Method, device, electronic device and storage medium for determining border backbone routing

Abstract

The present invention relates to the field of computer network technology, and in particular to a method, device, electronic device and storage medium for determining a border backbone route. The method determines the network topology of a target geographical area based on measurement and open source information; determines a first candidate border IP address based on the geographical location of an IP address; divides the first border IP address and a second candidate border IP address based on a plurality of border verification parameters; predicts the second candidate border IP address based on a prediction model trained on the first border IP address to obtain a confidence level of whether it is a border IP address; selects a second border IP address with a confidence level higher than a confidence level threshold, and determines the border backbone route of the target geographical area based on the first border IP address and a router alias resolution algorithm. In this way, the network boundary of the target geographical area is fully verified through a plurality of border verification parameters, a more accurate border IP address is obtained, and the accuracy of determining the border backbone route is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of computer networks, and in particular to a method, device, electronic equipment and storage medium for determining a border backbone route. Background Art

[0002] Backbone Area Border Router (BABR) refers to the key routers located at the network border in the network topology and responsible for the main data transmission tasks. These routers connect different areas or autonomous systems (AS) and are responsible for processing data traffic across network boundaries.

[0003] The existing border backbone routing identification method relies on the IP address geolocation library to screen the border IP addresses. However, the IP address geolocation library has the problems of inaccurate positioning and slow data update. The border IP addresses obtained by screening the IP address geolocation library are often not the real borders of the region. Therefore, the accuracy of the border backbone routing obtained based on this is low. Summary of the invention

[0004] In view of this, the embodiments of the present application at least provide a method, device, electronic device and storage medium for determining border backbone routes. The present application comprehensively verifies the network boundaries of the target geographical area through multiple boundary verification parameters to obtain a more accurate boundary IP address, thereby improving the accuracy of determining the border backbone routes.

[0005] This application mainly includes the following aspects:

[0006] In a first aspect, an embodiment of the present application provides a method for determining a border backbone route, the method comprising:

[0007] Determining a network topology structure of the target geographical area based on measured network topology information and open source network topology information of the target geographical area;

[0008] Determine a plurality of first candidate boundary IP addresses of the target geographic area based on the geographic location of each IP address in the network topology;

[0009] Based on a plurality of preset boundary verification parameters, perform boundary judgment on each of the first candidate boundary IP addresses, mark the first candidate boundary IP address whose number of boundary verification parameters passing the boundary judgment is greater than or equal to the preset number threshold as the first boundary IP address, and mark the first candidate boundary IP address whose number of boundary verification parameters passing the boundary judgment is less than the number threshold as the second candidate boundary IP address;

[0010] Based on the boundary verification parameters of each of the first boundary IP addresses, at least one prediction model is trained, and based on the at least one trained prediction model, the boundary verification parameter of each of the second candidate boundary IP addresses is predicted to obtain the confidence level of whether each of the second candidate boundary IP addresses is a boundary IP address;

[0011] A plurality of second boundary IP addresses with confidence levels higher than a preset confidence threshold are selected from each of the second candidate boundary IP addresses, and the boundary backbone routing of the target geographic area is determined based on each of the first boundary IP addresses, the second boundary IP addresses and the router alias resolution algorithm.

[0012] In a second aspect, an embodiment of the present application further provides a device for determining a border backbone route, the device for determining a border backbone route comprising:

[0013] A first determination module, configured to determine a network topology structure of a target geographical area based on measured network topology information and open source network topology information of the target geographical area;

[0014] A second determination module, configured to determine a plurality of first candidate boundary IP addresses of the target geographic area based on the geographic location of each IP address in the network topology structure;

[0015] A judgment classification module, used for performing boundary judgment on each of the first candidate boundary IP addresses based on a plurality of preset boundary verification parameters, marking the first candidate boundary IP addresses whose number of boundary verification parameters passing the boundary judgment is greater than or equal to a preset number threshold as first boundary IP addresses, and marking the first candidate boundary IP addresses whose number of boundary verification parameters passing the boundary judgment is less than the number threshold as second candidate boundary IP addresses;

[0016] A training prediction module, used to train at least one prediction model based on the boundary verification parameters of each of the first boundary IP addresses, and predict the boundary verification parameters of each of the second candidate boundary IP addresses based on the trained at least one prediction model to obtain the confidence level of whether each of the second candidate boundary IP addresses is a boundary IP address;

[0017] The third determination module is used to select multiple second boundary IP addresses with confidence levels higher than a preset confidence threshold from each of the second candidate boundary IP addresses, and determine the boundary backbone routing of the target geographic area based on each of the first boundary IP addresses, the second boundary IP addresses and the router alias resolution algorithm.

[0018] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the method for determining the border backbone routing as described above.

[0019] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for determining the border backbone route as described above are executed.

