Network fault node positioning method and device, electronic equipment and storage medium

Abstract

The invention relates to a network fault node positioning method and device, electronic equipment and a storage medium, and belongs to the technical field of node positioning, and the method comprises the steps: determining and marking network fault nodes from a plurality of network nodes of a space-ground integrated information network, and obtaining a digital list according to the marked network fault nodes; mining from the unmarked network nodes through a relevance mining algorithm to determine a first network fault node, marking the first network fault node, and updating the marked first network fault node into the digital list to obtain a first digital list; and storing the first digital list into a cache, and performing federated learning on the first digital list in the cache to obtain the maximum value of the network fault node in the plurality of network nodes. According to the method, the network fault nodes are determined and marked, the network fault nodes are mined, determined and marked from the unmarked network nodes, the whole solution space of the information network can be searched, and all the fault nodes in the space-ground integrated information network are obtained through federated learning.

Description

Technical Field

[0001] The present invention belongs to the technical field of network fault node positioning, and in particular relates to a network fault node positioning method and device. Background Art

[0002] The functions of nodes in the integrated space-ground information network are becoming increasingly complex, the management and control capabilities are constantly improving, and the amount of managed data is also growing. Traditional centralized storage technology has problems such as low performance, cost surge, and single point failure when dealing with large-scale data. When solving the unified management needs of massive network information and user information, we can refer to the advanced distributed file system (Hadoop Distributed File System, HDFS) on the ground. However, the fault alarms and performance alarms in the integrated space-ground information network are massive and cross-domain, so it is difficult to locate network faults. How to solve the difficulty of locating network faults is an urgent problem to be solved. Summary of the invention

[0003] In view of the above deficiencies in the prior art, the purpose of the invention is to provide a network fault node locating method, device, electronic device and storage medium, to determine the network fault node and mark it, to mine and determine the network fault node from unmarked network nodes and mark it, which can not only search the entire solution space of the information network, but also obtain all fault nodes in the integrated space-ground information network through federated learning.

[0004] A first aspect of the present invention provides a method for locating a network fault node, comprising:

[0005] Determine and mark network fault nodes from multiple network nodes of the space-ground integrated information network, and obtain a digital list based on the marked network fault nodes;

[0006] Mining from unmarked network nodes using a correlation mining algorithm to determine a first network fault node and marking it, and updating the marked first network fault node to the digital list to obtain a first digital list;

[0007] The first number list is stored in a cache, and federated learning is performed on the first number list in the cache to obtain a maximum value of network fault nodes among multiple network nodes.

[0008] Furthermore, in the above-mentioned method for locating a network fault node, determining and marking the network fault node from a plurality of network nodes of the space-ground integrated information network includes:

[0009] Obtain massive alarm events from the alarm information sources of the integrated space-ground information network;

[0010] After extracting massive alarm event vectors through principal component analysis, massive alarm events are mapped into principal component subspace and residual subspace;

[0011] Reduce the dimensions of the principal subspace and the residual subspace to determine whether the massive alarm events are multi-source and cross-domain alarm events. If the determination result is that they are not multi-source and cross-domain alarm events;

[0012] Extract key features of massive alarm events;

[0013] Select the features related to the network fault nodes from the key features;

[0014] Determine that a node corresponding to a feature related to a network fault node is a network fault node and mark it;

[0015] Among them, the sources of warning information of the integrated space-ground information network include at least: space-based network, ground network, information port and information service.

[0016] Furthermore, in the above-mentioned method for locating a network fault node, mining from unmarked network nodes by using a correlation mining algorithm to determine the first network fault node and marking it includes:

[0017] Performing association mining on the nodes through which the data of each marked network node passes through one by one using an association mining algorithm to determine the first network fault node that is not marked;

[0018] The first network fault node that is not marked is marked.

[0019] Furthermore, in the above-mentioned method for locating a network fault node, performing federated learning on the first digital list in the cache to obtain the maximum value of the network fault node among multiple network nodes includes:

[0020] Determine a transmission path based on the network fault node in the first digital list;

[0021] The transmission path is executed N times through federated learning until the maximum value of network failure nodes among multiple network nodes is obtained and the execution stops;

[0022] Wherein, N is a natural number greater than 1.

