CN116827426A - Network fault diagnosis method, device and computer readable storage medium - Google Patents
Network fault diagnosis method, device and computer readable storage medium Download PDFInfo
- Publication number
- CN116827426A CN116827426A CN202311016351.7A CN202311016351A CN116827426A CN 116827426 A CN116827426 A CN 116827426A CN 202311016351 A CN202311016351 A CN 202311016351A CN 116827426 A CN116827426 A CN 116827426A
- Authority
- CN
- China
- Prior art keywords
- network
- sample
- information
- fault
- fault diagnosis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 112
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 230000008569 process Effects 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 20
- 230000003287 optical effect Effects 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 claims description 7
- 230000004044 response Effects 0.000 claims description 3
- 238000002405 diagnostic procedure Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 6
- 238000012423 maintenance Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000004807 localization Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 230000002787 reinforcement Effects 0.000 description 2
- 230000011664 signaling Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/07—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems
- H04B10/075—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal
- H04B10/077—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal using a supervisory or additional signal
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/07—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems
- H04B10/075—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal
- H04B10/077—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal using a supervisory or additional signal
- H04B10/0771—Fault location on the transmission path
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
Abstract
The present disclosure provides a method, apparatus, and computer-readable storage medium for diagnosing network failure. The diagnostic method includes obtaining input parameters, inputting the input parameters into a pre-trained fault diagnosis model, and providing a fault diagnosis result to a network management unit for processing a network fault. The input parameters include alert information generated by the alert devices in the network and network information of the alert devices. The network information includes a port identification of the alarm device and network connection information of the alarm device. The fault diagnosis result includes positioning information of the network fault and a waiting time for suggesting to process the network fault. The positioning information of the network fault comprises a port identifier corresponding to the root cause alarm information in the alarm information.
Description
Technical Field
The present disclosure relates to the field of communication networks, and in particular to a method, apparatus and computer readable storage medium for diagnosing network faults.
Background
As optical networks evolve, a dramatic increase in the number of network devices and links will lead to more frequent failures. The diagnosis of network faults is critical to the management and operation of the optical network.
Disclosure of Invention
In the related art, operation and maintenance personnel perform manual diagnosis on network faults, and the duration of the manual diagnosis is long, so that the efficiency of diagnosing the network faults is low. In addition, failure of the network device may cause derivative alarms for numerous network devices, thereby generating massive alarm information. The operation and maintenance personnel are difficult to diagnose the network faults according to the massive alarm information, so that the accuracy of diagnosing the network faults is low.
In order to solve at least some of the above problems, embodiments of the present disclosure propose the following solutions.
According to an aspect of the embodiments of the present disclosure, there is provided a method for diagnosing a network failure, including: acquiring input parameters, wherein the input parameters comprise alarm information generated by alarm equipment in a network and network information of the alarm equipment, and the network information comprises port identification of the alarm equipment and network connection information of the alarm equipment; inputting the input parameters into a pre-trained fault diagnosis model to obtain a fault diagnosis result, wherein the fault diagnosis result comprises positioning information of network faults and waiting time for suggesting to process the network faults, and the positioning information of the network faults comprises port identifiers corresponding to root cause alarm information in the alarm information; the fault diagnosis result is provided to the network management unit for handling the network fault.
In some embodiments, the alert information includes a time at which the alert information was generated.
In some embodiments, the network information further includes performance information of the alert device.
In some embodiments, the fault diagnosis result further comprises a confidence level of the location information of the network fault, wherein providing the fault diagnosis result to the network management unit comprises: judging whether the confidence coefficient of the positioning information of the network fault is smaller than a preset threshold value; and providing the fault diagnosis result to the network management unit in response to determining that the confidence level of the positioning information of the network fault is less than a preset threshold.
In some embodiments, the fault diagnosis results further include a suggested operation to recover from the network fault.
In some embodiments, the method of diagnosing a network failure further comprises: and updating a knowledge base according to the input parameters and the fault diagnosis result, wherein the knowledge base is constructed based on the diagnosis experience of the historical faults.