[0020] The method, device, electronic device and storage medium for determining the border backbone route provided in the embodiment of the present application determine the network topology structure of the target geographical area based on the measured network topology information and open source network topology information of the target geographical area; determine multiple first candidate border IP addresses of the target geographical area based on the geographical location of each IP address in the network topology structure; perform boundary judgment on each first candidate border IP address based on multiple preset boundary verification parameters, mark the first candidate border IP address whose number of boundary verification parameters passing the boundary judgment is greater than or equal to the preset number threshold as the first border IP address, and mark the first candidate border IP address whose number of boundary verification parameters passing the boundary judgment is less than the number threshold as the second candidate border IP address; train at least one prediction model based on the boundary verification parameters of each first border IP address, and predict the boundary verification parameters of each second candidate border IP address based on the at least one trained prediction model to obtain the confidence of whether each second candidate border IP address is a border IP address; select multiple second border IP addresses whose confidence is higher than the preset confidence threshold from each second candidate border IP address, and determine the border backbone route of the target geographical area based on each first border IP address, the second border IP address and the router alias resolution algorithm. In this way, the network boundary of the target geographic area is fully verified through multiple boundary verification parameters, a more accurate boundary IP address is obtained, and the accuracy of boundary backbone routing determination is improved.

[0021] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A flow chart of a method for determining a border backbone route provided by an embodiment of the present application is shown;

[0024] Figure 2 One of the functional module diagrams of a device for determining a border backbone route provided in an embodiment of the present application is shown;

[0025] Figure 3 A second functional module diagram of a device for determining a border backbone route provided in an embodiment of the present application is shown;

[0026] Figure 4 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0028] To facilitate the understanding of the present application, the technical solution provided by the present application is described in detail below in conjunction with specific embodiments.

[0029] The embodiments of the present application provide a method, device, electronic device and storage medium for determining border backbone routes, which comprehensively verify the network boundaries of the target geographical area through multiple boundary verification parameters, obtain more accurate boundary IP addresses, and improve the accuracy of determining border backbone routes.

[0030] See also Figure 1 , Figure 1 A flow chart of a method for determining a border backbone route provided by an embodiment of the present application. Figure 1As shown, the method for determining the border backbone route provided in the embodiment of the present application includes the following steps:

[0031] S101, determining a network topology structure of a target geographical area based on measured network topology information and open source network topology information of the target geographical area.

[0032] In the embodiment of the present application, the reason why the border backbone route is determined is that the border backbone route undertakes the main data transmission task of the communication area. In order to ensure the network transmission of the area and maintain the network security of the area, the border backbone route of the area needs to be specially maintained and monitored in a centralized manner to prevent the failure of the border backbone route from affecting the data transmission, or from being attacked by the network outside the area and affecting the network security of the area. Therefore, the determination of the border backbone route needs to ensure the accuracy of the determination of the border backbone route, avoid unnecessary waste of network maintenance and monitoring resources, and ensure the integrity of the determination of the border backbone route to prevent the occurrence of missed monitoring of the border backbone route, thereby causing security problems.

[0033] Here, the existing regional network boundary backbone routing identification technology often adopts a sampling method when acquiring the network topology, and the acquisition of the network topology is not complete. Based on this, the embodiment of the present application determines the network topology structure of the target geographical area by acquiring the measured network topology information and open source network topology information of the target geographical area, so that the determined network topology structure can be more complete. Among them, the target geographical area is a specific city selected according to demand, such as Beijing and Xi'an; or certain cities that are geographically close, such as the Yangtze River Delta city cluster, the Pearl River Delta city cluster, etc. The measured network topology information is the network topology information obtained by actively measuring the target geographical area. The open source network topology information is the network topology information of the target geographical area obtained from an open source website.

[0034] S102: Determine a plurality of first candidate boundary IP addresses of the target geographic area based on the geographic locations of the respective IP addresses in the network topology.

[0035] Here, based on the geographical location of each IP address in the network topology structure, IP addresses suspected to be at the boundary of the target geographical area are selected as a plurality of first candidate boundary IP addresses of the target geographical area.

[0036] S103, based on multiple preset boundary verification parameters, perform boundary judgment on each of the first candidate boundary IP addresses, mark the first candidate boundary IP address whose number of boundary verification parameters passing the boundary judgment is greater than or equal to the preset number threshold as the first boundary IP address, and mark the first candidate boundary IP address whose number of boundary verification parameters passing the boundary judgment is less than the number threshold as the second candidate boundary IP address.

[0037] Here, in order to solve the problem that the existing border backbone route identification method that relies on the IP address geolocation library has low accuracy, cannot be verified, and lacks persuasiveness in identifying the border IP addresses, the embodiment of the present application uses multiple preset border verification parameters to assist in screening and verifying the border IP addresses, so as to obtain more accurate border IP addresses, thereby improving the accuracy of border backbone route determination.

