Network optimization method, apparatus, storage medium, and computer program product

Abstract

The application discloses a network optimization method and device, a storage medium and a computer program product. The method comprises the following steps: acquiring the occurrence frequency of a plurality of transmission links of a wireless communication network in a target period; determining at least one primary transmission link with an occurrence frequency greater than a frequency threshold from the plurality of transmission links of the wireless communication network; for each primary transmission link, acquiring first backup transmission link state data of the primary transmission link, and analyzing the first backup transmission link state data by using a transit freedom evaluation model to obtain the link transit freedom of the primary transmission link; determining the network transit freedom of the wireless communication network based on the link transit freedom of each primary transmission link, and performing transit freedom optimization on the wireless communication network when the network transit freedom is less than a freedom threshold. The application solves the technical problem that the wireless communication network has insufficient optimization capability, the load of network equipment is unbalanced, and the network communication efficiency is low.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and more specifically, to a network optimization method, apparatus, storage medium, and computer program product. Background Technology

[0002] In modern communication network and data center management, network efficiency, stability, and reliability are undoubtedly the foundation for ensuring business continuity and improving user experience. However, with the continuous expansion of network scale and the rapid increase in complexity, various network problems have emerged, such as network congestion, transmission delays, and single points of failure. These issues make it difficult for networks to adapt to rapidly changing network environments and the demands of massive data transmission, thus restricting the quality and efficiency of data transmission. Therefore, existing wireless communication networks suffer from insufficient dynamic optimization capabilities and uneven load distribution on network devices, leading to excessive data traffic on some paths and causing network transmission path congestion.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a network optimization method, apparatus, storage medium, and computer program product to at least solve the technical problems of insufficient optimization capabilities and unbalanced load on network devices in wireless communication networks, resulting in low network communication efficiency.

[0005] According to one aspect of the embodiments of this application, a network optimization method is provided, comprising: obtaining the occurrence frequency of multiple transmission links in a wireless communication network within a target period; determining at least one primary transmission link from the multiple transmission links of the wireless communication network whose occurrence frequency is greater than a preset frequency threshold; for each primary transmission link, obtaining the state data of a first backup transmission link of the primary transmission link, and analyzing the state data of the first backup transmission link using a pre-trained relay degree of freedom evaluation model to obtain the link relay degree of freedom of the primary transmission link, wherein the state data of the first backup transmission link is used to reflect the link state data of the backup transmission links associated with the primary transmission link, and the link state data includes at least: link transmission performance and link failure probability; determining the network relay degree of freedom of the wireless communication network based on the link relay degree of freedom of each primary transmission link, and optimizing the relay degree of freedom of the wireless communication network when the network relay degree of freedom is less than a preset degree of freedom threshold.

[0006] Optionally, obtaining the occurrence frequency of multiple transmission links in the wireless communication network within a target period includes: constructing a network topology map of the wireless communication network, wherein the network topology map is constructed based on the various network devices in the wireless communication network and the transmission relationships between the various network devices, and the network topology map includes: multiple network device nodes and the connections connecting the various network device nodes; obtaining the connection data of each connection in the network topology map within the target period, wherein the connection data includes at least: source IP address and destination IP address; and determining the occurrence frequency of each transmission link in the wireless communication network within the target period based on the connection data.

[0007] Optionally, constructing a network topology map of a wireless communication network includes: identifying multiple network devices within the wireless communication network, wherein the device types of the network devices include at least one of the following: routers, switches, and servers; obtaining the transmission relationships between the various network devices through a preset method, wherein the preset method includes at least one of the following: viewing the configuration files of the network devices, querying the network management system, or calling a network scanning tool; and using each network device as a topology node and the transmission relationships between the network devices as the connection relationships between the topology nodes to construct a network topology map.

[0008] Optionally, acquiring the status data of the first backup transmission link of the primary transmission link includes: acquiring at least one backup transmission link of the primary transmission link; acquiring multiple link performance data of the backup transmission link, wherein the types of link performance data include at least one of the following: latency, packet loss rate, and channel load; standardizing each link performance data and calculating the information entropy of each standardized link performance data; determining the weight value of each link performance data based on the information entropy and using the entropy weight method; determining the link transmission performance of the backup transmission link based on multiple link performance data and their corresponding weight values; dividing the backup transmission link into multiple sub-transmission paths based on the pairwise adjacent transmission nodes within the backup transmission link; acquiring historical fault data of each sub-transmission path and analyzing the historical fault data of each sub-transmission path using a neural network model to obtain the fault probability of each sub-transmission path; and determining the link fault probability of the backup transmission link based on the fault probability of each sub-transmission path within the backup transmission link.

[0009] Optionally, obtaining at least one backup transmission link for the primary transmission link includes: identifying the transmission network device on the primary transmission link and determining whether the transmission network device is a relay network device, wherein the relay network device is a network device with relay function other than the source network device and the destination network device; if the transmission network device is a relay network device, determining at least one transmission link in the wireless communication network based on the source network device, the relay network device, and the destination network device in the primary transmission link; calculating the distance between each transmission link and the primary transmission link, and using the transmission link whose distance is less than a preset distance threshold as the backup transmission link for the primary transmission link.

[0010] Optionally, determining whether a transmission network device is a relay network device includes: determining whether the transmission network device is an intermediate network device; if the transmission network device is an intermediate network device, obtaining historical transmission performance data of the intermediate network device within the primary transmission link according to a preset method, wherein the historical transmission performance data includes at least one of the following: forwarded data volume, forwarding success rate, transmission latency, and packet loss rate; determining the relationship between the historical transmission performance data and a preset transmission performance indicator threshold; if the historical transmission performance data is greater than the transmission performance indicator threshold, determining that the transmission network device is a relay network device; if the historical transmission performance data is not greater than the transmission performance indicator threshold, determining that the transmission network device is not a relay network device.