In some embodiments, the fault diagnosis model is trained according to the following: acquiring sample input parameters, wherein the sample input parameters comprise sample alarm information generated by sample alarm equipment and sample network information of the sample alarm equipment, and the sample network information comprises sample port identification of the sample alarm equipment and sample network connection information of the sample alarm equipment; and training the fault diagnosis model by taking the sample input parameters and sample fault diagnosis results corresponding to the sample input parameters as training data, wherein the sample fault diagnosis results comprise positioning information of sample faults and waiting time for suggesting to process the sample faults.
In some embodiments, the sample alert information includes a time at which the sample alert information was generated, and the sample network information further includes sample performance information of the sample alert device.
In some embodiments, training the fault diagnosis model further comprises: acquiring a knowledge base which is constructed based on diagnosis experience of historical faults; and training the fault diagnosis model by taking the sample input parameters, the sample fault diagnosis results corresponding to the sample input parameters and the knowledge base as training data.
In some embodiments, the alert device is an optical transmission device.
According to another aspect of the embodiments of the present disclosure, there is provided a network failure diagnosis apparatus including a module that performs the method of any one of the embodiments described above.
According to still another aspect of the embodiments of the present disclosure, there is provided a diagnostic apparatus for network failure, including: a memory; and a processor coupled to the memory, the processor configured to perform the method of any of the above embodiments based on instructions stored in the memory.
According to yet another aspect of the disclosed embodiments, a computer readable storage medium is provided, comprising computer program instructions, wherein the computer program instructions, when executed by a processor, implement the method of any of the above embodiments.
According to a further aspect of the disclosed embodiments, there is provided a computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method of any of the above embodiments.
In the embodiment of the disclosure, the input parameters are acquired and input into the pre-trained fault diagnosis model to obtain the fault diagnosis result, so that the network fault can be rapidly and accurately diagnosed, and the accuracy and efficiency of diagnosing the network fault are improved. In addition, the fault diagnosis result comprises the positioning information of the network fault and the waiting time for suggesting to process the network fault, so that the network management unit can process the network fault in time according to the positioning information and the waiting time, and the efficiency of processing the network fault is improved.
The technical scheme of the present disclosure is described in further detail below through the accompanying drawings and examples.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings may be obtained according to these drawings without inventive effort to a person of ordinary skill in the art.
FIG. 1 is a flow diagram of a method of diagnosing network faults according to some embodiments of the present disclosure;
FIG. 2 is a flow diagram of a method of diagnosing network faults according to further embodiments of the present disclosure;
FIG. 3 is a flow diagram of training a fault diagnosis model according to some embodiments of the present disclosure;
FIG. 4 is a schematic structural diagram of a method apparatus for diagnosing network failure according to some embodiments of the present disclosure;
fig. 5 is a schematic structural view of a network failure diagnosis apparatus according to other embodiments of the present disclosure.
Detailed Description
The following description of the technical solutions in the embodiments of the present disclosure will be made clearly and completely with reference to the accompanying drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are only some embodiments of the present disclosure, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments in this disclosure without inventive faculty, are intended to fall within the scope of this disclosure.
The relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless it is specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective parts shown in the drawings are not drawn in actual scale for convenience of description.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.
Fig. 1 is a flow diagram of a method of diagnosing network faults according to some embodiments of the present disclosure.
In step 102, input parameters are obtained, the input parameters including alarm information generated by an alarm device in a network and network information of the alarm device, the network information including a port identification of the alarm device and network connection information of the alarm device.
In some embodiments, the alert device is an optical transmission device. For example, the alerting device is a network element.
In some embodiments, the input parameters are obtained by a network management unit. For example, the network management unit is a network management system (MC). Further, in some examples, the MC obtains the input parameters through a southbound interface. The southbound interface is an interface for managing other gateway devices downward.
As some non-limiting implementations, the alert information includes an identification of the alert information, an alert level, an alert category. For example, the identification of the alert information is the Identity (ID) of the alert information; the alarm level is one of an emergency alarm, an important alarm, a general alarm and a prompt alarm; the alarm class is one of a power system, an environmental system, a signaling system, a relay system, a hardware system, a software system, an operating system, a communication system, and a quality of service.
