Fault processing method and apparatus

Abstract

The present disclosure relates to the technical field of artificial intelligence, and particularly relates to a fault processing method and device. The method comprises the following steps: receiving a fault processing capability scheduling request sent by a fault server; performing information verification on fault handling capability and an alarm network element device according to scheduling request parameters carried in the fault processing capability scheduling request, and obtaining a verification result; in the case that the verification result indicates that the verification is successful and the fault level of a main fault node is higher than a preset level, starting a processing flow corresponding to the main fault node, wherein the processing flow is used for performing fault processing on the main fault node and a related node set of the main fault node; and in the case that the verification result indicates that the verification fails, assigning a fault work order to a target device, wherein the fault work order is used to instruct the target device to perform fault processing according to received artificial instructions. The present disclosure can improve the accuracy and efficiency of fault processing.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to a fault handling method and apparatus. Background Technology

[0002] With the development of network intelligence, network operations and maintenance (O&M) can increasingly leverage technologies such as artificial intelligence and big data to automate and intelligentize O&M work. Network O&M refers to a series of activities involving the maintenance, management, optimization, and troubleshooting of network systems, network devices, and network applications to ensure stable, efficient, and secure network operation. For example, expert experience databases can be used to handle faults. However, with the increasing number and types of network devices, relying solely on expert experience for fault handling results in lower accuracy and timeliness. Summary of the Invention

[0003] This disclosure provides a fault handling method and apparatus, which can improve the accuracy and efficiency of fault handling. The technical solution of this disclosure is as follows:

[0004] According to a first aspect of the present disclosure, a fault handling method is provided, comprising:

[0005] Receive fault handling capability scheduling requests sent by faulty servers;

[0006] Based on the scheduling request parameters carried in the fault handling capability scheduling request, the fault handling capability and alarm network element information are verified, and the verification results are obtained.

[0007] If the verification result indicates that the verification was successful and the fault level of the main fault node is higher than the preset level, the processing flow corresponding to the main fault node is started. The processing flow is used to perform fault processing on the main fault node and the set of related nodes of the main fault node.

[0008] If the verification result indicates that the verification failed, a fault work order is dispatched to the target device, wherein the fault work order is used to instruct the target device to handle the fault according to the received manual instructions.

[0009] According to some embodiments, when the verification result indicates successful verification and the fault level of the primary fault node is higher than a preset level, the process corresponding to the primary fault node is initiated, including:

[0010] If the verification result indicates that the verification was successful, obtain the fault alarm information corresponding to the main fault node;

[0011] Based on the fault alarm information, the fault level corresponding to the main fault node is obtained;

[0012] A fault handling strategy corresponding to the fault level is executed on the primary fault node and the set of related nodes of the primary fault node.

[0013] According to some embodiments, the execution of a fault handling strategy corresponding to the fault level on the primary fault node and the set of related nodes of the primary fault node includes:

[0014] If the fault level is higher than a preset level, obtain a set of related nodes corresponding to the main fault node, wherein the set of related nodes includes at least one node whose association with the main fault node is greater than a relationship threshold.

[0015] Based on the relevant node set, issue alarm information or provide fault handling solutions to the target device corresponding to the relevant node set;

[0016] The fault handling strategy corresponding to the fault level is executed on the main fault node.

[0017] According to some embodiments, obtaining the set of related nodes corresponding to the primary fault node includes:

[0018] Based on the fault alarm information, the diffusion range and fault propagation path corresponding to the main fault node are obtained;

[0019] Based on the fault propagation path and the diffusion range, obtain the node set corresponding to the main fault node, wherein the node set includes at least one node covered by the diffusion range;

[0020] Interconnection functions are used to verify the relationships between nodes in the node set, and the relationships between each node and the main fault node are obtained.

[0021] Based on the aforementioned association, obtain the set of related nodes in the node set.

[0022] According to some embodiments, obtaining the diffusion range and fault propagation path corresponding to the main fault node based on the fault alarm information includes:

[0023] A clustering algorithm is used to cluster the historical fault data set to obtain the fault category set corresponding to the historical fault data set;

[0024] Classify each fault category in the fault category set and obtain the classification results;

[0025] Based on network asset information, obtain current network status information;

[0026] The current network state information and the historical fault data set are predicted by a fault propagation prediction model to obtain the propagation path corresponding to the main fault node.

[0027] Based on the current network status information, obtain the target node and associated links in the network topology where the primary fault node is located;

[0028] The classification results, the target node, and the associated links are simulated using fault propagation rules to obtain the propagation range and fault propagation path corresponding to the main fault node.

[0029] According to some embodiments, obtaining the set of related nodes in the node set based on the association relationship includes:

[0030] The network topology corresponding to each node in the node set is obtained by using the K-truss algorithm with a K-shaped truss.

[0031] Based on the network topology, obtain the medium centrality and proximity centrality of each node;

[0032] Based on the medium centrality and the proximity centrality, obtain the k-truss value between each node and the primary fault node;

[0033] Add nodes whose k-truss values ​​are greater than a preset value to the relevant node set;

[0034] or

[0035] A preset number of nodes are added to the relevant node set in descending order of the k-truss values.

