Fault type determination method and device, equipment, medium and program product

Abstract

The invention discloses a fault type determination method and device, equipment, a medium and a program product, and belongs to the technical field of big data. The method comprises the following steps: acquiring key node state information in a first data packet under the condition that a target network node sends the first data packet; analyzing the key node state information by using a preset fault analysis model to obtain an analysis result; when the analysis result is the operation fault, key node state information and basic node state information in a second data packet sent by the target network node are acquired; and determining a fault type of the target network node according to a comparison result between the key node state information and the basic node state information in the second data packet and corresponding preset thresholds. According to the embodiment of the invention, the fault can be quickly identified, and the specific fault type of the target network node can be accurately judged, so that the efficiency and accuracy of fault detection are greatly improved, and the stability and reliability of network operation are improved.

Description

Technical Field

[0001] The present application belongs to the field of big data technology, and in particular, relates to a method, device, equipment, medium and program product for determining a fault type. Background Art

[0002] As networks continue to grow in size and complexity, rapid detection and recovery of network failures becomes critical.

[0003] However, traditional network fault detection methods, such as those that rely on periodic polling mechanisms or post-event log analysis, are powerless in the face of rapidly changing network environments. These methods not only fail to achieve immediate responses to network faults, but also result in significant delays in fault discovery and processing. This delay not only directly reduces the overall quality of network services and impairs user experience, but is also likely to further cause business continuity interruptions, posing a serious threat to the stability and reliability of network operations. In addition, after a fault occurs, existing network fault detection methods are difficult to quickly and accurately locate the specific fault type, which restricts the improvement of network fault detection and recovery capabilities, and often puts network operators in a passive position when facing faults.

[0004] Therefore, existing network fault detection technologies have the problems of low fault detection efficiency, untimely response, and difficulty in accurately and efficiently determining the specific fault type of the network node. Summary of the invention

[0005] The embodiments of the present application provide a method, apparatus, device, medium and program product for determining a fault type, which can quickly identify faults and accurately determine the specific fault type of a target network node, thereby improving the efficiency and accuracy of fault detection and improving the stability and reliability of network operations.

[0006] In a first aspect, an embodiment of the present application provides a method for determining a fault type, including:

[0007] When the target network node sends a first data packet, acquiring key node status information in the first data packet;

[0008] Analyze the key node status information in the first data packet using a preset fault analysis model to obtain an analysis result;

[0009] When the analysis result is an operation failure, obtaining key node status information and basic node status information in a second data packet sent by the target network node;

[0010] The fault type of the target network node is determined according to the comparison result between the key node status information and the basic node status information in the second data packet and the corresponding preset thresholds.

[0011] In a possible embodiment of the first aspect, determining a fault type of a target network node according to a comparison result between the key node status information and the basic node status information in the second data packet and a corresponding preset threshold value includes:

[0012] Compare the key node status information and the basic node status information in the second data packet with the corresponding preset thresholds to obtain a target comparison result;

[0013] In the preset correspondence between the comparison result and the fault type, a target fault type corresponding to the target comparison result is obtained, and the target fault type is used as the fault type of the target network node.

[0014] In a possible embodiment of the first aspect, when the target network node sends a first data packet, before acquiring key node status information in the first data packet, the method further includes:

[0015] Using preset packet filters, monitor the target network nodes at the kernel layer;

[0016] When the target network node sends a first data packet, obtaining key node status information in the first data packet includes:

[0017] When the preset data packet filter detects that the target network node sends a first data packet, the preset data packet filter is used to obtain key node status information in the first data packet;

[0018] When the analysis result is an operation failure, key node status information and basic node status information in the second data packet sent by the target network node are obtained, including:

[0019] When the analysis result is an operation failure and the preset data packet filter detects that the target network node sends a second data packet, the preset data packet filter is used to obtain key node status information and basic node status information in the second data packet.

[0020] In a possible embodiment of the first aspect, the key node status information in the first data packet is analyzed by using a preset fault analysis model to obtain an analysis result, including:

[0021] Storing the key node status information in the first data packet according to a preset structure;

[0022] Sending the key node status information in the stored first data packet to the user layer according to a preset period;

[0023] The key node status information in the first data packet is analyzed using the fault analysis model preset in the user layer to obtain an analysis result.

[0024] In a possible embodiment of the first aspect, the key node status information in the first data packet is analyzed by using a fault analysis model preset in the user layer to obtain an analysis result, including:

[0025] Calculate the average value of the key node status information of the same type in the first data packet to obtain the target key node information;

[0026] The fault analysis model preset in the user layer is used to analyze the target key node status information to obtain the analysis results.

[0027] In a possible embodiment of the first aspect, before analyzing the key node status information in the first data packet by using a preset fault analysis model to obtain an analysis result, the method further includes:

[0028] Obtain the full amount of historical node status information and historical fault type information of each network node within a preset period of time;

[0029] The information of historical fault types is used as the supervision result, and the full amount of historical node status information is used as the training sample. The preset original fault analysis model is trained in a supervised manner to obtain the fault analysis model.

[0030] In a possible embodiment of the first aspect, the fault analysis model includes weight coefficients corresponding to the status information of each node; the weight coefficient corresponding to the key node status information is greater than or equal to a preset weight coefficient threshold; the weight coefficient corresponding to the basic node status information is less than the preset weight coefficient threshold.

[0031] In a possible embodiment of the first aspect, the present invention further includes:

[0032] In the preset correspondence relationship between the fault type and the solution, obtaining the target solution corresponding to the fault type of the target network node;

[0033] Execute the target solution.

[0034] In a possible embodiment of the first aspect, the present invention further includes:

[0035] Get the execution results of the target solution;

[0036] On the target page, information about the fault type of the target network node and information about the execution result of the target solution are displayed.

