Network fault diagnosis method and device, and computer readable storage medium
By using a pre-trained fault diagnosis model and knowledge base updates, the problems of low efficiency and poor accuracy in network fault diagnosis are solved, enabling fast and accurate network fault location and handling.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA TELECOM CORP LTD TECHNOLOGY INNOVATION CENTER
- Filing Date
- 2023-08-14
- Publication Date
- 2026-05-29
Smart Images
Figure CN116827426B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of communication networks, and in particular to methods, apparatus and computer-readable storage media for diagnosing network faults. Background Technology
[0002] With the development of optical networks, the rapid increase in the number of network devices and links will lead to more frequent failures. Network fault diagnosis is crucial for the management and maintenance of optical networks. Summary of the Invention
[0003] In related technologies, network maintenance personnel manually diagnose network faults, which is time-consuming and therefore inefficient. Furthermore, network device failures generate numerous related alarms, resulting in a massive amount of alarm information. Maintenance personnel struggle to diagnose network faults based on this vast amount of alarm data, leading to low accuracy in fault diagnosis.
[0004] To address at least some of the above-mentioned problems, the present disclosure provides the following solutions.
[0005] According to one aspect of the present disclosure, a method for diagnosing network faults is provided, comprising: acquiring input parameters, the input parameters including alarm information generated by an alarm device in the network and network information of the alarm device, the network information including port identifier and network connection information of the alarm device; inputting the input parameters into a pre-trained fault diagnosis model to obtain a fault diagnosis result, the fault diagnosis result including network fault location information and a suggested waiting time for handling the network fault, the network fault location information including the port identifier corresponding to the root cause alarm information in the alarm information; and providing the fault diagnosis result to a network management unit for handling the network fault.
[0006] In some embodiments, the alarm information includes the time when the alarm information was generated.
[0007] In some embodiments, the network information also includes performance information of the alarm device.
[0008] In some embodiments, the fault diagnosis result further includes the confidence level of the network fault location information, wherein providing the fault diagnosis result to the network management unit includes: determining whether the confidence level of the network fault location information is less than a preset threshold; and providing the fault diagnosis result to the network management unit in response to determining that the confidence level of the network fault location information is less than the preset threshold.
[0009] In some embodiments, the fault diagnosis results may also include recommended maintenance operations for recovering from network faults.
[0010] In some embodiments, the network fault diagnosis method further includes updating a knowledge base based on input parameters and fault diagnosis results, wherein the knowledge base is constructed based on historical fault diagnosis experience.
[0011] In some embodiments, the fault diagnosis model is trained as follows: sample input parameters are obtained, including sample alarm information generated by the sample alarm device and sample network information of the sample alarm device, the sample network information including the sample port identifier and sample network connection information of the sample alarm device; the fault diagnosis model is trained using the sample input parameters and the corresponding sample fault diagnosis results as training data, the sample fault diagnosis results including the location information of the sample fault and the suggested waiting time for handling the sample fault.
[0012] In some embodiments, the sample alarm information includes the time when the sample alarm information is generated, and the sample network information also includes the sample performance information of the sample alarm device.
[0013] In some embodiments, training the fault diagnosis model further includes: acquiring a knowledge base, which is constructed based on diagnostic experience of historical faults; and training the fault diagnosis model using sample input parameters, sample fault diagnosis results corresponding to the sample input parameters, and the knowledge base as training data.
[0014] In some embodiments, the alarm device is an optical transmission device.
[0015] According to another aspect of the present disclosure, a network fault diagnosis apparatus is provided, including a module that performs the method of any of the above embodiments.
[0016] According to another aspect of the present disclosure, a network fault diagnosis apparatus is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute the method of any of the above embodiments based on instructions stored in the memory.
[0017] According to another aspect of the present disclosure, a computer-readable storage medium is provided, including computer program instructions, wherein the computer program instructions, when executed by a processor, implement the method of any of the above embodiments.
[0018] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, it implements the method of any of the above embodiments.