[0036] According to some embodiments, providing a fault handling solution to the target device corresponding to the relevant node set based on the relevant node set includes:

[0037] Based on the set of relevant nodes, fault handling experience, and the fault propagation path, determine the fault handling scheme corresponding to each relevant node in the set of relevant nodes;

[0038] The fault handling solution is provided to the target device corresponding to each of the relevant nodes in the relevant node set.

[0039] According to a second aspect of the embodiments of this disclosure, a

[0040] The request receiving unit is used to receive fault handling capability scheduling requests sent by the faulty server.

[0041] The result acquisition unit is used to verify the information of fault handling capability and alarm network element devices based on the scheduling request parameters carried by the fault handling capability scheduling request, and to obtain the verification result.

[0042] The fault handling unit is used to initiate the processing flow corresponding to the main fault node when the verification result indicates that the verification is successful and the fault level of the main fault node is higher than the preset level. The processing flow is used to perform fault handling on the main fault node and the set of related nodes of the main fault node.

[0043] A fault handling unit is configured to dispatch a fault work order to a target device when the verification result indicates that the verification has failed, wherein the fault work order is used to instruct the target device to perform fault handling according to the received manual instructions.

[0044] According to a third aspect of the present disclosure, a network device is provided, comprising:

[0045] processor;

[0046] Memory used to store the processor's executable instructions;

[0047] The processor is configured to execute the instructions to implement the fault handling method described in any one of the preceding aspects.

[0048] According to a fourth aspect of the present disclosure, a storage medium is provided that, when instructions in the storage medium are executed by a processor of a network device, enables the network device to perform the fault handling method described in any of the preceding aspects.

[0049] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method described in any one of the preceding aspects.

[0050] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects:

[0051] In some or related embodiments, a fault handling capability scheduling request is received from a fault server; based on the scheduling request parameters carried in the fault handling capability scheduling request, information verification of fault handling capabilities and alarm network element devices is performed, and verification results are obtained; if the verification result indicates successful verification and the fault level of the main fault node is higher than a preset level, the processing flow corresponding to the main fault node is initiated, wherein the processing flow is used to handle the fault of the main fault node and the set of related nodes of the main fault node; if the verification result indicates failed verification, a fault work order is dispatched to the target device, wherein the fault work order is used to instruct the target device to handle the fault according to the received manual instructions. Therefore, faults can be handled through scheduling request parameters, and different fault handling measures can be adopted for different verification results. This can reduce the limitation of the expert experience base on the analysis capability of fault propagation, identify nodes related to the main fault node, restrict the propagation path of the main fault node's fault, reduce the impact of faults on the system, and can be applied to scenarios where the number and types of network devices are constantly increasing. This technical solution is applicable to multiple scenarios, can improve the accuracy and efficiency of fault handling, and can improve the node update capability of the network operation and maintenance fault handling process.

[0052] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0053] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0054] Figure 1 This is a flowchart illustrating a fault handling method according to an exemplary embodiment;

[0055] Figure 2 This is a flowchart illustrating a fault handling method according to an exemplary embodiment;

[0056] Figure 3 This is an example schematic diagram of a fault handling system according to an exemplary embodiment;

[0057] Figure 4 This is a block diagram illustrating a fault handling apparatus according to an exemplary embodiment;

[0058] Figure 5 This is a block diagram illustrating a network device according to an exemplary embodiment. Detailed Implementation

[0059] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0060] This disclosure provides fault handling methods and apparatus. In some embodiments, the terms fault handling method, information processing method, and communication method can be used interchangeably; the terms fault handling apparatus, information processing apparatus, and communication apparatus can be used interchangeably; and the terms information processing system and communication system can be used interchangeably.

[0061] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0062] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0063] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0064] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0065] In the embodiments of this disclosure, "multiple" refers to two or more.

[0066] In some embodiments, the terms “at least one of”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0067] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0068] In some embodiments, "terminal" or "terminal device" may be referred to as "user equipment (UE)," "user terminal," "mobile station (MS)," "mobile terminal (MT)," "subscriber station," "mobile unit," "subscriber unit," "wireless unit," "remote unit," "mobile device," "wireless device," "wireless communication device," "remote device," "mobile subscriber station," "access terminal," "mobile terminal," "wireless terminal," "remote terminal," "handset," "user agent," "mobile client," "client," etc.

[0069] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0070] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0071] Figure 1 This is a flowchart illustrating a fault handling method according to an exemplary embodiment, such as... Figure 1 As shown, this fault handling method can be used in scenarios where fault information is scheduled for processing when a fault occurs, and includes the following steps:

[0072] In step S11, a fault handling capability scheduling request is received from the faulty server;

[0073] According to some embodiments, the execution subject of this disclosure is a network device. The name of the network device is not limited. For example, the network device may also be called a server, a server cluster, or an operation server in a fault handling system.

[0074] According to some embodiments, the faulty server may be, for example, a server capable of acquiring fault information. The name of the faulty server is not limited. The faulty server may also be referred to as a fault center. The faulty server does not specifically refer to a particular fixed server. For example, when the server identifier of the faulty server changes, the faulty server may also change accordingly. For example, when the server experiencing the fault changes, the faulty server may also change accordingly.

[0075] In some embodiments, a fault handling capability scheduling request may be, for example, a request to process fault information sent by a faulty server. This fault handling capability scheduling request may be, for example, a request sent by the faulty server to the operation server. The fault handling capability scheduling request is not specifically a fixed request. For example, when the time point corresponding to the request changes, the fault handling capability scheduling request may also change accordingly. For example, when the parameters included in the fault handling capability scheduling request change, the fault handling capability scheduling request may also change accordingly.