[0037] Based on the same inventive concept, in a second aspect, an embodiment of the present application further provides a device for determining a fault type, including:

[0038] An acquisition module, configured to acquire key node status information in a first data packet when a target network node sends a first data packet;

[0039] An analysis module, used to analyze the key node status information in the first data packet using a preset fault analysis model to obtain an analysis result;

[0040] The acquisition module is further used to acquire the key node status information and the basic node status information in the second data packet sent by the target network node when the analysis result is an operation failure;

[0041] The determination module is used to determine the fault type of the target network node according to the comparison result between the key node status information and the basic node status information in the second data packet and the corresponding preset threshold value.

[0042] Based on the same inventive concept, in the third aspect, an embodiment of the present application also provides a device for determining a fault type, which includes a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the first aspect, or the method for determining the fault type in any embodiment of the first aspect.

[0043] Based on the same inventive concept, in the fourth aspect, an embodiment of the present application further provides a computer storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method for determining the fault type in the first aspect or any embodiment of the first aspect is implemented.

[0044] Based on the same inventive concept, in the fifth aspect, an embodiment of the present application also provides a computer program product. When the instructions in the computer program product are executed by the processor of the device, the device can execute the method for determining the fault type in the first aspect or any embodiment of the first aspect.

[0045] The method, device, equipment, medium and program product for determining the fault type of the embodiment of the present application, when the method detects that the target network node sends a first data packet at the first time, the key node status information in the full node status information carried by the first data packet can be quickly extracted, and then the key node status information extracted from the first data packet is analyzed by using a preset trained fault analysis model to obtain an analysis result, and then when the analysis result is an operation fault, the full node status information in the second data packet can be obtained when the target network node sends a second data packet, including the key node status information and the basic node status information, and then the fault type of the target network node can be determined according to the comparison result between the key node status information and the basic node status information in the second data packet and the corresponding preset threshold. By real-time monitoring and extracting the key node status information in the data packet sent by the target network node at the first time, using the preset fault analysis model to quickly determine whether there is an operation fault, and after confirming the fault, further obtaining the detailed full node status information of the target network node, and comparing it with the preset threshold, the specific fault type of the target network node can be efficiently and accurately determined, thereby greatly improving the efficiency and accuracy of fault detection and diagnosis, and improving the stability and reliability of network operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Other features, objects and advantages of the present application will become more apparent by reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings, in which the same or similar reference numerals represent the same or similar features and the accompanying drawings are not drawn to scale.

[0047] Figure 1 This is a flow chart of a method for determining a fault type provided in an embodiment of the present application;

[0048] Figure 2 This is another flowchart of the method for determining the fault type provided in the embodiment of the present application;

[0049] Figure 3 This is another flowchart of the method for determining the fault type provided in the embodiment of the present application;

[0050] Figure 4 is another flowchart of a method for determining a fault type provided in an embodiment of the present application;

[0051] Figure 5 This is another flowchart of the method for determining the fault type provided in the embodiment of the present application;

[0052] Figure 6 This is another flowchart of the method for determining the fault type provided in the embodiment of the present application;

[0053] Figure 7 is another flowchart of a method for determining a fault type provided in an embodiment of the present application;

[0054] Figure 8 This is another flowchart of the method for determining the fault type provided in the embodiment of the present application;

[0055] Fig. 9 It is a structural schematic diagram of a device for determining a fault type provided in an embodiment of the present application;

[0056] Fig.10 It is a structural diagram of a device for determining a fault type provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only configured to explain the present application and are not configured to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0058] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0059] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0060] It is obvious to those skilled in the art that various modifications and changes can be made in the present application without departing from the spirit or scope of the present application. Therefore, the present application is intended to cover modifications and changes of the present application that fall within the scope of the corresponding claims (technical solutions for protection) and their equivalents. It should be noted that the implementation methods provided in the embodiments of the present application can be combined with each other without contradiction.

[0061] It should be noted that the acquisition, storage, use and processing of data in the embodiments of the present application are in compliance with the relevant provisions of national laws and regulations.

[0062] It should also be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0063] Before describing the technical solutions provided by the embodiments of the present application, in order to facilitate the understanding of the embodiments of the present application, the present application first specifically describes the problems existing in the related art:

[0064] As networks continue to grow in size and complexity, rapid detection and recovery of network failures becomes critical.

[0065] However, related network fault detection methods, such as those that rely on periodic polling mechanisms or post-event log analysis, are powerless in the face of rapidly changing network environments. These methods not only fail to achieve immediate response to network faults, but also lead to significant delays in fault discovery and processing. This delay not only directly reduces the overall quality of network services and impairs user experience, but is also likely to further cause business continuity interruptions, posing a serious threat to the stability and reliability of network operations. Moreover, after a fault occurs, it is difficult for related network fault detection methods to quickly and accurately locate the specific fault type, which restricts the improvement of network fault detection and recovery capabilities, and often puts network operators in a passive position when facing faults. Therefore, related network fault detection technologies have the problems of low fault detection efficiency, untimely response, and difficulty in accurately and efficiently determining the specific fault type of network nodes.

[0066] The relevant technologies not only have problems of low fault detection efficiency and untimely response, but also have problems such as insufficient flexibility, low recovery efficiency, high resource consumption and high false alarm rate.

[0067] Among them, the fault detection efficiency is low and the response is not timely: the relevant network fault detection methods usually adopt a periodic polling method, which leads to a large delay in fault detection and affects the timeliness of fault response.

[0068] Insufficient flexibility: Most related network fault detection methods lack sufficient flexibility and are difficult to adapt to changes in the network environment, especially when faced with complex and dynamic network architectures.

[0069] Inefficient recovery: Once a failure is detected, existing recovery mechanisms often require manual intervention and have a low degree of automation, resulting in inefficient recovery.