[0011] Optionally, the training process of the transit degree of freedom evaluation model includes: obtaining multiple sets of training samples, wherein each set of training samples includes: the status data of the second backup transmission link of the primary transmission link sample and the corresponding link transit degree of freedom; constructing a neural network model, wherein the neural network model includes at least: an input layer, a hidden layer, and an output layer; and iteratively training the neural network model based on multiple sets of training samples to obtain the transit degree of freedom evaluation model.

[0012] According to another aspect of the embodiments of this application, a network optimization apparatus is also provided, comprising: an acquisition module, configured to acquire the occurrence frequency of multiple transmission links in a wireless communication network within a target period; a determination module, configured to determine at least one primary transmission link from the multiple transmission links of the wireless communication network whose occurrence frequency is greater than a preset frequency threshold; an evaluation module, configured to, for each primary transmission link, acquire first backup transmission link status data of the primary transmission link, and analyze the first backup transmission link status data using a pre-trained relay degree of freedom evaluation model to obtain the link relay degree of freedom of the primary transmission link, wherein the first backup transmission link status data is used to reflect the link status data of backup transmission links associated with the primary transmission link, and the link status data includes at least: link transmission performance and link failure probability; and an optimization module, configured to determine the network relay degree of freedom of the wireless communication network based on the link relay degree of freedom of each primary transmission link, and optimize the relay degree of freedom of the wireless communication network when the network relay degree of freedom is less than a preset degree of freedom threshold.

[0013] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored computer program, wherein the device where the non-volatile storage medium is located executes the above-described network optimization method by running the computer program.

[0014] According to another aspect of the embodiments of this application, a computer program product is also provided, the computer program product including a stored computer program, wherein the computer program implements the above-described network optimization method when executed by a processor.

[0015] In this embodiment, the primary transmission links in the wireless communication network are dynamically identified by analyzing the frequency of their occurrence. Then, a pre-trained relay degree of freedom evaluation model is used to analyze the status data of the backup transmission links of each primary transmission link to obtain the relay degree of freedom of each primary transmission link. Finally, the overall network relay degree of freedom of the wireless communication network is obtained based on the relay degree of freedom of each primary transmission link. The relationship between the overall network relay degree of freedom and a preset degree of freedom threshold is analyzed. If the overall network relay degree of freedom is less than the degree of freedom threshold, it indicates that the relay capability of the wireless communication network is poor, and there may be network transmission path congestion caused by excessive traffic on some paths. Therefore, the optimization system can perform relay degree of freedom optimization operations on the wireless communication network to enhance the network's self-healing capability and maintenance efficiency. In the entire optimization process described above, this application considers the overall transit freedom of the network rather than optimizing a single link in isolation. This helps to achieve the goal of globally optimal network performance and stability, enables more accurate resource allocation and optimization decisions, reduces the risk of single point of failure, and thus solves the technical problems of insufficient optimization capabilities and unbalanced load on network devices in wireless communication networks, resulting in low network communication efficiency. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 This is a hardware structure block diagram of an optional computer terminal for implementing a network optimization method according to an embodiment of this application;

[0018] Figure 2 This is a flowchart illustrating an optional network optimization method according to an embodiment of this application;

[0019] Figure 3 This is a schematic diagram of an optional network topology according to an embodiment of this application;

[0020] Figure 4 This is a schematic diagram of an optional network optimization device according to an embodiment of this application;

[0021] Figure 5 This is a schematic diagram of the structure of an optional electronic device according to an embodiment of this application. Detailed Implementation

[0022] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0024] Furthermore, all information and data (including but not limited to user device information, user personal information, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties. For example, this system has an interface with the relevant user or organization. Before obtaining relevant information, it needs to send an acquisition request to the aforementioned user or organization through the interface, and obtain the relevant information after receiving consent from the aforementioned user or organization.

[0025] To better understand the embodiments of this application, the technical terms involved in the embodiments of this application are explained below:

[0026] Degrees of freedom: In classical mechanics, degrees of freedom refer to the number of directions in which a system can move independently. For example, a point mass has three degrees of freedom in three-dimensional space (x, y, z directions), while a rigid body has six degrees of freedom in three-dimensional space (three translational degrees of freedom and three rotational degrees of freedom).

[0027] Delay: In communications, computer science, and engineering, it usually refers to the time required for a signal or data packet (message / packet / bit stream) to travel from transmission to reception in a system. It is also called latency or delay.

[0028] Packet loss rate: This refers to the proportion of data packets lost during network transmission. Packet loss rate is usually expressed as a percentage, and its calculation formula is: Packet loss rate = (Number of lost data packets / Number of transmitted data packets) × 100%.

[0029] Information entropy is a concept in information theory used to measure the uncertainty of information. In information theory, information entropy represents the uncertainty of a random variable; a larger value indicates higher uncertainty, and a smaller value indicates lower uncertainty. The formula for calculating information entropy is: Where H(X) represents the information entropy of the random variable X, n represents the number of possible structures of the random variable, and P(x) i ) represents the probability that random variable X takes the i-th outcome, log b It represents the logarithm to the base 2.

[0030] Entropy Weight Method: This is an objective weighting method used to determine the weights of each indicator in a multi-indicator comprehensive evaluation system. This method is based on the concept of information entropy, arguing that the lower the information entropy, the greater the amount of information provided, and therefore the greater the weight of that indicator.

[0031] Example 1

[0032] Currently, as network scale and complexity continue to increase, network problems in wireless communication networks are also increasing, making it difficult for wireless communication networks to adapt to rapidly changing network environments and data transmission needs, resulting in a sharp decline in network communication efficiency.

[0033] Therefore, this application provides a method embodiment for network optimization, which aims to enhance network redundancy and fault recovery capabilities, and improve network performance and stability by identifying the network relay degrees of freedom of the entire network and optimizing the wireless communication network based on these degrees of freedom.