[0076] According to some embodiments, during fault handling, a fault handling capability scheduling request sent by the faulty server can be received.

[0077] In step S12, the fault handling capability and alarm network element information are verified according to the scheduling request parameters carried in the fault handling capability scheduling request, and the verification result is obtained.

[0078] According to some embodiments, the scheduling request parameters may be parameters carried in the fault handling capability scheduling request, used to schedule fault information by the operating server. These scheduling request parameters may also be referred to as a scheduling request parameter set or a scheduling request parameter collection. This disclosure does not limit this. The scheduling request parameter does not specifically refer to a single fixed parameter. For example, when the number of parameters corresponding to the scheduling request parameter changes, the scheduling request parameter may also change accordingly. For example, when a parameter included in the scheduling request parameter changes, the scheduling request parameter may also change accordingly.

[0079] In some embodiments, fault handling capability is used, for example, to indicate the ability of each faulty target device to handle a fault. This fault handling capability does not specifically refer to a particular fixed capability. The name of this fault handling capability is also not specific to any particular fixed name. For example, this fault handling capability may also be called fault processing capability, or fault handling capability, etc.

[0080] According to some embodiments, an alarm network element device can be used, for example, to indicate the device that alarms for a fault. This alarm network element device may include, for example, a variety of different devices. For instance, different alarm messages may correspond to different alarm network element devices.

[0081] In some embodiments, information verification can be used, for example, to indicate the verification method for processing fault information.

[0082] According to some embodiments, the verification result can be used, for example, to indicate the result of verification of fault handling capabilities and alarm network element information. This verification result is not specifically a fixed result. For example, when the verification method changes, the verification result can also change accordingly.

[0083] According to some embodiments, for example, the fault handling capability and alarm network element information can be verified based on the scheduling request parameters carried by the fault handling capability scheduling request, and the verification result can be obtained.

[0084] In step S13, if the verification result indicates that the verification was successful and the fault level of the main fault node is higher than the preset level, the processing flow corresponding to the main fault node is started. The processing flow is used to perform fault processing on the main fault node and the set of related nodes of the main fault node.

[0085] According to some embodiments, the processing flow is a process for handling the fault of the primary fault node. This processing flow is not specifically defined by a fixed procedure. For example, the processing flow may change accordingly when the fault type corresponding to the primary fault node changes. For example, the processing flow may also change accordingly when a modification instruction for the processing flow is received.

[0086] According to some embodiments, the primary fault node can refer to the fault node corresponding to the fault alarm information, such as the node that generated the fault alarm information. The primary fault node does not specifically refer to a fixed node. For example, when the node identifier corresponding to the primary fault node changes, the primary fault node can also change accordingly.

[0087] According to some embodiments, the set of related nodes of the primary fault node may, for example, be a collection of at least one related node. This set of related nodes does not specifically refer to a fixed set. Related nodes may, for example, indicate nodes that are associated with and affected by the primary fault node. For example, the set of related nodes may change when the number of related nodes included in it changes. For example, the set of related nodes may also change when any related node in it changes.

[0088] In some embodiments, when the verification result indicates that the verification was successful and the fault level of the main fault node is higher than a preset level, the processing flow corresponding to the main fault node is initiated. The processing flow is used to perform fault handling on the main fault node and the set of related nodes of the main fault node.

[0089] In step S14, if the verification result indicates that the verification failed, a fault work order is dispatched to the target device, wherein the fault work order is used to instruct the target device to handle the fault according to the received manual instructions.

[0090] In some embodiments, the manual instruction may be an instruction sent via a terminal. This manual instruction is not specifically a single, fixed instruction. It includes, but is not limited to, voice instructions, click instructions, or gesture instructions. The manual instruction is used to instruct the device to handle the current fault.

[0091] According to some embodiments, a fault work order can, for example, refer to fault alarm information. This fault work order does not specifically refer to a particular fixed work order. For example, when the fault information corresponding to a fault work order changes, the fault work order may also change accordingly. For example, when the upload time of a fault work order changes, the fault work order may also change accordingly.

[0092] In some embodiments, the target device may be used to indicate the device receiving the fault work order. The target device may be determined based on the fault type corresponding to the fault work order. For example, the target device may change accordingly if the fault work order changes. The name of the target device is not limited. For example, the target device may also be called a fault target device, a processing device, etc. For example, the target device may change accordingly when its device identifier changes. For example, the target device may change accordingly when the manual instruction changes.

[0093] When the target device receives the fault work order, it can process it. For example, the target device can process it according to the received fault processing instructions. The target device can process the fault work order independently, or it can interact with other devices to process the fault work order. The other devices may include at least one network element or at least one terminal, which is not limited in this embodiment.