[0070] High resource consumption: Some software-based fault detection technologies may consume a lot of computing resources and affect the overall performance of the system.

[0071] High false alarm rate: Related network fault detection technologies sometimes produce high false alarm rates, leading to unnecessary alarms and waste of resources.

[0072] Based on this, the embodiments of the present application provide a method, device, equipment, medium and program product for determining the fault type, which can quickly identify faults and accurately determine the specific fault type of the target network node, thereby greatly improving the efficiency and accuracy of fault detection and diagnosis, improving the stability and reliability of network operations, and solving problems such as detection delays, lack of flexibility, low recovery efficiency, high resource consumption and high false alarm rate.

[0073] The method for determining the fault type provided in the embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0074] Figure 1 FIG. 1 is a flow chart of a method for determining a fault type provided in an embodiment of the present application. Figure 1 As shown, the method may include steps S110 to S140.

[0075] S110, when the target network node sends a first data packet, obtain key node status information in the first data packet.

[0076] A network node is a network device or component with an independent address and the ability to transmit and receive data, such as a network interface card or a bridge.

[0077] A data packet is a basic data unit in network communication. When no operation failure of the target network node is detected, the data packet sent by the target network node monitored in real time can be called the first data packet. The data packet can include node status information of the network node, such as packet loss rate, delay, error rate, etc.

[0078] Key node status information is node status information that can accurately reflect the network operation status and has a direct impact on network performance or stability.

[0079] Specifically, the target network node can be monitored in real time, and when the target network node sends a first data packet, representative key node status information in the first data packet can be immediately obtained from the full amount of node status information in the first data packet.

[0080] S120, using a preset fault analysis model, analyzing the key node status information in the first data packet to obtain an analysis result.

[0081] The preset fault analysis model is a predefined and configured fault analysis model used to identify possible faults by analyzing network node status information. The fault analysis model can be trained based on machine learning, statistics, rule engines or other technologies, and can extract features from input data and determine whether the operating status of the network node is in a normal state or a faulty state based on these features.

[0082] Specifically, by using a preset fault analysis model, the key status information contained in the first data packet sent by the target network node is analyzed to obtain an analysis result.

[0083] S130: When the analysis result is an operation failure, obtain key node status information and basic node status information in a second data packet sent by the target network node.

[0084] Among them, when the analysis result obtained by the pre-set fault analysis model is that the target network node has an operation failure, the data packet sent by the target network node continues to be monitored in real time. The data packet can be called a second data packet. The second data packet is a data packet obtained when a failure occurs in the target network node, and is used for further diagnosis and confirmation of the specific fault type.

[0085] The basic node status information is the node status information of the full amount of node status information of the network node except the key node status information.

[0086] It should be noted that which of the full amount of node status information of the network nodes belongs to the key node status information and which belongs to the basic node status information can be determined by the fault analysis model obtained through training.

[0087] Specifically, when the preset fault analysis model determines that the target network node has an operational fault, full node status information, including key node status information and basic node status information, can be further extracted from the second data packet sent by the target network node to facilitate more in-depth diagnosis and analysis.

[0088] S140: Determine the fault type of the target network node according to a comparison result between the key node status information and the basic node status information in the second data packet and corresponding preset thresholds.

[0089] The preset threshold is a critical value set in advance and used to evaluate whether the network node status is normal. The preset threshold can be set as needed, and this is not limited in the embodiments of the present application.

[0090] Specifically, by comparing the full amount of node status information (such as key node status information and basic node status information) contained in the second data packet with pre-set thresholds, it is possible to determine which node status information of the target network node is abnormal, thereby determining the specific fault type.

[0091] The method for determining the fault type provided in the embodiment of the present application is to immediately extract the key node status information from the full node status information carried by the first data packet when the target network node sends a first data packet in real time, and then use the preset trained fault analysis model to analyze the key node status information extracted from the first data packet to obtain the analysis result, and then when the analysis result is an operation fault, the full node status information in the second data packet can be obtained when the target network node sends a second data packet, including the key node status information and the basic node status information, and then the fault type of the target network node can be determined according to the comparison result between the key node status information and the basic node status information in the second data packet and the corresponding preset threshold. By real-time monitoring and extracting the key node status information in the data packet sent by the target network node at the first time, using the preset fault analysis model to quickly determine whether there is an operation fault, and after confirming the fault, further obtaining the detailed full node status information of the target network node, and comparing it with the preset threshold, the specific fault type of the target network node can be efficiently and accurately determined, thereby greatly improving the efficiency and accuracy of fault detection and diagnosis, and improving the stability and reliability of network operation.

[0092] It should be noted that the embodiment of the present application monitors in real time and extracts the key node status information in the data packet sent by the target network node at the first time, and uses the preset fault analysis model to quickly determine whether there is an operational fault. Once the fault is confirmed, the full node status information of the target network node (including key node status information and basic node status information) is further obtained, and compared with the preset threshold, so that the specific fault type of the target network node can be efficiently and accurately determined. This method greatly improves the efficiency and accuracy of fault detection and diagnosis, and improves the stability and reliability of network operations. However, the related technology lacks the ability to monitor in real time, quickly extract key information and use preset models for judgment, and after confirming the fault, the related technology fails to further obtain detailed full node status information and accurately compare with the preset threshold, so the embodiment of the present application can solve the problem that the efficiency and accuracy of fault detection and diagnosis of the related technology are not high.

[0093] Figure 2 This is another flowchart of the method for determining the fault type provided in an embodiment of the present application.

[0094] In some embodiments, Figure 2 As shown, step S140 determines the fault type of the target network node according to the comparison result between the key node status information and the basic node status information in the second data packet and the corresponding preset threshold value, and may include steps S141 and S142.