As some implementations, the port identification of the alert device is a port ID of the alert device. In some embodiments, the port identification of the alarm device further includes one or more of an identification of the alarm device and an identification of a slot of the alarm device to identify the ports from top to bottom in a device-slot-port order. For example, the port identification of the alarm device may include a combination of an alarm device ID, a slot ID, and a port ID.
As some implementations, the network connection information of the alert device is a network topology of the network connection of the alert device. For example, the network connection information may indicate how the alerting device is connected to ports of other devices in the network.
In step 104, the input parameters are input into a pre-trained fault diagnosis model to obtain a fault diagnosis result. The fault diagnosis result comprises positioning information of the network fault and waiting time for suggesting to process the network fault, wherein the positioning information of the network fault comprises a port identifier corresponding to root cause alarm information in the alarm information.
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.
In some embodiments, the positioning information of the network fault includes a port identifier corresponding to the root cause alarm information in the alarm information.
As some implementations, the location information of the network failure also includes one or more of an alarm device ID and a slot ID of the alarm device.
As some implementations, the proposed latency to handle network failures may include zero and non-zero values. Thus, the wait time may be an indication of the type of fault. A zero value indicates that the fault type is a bursty fault and immediate handling of the network fault is required. A non-zero value indicates that the fault type is a slow-forward fault and processing of the network fault may be deferred. As other implementations, it is proposed that the latency for handling network failures range from [0, ++ infinity). For example, it is recommended that the latency time for handling a network failure is 0 days, that is, the network failure is a burst-type failure, and immediate handling of the network failure is required. For another example, it is suggested that the latency time for handling the network failure is 10 days, that is, the network failure is a slow-release type failure, and the network failure can be handled on the 10 th day.
In step 106, the fault diagnosis result is provided to the network management unit for handling the network fault.
In some embodiments, the fault diagnosis model belongs to a network management unit. In other embodiments, the fault diagnosis model does not belong to the network management unit.
In some embodiments, the method of diagnosing network faults further comprises updating a knowledge base based on input parameters and fault diagnosis results, the knowledge base being constructed based on historical fault diagnosis experience.
According to the embodiment, the input parameters are acquired and input into the pre-trained fault diagnosis model to obtain the fault diagnosis result, so that the network fault can be rapidly and accurately diagnosed, and the accuracy and the efficiency of the network fault diagnosis are improved. In addition, the fault diagnosis result comprises the positioning information of the network fault and the waiting time for suggesting to process the network fault, so that the network management unit can process the network fault in time according to the positioning information and the waiting time, and the efficiency of processing the network fault is improved.
In some embodiments, the alert information includes a time at which the alert information was generated.
In the above embodiment, by considering the time when the alarm information is generated in the input parameters of the fault diagnosis model, the fault diagnosis can be more accurately performed and the fault recovery advice can be given. For example, alarm information having a later generation time may be given a smaller weight when performing fault diagnosis than alarm information having a earlier generation time. For another example, the time at which the alert information is generated may have a greater correlation with the latency of suggesting a processing network failure, which may be determined in part based on the time at which the alert information is generated.
In some embodiments, the network information further includes performance information of the alert device. The performance information may include one or more of power, temperature, power loss, and gain of the alerting device.
In the above embodiment, by considering the performance information of the alarm device in the input parameters of the fault diagnosis model, fault diagnosis can be performed more accurately and fault recovery advice can be given. For example, the performance information of the alert device may reflect, in part, the operating state of the network, helping to determine how urgent the network failure is, and thus further determining the latency suggested to handle the network failure.
In some embodiments, the fault diagnosis result further includes a confidence level of the location information of the network fault. Wherein the fault diagnosis result is provided to the network management unit according to steps S1-S2.
In step S1, it is determined whether the confidence level of the positioning information of the network fault is smaller than a preset threshold.
