Local area network (LAN) element management methods, devices, electronic equipment, and storage media

Abstract

This application relates to a method, apparatus, electronic device, and storage medium for managing network elements in a local area network (LAN). The method is applied to control devices within a LAN, which includes multiple network elements. The method includes: acquiring network element resource information and communication information corresponding to each of the multiple network elements; extracting features from the network element resource information of each network element to obtain resource features corresponding to each network element; generating a target feature matrix for the LAN based on the resource features of each network element; generating a target adjacency matrix for the LAN based on the communication information of each of the multiple network elements; generating a resource matrix for the LAN based on a graph convolutional neural network, using the target feature matrix and the target adjacency matrix; and managing the traffic corresponding to each network element based on the resource matrix. This LAN network element management method, apparatus, control device, and storage medium improve the intelligence level of network element management.

Description

Technical Field

[0001] This application relates to the field of Internet technology, specifically to a method, apparatus, electronic device, and storage medium for managing network elements in a local area network. Background Technology

[0002] Currently, network asset management, especially the management of network elements within enterprise local area networks (LANs), almost entirely relies on manual approval, management, and inspection. Therefore, the management of various network elements within the LAN is dominated by manual judgment, resulting in low efficiency and a high risk of subjective errors. Summary of the Invention

[0003] This application discloses a method, apparatus, electronic device, and storage medium for managing network elements in a local area network (LAN), which can improve the efficiency and accuracy of network element management, thereby enhancing the level of intelligence in network element management.

[0004] In a first aspect, embodiments of this application disclose a network element management method for a local area network (LAN), applied to a control device in the LAN, wherein the LAN further includes multiple network elements; the method includes:

[0005] Obtain network element resource information corresponding to the plurality of network elements respectively, and communication information corresponding to the plurality of network elements respectively; wherein, the communication information corresponding to the first network element is used to indicate the various other network elements that the first network element can communicate with, and the first network element is any one of the plurality of network elements;

[0006] Extract the features of the network element resource information corresponding to each network element to obtain the resource features corresponding to each network element;

[0007] Based on the resource characteristics corresponding to each of the network elements, a target feature matrix corresponding to the local area network is generated;

[0008] Based on the communication information corresponding to the multiple network elements, a target adjacency matrix corresponding to the local area network is generated;

[0009] Based on a graph convolutional neural network, a resource matrix corresponding to the local area network is generated according to the target feature matrix and the target adjacency matrix. The resource matrix is ​​used to indicate the association relationship of the multiple network elements in the local area network.

[0010] Based on the resource matrix, the traffic corresponding to each network element is managed.

[0011] As an optional implementation, in a first aspect of this application, the communication information corresponding to the first network element includes communication information of the first network element accessing the second network element. This communication information includes the number of first ports that the first network element can access in the second network element, the number of second ports that the second network element can access in the first network element, and the communication protocol types supported by the first network element and the second network element. The second network element is any other network element that the first network element can communicate with. The step of generating a target adjacency matrix corresponding to the local area network based on the communication information corresponding to the plurality of network elements includes: generating matrix elements corresponding to the first network element accessing the second network element based on the number of first ports, the number of second ports, and the communication protocol types; and generating the target adjacency matrix corresponding to the local area network based on matrix elements corresponding to any network element in the local area network accessing another network element.

[0012] As an optional implementation, in a first aspect of this application, the step of generating a resource matrix corresponding to the local area network based on a graph convolutional neural network, according to the target feature matrix and the target adjacency matrix, includes: using the target feature matrix and the target adjacency matrix as the input matrix of the first layer of the graph convolutional neural network; encoding the input matrix of the current layer based on the graph convolution formula corresponding to the current layer to obtain the output matrix of the current layer; using the output matrix of the current layer and the target adjacency matrix as the input matrix of the next layer, and continuing to execute the step of encoding the input matrix of the current layer based on the graph convolution formula corresponding to the current layer to obtain the output matrix of the current layer, until the output matrix of the last layer is obtained; and using the output matrix of the last layer as the resource matrix corresponding to the local area network.

[0013] As an optional implementation, in a first aspect of this application, the training process of the graph convolutional neural network includes: acquiring a sample set and constructing a pre-trained graph convolutional neural network according to preset parameters; the sample set includes multiple sample feature matrices, corresponding sample adjacency matrices, and corresponding target resource matrices; based on the pre-trained graph convolutional neural network, generating a sample resource matrix corresponding to the first sample feature matrix according to the first sample feature matrix and the corresponding sample adjacency matrix; the first sample feature matrix is ​​any sample feature matrix in the sample set; calculating the loss error corresponding to the pre-trained graph convolutional neural network according to the sample resource matrix and the corresponding target resource matrix of each sample feature matrix; if the loss error is greater than a preset loss value, adjusting the graph convolution formula corresponding to each layer in the pre-trained graph convolutional neural network to obtain a new pre-trained graph convolutional neural network; repeatedly executing the step of generating the sample resource matrix corresponding to the first sample feature matrix based on the pre-trained graph convolutional neural network and the corresponding sample adjacency matrix, until the loss error is less than or equal to the preset loss value, and obtaining a trained graph convolutional neural network.

[0014] As an optional implementation, in a first aspect of this application embodiment, the resource matrix includes network element vectors corresponding to the plurality of network elements respectively, and the network element vector corresponding to the first network element is used to indicate the association relationship between the first network element and each network element in the local area network; the step of managing the traffic corresponding to each network element according to the resource matrix includes: receiving an access request sent by the first network element, the access request including network element information corresponding to a third network element to be accessed by the first network element; the third network element is any network element in the local area network that is different from the first network element; determining, according to the access request, a first network element vector corresponding to the first network element and a second network element vector corresponding to the third network element from the resource matrix; calculating the vector distance between the first network element vector and the second network element vector to obtain a first distance; if the first distance is less than or equal to a preset distance threshold, then forwarding the access request to the third network element.

[0015] As an optional implementation, in a first aspect of the present application, the step of managing the traffic corresponding to each network element according to the resource matrix includes: if no network element resource information sent by the first network element is received within a preset time period, then, according to the resource matrix, determining at least one accessible network element that can access the first network element, and at least one accessed network element that the first network element can access; adjusting the traffic transmission direction between the at least one accessible network element and the at least one accessed network element, so that the at least one accessible network element can access the at least one accessed network element.

[0016] As an optional implementation, in a first aspect of this application, the network element resource information corresponding to the first network element includes multiple target network element resources corresponding to the first network element; the step of extracting features of the network element resource information corresponding to each network element to obtain resource features corresponding to each network element includes: determining the mapping data corresponding to the multiple target network element resources corresponding to the first network element according to a resource mapping table, so as to obtain resource features corresponding to the first network element; the resource mapping table includes each network element resource and its corresponding mapping value.

[0017] Secondly, embodiments of this application disclose a network element management device for a local area network (LAN), applied to a control device within the LAN, wherein the LAN further includes multiple network elements; the device includes:

[0018] The information acquisition module is used to acquire network element resource information corresponding to the plurality of network elements respectively, and communication information corresponding to the plurality of network elements respectively; wherein, the communication information corresponding to the first network element is used to indicate the various other network elements that the first network element can communicate with, and the first network element is any one of the plurality of network elements;

[0019] The feature extraction module is used to extract features of the network element resource information corresponding to each network element, and obtain the resource features corresponding to each network element.

[0020] The matrix generation module is used to generate a target feature matrix corresponding to the local area network based on the resource characteristics corresponding to each network element.

[0021] The matrix generation module is further configured to generate a target adjacency matrix corresponding to the local area network based on the communication information corresponding to the plurality of network elements respectively.

[0022] The graph convolution module is used to generate a resource matrix corresponding to the local area network based on the target feature matrix and the target adjacency matrix, according to the graph convolutional neural network. The resource matrix is ​​used to indicate the association relationship of the multiple network elements in the local area network.