[0023] Furthermore, in the above-mentioned method for locating a network fault node, after reducing the dimensions of the principal component subspace and the residual subspace, the method further includes:

[0024] If the judgment result is that the alarm event is a multi-source, cross-domain alarm event;

[0025] Filtering, counting, compressing, generalizing, classifying and pattern matching the multi-source and cross-domain alarm events to obtain a first mass alarm event;

[0026] Extracting key features of the first massive alarm event;

[0027] Selecting features related to network fault nodes from key features of the first massive alarm event;

[0028] A node corresponding to the feature related to the network fault node is determined as a network fault node and marked.

[0029] Furthermore, in the above-mentioned method for locating a network fault node, mining from unmarked network nodes by using a correlation mining algorithm to determine the first network fault node and marking it also includes:

[0030] If the first network fault node is not determined by the association mining algorithm, the first network fault node is determined and marked by the uniform pool strategy.

[0031] Furthermore, in the above-mentioned method for locating a network fault node, determining and marking the first network fault node by using a uniform pool strategy includes:

[0032] Look up in the distributed hash table and calculate the Euclidean distance between each unmarked network node and the marked network failure node;

[0033] The network nodes with the closest Euclidean distance between the unmarked network nodes and the marked network failure nodes are stored in the uniform pool;

[0034] When there are multiple unmarked network nodes in the uniform pool whose Euclidean distances are equal to one of the marked network fault nodes, a first network fault node is determined from the multiple unmarked network nodes and marked.

[0035] A second aspect of the present invention further provides a network fault node location device, comprising:

[0036] Determination module: used to determine and mark network fault nodes from multiple network nodes of the integrated space-ground information network, and obtain a digital list based on the marked network fault nodes;

[0037] Mining module and updating module: used to mine and identify the first network fault node from the unmarked network nodes by using the association mining algorithm and mark it, and update the marked first network fault node to the digital list to obtain the first digital list;

[0038] Federated learning module: used to store the first number list in the cache, and perform federated learning on the first number list in the cache to obtain the maximum value of the network fault node.

[0039] According to a third aspect of the present invention, an electronic device is provided, comprising: a processor and a memory;

[0040] The processor is used to execute any one of the above network fault node location methods by calling the program or instruction stored in the memory.

[0041] In a fourth aspect of the present invention, a computer-readable storage medium is further proposed, wherein the computer-readable storage medium stores a program or instruction, and the program or instruction enables a computer to execute any one of the above methods for locating a network fault node.

[0042] The beneficial effects of the present invention are as follows: the present invention determines and marks network fault nodes from multiple network nodes of the integrated space-ground information network, and obtains a digital list based on the marked network fault nodes; determines and marks the first network fault node from the unmarked network nodes through the association mining algorithm, and updates the marked first network fault node to the digital list to obtain the first digital list; stores the first digital list in the cache, and performs federated learning on the first digital list in the cache to obtain the maximum value of the network fault nodes in multiple network nodes. The present invention determines and marks network fault nodes, and mines and determines network fault nodes from unmarked network nodes and marks them, which can not only search the entire solution space of the information network, but also obtain all fault nodes in the integrated space-ground information network through federated learning. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are only used to illustrate specific embodiments and are not considered to limit the present invention. In the entire drawings, the same reference symbols represent the same components. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0044] Figure 1 A diagram of a method for locating a network fault node provided by an embodiment of the present invention;

[0045] Figure 2 A method for determining and marking network fault nodes from multiple network nodes of a space-ground integrated information network provided by an embodiment of the present invention Figure 1 ;

[0046] Figure 3 A method diagram for determining and marking a first network fault node by mining through a correlation mining algorithm provided by an embodiment of the present invention;

[0047] Figure 4 A method diagram for obtaining the maximum value of network fault nodes among multiple network nodes through federated learning provided by an embodiment of the present invention;

[0048] Figure 5 A method for determining and marking network fault nodes from multiple network nodes of a space-ground integrated information network provided by an embodiment of the present invention Figure 2 ;

[0049] Figure 6 A method diagram for determining and marking a first network fault node through a uniform pool strategy provided by an embodiment of the present invention;

[0050] Figure 7 A diagram of a network fault node locating device provided by an embodiment of the present invention;

[0051] Figure 8 A schematic block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making creative work should fall within the scope of protection of the present invention.