[0038] Specifically, firstly, a boundary judgment is performed on each first candidate boundary IP address through a plurality of preset boundary verification parameters, and each first candidate boundary IP is preliminarily screened and marked according to the number of boundary verification parameters that pass the boundary judgment, and the first candidate boundary IP address whose number of boundary verification parameters that pass the boundary judgment is greater than or equal to the preset number threshold is marked as the first boundary IP address, and the first candidate boundary IP address whose number of boundary verification parameters that pass the boundary judgment is less than the said number threshold is marked as the second candidate boundary IP address. Among them, the preset number threshold can be specifically set according to the actual situation, and is generally set to more than half of the number of boundary verification parameters, and no specific limitation is made here. In this way, the first candidate boundary IP address that can pass the boundary judgment of most boundary verification parameters is regarded as the boundary IP address determined by the target geographical area, and is marked as the first boundary IP address. The first candidate boundary IP address that fails to pass the boundary judgment of most boundary verification parameters is marked as the second candidate boundary IP address for further verification later.

[0039] Furthermore, the preset multiple boundary verification parameters include at least one of an IP address geolocation parameter, a delay parameter, a node geographic location information parameter, and a node other information parameter; the node geographic location information parameter includes at least one of the node's domain name registration information, host name information, and route tracking information; the node other information parameters include at least one of the node's asset information and the node's hierarchical information of the autonomous system in which the node is located.

[0040] Among them, the IP address geolocation parameter is a parameter obtained from the IP address geolocation database. The IP address geolocation database can intuitively reflect the geographical location of the node and is a powerful basis for judging whether the node is in the region. In the embodiment of the present application, the IP2Location database and the Geolite2 database are used to perform geolocation of the IP address; the delay parameter can reflect the distance relationship between two nodes. The distance between two nodes with short delay is also short in geographical location. In the embodiment of the present application, a series of detection points deployed in the PingPe platform are used to perform ping measurement on each first candidate boundary IP address to judge its approximate location; the domain name registration (WH The OIS information can sometimes reflect the location of the node. The hostname information contains the server used by the node, and this server often indicates its geographical location. When the traceroute information displays the path passed, the path may contain geographical location information. These parameters can be used as an aid to verify the geographical location of the node. The asset information of the node in the other information parameters of the node can reflect the device type of the node and can also assist in judgment. The tier information of the autonomous system (AS) where the node is located reflects the level of the node. If the tier is too low, the possibility of it being a boundary will also decrease. These auxiliary parameters can also provide a basis for boundary judgment.

[0041] S104, based on the boundary verification parameters of each of the first boundary IP addresses, train at least one prediction model, and predict the boundary verification parameters of each of the second candidate boundary IP addresses based on the trained at least one prediction model to obtain the confidence level of whether each of the second candidate boundary IP addresses is a boundary IP address.

[0042] Here, in order to further verify the second candidate boundary IP address, the embodiment of the present application uses the boundary verification parameters of each first boundary IP address as training set data to train at least one prediction model. Among them, the prediction model can be at least one of a decision tree model, a random forest model, a support vector machine (SVM) model, a K nearest neighbor (KNN) model, etc. Since the first boundary IP address can be regarded as a confident boundary IP address, the prediction model trained based on the boundary verification parameters of each first boundary IP address is capable of evaluating and predicting whether the IP address is a boundary IP address. Take each second candidate boundary IP address as a test set, and predict the boundary verification parameters of each second candidate boundary IP address based on at least one trained prediction model to obtain the confidence of whether each second candidate boundary IP address is a boundary IP address.

[0043] Furthermore, by combining the prediction results of various prediction models, the confidence ranking of each second candidate boundary IP address can be obtained, among which the second candidate boundary IP address that can be predicted by more prediction models ranks relatively high in the confidence ranking.

[0044] S105, selecting multiple second boundary IP addresses with confidence levels higher than a preset confidence threshold from each of the second candidate boundary IP addresses, and determining the boundary backbone routing of the target geographic area based on each of the first boundary IP addresses, the second boundary IP addresses and the router alias resolution algorithm.

[0045] Here, multiple second boundary IP addresses with confidence higher than the preset confidence threshold are selected from each second candidate boundary IP address as the boundary IP address determined by the secondary screening. Among them, the preset confidence threshold is adjusted according to the actual screening accuracy requirement. For example, when the accuracy requirement is high, the confidence threshold can be adjusted to 0.8, and when the accuracy requirement is low, the confidence threshold can be adjusted to 0.5. No specific restrictions are made here. At the same time, since the identification of the boundary backbone routing in the prior art often stays at the IP level, ignoring that the boundary backbone routing often exists in the form of routers or nodes (Point of Presence, POP) in the topological network, the boundary backbone routing obtained by the prior art is often imperfect. In order to solve this problem, the embodiment of the present application is based on each first boundary IP address, the second boundary IP address and the router alias resolution algorithm, and uses the router alias resolution algorithm to establish a mapping of the boundary IP address to the boundary backbone routing, and determine the accurate and comprehensive boundary backbone routing of the target geographical area.

