart park service platform, and the node tracing of the current stage can be performed for the linkage operation and maintenance abnormal event to generate the operation of the second abnormal source node of the current stage tracing, until the tracing is ended, and the second abnormal source node selected in the final stage is determined as the second reference abnormal source node of the linkage operation and maintenance abnormal event.

[0101] In some alternative implementations, the abnormal source node with the largest node excitation can be selected from the second abnormal source node traced in the current stage and the second abnormal source node selected in the forward stage and determined as the iterative second abnormal source node, and the iterative second abnormal source node can be determined as the second abnormal source node selected in the current stage.

[0102] In some alternative embodiments, determining an iterative second abnormal source node from the second abnormal source node traced in the current stage and the second abnormal source node selected in the forward stage includes: determining the significance weight of the second abnormal source node traced in the current stage based on the node excitation data of the second abnormal source node traced in the current stage; determining the significance weight of the second abnormal source node selected in the forward stage based on the node excitation data of the second abnormal source node selected in the forward stage; obtaining the second selection hit parameter corresponding to the current stage; determining the iterative second abnormal source node from the second abnormal source node traced in the current stage and the second abnormal source node selected in the forward stage based on the second selection hit parameter, the significance weight of the second abnormal source node traced in the current stage, and the significance weight of the second abnormal source node selected in the forward stage.

[0103] In some alternative implementations, the significance weight of the second abnormal source node traced in the current stage can be determined based on the node excitation data of the second abnormal source node traced in the current stage, and the significance weight of the second abnormal source node selected in the forward stage can be determined based on the node excitation data of the second abnormal source node selected in the forward stage. Furthermore, the second selection hit parameter corresponding to the current stage can be obtained, and based on the second selection hit parameter, the significance weight of the second abnormal source node traced in the current stage, and the significance weight of the second abnormal source node selected in the forward stage, the iterative second abnormal source node is determined from the second abnormal source node traced in the current stage and the second abnormal source node selected in the forward stage.

[0104] In some alternative implementations, the excitation parameter depth data in the node excitation data of the second abnormal source node traced at the current stage can be mapped to the excitation parameter span data corresponding to the second abnormal source node traced at the current stage. Furthermore, the significance weight of the second abnormal source node traced at the current stage can be determined based on the excitation parameter span data corresponding to the second abnormal source node traced at the current stage. For example, the excitation parameter span data corresponding to the second abnormal source node traced at the current stage, that is, the excitation parameter span value, can be directly used as the significance weight of the second abnormal source node traced at the current stage. Alternatively, the excitation parameter span data corresponding to the second abnormal source node traced at the current stage, that is, the excitation parameter span value, can also be fused to generate the significance weight of the second abnormal source node traced at the current stage.

[0105] In some alternative implementations, the excitation parameter depth data in the node excitation data of the second abnormal source node selected in the forward stage can be mapped to the excitation parameter span data corresponding to the second abnormal source node selected in the forward stage. Furthermore, the significance weight of the second abnormal source node selected in the forward stage can be determined based on the excitation parameter span data corresponding to the second abnormal source node selected in the forward stage. For example, the excitation parameter span data corresponding to the second abnormal source node selected in the forward stage, that is, the excitation parameter span value, can be directly used as the significance weight of the second abnormal source node selected in the forward stage. Alternatively, the excitation parameter span data corresponding to the second abnormal source node selected in the forward stage, that is, the excitation parameter span value, can also be fused to generate the significance weight of the second abnormal source node selected in the forward stage.

[0106] Therefore, by using the second selection hit parameter of the current stage, the significance weight of the second abnormal source node traced in the current stage, and the significance weight of the second abnormal source node selected in the forward stage, the iterative second abnormal source node is determined from the second abnormal source node traced in the current stage and the second abnormal source node selected in the forward stage, so as to improve the reliability of the second abnormal source node selected in the current stage, so as to ensure the comprehensiveness of the reference abnormal source node selected corresponding to the linkage operation and maintenance abnormal event of each operation and maintenance abnormal event when marking the abnormal root cause of each operation and maintenance abnormal event in the smart park service platform.