[0053] Furthermore, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concepts disclosed in the present invention.

[0054] In the description of the present invention, the terms "first", "second", and "third" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be internal communication between two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0055] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of methods and systems consistent with some aspects of the present invention as detailed in the appended claims.

[0056] Before introducing the embodiments of the present invention, professional terms involved in the present invention are first introduced.

[0057] HDFS is a major component of the Hadoop project under the Apache Foundation. It is designed as a distributed file system suitable for running on commodity hardware. HDFS is a highly fault-tolerant system that can provide high-throughput data access and is very suitable for applications based on large-scale data sets.

[0058] The goal of the uniform pool strategy is to ensure that the algorithm can search the entire solution space and avoid the situation where a certain area is not searched because there is no solution distribution at present. From the perspective of ensuring population diversity, this strategy saves the nearest individuals of each reference point into a uniform pool, and the individuals in the pool participate in the evolution operation with the same probability as other individuals.

[0059] Federated machine learning (Federated Machine Learning / Federated Learning), also known as federated learning, joint learning, and alliance learning, is a machine learning framework that can effectively help multiple institutions use data and conduct machine learning modeling while meeting the requirements of user privacy protection, data security, and government regulations.

[0060] The present invention proposes a network fault node positioning method, device, electronic device and storage medium, which determine the network fault node and mark it, and mine and determine the network fault node from unmarked network nodes and mark it. It can not only search the entire solution space of the information network, but also obtain all fault nodes in the integrated space-ground information network through federated learning.

[0061] Method Embodiment

[0062] Figure 1 A diagram of a network fault node locating method provided by an embodiment of the present invention.

[0063] In the first aspect of the present invention, a method for locating a network fault node is proposed. Figure 1 , including three steps from S1 to S3:

[0064] S1: Determine and mark network fault nodes from multiple network nodes of the space-ground integrated information network, and obtain a digital list based on the marked network fault nodes.

[0065] Specifically, in an embodiment of the present invention, a method for determining and marking network fault nodes from multiple network nodes of a space-ground integrated information network is described in detail below, and a digital list is obtained based on the marked network fault nodes, and the digital list includes: the position of the marked network fault nodes in the space-ground integrated information network and the number of marked network fault nodes.

[0066] S2: Determine the first network fault node from the unmarked network nodes by using the association mining algorithm and mark it, and update the marked first network fault node into the digital list to obtain a first digital list.

[0067] Specifically, in an embodiment of the present invention, a method for determining and marking a first network fault node by mining from unmarked network nodes through a correlation mining algorithm is described in detail below. If the first network fault node is not mined through the correlation mining algorithm, the first network fault node is further determined and marked through a uniform pool strategy. The method for further determining and marking the first network fault node through a uniform pool strategy is described in detail below. The first digital list includes: the position of the marked network fault node in the integrated space-ground information network, the position of the first network fault node in the integrated space-ground information network, and the total number of marked network fault nodes.

[0068] S3: Storing the first number list in a cache, and performing federated learning on the first number list in the cache to obtain a maximum value of network fault nodes among multiple network nodes.

[0069] Specifically, in an embodiment of the present invention, the first digital list includes: the position of the marked network fault node in the integrated space-ground information network, the position of the first network fault node in the integrated space-ground information network, and the total number of marked network fault nodes. The first digital list is stored in a cache, and federated learning is performed on the first digital list in the cache to obtain the maximum value of the network fault nodes among multiple network nodes to ensure that all fault nodes in the integrated space-ground information network can be obtained. The method of performing federated learning on the first digital list in the cache to obtain the maximum value of the network fault nodes among multiple network nodes is described in detail below.