[0046] Further, the determining the network topology structure of the target geographical area based on the measured network topology information and the open source network topology information of the target geographical area includes:

[0047] Step a1, deploying a plurality of detection points inside and outside the target geographical area respectively, and performing multiple measurements at each of the detection points using a network diagnostic tool to obtain measured network topology information of the target geographical area.

[0048] Here, through traceroute technology, multiple detection points are deployed inside and outside the target geographical area, and network diagnostic tools are used to perform multiple measurements at each detection point to obtain the measured network topology information of the target geographical area. Among them, traceroute is a network diagnostic tool used to determine the path of a data packet from one computer to another (usually to a specific host or network service). The measured network topology information includes the IP address of each hop in the network, as well as the autonomous system (AS), country, city, WHOIS information, etc. corresponding to the IP address.

[0049] Step a2: Acquire historical network topology data of the target geographical area from an open source website to obtain open source network topology information of the target geographical area.

[0050] Here, the historical network topology dataset of the target geographical area for many years is obtained from the open source website CAIDA to obtain the open source network topology information of the target geographical area.

[0051] Step a3: taking the union of the measured network topology information and the open source network topology information of the target geographical area to obtain the network topology structure of the target geographical area.

[0052] Here, the two are integrated, and the measured network topology information and the open source network topology information of the target geographical area are taken as the union to obtain a relatively complete network topology structure of the target geographical area.

[0053] Furthermore, the determining of a plurality of first candidate boundary IP addresses of the target geographical area based on the geographical location of each IP address in the network topology structure includes:

[0054] Step b1, searching the IP address geolocation database to obtain the geographical location of each IP address in the network topology, and determining multiple target IP addresses; the target IP address is the first IP address that spans from within the target geographic area to outside the area.

[0055] Here, the IP address geolocation technology is used to find the first IP address in the network topology that crosses from the area to outside the area from the IP address geolocation database, and record it as a suspected boundary IP address and determine it as the target IP address.

[0056] Step b2: determine each of the target IP addresses and the IP addresses two hops before and after each of the target IP addresses as a plurality of first candidate boundary IP addresses of the target geographical area.

[0057] Here, two hops are taken before and after the suspected boundary IP address to form a network topology fragment with a length of 5 IP addresses as the suspected boundary fragment. It is generally believed that the suspected boundary fragment contains the IP address of the actual regional network boundary. Therefore, each target IP address and the IP addresses two hops before and after each target IP address are determined as multiple first candidate boundary IP addresses of the target geographic area.

[0058] In a possible implementation, when the number of prediction models is more than one, predicting the boundary verification parameter of each second candidate boundary IP address based on the at least one trained prediction model to obtain the confidence of whether each second candidate boundary IP address is a boundary IP address includes:

[0059] Step c1, for any of the second candidate boundary IP addresses, input all boundary verification parameters of the second candidate boundary IP address into each of the prediction models respectively, and obtain the first confidence level of each prediction model in predicting whether the second candidate boundary IP address is a boundary IP address.

[0060] Here, for any second candidate boundary IP address, all boundary verification parameters of the second candidate boundary IP address are input into each prediction model as test set data to obtain the first confidence level of each prediction model in predicting whether the second candidate boundary IP address is a boundary IP address.

[0061] Step c2: based on the reference weights of the prediction models, weighted average is performed on the first confidences corresponding to the prediction models to obtain the second confidence of the second candidate boundary IP address.

[0062] Here, based on the reference weights of the prediction models, the first confidences corresponding to the prediction models are weighted averaged to obtain the second confidence of the second candidate boundary IP address, wherein the reference weights of the prediction models are the matching degrees between the prediction models and the target geographic area.

[0063] Step c3: determining the second confidence level of each of the second candidate boundary IP addresses as the confidence level of whether each of the second candidate boundary IP addresses is a boundary IP address.

[0064] Here, the second confidence level of each second candidate boundary IP address is determined as the confidence level of whether each second candidate boundary IP address is a boundary IP address.

[0065] In the embodiment of the present application, the reason for selecting multiple prediction models is that different prediction models have different verification effects on target geographical areas with different network topologies. In the embodiment of the present application, multiple prediction models are trained and then used to evaluate and predict the test set data. At the same time, the reference weights of each prediction model are set according to the degree of match between each prediction model and the target geographical area, and a weighted average is performed to obtain the confidence level of whether each second candidate boundary IP address is a boundary IP address.

[0066] Further, the reference weights of the prediction models are determined according to the following steps:

[0067] Step d1, for any of the prediction models, determines the first matching degree of the prediction model relative to the target geographic area based on the distribution of the first confidence levels of each of the second candidate boundary IP addresses output by the prediction model and the distribution of the number of boundary verification parameters of each of the second candidate boundary IP addresses that pass boundary judgment.