[0094] In some or related embodiments, a fault handling capability scheduling request is received from a fault server; based on the scheduling request parameters carried in the fault handling capability scheduling request, information verification of fault handling capabilities and alarm network element devices is performed, and verification results are obtained; if the verification result indicates successful verification and the fault level of the main fault node is higher than a preset level, the processing flow corresponding to the main fault node is initiated, wherein the processing flow is used to handle the fault of the main fault node and the set of related nodes of the main fault node; if the verification result indicates failed verification, a fault work order is dispatched to the target device, wherein the fault work order is used to instruct the target device to handle the fault according to the received manual instructions. Therefore, faults can be handled through scheduling request parameters, and different fault handling measures can be adopted for different verification results. This can reduce the limitation of the expert experience base on the analysis capability of fault propagation, identify nodes related to the main fault node, restrict the propagation path of the main fault node's fault, reduce the impact of faults on the system, and this technical solution can be applied to various scenarios, improving the accuracy and efficiency of fault handling.

[0095] Figure 2 This is a flowchart illustrating a fault handling method according to an exemplary embodiment, such as... Figure 2 As shown, this fault handling method can be used in network operation and maintenance scenarios for intelligent fault handling, and includes the following steps:

[0096] In step S21, a fault handling capability scheduling request is received from the faulty server;

[0097] According to some embodiments, the execution subject of this disclosure is a network device. The name of the network device is not limited. For example, the network device may also be called a server, or a server cluster, etc.

[0098] in, Figure 3 This is an example illustration of a fault handling system according to an exemplary embodiment. For example... Figure 3As shown, a fault handling system may include, for example, a fault server and an operation server. The operation server, for example, can use a fault handling capability query interface to allow subscribers to query the fault handling capability list before scheduling fault operations, and can receive fault handling scheduling interface request information and record it in a fault handling scheduling information table. The fault server can send fault handling capability scheduling requests to the operation server.

[0099] In step S22, the fault handling capability and alarm network element information are verified according to the scheduling request parameters carried in the fault handling capability scheduling request, and the verification result is obtained.

[0100] The specific process is as described above and will not be repeated here.

[0101] In step S23, if the verification result indicates that the verification was successful, the fault alarm information corresponding to the main fault node is obtained;

[0102] The specific process is as described above and will not be repeated here.

[0103] According to some embodiments, the operation server can obtain fault alarm information monitored from the faulty server through an interface. This fault alarm information includes the time, location, category, and initial impact range of the fault. The time of fault occurrence refers to the specific date and time of the fault. The location of the fault occurrence may include, for example, the data center number, rack location, or the area covered by the fault. The category of the fault can be confirmed, for example, by analyzing fault codes and system logs. The initial impact range of the fault is confirmed using existing fault level standards for the faulty server.

[0104] In step S24, the fault level corresponding to the main fault node is obtained based on the fault alarm information;

[0105] The specific process is as described above and will not be repeated here.

[0106] In some embodiments, the number of affected business systems and users can be analyzed by fault category and location information to determine the scope of impact, and the fault alarm information can be compared with historical fault data to obtain the fault level corresponding to the current main fault.

[0107] The fault level is not a specific, fixed level. For example, the fault level can be determined based on the fault server's current fault information classification criteria, combined with the importance of the fault information's impact on services and the network type of the faulty server. Specifically, according to the fault level classification of the 5GC core network, the fault level could include, for example:

[0108] Level 1 fault: Affects the services provided by the system and requires immediate action, such as when a device or resource is completely unavailable and requires immediate recovery.

[0109] Level 2 fault: Affects service quality, such as a decline in the service quality of a certain device or resource, requiring processing to restore full capability;

[0110] Level 3 fault: Service quality has not been affected within the preset time period, but in order to avoid more serious faults, it is necessary to handle or observe at the preset time point;

[0111] Level 4 fault: This indicates that there may be a potential error affecting the service provided. Different measures should be taken depending on the specific error.

[0112] According to some embodiments, the severity of a fault can be classified according to the fault level. For example, a level 1 fault may correspond to an urgent severity, a level 2 fault to an important severity, a level 3 fault to a minor severity, and a level 4 fault to a general severity.

[0113] In step S25, if the fault level is higher than a preset level, a fault handling strategy corresponding to the fault level is executed on the main fault node and the set of related nodes of the main fault node.

[0114] The specific process is as described above and will not be repeated here.

[0115] According to some embodiments, the execution of a fault handling strategy corresponding to the fault level on the primary fault node and the set of related nodes of the primary fault node includes:

[0116] If the fault level is higher than a preset level, obtain a set of related nodes corresponding to the main fault node, wherein the set of related nodes includes at least one node whose association with the main fault node is greater than a relationship threshold.

[0117] Based on the relevant node set, issue alarm information or provide fault handling solutions to the target device corresponding to the relevant node set;

[0118] A fault handling strategy corresponding to the fault level is executed on the primary fault node. Therefore, when the fault level is higher than the preset level, nodes that are strongly correlated with the current primary fault node can be analyzed. Through the analysis of strongly correlated nodes, related nodes affected by the primary fault node can be obtained, alarm information can be issued or fault handling solutions can be provided, the risk of fault propagation of related nodes can be controlled, the fault handling time can be reduced, and the fault handling efficiency can be improved.

[0119] According to some embodiments, the preset level can be, for example, a level where the impact of a fault exceeds a threshold. This preset level does not specifically refer to a fixed level. For example, the preset level could be a level-two fault. For example, the preset level can change accordingly when a modification instruction for the preset level is received. For example, the preset level can also change accordingly when the specific level corresponding to the preset level changes.

[0120] When the fault level is lower than the preset level, only the main fault node needs to be processed, without processing the set of related nodes of the main fault node.