[0034] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0035] The methods and embodiments provided in this application can be executed on mobile terminals, computer terminals, or similar computing devices. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for implementing a network optimization method is shown. Figure 1As shown, the computer terminal 10 (or mobile device 10) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0036] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0037] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the network optimization method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the network optimization method of the application described above. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0038] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0039] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0040] Under the above operating environment, Figure 2 This is a flowchart illustrating an optional network optimization method according to an embodiment of this application, such as... Figure 2 As shown, the method includes at least steps S202-S206, wherein:

[0041] Step S202: Obtain the frequency of occurrence of multiple transmission links in the wireless communication network within the target period.

[0042] In the technical solution provided in step S202, when determining whether the wireless communication network needs to be periodically optimized, the optimization system can first obtain the frequency (i.e., number of occurrences) of multiple transmission links of the wireless communication network in the target period. The target period can be determined according to the actual optimization requirements and network scale.

[0043] Step S204: Determine at least one primary transmission link from among multiple transmission links of the wireless communication network whose frequency exceeds a preset frequency threshold.

[0044] In the technical solution provided in step S204, the optimization system can select the primary transmission link with a frequency greater than the preset frequency from multiple transmission links in the wireless communication network based on the frequency of occurrence of each transmission link obtained above. That is, the selected primary transmission link has a high usage frequency in the wireless communication network and is a network performance bottleneck or critical transmission path.

[0045] Step S206: For each primary transmission link, obtain the status data of the first backup transmission link of the primary transmission link, and analyze the status data of the first backup transmission link using the pre-trained relay degree of freedom evaluation model to obtain the link relay degree of freedom of the primary transmission link.

[0046] In the technical solution provided in step S206, for each primary transmission link selected in step S204, the optimization system can first obtain the status data of the first backup transmission link of the primary transmission link. This first backup transmission link status data reflects the link status data of the backup transmission links associated with the primary transmission link, and the link status data includes at least: link transmission performance and link failure probability. Then, the first backup transmission link status data is input into a pre-trained relay degree-of-freedom evaluation model. The relay degree-of-freedom evaluation model analyzes the first backup transmission link status data to obtain the link relay degree of freedom of the primary transmission link. This link relay degree of freedom reflects the spatial degree of freedom of the primary transmission link within the wireless communication network.

[0047] Step S208: Determine the network relay degree of the wireless communication network based on the link relay degree of freedom of each primary transmission link, and optimize the relay degree of freedom of the wireless communication network when the network relay degree of freedom is less than the preset degree of freedom threshold.

[0048] In the technical solution provided in step S208, the optimization system can determine the weight value of the primary transmission link based on factors such as the frequency of occurrence and traffic volume of the primary transmission link. Then, it performs a weighted summation of the link relay degrees of freedom of each primary transmission link determined in step S206 and the weight value of each primary transmission link to obtain the network relay degrees of freedom of the wireless communication network. Next, it compares the obtained network relay degrees of freedom of the wireless communication network with a preset degree-of-freedom threshold. If the network relay degrees of freedom of the wireless communication network are less than the threshold, it indicates that the relay capacity of the wireless communication network is insufficient, and corresponding relay degree-of-freedom optimization needs to be performed, such as adjusting bandwidth or adding routes.

[0049] The method described in this embodiment will be further described below.

[0050] As an optional implementation, in the technical solution provided in step S202 above, the optimization system can obtain the occurrence frequency of each transmission link by the following methods:

[0051] Step S2021: Construct the network topology diagram of the wireless communication network.

[0052] In the technical solution provided in step S2021 above, the network topology diagram is constructed based on the various network devices within the wireless communication network and the transmission relationships between them. Therefore, the constructed network topology diagram includes: multiple network device nodes and the connections between these network device nodes. Its specific construction process includes:

[0053] Step 1: Identify the multiple network devices within the wireless communication network. These network devices include, but are not limited to, routers, switches, and servers.

[0054] Step 2: Obtain the transmission relationships between various network devices (i.e., direct communication links exist between network devices) through preset methods. These preset methods include, but are not limited to: viewing network device configuration files, querying the Network Management System (NMS), and using network scanning tools.

[0055] Network device configuration files record the device's network configuration information, including IP address, subnet mask, gateway, and routing table. Therefore, by viewing the configuration file, one can understand the transmission relationships between network devices, such as which devices are directly connected and which communicate through a router. A network management system, as a software system used to monitor, manage, and maintain computer networks and related equipment, typically includes functional modules such as network monitoring, configuration management, performance management, security management, and fault management. Therefore, by querying the network management system, one can understand the transmission relationships between network devices. Additionally, network scanning tools can detect which devices are communicating with other devices, as well as information such as their transmission protocols and port numbers, to obtain the connection information between various network devices. Commonly used network scanning tools include, but are not limited to, Nmap, Wireshark, and Angry IP Scanner.

[0056] Step 3: Treat each network device as a topology node, and the transmission relationships between network devices as the connection relationships between topology nodes, in order to construct a network topology graph.

[0057] In other words, based on the network devices within the wireless communication network and the transmission relationships between them, the network topology is simulated. Within this network topology diagram, each network device is represented by a node, and the transmission relationships between the network devices are represented by lines, thus obtaining the network topology diagram of the wireless communication network. Figure 3 As shown.

[0058] It should be noted that the network topology diagram constructed above includes at least one of the following structural types: bus network topology, star network topology, ring network topology, tree network topology, mesh network topology, and hybrid network topology. This application embodiment does not impose specific limitations on the structural type; the specific type can be set according to the actual application scenario.

[0059] Step S2022: Obtain the connection data of each connection in the network topology diagram within the target period.

[0060] In the technical solution provided in step S2022 above, the connection data of each connection in the network topology map within the target period is obtained by using the logs of network devices, the database of NMS, or network monitoring tools. The connection data includes, but is not limited to, information such as source IP address, destination IP address, transmission time, and transmission data volume.

[0061] Step S2023: Determine the frequency of occurrence of each transmission link in the wireless communication network within the target period based on the connection data.

[0062] In the technical solution provided in step S2023 above, the optimization system can organize the connection data of each connection in the network topology diagram, remove invalid data, and count the connections with the same source IP address and the same destination IP address. Each time a connection appears, the count of that connection is incremented by one until the connection data of each connection in the network topology diagram within the target period is counted, and the occurrence frequency of each connection is obtained. The occurrence frequency of each connection is then used as the occurrence frequency of the corresponding transmission link in the wireless communication network.

