Intelligent operation and maintenance network fault monitoring method, system, equipment and medium

Abstract

The invention discloses an intelligent operation and maintenance network fault monitoring method, system and device and a medium, a communication network architecture is visualized through full-link topology reduction and real-time topology drawing, monitoring and maintenance are facilitated, and problems can be found and solved in time. Through combination of GIS and OTDR technologies, a communication optical cable fault point can be accurately positioned. The communication network architecture is visualized through full-link topology reduction and real-time topology drawing, monitoring and maintenance are facilitated, and problems can be found and solved in time; fault data in communication data can be quickly identified through real-time difference monitoring of communication data flow characteristics; by tracing the identified fault data and predicting the propagation path of the fault, multi-dimensional fault reason analysis and prediction can be carried out, the fault detection, positioning, tracing and prediction capabilities of the communication network are improved, and the intelligent operation and maintenance capability of the network is enhanced, so that the reliability of the network and the continuity of services are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of communication fault processing, and in particular to an intelligent operation and maintenance network fault monitoring method, system, equipment and medium. Background Art

[0002] With the rapid development of information technology, communication networks have become one of the basic infrastructures of modern society. As a key component of communication networks, optical cables carry a large amount of data transmission tasks. The stability and reliability of optical cable networks are crucial to ensuring communication quality and improving user experience. Therefore, effective fault monitoring and diagnosis of optical cable networks are important challenges faced by communication operators and network maintenance personnel. The purpose of fault monitoring is to promptly detect and resolve abnormal conditions in the network to prevent the spread of faults and the expansion of their impact. Through fault monitoring, network outage time can be reduced and network availability and service quality can be improved. In addition, fault monitoring can also provide data support for network optimization, helping operators to better plan and adjust network resources. Existing optical cable fault monitoring technologies mainly include the following methods:

[0003] 1. Regular inspection: Regularly inspect the optical cable line through manual or automated equipment to record the status and performance indicators of the optical cable. Although this method can find some obvious faults, it often lacks real-time and predictive capabilities;

[0004] 2. Performance monitoring: Use the network management system (NMS) to monitor the key performance indicators (KPIs) of the optical cable network, such as signal strength, bit error rate, etc. This method can provide real-time network status information, but has limited ability to analyze and locate complex fault causes;

[0005] 3. Fault reporting system: Relying on fault information reported by users for processing. This method has a fast response speed, but it can only solve problems that users directly experience, and is powerless for potential or unnoticed faults;

[0006] 4. Model-based prediction: Use historical data and statistical models to predict possible failures. This method has a certain degree of foresight, but the accuracy of the model is limited by the quality of the data and the complexity of the model.

[0007] Therefore, existing technologies often find it difficult to achieve real-time monitoring of optical cable networks, resulting in delays in fault discovery and response, and low positioning accuracy. It is difficult to extract valuable information from massive data and conduct in-depth fault cause analysis. There is a lack of multi-dimensional analysis, and often only a single factor is considered. There is a lack of multi-dimensional comparative analysis, making it difficult to fully understand the causes and impacts of faults. Summary of the invention

[0008] The technical problem to be solved by the present invention is that the monitoring accuracy is low and not real-time, and the fault consideration factors are single and lack multi-dimensional analysis. The purpose is to provide an intelligent operation and maintenance network fault monitoring method, system, equipment and medium. Through full-link topology restoration and real-time topology drawing, the communication network architecture is visualized, which is convenient for monitoring and maintenance, and problems can be discovered and solved in time; by combining GIS and OTDR technology, the communication optical cable fault point can be accurately located; through full-link topology restoration and real-time topology drawing, the communication network architecture is visualized, which is convenient for monitoring and maintenance, and problems can be discovered and solved in time; through real-time differential monitoring of communication data flow characteristics, fault data in communication data can be quickly identified; by tracing the identified fault data and predicting the propagation path of the fault, multi-dimensional fault cause analysis and prediction can be performed, thereby improving the fault detection, positioning, tracing and prediction capabilities of the communication network, enhancing the intelligent operation and maintenance capabilities of the network, thereby improving the reliability of the network and the continuity of business.