In step S2, in response to determining that the confidence level of the positioning information of the network fault is not less than the preset threshold, the fault diagnosis result is provided to the network management unit. This condition indicates that the localization information of the network failure outputted by the failure diagnosis model is more reliable. Accordingly, the network management unit can process the network failure according to the location information of the network failure indicated in the failure diagnosis result and the waiting time suggested to process the network failure.
As some implementations, when the confidence of the positioning information of the network fault is smaller than a preset threshold, a request for applying for expert opinion will be output.
According to the embodiment, the confidence coefficient of the positioning information of the network fault is output through the fault diagnosis model, so that different processing can be carried out on the fault diagnosis result according to the confidence coefficient of the fault diagnosis result, the fault processing efficiency is further improved, and improper processing caused by false detection can be avoided.
In some embodiments, the fault diagnosis results further include a suggested operation to recover from the network fault. The recommended operation may be, for example, switching routes, restarting a particular network device, reducing an operating temperature of the network device, etc.
According to the embodiment, the suggested operation and maintenance operation for recovering the network faults is output through the fault diagnosis model, so that the network management unit can rapidly process the network faults according to the suggested operation and maintenance operation, and the network fault processing efficiency is further improved.
Algorithms for analyzing and diagnosing network faults in the related art cannot be widely applied due to various factors such as complex network level, transmission technology difference, undefined interface data requirements, nonstandard processing flow, different function requirements and the like. In contrast, the method according to the embodiments of the present disclosure may be applied to various networks, for example, various optical transmission networks including optical transmission devices, and may be capable of locating faults occurring at various levels in the network.
In addition, the network management system in the related art can only diagnose and process the burst type fault and the slow type fault respectively under the condition of human intervention, and high operation and maintenance cost and time are required. The method according to the embodiment of the disclosure provides a unified mechanism capable of automatically detecting and processing the two types of faults at the same time, thereby being beneficial to realizing the intellectualization and unification of a network management system and helping to quickly and accurately remove the faults.
Fig. 2 is a flow diagram of a method of diagnosing network faults according to further embodiments of the present disclosure.
As some implementations, the fault diagnosis model includes an encoder layer, a localization layer of network faults, an optical network health analysis layer, an evidence regression layer, and a decision layer.
In step 202, input parameters are obtained through the southbound interface of the MC.
In step 204, the input parameters are input to the encoder layer of the fault diagnosis model to perform data cleaning and data encoding on the input parameters, and a feature matrix of the input parameters is obtained. The feature matrix includes, for example, a feature matrix of alarm information and a feature matrix of network information. As some implementations, data cleansing includes removing duplicate records in the data, detecting and processing outliers in the data, normalizing the data format to a consistent format, and so forth.
In step 206, the feature matrix of the input parameters is input to the network fault locating layer to obtain the network fault locating information.
In step 208, the network fault location information is input into the optical network health analysis layer to obtain a latency suggested to handle the network fault.
At step 210, the location information of the network failure is input into an evidence regression layer to obtain a confidence level of the location information of the network failure.
In step 212, the location information of the network fault, the latency of suggesting processing the network fault, and the confidence of the location information of the network fault are entered into a decision layer to obtain a suggested operation and maintenance operation to recover the network fault.
Some implementations of training a fault diagnosis model are described below.
FIG. 3 is a flow diagram of training a fault diagnosis model according to some embodiments of the present disclosure.
In step 302, sample input parameters are obtained, the sample input parameters including sample alarm information generated by a sample alarm device and sample network information of the sample alarm device, the sample network information including a sample port identification of the sample alarm device and sample network connection information of the sample alarm device.
In some embodiments, the sample alert device is an optical transmission device, e.g., the sample alert device is a network element. The sample alert device may be the same as or different from the alert device of fig. 1.
As some implementations, the sample alert information includes an identification of the sample alert information, an alert level, an alert category. For example, the identification of the sample alert information is the ID of the sample alert information; the alarm level is one of an emergency alarm, an important alarm, a general alarm and a prompt alarm; the alarm class is one of a power system, an environmental system, a signaling system, a relay system, a hardware system, a software system, an operating system, a communication system, and a quality of service.