[0063] As an optional implementation, in the technical solution provided in step S204 above, the optimization system can determine the primary transmission link by comparing the occurrence frequency of each transmission link with a frequency threshold.

[0064] In addition, the optimization system can also arrange the occurrence frequency of each transmission link in the wireless communication network in descending order, and select the top N transmission links as the primary transmission links.

[0065] It should be noted that the settings for N and the frequency threshold can be selected according to the specific network scale in the actual application scenario.

[0066] As an optional implementation, in the technical solution provided in step S206 above, the optimization system can obtain the first backup transmission link status data of each primary transmission link sequentially through the following steps, including:

[0067] Step S2061: Obtain at least one backup transmission link of the primary transmission link. The backup transmission link is a transmission link adjacent to or close to the primary transmission link and capable of performing relay functions.

[0068] Therefore, in this embodiment of the application, the optimization system can obtain the backup transmission links for each primary transmission link through the following steps S1-S4, including:

[0069] Step S1: Identify the transmission network device on the primary transmission link and determine whether the transmission network device is a relay network device.

[0070] The aforementioned transmission network devices include at least one of the following types: source network devices (i.e., link senders) and destination network devices (i.e., link receivers), intermediate network devices, and intermediate network devices with relay functions (hereinafter referred to as relay network devices). Therefore, the optimization system can first obtain each transmission network device on the primary transmission link and determine whether the transmission network device is a relay network device.

[0071] Specifically, the optimization system can determine whether the transmission network device is a relay network device through the following steps S11-S13, including:

[0072] Step S11: Determine whether the transmission network device is an intermediate network device. The intermediate network device can be understood as other network devices in the primary transmission link besides the source network device and the destination network device.

[0073] Step S12: When the transmission network device is an intermediate network device, obtain the historical transmission performance data of the intermediate network device in the primary transmission link according to a preset method.

[0074] The aforementioned preset methods include, but are not limited to, viewing network device configuration files, querying the Network Management System (NMS), and using network scanning tools. The acquired historical transmission performance data refers to key performance indicators extracted from the historical processing information of intermediate network devices in the primary transmission link, including, but not limited to, forwarded data volume, forwarding success rate, transmission latency, and packet loss rate. These key performance indicators can be used to evaluate intermediate network devices that function as relays in the primary transmission link.

[0075] Step S13: Determine the relationship between historical transmission performance data and a preset transmission performance index threshold. If the historical transmission performance data is greater than the transmission performance index threshold, determine that the transmission network device is a relay network device. If the historical transmission performance data is not greater than the transmission performance index threshold, determine that the transmission network device is not a relay network device.

[0076] In the technical solutions provided in steps S11-S13 above, intermediate network devices in the primary transmission link are screened to obtain relay network devices with relay functions. Since these relay network devices play a crucial role in the link transmission process, they will be given priority in subsequent network optimization and fault recovery, providing strong support for these processes.

[0077] Step S2: When the transmission network device is a relay network device, at least one transmission link in the wireless communication network is determined based on the source network device, relay network device and destination network device in the primary transmission link.

[0078] In other words, if a relay network device exists, the optimization system can identify at least one transmission link within the wireless communication network that has the same source network device, relay network device, and destination network device as the primary transmission link, based on the source network device, relay network device, and destination network device of the primary transmission link.

[0079] Step S3: Calculate the distance between each transmission link and the primary transmission link, and designate the transmission links whose distance is less than a preset distance threshold as backup transmission links for the primary transmission link.

[0080] Since backup transmission links should be links adjacent to or close to the primary transmission link, the optimization system can also calculate the shortest topological distance between each transmission link and the primary transmission link within the network topology graph using graph-based shortest path algorithms (such as Dijkstra's algorithm or Bellman-Ford's algorithm) to select the backup transmission link that is closest to the primary transmission link from multiple transmission paths.

[0081] Step S2062: Determine the link transmission performance of each backup transmission link of the primary transmission link.

[0082] Optionally, the optimization system can determine the link transmission performance of the backup transmission link by methods including:

[0083] Step 1: Obtain performance data for multiple backup transmission links.

[0084] Specifically, the optimization system first acquires real-time link performance data of the backup transmission links through network performance monitoring tools or network management systems to ensure the reliability of the subsequently determined link transmission performance results. The types of link performance data acquired include, but are not limited to, communication latency, packet loss rate, and link channel load. Communication latency refers to the time it takes for a data packet to travel from the sender to the receiver, reflecting the transmission speed of the transmission link. Packet loss rate refers to the proportion of data packets lost during transmission out of the total number of transmitted data packets, reflecting the transmission quality of the transmission link. Link channel load reflects the amount of data currently being transmitted on the transmission link and is one of the important indicators for evaluating link performance.

[0085] Next, the performance data of each link are standardized, and the information entropy of each processed link performance data is calculated.

[0086] Specifically, since the units and dimensions of the three indicators—link communication latency, packet loss rate, and channel load—are different, they need to be standardized first to make them have the same dimensions and range for easy subsequent calculations. Then, the information entropy of the standardized link performance data is calculated. The information entropy is used to evaluate the importance of the link performance data. Generally, the larger the information entropy, the lower the importance of the link performance data in evaluating link performance.

[0087] Then, based on information entropy, the weight values ​​of each link performance data are determined using the entropy weight method.

[0088] In determining weight values ​​using the entropy weighting method, the lower the information entropy of link performance data, the greater the amount of information it provides, and the greater its weight; conversely, the higher the information entropy of link performance data, the less information it provides, and the smaller its weight. It should be noted that the weight values ​​for each link performance data point determined above can be adjusted according to actual circumstances to obtain more accurate weight values.

[0089] Finally, the transmission performance of the backup transmission link is determined based on multiple link performance data and their corresponding weight values.