[0023] The network element management module is used to manage the traffic corresponding to each network element according to the resource matrix.

[0024] Thirdly, embodiments of this application disclose an electronic device, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the processor causes the processor to implement the method described in any of the above embodiments.

[0025] Fourthly, embodiments of this application disclose a computer-readable storage medium that stores a computer program, which, when executed by a processor, implements the methods described in any of the above embodiments.

[0026] Fifthly, embodiments of this application disclose a computer program product, including a computer program, wherein when the computer program is executed by a processor, it implements the method described in any of the above embodiments.

[0027] The embodiments of this application disclose a method, apparatus, control device, and storage medium for managing network elements in a local area network (LAN). This method acquires network element resource information and communication information corresponding to multiple network elements. The communication information corresponding to a first network element indicates which other network elements the first network element can communicate with, and the first network element is any one of the multiple network elements. Features of the network element resource information corresponding to each network element are extracted to obtain resource features corresponding to each network element. A target feature matrix corresponding to the LAN is generated based on the resource features corresponding to each network element. A target adjacency matrix corresponding to the LAN is generated based on the communication information corresponding to multiple network elements. A resource matrix corresponding to the LAN is generated based on a graph convolutional neural network, according to the target feature matrix and the target adjacency matrix. The resource matrix indicates the association relationships of multiple network elements in the LAN. Traffic corresponding to each network element is managed based on the resource matrix. In this embodiment, the control device in the local area network (LAN) extracts resource features from the network element resource information of each network element to generate a target feature matrix, and generates a target adjacency matrix based on the communication information corresponding to each network element. The target feature matrix and target adjacency matrix are then processed by a graph convolutional neural network to obtain a resource matrix. Since the target feature matrix and target adjacency matrix can accurately characterize the resource status of each network element in the LAN and the communication relationships between different network elements, the resulting resource matrix can accurately reflect the correlation relationships between different network elements within the LAN. Based on this resource matrix, the control device can more accurately manage the traffic of each network element in the LAN according to the correlation relationships between different network elements, improving the efficiency and accuracy of network element management and enhancing the intelligence level of network element management. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is an application scenario diagram of a local area network (LAN) element management method in one embodiment;

[0030] Figure 2 This is a flowchart of a local area network (LAN) element management method in one embodiment;

[0031] Figure 3 This is a flowchart illustrating the generation of a target adjacency matrix in one embodiment;

[0032] Figure 4 This is a flowchart illustrating the generation of a resource matrix in one embodiment;

[0033] Figure 5 This is a flowchart illustrating the training process of a convolutional neural network in one embodiment.

[0034] Figure 6 This is a flowchart illustrating the management process of network elements in one embodiment;

[0035] Figure 7 This is a flowchart illustrating the management process of network elements in one embodiment;

[0036] Figure 8 This is a block diagram of a local area network (LAN) element management device in one embodiment.

[0037] Figure 9 This is a structural block diagram of the control device in one embodiment. Detailed Implementation

[0038] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0039] It should be noted that the terms "comprising" and "having," and any variations thereof, in the embodiments and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0040] It is understood that the terms "first," "second," etc., used in this application may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another. For example, without departing from the scope of this application, a first sub-energy portion may be referred to as a second sub-energy portion, and similarly, a second sub-energy portion may be referred to as a first sub-energy portion. Both the first and second sub-energy portions contain at least one sub-energy portion, but they are different sub-energy portions.

[0041] In related technologies, information about each network element is identified manually, and the status of each network element and its communication relationship with other network elements are also managed manually. Specifically, traffic management, policy approval, and network communication all rely on manual judgment. It is necessary for humans to conduct regular or irregular network checks to discover potential problems. There is a lack of automated management methods, making it impossible to respond to various emergencies in a timely manner and to perform automated operations.

[0042] This application discloses a method, apparatus, electronic device, and storage medium for managing network elements in a local area network (LAN), which can improve the efficiency and accuracy of network element management and enhance the level of intelligence in network element management.

[0043] The following is an introduction to some of the terms used in this application:

[0044] Local Area Network (LAN): In this application, a LAN, also known as an intranet, refers to a communication network that connects various computers, peripherals, and databases within a predetermined area (such as an office, a building, or a floor). For example, the internal network of an organization or enterprise.

[0045] Network element: refers to various network devices and servers in a local area network, including but not limited to physical network elements (such as switches, routers, base stations, etc.) and virtual network elements (such as virtual machines, containers, etc.).

[0046] Network element resource information refers to detailed information about the network element itself, such as its physical information and model parameters.

[0047] The communication information corresponding to a network element describes the communication relationship between the network element and other network elements in the local area network that can communicate.

[0048] The target feature matrix contains the resource characteristics of each network element in the local area network (LAN). Each row of the target feature matrix can represent a network element, and each column can represent a resource characteristic (such as CPU utilization, memory utilization, disk utilization, etc.). The target feature matrix can include N*M elements, where N represents the number of network elements in the LAN, and M represents the number of resource characteristics for each network element. For example, the element x in the target feature matrix... 12 It can represent the resource characteristics of the second network element of the first network element in a local area network.

[0049] A target adjacency matrix is ​​used to characterize the communication relationships between different network elements in a local area network (LAN). The target adjacency matrix can include N*N elements, each representing whether one network element can access another, or the degree of access from one network element to another. For example, the element y in the target adjacency matrix... 12 A value of 1 indicates that the first network element in the local area network can access the second network element.

[0050] A resource matrix is ​​used to indicate the relationships between multiple network elements in a local area network (LAN). The resource matrix integrates the resource information and corresponding communication information of each network element; each element can represent a resource characteristic or communication information. For example, element z of the resource matrix... 12 It can represent the correlation strength between the first network element and the second network element in a local area network in terms of specific resource characteristics or communication information.

[0051] Graph Convolutional Neural Networks (GNNs) are neural network models used to process graph data. Their core idea is to extend convolution operations from traditional data (such as images or grids) to graph data. In this application, a GNN can learn a graph convolution formula that aggregates the features of a node (network element) in the graph data as well as the features of its neighboring nodes, thereby generating a relational representation of the node.

[0052] Figure 1 For the application scenarios of local area network (LAN) element management methods, the LAN element management analysis method provided in this application can be applied to, for example... Figure 1 In the control device 100 shown. For example... Figure 1 As shown, within the local area network (LAN) where the control device 100 is located, the control device 100 can communicate with any network element 110 within the LAN. The control device 100 may include, but is not limited to, smart terminal devices, tablet computers, PCs (Personal Computers), computers, laptops, servers, or server clusters. Any network element 110 needs to communicate with other network elements 110 through the control device 100.

[0053] It should be noted that each network element 110 connected to this local area network is managed by the control device 100 of this local area network. This management includes access management, traffic management, security management, and other aspects.

[0054] Access management is used to control whether each network element 110 in a local area network can access another network element 110. Through access management, it can be ensured that only network elements 110 authorized by the control device 100 can access specific network resources or services, thereby preventing unauthorized access and data leakage.

[0055] Traffic management controls the uplink and downlink speeds of network element 110 in obtaining network services, as well as the allocation of network resources. It also involves the feasibility management of network element communication and the management of network element data packet transmission. Traffic management can include bandwidth limiting, traffic priority settings, and traffic monitoring. Through traffic management, it is possible to ensure that network resources in the local area network are allocated reasonably, avoiding network congestion and performance degradation.

[0056] Security management is used to detect whether network element 110 is secure in order to determine whether to grant network element 110 network services for the local area network. Through security management, security risks such as network attacks and virus intrusions can be detected and addressed in a timely manner, protecting network and data security.