[0068] In the embodiment of the present application, there are two ways to determine the degree of match between the prediction model and the target geographic area. The first way is to determine the first degree of match between the prediction model and the target geographic area for any prediction model based on the distribution of the first confidence levels of each second candidate boundary IP address output by the prediction model and the distribution of the number of boundary verification parameters of each second candidate boundary IP address that passes boundary judgment. That is, the higher the degree of similarity between the distribution of the number of boundary verifications of each second candidate boundary IP address that passes boundary judgment during the first verification and the confidence level output by the corresponding prediction model, the higher the degree of match between the prediction model and the network topology of the target geographic area. Conversely, the lower the degree of similarity, the lower the degree of match.

[0069] Step d2, input all boundary verification parameters of each IP address in the network topology structure into the prediction model, predict multiple third candidate boundary IP addresses of the target geographical area, and determine the second matching degree of the prediction model relative to the target geographical area based on the similarity between the set of the third candidate boundary IP addresses and the set of the first candidate boundary IP addresses.

[0070] Here, the second method is to input all boundary verification parameters of each IP address in the network topology into the prediction model, predict multiple third candidate boundary IP addresses of the target geographical area, and determine the second matching degree of the prediction model relative to the target geographical area based on the similarity between the set of third candidate boundary IP addresses and the set of first candidate boundary IP addresses obtained above. That is, the prediction model is used to predict all IP addresses in the target geographical area, and then the similarity between the candidate boundary IP addresses predicted by the prediction model and the first candidate boundary IP addresses obtained through the geographical location of the IP addresses is used as the matching degree of the prediction model relative to the target geographical area. If the degree of overlap is higher, it means that the matching degree of the prediction model and the network topology of the target geographical area is higher. Conversely, the lower the degree of overlap, the lower the matching degree.

[0071] Step d3: determining a reference weight of each prediction model based on the first matching degree and / or the second matching degree of each prediction model.

[0072] Here, based on the first matching degree and / or the second matching degree of each prediction model, the reference weight of each prediction model is determined. In the embodiment of the present application, the above two matching methods can be used alone to determine the reference weight of each prediction model, or can be used together to determine the reference weight of each prediction model, and no specific limitation is made here.

[0073] Further, the determining of the border backbone routing of the target geographical area based on each of the first border IP address, the second border IP address and the router alias resolution algorithm includes:

[0074] Step e1, clustering the IP addresses belonging to the same router in the first boundary IP address and the second boundary IP address according to the router alias resolution algorithm to obtain multiple target routers.

[0075] Here, according to the router alias resolution algorithm, the IP addresses belonging to the same router in the first boundary IP address and the second boundary IP address are clustered to obtain multiple target routers. In the embodiment of the present application, the router alias resolution algorithm uses the router interface merging function to realize the mapping of the boundary IP address to the boundary backbone router. Specifically, based on the obtained data set of the boundary IP address, a router alias resolution method based on the IP identification field (IP-ID, IP identification) is adopted. Since multiple interface IPs of the router usually share a unique counter, each time a message is generated, the counter will set a corresponding value in the IP identification field of the message header. If the message is continuous, the IP-ID value often increases continuously and linearly. According to this feature, the method based on the identification field sends multiple request messages to the boundary IP addresses that may have an alias relationship in a short period of time, and uses the similarity relationship of the IP-ID sequence in the corresponding message to perform router alias resolution. The embodiment of the present application uses the router alias resolution algorithm to cluster the boundary IP addresses belonging to the same router to obtain multiple target routers. It should also be noted that part of the topology data in the embodiment of the present application comes from the open source data downloaded by CAIDA. The CAIDA ITDK dataset performs partial alias resolution on the detection results. Therefore, for this part of the data, the effect of router alias resolution is verifiable.

[0076] Step e2: determine each of the target routers as a border backbone router of the target geographical area.

[0077] Here, each target router is determined as a border backbone route of the target geographical area, and finally a router-level border backbone route is obtained.

[0078] The embodiment of the present application provides a method for determining a border backbone route, including: determining a network topology structure of a target geographical area based on measured network topology information and open source network topology information of the target geographical area; determining a plurality of first candidate border IP addresses of the target geographical area based on the geographical locations of each IP address in the network topology structure; performing boundary judgment on each first candidate border IP address based on a plurality of preset boundary verification parameters, marking a first candidate border IP address whose number of boundary verification parameters passing the boundary judgment is greater than or equal to a preset number threshold as a first border IP address, and marking a first candidate border IP address whose number of boundary verification parameters passing the boundary judgment is less than the number threshold as a second candidate border IP address; training at least one prediction model based on the boundary verification parameters of each first border IP address, and predicting the boundary verification parameters of each second candidate border IP address based on the at least one trained prediction model to obtain a confidence level of whether each second candidate border IP address is a border IP address; selecting a plurality of second border IP addresses whose confidence levels are higher than a preset confidence threshold from each second candidate border IP address, and determining a border backbone route of the target geographical area based on each first border IP address, the second border IP address, and a router alias resolution algorithm. In this way, the network boundary of the target geographic area is fully verified through multiple boundary verification parameters, a more accurate boundary IP address is obtained, and the accuracy of boundary backbone routing determination is improved.