[0090] Specifically, the optimization system can perform a weighted summation of the communication latency, packet loss rate, and link channel load of the backup transmission link with their corresponding weight values ​​to obtain the overall link transmission performance of the backup transmission link.

[0091] In particular, the optimization system can also compare the overall link transmission performance of each backup transmission link with a preset performance threshold to filter the backup transmission links of the primary transmission link obtained in step S2061, and select the backup transmission link with the best overall link transmission performance for the link selection strategy, so as to provide strong support for subsequent network optimization.

[0092] Step S2063: Determine the link failure probability of each backup transmission link of the primary transmission link.

[0093] Optionally, the optimization system can determine the link failure probability of the backup transmission link by methods including:

[0094] First, based on the pairwise adjacent transmission nodes within the backup transmission link, the backup transmission link is divided into multiple sub-transmission paths;

[0095] Then, historical fault data of each sub-transmission path is obtained, and the historical fault data of each sub-transmission path is analyzed using a neural network model to obtain the fault probability of each sub-transmission path.

[0096] Finally, the link failure probability of the backup transmission link is determined based on the failure probability of each sub-transmission path within the backup transmission link.

[0097] In the technical solution provided in step S2063 above, the optimization system can identify sub-transmission paths (i.e., transmission segments) between every two adjacent nodes in the backup transmission link to obtain multiple sub-transmission paths of the backup transmission link. Then, the optimization system can obtain historical fault data for each sub-transmission path by querying the network management system, and perform data cleaning on the obtained historical fault data to remove incomplete or erroneous data; it can then perform aggregate analysis on the historical fault data of each sub-transmission path to calculate key statistical indicators for each sub-transmission path, such as the frequency of fault occurrence and fault interval time; and use the key statistical indicators of each sub-transmission path as input to a neural network model to obtain the predicted fault probability of each sub-transmission path output by the model. The aforementioned neural network model can be obtained through iterative training using multiple training samples, each training sample including: key statistical indicators obtained from the aggregate analysis of historical fault data of the transmission path sample and the fault probability of that transmission path sample. Finally, the optimization system can calculate the product of the fault probabilities of each sub-transmission path and use the resulting product as the link fault probability of the backup transmission link sample. It should be noted that the above situation applies to cases where the failure in the backup transmission link is caused by the failure of at least one sub-transmission path, and therefore the failures of each sub-transmission path are independent.

[0098] In addition, for situations where there are dependencies between sub-transmission paths (e.g., if the failure probability of one sub-transmission path is high, it will cause the failure of the next sub-transmission path), this application also proposes to use Markov models or Bayesian networks to calculate the link failure probability of backup transmission links.

[0099] Specifically, when calculating the link failure probability of the backup transmission link, the dependencies between the sub-transmission links in the backup transmission link can first be determined based on the network topology diagram of the wireless communication network. Since this application divides the network according to adjacent nodes, the conditional probability of the current sub-transmission link failing can be directly used as the failure probability of the current sub-transmission link. The conditional probability can be determined using a Markov model or a Bayesian network. Finally, the link failure probability of the backup transmission link is determined based on the failure probabilities of each sub-transmission link.

[0100] For example, the failure probabilities of multiple sub-transmission paths in a backup transmission link can be denoted as: p1, p 2|1 ,…,p n|n-1 Where p1 represents the independent failure probability of the first sub-transmission path (which can be obtained through the prediction model described above), pn|n-1 Let Pn represent the probability of the nth sub-transmission path failing when the (n-1)th sub-transmission path fails. Then, the normal probability of each sub-transmission path can be calculated separately, denoted as P1, P2, ..., Pn. n Where P1 = 1 - p1, which represents the normal probability of the first sub-transmission path, and P2 = P1 × (1 - p1) / 2. 2|1 ), which represents the probability that both the first and second sub-transmission paths are normal, P. n =P n-1 ×(1-p n|n-1 ), which represents the probability that all sub-transmission paths are normal. Therefore, the link failure probability of the backup transmission link can be written as: P total =1-P n Throughout the above process, the probability of the entire backup transmission link failing is calculated step by step by considering the dependencies between multiple sub-transmission paths of the backup transmission link.

[0101] As an optional implementation, in the technical solution provided in step S206 above, the training process of the aforementioned transit degree-of-freedom evaluation model includes:

[0102] Step 1: Obtain multiple sets of training samples.

[0103] Specifically, the optimization system can obtain multiple sets of training samples using the following method:

[0104] First, obtain multiple samples using transmission links;

[0105] Then, the status data of the second backup transmission link and the corresponding link relay degrees of freedom of each primary transmission link sample are obtained, and the obtained status data of the second backup transmission link are preprocessed.

[0106] Finally, the link relay degrees of freedom corresponding to the second backup transmission link status data of each primary transmission link sample after processing are used to form multiple sets of training samples.

[0107] Therefore, each training sample includes: the status data of the second backup transmission link of the primary transmission link sample and the corresponding relay degrees of freedom (labels). It should be noted that the method for obtaining the status data of the first backup transmission link is used to obtain the status data of the second backup transmission link, and the status data of the second backup transmission link also includes: the link status data of multiple backup transmission link samples of the primary transmission link sample, such as link transmission performance, link failure probability, etc. The relay degrees of freedom of the primary transmission link sample can be determined by manual calculation or other methods.

[0108] Step 2: Construct a neural network model.

[0109] The aforementioned neural network model can be a fully connected neural network (FCNN) structure, and this structure includes at least: an input layer, hidden layers (which can have multiple layers), and an output layer.

[0110] In addition, the weights and biases of the neural network model can be pre-initialized. Initialization methods include at least one of the following: He initialization, Xavier initialization (also known as Glorot initialization), etc. It should be noted that the chosen initialization method should match the activation function of the actual application scenario. He initialization is suitable for ReLU and its variants (such as LeakyReLU, PReLU, etc.) activation functions; Xavier initialization is suitable for sigmoid and tanh activation functions.

[0111] Step 3: Iteratively train the neural network model based on multiple sets of training samples to obtain the intermediate degree of freedom evaluation model.