[0070] Figure 2 A method for determining and marking network fault nodes from multiple network nodes of a space-ground integrated information network provided by an embodiment of the present invention Figure 1 .

[0071] Furthermore, in the above-mentioned method for locating a network fault node, the network fault node is determined and marked from multiple network nodes of the integrated space-ground information network, and combined with Figure 2 , including six steps from S21 to S26:

[0072] S21: Obtain massive alarm events from the alarm information sources of the integrated space-ground information network.

[0073] Specifically, in the embodiment of the present invention, the sources of alarm information of the space-ground integrated information network include at least: space-based network, ground network, information port and information service.

[0074] S22: After extracting massive alarm event vectors through principal component analysis, the massive alarm events are mapped into principal component subspace and residual subspace.

[0075] Specifically, in the embodiment of the present invention, the principal component subspace contains main and real alarm information, and the residual subspace contains false alarms or erroneous alarms.

[0076] S23: reducing the dimensions of the principal element subspace and the residual subspace, and determining whether the massive alarm events are multi-source and cross-domain alarm events. If the determination result is that the massive alarm events are not multi-source and cross-domain alarm events,

[0077] Specifically, in an embodiment of the present invention, the dimensionality reduction processing of the principal component subspace and the residual subspace is performed in order to realize the extraction of key features. Before extracting the key features of massive alarm events, it is determined whether the massive alarm events are multi-source and cross-domain alarm events. If the judgment result is that they are not multi-source and cross-domain alarm events, the step of extracting key features is directly performed.

[0078] S24: Extract key features of massive alarm events.

[0079] Specifically, in the embodiment of the present invention, the key features of the extracted massive alarm events include not only network node failure features but also performance failure features and the like.

[0080] S25: Select features related to network fault nodes from the key features.

[0081] Specifically, in the embodiment of the present invention, features related to network fault nodes may be selected from key features through strategies such as keywords.

[0082] S26: Determine that a node corresponding to a feature related to the network fault node is a network fault node and mark it.

[0083] Specifically, in the embodiment of the present invention, a node corresponding to a feature related to a network fault node is determined as a network fault node and marked. The marking here may be by numbers or different colors.

[0084] Figure 3 A method diagram for determining and marking a first network fault node by mining through a correlation mining algorithm is provided in an embodiment of the present invention.

[0085] Furthermore, in the above-mentioned method for locating a network fault node, a first network fault node is determined and marked by mining from unmarked network nodes using a correlation mining algorithm, and combined with Figure 3 , including two steps from S31 to S32:

[0086] S31: performing association mining on the nodes through which the data of each marked network node passes through by using an association mining algorithm to determine the first network fault node that is not marked;

[0087] S32: Mark the unmarked first network fault node.

[0088] Specifically, in an embodiment of the present invention, after determining the network fault node, further mining is performed through a correlation mining algorithm to determine an unmarked first network fault node, where the association relationship is between a marked network fault node and an unmarked network node, and the unmarked first network fault node is marked. The first network fault node can be any unmarked network node.

[0089] Figure 4 A method diagram for obtaining the maximum value of network fault nodes among multiple network nodes through federated learning provided in an embodiment of the present invention.

[0090] Furthermore, in the above-mentioned method for locating a network fault node, a federated learning is performed on the first digital list in the cache to obtain the maximum value of the network fault node among multiple network nodes, and combined with Figure 4 , including two steps from S41 to S42:

[0091] S41: determining a transmission path according to the network fault node in the first digital list;

[0092] S42: executing the transmission path N times through federated learning until the maximum value of network fault nodes among multiple network nodes is obtained and then stopping the execution;

[0093] Wherein, N is a natural number greater than 1.

[0094] Specifically, in an embodiment of the present invention, the transmission path is executed N times through federated learning, so that unmarked network fault nodes are found and marked. Here, the maximum value is executed many times, but the maximum value of the network fault node does not change, then the execution is stopped.

[0095] Figure 5 A method for determining and marking network fault nodes from multiple network nodes of a space-ground integrated information network provided by an embodiment of the present invention Figure 2 .

[0096] Furthermore, in the above-mentioned method for locating a network fault node, after reducing the dimensions of the principal element subspace and the residual subspace, the Figure 5 , and also includes five steps from S51 to S55:

[0097] S51: If the judgment result is that the alarm event is a multi-source, cross-domain alarm event;

[0098] S52: Filter, count, compress, generalize, classify, and pattern match multi-source and cross-domain alarm events to obtain a first mass alarm event.

[0099] Specifically, in the embodiment of the present invention, multi-source and cross-domain alarm events are filtered, counted, compressed, generalized, classified and pattern matched, so as to be merged into a first massive alarm event with more information, thereby improving the efficiency of fault diagnosis.

[0100] S53: Extract key features of the first massive alarm event.

[0101] Specifically, in the embodiment of the present invention, the key features of the first massive alarm event with more information content are extracted, which include not only network node failure features but also performance failure features and the like.

[0102] S54: Selecting features related to network fault nodes from among the key features of the first massive alarm event.

[0103] Specifically, in the embodiment of the present invention, features related to network fault nodes may be selected from key features of the first massive alarm events by using strategies such as keywords.

[0104] S55: Determine that a node corresponding to a feature related to the network fault node is a network fault node and mark it.

[0105] Specifically, in the embodiment of the present invention, a node corresponding to a feature related to a network fault node is determined as a network fault node and marked. The marking here may be by numbers or different colors.

[0106] Furthermore, in the above-mentioned method for locating a network fault node, mining from unmarked network nodes by using a correlation mining algorithm to determine the first network fault node and marking it also includes:

[0107] If the first network fault node is not determined by the association mining algorithm, the first network fault node is determined and marked by the uniform pool strategy.

[0108] Specifically, the following describes a method for determining and marking the first network faulty node by using a uniform pool strategy in conjunction with steps S61 to S63.

[0109] Figure 6 A method diagram for determining and marking a first network faulty node through a uniform pool strategy is provided in an embodiment of the present invention.

[0110] Furthermore, in the above-mentioned method for locating a network fault node, the first network fault node is determined and marked by a uniform pool strategy, and combined with Figure 6 , including three steps from S61 to S63:

[0111] S61: Searching in the distributed hash table, calculating the Euclidean distance between each unmarked network node and the marked network fault node;

[0112] S62: save the network node whose Euclidean distance between the unmarked network node and the marked network fault node is closest in the uniform pool;

[0113] S63: When there are multiple unmarked network nodes in the uniform pool whose Euclidean distances are equal to one of the marked network fault nodes, a first network fault node is determined from the multiple unmarked network nodes and marked.

[0114] Specifically, in an embodiment of the present invention, after determining the network fault node, further mining is performed through a correlation mining algorithm to determine the network fault node. If the network fault node is not mined, the network fault node is determined and marked through a uniform pool strategy. The uniform pool strategy determines the network fault node. The uniform pool strategy is determined by the Euclidean distance between the unmarked network node and the marked network fault node. The first network fault node can be any unmarked network node.

[0115] Device Embodiment

[0116] Figure 7 A diagram of a network fault node locating device provided in an embodiment of the present invention.

[0117] A second aspect of the present invention further provides a network fault node location device, comprising:

[0118] Determination module 71: used to determine and mark network fault nodes from multiple network nodes of the integrated space-ground information network, and obtain a digital list based on the marked network fault nodes.

[0119] Specifically, in an embodiment of the present invention, the determination module 71 determines and marks the network fault nodes from multiple network nodes of the integrated space-ground information network, and obtains a digital list based on the marked network fault nodes, which includes: the position of the marked network fault nodes in the integrated space-ground information network and the number of the marked network fault nodes.

[0120] The mining module 72 and the updating module 73 are used to mine and identify the first network fault node from the unmarked network nodes by using the association mining algorithm and mark it, and update the marked first network fault node to the digital list to obtain the first digital list.

[0121] Specifically, in an embodiment of the present invention, the method in which the mining module 72 determines the first network fault node and marks it from the unmarked network nodes through the association mining algorithm is described in detail below. If the first network fault node is not mined through the association mining algorithm, the first network fault node is further determined and marked through the uniform pool strategy. The updating module 73 updates the marked first network fault node to the digital list to obtain a first digital list. The first digital list includes: the position of the marked network fault node in the integrated space-ground information network, the position of the first network fault node in the integrated space-ground information network, and the total number of marked network fault nodes.

[0122] The federated learning module 74 is used to store the first number list in a cache, and perform federated learning on the first number list in the cache to obtain the maximum value of the network fault node.

[0123] Specifically, in an embodiment of the present invention, the first digital list includes: the position of the marked network fault node in the integrated space-ground information network, the position of the first network fault node in the integrated space-ground information network, and the total number of marked network fault nodes. The first digital list is stored in the cache, and the federated learning module 74 performs federated learning on the first digital list in the cache to obtain the maximum value of the network fault nodes among multiple network nodes, ensuring that all fault nodes in the integrated space-ground information network can be obtained.

[0124] According to a third aspect of the present invention, an electronic device is provided, comprising: a processor and a memory;

[0125] The processor is used to execute any one of the above network fault node location methods by calling the program or instruction stored in the memory.

[0126] In a fourth aspect of the present invention, a computer-readable storage medium is further proposed, wherein the computer-readable storage medium stores a program or instruction, and the program or instruction enables a computer to execute any one of the above methods for locating a network fault node.

[0127] Figure 8 It is a schematic block diagram of an electronic device provided by an embodiment of the present invention.

[0128] like Figure 8 As shown, the electronic device includes: at least one processor 801, at least one memory 802 and at least one communication interface 803. The various components in the electronic device are coupled together through a bus system 804. The communication interface 803 is used to transmit information between external devices. It can be understood that the bus system 804 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 804 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 8Various buses are labeled as bus system 804 .

[0129] It can be understood that the memory 802 in this embodiment can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0130] In some implementations, the memory 802 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system and application programs.

[0131] The operating system includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application includes various application programs, such as a media player (Media Player), a browser (Browser), etc., which are used to implement various application services. A program that implements any method of a network fault node location method provided in an embodiment of the present invention can be included in the application.

[0132] In an embodiment of the present invention, the processor 801 calls a program or instruction stored in the memory 802, specifically, a program or instruction stored in an application, and the processor 801 is used to execute the steps of each embodiment of a network fault node location method provided in an embodiment of the present invention.

[0133] Determine and mark network fault nodes from multiple network nodes of the space-ground integrated information network, and obtain a digital list based on the marked network fault nodes;

[0134] Mining from unmarked network nodes using a correlation mining algorithm to determine a first network fault node and marking it, and updating the marked first network fault node to the digital list to obtain a first digital list;

[0135] The first number list is stored in a cache, and federated learning is performed on the first number list in the cache to obtain a maximum value of network fault nodes among multiple network nodes.

[0136] Any method in a network fault node location method provided in an embodiment of the present invention can be applied to the processor 801, or implemented by the processor 801. The processor 801 can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 801 or an instruction in the form of software. The above processor 801 can be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0137] The steps of any method in a method for locating a network fault node provided by an embodiment of the present invention can be directly embodied as being executed by a hardware decoding processor, or being executed by a combination of hardware and software units in the decoding processor. The software unit can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 802, and the processor 801 reads the information in the memory 802 and completes the steps of the method in combination with its hardware.

[0138] Those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features from different embodiments is meant to be within the scope of the present invention and to form different embodiments.

[0139] Those skilled in the art will appreciate that the description of each embodiment has its own emphasis, and for parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0140] Although the embodiments of the present invention are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims. The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of various equivalent modifications or substitutions within the technical scope disclosed by the present invention, and these modifications or substitutions should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

[0141] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for locating a network fault node, characterized in that: include: Determine and mark network fault nodes from multiple network nodes of the space-ground integrated information network, and obtain a digital list based on the marked network fault nodes; Mining from unmarked network nodes using a correlation mining algorithm to determine a first network fault node and marking it, and updating the marked first network fault node to the digital list to obtain a first digital list; The first number list is stored in a cache, and federated learning is performed on the first number list in the cache to obtain a maximum value of network fault nodes among multiple network nodes.

2. A method for locating a network fault node according to claim 1, characterized in that: The determining and marking of network fault nodes from a plurality of network nodes in the integrated space-ground information network includes: Obtain massive alarm events from the alarm information sources of the integrated space-ground information network; After extracting massive alarm event vectors through principal component analysis, massive alarm events are mapped into principal component subspace and residual subspace; Reduce the dimensions of the principal subspace and the residual subspace to determine whether the massive alarm events are multi-source and cross-domain alarm events. If the determination result is that they are not multi-source and cross-domain alarm events; Extract key features of massive alarm events; Select the features related to the network fault nodes from the key features; Determine that a node corresponding to the characteristic related to the network fault node is a network fault node and mark it; Among them, the sources of warning information of the integrated space-ground information network include at least: space-based network, ground network, information port and information service.

3. A method for locating a network fault node according to claim 1, characterized in that: The step of mining from unmarked network nodes by using a correlation mining algorithm to determine the first network fault node and marking it includes: Performing association mining on the nodes through which the data of each marked network node passes through one by one using an association mining algorithm to determine the first network fault node that is not marked; The first network fault node that is not marked is marked.

4. A method for locating a network fault node according to claim 1, characterized in that: The step of performing federated learning on the first digital list in the cache to obtain a maximum value of network fault nodes among a plurality of network nodes includes: Determine a transmission path based on the network fault node in the first digital list; The transmission path is executed N times through federated learning until the maximum value of network failure nodes among multiple network nodes is obtained and the execution stops; Wherein, N is a natural number greater than 1.

5. A method for locating a network fault node according to claim 2, characterized in that: After reducing the dimensions of the principal component subspace and the residual subspace, the method further includes: If the judgment result is that the alarm event is a multi-source, cross-domain alarm event; Filtering, counting, compressing, generalizing, classifying and pattern matching the multi-source and cross-domain alarm events to obtain a first mass alarm event; Extracting key features of the first massive alarm event; Selecting features related to network fault nodes from key features of the first massive alarm event; A node corresponding to the feature related to the network fault node is determined as a network fault node and marked.

6. A method for locating a network fault node according to claim 1, characterized in that: The method of mining from unmarked network nodes by using a correlation mining algorithm to determine the first network fault node and marking it also includes: If the first network fault node is not determined by the association mining algorithm, the first network fault node is determined and marked by the uniform pool strategy.

7. A method for locating a network fault node according to claim 6, characterized in that: The step of determining and marking the first network fault node by using a uniform pool strategy includes: Look up in the distributed hash table and calculate the Euclidean distance between each unmarked network node and the marked network failure node; The network nodes with the closest Euclidean distance between the unmarked network nodes and the marked network failure nodes are stored in the uniform pool; When there are multiple unmarked network nodes in the uniform pool whose Euclidean distances are equal to one of the marked network fault nodes, a first network fault node is determined from the multiple unmarked network nodes and marked.

8. A network fault node location device, characterized in that: include: Determination module: used to determine and mark network fault nodes from multiple network nodes of the integrated space-ground information network, and obtain a digital list based on the marked network fault nodes; Mining module and updating module: used to mine and identify the first network fault node from the unmarked network nodes by using the association mining algorithm and mark it, and update the marked first network fault node to the digital list to obtain the first digital list; Federated learning module: used to store the first digital list in a cache, and perform federated learning on the first digital list in the cache to obtain the maximum value of the network fault node.

9. An electronic device, characterized in that: include: Processor and memory; The processor is used to execute a network fault node locating method as described in any one of claims 1 to 7 by calling the program or instruction stored in the memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program or instruction, and the program or instruction enables a computer to execute a network fault node location method as described in any one of claims 1 to 7.

Images