[0009] The present invention is achieved through the following technical solutions:

[0010] A first aspect of the present invention provides an intelligent operation and maintenance network fault monitoring method, comprising the following specific steps:

[0011] Obtain the optical cable data of the target detection area, draw the real-time topology through full-link topology restoration, and generate the communication network architecture;

[0012] Extract communication transmission lines based on network architecture, and locate and identify communication transmission lines based on GIS and optical time domain reflectometer OTDR technology;

[0013] Based on the positioning and identification, the communication data is segmented into sessions according to the five-tuple, and the communication data flow features are extracted based on the segmented communication data;

[0014] Monitor the real-time differences in communication data stream characteristics and identify faulty data in communication data;

[0015] Based on cross-layer analysis, the identified fault data is traced to its source, the sampling rate and message interception length are set, and the source port message of the fault data is parsed to obtain multi-dimensional time series data of the fault data;

[0016] Perform cross-layer analysis on multi-dimensional time series data, trace the source of identified fault data, and predict the propagation path of the fault;

[0017] Perform intelligent operation and maintenance network adjustments based on predicted fault data.

[0018] Furthermore, the positioning and identification of the communication transmission line based on GIS and optical time domain reflectometer OTDR technology specifically includes:

[0019] Acquire communication transmission lines, extract the map topology corresponding to the communication transmission lines based on GIS and optical time domain reflectometer (OTDR) technology, and digitize the extracted network data;

[0020] Extract time domain reflection features of optical pulses based on digitized data;

[0021] Based on the time domain reflection characteristics, the fiber Bragg grating is used to mark the communication line to obtain a communication transmission line with positioning and identification.

[0022] Further, the extracting of communication data stream features from the communication data based on positioning and identification specifically includes:

[0023] Collect network traffic and data indicators based on communication data, and clean and desensitize the collected data;

[0024] The traffic data is segmented into sessions according to the five-tuple, and all packets with the same five-tuple are defined as a communication data flow;

[0025] Divide the communication data stream according to the different data types of each attribute;

[0026] The key features of each session are extracted and classified according to the divided communication data streams to obtain the communication data stream features.

[0027] Further, the communication data is segmented into sessions according to five-tuples based on the positioning and identification, and communication data flow feature extraction is performed based on the segmented communication data, specifically including:

[0028] Collect network traffic and data indicators based on communication data, and clean and desensitize the collected data;

[0029] The traffic data is segmented into sessions according to the five-tuple, and all packets with the same five-tuple are defined as a communication data flow;

[0030] Divide the communication data stream according to the different data types of each attribute;

[0031] The key features of each session are extracted and classified according to the divided communication data streams to obtain the communication data stream features.

[0032] Furthermore, the cross-layer analysis of the multi-dimensional time series data and tracing of the identified fault data specifically include:

[0033] Construct a deep autoencoder network structure and use multiple deep autoencoders for unlabeled high-dimensional data in multi-dimensional time series;

[0034] Use unlabeled multi-dimensional time series data to integrate multiple deep autoencoders for training, use the hidden layer output of the autoencoder as the feature representation of the data, and obtain abnormal features;

[0035] Based on the abnormal features, learn the mapping from abnormal features to latent space and reconstruct the latent space features of the data;

[0036] The reconstruction error of each layer of the deep autoencoder network structure is calculated based on the extracted abnormal features. The structure and parameters of the deep autoencoder are optimized through reverse iteration according to the calculation results to obtain the fault generation model of the communication network.

[0037] Furthermore, the predicted fault propagation path specifically includes:

[0038] Based on the fault generation model of the communication network, end-to-end hop-by-hop detection is performed on the faulty node, and fault detection data of the faulty node is collected hop by hop;

[0039] Locating the faulty node based on the faulty node's faulty detection data and the communication network identifier;

[0040] Compute the representation of the faulty node and its neighboring nodes, and identify the affected area;

[0041] Dynamically adjust the network status, update the representation of each node in real time by aggregating neighbor nodes, and predict the fault propagation path.