[0095] S141, comparing the key node status information and the basic node status information in the second data packet with corresponding preset thresholds to obtain a target comparison result.

[0096] Specifically, after the operation fails and the key node status information and basic node status information in the second data packet sent by the target network node are obtained, each key node status information in the second data packet can be compared with its corresponding preset threshold, and each basic node status information in the second data packet can be compared with its corresponding preset threshold, and the final target comparison result can be obtained.

[0097] S142, in the preset correspondence relationship between the comparison result and the fault type, obtaining a target fault type corresponding to the target comparison result, and using the target fault type as the fault type of the target network node.

[0098] The preset correspondence between the comparison result and the fault type is a predefined mapping relationship, which specifies which fault type different comparison results correspond to.

[0099] Specifically, by querying the correspondence between the preset comparison result and the fault type, the fault type corresponding to the target comparison result obtained by comparing the key node status information and the basic node status information with the preset threshold can be determined. This fault type can be called the target fault type.

[0100] The embodiment of the present application can compare the key and basic node status information in the second data packet with the preset threshold value, quickly obtain the target comparison result, and quickly determine the target fault type of the target network node by querying the mapping relationship between the predefined comparison result and the fault type, thereby significantly improving the diagnostic efficiency and accuracy of network faults.

[0101] Figure 3 This is another flowchart of the method for determining the fault type provided in an embodiment of the present application.

[0102] In some embodiments, Figure 3As shown, when the target network node sends a first data packet, before acquiring the key node status information in the first data packet, the method may further include step S150.

[0103] S150, using a preset data packet filter, monitors the target network node at the kernel layer.

[0104] Among them, the preset data packet filter can be used to filter network data packets. The preset data packet filter can be used to monitor the data packets sent by the target network node at the kernel layer.

[0105] For example, the preset packet filter may be an extended Berkeley Packet Filter (eBPF). As an emerging kernel programming framework, eBPF technology can achieve efficient and flexible network packet processing and system event tracking at the kernel level. eBPF technology allows user space programs in a security sandbox to run in the kernel, thereby achieving high-performance network filtering, performance monitoring, system tracking and other functions.

[0106] It should be noted that eBPF technology provides powerful basic capabilities, but how to use eBPF to achieve efficient network fault detection and recovery is still a problem worth studying.

[0107] Specifically, by using the preset data packet filter, the data packet transmission status of the target network node is monitored in real time at the kernel level of the operating system, which can achieve an immediate response to network failures.

[0108] Step S110, when the target network node sends a first data packet, obtains key node status information in the first data packet, which may include step S111.

[0109] S111, when the preset data packet filter detects that the target network node sends a first data packet, the preset data packet filter is used to obtain key node status information in the first data packet.

[0110] Specifically, when the preset data packet filter detects that the target network node has sent out a first data packet, the filter can be used to instantly extract key node status information in the first data packet.

[0111] In the case where the analysis result is an operation failure, step S130 obtains key node status information and basic node status information in a second data packet sent by the target network node, which may include step S131.

[0112] S131, when the analysis result is an operation failure and the preset data packet filter detects that the target network node sends a second data packet, the preset data packet filter is used to obtain key node status information and basic node status information in the second data packet.

[0113] Specifically, when the analysis result is an operational failure, the preset data packet filter can continue to monitor the data packet (second data packet) sent by the target network node in real time, and use the preset data packet filter to extract and obtain the full amount of node status information contained in the second data packet, such as key node status information and basic node status information.

[0114] The embodiment of the present application utilizes a preset packet filter (such as eBPF) to monitor the packet transmission of the target network node in real time at the kernel level, and can send the monitored first packet to the fault analysis model of the user layer for fault analysis, and instantly obtain the key node status information and basic node status information in the second packet when the analysis result is an operating failure, thereby achieving instant response and efficient detection and positioning of network faults, thereby improving the efficiency and accuracy of network management.

[0115] Figure 4 This is another flowchart of the method for determining the fault type provided in an embodiment of the present application.

[0116] In some embodiments, Figure 4 As shown, step S120 uses a preset fault analysis model to analyze the key node status information in the first data packet to obtain an analysis result, which may include steps S121 to S123.

[0117] S121, storing the key node status information in the first data packet according to a preset structure.

[0118] Specifically, after the key node status information in the first data packet is acquired by using the preset data packet filter, the key node status information in the first data packet may be stored according to a preset structure (such as a map data structure of eBPF).

[0119] S122, sending the key node status information stored in the first data packet to the user layer according to a preset period.

[0120] Specifically, according to a preset time period, the key node status information in the first data packet that has been stored is transmitted from the kernel layer to the user layer for further processing and analysis by the user layer.

[0121] S123, using the fault analysis model preset in the user layer, analyze the key node status information in the first data packet to obtain an analysis result.

[0122] Specifically, at the user layer, the key node status information extracted from the first data packet is analyzed using a pre-set fault analysis model to obtain an analysis result of whether the target network node has a network fault. For example, the preset period is 10ms, and the key node status information stored in the first data packet can be sent to the user layer every 10ms, and then the key node status information is analyzed using the pre-set fault analysis model of the user layer to obtain an analysis result.

[0123] The embodiment of the present application utilizes a preset period to send key node status information from the kernel layer to the user layer for analysis, which can achieve real-time monitoring of the network status, and by reasonably setting the time period (such as every 10ms, every 20ms, etc.), it can avoid frequent data transmission and analysis operations, thereby effectively saving computing resources, and can optimize the use of system resources while ensuring the timeliness and accuracy of fault detection, thereby improving overall operating efficiency.

[0124] Figure 5 This is another flowchart of the method for determining the fault type provided in an embodiment of the present application.

[0125] In some embodiments, Figure 5 As shown, step S123 uses the fault analysis model preset in the user layer to analyze the key node status information in the first data packet to obtain the analysis result, which may include steps S1231 and S1232.