As some implementations, the sample port identification of the sample alert device is a port ID of the sample alert device.
In some embodiments, the sample network information of the sample alarm device further comprises one or more of an ID of the sample alarm device and an ID of a slot of the sample alarm device.
As some implementations, the sample network connection information of the sample alert device is a network topology of the sample network connection of the sample alert device.
In step 304, the sample input parameter and the sample fault diagnosis result corresponding to the sample input parameter are used as training data to train the fault diagnosis model, wherein the sample fault diagnosis result comprises the positioning information of the sample fault and the waiting time for suggesting to process the sample fault.
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.
In some embodiments, the location information of the sample network failure includes a port ID corresponding to the root cause alarm information in the sample alarm information.
As some implementations, the location information of the sample network fault further includes one or more of a sample alarm device ID and a sample slot ID.
As a matter of some of the implementations, the latency for handling a sample network failure is recommended to range from a value of 0, ++ infinity A kind of electronic device. For example, it is recommended that the latency of the sample handling of the network fault is 0 days, that is, the sample network fault is a burst-type sample fault, and immediate handling of the sample network fault is required. For another example, it is recommended that the waiting time for handling the sample network fault is 10 days, that is, the sample network fault is a slow-release type fault, and the sample network fault is handled on the 10 th day.
According to the embodiment, the sample input parameters and the sample fault diagnosis results corresponding to the sample input parameters are used as training data to train the fault diagnosis model, so that the accuracy of training the fault diagnosis model is improved. In addition, the training data comprises waiting time for suggesting to process the sample network fault, so that the fault diagnosis model can output the waiting time for suggesting to process the fault when performing fault diagnosis, thereby improving the efficiency of fault processing.
In some embodiments, the sample alert information includes a time at which the sample alert information was generated, and the sample network information further includes sample performance information of the sample alert device.
In some embodiments, the sample performance information of the sample alert device includes one or more of the power, temperature, power loss, and gain of the alert device.
According to the embodiment, the input parameters further comprise the time when the sample alarm information is generated and the sample performance information of the sample alarm equipment, so that the accuracy of training the fault diagnosis model is further improved.
In some embodiments, the method of training a fault diagnosis model further comprises steps S3-S4.
In step S3, a knowledge base is obtained, which is built based on the diagnostic experience of the historical fault.
In step S4, the sample input parameters, the sample fault diagnosis results corresponding to the sample input parameters, and the knowledge base are used as training data to train the fault diagnosis model.
As some implementations, rules in the knowledge base are utilized to guide the learning of the network fault diagnosis model. For example, there are 20 pieces of sample alarm information, and the sample alarm information of 5 th to 20 th pieces is derived sample alarm information of 1 st to 4 th pieces of sample alarm information according to rules of a knowledge base. Therefore, the fault diagnosis model only needs to learn the relation between the 1 st to 4 th sample alarm information and the corresponding sample fault diagnosis result.
According to the embodiment, the sample input parameters, the sample fault diagnosis results corresponding to the sample input parameters and the knowledge base are used as training data, and the knowledge base is used as the depth priori knowledge of the network fault diagnosis model to guide the training of the network fault diagnosis model, so that the training efficiency of the fault diagnosis model is improved.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different manner from other embodiments, so that the same or similar parts between the embodiments are mutually referred to. For the device embodiments, since they basically correspond to the method embodiments, the description is relatively simple, and the relevant points are referred to in the description of the method embodiments.
In some embodiments, a diagnostic apparatus for network failure is provided, comprising: a module for performing the method of any of the embodiments described above. The following is a detailed description with reference to fig. 4.
Fig. 4 is a schematic structural diagram of a network failure diagnosis apparatus according to some embodiments of the present disclosure.
As shown in fig. 4, the network fault diagnosis apparatus includes an acquisition module 401, an input module 402, and a provision module 403.