[0057] The control device 100 can obtain network element resource information from each network element 110, and obtain communication information corresponding to each network element 110 from each network element 110 or from the control device 100 itself. The control device 100 extracts features from the network element resource information corresponding to each network element 110 to obtain resource features corresponding to each network element 110; and generates a target feature matrix corresponding to the local area network based on the resource features corresponding to each network element 110. The control device 100 can generate a target adjacency matrix corresponding to the local area network based on the communication information corresponding to multiple network elements 110 respectively; then, based on a graph convolutional neural network, it generates a resource matrix corresponding to the local area network based on the target feature matrix and the target adjacency matrix. The control device 100 manages the traffic corresponding to each network element 110 according to the resource matrix, thereby improving the efficiency and accuracy of network element management and enhancing the intelligence level of the control device 100 in managing network elements 110.

[0058] like Figure 2 As shown, in one embodiment, a method for managing network elements in a local area network is provided, which can be applied to the aforementioned control device. The method may include the following steps:

[0059] Step 210: Obtain the network element resource information corresponding to each of the multiple network elements, as well as the communication information corresponding to each of the multiple network elements.

[0060] In some embodiments, the first network element is any one of multiple network elements within a local area network.

[0061] In some embodiments, the network element resource information corresponding to the first network element may include multiple target network element resources corresponding to the first network element. Here, target network element resources refer to various information that can describe and define the characteristics and capabilities of a network element. Specifically, the multiple target network element resources in the network element resource information may include, but are not limited to, the network element's model, serial number, hardware configuration (such as CPU, memory, disk, etc.), software version, interface type, etc. For example, the network element resource information of a router may include its brand, model, CPU model, memory size, network interface type and quantity, etc.

[0062] In some embodiments, the communication information corresponding to the first network element may include, but is not limited to, one or more of the following: the first network element's own IP address, port number, number of ports, MAC address, routing table, and access control list. It may also include, one or more of the following: the IP address (Internet Protocol Address), MAC address (Media Access Control Address), port number, number of ports, routing table, and access control list of other network elements that the first network element can communicate with. Here, a routing table refers to a database or table structure within a network element used to determine how data packets are transmitted from the source address to the destination address via the network; an access control list refers to a network security policy tool used to define which data packets can be received and which data packets can be denied access; other network elements refer to any network element within the local area network that is different from the first network element.

[0063] Optionally, the communication information corresponding to the first network element includes communication information of the first network element accessing the second network element. This communication information includes the number of first ports that the first network element can access in the second network element, the number of second ports that the second network element can access from the first network element, and the communication protocol types supported by the first and second network elements. The first network element is any network element in the local area network; the second network element is any other network element that the first network element can communicate with. For example, the communication information of network element A accessing network element B includes that the first port that network element A can access in network element B is port a, the second port that network element B can access from network element A is port c, and the supported communication protocol type is TCP (Transmission Control Protocol), meaning that port a of network element A can send an access request to port c of network element B via the CAN bus protocol and receive a response.

[0064] In some embodiments, each network element in the local area network (LAN) may send network element resource information to the control device at first time intervals. Optionally, the first time interval can be set according to the network services of the LAN. For example, when network services change frequently, the first time interval can be set to a shorter interval; while when network services are relatively stable or resources do not change much, the first time interval can be set to a longer interval.

[0065] Optionally, the control device can send resource acquisition requests to various networks. Upon receiving a resource acquisition request, each network element sends its network element resource information to the control device. The resource acquisition request is used to request network element resource information from each network element. Specifically, the resource acquisition request may contain the specific network element resources for which the control device needs to acquire network element resource information. The network element can then send the required network element resource information to the control device based on the resource acquisition request.

[0066] In some embodiments, the control device may obtain a preset permission table and retrieve communication information corresponding to each network element currently connected to the local area network from the preset permission table. The preset permission table is used to indicate the access permission relationships between various network elements and may include which other network elements a network element can access, or which other network elements can access the network element. Optionally, the preset permission table may be updated in real time.

[0067] In some embodiments, the control device can determine the communication level corresponding to each network element and the network element resource information corresponding to each network element, wherein each network element can access other network elements with a communication level no higher than its own. Optionally, the communication level corresponding to each network element can be determined based on factors such as the hardware configuration and software version of the network element.

[0068] The various methods for obtaining network element resource information described in the above embodiments can accurately and flexibly obtain network element resource information and communication information corresponding to multiple network elements, providing accurate basic information for subsequent management. It should be noted that other methods can also be used to obtain network element resource information for each network element, and are not limited to the methods described above.

[0069] Step 220: Extract the features of the network element resource information corresponding to each network element to obtain the resource features corresponding to each network element.

[0070] Resource characteristics refer to the key attributes or features that can summarize and describe network element resource information, enabling accurate understanding of the performance and status of the corresponding network element. Optionally, resource characteristics may include multiple target network element resources corresponding to the first network element and / or their specific numerical values.

[0071] Specifically, resource characteristics may include hardware characteristics (such as the CPU type, quantity, clock speed, memory size, disk type or capacity, etc. of the network element), software characteristics (such as the operating system version, supported network protocols, software modules and applications, etc. of the network element), network characteristics (such as network configuration information such as the IP address, MAC address, subnet mask, gateway address, DNS server address, etc. of the network element), and security characteristics (such as the firewall settings, encryption technology, authentication mechanism, security policy, etc. of the network element).

[0072] In some embodiments, the control device can determine the mapping data corresponding to multiple target network element resources corresponding to the first network element according to a resource mapping table, so as to obtain the resource characteristics corresponding to the first network element; the resource mapping table contains each network element resource and its corresponding mapping value. Mapping network element resources to resource characteristics in numerical form can help the control device better understand and manage network element resources.

[0073] Optionally, for network element resources that can be converted into numerical values, the control device can directly convert the network element resource into a numerical value; for network element resources that cannot be directly converted into numerical values, the control device can determine the numerical value mapped to the network element resource through a resource mapping table. For example, the IP address of a network element can be converted into an integer form (e.g., the IPv4 address "192.168.1.1" can be converted into "3232301153"); for communication protocols, the mapping value for TCP can be 1, and the mapping value for UDP (User Datagram Protocol) can be 2.

[0074] Step 230: Generate the target feature matrix corresponding to the local area network based on the resource characteristics of each network element.

[0075] In some embodiments, when each network element accesses the local area network (LAN), the control device assigns a corresponding number to each network element, where the number indicates the order in which the network element joined the LAN. After obtaining the resource characteristics of each network element, the control device can generate a target feature matrix corresponding to the LAN based on the corresponding number and resource characteristics of each network element. Further, the row number of each network element's resource characteristics in the target feature matrix can match the corresponding number of the network element. For example, if network element A's number is 2, then all resource characteristics of network element A are in the second row of the target feature matrix corresponding to the LAN.

[0076] In some embodiments, the control device constructs a feature vector for each of the N network elements in the local area network based on the resource characteristics corresponding to each element. For example, the feature vector of the i-th network element is X. i ={x i1 ,x i2 ,...,x iD}, i = 1, 2, ..., N, where N is a positive integer, D represents the number of resource features corresponding to each network element, and x i1 This represents the first resource feature of the i-th network element.

[0077] Optionally, the control device can construct a target feature matrix corresponding to the local area network based on the feature vectors of each network element. For example, Among them, X N This represents the feature vector of the Nth network element.

[0078] Step 240: Generate the target adjacency matrix corresponding to the local area network based on the communication information corresponding to the multiple network elements.

[0079] Specifically, if there are N network elements in a local area network (LAN), then the target adjacency matrix corresponding to the LAN can be: Among them, a 12 This indicates that the first network element in the local area network can access the second network element.

[0080] It should be noted that since network elements cannot access each other, the diagonal lines of the target connection matrix corresponding to the local area network are all 0.