[0126] S1231, calculating the average value of the key node status information of the same type in the first data packet to obtain the target key node information.

[0127] Specifically, the key node status information of the same type in the first data packet is aggregated, for example, the target key node information is obtained by calculating the average value of the key node status information of the same type. For example, the target network node sends the first data packet with a sending period of 1ms, and the preset period is 10ms, then 10 key node status information of the same type can be stored every 10ms, for example, 10 error rate information can be stored, and then the key node status information in the stored first data packet can be sent to the user layer, and then the user layer can calculate the average value of the key node status information of the same type in the first data packet to obtain the target key node information, for example, the average value of 10 error rates can be calculated to obtain the target error rate.

[0128] S1232, using the fault analysis model preset in the user layer, analyze the target key node status information to obtain the analysis result.

[0129] Specifically, at the user layer, by using a pre-configured fault analysis model to analyze the status information of each target key node, an analysis result of whether the target network node has an operation fault can be obtained.

[0130] The embodiment of the present application effectively reduces the amount of data required to be processed during the analysis process by calculating the average value of the same type of key node status information as the target key node information. Compared with directly analyzing each key node status information, analyzing the average value can significantly reduce the computing load, thereby saving computing resources. Subsequently, the target key node information is analyzed using a preset fault analysis model, which not only improves the analysis efficiency, but also ensures the accuracy and reliability of the analysis results, and can optimize resource usage while ensuring the accuracy of fault detection, so that the system can run more efficiently.

[0131] Figure 6 This is another flowchart of the method for determining the fault type provided in an embodiment of the present application.

[0132] In some embodiments, Figure 6 As shown, in step S120, the key node status information in the first data packet is analyzed using a preset fault analysis model, and before obtaining the analysis result, the method may further include steps S161 and S162.

[0133] S161, obtaining the full amount of historical node status information and historical fault type information of each network node within a preset time period.

[0134] Specifically, before using the preset fault analysis model for analysis, the preset fault analysis model can be obtained through supervised training. Before supervised training, the information of training samples and supervision results can be obtained, that is, all historical node status information of all network nodes in a specific historical time period and the information of the real historical fault types that have been determined can be collected.

[0135] S162, using the information of historical fault types as the supervision result and the full amount of historical node status information as the training sample, performing supervised training on the preset original fault analysis model to obtain a fault analysis model.

[0136] Specifically, historical fault type information is used as the expected output (i.e., supervision result), and the full amount of historical node status information is used as input data (i.e., training sample). The originally set original fault analysis model is trained under supervised guidance to optimize and calibrate the model parameters, and finally a trained fault analysis model that can accurately analyze the fault type is obtained.

[0137] The embodiment of the present application can significantly improve the accuracy and reliability of the fault analysis model by first collecting all historical node status information and historical fault type information before using the preset fault analysis model for analysis, and using this as training samples and supervision results to conduct supervised training on the original fault analysis model. This can ensure that the model can more accurately analyze key node status information in actual applications, thereby more effectively determining the fault type and improving the efficiency of fault detection and processing.

[0138] In some embodiments, the fault analysis model includes weight coefficients corresponding to each node status information; the weight coefficient corresponding to the key node status information is greater than or equal to a preset weight coefficient threshold; the weight coefficient corresponding to the basic node status information is less than a preset weight coefficient threshold.

[0139] The preset weight coefficient threshold is a preset numerical limit used to distinguish between key node status information and basic node status information. For example, the preset weight coefficient threshold may be 0.1, and for another example, the preset weight coefficient threshold may be 0.2. The preset weight coefficient threshold may be set as required, and the embodiments of the present application do not limit this.

[0140] Specifically, since the trained fault analysis model includes the weight coefficients corresponding to each node status information, the node status information with a weight coefficient greater than or equal to the preset weight coefficient threshold can be used as the key node status information, and the node status information with a weight coefficient less than the preset weight coefficient threshold can be used as the basic node status information. In other words, by comparing the weight coefficients of each node status information with the preset weight coefficient threshold, it is possible to select which ones belong to the key node status information and which ones belong to the basic node status information from the full amount of node status information.

[0141] It should be noted that the weight coefficient corresponding to the key node status information in the first data packet is greater than or equal to the preset weight coefficient threshold. The weight coefficient corresponding to the key node status information in the second data packet is greater than or equal to the preset weight coefficient threshold. The weight coefficient corresponding to the basic node status information in the second data packet is less than the preset weight coefficient threshold.

[0142] By setting a preset weight coefficient threshold, the embodiment of the present application can accurately filter out key information that is crucial to fault analysis from a large amount of node status information as a clear boundary, while excluding relatively minor information, thereby greatly improving data processing speed and analysis efficiency on the basis of ensuring analysis accuracy, and being able to respond to and handle network faults more quickly. And by inputting key node status information whose weight coefficient is greater than or equal to the preset weight coefficient threshold into a preset trained fault analysis model for fault analysis, compared to using all node status information, the amount of data processing can be reduced, and while ensuring accuracy, the analysis speed, efficiency and reliability of the results can be improved, thereby achieving an immediate response to network faults.

[0143] Figure 7 This is another flowchart of the method for determining the fault type provided in an embodiment of the present application.

[0144] In some embodiments, Figure 7 As shown, the method for determining the fault type may further include steps S171 and S172.

[0145] S171, obtaining a target solution corresponding to the fault type of the target network node in a preset correspondence relationship between the fault type and the solution.

[0146] Specifically, in the set mapping relationship between fault types and solutions, the solution corresponding to the fault type encountered by the target network node can be searched and determined, and the solution can be called a target solution.

[0147] S172, executing the target solution.

[0148] Specifically, it can be executed according to the target solution to solve the operation failure problem of the target network node.