[0019] In this embodiment, by acquiring input parameters and inputting them into a pre-trained fault diagnosis model, fault diagnosis results are obtained, enabling rapid and accurate diagnosis of network faults and improving the accuracy and efficiency of network fault diagnosis. Furthermore, the fault diagnosis results include the location information of the network fault and a suggested waiting time for handling the fault, allowing the network management unit to promptly address the network fault based on the location information and waiting time, thus improving the efficiency of network fault handling.
[0020] The technical solutions of this disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description
[0021] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0022] Figure 1 This is a schematic flowchart of a network fault diagnosis method according to some embodiments of the present disclosure;
[0023] Figure 2 This is a flowchart illustrating a method for diagnosing network faults according to some embodiments of the present disclosure;
[0024] Figure 3 This is a schematic flowchart of training a fault diagnosis model according to some embodiments of the present disclosure;
[0025] Figure 4 This is a schematic diagram of the structure of a network fault diagnosis method and apparatus according to some embodiments of the present disclosure;
[0026] Figure 5 This is a schematic diagram of the structure of a network fault diagnosis device according to other embodiments of the present disclosure. Detailed Implementation
[0027] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.
[0028] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values of the components and steps set forth in these embodiments do not limit the scope of this disclosure.
[0029] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.
[0030] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.
[0031] In all examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.
[0032] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.
[0033] Figure 1 This is a schematic flowchart of a network fault diagnosis method according to some embodiments of the present disclosure.
[0034] In step 102, input parameters are obtained. These input parameters include alarm information generated by alarm devices in the network and network information of the alarm devices. The network information includes the port identifier of the alarm devices and the network connection information of the alarm devices.
[0035] In some embodiments, the alarm device is an optical transmission device. For example, the alarm device is a network element.
[0036] In some embodiments, input parameters are obtained through a network management unit (MC). For example, the MC is a network management system (MC). Further, in some examples, the MC obtains input parameters through a southbound interface. The southbound interface is an interface used to manage other gateway devices.
[0037] As some non-restrictive implementations, alarm information includes alarm information identifier, alarm level, and alarm category. For example, the alarm information identifier is the alarm information identity (ID); the alarm level is one of emergency alarm, important alarm, general alarm, and alert alarm; the alarm category is one of power system, environmental system, signaling system, relay system, hardware system, software system, operating system, communication system, and service quality.
[0038] In some implementations, the port identifier of an alarm device is the port ID of the alarm device. In some embodiments, the port identifier of an alarm device also includes one or more of the identifier of the alarm device and the identifier of the slot of the alarm device, to identify the port hierarchically from top to bottom in the order of device-slot-port. For example, the port identifier of an alarm device may include a combination of alarm device ID, slot ID, and port ID.
[0039] In some implementations, the network connectivity information of an alarm device is the network topology of the alarm device's network connections. For example, network connectivity information can indicate how the alarm device connects to the ports of other devices in the network.
[0040] In step 104, the input parameters are input into the pre-trained fault diagnosis model to obtain the fault diagnosis results. The fault diagnosis results include the location information of the network fault and the suggested waiting time for handling the network fault. The location information of the network fault includes the port identifier corresponding to the root cause alarm information in the alarm information.
[0041] In some embodiments, the fault diagnosis model is a neural network model. In other embodiments, the fault diagnosis model is a reinforcement learning network model.
[0042] In some embodiments, the location information of the network fault includes the port identifier corresponding to the root cause alarm information in the alarm information.
[0043] As part of some implementations, network fault location information may also include one or more of the alarm device ID and the slot ID of the alarm device.
[0044] As some implementations, it is suggested that the waiting time for handling network faults can include zero or non-zero values. This waiting time can thus serve as an indicator of the fault type. A zero value indicates a sudden fault, requiring immediate handling. A non-zero value indicates a gradually changing fault, allowing for delayed handling. In other implementations, it is suggested that the waiting time for handling network faults range from [0, +∞). For example, a suggested waiting time of 0 days indicates a sudden fault requiring immediate handling. Another example is a suggested waiting time of 10 days, indicating a gradually changing fault that can be handled on the 10th day.