[0121] In some embodiments, the set of related nodes may be a collection of at least one related node. This set of related nodes does not specifically refer to a fixed set. Related nodes may, for example, indicate nodes associated with and affected by the primary faulty node. For example, the set of related nodes may change when the number of related nodes included in it changes. For example, the set of related nodes may also change when any related node in it changes.

[0122] According to some embodiments, obtaining the set of related nodes corresponding to the primary fault node includes:

[0123] Based on the fault alarm information, the diffusion range and fault propagation path corresponding to the main fault node are obtained;

[0124] Based on the fault propagation path and the diffusion range, obtain the node set corresponding to the main fault node, wherein the node set includes at least one node covered by the diffusion range;

[0125] Interconnection functions are used to verify the relationships between nodes in the node set, and the relationships between each node and the main fault node are obtained.

[0126] Based on the aforementioned relationships, the set of related nodes in the node set is obtained. Therefore, the node range covered by the fault can be determined according to the fault propagation path and diffusion range. The relationships between each node can be determined through interconnection functions, thereby determining the set of related nodes, improving the accuracy of determining the set of related nodes, reducing the scope of the fault's impact, and improving fault handling efficiency.

[0127] According to some embodiments, obtaining the diffusion range and fault propagation path corresponding to the main fault node based on the fault alarm information includes:

[0128] A clustering algorithm is used to cluster the historical fault data set to obtain the fault category set corresponding to the historical fault data set;

[0129] Classify each fault category in the fault category set and obtain the classification results;

[0130] Based on network asset information, obtain current network status information;

[0131] The current network state information and the historical fault data set are predicted by a fault propagation prediction model to obtain the propagation path corresponding to the main fault node.

[0132] Based on the current network status information, obtain the target node and associated links in the network topology where the primary fault node is located;

[0133] The classification results, target nodes, and associated links are simulated using fault propagation rules to obtain the propagation range and fault propagation path corresponding to the main fault node. Therefore, by combining the fault propagation prediction model and key nodes strongly correlated with the main fault node, a fault handling process can be determined, thereby improving fault handling efficiency.

[0134] According to some embodiments, obtaining the set of related nodes in the node set based on the association relationship includes:

[0135] The network topology corresponding to each node in the node set is obtained by using the K-truss algorithm with a K-shaped truss.

[0136] Based on the network topology, obtain the medium centrality and proximity centrality of each node;

[0137] Based on the medium centrality and the proximity centrality, obtain the k-truss value between each node and the primary fault node;

[0138] Add nodes whose k-truss values ​​are greater than a preset value to the relevant node set;

[0139] or

[0140] According to the k-truss values ​​in descending order, a preset number of nodes are added to the relevant node set. Therefore, the Louvain algorithm can be used to perform community detection on the network, identify several closely connected node groups, form the network's community structure, and analyze the average k-truss value of nodes within each community, as well as the connection density between communities. Based on the connection strength within the community, target nodes are determined, improving the accuracy of target node determination and fault handling.

[0141] According to some embodiments, for example, a fault propagation prediction model can be used to predict the trend and scope of a fault's potential spread. This fault propagation prediction model can, for example, analyze historical fault data and current network state information to obtain the propagation path, and may specifically include:

[0142] Acquire a historical fault data set and extract fault alarm information for each fault, specifically including time, location, category, and impact range. Improve data availability and consistency through data cleaning and formatting. Cluster the historical fault data to obtain multiple fault category sets, and analyze the processed historical fault data using a clustering algorithm to determine the fault categories.

[0143] According to some embodiments, the K-means clustering algorithm can be used to analyze the processed historical fault data set. For example, the number of clusters k=5, the number of iterations is 100, and the convergence threshold is 001 to obtain the classification results of fault categories, including hardware faults, software faults, transmission and relay faults, power environment faults, equipment performance alarms, configuration faults, etc.

[0144] Hardware failures can include faults caused by hardware devices such as equipment, boards, and ports; software failures can include faults caused by equipment system software problems; transmission and relay failures can include faults caused by network connection problems such as various links; power and environment failures can include faults caused by the operating environment of the computer room equipment, including power supply and temperature; equipment performance alarms can include faults related to equipment operating performance; and configuration failures can include faults related to equipment system resource configuration.

[0145] According to some embodiments, the operation server can retrieve network asset information from the network management system to obtain current network status information, including network topology, device operating status, device model, and importance level. Based on the current network status, it can identify important nodes and associated links in the network topology where the primary fault node is located. This important node could be, for example, a target node.

[0146] The network status data includes metrics such as network topology, device CPU utilization, memory usage, and link bandwidth utilization, collected every 5 minutes. The PageRank algorithm, for example, treats the connections between nodes in the network topology as edges. Based on the number of edges connecting nodes and other metrics such as network status data, the PageRank algorithm calculates the importance score of network nodes, identifying important nodes with high importance scores and the associated links formed by multiple important nodes.

[0147] According to some embodiments, based on the classification results of the fault category and the target node, a fault propagation rule is used to simulate and predict the possible propagation path and spread range of the fault of the main fault node in the network topology.