The acquisition module 401 is configured to acquire input parameters, the input parameters including alarm information generated by an alarm device in a network and network information of the alarm device, the network information including a port identification of the alarm device and network connection information of the alarm device.
The input module 402 is configured to input the input parameters into a pre-trained fault diagnosis model to obtain a fault diagnosis result, where the fault diagnosis result includes positioning information of the network fault and a waiting time for suggesting to process the network fault, and the positioning information of the network fault includes a port identifier corresponding to root cause alarm information in the alarm information.
The providing module 403 is configured to provide the fault diagnosis result to the network management unit for handling the network fault.
Fig. 5 is a schematic structural view of a network failure diagnosis apparatus according to still other embodiments of the present disclosure.
As shown in fig. 5, a network failure diagnosis apparatus 500 includes a memory 501 and a processor 502 coupled to the memory 501, the processor 502 being configured to perform the method of any of the foregoing embodiments based on instructions stored in the memory 501.
Memory 501 may include, for example, system memory, fixed nonvolatile storage media, and the like. The system memory may store, for example, an operating system, application programs, boot Loader (Boot Loader), and other programs.
The network failure diagnosis apparatus 500 may further include an input-output interface 503, a network interface 504, a storage interface 505, and the like. These interfaces 503, 504, 405, and between the memory 501 and the processor 502 may be connected, for example, by a bus 506. The input output interface 503 provides a connection interface for input output devices such as a display, mouse, keyboard, touch screen, etc. Network interface 504 provides a connection interface for various networking devices. The storage interface 505 provides a connection interface for external storage devices such as SD cards, U discs, and the like.
The disclosed embodiments also provide a computer readable storage medium comprising computer program instructions which, when executed by a processor, implement the method of any of the above embodiments.
The disclosed embodiments also provide a computer program product comprising a computer program which, when executed by a processor, implements the method of any of the above embodiments.
Thus, various embodiments of the present disclosure have been described in detail. In order to avoid obscuring the concepts of the present disclosure, some details known in the art are not described. How to implement the solutions disclosed herein will be fully apparent to those skilled in the art from the above description.
It will be appreciated by those skilled in the art that embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may 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.) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that functions specified in one or more of the flowcharts and/or one or more of the blocks in the block diagrams may be implemented by computer program instructions. These computer program instructions may 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, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It will be understood by those skilled in the art that the foregoing embodiments may be modified and equivalents substituted for elements thereof without departing from the scope and spirit of the disclosure. The scope of the present disclosure is defined by the appended claims.
Claims (14)
1. A method of diagnosing a network failure, comprising:
acquiring input parameters, wherein the input parameters comprise alarm information generated by alarm equipment in a network and network information of the alarm equipment, and the network information comprises port identification of the alarm equipment and network connection information of the alarm equipment;
inputting the input parameters into a pre-trained fault diagnosis model to obtain a fault diagnosis result, wherein the fault diagnosis result comprises positioning information of network faults and waiting time for suggesting to process the network faults, and the positioning information of the network faults comprises port identifiers corresponding to root cause alarm information in the alarm information;
and providing the fault diagnosis result to a network management unit for processing the network fault.
2. The method of claim 1, wherein the alert information comprises a time at which alert information was generated.
3. The method of claim 1, wherein the network information further comprises performance information of the alert device.
4. The method of claim 1, wherein the fault diagnosis result further comprises a confidence level of location information of the network fault,
wherein providing the failure diagnosis result to the network management unit includes:
judging whether the confidence coefficient of the positioning information of the network fault is smaller than a preset threshold value; and
and providing the fault diagnosis result to a network management unit in response to judging that the confidence coefficient of the positioning information of the network fault is not smaller than a preset threshold value.
5. The method of claim 4, wherein the fault diagnosis result further comprises a suggested operation to recover the network fault.
6. The method of claim 1, further comprising: and updating a knowledge base according to the input parameters and the fault diagnosis result, wherein the knowledge base is constructed based on the diagnosis experience of the historical fault.