[0045] In step 106, the fault diagnosis results are provided to the network management unit for handling the network fault.
[0046] In some embodiments, the fault diagnosis model is part of the network management unit. In other embodiments, the fault diagnosis model is not part of the network management unit.
[0047] In some embodiments, the network fault diagnosis method further includes updating a knowledge base based on input parameters and fault diagnosis results, the knowledge base being constructed based on historical fault diagnosis experience.
[0048] The above embodiments, by acquiring input parameters and inputting them into a pre-trained fault diagnosis model to obtain fault diagnosis results, enable rapid and accurate diagnosis of network faults, improving the accuracy and efficiency of network fault diagnosis. Furthermore, the fault diagnosis results include the location information of the network fault and a suggested waiting time for handling the fault, allowing the network management unit to promptly address the network fault based on the location information and waiting time, thus improving the efficiency of network fault handling.
[0049] In some embodiments, the alarm information includes the time when the alarm information was generated.
[0050] The above embodiments, by considering the generation time of alarm information in the input parameters of the fault diagnosis model, can more accurately diagnose faults and provide fault recovery suggestions. For example, alarm information generated earlier can be given less weight during fault diagnosis compared to alarm information generated later. Furthermore, the generation time of alarm information may be highly correlated with the suggested waiting time for handling network faults; therefore, the suggested waiting time for handling network faults can be determined partly based on the generation time of the alarm information.
[0051] In some embodiments, the network information also includes performance information of the alarm device. The performance information may include one or more of the alarm device's power, temperature, power loss, and gain.
[0052] The above embodiments, by incorporating the performance information of alarm devices into the input parameters of the fault diagnosis model, can more accurately diagnose faults and provide fault recovery suggestions. For example, the performance information of alarm devices can partially reflect the network's operating status, helping to determine the urgency of network faults and thus further determining the recommended waiting time for handling network faults.
[0053] In some embodiments, the fault diagnosis result further includes the confidence level of the network fault location information. The fault diagnosis result is provided to the network management unit according to steps S1-S2.
[0054] In step S1, it is determined whether the confidence level of the network fault location information is less than a preset threshold.
[0055] In step S2, in response to the fact that the confidence level of the network fault location information is not less than a preset threshold, the fault diagnosis result is provided to the network management unit. This indicates that the network fault location information output by the fault diagnosis model is relatively reliable. Accordingly, the network management unit can handle the network fault based on the network fault location information indicated in the fault diagnosis result and the suggested waiting time for handling the network fault.
[0056] As one implementation method, when the confidence level of the network fault location information is less than a preset threshold, a request for expert opinion will be output.
[0057] The above embodiments output the confidence level of the network fault location information through the fault diagnosis model, which enables different processing of the fault diagnosis results based on the confidence level of the fault diagnosis results, further improving the efficiency of fault handling and avoiding improper processing due to false detection.
[0058] In some embodiments, the fault diagnosis results also include recommended maintenance operations for resolving network faults. Recommended maintenance operations may include, for example, switching routes, restarting specific network devices, or reducing the operating temperature of network devices.
[0059] The above embodiments output suggested maintenance operations for network fault recovery through the fault diagnosis model, enabling the network management unit to quickly handle network faults based on the suggested maintenance operations, thereby further improving the efficiency of network fault handling.
[0060] Algorithms for analyzing and diagnosing network faults in related technologies cannot be widely applied due to various factors such as complex network layers, differences in transmission technologies, unclear interface data requirements, non-standard processing procedures, and inconsistent functional requirements. In contrast, the method according to embodiments of this disclosure can be applied to various networks, such as various optical transmission networks including optical transmission equipment, and can locate faults occurring at each layer of the network.
[0061] Furthermore, in related technologies, network management systems can only diagnose and handle sudden and gradually changing faults separately with human intervention, requiring high operation and maintenance costs and time. The method according to embodiments of this disclosure provides a unified mechanism that can automatically detect and handle both types of faults simultaneously, contributing to the intelligence and unification of the network management system and facilitating rapid and accurate fault troubleshooting.
[0062] Figure 2 This is a flowchart illustrating a method for diagnosing network faults according to some embodiments of the present disclosure.
[0063] As some implementation methods, the fault diagnosis model includes an encoder layer, a network fault location layer, an optical network health analysis layer, an evidence regression layer, and a decision layer.
[0064] In step 202, the input parameters are obtained through the southbound interface of the MC.
[0065] In step 204, the input parameters are input into the encoder layer of the fault diagnosis model to perform data cleaning and encoding, resulting in a feature matrix of the input parameters. The feature matrix may include, for example, feature matrices for alarm information and feature matrices for network information. Data cleaning may include removing duplicate records, detecting and processing outliers, and standardizing the data format to a consistent format.
[0066] In step 206, the feature matrix of the input parameters is input into the network fault location layer to obtain the network fault location information.
[0067] In step 208, the location information of the network fault is input into the optical network health analysis layer to obtain the suggested waiting time for handling the network fault.
[0068] In step 210, the location information of the network fault is input into the evidence regression layer to obtain the confidence level of the location information of the network fault.
[0069] In step 212, the location information of the network fault, the suggested waiting time for handling the network fault, and the confidence level of the location information of the network fault are input into the decision layer to obtain the suggested operation and maintenance operation for restoring the network fault.
[0070] The following section introduces some implementation methods for training fault diagnosis models.
[0071] Figure 3 This is a schematic flowchart illustrating the training of a fault diagnosis model according to some embodiments of the present disclosure.
[0072] In step 302, sample input parameters are obtained. These sample input parameters include sample alarm information generated by the sample alarm device and sample network information of the sample alarm device. The sample network information includes the sample port identifier and sample network connection information of the sample alarm device.
[0073] In some embodiments, the sample alarm device is an optical transmission device, for example, a network element. The sample alarm device can be connected to... Figure 1 The alarm devices in the system can be the same or different.
[0074] As some implementation methods, sample alarm information includes the sample alarm information identifier, alarm level, and alarm category. For example, the identifier of sample alarm information is the sample alarm information ID; the alarm level is one of emergency alarm, important alarm, general alarm, and alert alarm; and the alarm category is one of power system, environmental system, signaling system, relay system, hardware system, software system, operating system, communication system, and service quality.
[0075] In some implementations, the sample port identifier of a sample alarm device is the port ID of the sample alarm device.
[0076] In some embodiments, the sample network information of the sample alarm device also includes one or more of the sample alarm device ID and the ID of the sample alarm device slot.
[0077] As one implementation, the sample network connection information of the sample alarm device is the network topology of the sample network connection of the sample alarm device.
[0078] In step 304, the fault diagnosis model is trained using the sample input parameters and the corresponding sample fault diagnosis results as training data. The sample fault diagnosis results include the location information of the sample fault and the suggested waiting time for handling the sample fault.
[0079] In some embodiments, the fault diagnosis model is a neural network model. In other embodiments, the fault diagnosis model is a reinforcement learning network model.
[0080] In some embodiments, the location information of the sample network fault includes the port ID corresponding to the sample root cause alarm information in the sample alarm information.
[0081] As part of some implementations, the location information for sample network faults also includes one or more of the sample alarm device ID and sample slot ID.
[0082] As some implementation methods, it is suggested that the waiting time for handling sample network faults ranges from [0, +∞). For example, it is suggested that the waiting time for handling sample network faults be 0 days, meaning that the sample network fault is a sudden type and needs to be handled immediately. Another example is that it is suggested that the waiting time for handling sample network faults be 10 days, meaning that the sample network fault is a slowly changing type and should be handled on the 10th day.
[0083] The above embodiments improve the accuracy of fault diagnosis model training by using sample input parameters and corresponding sample fault diagnosis results as training data to train the fault diagnosis model. Furthermore, the training data includes the suggested waiting time for handling the sample network fault, enabling the fault diagnosis model to output the suggested waiting time for fault handling during fault diagnosis, thereby improving the efficiency of fault handling.
[0084] In some embodiments, the sample alarm information includes the time when the sample alarm information is generated, and the sample network information also includes the sample performance information of the sample alarm device.
[0085] In some embodiments, the sample performance information of the sample alarm device includes one or more of the following: power, temperature, power loss, and gain of the alarm device.
[0086] The above embodiments further improve the accuracy of fault diagnosis model training by including the time when the sample alarm information is generated and the sample performance information of the sample alarm device as input parameters.
[0087] In some embodiments, the method for training a fault diagnosis model further includes steps S3-S4.
[0088] In step S3, a knowledge base is obtained, which is constructed based on diagnostic experience of historical faults.
[0089] In step S4, the fault diagnosis model is trained using the sample input parameters, the sample fault diagnosis results corresponding to the sample input parameters, and the knowledge base as training data.
[0090] One implementation approach utilizes rules from a knowledge base to guide the learning of the network fault diagnosis model. For example, given 20 sample alarm messages, the rules in the knowledge base determine that alarm messages 5-20 are derived from alarm messages 1-4. Therefore, the fault diagnosis model only needs to learn the relationship between alarm messages 1-4 and their corresponding fault diagnosis results.
[0091] The above embodiments improve the efficiency of fault diagnosis model training by using sample input parameters, sample fault diagnosis results corresponding to the sample input parameters, and a knowledge base as training data, and by using the knowledge base as deep prior knowledge to guide the training of the network fault diagnosis model.
[0092] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus embodiments, since they largely correspond to the method embodiments, the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.
[0093] In some embodiments, a network fault diagnosis apparatus is provided, comprising: a module for performing the method of any of the above embodiments. The following is in conjunction with... Figure 4 Please provide a detailed explanation.
[0094] Figure 4 This is a schematic diagram of the structure of a network fault diagnosis device according to some embodiments of the present disclosure.
[0095] like Figure 4 As shown, the network fault diagnosis device includes an acquisition module 401, an input module 402, and a provision module 403.
[0096] The acquisition module 401 is configured to acquire input parameters, including alarm information generated by alarm devices in the network and network information of the alarm devices. The network information includes the port identifier of the alarm devices and the network connection information of the alarm devices.
[0097] The input module 402 is configured to input input parameters into a pre-trained fault diagnosis model to obtain fault diagnosis results. The fault diagnosis results include network fault location information and suggested waiting time for handling network faults. The network fault location information includes the port identifier corresponding to the root cause alarm information in the alarm information.
[0098] The providing module 403 is configured to provide fault diagnosis results to the network management unit for handling network faults.
[0099] Figure 5 This is a schematic diagram of the structure of a network fault diagnosis device according to some embodiments of the present disclosure.
[0100] like Figure 5 As shown, the network fault diagnosis device 500 includes a memory 501 and a processor 502 coupled to the memory 501. The processor 502 is configured to execute the method of any of the foregoing embodiments based on instructions stored in the memory 501.
[0101] The memory 501 may include, for example, system memory, fixed non-volatile storage media, etc. The system memory may store, for example, an operating system, application programs, a boot loader, and other programs.
[0102] The network fault diagnosis device 500 may also include an input / output interface 503, a network interface 504, and a storage interface 505. These interfaces 503, 504, and 505, as well as the memory 501 and processor 502, can be connected via, for example, a bus 506. The input / output interface 503 provides a connection interface for input / output devices such as monitors, mice, keyboards, and touchscreens. The network interface 504 provides a connection interface for various networked devices. The storage interface 505 provides a connection interface for external storage devices such as SD cards and USB flash drives.
[0103] This disclosure also provides a computer-readable storage medium including computer program instructions that, when executed by a processor, implement the method of any of the above embodiments.
[0104] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the method of any of the above embodiments.