[0107] In some alternative implementations, the method also includes: for each operation and maintenance abnormal event in the smart park service platform, determining one or more basic linkage operation and maintenance abnormal events of the operation and maintenance abnormal event from the smart park service platform; for each basic linkage operation and maintenance abnormal event, if there is no abnormal intersection position between the basic linkage operation and maintenance abnormal event and the cyclic operation and maintenance abnormal event, then the basic linkage operation and maintenance abnormal event is used as the linkage operation and maintenance abnormal event of the operation and maintenance abnormal event; wherein, the cyclic operation and maintenance abnormal event is an operation and maintenance abnormal event that triggers a cycle on the first abnormal source node.

[0108] In some alternative implementations, for each operation and maintenance abnormal event in the smart park service platform, one or more basic linkage operation and maintenance abnormal events of the operation and maintenance abnormal event can be determined from the smart park service platform. The operation and maintenance abnormal event that triggers a cycle on the first abnormal source node of the operation and maintenance abnormal event can be determined as a cyclic operation and maintenance abnormal event. For each basic linkage operation and maintenance abnormal event, if there is no abnormal intersection position between the basic linkage operation and maintenance abnormal event and the cyclic operation and maintenance abnormal event, the basic linkage operation and maintenance abnormal event can be used as the linkage operation and maintenance abnormal event of the operation and maintenance abnormal event. If there is an abnormal intersection position between the basic linkage operation and maintenance abnormal event and the cyclic operation and maintenance abnormal event, the basic linkage operation and maintenance abnormal event can be skipped, that is, the basic linkage operation and maintenance abnormal event that has an abnormal intersection position with the cyclic operation and maintenance abnormal event will not be used as the linkage operation and maintenance abnormal event of the operation and maintenance abnormal event.

[0109] In some alternative implementations, for each operation and maintenance abnormal event in the smart park service platform, one or more basic linked operation and maintenance abnormal events of the operation and maintenance abnormal event are determined from the smart park service platform, and the basic linked operation and maintenance abnormal events are directly used as the linked operation and maintenance abnormal events of the operation and maintenance abnormal event.

[0110] In some alternative embodiments, the first reference abnormal source node and the second reference abnormal source node constitute a reference abnormal source node sequence; selecting a target abnormal source node from the first reference abnormal source node and the second reference abnormal source node comprises: selecting a target abnormal source node from the reference abnormal source node sequence; wherein, the possibility of each reference abnormal source node in the reference abnormal source node sequence being selected is positively correlated with the node incentive data of the reference abnormal source node.

[0111] In some alternative implementations, the reference abnormal source node with the largest node stimulus data may be selected from the first reference abnormal source node and the second reference abnormal source node to be determined as the target abnormal source node.

[0112] In some alternative implementations, the node incentive data of the target abnormal source node is combined to determine the node incentive generated by the target abnormal source node of the operation and maintenance abnormal event for the operation and maintenance abnormal event, and generate the target node incentive data corresponding to the operation and maintenance abnormal event, including: updating the incentive parameter depth data in the node incentive data of the target abnormal source node according to the significance weight of the target abnormal source node, and generating the incentive parameter attribute data of the target abnormal source node; the significance weight of the target abnormal source node reflects the depth of the incentive parameter in the node incentive data of the target abnormal source node; the incentive parameter attribute data of the target abnormal source node is weighted by the average significance weight of each target abnormal source node of the operation and maintenance abnormal event, and generating the target node incentive data corresponding to the operation and maintenance abnormal event; wherein, the average significance weight reflects the average depth of the incentive parameter in the node incentive data of each target abnormal source node.