[0148] For example, the SIR propagation model can be used to simulate fault propagation. The propagation probability is set to 6, the maximum propagation hops to 5, and 1000 simulations are performed to statistically analyze the fault propagation path and its impact range. Analysis of the simulation results shows that the fault mainly propagates along the path from the core switch to the aggregation switch and then to the access switch, affecting an average of 2-3 downstream nodes. The confidence level of the prediction results is evaluated: a prior probability of the fault occurrence and a posterior probability of the model prediction are set, and the `predict` function is used to calculate the confidence level of the prediction results. When the confidence level is greater than 8, the simulated fault propagation path is considered valid, and all nodes covered by all valid fault paths are likely to be fault-related nodes of the primary fault node.

[0149] According to some embodiments, the K-truss algorithm can be used to analyze the network topology of the fault-covered nodes of the current primary fault node, and to determine the connection strength and structure between different nodes in the network topology associated with the primary fault node, thereby identifying the key nodes that are strongly associated with the primary fault node. These key nodes may, for example, be related nodes.

[0150] In this network element topology, each node is interconnected with the others through an interconnection function. Specifically, a time series similarity algorithm is used to analyze the changing trends of the expected fault values ​​of two nodes. If a following relationship exists between the two nodes, they are interconnected through the interconnection function, meaning they are strongly correlated. When one node is in a fault state, the state of the other interconnected node is affected by its fault state and is also prone to failure. Moreover, the influence between the two can be unidirectional.

[0151] According to some implementations, when the network topology is obtained, the K-truss algorithm can be used to perform preliminary analysis of the network to obtain the maximum k-truss value between each pair of nodes. By analyzing the obtained k-truss values, the connection strength of each node in the network is determined, where a higher k-truss value indicates a tighter connection between nodes. If the k-truss values ​​between nodes are high, these nodes may constitute the core layer of the network. The hierarchical structure of the network is identified through the connection patterns of these core nodes. After obtaining the hierarchical structure data, for nodes in the core layer, the network mediation and control capabilities of these nodes are further analyzed to determine the key nodes.

[0152] According to some implementation examples, in a network topology consisting of 100 nodes, K-truss algorithm analysis revealed that 80% of the node pairs had a k-truss value greater than or equal to 5, indicating that the connections between these nodes are very tight and they may constitute the core layer of the network. Further analysis of the network mediation and control power of these core nodes, by calculating the betweenness centrality and proximity centrality of the nodes, identified the top 10% of key nodes, which play important mediation and control roles in the network.

[0153] Betweenness centrality BCI can be used to indicate the number of shortest paths through nodes in the network, and the formula for calculating BCid can be, for example, as shown in formula (1):

[0154]

[0155] Where Nist represents the number of paths that pass through node i and are the shortest paths; gst represents the number of shortest paths connecting s and t.

[0156] Proximity centrality CCI can be used to indicate the importance of a node, and the formula for calculating CCI can be, for example, as shown in formula (2), and the formula for calculating di can be, for example, as shown in formula (3):

[0157]

[0158] Where di represents the average distance from node i to all other points, and the reciprocal of this average distance is the proximity centrality.

[0159] According to some embodiments, providing a fault handling solution to the target device corresponding to the relevant node set based on the relevant node set includes:

[0160] Based on the set of relevant nodes, fault handling experience, and the fault propagation path, determine the fault handling scheme corresponding to each relevant node in the set of relevant nodes;

[0161] The fault handling solution is provided to the target device corresponding to each of the relevant nodes in the relevant node set.

[0162] According to some embodiments, for example, if the relevant node is a hardware failure, the corresponding failure handling scheme can be determined based on hardware performance parameters, failure handling experience, and the failure propagation path.

[0163] In some embodiments, for example, if the target node is a software defect, the software configuration file of the node is obtained, and the corresponding fault handling solution for the target node can be obtained, such as code review and generation of a repair solution.

[0164] In step S26, if the verification result indicates that the verification failed, a fault work order is dispatched to the target device, wherein the fault work order is used to instruct the target device to handle the fault according to the received manual instructions.

[0165] The specific process is as described above and will not be repeated here.

[0166] According to some embodiments, when the operation server receives a fault handling capability scheduling request, it can perform scheduling verification rule matching. If the verification rule matches successfully, the automatic handling process for the main fault node is executed; if the verification rule fails to match, the fault information is marked as requiring manual intervention, and a work order is automatically dispatched to the corresponding operation and maintenance team through the fault handling system to ensure that the fault is handled in a timely manner.

[0167] In one or related embodiments, if the verification result indicates successful verification, fault alarm information corresponding to the main fault node is obtained; based on the fault alarm information, the fault level corresponding to the main fault node is obtained; and a fault handling strategy corresponding to the fault level is executed on the main fault node and the set of related nodes of the main fault node. Therefore, the fault handling strategy can be determined based on the fault level, which can improve the accuracy of the fault handling strategy determination.

[0168] A block diagram of a fault handling apparatus is shown according to an exemplary embodiment. (Refer to...) Figure 4 The device 400 includes:

[0169] The request receiving unit 401 is used to receive the fault handling capability scheduling request sent by the faulty server;

[0170] The result acquisition unit 402 is used to perform information verification of fault handling capability and alarm network element devices based on the scheduling request parameters carried by the fault handling capability scheduling request, and to obtain the verification result.

[0171] The fault handling unit 403 is used to initiate the processing flow corresponding to the main fault node when the verification result indicates that the verification is successful and the fault level of the main fault node is higher than the preset level. The processing flow is used to perform fault handling on the main fault node and the set of related nodes of the main fault node.