[0079] Based on the same application concept, the embodiments of the present application also provide a device for determining border backbone routes corresponding to the method for determining border backbone routes provided in the above embodiments. Since the principle of solving the problem by the device in the embodiments of the present application is similar to the method for determining border backbone routes in the above embodiments of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0080] See also Figure 2 , Figure 2 This is one of the functional module diagrams of a device for determining a border backbone route provided in an embodiment of the present application. Figure 2 As shown, the border backbone route determination device 200 includes:

[0081] The first determination module 210 is configured to determine a network topology structure of a target geographical area based on measured network topology information and open source network topology information of the target geographical area.

[0082] The second determination module 220 is configured to determine a plurality of first candidate boundary IP addresses of the target geographic area based on the geographic location of each IP address in the network topology.

[0083] The judgment classification module 230 is used to perform boundary judgment on each of the first candidate boundary IP addresses based on a plurality of preset boundary verification parameters, and mark the first candidate boundary IP address whose number of boundary verification parameters passing the boundary judgment is greater than or equal to a preset number threshold as a first boundary IP address, and mark the first candidate boundary IP address whose number of boundary verification parameters passing the boundary judgment is less than the number threshold as a second candidate boundary IP address.

[0084] The training prediction module 240 is used to train at least one prediction model based on the boundary verification parameters of each of the first boundary IP addresses, and predict the boundary verification parameters of each of the second candidate boundary IP addresses based on the trained at least one prediction model to obtain the confidence level of whether each of the second candidate boundary IP addresses is a boundary IP address.

[0085] The third determination module 250 is used to select multiple second boundary IP addresses with confidence levels higher than a preset confidence threshold from each of the second candidate boundary IP addresses, and determine the boundary backbone routing of the target geographic area based on each of the first boundary IP addresses, the second boundary IP addresses and the router alias resolution algorithm.

[0086] For further information, see Figure 3 , Figure 3 The second functional module diagram of a device for determining a border backbone route provided in an embodiment of the present application is as follows: Figure 3 As shown, the border backbone route determination device 200 also includes:

[0087] A topology measurement module 260 is used to deploy multiple detection points inside and outside the target geographical area, and use a network diagnostic tool to perform multiple measurements at each of the detection points to obtain measured network topology information of the target geographical area;

[0088] A topology acquisition module 270 is used to acquire historical network topology data of the target geographical area from an open source website to obtain open source network topology information of the target geographical area;

[0089] The first determination module 210 is further configured to obtain a network topology structure of the target geographical area by taking a union of the measured network topology information and the open source network topology information of the target geographical area.

[0090] Further, when the second determination module 220 is used to determine a plurality of first candidate boundary IP addresses of the target geographical area based on the geographical location of each IP address in the network topology structure, the second determination module 220 is specifically used to:

[0091] Finding the geographical location of each IP address in the network topology from an IP address geolocation database and determining a plurality of target IP addresses; the target IP address is the first IP address that crosses from within the target geographic area to outside the area;

[0092] Each of the target IP addresses, and the IP addresses two hops before and after each of the target IP addresses, are determined as a plurality of first candidate boundary IP addresses of the target geographic area.

[0093] In a possible implementation, when the number of prediction models is more than one, the training prediction module 240 is used to predict the boundary verification parameter of each second candidate boundary IP address based on the at least one trained prediction model to obtain the confidence of whether each second candidate boundary IP address is a boundary IP address, and the training prediction module 240 is specifically used to:

[0094] For any of the second candidate boundary IP addresses, all boundary verification parameters of the second candidate boundary IP address are respectively input into each of the prediction models to obtain a first confidence level of each prediction model in predicting whether the second candidate boundary IP address is a boundary IP address;

[0095] Based on the reference weights of the prediction models, weighted average is performed on the first confidences corresponding to the prediction models to obtain a second confidence of the second candidate boundary IP address;

[0096] The second confidence level of each of the second candidate boundary IP addresses is determined as the confidence level of whether each of the second candidate boundary IP addresses is a boundary IP address.