[0042] A second aspect of the present invention provides an intelligent operation and maintenance network fault monitoring system, which is applied to an intelligent operation and maintenance network fault monitoring method, including:

[0043] A data acquisition module, used to obtain optical cable data of the target detection area;

[0044] The topology generation module is used to draw the real-time topology through full-link topology restoration, generate the communication network architecture, and extract the communication transmission lines according to the network architecture;

[0045] Positioning module, used to locate and identify communication transmission lines based on GIS and optical time domain reflectometer OTDR technology;

[0046] Feature extraction module: extracts communication data stream features based on positioning and identification;

[0047] Data monitoring module: used to monitor the real-time differences in communication data flow characteristics, identify fault data in communication data, and trace the identified fault data based on cross-layer analysis to predict the propagation path of the fault.

[0048] A third aspect of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, an intelligent operation and maintenance network fault monitoring method is implemented.

[0049] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for monitoring faults in an intelligent operation and maintenance network.

[0050] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0051] Through full-link topology restoration and real-time topology drawing, the communication network architecture is visualized, which is convenient for monitoring and maintenance, and can timely discover and solve problems; by combining GIS and OTDR technology, the fault point of the communication optical cable can be accurately located; through full-link topology restoration and real-time topology drawing, the communication network architecture is visualized, which is convenient for monitoring and maintenance, and can timely discover and solve problems; through real-time differential monitoring of communication data flow characteristics, fault data in communication data can be quickly identified; by tracing the identified fault data and predicting the propagation path of the fault, multi-dimensional fault cause analysis and prediction can be performed, which improves the fault detection, positioning, tracing and prediction capabilities of the communication network, enhances the network's intelligent operation and maintenance capabilities, and thus improves network reliability and business continuity. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0053] Figure 1 This is a monitoring method in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0055] As a possible implementation, Figure 1As shown, this embodiment provides an intelligent operation and maintenance network fault monitoring method, including the following specific steps: obtaining optical cable data in the target detection area, drawing a real-time topology through full-link topology restoration, and generating a communication network architecture; extracting communication transmission lines based on the network architecture, and locating and identifying the communication transmission lines based on GIS and optical time domain reflectometer OTDR technology; performing session segmentation on the communication data according to five-tuple traffic data based on the positioning and identification, and extracting communication data stream features based on the segmented communication data; monitoring the real-time differences in communication data stream features, and identifying fault data in the communication data; tracing the source of the identified fault data based on cross-layer analysis, setting the sampling rate and message interception length, parsing the source port message of the fault data, and obtaining multi-dimensional time series data of the fault data; performing cross-layer analysis on the multi-dimensional time series data, tracing the source of the identified fault data, and predicting the propagation path of the fault; and adjusting the intelligent operation and maintenance network according to the predicted fault data. This embodiment visualizes the communication network architecture through full-link topology restoration and real-time topology drawing, which is convenient for monitoring and maintenance, and can timely discover and solve problems; by combining GIS and OTDR technology, the fault point of the communication optical cable can be accurately located; the communication network architecture is visualized through full-link topology restoration and real-time topology drawing, which is convenient for monitoring and maintenance, and can timely discover and solve problems; through real-time differential monitoring of communication data flow characteristics, fault data in communication data can be quickly identified; by tracing the identified fault data and predicting the propagation path of the fault, multi-dimensional fault cause analysis and prediction can be performed, thereby improving the fault detection, positioning, tracing and prediction capabilities of the communication network, enhancing the network's intelligent operation and maintenance capabilities, and thus improving the network's reliability and business continuity.

[0056] In some possible implementations, drawing a real-time topology through full-link topology restoration to generate a communication network architecture specifically includes:

[0057] First, the obtained optical cable data of the target detection area needs to be used as the basic information for map digitization conversion. In this embodiment, it can be implemented through the JuncTry map digitization processing system, which supports multiple data formats, including vector data (such as Shp, GeoJSON) and structured data (such as CSV, Excel), as well as geographic database types (such as Geodatabase).