[0172] The fault handling unit 403 is further configured to dispatch a fault work order to the target device when the verification result indicates that the verification has failed, wherein the fault work order is used to instruct the target device to perform fault handling according to the received manual instructions.

[0173] The fault handling unit 403 may further include an automatic fault handling subunit 4031, which is used to start the processing flow corresponding to the main fault node when the verification result indicates that the verification is successful and the fault level of the main fault node is higher than the preset level. The processing flow is used to perform fault handling on the main fault node and the set of related nodes of the main fault node.

[0174] According to some embodiments, the fault handling unit 403 is used to initiate the processing flow corresponding to the main fault node when the verification result indicates successful verification and the fault level of the main fault node is higher than a preset level, specifically for:

[0175] If the verification result indicates that the verification was successful, obtain the fault alarm information corresponding to the main fault node;

[0176] Based on the fault alarm information, the fault level corresponding to the main fault node is obtained;

[0177] A fault handling strategy corresponding to the fault level is executed on the primary fault node and the set of related nodes of the primary fault node.

[0178] According to some embodiments, when the fault handling unit 403 executes a fault handling strategy corresponding to the fault level on the main fault node and the set of related nodes of the main fault node, it is specifically used for:

[0179] If the fault level is higher than a preset level, obtain a set of related nodes corresponding to the main fault node, wherein the set of related nodes includes at least one node whose association with the main fault node is greater than a relationship threshold.

[0180] Based on the relevant node set, issue alarm information or provide fault handling solutions to the target device corresponding to the relevant node set;

[0181] The fault handling strategy corresponding to the fault level is executed on the main fault node.

[0182] According to some embodiments, when the fault processing unit 403 is used to obtain the set of related nodes corresponding to the main fault node, it is specifically used for:

[0183] Based on the fault alarm information, the diffusion range and fault propagation path corresponding to the main fault node are obtained;

[0184] Based on the fault propagation path and the diffusion range, obtain the node set corresponding to the main fault node, wherein the node set includes at least one node covered by the diffusion range;

[0185] Interconnection functions are used to verify the relationships between nodes in the node set, and the relationships between each node and the main fault node are obtained.

[0186] Based on the aforementioned association, obtain the set of related nodes in the node set.

[0187] According to some embodiments, when the fault processing unit 403 obtains the diffusion range and fault propagation path corresponding to the main fault node based on the fault alarm information, it is specifically used for:

[0188] A clustering algorithm is used to cluster the historical fault data set to obtain the fault category set corresponding to the historical fault data set;

[0189] Classify each fault category in the fault category set and obtain the classification results;

[0190] Based on network asset information, obtain current network status information;

[0191] The current network state information and the historical fault data set are predicted by a fault propagation prediction model to obtain the propagation path corresponding to the main fault node.

[0192] Based on the current network status information, obtain the target node and associated links in the network topology where the primary fault node is located;

[0193] The classification results, the target node, and the associated links are simulated using fault propagation rules to obtain the propagation range and fault propagation path corresponding to the main fault node.

[0194] According to some embodiments, when the fault handling unit 403 obtains the set of related nodes in the node set based on the association relationship, it is specifically used for:

[0195] The network topology corresponding to each node in the node set is obtained by using the K-truss algorithm with a K-shaped truss.

[0196] Based on the network topology, obtain the medium centrality and proximity centrality of each node;

[0197] Based on the medium centrality and the proximity centrality, obtain the k-truss value between each node and the primary fault node;

[0198] Add nodes whose k-truss values ​​are greater than a preset value to the relevant node set;

[0199] or

[0200] A preset number of nodes are added to the relevant node set in descending order of the k-truss values.

[0201] According to some embodiments, when the fault handling unit 403 provides a fault handling solution to the target device corresponding to the relevant node set based on the relevant node set, it is specifically used for:

[0202] Based on the set of relevant nodes, fault handling experience, and the fault propagation path, determine the fault handling scheme corresponding to each relevant node in the set of relevant nodes;

[0203] The fault handling solution is provided to the target device corresponding to each of the relevant nodes in the relevant node set.

[0204] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0205] In some or related embodiments, a request receiving unit is used to receive a fault handling capability scheduling request sent by a faulty server; a result acquisition unit is used to verify the fault handling capability and alarm network element information according to the scheduling request parameters carried in the fault handling capability scheduling request, and obtain the verification result; a fault handling unit is used to start the processing flow corresponding to the main fault node if the verification result indicates successful verification; and a fault handling unit is used to dispatch a fault work order to the target device if the verification result indicates failed verification, wherein the fault work order is used to instruct the target device to perform fault handling according to the received manual instructions. Therefore, faults can be handled through scheduling request parameters, and different fault handling measures can be adopted for different verification results. This can reduce the limitation of the expert experience base on the analysis capability of fault propagation, identify nodes related to the main fault node, restrict the propagation path of the main fault node, reduce the impact of the fault on the system, and this technical solution can be applied to various scenarios, improving the accuracy and efficiency of fault handling.

[0206] Figure 5 This is a block diagram of a network device 500 provided in an embodiment of this disclosure. For example, the network device 500 can be provided as a network device. See also... Figure 5The network device 500 includes a processing component 522, which further includes at least one processor, and memory resources represented by memory 532 for storing instructions, such as application programs, that can be executed by the processing component 522. The application programs stored in memory 532 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 522 is configured to execute instructions to perform any of the methods described above applied to the network device.