[0113] For example, for each abnormal operation and maintenance event in the smart park service platform, the excitation parameter depth data in the node excitation data of the target abnormal source node can be updated according to the significance weight of the target abnormal source node of the abnormal operation and maintenance event, and the excitation parameter attribute data of the target abnormal source node of the abnormal operation and maintenance event can be generated. Furthermore, the average significance weight of each target abnormal source node of the abnormal operation and maintenance event can be weighted with the excitation parameter attribute data of the target abnormal source node of the abnormal operation and maintenance event to generate the target node excitation data corresponding to the abnormal operation and maintenance event.

[0114] In some alternative implementations, the excitation parameter depth data in the node excitation data of the target abnormal source node can be mapped to the excitation parameter saturation data corresponding to the target abnormal source node, and the significance weight of the target abnormal source node can be determined based on the excitation parameter saturation data corresponding to the target abnormal source node. For each operation and maintenance abnormal event in the smart park service platform, the excitation parameter depth data in the node excitation data of the target abnormal source node can be updated according to the significance weight of the target abnormal source node of the operation and maintenance abnormal event, and the excitation parameter attribute data of the target abnormal source node of the operation and maintenance abnormal event can be generated. For each target abnormal source node of the operation and maintenance abnormal event, the excitation parameter depth data in the node excitation data of the target abnormal source node is mapped to the excitation parameter saturation data corresponding to the target abnormal source node, and the significance weight of the target abnormal source node is determined based on the excitation parameter saturation data corresponding to the target abnormal source node. The computer device can average the significance weights of each target abnormal source node of the operation and maintenance abnormal event to generate an average significance weight of each target abnormal source node. Furthermore, the average significance weight of each target abnormal source node of the operation and maintenance abnormal event can be weighted with the incentive parameter attribute data of the target abnormal source node of the operation and maintenance abnormal event to generate the target node incentive data corresponding to the operation and maintenance abnormal event.

[0115] In some alternative implementations, the present embodiment may also map the excitation parameter depth data in the node excitation data of the target abnormal source node to the excitation parameter span data corresponding to the target abnormal source node; and determine the significance weight of the target abnormal source node based on the excitation parameter span data corresponding to the target abnormal source node.

[0116] In some alternative implementations, the excitation parameter depth data in the node excitation data of the target abnormal source node can be mapped to the excitation parameter span data corresponding to the target abnormal source node, and the significance weight of the target abnormal source node can be determined based on the excitation parameter span data corresponding to the target abnormal source node. For each operation and maintenance abnormal event in the smart park service platform, the excitation parameter depth data in the node excitation data of the target abnormal source node can be updated according to the significance weight of the target abnormal source node of the operation and maintenance abnormal event, and the excitation parameter attribute data of the target abnormal source node of the operation and maintenance abnormal event can be generated. Furthermore, the average significance weight of each target abnormal source node of the operation and maintenance abnormal event can be weighted with the excitation parameter attribute data of the target abnormal source node of the operation and maintenance abnormal event to generate the target node excitation data corresponding to the operation and maintenance abnormal event.

[0117] In some alternative implementations, the present embodiment may also map the excitation parameter depth data in the node excitation data of the target abnormal source node to the excitation parameter span data corresponding to the target abnormal source node for each target abnormal source node of the operation and maintenance abnormal event; determine the significance weight of the target abnormal source node based on the excitation parameter span data corresponding to the target abnormal source node; and average the significance weights of each target abnormal source node of the operation and maintenance abnormal event to generate an average significance weight of each target abnormal source node.

[0118] In some alternative implementations, for each operation and maintenance abnormal event in the smart park service platform, the excitation parameter depth data in the node excitation data of the target abnormal source node can be updated according to the significance weight of the target abnormal source node of the operation and maintenance abnormal event, and the excitation parameter attribute data of the target abnormal source node of the operation and maintenance abnormal event is generated. For each target abnormal source node of the operation and maintenance abnormal event, the excitation parameter depth data in the node excitation data of the target abnormal source node is mapped to the excitation parameter span data corresponding to the target abnormal source node, and the significance weight of the target abnormal source node is determined based on the excitation parameter span data corresponding to the target abnormal source node. Then, the significance weights of each target abnormal source node of the operation and maintenance abnormal event can be averaged to generate the average significance weight of each target abnormal source node. Then, the average significance weight of each target abnormal source node of the operation and maintenance abnormal event can be weighted with the excitation parameter attribute data of the target abnormal source node of the operation and maintenance abnormal event to generate the target node excitation data corresponding to the operation and maintenance abnormal event.