[0149] The embodiment of the present application can automatically and quickly solve the operation failure problem of the target network node by quickly obtaining and executing the target solution corresponding to the failure type of the target network node in the preset correspondence between the failure type and the solution, thereby effectively improving the efficiency and accuracy of fault handling.

[0150] Figure 8 This is another flowchart of the method for determining the fault type provided in an embodiment of the present application.

[0151] In some embodiments, Figure 8 As shown, steps S173 and S174 are also included.

[0152] S173, obtaining the execution result of the target solution.

[0153] Specifically, obtaining the execution result of the target solution means collecting and evaluating the actual results or impacts of the target solution corresponding to the specific fault type after the solution is implemented to determine whether the problem is effectively solved or improved. For example, the execution result can be success or failure.

[0154] S174, on the target page, displaying information about the fault type of the target network node and information about the execution result of the target solution.

[0155] Specifically, on the target page, detailed information about the fault type of the target network node and the execution result information of the target solution implemented for the fault can be displayed, so that the user can understand the fault status and solution progress at a glance.

[0156] The embodiments of the present application not only ensure that users can timely understand the fault resolution status of the target network node by obtaining and displaying the execution results of the target solution, but also significantly improve the transparency and efficiency of the fault handling process, allowing users to quickly determine whether the fault is effectively handled, thereby accelerating the fault recovery process.

[0157] In one embodiment, the fault type determination system may include a data collection module, a data analysis module, a fault location module, a fault recovery module, and a result feedback module. Specifically:

[0158] 1) The data collection module is responsible for collecting node status information of network nodes at the kernel level. It can capture the first data packet of a network node (such as a network interface) by writing an eBPF program and record key performance indicators (key node status information).

[0159] For example: 1.1) Write an eBPF program to capture key node status information in the data packets of the network interface; 1.2) Use the eBPF map data structure to store the collected key node status information; 1.3) Periodically export the key node status information to the user layer for further analysis.

[0160] The data collection module sends the collected node status information to the data analysis module.

[0161] It should be noted that the data collection module in the related art uses the traditional Simple Network Management Protocol (SNMP) protocol or other network monitoring tools to collect the status information of network devices. The SNMP protocol is relatively mature and easy to integrate into the existing network management system, but the speed of SNMP data collection is slow, which may cause detection delays; and its flexibility and customization are not as good as eBPF technology. This application uses eBPF technology to collect node status information of network nodes at the kernel level, which can ensure the real-time and accuracy of information and significantly reduce the time delay of fault detection. By using the eBPF program, resource consumption can also be reduced to ensure that the overall performance of the system is not affected.

[0162] 2) Data analysis module, which performs real-time analysis on the key node status information received to identify whether there is a network operation failure at each target network node. Machine learning algorithms can be used to analyze the collected data to identify whether there is a network operation failure.

[0163] For example: supervised learning methods are used to train models to identify normal and abnormal network operation. Steps: 2.1) Data preprocessing: clean and standardize the collected data. 2.2) Feature extraction: extract meaningful features from the raw data. 2.3) Model training: use historical data to train the fault classification model. 2.4) Anomaly detection: apply the trained fault classification model in real time to detect abnormal behavior in the network. 2.5) Result output: after the data analysis module identifies the existence of an operation fault, it notifies the fault location module to locate it.

[0164] It should be noted that the related art uses the traditional threshold comparison method to directly perform fault diagnosis analysis, which does not require a complex model training process, but the accuracy of the single threshold comparison method is low, and it is easy to produce false positives or false negatives. The data analysis module of the embodiment of the present application combines the machine learning algorithm for intelligent analysis, which can realize intelligent analysis of collected data, quickly locate the cause and type of network failure, improve the accuracy and efficiency of fault detection, and reduce the false alarm rate.

[0165] 3) Fault location module: When a running fault is detected, the tracing capability of eBPF can be used to quickly locate the specific type of fault.

[0166] For example, the full node status information in the second data packet sent by the network node is obtained through the tracking function of eBPF. For example, by using the probe function of eBPF to track specific kernel function calls, detailed information of the target network node (such as full node status information) can be obtained to determine the specific fault type.

[0167] After the fault location module determines the specific fault type, it passes the relevant information to the fault recovery module.

[0168] It should be noted that the related art uses log analysis methods to locate faults, which are applicable to various types of faults and easy to implement, but the locating speed of the log analysis method is slow and requires a lot of manual analysis work. The embodiment of the present application uses the tracking function of eBPF to quickly locate the specific type of fault.

[0169] 4) Fault recovery module, which can execute corresponding recovery measures according to the fault type. A set of automatic recovery strategies can be designed in advance, such as redirecting traffic, restarting network components, etc.

[0170] For example, select the appropriate recovery strategy based on the fault type: use the eBPF program to update the network routing table or enable the backup link. Then send commands to the network nodes to perform recovery operations.

[0171] The fault recovery module performs the recovery operation and feeds the result back to the result feedback module.

[0172] It should be noted that the related art adopts a manual recovery mechanism, which allows administrators to flexibly adjust the recovery strategy according to specific circumstances. However, the manual recovery mechanism is inefficient, takes a long time to recover, and may cause service interruption. The embodiment of the present application adopts an automatic recovery strategy, such as redirecting traffic, restarting network components, etc., which can take action immediately after detecting a fault without manual intervention, greatly improving the recovery efficiency.

[0173] 5) Result feedback module, used to report the results of fault detection and recovery to the user or management system. The process of fault detection and recovery can be recorded and reported to the external system through the user interface or API.

[0174] For example, you can create log files to record the process of fault detection and recovery, and push the results to external systems through RESTful APIs.

[0175] The result feedback module reports the final fault detection and recovery status to the user or management system.