[0207] Network device 500 may also include a power supply component 527 configured to perform power management of network device 500, a wired or wireless network interface 550 configured to connect network device 500 to a network, and an input / output (I / O) interface 558. Network device 500 can operate on an operating system stored in memory 532, such as Windows Server™, Mac OS X™, Unix™, Linux™, Free BSD™, or similar.

[0208] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0209] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0210] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0211] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0212] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0213] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0214] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0215] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A fault handling method, characterized in that, include: Receive fault handling capability scheduling requests sent by faulty servers; Based on the scheduling request parameters carried in the fault handling capability scheduling request, the fault handling capability and alarm network element information are verified, and the verification results are obtained. If the verification result indicates that the verification was successful and the fault level of the main fault node is higher than the preset level, the processing flow corresponding to the main fault node is started. The processing flow is used to perform fault processing on the main fault node and the set of related nodes of the main fault node. If the verification result indicates that the verification failed, a fault work order is dispatched to the target device, wherein the fault work order is used to instruct the target device to handle the fault according to the received manual instructions.

2. The method according to claim 1, characterized in that, When the verification result indicates successful verification and the fault level of the primary fault node is higher than a preset level, the corresponding processing procedure for the primary fault node is initiated, including: If the verification result indicates that the verification was successful, obtain the fault alarm information corresponding to the main fault node; Based on the fault alarm information, the fault level corresponding to the main fault node is obtained; A fault handling strategy corresponding to the fault level is executed on the primary fault node and the set of related nodes of the primary fault node.

3. The method according to claim 2, characterized in that, The execution of a fault handling strategy corresponding to the fault level on the primary fault node and the set of related nodes of the primary fault node includes: If the fault level is higher than a preset level, obtain a set of related nodes corresponding to the main fault node, wherein the set of related nodes includes at least one node whose association with the main fault node is greater than a relationship threshold. Based on the relevant node set, issue alarm information or provide fault handling solutions to the target device corresponding to the relevant node set; The fault handling strategy corresponding to the fault level is executed on the main fault node.

4. The method according to claim 3, characterized in that, The step of obtaining the set of related nodes corresponding to the primary fault node includes: Based on the fault alarm information, the diffusion range and fault propagation path corresponding to the main fault node are obtained; Based on the fault propagation path and the diffusion range, obtain the node set corresponding to the main fault node, wherein the node set includes at least one node covered by the diffusion range; Interconnection functions are used to verify the relationships between nodes in the node set, and the relationships between each node and the main fault node are obtained. Based on the aforementioned association, obtain the set of related nodes in the node set.

5. The method according to claim 4, characterized in that, The step of obtaining the diffusion range and fault propagation path corresponding to the main fault node based on the fault alarm information includes: A clustering algorithm is used to cluster the historical fault data set to obtain the fault category set corresponding to the historical fault data set; Classify each fault category in the fault category set and obtain the classification results; Based on network asset information, obtain current network status information; The current network state information and the historical fault data set are predicted by a fault propagation prediction model to obtain the propagation path corresponding to the main fault node. Based on the current network status information, obtain the target node and associated links in the network topology where the primary fault node is located; The classification results, the target node, and the associated links are simulated using fault propagation rules to obtain the propagation range and fault propagation path corresponding to the main fault node.

6. The method according to claim 4, characterized in that, The step of obtaining the related node set in the node set based on the association relationship includes: The network topology corresponding to each node in the node set is obtained by using the K-truss algorithm with a K-shaped truss. Based on the network topology, obtain the medium centrality and proximity centrality of each node; Based on the medium centrality and the proximity centrality, obtain the k-truss value between each node and the primary fault node; Add nodes whose k-truss values ​​are greater than a preset value to the relevant node set; or A preset number of nodes are added to the relevant node set in descending order of the k-truss values.

7. The method according to claim 5, characterized in that, The step of providing a fault handling solution to the target device corresponding to the relevant node set based on the relevant node set includes: Based on the set of relevant nodes, fault handling experience, and the fault propagation path, determine the fault handling scheme corresponding to each relevant node in the set of relevant nodes; The fault handling solution is provided to the target device corresponding to each of the relevant nodes in the relevant node set.

8. A fault handling device, characterized in that, include: The request receiving unit is used to receive fault handling capability scheduling requests sent by the faulty server. The result acquisition unit is used to verify the information of fault handling capability and alarm network element devices based on the scheduling request parameters carried by the fault handling capability scheduling request, and to obtain the verification result. The fault handling unit is used to initiate the processing flow corresponding to the main fault node when the verification result indicates that the verification is successful and the fault level of the main fault node is higher than the preset level. The processing flow is used to perform fault handling on the main fault node and the set of related nodes of the main fault node. A fault handling unit is configured to dispatch a fault work order to a target device when the verification result indicates that the verification has failed, wherein the fault work order is used to instruct the target device to perform fault handling according to the received manual instructions.

9. A network device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the fault handling method as described in any one of claims 1 to 7.

10. A storage medium storing instructions, characterized in that, When the instruction is executed on the communication device, the communication device performs the fault handling method as described in any one of claims 1 to 7.

Images