[0119] In some alternative implementations, the excitation parameter depth data in the node excitation data of the target abnormal source node can be mapped to the excitation parameter span data corresponding to the target abnormal source node, and the significance weight of the target abnormal source node can be determined based on the excitation parameter span data corresponding to the target abnormal source node. For each operation and maintenance abnormal event in the smart park service platform, the excitation parameter depth data in the node excitation data of the target abnormal source node can be updated according to the significance weight of the target abnormal source node of the operation and maintenance abnormal event, and the excitation parameter attribute data of the target abnormal source node of the operation and maintenance abnormal event can be generated. For each target abnormal source node of the operation and maintenance abnormal event, the excitation parameter depth data in the node excitation data of the target abnormal source node is mapped to the excitation parameter span data corresponding to the target abnormal source node, and the significance weight of the target abnormal source node is determined based on the excitation parameter span data corresponding to the target abnormal source node. Furthermore, the significance weights of each target abnormal source node of the operation and maintenance abnormal event can be averaged to generate the average significance weight of each target abnormal source node. Furthermore, the average significance weight of each target abnormal source node of the operation and maintenance abnormal event can be weighted with the incentive parameter attribute data of the target abnormal source node of the operation and maintenance abnormal event to generate the target node incentive data corresponding to the operation and maintenance abnormal event.

[0120] The steps of a further embodiment are described below, which specifically include the following steps:

[0121] Step S202: for each operation and maintenance abnormal event in the smart park service platform, the node tracing of the operation and maintenance abnormal event at the current stage is performed to obtain the first non-directly connected abnormal source node of the current stage tracing.

[0122] Step S204, based on the node incentive data of the first indirect abnormal source node traced in the current stage, determine the significance weight of the first indirect abnormal source node traced in the current stage; the significance weight of the first indirect abnormal source node is positively correlated with the node incentive data of the first indirect abnormal source node.

[0123] Step S206, determining the significance weight of the first indirect abnormal source node selected in the forward stage based on the node excitation data of the first indirect abnormal source node selected in the forward stage.

[0124] Step S208, obtaining the first selection hit parameter corresponding to the current stage.

[0125] Step S210, based on the first selection hit parameter, the significance weight of the first indirect abnormal source node traced in the current stage, and the significance weight of the first indirect abnormal source node selected in the forward stage, determine the iterative first indirect abnormal source node from the first indirect abnormal source node traced in the current stage and the first indirect abnormal source node selected in the forward stage, and determine the iterative first indirect abnormal source node as the first indirect abnormal source node selected in the current stage.

[0126] Step S212, taking the backward stage as the current stage of iteration, returning to the operation of tracing the nodes of the current stage for the operation and maintenance abnormal event to obtain the first non-directly connected abnormal source node of the current stage tracing, until the tracing is completed, the first non-directly connected abnormal source node selected in the final stage is determined as the first reference non-directly connected abnormal source node.

[0127] Step S214: for each operation and maintenance abnormal event in the smart park service platform, one or more basic linkage operation and maintenance abnormal events of the operation and maintenance abnormal event are determined from the smart park service platform.

[0128] Step S216: For each basic linkage operation and maintenance abnormal event, if there is no abnormal intersection position between the basic linkage operation and maintenance abnormal event and the cyclic operation and maintenance abnormal event, the basic linkage operation and maintenance abnormal event is used as the linkage operation and maintenance abnormal event of the operation and maintenance abnormal event; the cyclic operation and maintenance abnormal event is an operation and maintenance abnormal event that triggers a cycle on the first non-directly connected abnormal source node.