[0097] Furthermore, the training prediction module 240 is further configured to determine the reference weights of the prediction models according to the following steps:

[0098] For any of the prediction models, based on the distribution of the first confidence levels of each of the second candidate boundary IP addresses output by the prediction model and the distribution of the number of boundary verification parameters for each of the second candidate boundary IP addresses that pass boundary judgment, determine the first matching degree of the prediction model relative to the target geographic area;

[0099] Inputting all boundary verification parameters of each IP address in the network topology structure into the prediction model, predicting a plurality of third candidate boundary IP addresses of the target geographical area, and determining a second matching degree of the prediction model relative to the target geographical area based on the similarity between the set of the third candidate boundary IP addresses and the set of the first candidate boundary IP addresses;

[0100] Based on the first matching degree and / or the second matching degree of each of the prediction models, a reference weight of each of the prediction models is determined.

[0101] Further, when the third determination module 250 is used to determine the border backbone routing of the target geographical area based on each of the first border IP address, the second border IP address and the router alias resolution algorithm, the third determination module 250 is specifically used to:

[0102] Clustering the IP addresses of the first boundary IP address and the second boundary IP address belonging to the same router according to the router alias resolution algorithm to obtain multiple target routers;

[0103] Each of the target routers is determined as a border backbone router of the target geographical area.

[0104] The embodiment of the present application provides a device for determining a border backbone route, including: a first determination module, used to determine the network topology structure of the target geographical area based on the measured network topology information and open source network topology information of the target geographical area; a second determination module, used to determine multiple first candidate border IP addresses of the target geographical area based on the geographical location of each IP address in the network topology structure; a judgment classification module, used to perform boundary judgment on each first candidate border IP address based on multiple preset boundary verification parameters, mark the first candidate border IP address whose number of boundary verification parameters passing the boundary judgment is greater than or equal to a preset number threshold as the first border IP address, and mark the first candidate border IP address whose number of boundary verification parameters passing the boundary judgment is greater than or equal to a preset number threshold as the first border IP address. The first candidate boundary IP address whose quantity is less than the quantity threshold is marked as the second candidate boundary IP address; the training prediction module is used to train at least one prediction model based on the boundary verification parameters of each first boundary IP address, and predict the boundary verification parameters of each second candidate boundary IP address based on the at least one trained prediction model to obtain the confidence of whether each second candidate boundary IP address is a boundary IP address; the third determination module is used to select multiple second boundary IP addresses with confidence higher than the preset confidence threshold from each second candidate boundary IP address, and determine the boundary backbone route of the target geographical area based on each first boundary IP address, the second boundary IP address and the router alias resolution algorithm. In this way, the network boundary of the target geographical area is fully verified through multiple boundary verification parameters, and a more accurate boundary IP address is obtained, which improves the accuracy of the boundary backbone route determination.

[0105] Based on the same application idea, please refer to Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4 As shown, the electronic device 400 includes a processor 410 , a memory 420 and a bus 430 .

[0106] The memory 420 stores machine-readable instructions executable by the processor 410. When the electronic device 400 is running, the processor 410 communicates with the memory 420 through the bus 430. The machine-readable instructions are executed by the processor 410 when running to perform the steps of the method for determining the border backbone routing as described in any of the above embodiments. The specific implementation method can be found in the method embodiment, which will not be repeated here.

[0107] Based on the same application concept, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for determining the border backbone route provided in the above embodiment are executed. The specific implementation method can be found in the method embodiment, which will not be repeated here.

[0108] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0109] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0110] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0111] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0112] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0113] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0114] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for determining a border backbone route, characterized in that: The method comprises: Determining a network topology structure of the target geographic area based on measured network topology information and open source network topology information of the target geographic area; Determine a plurality of first candidate boundary IP addresses of the target geographic area based on the geographic location of each IP address in the network topology; Based on a plurality of preset boundary verification parameters, a boundary judgment is performed on each of the first candidate boundary IP addresses, and a first candidate boundary IP address whose number of boundary verification parameters passing the boundary judgment is greater than or equal to a preset number threshold is marked as a first boundary IP address, and a first candidate boundary IP address whose number of boundary verification parameters passing the boundary judgment is less than the number threshold is marked as a second candidate boundary IP address; the plurality of preset boundary verification parameters include an IP address geolocation parameter, a latency parameter, a node geographic location information parameter, a node asset information, and hierarchical information of the autonomous system where the node is located; Based on the boundary verification parameters of each of the first boundary IP addresses, at least one prediction model is trained, and based on the at least one trained prediction model, the boundary verification parameter of each of the second candidate boundary IP addresses is predicted to obtain the confidence level of whether each of the second candidate boundary IP addresses is a boundary IP address; A plurality of second boundary IP addresses with confidence levels higher than a preset confidence threshold are selected from each of the second candidate boundary IP addresses, and the boundary backbone routing of the target geographic area is determined based on each of the first boundary IP addresses, the second boundary IP addresses and the router alias resolution algorithm.