7. The method of claim 1, wherein the fault diagnosis model is trained according to:
acquiring sample input parameters, wherein the sample input parameters comprise sample alarm information generated by sample alarm equipment and sample network information of the sample alarm equipment, and the sample network information comprises a sample port identification of the sample alarm equipment and sample network connection information of the sample alarm equipment;
and training the fault diagnosis model by taking the sample input parameters and sample fault diagnosis results corresponding to the sample input parameters as training data, wherein the sample fault diagnosis results comprise positioning information of the sample faults and waiting time for suggesting to process the sample faults.
8. The method of claim 7, wherein the sample alert information includes a time at which sample alert information was generated, the sample network information further including sample performance information of the sample alert device.
9. The method of claim 7, further comprising:
acquiring a knowledge base which is constructed based on diagnosis experience of historical faults;
and training the fault diagnosis model by taking the sample input parameters, sample fault diagnosis results corresponding to the sample input parameters and the knowledge base as training data.
10. The method of any of claims 1-9, wherein the alerting device is an optical transmission device.
11. A diagnostic device for network failure, comprising: a module for performing the method of any one of claims 1-10.
12. A diagnostic device for network failure, comprising:
a memory; and
a processor coupled to the memory and configured to perform the method of any of claims 1-10 based on instructions stored in the memory.
13. A computer readable storage medium comprising computer program instructions, wherein the computer program instructions, when executed by a processor, implement the method of any of claims 1-10.
14. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method of any of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311016351.7A CN116827426A (en) | 2023-08-14 | 2023-08-14 | Network fault diagnosis method, device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311016351.7A CN116827426A (en) | 2023-08-14 | 2023-08-14 | Network fault diagnosis method, device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116827426A true CN116827426A (en) | 2023-09-29 |
Family
ID=88118631
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311016351.7A Pending CN116827426A (en) | 2023-08-14 | 2023-08-14 | Network fault diagnosis method, device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116827426A (en) |
-
2023
- 2023-08-14 CN CN202311016351.7A patent/CN116827426A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10373065B2 (en) | Generating database cluster health alerts using machine learning | |
| CN113935497A (en) | Intelligent operation and maintenance fault processing method, device and equipment and storage medium thereof | |
| KR20180108446A (en) | System and method for management of ict infra | |
| CN113516244B (en) | Intelligent operation and maintenance method and device, electronic equipment and storage medium | |
| CN113359682B (en) | Equipment fault prediction method, device, equipment fault prediction platform and medium | |
| CN112565187B (en) | Power grid attack detection method, system, equipment and medium based on logistic regression | |
| CN113516174A (en) | Call chain abnormality detection method, computer device, and readable storage medium | |
| CN112801434A (en) | Method, device, equipment and storage medium for monitoring performance index health degree | |
| CN113392893A (en) | Method, device, storage medium and computer program product for positioning service fault | |
| CN110275992B (en) | Emergency processing method, device, server and computer readable storage medium | |
| CN113676343B (en) | Fault source positioning method and device for power communication network | |
| CN108377209A (en) | Equipment fault detecting system based on SCADA and detection method | |
| CN109687999A (en) | A kind of association analysis method of alarm failure, device and equipment | |
| CN110727669B (en) | Electric power system sensor data cleaning device and cleaning method | |
| CN116827426A (en) | Network fault diagnosis method, device and computer readable storage medium | |
| CN109698026B (en) | Component identification in fault handling of medical devices | |
| CN114265324B (en) | Method and device for monitoring running state of equipment and terminal equipment | |
| CA2793952C (en) | Extracting data related to clinical diagnostic instruments | |
| CN111935279B (en) | Internet of things network maintenance method based on block chain and big data and computing node | |
| CN111950448B (en) | High-voltage isolating switch fault state detection method and device based on machine vision | |
| CN110765486B (en) | Asset fault identification method | |
| CN107121616B (en) | Method and device for fault positioning of intelligent instrument | |
| CN114416417A (en) | System abnormity monitoring method, device, equipment and storage medium | |
| CN115544202A (en) | Alarm processing method, device and storage medium | |
| CN112948154A (en) | System abnormity diagnosis method, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |