Network node positioning method, apparatus, device, and medium

Abstract

Embodiments of the present application provide a network node positioning method, device, equipment and medium. In a case where it is determined that a sudden event affecting network operation exists, a weight matrix and local station positions of N local stations are obtained. For the qth local station, an event influence degree of the qth local station is determined based on M weights associated with the qth local station in the weight matrix. An event occurrence area of the sudden event is determined by clustering K local stations according to the local station positions of the K local stations. A target network node is positioned from J network abnormal nodes. Embodiments of the present application improve the positioning efficiency of network nodes that need to be repaired as soon as possible.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of network node positioning, and particularly relates to a network node positioning method, device, equipment and medium. BACKGROUND

[0002] In the existing network management mode, since different types of network resources are relatively independent, when a sudden event such as flood disaster, strong wind invasion, construction excavation, etc. causes an impact on network operation, the range of influence is relatively wide.

[0003] In order to restore normal network operation as soon as possible, in the prior art, the network nodes affected by the above-mentioned sudden events are analyzed and positioned in an offline collaborative manner, so as to repair the network of the network nodes. However, in the prior art, the positioning efficiency of the network nodes affected by the above-mentioned sudden events is low. SUMMARY

[0004] The embodiments of the application provide a network node positioning method, device, equipment and medium, and the positioning efficiency of the network nodes that need to be repaired as soon as possible is improved.

[0005] In a first aspect, the embodiments of the application provide a network node positioning method, and the method comprises the following steps.

[0006] In a case where it is determined that there is a sudden event affecting network operation, a weight matrix and local station positions of N local stations are obtained, the weight matrix is an M-row and N-column matrix, a weight in the pth row and qth column of the weight matrix is used to represent the importance of a pth network abnormal node to a qth local station, p = 1, 2, …, M, q = 1, 2, …, N, and M and N are positive integers;

[0007] For the qth local station, an event influence degree of the qth local station is determined based on M weights associated with the qth local station in the weight matrix, and the event influence degree of the qth local station represents the degree of influence of the qth local station by the sudden event;

[0008] An event occurrence region of the sudden event is determined by clustering K local stations according to the local station positions of the K local stations, the K local stations include local stations with an event influence degree greater than a preset influence degree threshold value selected from the N local stations, the event occurrence region includes J network abnormal nodes, K is a positive integer less than or equal to N, and J is a positive integer less than or equal to M;

[0009] A target network node is determined from the J network abnormal nodes, and the target network node is a network node with the greatest influence on network operation in the J network abnormal nodes.

[0010] In an optional implementation of the first aspect, before the weight matrix and the local station positions of the N local stations are obtained, the method further comprises the following steps.

[0011] monitoring network running data of each network node in the plurality of network nodes in real time;

[0012] determining M network anomaly nodes from the plurality of network nodes, wherein the network running data of the M network anomaly nodes does not conform to a first preset rule, and determining N local stations associated with the M network anomaly nodes.

[0013] In an optional implementation of the first aspect, the weight matrix is obtained, comprising:

[0014] for the pth network anomaly node in the M network anomaly nodes, determining a resource type of a resource carried by the pth network anomaly node, and belonging information between the pth network anomaly node and the N local stations respectively;

[0015] based on the resource type of the resource carried by the pth network anomaly node and the belonging information between the pth network anomaly node and the N local stations respectively, determining a weight of the pth network anomaly node to each local station in the N local stations according to a second preset rule, to obtain the weight matrix.

[0016] In an optional implementation of the first aspect, for the qth local station, determining an event influence degree of the qth local station based on M weights associated with the qth local station in the weight matrix, comprising:

[0017] determining a sum of the M weights associated with the qth local station in the weight matrix as a first value;

[0018] based on the second value, determining the event influence degree of the qth local station, the second value comprising a ratio between the first value and a number of network anomaly nodes.

[0019] In an optional implementation of the first aspect, according to local station positions of K local stations, determining an event occurrence region of the emergency event by clustering the K local stations, comprising:

[0020] for each local station in the K local stations, taking the local station position of the local station as a center, and determining a circular region corresponding to the local station according to a preset radius, and determining a number of local stations in the circular region;

[0021] in a case where the number of local stations is greater than or equal to a preset density threshold, determining the local station as a core local station, to obtain at least one core local station;

[0022] determining the circular region corresponding to the at least one core local station as the event occurrence region of the emergency event.

[0023] In an optional implementation of the first aspect, before determining the target network node from the J network anomaly nodes, the method further comprises:

[0024] constructing a directed graph of the event occurrence region, the directed graph being used to represent transmission relationships of network links between the J network anomaly nodes in the event occurrence region, the directed graph comprising the J network anomaly nodes and at least one directed edge used to connect any two of the J network anomaly nodes;

[0025] determining, for each of the J network anomaly nodes, a number of first directed edges and a number of second directed edges, the first directed edge being a directed edge of the at least one directed edge whose terminal point is the network anomaly node, and the second directed edge being a directed edge of the at least one directed edge whose starting point is the network anomaly node;

[0026] determining a target network node from the J network anomaly nodes, comprising:

[0027] determining, for each of the J network anomaly nodes, a sum of the number of first directed edges and the number of second directed edges corresponding to the network anomaly node as a first centrality of the network anomaly node;

[0028] determining a node with a maximum first centrality from the J network anomaly nodes as the target network node.

[0029] In an optional implementation of the first aspect, the target network node is determined from the J network anomaly nodes, comprising:

[0030] determining, for each of the J network anomaly nodes, a sum of the number of first directed edges and the number of second directed edges corresponding to the network anomaly node as a first centrality of the network anomaly node;

[0031] determining a ratio between the first centrality of the network anomaly node and a preset value as a second centrality of the network anomaly node, the preset value being determined based on a number of nodes of the J network anomaly nodes;

[0032] determining a node with a maximum second centrality from the J network anomaly nodes as the target network node.

[0033] In a second aspect, an embodiment of the present application provides a network node positioning device, the device comprising:

[0034] an obtaining module, configured to, in a case where it is determined that a sudden event affecting network operation exists, obtain a weight matrix and local station positions of N local stations, the weight matrix being an M-row-by-N-column matrix, a weight in a pth row and a qth column of the weight matrix being used to represent an importance degree of a pth network anomaly node to a qth local station, p = 1, 2, …, M, q = 1, 2, …, N, M and N being positive integers;

[0035] The determining module is configured to determine, for the qth local station, an event influence degree of the qth local station based on M weights associated with the qth local station in the weight matrix, the event influence degree of the qth local station representing a degree of influence of the qth local station by the emergency event;

[0036] The clustering module is configured to determine an event occurrence region of the emergency event by clustering the K local stations according to local station positions of the K local stations, the K local stations including local stations with event influence degrees greater than a preset influence degree threshold and selected from the N local stations, the event occurrence region including J network abnormal nodes, K is a positive integer less than or equal to N, and J is a positive integer less than or equal to M.

[0037] The determining module is further configured to determine a target network node from the J network abnormal nodes, the target network node being a network node with the greatest influence on network operation among the J network abnormal nodes.

[0038] In a third aspect, an electronic device is provided, including: a memory configured to store computer program instructions; and a processor configured to read and run the computer program instructions stored in the memory to execute the network node positioning method provided in any of the optional implementation manners of the first aspect.

[0039] In a fourth aspect, a computer storage medium is provided, and the computer storage medium stores computer program instructions. When the computer program instructions are executed by a processor, the network node positioning method provided in any of the optional implementation manners of the first aspect is implemented.

[0040] In a fifth aspect, a computer program product is provided, and the computer program product includes a computer program. When the computer program is executed by a processor, the network node positioning method provided in any of the optional implementation manners of the first aspect is implemented.

[0041] In the embodiment of the present application, in the case that it is determined that there is a sudden event affecting the network operation, the weight matrix and the station positions of the N stations can be obtained, the weight matrix is a matrix of M rows and N columns, and the weight in the pth row and the qth column of the weight matrix is used to represent the importance degree of the pth network abnormal node to the qth station, where p=1, 2, …, M, q=1, 2, …, N, M and N are positive integers. Based on this, considering that the network node itself does not have a spatial geographic attribute, that is, the network node does not have a geographic position, for the qth station, the event influence degree of the qth station is determined based on the M weights associated with the qth station in the weight matrix. Since the K stations include the stations whose event influence degrees are greater than the preset influence degree threshold selected from the N stations, that is, the K stations are determined from the N stations that are greatly affected by the sudden event, and then the event occurrence area of the sudden event is determined by clustering the K stations according to the station positions of the K stations, and since the event occurrence area includes the J network abnormal nodes, the network node with the greatest impact on the network operation can be located from the J network abnormal nodes. In this way, not only can the station positions of the multiple stations greatly affected by the sudden event be clustered to accurately and quickly locate the event occurrence area of the sudden event, but also the network node that needs to be repaired as soon as possible can be accurately and quickly determined from the network abnormal nodes in the event occurrence area, thereby improving the positioning efficiency of the network node that needs to be repaired as soon as possible. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments of the present application will be briefly introduced below. Those skilled in the art can also obtain other drawings according to these drawings without creating any creative labor.

[0043] Figure 1 is one of the flowcharts of the network node positioning method provided by the embodiments of the present application;

[0044] Figure 2 is another flowchart of the network node positioning method provided by the embodiments of the present application;

[0045] Figure 3 is a third flowchart of the network node positioning method provided by the embodiments of the present application;

[0046] Figure 4 is a fourth flowchart of the network node positioning method provided by the embodiments of the present application;

[0047] Figure 5 is a fifth flowchart of the network node positioning method provided by the embodiments of the present application;

[0048] Figure 6is a structural schematic diagram of a network node positioning device provided by an embodiment of the present application.

[0049] Figure 7 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0050] The features and exemplary embodiments of various aspects of the present application will be described in detail below with reference to the drawings. To make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, but not to limit the present application. The present application can be implemented without some of the specific details by those skilled in the art. The following description of the embodiments is only to provide a better understanding of the present application by showing examples of the present application.

[0051] It should be noted that, in this document, relational terms such as first and second and the like can only be used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or apparatus that includes a list of elements does not only include those elements, but also includes other elements not explicitly listed or other elements inherent to such process, method, article or apparatus. Without more limitations, an element defined by the phrase "comprising a" does not exclude the existence of additional identical elements in the process, method, article or apparatus that includes the element.

[0052] In this document, the term "and / or" is only used to describe the associated relationship of associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the existence of A alone, the existence of A and B together, and the existence of B alone.

[0053] In the existing network management mode, different types of network resources are relatively independent. When sudden events such as flood disasters, strong wind attacks, and construction excavation cause impact on network operation, the scope of influence is wide.

[0054] In the existing network management mode, the current communication network resources can be divided into three categories and 11 subtypes according to functions, which can be shown in Table 1 as follows:

[0055] Table 1 Type division of communication network resources

[0056] Base Specialty Space, Public, Transmission, Motion Support Specialty Core Network, Content Network, Bearing Network Business Specialty Home Guest, Gather Guest, IDC, Network Cloud

[0057] Based on this, in order to restore normal network operation as soon as possible, taking the example of heavy rain in A area causing multiple machine rooms in A area to be flooded, power supply interruption leading to large area machine room power failure, transmission interruption, base station service stop, etc., the existing technology processing flow is as follows:

[0058] Step 1: Monitor and collect network operation data: For dynamic environment, transmission, wireless and other network resources, monitoring systems, sensors, network monitoring tools, etc. can be used to collect and detect network operation related data, including network traffic, device status, network connection, environmental parameters, etc. When heavy rain causes multiple machine rooms to be flooded, not only will the network nodes affected will be impacted, but the operation of other network nodes associated with the network nodes will also be impacted, so maintenance personnel will find that various types of network resource related large area network operation data are abnormal through monitoring tools.

[0059] Step 2: Locate the area where the incident occurred: When a sudden event impacts network operation, the scope of the impact is wide, and it is difficult to analyze and locate it only by relying on network operation data. Communication operators usually cooperate with local governments, disaster management agencies, etc. to understand the disaster area and the extent of the disaster, collect external geological, meteorological and other data, and analyze and locate the area where the incident occurred.

[0060] Step 3: Locate the affected network nodes: After determining the area where the incident occurred, personnel will be dispatched to conduct on-site investigation to check the damage to network facilities and coordinate to locate the affected network nodes. This may involve checking communication towers, transmission lines, optical fiber cables, equipment rooms, etc.

[0061] Step 4: Evaluate network service interruption: By locating the affected network junction, combined with the association between network resources and business bearing, the scope and degree of service interruption are evaluated. This may include telephone service, mobile communication, broadband Internet, etc.

[0062] Step 5: Determine the priority recovery area: According to the evaluation results of network service interruption, determine the priority recovery area and service. This may include emergency rescue centers, medical institutions, important infrastructure, etc.

[0063] Step 6: Repair key network nodes and restore key services.

[0064] In summary, in the above manner, the shared data relies on external units such as the government and disaster management agencies, and the timeliness of information acquisition is poor, so that when the network operation is impacted, the event occurrence area of the sudden event cannot be located in time, and further, the efficiency of locating the network nodes affected by the sudden event is poor. Moreover, in the process of locating the network nodes affected by the sudden event, it is also necessary to locate through offline cooperation such as on-site investigation, so that the efficiency of locating the network nodes affected by the sudden event is low.

[0065] Therefore, in order to solve the above problems, the embodiment of the present application provides a network node positioning method, device, equipment and medium. In the case where it is determined that there is a sudden event affecting network operation, the weight matrix and the station positions of N stations can be obtained. The weight matrix is an M-row and N-column matrix, and the weight of the pth row and qth column in the weight matrix is used to represent the importance of the pth network abnormal node to the qth station, where p = 1, 2, …, M, q = 1, 2, …, N, and M and N are positive integers. Based on this, considering that the network node itself does not have spatial geographic attributes, that is, the network node does not have a geographic position, for the qth station, the event influence degree of the qth station is determined based on the M weights associated with the qth station in the weight matrix. Since the K stations include the stations with an event influence degree greater than a preset influence degree threshold selected from the N stations, that is, the K stations with a greater influence of the sudden event are determined from the N stations, and then the event occurrence area of the sudden event is determined by clustering the K stations according to the station positions of the K stations. Since the event occurrence area includes J network abnormal nodes, the network node with the greatest impact on network operation can be located from the J network abnormal nodes. In this way, the station positions of the multiple stations with a greater influence of the sudden event can be clustered to accurately and quickly locate the event occurrence area of the sudden event, and then the network node that needs to be repaired as soon as possible can be accurately and quickly determined from the network abnormal nodes in the event occurrence area, and the positioning efficiency of the network node that needs to be repaired as soon as possible is improved.

[0066] It should be noted that the network node positioning method provided by the embodiment of the present application can be executed by a network node positioning device or a control module in the network node positioning device for executing the network node positioning method. In the embodiment of the present application, the network node positioning device executes the network node positioning method as an example to illustrate the network node positioning method provided by the embodiment of the present application.

[0067] The network node positioning method provided by the embodiment of the present application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0068] Figure 1 is a flowchart of a network node positioning method provided by the embodiment of the present application.

[0069] As shown in the method, the execution subject can be a network node positioning device. Based on this, the method can specifically include the following steps. Figure 1

[0070] S110, in the case where it is determined that there is a sudden event affecting the operation of the network, obtaining a weight matrix and station positions of N stations.

[0071] Wherein, the above-mentioned sudden event refers to an event that can affect the normal operation of the network, for example, flood disaster, strong wind invasion and construction excavation, etc. Herein, no specific limitation is made. In addition, the station positions of the above-mentioned N stations can be the geographical positions of the N stations respectively, wherein N is a positive integer, herein no specific limitation is made.

[0072] In some embodiments, the above-mentioned weight matrix can be an M-row and N-column matrix, the weight of the pth row and the qth column in the weight matrix is used to represent the importance of the pth network abnormal node to the qth station, p=1, 2, …, M, q=1, 2, …, N, M, N are positive integers.

[0073] Specifically, in the case where it is determined that there is a sudden event affecting the operation of the network, that is, when the sudden event has an impact on the operation of the communication network, the network node positioning device can obtain a weight matrix representing the importance of each network abnormal node in M network abnormal nodes to each station in N stations, and the station positions of the N stations.

[0074] In one example, the above-mentioned weight matrix M UL may be as shown in the following formula (1):

[0075]

[0076] Wherein, M is the number of network abnormal nodes, N is the number of stations. a p,q is a weight, used to represent the importance of the pth network abnormal node to the qth station. It should be noted that, the larger a p,q , the more important the pth network abnormal node to the qth station, and vice versa, no more description.

[0077] S120, for the qth station, based on the M weights associated with the qth station in the weight matrix, determining the event influence degree of the qth station.

[0078] In some embodiments, the event influence degree of the qth station is used to represent the degree of influence of the qth station by the sudden event.

[0079] ​Specifically, since the weight matrix is an M-row and N-column matrix, and the weight in the pth row and qth column of the weight matrix is used to represent the importance of the pth network anomaly node to the qth local station, it can be known that M is the number of network anomaly nodes, and N is the number of local stations.

[0080] Based on this, for the qth local station, there are M weights of the M network anomaly nodes to the qth local station in the weight matrix, so that the network node positioning device can determine the event influence degree of the qth local station based on the M weights associated with the qth local station in the weight matrix, so that the event occurrence region of the sudden event can be determined through the local station positions of the local stations affected by the sudden event. And since q = 1, 2, …, N, the network node positioning device can obtain the event influence degree of each of the N local stations.

[0081] S130, according to the local station positions of the K local stations, the event occurrence region of the sudden event is determined by clustering the K local stations.

[0082] In some embodiments, the K local stations include local stations whose event influence degrees are greater than a preset influence degree threshold selected from the N local stations, and K is a positive integer less than or equal to N. Wherein, the preset influence degree threshold can be set in advance based on actual experience or situation, for example, the preset influence degree threshold can be set to 0.6, which is not limited here.

[0083] Here, considering that the network node itself does not have a spatial geographic attribute, that is, the network node does not have a geographic position, based on this, after the network node positioning device obtains the event influence degree of each of the N local stations, the network node positioning device can first select K local stations whose event influence degrees are greater than a preset influence degree threshold from the N local stations based on the event influence degree of each of the N local stations, that is, determine the local stations that are greatly affected by the sudden event among the N local stations, and then the event occurrence region of the sudden event can be determined by clustering the K local stations according to the local station positions of the K local stations.

[0084] It should be noted that the event occurrence region involved above can include J network anomaly nodes, and J is a positive integer less than or equal to M, which is not limited here.

[0085] S140, positioning a target network node from the J network anomaly nodes.

[0086] In some embodiments, the target network node involved above can be the network node that has the greatest impact on network operation among the J network anomaly nodes, or it can be understood that the target network node can be the network node that needs to be repaired first among all network anomaly nodes, which is not limited here.

[0087] Specifically, after the network node positioning apparatus can determine the event occurrence region of the emergency event, since the event occurrence region can include J network abnormal nodes, the network node positioning apparatus can locate the network node with the greatest impact on network operation from the J network abnormal nodes, that is, determine the network node most in need of being repaired in priority from the J network abnormal nodes.

[0088] In one example, in the process of locating the target network node from the J network abnormal nodes, the target network node with the greatest preset priority can be determined from the J network abnormal nodes based on the respective preset priorities of the J network abnormal nodes. The preset priority can be set in advance based on actual experience or circumstances, which is not limited here.

[0089] In the embodiments of the present application, in the case where it is determined that there is an emergency event affecting network operation, the weight matrix and the station positions of the N stations can be obtained. The weight matrix is an M-row and N-column matrix, and the weight in the pth row and qth column of the weight matrix is used to represent the importance of the pth network abnormal node to the qth station, where p = 1, 2, …, M, q = 1, 2, …, N, and M and N are positive integers. Based on this, considering that the network node itself does not have spatial geographic attributes, that is, the network node does not have a geographic position, for the qth station, the event influence degree of the qth station is determined based on the M weights associated with the qth station in the weight matrix. Since the K stations include the stations with an event influence degree greater than a preset influence degree threshold selected from the N stations, that is, the K stations are determined from the N stations that are more affected by the emergency event, and then the event occurrence region of the emergency event is determined by clustering the K stations according to the station positions of the K stations, and since the event occurrence region includes J network abnormal nodes, the network node with the greatest impact on network operation can be located from the J network abnormal nodes. In this way, not only can the station positions of the multiple stations more affected by the emergency event be clustered to accurately and quickly locate the event occurrence region of the emergency event, but also the network node that needs to be repaired as soon as possible can be accurately and quickly determined from the network abnormal nodes in the event occurrence region, thereby improving the positioning efficiency of the network node that needs to be repaired as soon as possible.

[0090] Since the weight matrix provided by the embodiments of the present application can be used to represent the importance of each network abnormal node to each station, before obtaining the weight matrix and the station positions of the N stations, the network abnormal nodes affected by the emergency event and the stations associated with the network abnormal nodes need to be determined. Based on this, in one embodiment, before obtaining the weight matrix and the station positions of the N stations, the network node positioning method described above can further include the following steps:

[0091] monitor network running data of each network node in the plurality of network nodes in real time;

[0092] determine M network anomaly nodes in which network running data does not conform to the first preset rule from the plurality of network nodes, and determine N stations associated with the M network anomaly nodes.

[0093] The first preset rule can be a rule for judging whether the network running data is abnormal, which is set in advance based on actual experience or situation, and is not limited herein.

[0094] In addition, the N stations associated with the M network anomaly nodes can include the respective belonging stations of the M network anomaly nodes, or the N stations associated with the M network anomaly nodes can include all stations in the area where the M network anomaly nodes are located, and is not limited herein.

[0095] Specifically, in the case that the emergency event has an impact on the operation of the passing network, the network node positioning device can monitor network running data of each network node in the plurality of network nodes in real time, and for each network running data, determine whether each network running data conforms to the first preset rule. If not, the network node corresponding to the network running data is determined as an anomaly network node. In this way, M network anomaly nodes in which network running data does not conform to the first preset rule can be determined from the plurality of network nodes, and N stations associated with the M network anomaly nodes can be determined.

[0096] In this embodiment, in the case that the emergency event has an impact on the operation of the passing network, network running data of each network node in the plurality of network nodes can be monitored in real time, and the network anomaly nodes in the plurality of network nodes and the plurality of stations associated with the network anomaly nodes can be determined by judging whether the network running data of each network node is abnormal network running data, thereby improving the accuracy of the network anomaly nodes and the stations associated with the network anomaly nodes.

[0097] Based on this, after determining the M network anomaly nodes, in one embodiment, as shown in Figure 2 The step of obtaining the weight matrix can specifically include the following steps:

[0098] S210, for a pth network anomaly node in the M network anomaly nodes, determine a resource type of a resource carried by the pth network anomaly node, and belonging information between the pth network anomaly node and the N stations.

[0099] The resource type of the resource can include a space, a public, a transmission, and the like, and can be specifically seen from Table 1. It should be noted that a network anomaly node can only carry one type of network resource.

[0100] In addition, the above-mentioned affiliation information is used to determine whether the network abnormal node belongs to the management and control range of a certain station, that is, to determine whether a certain station is the affiliation station of the network abnormal node.

[0101] Specifically, after determining the M network abnormal nodes, the network node positioning device can determine, for the pth network abnormal node in the M network abnormal nodes, the resource type of the resource carried by the pth network abnormal node, and the affiliation information between the pth network abnormal node and the N stations.

[0102] In S220, based on the resource type of the resource carried by the pth network abnormal node and the affiliation information between the pth network abnormal node and the N stations, the weight of the pth network abnormal node to each of the N stations is determined according to a second preset rule, to obtain a weight matrix.

[0103] The second preset rule can be a rule set in advance based on actual experience or situation, which is not limited here. In an example, the second preset rule can be specifically set as: the weight of the network abnormal node carrying the resource of the resource type of transmission, dynamic ring, etc. to the affiliation station of the network abnormal node is 1.0; the weight of the network abnormal node carrying the resource of the resource type of core network, bearer network, etc. to the affiliation station of the network abnormal node is 0.7, the weight of the network abnormal node carrying the resource of the resource type of wireless network, home customer, etc. to the station is 0.5; the weight of the network abnormal node to the other stations in the N stations except the affiliation station of the network abnormal node is 0.

[0104] Based on this, after determining the resource type of the resource carried by the pth network abnormal node and the affiliation information between the pth network abnormal node and the N stations, the affiliation station of the pth network abnormal node can be determined from the N stations based on the affiliation information between the pth network abnormal node and the N stations, and then the weight of the pth network abnormal node to the affiliation station can be set based on the resource type of the resource carried by the pth network abnormal node and according to the second preset rule.

[0105] In addition, for the other stations in the N stations except the affiliation station of the pth network abnormal node, the network node positioning device can set the weight of the pth network abnormal node to the other stations in the N stations except the affiliation station of the pth network abnormal node according to the second preset rule, so that the weight matrix can be obtained.

[0106] In this embodiment, the weight of each network anomaly node to each local station can be set according to a preset rule by the resource type of the resource carried by each network anomaly node and the belonging relationship between each network anomaly node and each local station, and then the weight matrix for representing the importance of each network anomaly node to each local station can be accurately obtained.

[0107] Since the network node itself does not have a spatial geographic attribute, that is, the network node does not have a geographic location, the network node positioning method provided in the embodiments needs to convert the clustering of network anomaly nodes in geographic locations into the clustering of local stations in geographic locations. Therefore, before that, the degree of influence of each local station affected by the emergency needs to be calculated in combination with the weight of the network anomaly node to each local station. Based on this, in order to accurately obtain the event influence degree of each local station, in an embodiment, the above S120 can specifically include the following steps:

[0108] determining that the sum of the M weights associated with the qth local station in the weight matrix is a first value;

[0109] determining the event influence degree of the qth local station based on the second value, the second value including the ratio between the first value and the number of network anomaly nodes.

[0110] Specifically, the network node positioning device can determine that the sum of the M weights associated with the qth local station in the weight matrix is a first value after obtaining the weight matrix, and then can determine the ratio between the first value and the number of network anomaly nodes (that is, M) as a second value, and then determine the event influence degree of the qth local station based on the second value.

[0111] In one example, the process of determining the event influence degree of the qth local station can be shown in the following formula (2):

[0112]

[0113] wherein g(L q ) is the event influence degree of the qth local station, a p,q is the importance of the pth network anomaly node to the qth local station, and M is the number of network anomaly nodes.

[0114] In this embodiment, the event influence degree of the qth local station can be accurately determined based on the M weights associated with the qth local station in the weight matrix for the qth local station, so that the accuracy of determining the local station greatly affected by the emergency can be improved subsequently.

[0115] After calculating the degree of influence of each station on the burst event and screening the stations with greater influence on the burst event from the plurality of stations, the clustering of network abnormal nodes in geographical position can be converted into the clustering of stations in geographical position based on the station position of the station with greater influence on the burst event by using a clustering algorithm (for example, the clustering algorithm can be a spatial clustering algorithm (Density-Based Spatial Clustering of Applications with Noise, DBSCAN)).

[0116] Specifically, in one embodiment, as shown in FIG. 13, Figure 3 The steps of S130 described above can specifically include the following steps:

[0117] S310, for each of the K stations, a circular region corresponding to the station is determined with the station position of the station as the center and according to a preset radius, and the number of stations in the circular region is determined.

[0118] The preset radius can be set in advance based on actual experience or conditions, and is not specifically limited here.

[0119] Specifically, the network node positioning device can determine, for each of the K stations, a circular region corresponding to the station with the station position of the station as the center and according to a preset radius, and then determine the number of stations in the circular region.

[0120] S320, in the case where the number of stations is greater than or equal to a preset density threshold, the station is determined to be a core station to obtain at least one core station.

[0121] The preset density threshold can be set in advance based on actual experience or conditions, and is not specifically limited here.

[0122] Specifically, after obtaining the number of stations in the circular region corresponding to a certain station, the network node positioning device can first determine whether the number of stations is greater than the preset density threshold. If the number of stations is greater than or equal to the preset density threshold, the station is determined to be a core station. In this way, at least one core station can be obtained.

[0123] It should be further noted that if the number of stations is less than the preset density threshold, it is determined whether the station is in the circular region corresponding to another core station. If it is, the station is determined to be a boundary station, otherwise, the station is determined to be a noise station.

[0124] In one example, it is assumed that the preset radius is ε and the preset density threshold is Minpts. Based on this, K local stations can be marked as unvisited first, and then one unvisited local station can be randomly selected from the K local stations as an object P, and the object P is marked as visited. The local station position of the object P is taken as the center of a circle, and a circular region corresponding to the object P is determined according to the preset radius ε. If there are at least Minpts objects in the circular region, the object P is put into the core local station cluster C. Otherwise, it is determined whether the object P is in the circular region corresponding to other objects in the core local station cluster C. If it is, the object P is determined to be a boundary object. Otherwise, the object P is determined to be a noise object.

[0125] In S330, the circular regions respectively corresponding to the at least one core local station are determined as the event occurrence region of the burst event.

[0126] Since the at least one core local station is obtained based on the clustering of the K local station positions, it is further illustrated that the current network operation anomaly has a clustering feature in geographical position, which is possibly caused by a burst event, and the geographical position of the core local station is possibly the event occurrence region of the burst event. Therefore, after obtaining the at least one core local station, the network node positioning device can determine that the circular regions respectively corresponding to the at least one core local station are the event occurrence region of the burst event.

[0127] In this embodiment, the local station positions of the local stations greatly affected by the burst event can be clustered. If at least one core local station can be determined in the clustering process, it indicates that the communication network anomaly is caused by a burst event. Then, the event occurrence region of the burst event can be accurately determined based on the circular regions respectively corresponding to the at least one core local station, and the positioning accuracy of the event occurrence region of the burst event is improved.

[0128] After the event occurrence region of the burst event is determined, the event occurrence region can include J network anomaly nodes. In order to accurately determine the network node having the greatest impact on the network operation from the J network anomaly nodes, in one embodiment, as shown in Figure 4 Before S140, the network node positioning method described above can further include the following steps:

[0129] In S410, a directed graph of the event occurrence region is constructed.

[0130] In some embodiments, the directed graph is used to represent the network link transmission relationship between the J network anomaly nodes in the event occurrence region. The directed graph can include the J network anomaly nodes and at least one directed edge for connecting any two network anomaly nodes in the J network anomaly nodes.

[0131] Specifically, considering that each network node is in collusion with each other through the transmission link, after determining the event occurrence region of the burst event and the J network abnormal nodes in the event occurrence region, a directed graph of the event occurrence region can be constructed by obtaining the network link transmission relationship between the J network abnormal nodes.

[0132] In one example, as shown in FIG. 4, by the transmission link data, the network nodes running abnormally can be associated and drawn into a complete end-to-end topology graph, that is, a directed graph, and then the centrality of the degree of each network node in the topology can be analyzed to find the target network node affecting the network operation. It should be noted that, Figure 5 Figure 5 only the transmission link between each network node (for example, the Basic Rate Interface (BRI) and the access router in FIG. 4) in a certain region is shown. Figure 5

[0133] S420, for each network abnormal node in the J network abnormal nodes, determining the number of first directed edges and the number of second directed edges.

[0134] In some embodiments, the first directed edge is a directed edge whose end point is the network abnormal node in at least one directed edge, and the second directed edge is a directed edge whose starting point is the network abnormal node in at least one directed edge.

[0135] Specifically, after the directed graph of the event occurrence region is constructed, since the directed graph can include J network abnormal nodes and at least one directed edge connecting any two network abnormal nodes in the J network abnormal nodes, the number of directed edges whose end point is the network abnormal node in at least one directed edge and the number of directed edges whose starting point is the network abnormal node in at least one directed edge can be determined for each network abnormal node in the J network abnormal nodes.

[0136] Based on this, S410 can specifically include the following steps:

[0137] For each network abnormal node in the J network abnormal nodes, the sum of the number of first directed edges and the number of second directed edges corresponding to the network abnormal node is determined as the first centrality of the network abnormal node.

[0138] The node with the largest first centrality is determined from the J network abnormal nodes as the target network node.

[0139] The first centrality represents the importance of the network abnormal node in the event occurrence region.

[0140] ​​Specifically, the network node positioning apparatus can determine, for each of the J network abnormal nodes, a sum of the number of the first directed edges and the number of the second directed edges corresponding to the network abnormal node as a first centrality of the network abnormal node. In this way, after obtaining the first centrality of each of the J network abnormal nodes, the network node positioning apparatus can determine, from the J network abnormal nodes, a network abnormal node with the largest first centrality as the target network node.

[0141] In one example, the above-mentioned calculation of the first centrality of the network abnormal node can be as shown in formula (3):

[0142]

[0143] wherein, is the number of the first directed edges, i.e., the in-degree of the network abnormal node. is the number of the second directed edges, i.e., the out-degree of the network abnormal node. DC1 is the first centrality.

[0144] In this embodiment, by calculating the centrality of each network abnormal node in the event occurrence region, the most important network abnormal node among the network abnormal nodes in the event occurrence region can be determined as the target network node, and thus the target network node can be repaired as soon as possible in the subsequent process, so as to restore the normal operation of the network as soon as possible.

[0145] Since the larger the scale of the directed graph is, the higher the centrality of each network abnormal node can be, based on this, in order to eliminate the influence of the growth of the scale of the directed graph on the centrality of the network abnormal node, the above-mentioned S140 can specifically include the following steps:

[0146] determining, for each of the J network abnormal nodes, a sum of the number of the first directed edges and the number of the second directed edges corresponding to the network abnormal node as a first centrality of the network abnormal node;

[0147] determining a ratio between the first centrality of the network abnormal node and a preset value as a second centrality of the network abnormal node;

[0148] determining, from the J network abnormal nodes, a network abnormal node with the largest second centrality as the target network node.

[0149] wherein, the preset value is determined based on the number of nodes of the J network abnormal nodes. For example, the preset value is equal to the number of nodes of the J network abnormal nodes minus one.

[0150] Specifically, the network node positioning apparatus can determine, for each of the J network anomaly nodes, a sum of the number of first directed edges and the number of second directed edges corresponding to the network anomaly node as a first centrality of the network anomaly node, and further determine a ratio between the first centrality of the network anomaly node and a preset value as a second centrality of the network anomaly node, so as to determine, from the J network anomaly nodes, a node with the maximum second centrality as the target network node.

[0151] In one example, the above-mentioned calculation of the second centrality of the network anomaly node can be as shown in formula (4):

[0152]

[0153] wherein, is the number of first directed edges, that is, the in-degree of the network anomaly node. is the number of second directed edges, that is, the out-degree of the network anomaly node. DC2 is the second centrality, and J is the number of network anomaly nodes in the event occurrence area.

[0154] In this embodiment, the influence of the scale growth of the directed graph on the centrality of the network anomaly node can be considered. In order to eliminate the influence of the scale growth of the directed graph on the centrality of the network anomaly node, the sum of the in-degree and the out-degree of each network anomaly node in the event occurrence area is determined as the first centrality, and the ratio between the first centrality and the preset value is determined as the second centrality. In this way, the obtained second centrality can eliminate the influence of the scale growth of the directed graph on the centrality of the network anomaly node, and then the target network node can be repaired as soon as possible in the subsequent process, so as to restore the normal operation of the network as early as possible.

[0155] Based on the same inventive concept, the embodiments of the present application also provide a network node positioning apparatus. Specifically, the network node positioning apparatus can be used for Figure 6 The network node positioning apparatus provided by the embodiments of the present application will be described in detail.

[0156] Figure 6 FIG. 1 is a structural schematic diagram of a network node positioning apparatus provided by an embodiment of the present application.

[0157] As shown in FIG. 6, the network node positioning apparatus 600 can include an acquisition module 610, a determination module 620, and a clustering module 630. Figure 6

[0158] ​The acquisition module 610 is configured to acquire a weight matrix and local station positions of N local stations in a case where it is determined that a sudden event affecting network operation exists, the weight matrix being an M-row and N-column matrix, a weight in the pth row and qth column of the weight matrix being used to represent an importance degree of a pth network abnormal node to a qth local station, p=1, 2,..., M, q=1, 2,..., N, M and N being positive integers;

[0159] The determination module 620 is configured to determine, for the qth local station, an event influence degree of the qth local station based on the M weights associated with the qth local station in the weight matrix, the event influence degree of the qth local station representing a degree of influence of the qth local station by the sudden event.

[0160] The clustering module 630 is configured to determine an event occurrence region of the sudden event by performing clustering processing on K local stations according to the local station positions of the K local stations, the K local stations including local stations whose event influence degrees are greater than a preset influence degree threshold and are selected from the N local stations, the event occurrence region including J network abnormal nodes, K being a positive integer less than or equal to N, and J being a positive integer less than or equal to M.

[0161] The determination module 620 is further configured to determine a target network node from the J network abnormal nodes, the target network node being a network node having the greatest influence on network operation among the J network abnormal nodes.

[0162] In an embodiment, the network node positioning apparatus provided by the embodiment of the present application can further include a monitoring module.

[0163] The monitoring module is configured to monitor network operation data of each network node in a plurality of network nodes in real time.

[0164] The determination module is further configured to determine M network abnormal nodes whose network operation data does not conform to a first preset rule from the plurality of network nodes, and determine N local stations associated with the M network abnormal nodes.

[0165] In an embodiment, the acquisition module is specifically configured to:

[0166] For a pth network abnormal node in the M network abnormal nodes, determine a resource type of a resource carried by the pth network abnormal node, and belonging information between the pth network abnormal node and N local stations respectively;

[0167] According to a second preset rule, determine a weight of the pth network abnormal node to each local station in the N local stations based on the resource type of the resource carried by the pth network abnormal node and the belonging information between the pth network abnormal node and the N local stations, to obtain the weight matrix.

[0168] In an embodiment, the determination module is specifically configured to:

[0169] determining a sum of the M weights associated with the qth local station in the weight matrix as a first value;

[0170] determining an event influence degree of the qth local station based on a second value, the second value comprising a ratio between the first value and the number of network abnormal nodes.

[0171] In an embodiment, the clustering module mentioned above is specifically configured to:

[0172] for each of the K local stations, taking the local station position of the local station as the center, and determining the number of local stations in the circular region corresponding to the local station according to the preset radius;

[0173] in a case where the number of local stations is greater than or equal to a preset density threshold, determining the local station as a core local station to obtain at least one core local station;

[0174] determining the circular region corresponding to each of the at least one core local station as an event occurrence region of the burst event.

[0175] In an embodiment, the network node positioning apparatus provided by the embodiment of the present application can further comprise a constructing module.

[0176] constructing a directed graph of the event occurrence region, the directed graph being used to represent the network link transmission relationship between the J network abnormal nodes in the event occurrence region, the directed graph comprising the J network abnormal nodes and at least one directed edge used to connect any two of the J network abnormal nodes;

[0177] for each of the J network abnormal nodes, determining the number of first directed edges and the number of second directed edges, the first directed edge being a directed edge of the at least one directed edge whose terminal point is the network abnormal node, and the second directed edge being a directed edge of the at least one directed edge whose starting point is the network abnormal node;

[0178] Based on this, the determining module mentioned above is specifically configured to:

[0179] for each of the J network abnormal nodes, determining a sum of the number of first directed edges and the number of second directed edges corresponding to the network abnormal node as a first centrality of the network abnormal node;

[0180] determining a node with the maximum first centrality from the J network abnormal nodes as a target network node.

[0181] In an embodiment, the determining module mentioned above is specifically configured to:

[0182] For each of the J network abnormal nodes, determine a sum of a number of first directed edges corresponding to the network abnormal node and a number of second directed edges corresponding to the network abnormal node as a first centrality of the network abnormal node;

[0183] Determine a ratio between the first centrality of the network abnormal node and a preset value as a second centrality of the network abnormal node, the preset value being determined based on a number of nodes of the J network abnormal nodes;

[0184] Determine a node with the largest second centrality from the J network abnormal nodes as a target network node.

[0185] In the embodiments of the present application, in the case where it is determined that there is a sudden event affecting network operation, a weight matrix and station positions of N stations can be obtained, the weight matrix being an M-row and N-column matrix, and a weight in the pth row and qth column of the weight matrix being used to represent an importance degree of a pth network abnormal node to a qth station, where p = 1, 2, …, M, q = 1, 2, …, N, and M and N are positive integers. Based on this, considering that network nodes themselves do not have spatial geographic attributes, that is, network nodes do not have geographic positions, for the qth station, an event influence degree of the qth station is determined based on M weights associated with the qth station in the weight matrix. Since the K stations include stations whose event influence degrees are greater than a preset influence degree threshold and are selected from the N stations, that is, the K stations are determined from the N stations as stations greatly affected by the sudden event, and then the event occurrence region of the sudden event is determined by clustering the K stations according to the station positions of the K stations, and since the event occurrence region includes the J network abnormal nodes, the network node with the greatest impact on network operation can be located from the J network abnormal nodes. In this way, not only can the event occurrence region of the sudden event be accurately and quickly located by clustering the station positions of the multiple stations greatly affected by the sudden event, but also the network node that needs to be repaired as soon as possible can be accurately and quickly determined from the network abnormal nodes in the event occurrence region, thereby improving the positioning efficiency of the network node that needs to be repaired as soon as possible.

[0186] Each module in the network node positioning apparatus provided by the embodiments of the present application can implement the method steps of any of the embodiments shown in the above Figure 1 to Figure 4 and achieve corresponding technical effects, and for brevity, will not be described here.

[0187] Figure 7 A hardware structure schematic diagram of an electronic device provided by the embodiments of the present application is shown.

[0188] The electronic device can include a processor 701 and a memory 702 having computer program instructions stored therein.

[0189] In particular, the processor 701 can include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or can be configured to implement one or more integrated circuits that embody the embodiments of the present application.

[0190] The memory 702 can include mass storage for data or instructions. As an example and not by way of limitation, the memory 702 can include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disc (e.g., a compact disc (CD) or a digital versatile disc (DVD)), a solid-state drive (SSD), a USB drive, or a combination of two or more of these. Where appropriate, the memory 702 can include removable or non-removable (or fixed) media, where appropriate. Where appropriate, the memory 702 can be internal or external to the integrated gateway disaster recovery device. In particular embodiments, the memory 702 is non-volatile, solid-state memory.

[0191] The memory can include read-only memory (ROM), random-access memory (RAM), magnetic disk storage mediums, optical storage mediums, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software that, when executed (by one or more processors), is operable to

[0192] The processor 701 implements any of the network node positioning methods in the above embodiments by reading and executing computer program instructions stored in the memory 702.

[0193] In one example, the electronic device can further include a communication interface 703 and a bus 710. As shown, the processor 701, the memory 702, and the communication interface 703 are connected through the bus 710 and complete communication among each other. Figure 7

[0194] The communication interface 703 is mainly used to realize the communication between the modules, devices, units and / or equipment in the embodiments of the present application.

[0195] ​Bus 710 includes a hardware, software, or both that couples components of the online data traffic metering device to each other. As an example without limitation, bus can include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand (IB) interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or another suitable bus or a combination of two or more of these. Where appropriate, bus 710 can include one or more buses. Although this application describes and illustrates a particular bus, this application contemplates any suitable bus or interconnect.

[0196] In addition, in combination with the network node positioning method in the above embodiments, the embodiments of the present application can provide a computer storage medium for implementation. The computer storage medium has computer program instructions stored thereon; the computer program instructions are executed by a processor to implement the network node positioning method provided by the embodiments of the present application.

[0197] The embodiments of the present application also provide a computer program product, which includes a computer program, and the computer program is executed by a processor to implement the network node positioning method provided by the embodiments of the present application.

[0198] It needs to be clear that the present application is not limited to the specific configurations and processes described above and shown in the drawings. For the sake of brevity, detailed descriptions of well-known methods are 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 steps, after understanding the spirit of the present application.

[0199] The functional blocks shown in the structural block diagrams above can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, functional cards, and the like. When implemented in software, the elements of the present application are program or code segments that are used to perform the required tasks. The program or code segments can be stored in a machine-readable medium, or transmitted through a data signal carried in a carrier wave over a transmission medium or communication link. A "machine-readable medium" includes any medium that can store or transport information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like. The code segments can be downloaded via computer networks such as the Internet, intranets, and the like.

[0200] It is also important to note that the examples mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the steps mentioned above, that is, the steps can be performed in the order mentioned in the examples, or in an order different from the examples, or several steps can be performed simultaneously.

[0201] The computer program instructions can also be loaded onto a computer, other programmable network node positioning apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable network node positioning apparatus, or other devices to produce the machine so that the instructions executed by the computer, other programmable network node positioning apparatus, or other devices implement the functions / acts specified in the flowchart and / or block diagram block or blocks. These processors can be, but are not limited to, general purpose processors, special purpose processors, special application processors, or field programmable logic circuits. It can also be understood that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can also be implemented by dedicated hardware, or a combination of dedicated hardware and computer instructions.

[0202] The above is merely a specific implementation of the present application. As can be clearly understood by a person skilled in the art from the above description, for the convenience and brevity of description, the specific working process of the system, module and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described herein again. It should be understood that the protection scope of the present application is not limited in this way, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed in the present application, and these modifications or replacements should be covered in the protection scope of the present application.

Claims

1. A network node positioning method, characterized by, The method comprises: In the case where it is determined that there is a sudden event affecting network operation, a weight matrix and local station positions of N local stations are acquired, the weight matrix is a matrix of M rows and N columns, a weight in the weight matrix at a row and a column is used to represent the importance of an abnormal node to a local station, =1, 2, …, M, =1, 2, …, N, M and N are positive integers;​​​​ For the first station, based on the M weights in the weight matrix associated with the first station, determine the event influence degree of the first station, the event influence degree of the first station representing the degree of influence of the first station by the sudden event; According to the station positions of K stations, the event occurrence region of the sudden event is determined by clustering the K stations, the K stations comprising stations with an event influence degree greater than a preset influence degree threshold selected from the N stations, the event occurrence region comprising J network abnormal nodes, K being a positive integer less than or equal to N, and J being a positive integer less than or equal to M; A target network node is located from the J network abnormal nodes, the target network node being a network node with the greatest influence on network operation among the J network abnormal nodes; Before the weight matrix and the station positions of the N stations are obtained, the method further comprises: Real-time monitoring of network operation data of each network node in a plurality of network nodes; From the plurality of network nodes, M network abnormal nodes with network operation data not meeting a first preset rule are determined, and N stations associated with the M network abnormal nodes are determined; Before the target network node is determined from the J network abnormal nodes, the method further comprises: A directed graph of the event occurrence region is constructed, the directed graph being used to represent network link transmission relationships between the J network abnormal nodes in the event occurrence region, the directed graph comprising the J network abnormal nodes and at least one directed edge connecting any two network abnormal nodes in the J network abnormal nodes; For each network abnormal node in the J network abnormal nodes, a number of first directed edges and a number of second directed edges are determined, the first directed edge being a directed edge in the at least one directed edge with a terminal point being the network abnormal node, and the second directed edge being a directed edge in the at least one directed edge with a starting point being the network abnormal node; The determination of the target network node from the J network abnormal nodes comprises: For each network abnormal node in the J network abnormal nodes, a sum of the number of first directed edges and the number of second directed edges corresponding to the network abnormal node is determined as a first centrality of the network abnormal node; A node with the greatest first centrality is determined from the J network abnormal nodes as the target network node.

2. The method of claim 1, wherein, The obtaining of the weight matrix comprises: For the M network abnormal nodes, the first The network anomaly node is determined to be the first... The resource type of the network abnormal node and the first The relationship between each network anomaly node and the N local stations; Based on the first The resource types of the network anomaly nodes and the first The association information between each of the network anomaly nodes and the N local stations is used to determine the first node according to the second preset rule. The weights of each of the N local stations are determined by assigning weights to the network anomaly nodes to each of the N local stations, thus obtaining a weight matrix.

3. The method of claim 1, wherein, The first The local station, based on the weight matrix and the first station The M weights associated with each local station determine the first... The impact of an event on each station includes: determining a sum of M weights in the weight matrix associated with the first station as a first value; Based on the second value, determine the first The event impact of a single station, the second value including the ratio between the first value and the number of abnormal network nodes.

4. The method of claim 1, wherein, The determination of the event occurrence region of the sudden event according to the station positions of the K stations by clustering the K stations comprises: For each station in the K stations, a circular region corresponding to the station is demarcated with the station position of the station as the center and according to a preset radius, and a number of stations in the circular region is determined; In a case where the number of stations is greater than or equal to a preset density threshold, the station is determined as a core station to obtain at least one core station; The circular regions corresponding to the at least one core station are determined as the event occurrence region of the sudden event.

5. The method of claim 1, wherein, The determination of the target network node from the J network abnormal nodes comprises: For each network abnormal node in the J network abnormal nodes, a sum of the number of first directed edges and the number of second directed edges corresponding to the network abnormal node is determined as a first centrality of the network abnormal node; determine a ratio between the first centrality of the network abnormal node and a preset value as a second centrality of the network abnormal node, the preset value being determined based on a number of the J network abnormal nodes; determine a node with the maximum second centrality from the J network abnormal nodes as a target network node.

6. A network node positioning apparatus, characterized by, The apparatus comprises: The acquisition module is configured to acquire a weight matrix and local station positions of N local stations in a case where it is determined that a sudden event affecting network operation exists, the weight matrix is an M-row and N-column matrix, a weight in the weight matrix at a row and a column is used to represent an importance degree of an abnormal node of an Mth network to an Nth local station, =1, 2, …, M, =1, 2, …, N, M and N are positive integers. ​​​​ The determining module is used for the first... The local station, based on the weight matrix and the first station The M weights associated with each local station determine the first... The impact of an event on a single station, the first The event impact of each station is characterized by the first The extent to which each station was affected by the aforementioned emergency; a clustering module configured to determine an event occurrence region of the emergency event by clustering the K local stations based on local station positions of the K local stations, the K local stations comprising local stations with an event influence degree greater than a preset influence degree threshold selected from the N local stations, the event occurrence region comprising J network abnormal nodes, K being a positive integer less than or equal to N, and J being a positive integer less than or equal to M; The determining module is further configured to determine a target network node from the J network abnormal nodes, the target network node being a network node with the greatest influence on network operation among the J network abnormal nodes. Before obtaining the weight matrix and the local station positions of the N local stations, the method further comprises: monitoring network operation data of each network node in a plurality of network nodes in real time; determining M network abnormal nodes with network operation data not conforming to a first preset rule from the plurality of network nodes, and determining N local stations associated with the M network abnormal nodes; Before determining the target network node from the J network abnormal nodes, the method further comprises: constructing a directed graph of the event occurrence region, the directed graph being used to represent network link transmission relationships between the J network abnormal nodes in the event occurrence region, the directed graph comprising the J network abnormal nodes and at least one directed edge connecting any two network abnormal nodes in the J network abnormal nodes; for each network abnormal node in the J network abnormal nodes, determining a number of first directed edges and a number of second directed edges, the first directed edge being a directed edge with a terminal point being the network abnormal node among the at least one directed edge, and the second directed edge being a directed edge with a starting point being the network abnormal node among the at least one directed edge; The determining of the target network node from the J network abnormal nodes comprises: for each network abnormal node in the J network abnormal nodes, determining a sum of the number of first directed edges and the number of second directed edges corresponding to the network abnormal node as a first centrality of the network abnormal node; determining a node with the maximum first centrality from the J network abnormal nodes as the target network node.

7. An electronic device, comprising: The device comprises a processor and a memory storing computer program instructions; The processor reads and executes the computer program instructions to implement the network node positioning method according to any one of claims 1-5.

8. A computer storage medium, characterized in that, The computer storage medium stores computer program instructions, and the computer program instructions are executed by the processor to implement the network node positioning method according to any one of claims 1-5.

Images