[0058] Transform and splice the basic information to establish topological relationships;

[0059] The deviation in the topological relationship is corrected, the map is vectorized, the topological relationship of the map is corrected and matched, and the communication network architecture is obtained.

[0060] For correction, in the 5G network architecture, the service quality and communication quality requirements in new scenarios require accurate prediction and estimation of site layout and network coverage requirements. This involves accurate prediction and estimation of the communication distance, coverage and signal reception quality of the new generation of mobile communication networks, as well as correction research on propagation models.

[0061] In some possible implementations, by combining GIS and OTDR technology, communication transmission lines can be effectively located and identified, and the management efficiency and fault response speed of communication lines can be improved. The communication transmission lines are located and identified based on GIS and optical time domain reflectometer OTDR technology, specifically including:

[0062] Acquire the communication transmission lines, and extract the map topology relationship corresponding to the communication transmission lines based on GIS and optical time domain reflectometer OTDR technology. The geographic information system (GIS) technology is used to collect, store, manage, analyze and describe the spatial geographic distribution data of the communication transmission lines, which can realize the collection and management of spatial related data. Through GIS technology, the spatial data and attribute data of the communication optical cable are uniformly stored and managed to realize the digitization of the map, which involves the analysis of the needs for accurate positioning of the communication optical cable faults, and the digitization of the map by combining GIS and OTDR technology to realize the unified storage and management of spatial data and attribute data.

[0063] The time domain reflection feature of the optical pulse is extracted based on the digital data; the attenuation and loss information of the optical fiber is measured by using the OTDR technology by emitting pulsed light into the optical fiber and receiving the scattered light power returned along the axial direction of the optical fiber. The OTDR system can largely solve the problem of the health status of optical fiber communication operations, and obtain the information of optical fiber transmission loss by measuring the back Rayleigh scattered light power returned along the axial direction of the optical fiber.

[0064] Based on the time domain reflection characteristics, the fiber Bragg grating is used to mark the communication line, and the communication transmission line with positioning and identification is obtained. It not only improves the maintenance efficiency of the communication line, but also enhances the ability to respond quickly to communication line failures.

[0065] In some possible implementations, based on the positioning and identification, the communication data is segmented into sessions according to the five-tuple, and the communication data flow feature is extracted based on the segmented communication data, specifically including:

[0066] Collect network traffic and data indicators based on communication data, and clean and desensitize the collected data;

[0067] The traffic data is segmented into sessions according to the five-tuple (source IP, destination IP, source port, destination port, protocol type), and all packets with the same five-tuple are defined as a communication data flow;

[0068] Divide the communication data stream according to the different data types of each attribute;

[0069] The key features of each session are extracted and classified according to the divided communication data streams to obtain the communication data stream features.

[0070] In this embodiment, key feature extraction and classification can utilize deep learning technologies, such as automatic encoder (SAE), convolutional neural network (CNN), recurrent neural network (RNN), deep belief network (DBN), etc., to extract the features of data streams and perform classification, wherein feature extraction includes flow statistical features and timing features, i.e., uplink and downlink data packet flow characteristics, data packet intervals, discreteness of data packets, data packet length distribution, timestamp information, etc.

[0071] In some possible implementations, the real-time differences in the characteristics of the communication data stream are monitored to identify fault data in the communication data, specifically including: inputting the characteristics of the communication data stream into a neural network model. The characteristics include the size of the data packet, the transmission time, the source and destination IP addresses, etc. The neural network model is learned and trained using labeled normal and abnormal communication data. The network parameters are continuously adjusted through the back propagation algorithm so that the model can better learn the characteristics of the communication data. The trained neural network model can identify the abnormal data characteristics and pattern structures in the network. Based on the analysis results of the neural network model, fault data in the communication network can be obtained.