[0112] Specifically, firstly, the optimization system can divide multiple training samples into multiple training groups, where each training group includes one or more training samples. Then, in each iteration of training, the optimization system inputs the training samples from each training group into a fully connected neural network. By calculating the output and activation function of each layer, the network obtains the predicted link transfer degrees of freedom for that training sample. The predicted link transfer degrees of freedom output by the network are compared with the actual link transfer degrees of freedom of the training sample, and the value of the loss function (such as mean squared error, cross-entropy loss, etc.) is calculated. Finally, based on the gradient information of the loss function, the weights and biases of the neural network are updated using the backpropagation algorithm. This process of forward propagation, loss calculation, and backpropagation is repeated until the performance of the neural network on the training set reaches the preset convergence conditions (such as the loss value no longer decreasing significantly, the number of iterations reaching the upper limit, etc.).

[0113] Furthermore, the optimization system can use a validation set during training to evaluate the model's performance. The validation set is a separate dataset from the training set, used to prevent overfitting and premature termination of training. Based on the performance evaluation results of the validation set, hyperparameters such as the neural network structure, learning rate, and regularization can be continuously adjusted to optimize the neural network model's performance. Simultaneously, the optimization system can use an independent test set to test the performance of the trained intermediate-degree-of-freedom recognition model, evaluating metrics such as accuracy, recall, and F1 score. The test set should contain data different from the training and validation sets to assess the model's generalization ability.

[0114] Finally, the trained intermediate degree-of-freedom recognition model is loaded into memory. For example, the raw data of the intermediate degree-of-freedom recognition model can be loaded from non-volatile memory into volatile memory so that the processor can run the intermediate degree-of-freedom recognition model. The raw data of the first neural network refers to the unprocessed data, which typically includes the parameters and structural data of the first neural network. The structural data can be the computational relationships based on the parameters, such as the forward propagation computational relationships between intermediate layers and between neurons. Specifically, the structural data can include the structure-related code of the intermediate degree-of-freedom recognition model, such as the code used to perform related calculations between intermediate layers and between neurons.

[0115] In one implementation, a region can be partitioned in memory for loading the intermediate degree-of-freedom recognition model, which may include a structural data storage area and a parameter storage area. The structural data storage area stores structurally related code, and the parameters referenced by it can be pointed to by pointers to the addresses of specific parameters in the parameter storage area. During the training process of the intermediate degree-of-freedom recognition model, it may be necessary to frequently update the parameters; in this case, updating the parameter values ​​in the parameter storage area is sufficient.

[0116] As an optional implementation, in the technical solution provided in step S208 above, the optimization system can optimize the relay degrees of freedom of the wireless communication network according to the following rules, including:

[0117] First, the network relay degree of freedom of the wireless communication network is determined based on the link relay degree of freedom of each primary transmission link.

[0118] Specifically, the link relay degrees of freedom of each primary transmission link and the weight values ​​of each primary transmission link are weighted and summed to obtain the network relay degrees of freedom of the wireless communication network. The weight values ​​of the primary transmission links can be determined based on factors such as the frequency of occurrence and traffic volume of the primary transmission links. For example, if the frequency of occurrence of a primary transmission link is higher, the corresponding weight value is higher, and vice versa.

[0119] Then, the relationship between the network's transit degrees of freedom and the preset degree-of-freedom threshold is determined, where,

[0120] If the network relay degree of freedom is not less than the preset degree of freedom threshold, it is determined that the wireless communication network does not have a problem with insufficient relay capacity, and there is no need to optimize the wireless communication network.

[0121] When the relay degree of freedom in the network is less than the preset degree of freedom threshold, the relay degree of freedom of the wireless communication network is optimized.

[0122] Among these optimization operations, the above-mentioned optimization operations can be used to add relay network equipment to the primary transmission link with low link relay freedom in the wireless communication network. The relay network equipment should be reasonably configured according to the network structure and traffic distribution. And / or, upgrade the relay network equipment on the primary transmission link. And / or, add a backup transmission link to the primary transmission link with low link relay freedom to improve the relay capability of the network.

[0123] Furthermore, after adding relay network equipment within the wireless communication network, the optimization system can synchronously update the network topology map of the wireless communication network to reflect the latest status of the wireless communication network. Then, based on the network optimization method described above, the system can evaluate the network relay freedom of the wireless communication network to determine whether further network topology optimization is needed to improve the network's relay capability and stability.

[0124] Therefore, the technical solution of this application analyzes the frequency of occurrence of transmission links in the wireless communication network to dynamically identify the primary transmission links in the wireless communication network. Then, a pre-trained relay degree of freedom evaluation model is used to analyze the status data of the backup transmission links of each primary transmission link to obtain the link relay degree of freedom of each primary transmission link. Finally, the overall network relay degree of freedom of the wireless communication network is obtained based on the link relay degree of freedom of each primary transmission link. The relationship between the overall network relay degree of freedom and the preset degree of freedom threshold is analyzed. If the overall network relay degree of freedom is less than the degree of freedom threshold, it indicates that the relay capability of the wireless communication network is poor, and there may be network transmission path congestion caused by excessive traffic on some paths. Therefore, the optimization system can adjust the bandwidth and add routes to the wireless communication network to enhance the network's self-healing capability and maintenance efficiency. In the entire optimization process described above, this application considers the overall transit freedom of the network rather than optimizing a single link in isolation. This helps to achieve the goal of globally optimal network performance and stability, enables more accurate resource allocation and optimization decisions, reduces the risk of single point of failure, and thus solves the technical problems of insufficient optimization capabilities and unbalanced load on network devices in wireless communication networks, resulting in low network communication efficiency.

[0125] Example 2

[0126] Based on Embodiment 1 of this application, an embodiment of a network optimization device is also provided, which executes the network optimization method described in the above embodiment during operation. Wherein, Figure 4 This is a schematic diagram of an optional network optimization device according to an embodiment of this application, such as... Figure 4 As shown, the network optimization device includes at least an acquisition module 41, a determination module 42, an evaluation module 43, and an optimization module 44, wherein:

[0127] Acquisition module 41 is used to acquire the frequency of occurrence of multiple transmission links in the wireless communication network within the target period;

[0128] The determining module 42 is used to determine at least one primary transmission link from multiple transmission links of the wireless communication network whose frequency is greater than a preset frequency threshold.

[0129] Evaluation module 43 is used to obtain the status data of the first backup transmission link of the primary transmission link for each primary transmission link, and to analyze the status data of the first backup transmission link using a pre-trained relay degree of freedom evaluation model to obtain the link relay degree of freedom of the primary transmission link. The status data of the first backup transmission link is used to reflect the link status data of the backup transmission link associated with the primary transmission link, and the link status data includes at least: link transmission performance and link failure probability.

[0130] The optimization module 44 is used to determine the network relay degree of the wireless communication network based on the link relay degree of freedom of each primary transmission link, and to optimize the relay degree of freedom of the wireless communication network when the network relay degree of freedom is less than a preset degree of freedom threshold.

[0131] It should be noted that each module in the above-mentioned network optimization device can be a program module (e.g., a set of program instructions to implement a certain function) or a hardware module. For the latter, it can be manifested in the following forms, but is not limited to them: each of the above modules is manifested as a processor, or the functions of each of the above modules are implemented by a processor.

[0132] Example 3

[0133] According to an embodiment of this application, a non-volatile storage medium is also provided, which stores a program, wherein the program controls the device where the non-volatile storage medium is located to execute the network optimization method in embodiment 1 when it runs.

[0134] Optionally, the device containing the non-volatile storage medium executes the following steps by running the program: obtaining the occurrence frequency of multiple transmission links in the wireless communication network within a target period; determining at least one primary transmission link from the multiple transmission links in the wireless communication network whose occurrence frequency is greater than a preset frequency threshold; for each primary transmission link, obtaining the first backup transmission link status data of the primary transmission link, and analyzing the first backup transmission link status data using a pre-trained relay degree of freedom evaluation model to obtain the link relay degree of freedom of the primary transmission link, wherein the first backup transmission link status data is used to reflect the link status data of the backup transmission links associated with the primary transmission link, and the link status data includes at least: link transmission performance and link failure probability; determining the network relay degree of freedom of the wireless communication network based on the link relay degree of freedom of each primary transmission link, and optimizing the relay degree of freedom of the wireless communication network when the network relay degree of freedom is less than a preset degree of freedom threshold.

[0135] According to an embodiment of this application, a computer program product is also provided, which includes a stored computer program, wherein the computer program implements the network optimization method in embodiment 1 when executed by a processor.

[0136] Optionally, the computer program performs the following steps: acquiring the occurrence frequency of multiple transmission links in the wireless communication network within a target period; identifying at least one primary transmission link from the multiple transmission links in the wireless communication network whose occurrence frequency is greater than a preset frequency threshold; for each primary transmission link, acquiring the first backup transmission link status data of the primary transmission link, and analyzing the first backup transmission link status data using a pre-trained relay degree of freedom evaluation model to obtain the link relay degree of freedom of the primary transmission link, wherein the first backup transmission link status data is used to reflect the link status data of the backup transmission links associated with the primary transmission link, and the link status data includes at least: link transmission performance and link failure probability; determining the network relay degree of freedom of the wireless communication network based on the link relay degree of freedom of each primary transmission link, and optimizing the relay degree of freedom of the wireless communication network when the network relay degree of freedom is less than a preset degree of freedom threshold.

[0137] According to an embodiment of this application, a processor is also provided for running a program, wherein the program executes the network optimization method in embodiment 1 during runtime.

[0138] Optionally, the program executes the following steps during runtime: obtaining the occurrence frequency of multiple transmission links in the wireless communication network within a target period; identifying at least one primary transmission link from the multiple transmission links in the wireless communication network whose occurrence frequency is greater than a preset frequency threshold; for each primary transmission link, obtaining the status data of the first backup transmission link of the primary transmission link, and analyzing the status data of the first backup transmission link using a pre-trained relay degree of freedom evaluation model to obtain the link relay degree of freedom of the primary transmission link, wherein the status data of the first backup transmission link is used to reflect the link status data of the backup transmission links associated with the primary transmission link, and the link status data includes at least: link transmission performance and link failure probability; determining the network relay degree of freedom of the wireless communication network based on the link relay degree of freedom of each primary transmission link, and optimizing the relay degree of freedom of the wireless communication network when the network relay degree of freedom is less than a preset degree of freedom threshold.

[0139] According to an embodiment of this application, an electronic device is also provided, wherein, Figure 5 This is a schematic diagram of the structure of an optional electronic device according to an embodiment of this application, such as... Figure 5 As shown, the electronic device includes one or more processors; a memory for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to run the programs, wherein the programs are configured to execute the network optimization method in Embodiment 1 above during runtime.

[0140] Optionally, the processor is configured to execute the following steps via a computer program: acquiring the occurrence frequency of multiple transmission links in the wireless communication network within a target period; determining at least one primary transmission link from the multiple transmission links in the wireless communication network whose occurrence frequency is greater than a preset frequency threshold; for each primary transmission link, acquiring the state data of a first backup transmission link of the primary transmission link, and analyzing the state data of the first backup transmission link using a pre-trained relay degree of freedom evaluation model to obtain the link relay degree of freedom of the primary transmission link, wherein the state data of the first backup transmission link is used to reflect the link state data of the backup transmission links associated with the primary transmission link, and the link state data includes at least: link transmission performance and link failure probability; determining the network relay degree of freedom of the wireless communication network based on the link relay degree of freedom of each primary transmission link, and optimizing the relay degree of freedom of the wireless communication network when the network relay degree of freedom is less than a preset degree of freedom threshold.

[0141] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0142] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0143] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0144] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0145] 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.