[0081] In some embodiments, the control device may use numerical values ​​in the target adjacency matrix to indicate whether any network element can access other network elements. For example, a value of 1 may be used to indicate that a network element on the horizontal axis can access a network element on the vertical axis, and a value of 0 may be used to indicate that a network element on the horizontal axis cannot access a network element on the vertical axis. For example, in a target adjacency matrix containing 5 network elements (network element 1, network element 2, network element 3, network element 4, and network element 5), assuming that network element 1 can only access network elements 2 and 3, then the elements in the first row and second column and the first row and third column of the target adjacency matrix will be 1, and the other elements in the first row will be 0.

[0082] It should be noted that the fact that network element 1 can access network element 2 does not mean that network element 2 can access network element 1. The control device needs to obtain the communication information corresponding to network element 1 and / or the communication information corresponding to network element 2 in order to determine whether network element 2 can access network element 1.

[0083] Specifically, assuming there are four network elements in the local area network (network element 1, network element 2, network element 3, and network element 4), where network element 1 can access network elements 2 and 3, network element 2 can access network elements 1 and 4, network element 3 can access network element 1, and network element 4 can access network element 2, then the target adjacency matrix of the local area network can be:

[0084] Step 250: Based on the graph convolutional neural network, generate the resource matrix corresponding to the local area network according to the target feature matrix and the target adjacency matrix.

[0085] In a local area network (LAN), control devices can treat network elements as nodes and determine directed edges based on communication information (e.g., network element 1 can access network element 2, indicating the existence of a directed edge from a node in network element 1 to a node in network element 2). This forms a directed graph structure corresponding to the LAN. Using a graph convolutional neural network, the network element resource information contained in the target feature matrix and the communication information between network elements contained in the target adjacency matrix can be fused to generate a resource matrix reflecting the relationships between multiple network elements in the LAN.

[0086] Step 260: Based on the resource matrix, manage the traffic corresponding to each network element.

[0087] The resource matrix contains network element vectors corresponding to multiple network elements. The network element vector corresponding to the first network element indicates the association relationship between the first network element and other network elements in the local area network. Specifically, the network element vector may contain information from multiple dimensions such as the network element's processing power, storage capacity, network bandwidth, and geographical location.

[0088] It should be noted that in the resource matrix, the elements on the same horizontal or vertical axis represent the elements in the network element vector corresponding to the same network element.

[0089] In some embodiments, the resource matrix may include target traffic thresholds for each network element in the local area network (LAN). These target traffic thresholds may include average traffic or maximum traffic within a preset time period. In the LAN, the control device can acquire the real-time traffic corresponding to each network element. If the real-time traffic corresponding to a first network element is detected to be greater than the target traffic threshold for that first network element in the resource matrix, the control device can determine that the first network element's traffic is abnormal and will not allow the first network element to access LAN network services. For example, if the network element vector corresponding to network element 3 in the resource matrix is ​​X3 = {0.1, 0.2, 10, 5, 0.1}, where the fourth element is the target traffic threshold, then if the control device detects that the real-time traffic of network element 3 is greater than 5, it considers the traffic of network element 3 to be abnormal. This effectively monitors and manages the network traffic of each network element in the LAN, ensuring that LAN network resources can be rationally allocated and used.

[0090] Optionally, if the control device determines that the traffic of the first network element is abnormal, it can also send an abnormality alert to the first network element. This alert is used to remind the first network element that its real-time traffic is too high. This helps to promptly remind administrators of potential network problems and take appropriate measures to resolve them.

[0091] Optionally, the control device can also, after sending an anomaly warning to the first network element and receiving a network access request from the first network element, detect the number of anomaly warnings sent to the first network element. Here, a network access request is a request from the network element to the control device to access the local area network (LAN) network service. If the number of such requests is less than a preset number, the first network element is allowed to re-access the LAN network service; if the number of such requests is greater than or equal to the preset number, the first network element is not allowed to re-access the LAN network service. For example, assuming the preset number is 5, if the terminal device detects a network access request from network element 4 and detects that 6 anomaly warnings have been sent to network element 4, then the control device will not allow network element 4 to re-access the LAN network service.

[0092] In some embodiments, if the control device detects a change in the network element resource information corresponding to any network element, or detects the access of a new network element to the local area network, or receives information that any network element has left the local area network, or at every second time interval, the control device recalculates a new resource matrix. By updating the resource matrix, the control device can more accurately understand the network element resources of each network element, thereby ensuring continuous monitoring and management of each network element.

[0093] In this embodiment, the control device in the local area network (LAN) extracts resource features from the network element resource information of each network element to generate a target feature matrix, and generates a target adjacency matrix based on the communication information corresponding to each network element. The target feature matrix and target adjacency matrix are then processed by a graph convolutional neural network to obtain a resource matrix. Since the target feature matrix and target adjacency matrix can accurately characterize the resource status of each network element in the LAN and the communication relationships between different network elements, the resulting resource matrix can accurately reflect the correlation relationships between different network elements within the LAN. Based on this resource matrix, the control device can more accurately manage the traffic of each network element in the LAN according to the correlation relationships between different network elements, improving the efficiency and accuracy of network element management, and simultaneously enhancing the intelligence level of network element management.

[0094] like Figure 3 As shown, in some embodiments, the step of generating a target adjacency matrix corresponding to the local area network based on the communication information corresponding to multiple network elements may include the following steps 302 to 304.

[0095] Step 302: Generate matrix elements corresponding to the access of the first network element to the second network element based on the number of the first port, the number of the second port, and the communication protocol type.

[0096] The first port count refers to the number of ports on the first network element that can be used to access the second network element. The second port count refers to the number of ports on the second network element that can be accessed and connected by the first network element. The communication protocol type refers to the type of protocol used by the first network element to communicate with the second network element (e.g., TCP, UDP, HTTP (Hypertext Transfer Protocol)).

[0097] In some embodiments, the control device can generate matrix elements corresponding to the first network element accessing the second network element based on an element mapping table, according to a first quantity interval to which the number of first ports belongs, a second quantity interval to which the number of second ports belongs, and a third quantity interval to which the number of communication protocol types belongs. The element mapping table contains each first quantity interval, each second quantity interval, each third quantity interval, and a common preset matrix element. For example, if the protocol types used by the first network element to communicate with the second network element include TCP and UDP, then the number of communication protocol types is 2.

[0098] For example, the preset first quantity interval includes interval 1, interval 2, and interval 3; the preset second quantity interval includes interval A, interval B, and interval C; and the preset third quantity interval includes interval a, interval b, and interval c. Assuming that the communication information of the first network element accessing the second network element may include the first quantity interval as interval 2, the second quantity interval as interval A, and the third quantity interval as interval a, the control device can determine the preset matrix element corresponding to interval 2, interval A, and interval a as the matrix element corresponding to the first network element accessing the second network element.

[0099] In some embodiments, the control device can determine the access level of the first network element to the second network element based on the number of first ports, the number of second ports, and the communication protocol type, and use the access level as a matrix element corresponding to the first network element's access to the second network element; the access level is used to indicate the first network element's access capability to the second network element. Specifically, the larger the number of first ports and the larger the number of second ports, the greater the corresponding access level; the greater the corresponding access level, the more the communication protocol type is within a preset protocol type range.

[0100] For example, if no port of network element 1 accesses any port of network element 2 through any protocol, the control device can consider the matrix element corresponding to network element 1 accessing network element 2 to be 0. If all ports of network element 1 can access port 80 of network element 2 through the TCP protocol, the control device can consider the matrix element corresponding to network element 1 accessing network element 2 to be 0.02. If all ports of network element 1 can access port 80 of network element 2 through the UDP protocol, the control device can consider the matrix element corresponding to network element 1 accessing network element 2 to be 0.01. If all ports of network element 1 can access ports 443, 22, and 80 of network element 2 through the TCP protocol, the control device can consider the matrix element corresponding to network element 1 accessing network element 2 to be 0.3. If all ports of network element 1 can access any port of network element 2 through any protocol, the control device can consider the matrix element corresponding to network element 1 accessing network element 2 to be 1.