[0176] It should be noted that the related technology notifies the administrator by means of email or text messages, which are simple, practical and easy to implement, but have poor real-time performance and may not meet the needs of certain application scenarios. The embodiment of the present application supports flexible configuration of fault detection rules and recovery strategies by reporting the results of fault detection and recovery to the user or management system, and can be customized according to different network environments and needs.

[0177] The fault type determination system provided in the embodiment of the present application integrates data collection, analysis, positioning, recovery and result feedback modules, and uses eBPF technology and machine learning algorithms to achieve real-time detection, rapid positioning and automatic recovery of network faults of each target network node, greatly improving the efficiency and accuracy of network operation and maintenance, while supporting flexible configuration to meet the customized needs of different network environments. In other words, the embodiment of the present application not only solves the problems of low fault detection efficiency and untimely response in related technologies through real-time data collection and analysis. It also provides highly configurable fault detection rules and recovery strategies to enhance the flexibility of the system. An automated fault recovery mechanism is implemented to improve recovery efficiency. By optimizing the eBPF program, resource consumption is reduced and the overall performance of the system is improved. The use of machine learning algorithms for intelligent analysis reduces the false alarm rate.

[0178] Based on the same inventive concept, the embodiment of the present application also provides a device for determining a fault type, such as Fig. 9 As shown, the device 900 may include an acquisition module 910 , an analysis module 920 , and a determination module 930 .

[0179] The acquisition module 910 is used to acquire key node status information in the first data packet when the target network node sends the first data packet;

[0180] The analysis module 920 is used to analyze the key node status information in the first data packet using a preset fault analysis model to obtain an analysis result;

[0181] The acquisition module 910 is further configured to acquire key node status information and basic node status information in a second data packet sent by the target network node when the analysis result is an operation failure;

[0182] The determination module 930 is used to determine the fault type of the target network node according to the comparison result between the key node status information and the basic node status information in the second data packet and the corresponding preset thresholds.

[0183] In some embodiments, the determination module is used to determine the fault type of the target network node according to the comparison result between the key node status information and the basic node status information in the second data packet and the corresponding preset threshold value, and can be specifically used to:

[0184] Compare the key node status information and the basic node status information in the second data packet with the corresponding preset thresholds to obtain a target comparison result;

[0185] In the preset correspondence between the comparison result and the fault type, a target fault type corresponding to the target comparison result is obtained, and the target fault type is used as the fault type of the target network node.

[0186] In some embodiments, when the target network node sends a first data packet, before acquiring the key node status information in the first data packet, the device further includes a monitoring module:

[0187] A monitoring module, used to monitor target network nodes at the kernel layer using a preset packet filter;

[0188] The acquisition module is used to acquire key node status information in the first data packet when the target network node sends the first data packet, and can be specifically used to:

[0189] When the preset data packet filter detects that the target network node sends a first data packet, the preset data packet filter is used to obtain key node status information in the first data packet;

[0190] The acquisition module is used to acquire key node status information and basic node status information in the second data packet sent by the target network node when the analysis result is an operation failure, and can be specifically used to:

[0191] When the analysis result is an operation failure and the preset data packet filter detects that the target network node sends a second data packet, the preset data packet filter is used to obtain key node status information and basic node status information in the second data packet.

[0192] In some embodiments, the analysis module is used to analyze the key node status information in the first data packet using a preset fault analysis model to obtain an analysis result, which can be specifically used to:

[0193] Storing the key node status information in the first data packet according to a preset structure;

[0194] Sending the key node status information in the stored first data packet to the user layer according to a preset period;

[0195] The key node status information in the first data packet is analyzed using the fault analysis model preset in the user layer to obtain an analysis result.

[0196] In some embodiments, the analysis module is used to analyze the key node status information in the first data packet using a fault analysis model preset in the user layer to obtain an analysis result, which can be specifically used to:

[0197] Calculate the average value of the key node status information of the same type in the first data packet to obtain the target key node information;

[0198] The fault analysis model preset in the user layer is used to analyze the target key node status information to obtain the analysis results.

[0199] In some embodiments, before analyzing the key node status information in the first data packet using a preset fault analysis model to obtain an analysis result, the device may further include a training module:

[0200] The acquisition module is also used to obtain the full amount of historical node status information and historical fault type information of each network node within a preset period of time;

[0201] The training module is used to use the information of historical fault types as the supervision result and the full amount of historical node status information as the training sample to perform supervised training on the preset original fault analysis model to obtain the fault analysis model.

[0202] In some embodiments, the fault analysis model includes weight coefficients corresponding to each node status information; the weight coefficient corresponding to the key node status information is greater than or equal to a preset weight coefficient threshold; the weight coefficient corresponding to the basic node status information is less than a preset weight coefficient threshold.

[0203] In some embodiments, the execution module is also included:

[0204] An acquisition module, used to acquire a target solution corresponding to the fault type of the target network node in a preset correspondence relationship between the fault type and the solution;

[0205] Execution module, used to execute the target solution.

[0206] In some embodiments, a display module is further included:

[0207] The acquisition module is also used to obtain the execution results of the target solution;

[0208] The display module is used to display information about the fault type of the target network node and information about the execution result of the target solution on the target page.

[0209] Each module in the device for determining the fault type provided in the embodiment of the present application can realize Figures 1 to 8 The functions of each step of the provided method for determining the fault type and its ability to achieve the corresponding technical effects are not described in detail here for the sake of brevity.

[0210] Fig.10 A schematic diagram of the hardware structure of a device for determining a fault type provided in an embodiment of the present application is shown.

[0211] The device for determining the fault type may include a processor 1001 and a memory 1002 storing computer program instructions.

[0212] Specifically, the processor 1001 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0213] The memory 1002 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 1002 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 1002 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 1002 may be inside or outside of a device for determining the type of fault. In a particular embodiment, the memory 1002 is a non-volatile solid-state memory.