[0072] In some possible implementations, tracing the source of the identified fault data based on cross-layer analysis specifically includes:

[0073] First, it is necessary to determine the appropriate sampling rate and message interception length to ensure that sufficient fault data can be captured for analysis. Then, the source port message of the fault data is parsed to obtain the multi-dimensional time series data of the fault data, which includes various performance indicators and state variables in the time series;

[0074] In multi-dimensional time series, multiple deep autoencoders are used to extract features from unlabeled high-dimensional data to obtain abnormal features. Specifically, the deep autoencoder consists of an encoder and a decoder. The encoder is responsible for compressing the data into a low-dimensional latent space, while the decoder attempts to reconstruct these low-dimensional representations back to the original data. By training the deep autoencoder, effective feature representations of the data can be learned. A communication network fault generation model based on abnormal features is then constructed to understand the internal mechanism of the fault, so that the root cause of the fault can be identified and guidance can be provided for fault prevention and repair, thereby improving the reliability and stability of the network.

[0075] In some possible implementations, a communication network fault generation model based on abnormal features is constructed, specifically including: selecting a suitable machine learning algorithm to model the fault mechanism based on the extracted abnormal features, using the extracted abnormal features as model input, and training the selected machine learning model. The trained model is used to predict the fault of the communication network, and the prediction results are compared with the actual fault conditions to evaluate the accuracy and effectiveness of the model. According to the prediction results of the model, the network status is dynamically adjusted to prevent or mitigate the impact of the fault. This may involve real-time monitoring of the network status and taking corresponding measures based on the prediction results, thereby realizing the prediction and prevention of communication network faults.

[0076] In some possible implementations, predicting the propagation path of a fault specifically includes:

[0077] Based on the fault generation model of the communication network, end-to-end hop-by-hop detection is performed on the faulty node, that is, each node in the communication network is detected one by one to collect fault detection data of the faulty node.

[0078] Using the collected fault detection data and combining it with network identification information, the location of the faulty node can be accurately determined;

[0079] By analyzing the status and behavior of the faulty node and its neighboring nodes, we construct a node representation and identify the affected area.

[0080] By aggregating neighbor nodes, the representation of each node is updated in real time to predict the possible propagation path of the fault. This can improve the accuracy of fault prediction and take preventive measures in time to reduce the impact of the fault on the network.

[0081] As a possible implementation mode, this embodiment provides an intelligent operation and maintenance network fault monitoring system, including:

[0082] A data acquisition module, used to obtain optical cable data of the target detection area;

[0083] The topology generation module is used to draw the real-time topology through full-link topology restoration, generate the communication network architecture, and extract the communication transmission lines according to the network architecture;

[0084] Positioning module, used to locate and identify communication transmission lines based on GIS and optical time domain reflectometer OTDR technology;

[0085] Feature extraction module: extracts communication data stream features based on positioning and identification;

[0086] Data monitoring module: used to monitor the real-time differences in communication data flow characteristics, identify fault data in communication data, and trace the identified fault data based on cross-layer analysis to predict the propagation path of the fault.

[0087] As a possible implementation method, this embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, an intelligent operation and maintenance network fault monitoring method is implemented.

[0088] As a possible implementation, this embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, an intelligent operation and maintenance network fault monitoring method is implemented.

[0089] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for monitoring network faults in intelligent operation and maintenance, characterized in that: The specific steps include: Obtain the optical cable data of the target detection area, draw the real-time topology through full-link topology restoration, and generate the communication network architecture; Extract communication transmission lines based on network architecture, and locate and identify communication transmission lines based on GIS and optical time domain reflectometer OTDR technology; Based on the positioning and identification, the communication data is segmented into sessions according to the five-tuple, and the communication data flow features are extracted based on the segmented communication data; Monitor the real-time differences in communication data stream characteristics and identify faulty data in communication data; Based on cross-layer analysis, the identified fault data is traced to its source, the sampling rate and message interception length are set, and the source port message of the fault data is parsed to obtain multi-dimensional time series data of the fault data; Perform cross-layer analysis on multi-dimensional time series data, trace the source of identified fault data, and predict the propagation path of the fault; Perform intelligent operation and maintenance network adjustments based on predicted fault data.