[0101] Step 304: Generate the target adjacency matrix corresponding to the local area network by accessing the matrix element corresponding to another network element from any network element in the local area network.

[0102] In some embodiments, the control device can sequentially fill the matrix elements corresponding to each network element accessing another network element into an N×N matrix to obtain the target adjacency matrix corresponding to the local area network. Here, N is the number of network elements contained in the local area network. Specifically, the same horizontal axis of the target adjacency matrix can represent the communication information of the same network element accessing other network elements, and the same vertical axis can represent the communication information of the same network element being accessed.

[0103] For example, in a local area network (LAN), there are three network elements (network element 1, network element 2, and network element 3). The matrix element corresponding to network element 1 accessing network element 2 is 0.1, and the matrix element corresponding to accessing network element 3 is 0.05; the matrix element corresponding to network element 2 accessing network element 1 is 0, and the matrix element corresponding to accessing network element 3 is 0.6; the matrix element corresponding to network element 3 accessing network element 1 is 1, and the matrix element corresponding to accessing network element 2 is 0.02. Therefore, the target adjacency matrix of the LAN can be:

[0104] In this embodiment of the application, by quantizing the communication information and using it as matrix elements, a more refined matrix element than the traditional binary (0 / 1) matrix can be obtained. Furthermore, the matrix elements are determined by comprehensively considering the number of first ports, the number of second ports, and the type of communication protocol. The resulting target adjacency matrix can better reflect the communication information of each network element in the local area network accessing another network element.

[0105] like Figure 4 As shown, in some embodiments, the steps are based on graph convolutional neural networks to generate a resource matrix corresponding to the local area network according to the target feature matrix and the target adjacency matrix, and may also include the following steps 402 to 410.

[0106] Step 402: Use the target feature matrix and the target adjacency matrix as the input matrix of the first layer of the graph convolutional neural network.

[0107] Step 404: Encode the input matrix of the current layer based on the graph convolution formula corresponding to the current layer to obtain the output matrix of the current layer.

[0108] In some embodiments, the propagation formula for GCN (Graph Convolutional Networks) is: Where A is the target adjacency matrix. Add the target adjacency matrix and the identity matrix. For matrix The degree matrix, H (l) Let W be the feature matrix of the l-th layer, σ(X) be the non-linear activation function, which can include the Softmax function, ReLU function, etc. (l) Here, H represents the parameters of the l-th layer, which are the weights multiplied onto the feature matrix, also known as the weight matrix. When l is 1, H... (l) Let X be the target feature matrix.

[0109] Specifically, the control device can obtain the graph convolution formula corresponding to each layer based on the propagation formula of GCN and the weight parameters corresponding to each layer.

[0110] Step 406: Determine if the current layer is the last layer. If yes, proceed to step 408; otherwise, proceed to step 410.

[0111] Step 408: Use the output matrix of the last layer as the resource matrix corresponding to the local area network.

[0112] If the control device detects that the current layer is the last layer, it uses the output matrix of the last layer as the resource matrix corresponding to the local area network. The output matrix of the last layer has been processed by a multi-layer graph convolutional network, which integrates the feature information and connection relationships (communication information) of the network elements, so it can be directly used as a resource matrix.

[0113] Step 410: Use the output matrix of the current layer and the target adjacency matrix as the input matrix of the next layer, and execute step 404.

[0114] In some embodiments, the control device uses the output matrix of the current layer and the target adjacency matrix as the input matrix of the next layer, and if it determines that the current layer is not the last layer, it can re-execute the encoding process of step 404 until the current layer is the last layer.

[0115] In this embodiment, the control device gradually extracts and fuses the resource characteristics and communication information of each network element in the local area network through a multi-layer graph convolutional network. Finally, it generates a resource matrix that more accurately reflects the resource distribution of each network element in the local area network and the communication relationship between each network element. This is beneficial for subsequent correct management of each network element in the local area network based on the resource matrix, thereby improving the efficiency and accuracy of network element management.

[0116] like Figure 5 As shown, in some embodiments, the training process of a graph convolutional neural network may include the following steps 502 to 512.

[0117] Step 502: Obtain the sample set and construct a pre-trained graph convolutional neural network according to preset parameters.

[0118] The sample set includes multiple sample feature matrices, corresponding sample adjacency matrices, and corresponding target resource matrices. The target resource matrix is ​​the actual resource matrix that the control device can obtain after acquiring the sample feature matrices and their corresponding sample adjacency matrices.

[0119] Preset parameters are used to define the structure, training parameters, and other related network components of the neural network. Mapping parameters may include, but are not limited to, the number of neural network layers, the initial weight matrix for each layer, the feature dimension, the learning rate, weight decay (regularization term), the optimizer type, and the loss function type.

[0120] In some embodiments, the control device can construct a pre-trained graph convolutional neural network based on the number of neural network layers and the initial weight matrix corresponding to each layer in the preset parameters.

[0121] In some embodiments, the control device can obtain sample feature matrices corresponding to multiple preset historical time periods based on the historical network element resource information corresponding to each network element in multiple preset historical time periods; and obtain sample adjacency matrices corresponding to multiple preset historical time periods based on the historical communication information corresponding to each network element in multiple preset historical time periods; and obtain target resource matrices corresponding to multiple preset historical time periods.

[0122] For example, the control device can obtain the sample feature matrix corresponding to historical time A based on the historical network element resource information corresponding to the multiple network elements contained in the local area network at historical time A; obtain the sample adjacency matrix corresponding to historical time A based on the historical communication information corresponding to the multiple network elements contained in the local area network at historical time A; and obtain the target resource matrix corresponding to historical time A.

[0123] Step 504: Based on the pre-trained graph convolutional neural network, generate the sample resource matrix corresponding to the first sample feature matrix according to the first sample feature matrix and the corresponding sample adjacency matrix.

[0124] The first sample feature matrix is ​​any sample feature matrix in the sample set. The sample resource matrix refers to the predicted resource matrix obtained by the control device through a pre-trained graph convolutional neural network after acquiring the sample feature matrix and the corresponding sample adjacency matrix.

[0125] In some embodiments, the control device may use the first sample feature matrix and the corresponding sample adjacency matrix as the input matrix of the first layer of a pre-trained graph convolutional neural network; and based on the pre-trained graph convolutional neural network, encode the input matrix of the current layer to obtain the output matrix of the current layer, until the output matrix of the last layer is obtained, which serves as the sample resource matrix corresponding to the first sample feature matrix.

[0126] Step 506: Calculate the loss error of the pre-trained graph convolutional neural network based on the sample resource matrix and the target resource matrix corresponding to each sample feature matrix.

[0127] In some embodiments, in order to evaluate the performance of a pre-trained graph convolutional neural network and thereby optimize the graph convolutional neural network, the control device can calculate the loss error of the pre-trained graph convolutional neural network to evaluate the performance and adjust the parameters of the neural network accordingly.

[0128] Optionally, the loss error calculation methods that the control device can use include, but are not limited to, mean squared error loss, cross-entropy loss, L1 norm loss, triplet loss, etc.

[0129] Specifically, taking cross-entropy loss as an example, the control device can calculate the loss error corresponding to the pre-trained graph convolutional neural network based on the cross-entropy loss function, according to the sample resource matrix and the corresponding target resource matrix corresponding to each sample feature matrix.

[0130] For example, the cross-entropy loss function is Where Y is the sample resource matrix, Let N be the target resource matrix, N be the number of network elements in the local area network, M be the feature dimension in the preset parameters, and y be the target resource matrix. ij Let i be the element in the i-th row and j-th column of the sample resource matrix. The element in the i-th row and j-th column of the target resource matrix.

[0131] Step 508: Determine whether the loss error is greater than the preset loss value. If yes, proceed to step 510; otherwise, proceed to step 512.

[0132] Step 510: Adjust the graph convolution formulas corresponding to each layer in the pre-trained graph convolutional neural network to obtain a new pre-trained graph convolutional neural network. Repeat step 504.

[0133] If the control device detects that the loss error is greater than the preset loss value, it means that the current pre-trained graph convolutional neural network cannot effectively fuse the feature matrix and the adjacency matrix. Therefore, the control device can adjust the graph convolution formula corresponding to each layer in the pre-trained graph convolutional neural network to obtain a new pre-trained graph convolutional neural network. Based on the new pre-trained graph convolutional neural network, the control device can re-execute the step of generating the sample resource matrix corresponding to the first sample feature matrix according to the first sample feature matrix and the corresponding sample adjacency matrix until the loss error is less than or equal to the preset loss value.

[0134] Step 512 yields the trained graph convolutional neural network.

[0135] If the control device detects that the loss error is less than or equal to the preset loss value, it means that the currently pre-trained graph convolutional neural network can fuse the resource features in the feature matrix and the communication information in the adjacency matrix. Furthermore, the resource matrix obtained by the pre-trained graph convolutional neural network can well indicate the relationship between multiple network elements in the local area network. Therefore, the currently pre-trained graph convolutional neural network is regarded as the trained graph convolutional neural network.

[0136] In the embodiments of this application, during the training process of the graph convolutional neural network, the performance of the graph convolutional neural network can be optimized by continuously adjusting the parameters of the neural network. This enables the trained graph convolutional neural network to more accurately understand the relationships between multiple network elements in the local area network, thereby improving the accuracy and efficiency of obtaining the resource matrix and helping to improve the intelligence of management.

[0137] like Figure 6 As shown, in some embodiments, the control device manages various network elements in the local area network, which may include the following steps 602 to 612.

[0138] Step 602: Receive the access request sent by the first network element.

[0139] In some embodiments, the control device can manage the access to and being accessed by various network elements in the local area network, including whether a first network element can access a third network element. The access request includes network element information corresponding to the third network element to be accessed by the first network element; the third network element is any network element in the local area network that is different from the first network element.

[0140] When a first network element needs to access a third network element, it will send a corresponding access request to the control device. The control device will then determine whether to forward the access request to the third network element based on the access request and the current resource matrix, that is, whether to allow the first network element to access the third network element.

[0141] Specifically, the network element information corresponding to the third network element to be accessed by the first network element may include, but is not limited to, which first ports the first network element requests to access the third network element, which protocols are provided for access, which second ports the first network element accesses the third network element, the identification information of the first network element, and the identification information of the third network element.

[0142] Step 604: Based on the access request, determine the first network element vector corresponding to the first network element and the second network element vector corresponding to the third network element from the resource matrix.

[0143] In some embodiments, the control device can obtain the first network element vector corresponding to the first network element and the second network element vector corresponding to the third network element from the resource matrix based on the identification information of the first network element and the third network element in the access request. Specifically, the control device can determine the row of the resource feature matrix where the resource feature of the network element is located based on the identification information of the first network element and the identification information of the third network element. The identification number of the network element indicates which row of the target feature matrix the resource feature of the network element is located in. According to the characteristics of graph convolutional neural networks, the dimension of the resource matrix is ​​the same as the dimension of the target feature matrix. Therefore, the control device can number the network element vectors to determine which row of the resource matrix the first network element vector and the second network element vector are located in.

[0144] Step 606: Calculate the vector distance between the first network element vector and the second network element vector to obtain the first distance.

[0145] In some embodiments, the vector distance calculation methods that the control device may use include Euclidean distance, Manhattan distance, cosine similarity, etc.

[0146] Taking Euclidean distance as an example, the control device can calculate the first distance between the first network element vector and the second network element vector according to the Euclidean formula. Specifically, the Euclidean formula is: Where d represents the first distance, n represents the number of elements in the network element vector, and x i Let y represent the i-th element of the first network element vector. i This represents the i-th element of the second network element vector.

[0147] Step 608: Determine whether the first distance is less than or equal to a preset distance threshold. If yes, proceed to step 610; otherwise, proceed to step 612.

[0148] Step 610: Forward the access request to the third network element.

[0149] If the control device detects that the vector distance between the first network element vector and the second network element vector is less than or equal to a preset distance threshold, it indicates that the first network element and the third network element are similar or close in terms of resources (features). That is, the first network element can access the third network element. In this case, the control device forwards the access request to the third network element so that the first network element can successfully access the third network element.

[0150] Step 612: Do not forward the access request to the third network element.

[0151] If the control device detects that the vector distance between the first network element vector and the second network element vector is greater than a preset distance threshold, it indicates that the first network element and the third network element have significant differences in resources (features). In this case, the control device will not forward the access request to the third network element, so that the first network element cannot access the third network element.

[0152] In this embodiment, by calculating the first distance between the network element vectors of two network elements and comparing it with a preset threshold, the control device can automatically determine whether to allow a network element to access another network element without manual analysis and approval, thereby improving the efficiency and accuracy of network element management for each network element.

[0153] like Figure 7 As shown, in some embodiments, the control device manages various network elements in the local area network, which may include the following steps 702 to 704.

[0154] Step 702: If no network element resource information sent by the first network element is received within a preset time period, then at least one accessible network element that can access the first network element and at least one accessed network element that the first network element can access are determined according to the resource matrix.

[0155] Accessible network elements refer to other network elements in a local area network that can access the first network element; accessed network elements refer to other network elements in a local area network that can be accessed by the first network element.

[0156] In some embodiments, each network element in the local area network can periodically send network element resource information to the control device. If the control device does not receive the network element resource information sent by the first network element within a preset time period, it indicates that the first network element may have a fault, communication interruption, or resource information update delay, which may cause the first network element to fail to access the local area network. In order to avoid the traffic transmission direction of other network elements in the local area network being affected by the first network element, it is necessary to adjust the traffic transmission direction of the accessible network elements and the accessed network elements.

[0157] Step 704: Adjust the traffic transmission direction between at least one accessible network element and at least one accessed network element so that at least one accessible network element can access at least one accessed network element.

[0158] In some embodiments, the control device may determine, based on the resource matrix, the access vector corresponding to at least one accessible network element and the access vector corresponding to at least one accessed network element; calculate the second distance between each accessible vector and each accessed vector; and adjust the traffic transmission direction from accessing the first network element from the accessible network element to accessing the accessed network element from the accessible network element to the accessed network element according to the order of the second distances from smallest to largest, until at least one accessible network element can access at least one accessed network element.

[0159] It should be noted that after adjusting the direction of traffic transmission, each accessible network element in the local area network can access at least one accessed network element, and each accessed network element can be accessed by at least one accessible network element.

[0160] For example, suppose there are 3 accessible network elements (network element A, network element B, and network element C) and 2 accessed network elements (network element a and network element b). The control module calculates the second distances between each accessible vector and each accessed vector as (network element A, network element a, 6), (network element A, network element b, 3), (network element B, network element a, 5), (network element B, network element b, 2), (network element C, network element a, 7), and (network element C, network element b, 4). Based on the ascending order of the second distances, the control module adjusts the traffic transmission direction between at least one accessible network element and at least one accessed network element, such that network element B accesses network element b, network element A accesses network element b, and network element C accesses network element b. At this point, all 3 accessible network elements have been adjusted, but network element a has not yet been accessed. Therefore, based on the ascending order of the second distances, network element B is positioned towards network element a, thus adjusting both accessed network elements.

[0161] In this embodiment, the control device monitors the network element resource information sent by each network element, enabling it to promptly detect and respond to potential problems such as faults, communication interruptions, or resource information update delays in the first network element. Furthermore, in the event of a problem with the first network element, the control device can quickly determine the accessible and accessed network elements based on the resource matrix and adjust their traffic transmission directions to ensure that traffic transmission in the local area network is not affected by a single network element failure, thereby optimizing the traffic path and improving the network efficiency of the local area network.

[0162] like Figure 8 As shown, in one embodiment, a local area network (LAN) element management device 800 is provided, which can be applied to the control device described above. The LAN element management device 800 may include an information acquisition module 810, a feature extraction module 820, a matrix generation module 830, a graph convolution module 840, and a network element management module 850.

[0163] The information acquisition module 810 is used to acquire network element resource information corresponding to multiple network elements and communication information corresponding to multiple network elements respectively; wherein, the communication information corresponding to the first network element is used to indicate the other network elements that the first network element can communicate with, and the first network element is any one of the multiple network elements.

[0164] The feature extraction module 820 is used to extract the features of the network element resource information corresponding to each network element, and obtain the resource features corresponding to each network element.

[0165] The matrix generation module 830 is used to generate a target feature matrix corresponding to the local area network based on the resource characteristics of each network element.

[0166] Optionally, the matrix generation module 830 is also used to generate a target adjacency matrix corresponding to the local area network based on the communication information corresponding to multiple network elements.

[0167] The graph convolution module 840 is used to generate a resource matrix corresponding to the local area network based on the target feature matrix and the target adjacency matrix, using a graph convolutional neural network. The resource matrix is ​​used to indicate the association relationship of multiple network elements in the local area network.

[0168] The network element management module 850 is used to manage the traffic corresponding to each network element according to the resource matrix.

[0169] Optionally, the communication information corresponding to the first network element includes the communication information of the first network element accessing the second network element. The communication information of the first network element accessing the second network element includes the number of first ports that the first network element can access the second network element, the number of second ports that the second network element can be accessed by the first network element, and the communication protocol types supported by the first network element and the second network element; the second network element is any other network element that the first network element can communicate with.

[0170] In some embodiments, the matrix generation module 830 is further configured to generate matrix elements corresponding to the access of the first network element to the second network element based on the number of the first port, the number of the second port, and the communication protocol type; and to generate a target adjacency matrix corresponding to the local area network based on the matrix elements corresponding to the access of any network element to another network element in the local area network.

[0171] Optionally, the graph convolution module 840 is further configured to use the target feature matrix and the target adjacency matrix as the input matrix of the first layer of the graph convolutional neural network; encode the input matrix of the current layer based on the graph convolution formula corresponding to the current layer to obtain the output matrix of the current layer; use the output matrix of the current layer and the target adjacency matrix as the input matrix of the next layer, and continue to execute the step of encoding the input matrix of the current layer based on the graph convolution formula corresponding to the current layer to obtain the output matrix of the current layer, until the output matrix of the last layer is obtained; and use the output matrix of the last layer as the resource matrix corresponding to the local area network.

[0172] In some embodiments, the network element management device 800 of the local area network may further include a neural network training module.

[0173] The neural network training module is used to acquire a sample set and construct a pre-trained graph convolutional neural network according to preset parameters. The sample set includes multiple sample feature matrices, corresponding sample adjacency matrices, and corresponding target resource matrices. Based on the pre-trained graph convolutional neural network, a sample resource matrix corresponding to the first sample feature matrix is ​​generated according to the first sample feature matrix and the corresponding sample adjacency matrix. The first sample feature matrix can be any sample feature matrix in the sample set. The loss error corresponding to the pre-trained graph convolutional neural network is calculated according to the sample resource matrix and the corresponding target resource matrix of each sample feature matrix. If the loss error is greater than the preset loss value, the graph convolution formula corresponding to each layer in the pre-trained graph convolutional neural network is adjusted to obtain a new pre-trained graph convolutional neural network. The step of generating the sample resource matrix corresponding to the first sample feature matrix according to the first sample feature matrix and the corresponding sample adjacency matrix based on the pre-trained graph convolutional neural network is repeated until the loss error is less than or equal to the preset loss value, and the trained graph convolutional neural network is obtained.

[0174] Optionally, the resource matrix contains network element vectors corresponding to multiple network elements, and the network element vector corresponding to the first network element is used to indicate the association relationship between the first network element and each network element in the local area network.

[0175] In some embodiments, the network element management module 850 is further configured to receive an access request sent by a first network element, the access request including network element information corresponding to a third network element to be accessed by the first network element; the third network element is any network element in the local area network that is different from the first network element; according to the access request, the first network element vector corresponding to the first network element and the second network element vector corresponding to the third network element are determined from the resource matrix; the vector distance between the first network element vector and the second network element vector is calculated to obtain a first distance; if the first distance is less than or equal to a preset distance threshold, the access request is forwarded to the third network element.

[0176] In some embodiments, the network element management module 850 is further configured to, if it does not receive network element resource information sent by the first network element within a preset time period, determine, according to the resource matrix, at least one accessible network element that can access the first network element, and at least one accessed network element that the first network element can access; and adjust the traffic transmission direction of at least one accessible network element and at least one accessed network element so that at least one accessible network element can access at least one accessed network element.

[0177] Optionally, the network element resource information corresponding to the first network element includes multiple target network element resources corresponding to the first network element.

[0178] In some embodiments, the feature extraction module 820 is further configured to determine the mapping data corresponding to the multiple target network element resources corresponding to the first network element according to the resource mapping table, so as to obtain the resource features corresponding to the first network element; the resource mapping table contains each network element resource and its corresponding mapping value.

[0179] In this embodiment, the control device in the local area network (LAN) extracts resource features from the network element resource information of each network element to generate a target feature matrix, and generates a target adjacency matrix based on the communication information corresponding to each network element. The target feature matrix and target adjacency matrix are then processed by a graph convolutional neural network to obtain a resource matrix. Since the target feature matrix and target adjacency matrix can accurately characterize the resource status of each network element in the LAN and the communication relationships between different network elements, the resulting resource matrix can accurately reflect the correlation relationships between different network elements within the LAN. Based on this resource matrix, the control device can more accurately manage the traffic of each network element in the LAN according to the correlation relationships between different network elements, improving the efficiency and accuracy of network element management and enhancing the intelligence level of network element management.

[0180] Figure 9 This is a structural block diagram of an electronic device in one embodiment. For example... Figure 9 As shown, the electronic device 900 may include one or more of the following components: a processor 910 and a memory 920 coupled to the processor 910, wherein the memory 920 may store one or more computer programs, which may be configured to implement the methods described in the above embodiments when executed by one or more processors 910.

[0181] Processor 910 may include one or more processing cores. Processor 910 connects to various parts within the electronic device 900 using various interfaces and lines, and performs various functions and processes data of the electronic device 900 by running or executing instructions, programs, code sets, or instruction sets stored in memory 920, and by calling data stored in memory 920. Optionally, processor 910 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 910 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 910 and may be implemented separately using a communication chip.

[0182] The memory 920 may include random access memory (RAM) or read-only memory (ROM). The memory 920 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 920 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method embodiments described above. The data storage area may also store data created by the electronic device 900 during use.

[0183] Understandably, the electronic device 900 may include more or fewer structural elements than those shown in the block diagram above, such as power supply, input buttons, camera, speaker, screen, RF (Radio Frequency) circuit, Wi-Fi (Wireless Fidelity) module, Bluetooth module, sensor, etc., and may not be limited herein.

[0184] This application discloses a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the methods described in the above embodiments.

[0185] This application discloses a computer program product, including a computer program, which, when executed by a processor, implements the methods described in the above embodiments.

[0186] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), etc.

[0187] Any references to memory, storage, databases, or other media used herein may include non-volatile and / or volatile memory. Suitable non-volatile memory may include ROM, Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which is used as an external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as Static RAM (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), Rambus DRAM (RDRAM), and Direct Rambus DRAM (DRDRAM).