[0129] Step S218: for each linkage operation and maintenance abnormal event of the operation and maintenance abnormal event, the node tracing of the linkage operation and maintenance abnormal event at the current stage is performed to obtain a second non-directly connected abnormal source node of the current stage tracing.

[0130] Step S220, based on the node incentive data of the second indirect abnormal source node traced in the current stage, determine the significance weight of the second indirect abnormal source node traced in the current stage; the significance weight of the second indirect abnormal source node is positively related to the node incentive data of the second indirect abnormal source node.

[0131] Step S222: determining the significance weight of the second indirect abnormal source node selected in the forward stage based on the node excitation data of the second indirect abnormal source node selected in the forward stage.

[0132] Step S224, obtaining the second selection hit parameter corresponding to the current stage.

[0133] Step S226, based on the second selection hit parameter, the significance weight of the second indirect abnormal source node traced in the current stage, and the significance weight of the second indirect abnormal source node selected in the forward stage, determine the iterative second indirect abnormal source node from the second indirect abnormal source node traced in the current stage and the second indirect abnormal source node selected in the forward stage, and determine the iterative second indirect abnormal source node as the second indirect abnormal source node selected in the current stage.

[0134] Step S228, taking the backward stage as the current stage of iteration, returning to the operation of tracing the nodes of the current stage for the linkage operation and maintenance abnormal event to obtain the second non-directly connected abnormal source node of the current stage tracing, until the tracing is completed, the second non-directly connected abnormal source node selected in the final stage is determined as the second reference non-directly connected abnormal source node.

[0135] Step S230, selecting a target non-directly connected abnormal source node from a reference abnormal source node sequence; the first reference non-directly connected abnormal source node and the second reference non-directly connected abnormal source node constitute a reference abnormal source node sequence; the possibility of each reference non-directly connected abnormal source node in the reference abnormal source node sequence being selected is positively correlated with the node incentive data of the reference non-directly connected abnormal source node.

[0136] Step S232, based on the significance weight of the target non-directly connected abnormal source node, update the excitation parameter depth data in the node excitation data of the target non-directly connected abnormal source node, and generate the excitation parameter attribute data of the target non-directly connected abnormal source node; the significance weight of the target non-directly connected abnormal source node reflects the depth of the excitation parameter in the node excitation data of the target non-directly connected abnormal source node.

[0137] Step S234, the average significance weight of each related non-directly connected abnormal source node of the operation and maintenance abnormal event is weighted by the incentive parameter attribute data of the target non-directly connected abnormal source node to generate the target node incentive data corresponding to the operation and maintenance abnormal event; the average significance weight reflects the average depth of the incentive parameter in the node incentive data of each related non-directly connected abnormal source node. The related non-directly connected abnormal source nodes include the first non-directly connected abnormal source node and the second non-directly connected abnormal source node; the target node incentive data is used to mark the abnormal root cause of the corresponding operation and maintenance abnormal event.

[0138] Further, Figure 2 FIG. 1 is a schematic diagram of the hardware structure of a smart park operation and maintenance system 100 for implementing the method provided in an embodiment of the present application. Figure 2As shown, the smart park operation and maintenance system 100 may include one or more processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 and a controller 108 for communication functions. It can be understood by those skilled in the art that Figure 2 The structure shown is for illustration only and does not limit the structure of the above-mentioned smart park operation and maintenance system 100. For example, the smart park operation and maintenance system 100 may also include Figure 2 More or fewer components as shown, or with Figure 2 Different configurations are shown.

[0139] The memory 104 can be used to store software programs and modules of application software, such as program instructions corresponding to the above-mentioned method embodiments in the embodiments of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned method for processing information of smart park operation and maintenance applied to artificial intelligence. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the smart park operation and maintenance system 100 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0140] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the smart park operation and maintenance system 100. In one example, the transmission device 106 includes a network adapter, which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency module, which is used to communicate with the Internet wirelessly.