2. The method for determining border backbone routing according to claim 1, characterized in that: The determining of the network topology structure of the target geographical area based on the measured network topology information and the open source network topology information of the target geographical area includes: Deploy multiple detection points inside and outside the target geographical area respectively, and use a network diagnostic tool to perform multiple measurements at each of the detection points to obtain measurement network topology information of the target geographical area; Acquire historical network topology data of the target geographical area from an open source website to obtain open source network topology information of the target geographical area; The measured network topology information and the open source network topology information of the target geographical area are combined to obtain the network topology structure of the target geographical area.

3. The method for determining border backbone routing according to claim 1, characterized in that: The step of determining a plurality of first candidate boundary IP addresses of the target geographical area based on the geographical locations of the respective IP addresses in the network topology structure comprises: Finding the geographical location of each IP address in the network topology from an IP address geolocation database and determining a plurality of target IP addresses; the target IP address is the first IP address that crosses from within the target geographic area to outside the area; Each of the target IP addresses, and the IP addresses two hops before and after each of the target IP addresses, are determined as a plurality of first candidate boundary IP addresses of the target geographic area.

4. The method for determining border backbone routing according to claim 1, characterized in that: The node geographic location information parameter includes at least one of the node's domain name registration information, host name information, and route tracking information.

5. The method for determining border backbone routing according to claim 1, characterized in that: When the number of prediction models is more than one, predicting the boundary verification parameter of each second candidate boundary IP address based on the at least one trained prediction model to obtain the confidence of whether each second candidate boundary IP address is a boundary IP address includes: For any of the second candidate boundary IP addresses, all boundary verification parameters of the second candidate boundary IP address are respectively input into each of the prediction models to obtain a first confidence level of each prediction model in predicting whether the second candidate boundary IP address is a boundary IP address; Based on the reference weights of the prediction models, weighted average is performed on the first confidences corresponding to the prediction models to obtain a second confidence of the second candidate boundary IP address; The second confidence level of each of the second candidate boundary IP addresses is determined as the confidence level of whether each of the second candidate boundary IP addresses is a boundary IP address.

6. The method for determining border backbone routing according to claim 5, characterized in that: The reference weights of the prediction models are determined according to the following steps: For any of the prediction models, based on the distribution of the first confidence levels of each of the second candidate boundary IP addresses output by the prediction model and the distribution of the number of boundary verification parameters for each of the second candidate boundary IP addresses that pass boundary judgment, determine the first matching degree of the prediction model relative to the target geographic area; Inputting all boundary verification parameters of each IP address in the network topology structure into the prediction model, predicting a plurality of third candidate boundary IP addresses of the target geographical area, and determining a second matching degree of the prediction model relative to the target geographical area based on the similarity between the set of the third candidate boundary IP addresses and the set of the first candidate boundary IP addresses; Based on the first matching degree and / or the second matching degree of each of the prediction models, a reference weight of each of the prediction models is determined.

7. The method for determining border backbone routing according to claim 1, characterized in that: The step of determining the border backbone routing of the target geographical area based on the first border IP address, the second border IP address and the router alias resolution algorithm includes: Clustering the IP addresses of the first boundary IP address and the second boundary IP address belonging to the same router according to the router alias resolution algorithm to obtain multiple target routers; Each of the target routers is determined as a border backbone router of the target geographical area.

8. A device for determining a border backbone route, characterized in that: The border backbone routing determination device includes: A first determination module, configured to determine a network topology structure of a target geographical area based on measured network topology information and open source network topology information of the target geographical area; A second determination module, configured to determine a plurality of first candidate boundary IP addresses of the target geographic area based on the geographic location of each IP address in the network topology structure; A judgment classification module, used to perform boundary judgment on each of the first candidate boundary IP addresses based on a plurality of preset boundary verification parameters, mark the first candidate boundary IP address whose number of boundary verification parameters passing the boundary judgment is greater than or equal to a preset number threshold as a first boundary IP address, and mark the first candidate boundary IP address whose number of boundary verification parameters passing the boundary judgment is less than the number threshold as a second candidate boundary IP address; the plurality of preset boundary verification parameters include IP address geolocation parameters, latency parameters, node geographic location information parameters, node asset information, and hierarchical information of the autonomous system where the node is located; A training prediction module, used to train at least one prediction model based on the boundary verification parameters of each of the first boundary IP addresses, and predict the boundary verification parameters of each of the second candidate boundary IP addresses based on the trained at least one prediction model to obtain the confidence level of whether each of the second candidate boundary IP addresses is a boundary IP address; The third determination module is used to select multiple second boundary IP addresses with confidence levels higher than a preset confidence threshold from each of the second candidate boundary IP addresses, and determine the boundary backbone routing of the target geographic area based on each of the first boundary IP addresses, the second boundary IP addresses and the router alias resolution algorithm.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to perform the steps of the method for determining the border backbone routing as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for determining a border backbone route according to any one of claims 1 to 7 are executed.

Images