2. The intelligent operation and maintenance network fault monitoring method according to claim 1 is characterized in that: Drawing the real-time topology through full-link topology restoration and generating the communication network architecture specifically includes: The optical cable data of the target detection area is used as the basic information for digital conversion of the map; Transform and splice the basic information to establish topological relationships; The deviation in the topological relationship is corrected, the map is vectorized, the topological relationship of the map is corrected and matched, and the communication network architecture is obtained.

3. The intelligent operation and maintenance network fault monitoring method according to claim 2 is characterized in that: The positioning and identification of the communication transmission line based on GIS and optical time domain reflectometer OTDR technology specifically includes: Acquire communication transmission lines, extract the map topology corresponding to the communication transmission lines based on GIS and optical time domain reflectometer (OTDR) technology, and digitize the extracted network data; Extract time domain reflection features of optical pulses based on digitized data; Based on the time domain reflection characteristics, the fiber Bragg grating is used to mark the communication line to obtain a communication transmission line with positioning and identification.

4. The intelligent operation and maintenance network fault monitoring method according to claim 1, characterized in that: The method of performing session segmentation on the traffic data according to the five-tuple based on the positioning and identification, and extracting communication data flow features based on the segmented communication data specifically includes: Collect network traffic and data indicators based on communication data, and clean and desensitize the collected data; The traffic data is segmented into sessions according to the five-tuple, and all packets with the same five-tuple are defined as a communication data flow; Divide the communication data stream according to the different data types of each attribute; The key features of each session are extracted and classified according to the divided communication data streams to obtain the communication data stream features.

5. The intelligent operation and maintenance network fault monitoring method according to claim 1, characterized in that: The real-time difference of the communication data stream characteristics is monitored to identify fault data in the communication data, specifically including: Build a neural network model and input the communication data stream features into the neural network model for learning and training. The learned and trained neural network model is used to analyze the abnormal data characteristics and pattern structure in the network to obtain fault data.

6. The intelligent operation and maintenance network fault monitoring method according to claim 1, characterized in that: The cross-layer analysis of the multi-dimensional time series data and tracing of the identified fault data specifically include: Construct a deep autoencoder network structure and use multiple deep autoencoders for unlabeled high-dimensional data in multi-dimensional time series; Use unlabeled multi-dimensional time series data to integrate multiple deep autoencoders for training, use the hidden layer output of the autoencoder as the feature representation of the data, and obtain abnormal features; Based on the abnormal features, learn the mapping from abnormal features to latent space and reconstruct the latent space features of the data; The reconstruction error of each layer of the deep autoencoder network structure is calculated based on the extracted abnormal features. The structure and parameters of the deep autoencoder are optimized through reverse iteration according to the calculation results to obtain the fault generation model of the communication network.

7. The intelligent operation and maintenance network fault monitoring method according to claim 6, characterized in that: The predicted fault propagation path specifically includes: Based on the fault generation model of the communication network, end-to-end hop-by-hop detection is performed on the faulty node, and fault detection data of the faulty node is collected hop by hop; Locating the faulty node based on the faulty node's faulty detection data and the communication network identifier; Compute the representation of the faulty node and its neighboring nodes, and identify the affected area; Dynamically adjust the network status, update the representation of each node in real time by aggregating neighbor nodes, and predict the fault propagation path.

8. An intelligent operation and maintenance network fault monitoring system, applied to an intelligent operation and maintenance network fault monitoring method according to any one of claims 1 to 7, characterized in that: include: A data acquisition module, used to obtain optical cable data of the target detection area; The topology generation module is used to draw the real-time topology through full-link topology restoration, generate the communication network architecture, and extract the communication transmission lines according to the network architecture; Positioning module, used to locate and identify communication transmission lines based on GIS and optical time domain reflectometer OTDR technology; Feature extraction module: extracts communication data stream features based on positioning and identification; Data monitoring module: used to monitor the real-time differences in communication data flow characteristics, identify fault data in communication data, and trace the identified fault data based on cross-layer analysis to predict the propagation path of the fault.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the intelligent operation and maintenance network fault monitoring method as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the intelligent operation and maintenance network fault monitoring method as described in any one of claims 1 to 7 is implemented.

Images