[0105] The embodiments of this disclosure have now been described in detail. To avoid obscuring the concept of this disclosure, some details known in the art have not been described. Those skilled in the art can fully understand how to implement the technical solutions disclosed herein based on the above description.
[0106] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0107] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that the functions specified in one or more flowchart illustrations and / or one or more blocks in a block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate functions for implementing the functions in the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0108] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0109] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0110] While specific embodiments of this disclosure have been described in detail by way of examples, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments or equivalent substitutions can be made to some technical features without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.
Claims
1. A method for diagnosing network faults, comprising: The input parameters include alarm information generated by an alarm device in the optical network and network information of the alarm device. The alarm information includes root cause alarm information. The network information of the alarm device includes the port identifier of the alarm device, the performance information of the alarm device, and the network connection information of the alarm device. The port identifier of the alarm device includes a combination of alarm device ID, slot ID, and port ID. The alarm device is an optical transmission device. The performance information includes at least one of the power, temperature, power loss, and gain of the optical transmission device. The alarm information includes the time when the alarm information was generated. The input parameters are input into a pre-trained fault diagnosis model to determine the fault diagnosis result. The fault diagnosis result includes the location information of the network fault and the suggested waiting time for handling the network fault. When determining the fault diagnosis result, alarm information generated earlier is given less weight than alarm information generated later. The suggested waiting time for handling the network fault is determined based on the generation time of the alarm information and the performance information. The waiting time is used to indicate the fault type. The fault type is used to determine whether to postpone handling the network fault. When the waiting time is zero, it indicates that the fault type is a burst fault. When the waiting time is non-zero, it indicates that the fault type is a slowly changing fault. The location information of the network fault includes the port identifier of the alarm device corresponding to the root cause alarm information in the alarm information. The fault diagnosis results are provided to the network management unit for handling the network faults. The step of providing the fault diagnosis results to the network management unit for handling the network fault includes: In the event that the fault type is a sudden fault, the network fault should be handled immediately. In the case of a slowly changing fault, the network fault is delayed according to the waiting time.
2. The method according to claim 1, wherein, The fault diagnosis results also include the confidence level of the network fault location information. Providing the fault diagnosis results to the network management unit includes: Determine whether the confidence level of the network fault location information is less than a preset threshold; and In response to the determination that the confidence level of the location information of the network fault is not less than a preset threshold, the fault diagnosis result is provided to the network management unit.
3. The method according to claim 2, wherein, The fault diagnosis results also include recommended maintenance operations for restoring the network fault.
4. The method according to claim 1, further comprising: The knowledge base is updated based on the input parameters and the fault diagnosis results. The knowledge base is constructed based on the diagnostic experience of historical faults.
5. The method according to claim 1, wherein, The fault diagnosis model is trained in the following manner: Obtain sample input parameters, which include sample alarm information generated by the sample alarm device and sample network information of the sample alarm device. The sample network information includes the sample port identifier of the sample alarm device and the sample network connection information of the sample alarm device. The sample alarm information includes the time when the sample alarm information was generated. The sample network information also includes the sample performance information of the sample alarm device. The fault diagnosis model is trained using the sample input parameters and the corresponding sample fault diagnosis results as training data. The sample fault diagnosis results include the location information of the sample fault and the suggested waiting time for handling the sample fault.
6. The method according to claim 5, further comprising: Acquire a knowledge base, which is built based on diagnostic experience of historical faults; The fault diagnosis model is trained using the sample input parameters, the sample fault diagnosis results corresponding to the sample input parameters, and the knowledge base as training data.
7. A network fault diagnosis device, comprising: A module that performs the method according to any one of claims 1-6.
8. A network fault diagnosis device, comprising: Memory; as well as A processor coupled to the memory is configured to execute the method of any one of claims 1-6 based on instructions stored in the memory.
9. A computer-readable storage medium comprising computer program instructions, wherein, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1-6.
10. A computer program product comprising a computer program, wherein, When the computer program is executed by a processor, it implements the method described in any one of claims 1-6.