[0141] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of the embodiments of the present application are described. Other embodiments are within the scope of the attached claims. In some cases, the actions or steps recorded in the claims can be performed according to an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0142] Each embodiment in the embodiments of the present application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the above different embodiments, since they are basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0143] A person of ordinary skill in the art will appreciate that all or part of the steps for implementing the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the above program may be loaded into a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

Claims

1. A method for processing smart park operation and maintenance information applied to artificial intelligence, characterized in that: The method comprises: For each operation and maintenance abnormal event in the smart park service platform, a first reference abnormal source node is selected from at least two first abnormal source nodes of the operation and maintenance abnormal event; the possibility of the first abnormal source node being selected is positively associated with the node incentive data of the first abnormal source node, and the node incentive data of the first abnormal source node refers to data or information related to the first abnormal source node, which is used to determine the positive association between it and the operation and maintenance abnormal event, specifically including real-time or historical monitoring data, log files or event records, fault reports or alarm notifications, and system status information from the first abnormal source node; Selecting a second reference abnormal source node from at least two second abnormal source nodes of the linkage operation and maintenance abnormal event of the operation and maintenance abnormal event; the possibility of the second abnormal source node being selected is positively related to the node incentive data of the second abnormal source node; Selecting a target abnormal source node from the first reference abnormal source node and the second reference abnormal source node; According to the node incentive data of the target abnormal source node, determine the node incentive generated by the target abnormal source node of the operation and maintenance abnormal event to the operation and maintenance abnormal event, and generate the target node incentive data corresponding to the operation and maintenance abnormal event; the target abnormal source node includes the first abnormal source node and the second abnormal source node; the target node incentive data is used to mark the abnormal root cause of the corresponding operation and maintenance abnormal event; For each operation and maintenance abnormal event in the smart park service platform, selecting a first reference abnormal source node from at least two first abnormal source nodes of the operation and maintenance abnormal event includes: For each abnormal operation and maintenance event in the smart park service platform, the node tracing of the abnormal operation and maintenance event at the current stage is performed to obtain the first abnormal source node of the current stage tracing; Determine an iterative first abnormal source node from the first abnormal source node traced in the current stage and the first abnormal source node selected in the forward stage, and determine the iterative first abnormal source node as the first abnormal source node selected in the current stage; Taking the backward stage as the current stage of iteration, returning to the operation of performing node tracing of the current stage for the operation and maintenance abnormal event to obtain the first abnormal source node of the current stage tracing, until the tracing is finished, determining the first abnormal source node selected in the final stage as the first reference abnormal source node; The step of determining the iterative first abnormal source node from the first abnormal source node traced back in the current stage and the first abnormal source node selected in the forward stage comprises: Determine the significance weight of the first abnormal source node traced back in the current stage based on the node incentive data of the first abnormal source node traced back in the current stage; Determine the significance weight of the first abnormal source node selected in the forward stage based on the node excitation data of the first abnormal source node selected in the forward stage; Get the first selection hit parameter corresponding to the current stage; Based on the first selection hit parameter, the significance weight of the first abnormal source node traced in the current stage, and the significance weight of the first abnormal source node selected in the forward stage, determining the iterative first abnormal source node from the first abnormal source node traced in the current stage and the first abnormal source node selected in the forward stage; The first abnormal source node selected in the forward stage is loaded into the node library corresponding to the operation and maintenance abnormal event; The step of determining the iterative first abnormal source node as the first abnormal source node selected in the current stage includes: Determine the iterative first abnormal source node as the first abnormal source node selected in the current stage, and replace the first abnormal source node selected in the forward stage in the node library corresponding to the operation and maintenance abnormal event with the first abnormal source node selected in the current stage; The selecting a second reference abnormal source node from at least two second abnormal source nodes of the linkage operation and maintenance abnormal event of the operation and maintenance abnormal event includes: For each linkage operation and maintenance abnormal event of the operation and maintenance abnormal event, performing node tracing at the current stage for the linkage operation and maintenance abnormal event to obtain a second abnormal source node traced at the current stage; Determine the significance weight of the second abnormal source node traced back in the current stage based on the node incentive data of the second abnormal source node traced back in the current stage; Determine the significance weight of the second abnormal source node selected in the forward stage based on the node excitation data of the second abnormal source node selected in the forward stage; Get the second selection hit parameter corresponding to the current stage; Based on the second selection hit parameter, the significance weight of the second abnormal source node traced in the current stage, and the significance weight of the second abnormal source node selected in the forward stage, an iterative second abnormal source node is determined from the second abnormal source node traced in the current stage and the second abnormal source node selected in the forward stage, and the iterative second abnormal source node is determined as the second abnormal source node selected in the current stage; Taking the backward stage as the current stage of iteration, returning to the operation of performing node tracing of the linkage operation and maintenance abnormal event in the current stage to obtain the second abnormal source node of the current stage tracing, until the tracing is finished, the second abnormal source node selected in the final stage is determined as the second reference abnormal source node; The method further comprises: For each operation and maintenance abnormal event in the smart park service platform, determine one or more basic linkage operation and maintenance abnormal events of the operation and maintenance abnormal event from the smart park service platform; For each basic linkage operation and maintenance abnormal event, if there is no abnormal intersection position between the basic linkage operation and maintenance abnormal event and the cyclic operation and maintenance abnormal event, the basic linkage operation and maintenance abnormal event is used as the linkage operation and maintenance abnormal event of the operation and maintenance abnormal event, and the cyclic operation and maintenance abnormal event is the operation and maintenance abnormal event that triggers the cycle on the first abnormal source node; The first reference abnormal source node and the second reference abnormal source node constitute a reference abnormal source node sequence; The selecting a target abnormal source node from the first reference abnormal source node and the second reference abnormal source node comprises: Selecting a target abnormal source node from the reference abnormal source node sequence, wherein the probability of each reference abnormal source node in the reference abnormal source node sequence being selected is positively related to the node incentive data of the reference abnormal source node; The step of determining the node incentive generated by the target abnormal source node of the operation and maintenance abnormal event to the operation and maintenance abnormal event based on the node incentive data of the target abnormal source node, and generating the target node incentive data corresponding to the operation and maintenance abnormal event, comprises: According to the significance weight of the target abnormal source node, the excitation parameter depth data in the node excitation data of the target abnormal source node is updated to generate the excitation parameter attribute data of the target abnormal source node; the significance weight of the target abnormal source node reflects the depth of the excitation parameter in the node excitation data of the target abnormal source node, and the excitation parameter depth data indicates the importance or influence of the excitation parameter on the target abnormal source node; The average significance weight of each target abnormal source node of the operation and maintenance abnormal event is weighted by the excitation parameter attribute data of the target abnormal source node to generate the target node excitation data corresponding to the operation and maintenance abnormal event, wherein the average significance weight reflects the average depth of the excitation parameter in the node excitation data of each target abnormal source node; The method further comprises: Mapping the excitation parameter depth data in the node excitation data of the target abnormal source node to the excitation parameter span data corresponding to the target abnormal source node, wherein the excitation parameter span data refers to describing the variation range or value range of a certain excitation parameter; Determining a significance weight of the target abnormal source node based on the excitation parameter span data corresponding to the target abnormal source node; And for each target abnormal source node of the operation and maintenance abnormal event, mapping the excitation parameter depth data in the node excitation data of the target abnormal source node to the excitation parameter span data corresponding to the target abnormal source node; Determining a significance weight of the target abnormal source node based on the excitation parameter span data corresponding to the target abnormal source node; The significance weights of the target abnormal source nodes of the operation and maintenance abnormal event are averaged to generate the average significance weights of the target abnormal source nodes.

2. A smart park operation and maintenance system, characterized in that: The smart park operation and maintenance system includes a processor and a readable storage medium, wherein the readable storage medium stores a program, and when the program is executed by the processor, the smart park operation and maintenance information processing method applied to artificial intelligence as described in claim 1 is implemented.

Images