[0188] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Those skilled in the art should also recognize that the embodiments described in the specification are optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0189] In the various embodiments of this application, it should be understood that the sequence number of each process does not necessarily imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0190] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0191] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they can be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0192] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0193] If the aforementioned integrated units are implemented as software functional units and sold or used as independent products, they can be stored in a computer-accessible memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several requests to cause a computer device (which can be a personal computer, server, or network device, specifically a processor in the computer device) to execute some or all of the steps of the methods described in the various embodiments of this application.

[0194] The foregoing has provided a detailed description of a local area network (LAN) element management method, apparatus, electronic device, and storage medium disclosed in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are merely for the purpose of helping to understand the method and its core ideas. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method of managing network elements of a local area network, characterized by, A control device applied to the local area network, the local area network further comprising a plurality of network elements; the method comprises: obtaining network element resource information corresponding to each of the plurality of network elements, and communication information corresponding to each of the plurality of network elements; wherein the communication information corresponding to a first network element indicates each other network element with which the first network element can communicate, the first network element being any network element in the plurality of network elements; extracting features of the network element resource information corresponding to each of the network elements to obtain resource features corresponding to each of the network elements; the resource features include at least one of hardware features, software features, network features, and security features; generating a target feature matrix corresponding to the local area network according to the resource features corresponding to each of the network elements; generating a target adjacency matrix corresponding to the local area network according to the communication information corresponding to each of the plurality of network elements; based on a graph convolutional neural network, generating a resource matrix corresponding to the local area network according to the target feature matrix and the target adjacency matrix, the resource matrix being used to indicate the association relationship of the plurality of network elements in the local area network; the resource matrix includes network element vectors corresponding to the plurality of network elements respectively; the network element vector corresponding to the first network element is used to indicate the association relationship of the first network element and each network element in the local area network; managing the traffic corresponding to each of the network elements according to the resource matrix; the management of the traffic corresponding to each of the network elements according to the resource matrix comprises: receiving an access request sent by the first network element, the access request including network element information corresponding to a third network element to be accessed by the first network element; the third network element being any network element different from the first network element in the local area network; determining a first network element vector corresponding to the first network element and a second network element vector corresponding to the third network element from the resource matrix according to the access request; calculating the vector distance between the first network element vector and the second network element vector to obtain a first distance; if the first distance is less than or equal to a preset distance threshold, forwarding the access request to the third network element.

2. The method of claim 1, wherein, the communication information corresponding to the first network element includes communication information of the first network element accessing a second network element, the communication information of the first network element accessing the second network element including a first port number of the second network element that the first network element can access, a second port number of the second network element that can be accessed by the first network element, and a communication protocol type supported by the first network element and the second network element; the second network element being any other network element with which the first network element can communicate; the generation of the target adjacency matrix corresponding to the local area network according to the communication information corresponding to each of the plurality of network elements comprises: generating a matrix element corresponding to the first network element accessing the second network element according to the first port number, the second port number, and the communication protocol type; generating the target adjacency matrix corresponding to the local area network according to the matrix element corresponding to any one network element accessing another network element in the local area network.

3. The method of claim 1, wherein, The generating of the resource matrix corresponding to the local area network based on the target feature matrix and the target adjacency matrix comprises: inputting the target feature matrix and the target adjacency matrix as input matrices of a first layer of a graph convolutional neural network; encoding the input matrices of the current layer based on a graph convolution formula corresponding to the current layer to obtain output matrices of the current layer; continuing to perform the step of encoding the input matrices of the current layer based on the graph convolution formula corresponding to the current layer to obtain the output matrices of the current layer by taking the output matrices of the current layer and the target adjacency matrix as input matrices of a next layer until output matrices of a last layer are obtained; taking the output matrices of the last layer as the resource matrix corresponding to the local area network.

4. The method of claim 1, wherein, The training process of the graph convolutional neural network comprises: obtaining a sample set and constructing a pre-trained graph convolutional neural network according to preset parameters; the sample set comprises a plurality of sample feature matrices, corresponding sample adjacency matrices and corresponding target resource matrices; generating a sample resource matrix corresponding to a first sample feature matrix based on the pre-trained graph convolutional neural network and the corresponding sample adjacency matrix; the first sample feature matrix is any sample feature matrix in the sample set; calculating a loss error corresponding to the pre-trained graph convolutional neural network according to the sample resource matrices corresponding to the sample feature matrices and the corresponding target resource matrices; if the loss error is greater than a preset loss value, adjusting the graph convolution formula corresponding to each layer in the pre-trained graph convolutional neural network to obtain a new pre-trained graph convolutional neural network; repeating the step of generating the sample resource matrix corresponding to the first sample feature matrix based on the pre-trained graph convolutional neural network and the corresponding sample adjacency matrix until the loss error is less than or equal to the preset loss value to obtain a trained graph convolutional neural network.

5. The method of claim 1, wherein, The management of the traffic corresponding to each network element according to the resource matrix comprises: if network element resource information sent by the first network element is not received within a preset time length, determining at least one accessible network element capable of accessing the first network element and at least one accessed network element capable of being accessed by the first network element according to the resource matrix; adjusting the traffic transmission direction of the at least one accessible network element and the at least one accessed network element to enable the at least one accessible network element to access the at least one accessed network element.

6. The method of claim 1, wherein, The network element resource information corresponding to the first network element comprises a plurality of target network element resources corresponding to the first network element; The extracting of the features of the network element resource information corresponding to each network element to obtain resource features corresponding to each network element comprises: determining mapping data corresponding to the plurality of target network element resources corresponding to the first network element according to a resource mapping table to obtain resource features corresponding to the first network element; the resource mapping table comprises each network element resource and corresponding mapping values.

7. A network element management apparatus for a local area network, characterized by A control device applied to the local area network, the local area network further comprising a plurality of network elements; the device comprises: an information acquisition module, configured to acquire network element resource information corresponding to each of the plurality of network elements, and communication information corresponding to each of the plurality of network elements; wherein the communication information corresponding to a first network element indicates each other network element with which the first network element can communicate, the first network element being any network element in the plurality of network elements; a feature extraction module, configured to extract features of the network element resource information corresponding to each of the network elements, to obtain resource features corresponding to each of the network elements; the resource features include at least one of hardware features, software features, network features, and security features; a matrix generation module, configured to generate a target feature matrix corresponding to the local area network according to the resource features corresponding to each of the network elements; the matrix generation module is further configured to generate a target adjacency matrix corresponding to the local area network according to the communication information corresponding to each of the plurality of network elements; a graph convolution module, configured to generate a resource matrix corresponding to the local area network based on a graph convolutional neural network and according to the target feature matrix and the target adjacency matrix, the resource matrix being used to indicate an association relationship of the plurality of network elements in the local area network; the resource matrix includes network element vectors corresponding to the plurality of network elements respectively; a network element vector corresponding to the first network element is used to indicate an association relationship of the first network element and each network element in the local area network; a network element management module, configured to manage traffic corresponding to each of the network elements according to the resource matrix; the network element management module is further configured to receive an access request sent by the first network element, the access request including network element information corresponding to a third network element to be accessed by the first network element; the third network element being any network element different from the first network element in the local area network; according to the access request, a first network element vector corresponding to the first network element and a second network element vector corresponding to the third network element are determined from the resource matrix; a vector distance between the first network element vector and the second network element vector is calculated to obtain a first distance; if the first distance is less than or equal to a preset distance threshold, the access request is forwarded to the third network element.

8. An electronic device, comprising: A device comprising a memory and a processor, the memory storing a computer program, the computer program being executed by the processor to cause the processor to implement the method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, the computer program being executed by a processor to implement the method of any one of claims 1 to 6.

Images