[0214] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of the present disclosure.

[0215] The processor 1001 implements any one of the methods for determining the fault type in the above embodiments by reading and executing computer program instructions stored in the memory 1002 .

[0216] In one example, the fault type determination device may further include a communication interface 1003 and a bus 1004. Fig.10 As shown, the processor 1001, the memory 1002, and the communication interface 1003 are connected via a bus 1004 and communicate with each other.

[0217] The communication interface 1003 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0218] The bus 1004 includes hardware, software or both, coupling the components of the fault type determination device to each other. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Linear Predictive Coding (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (Peripheral Component Interconnect-X, PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VESA Local Bus, VLB) bus or other suitable buses or a combination of two or more of these. Where appropriate, the bus 1004 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0219] The device can execute the method for determining the fault type in the embodiment of the present application based on each unit / component in the fault type determination device, thereby realizing the combination of Figures 1 to 7 Describes the method for determining the type of fault.

[0220] In addition, in combination with the method for determining the fault type in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the methods for determining the fault type in the above embodiment is implemented.

[0221] The present application also provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes each process of implementing any one of the above-mentioned fault type determination method embodiments.

[0222] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0223] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), appropriate firmware, plug-in, function card, etc. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or communication link by a data signal carried in a carrier. "Machine-readable medium" may include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memory (Read-Only Memory, ROM), flash memory, erasable read-only memory (Erasable Read Only Memory, EROM), floppy disks, compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical discs, hard disks, optical fiber media, radio frequency (Radio Frequency, RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0224] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0225] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0226] The above are only specific implementation methods of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for determining a fault type, characterized in that: include: When the target network node sends a first data packet, acquiring key node status information in the first data packet; Analyze the key node status information in the first data packet using a preset fault analysis model to obtain an analysis result; When the analysis result is an operation failure, obtaining key node status information and basic node status information in a second data packet sent by the target network node; The fault type of the target network node is determined according to a comparison result between the key node status information and the basic node status information in the second data packet and the corresponding preset thresholds.

2. The method according to claim 1, characterized in that The determining the fault type of the target network node according to a comparison result between the key node status information and the basic node status information in the second data packet and the corresponding preset thresholds includes: Compare the key node status information and the basic node status information in the second data packet with corresponding preset thresholds to obtain a target comparison result; In the preset correspondence between the comparison result and the fault type, a target fault type corresponding to the target comparison result is obtained, and the target fault type is used as the fault type of the target network node.

3. The method according to claim 1, characterized in that In the case where the target network node sends a first data packet, before acquiring the key node status information in the first data packet, the method further includes: Using preset packet filters, monitor the target network nodes at the kernel layer; The step of acquiring key node status information in a first data packet when the target network node sends the first data packet includes: When the preset data packet filter detects that the target network node sends a first data packet, using the preset data packet filter to obtain key node status information in the first data packet; When the analysis result is an operation failure, obtaining key node status information and basic node status information in a second data packet sent by the target network node includes: When the analysis result is an operation failure and the preset data packet filter detects that the target network node sends a second data packet, the preset data packet filter is used to obtain key node status information and basic node status information in the second data packet.

4. The method according to claim 3, characterized in that The method of analyzing the key node status information in the first data packet by using a preset fault analysis model to obtain an analysis result includes: Storing the key node status information in the first data packet according to a preset structure; Sending the key node status information stored in the first data packet to the user layer according to a preset period; The key node status information in the first data packet is analyzed using the fault analysis model preset in the user layer to obtain an analysis result.

5. The method according to claim 4, characterized in that The using of the fault analysis model preset in the user layer to analyze the key node status information in the first data packet to obtain the analysis result includes: Calculate the average value of the key node status information of the same type in the first data packet to obtain the target key node information; The target key node status information is analyzed using the fault analysis model preset in the user layer to obtain an analysis result.

6. The method according to claim 1, characterized in that Before analyzing the key node status information in the first data packet using the preset fault analysis model to obtain the analysis result, the method further includes: Obtain the full amount of historical node status information and historical fault type information of each network node within a preset period of time; The information of the historical fault types is used as the supervision result, and the full amount of historical node status information is used as the training sample, and the preset original fault analysis model is subjected to supervised training to obtain the fault analysis model.

7. The method according to claim 1, characterized in that The fault analysis model includes weight coefficients corresponding to the status information of each node; the weight coefficient corresponding to the status information of the key node is greater than or equal to the preset weight coefficient threshold; The weight coefficient corresponding to the basic node status information is less than the preset weight coefficient threshold.

8. The method according to any one of claims 1 to 7, characterized in that: Also includes: In the preset correspondence relationship between the fault type and the solution, obtaining the target solution corresponding to the fault type of the target network node; Execute the target solution.

9. The method according to claim 8, characterized in that Also includes: Obtaining the execution result of the target solution; On the target page, information about the fault type of the target network node and information about the execution result of the target solution are displayed.

10. A device for determining a fault type, characterized in that: include: An acquisition module, configured to acquire key node status information in a first data packet when a target network node sends the first data packet; An analysis module, used to analyze the key node status information in the first data packet using a preset fault analysis model to obtain an analysis result; The acquisition module is further used to acquire the key node status information and the basic node status information in the second data packet sent by the target network node when the analysis result is an operation failure; A determination module is used to determine the fault type of the target network node according to a comparison result between the key node status information and the basic node status information in the second data packet and the corresponding preset thresholds.

11. A device for determining a fault type, characterized in that: The device comprises: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the method for determining the fault type according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method for determining a fault type according to any one of claims 1 to 9 is implemented.

13. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of a device, the device is enabled to perform the method for determining a fault type according to any one of claims 1 to 9.

Images