[0146] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to related technologies, 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 storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0147] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A network optimization method, characterized in that, include: Obtain the frequency of occurrence of multiple transmission links in a wireless communication network within a target period; Determine at least one primary transmission link from among the multiple transmission links of the wireless communication network whose frequency of occurrence is greater than a preset frequency threshold; For each primary transmission link, the status data of the first backup transmission link of the primary transmission link is obtained, and the status data of the first backup transmission link is analyzed using a pre-trained relay degree of freedom evaluation model to obtain the link relay degree of freedom of the primary transmission link. The status data of the first backup transmission link is used to reflect the link status data of the backup transmission link associated with the primary transmission link, and the link status data includes at least: link transmission performance and link failure probability. The network relay degree of the wireless communication network is determined based on the link relay degree of each of the primary transmission links, and the wireless communication network is optimized for relay degree of freedom when the network relay degree of freedom is less than a preset degree of freedom threshold. The process of acquiring the status data of the first backup transmission link of the primary transmission link includes: acquiring at least one backup transmission link of the primary transmission link; acquiring multiple link performance data of the backup transmission link, wherein the types of the link performance data include at least one of the following: latency, packet loss rate, and channel load; standardizing each of the link performance data and calculating the information entropy of each standardized link performance data; determining the weight value of each of the link performance data based on the information entropy and using the entropy weight method; determining the link transmission performance of the backup transmission link based on the multiple link performance data and the corresponding weight values; dividing the backup transmission link into multiple sub-transmission paths based on the pairwise adjacent transmission nodes within the backup transmission link; acquiring historical fault data of each of the sub-transmission paths and analyzing the historical fault data of each of the sub-transmission paths using a neural network model to obtain the fault probability of each of the sub-transmission paths; and determining the link fault probability of the backup transmission link based on the fault probabilities of each of the sub-transmission paths within the backup transmission link.

2. The method according to claim 1, characterized in that, Obtaining the frequency of occurrence of multiple transmission links in a wireless communication network within a target period includes: A network topology diagram of the wireless communication network is constructed, wherein the network topology diagram is constructed based on the various network devices in the wireless communication network and the transmission relationships between the various network devices, and the network topology diagram includes: multiple network device nodes and the lines connecting the various network device nodes; Obtain the connection data of each connection in the network topology map within the target period, wherein the connection data includes at least: source IP address and destination IP address; The frequency of occurrence of each transmission link in the wireless communication network within the target period is determined based on the connection data.

3. The method according to claim 2, characterized in that, Constructing the network topology diagram of the wireless communication network includes: Identify multiple network devices within the wireless communication network, wherein the device type of the network devices includes at least one of the following: router, switch, server; The transmission relationship between the various network devices is obtained through a preset method, wherein the preset method includes at least one of the following: viewing the configuration file of the network device, querying the network management system, or calling a network scanning tool; Each of the network devices is used as a topology node, and the transmission relationship between the network devices is used as the connection relationship between the topology nodes to construct the network topology graph.

4. The method according to claim 1, characterized in that, Acquiring at least one backup transmission link of the primary transmission link includes: Identify the transmission network device on the primary transmission link and determine whether the transmission network device is a relay network device, wherein the relay network device is a network device with relay function other than the source network device and the destination network device; When the transmission network device is the relay network device, at least one transmission link in the wireless communication network is determined based on the source network device, the relay network device, and the destination network device in the primary transmission link. Calculate the distance between each of the transmission links and the primary transmission link, and designate the transmission links whose distance is less than a preset distance threshold as backup transmission links for the primary transmission link.

5. The method according to claim 4, characterized in that, Determining whether the transmission network device is a relay network device includes: Determine whether the transmission network device is an intermediate network device; When the transmission network device is the intermediate network device, the historical transmission performance data of the intermediate network device in the primary transmission link is obtained according to a preset method, wherein the historical transmission performance data includes at least one of the following: forwarding data volume, forwarding success rate, transmission delay, and packet loss rate. Determine the relationship between the historical transmission performance data and the preset transmission performance index threshold; If the historical transmission performance data is greater than the transmission performance index threshold, the transmission network device is determined to be the relay network device; If the historical transmission performance data is not greater than the transmission performance index threshold, it is determined that the transmission network device is not the relay network device.

6. The method according to claim 1, characterized in that, The training process of the transit degree of freedom evaluation model includes: Multiple sets of training samples are obtained, wherein each set of training samples includes: the status data of the second backup transmission link of the primary transmission link sample and the corresponding link relay degrees of freedom; Construct a neural network model, wherein the neural network model includes at least: an input layer, a hidden layer, and an output layer; The neural network model is iteratively trained based on multiple sets of training samples to obtain the intermediate degree of freedom evaluation model.

7. A network optimization device, characterized in that, include: The acquisition module is used to acquire the frequency of occurrence of multiple transmission links in the wireless communication network within a target period. The determining module is used to determine, from multiple transmission links of the wireless communication network, at least one primary transmission link whose occurrence frequency is greater than a preset frequency threshold; The evaluation module is used to acquire the first backup transmission link status data of the primary transmission link for each primary transmission link, and analyze the first backup transmission link status data using a pre-trained relay degree of freedom evaluation model to obtain the link relay degree of freedom of the primary transmission link. The first backup transmission link status data is used to reflect the link status data of the backup transmission links associated with the primary transmission link, and the link status data includes at least: link transmission performance and link failure probability. An optimization module is used to determine the network relay degree of the wireless communication network based on the link relay degree of freedom of each of the primary transmission links, and to optimize the relay degree of freedom of the wireless communication network when the network relay degree of freedom is less than a preset degree of freedom threshold. The process of acquiring the status data of the first backup transmission link of the primary transmission link includes: acquiring at least one backup transmission link of the primary transmission link; acquiring multiple link performance data of the backup transmission link, wherein the types of the link performance data include at least one of the following: latency, packet loss rate, and channel load; standardizing each of the link performance data and calculating the information entropy of each standardized link performance data; determining the weight value of each of the link performance data based on the information entropy and using the entropy weight method; determining the link transmission performance of the backup transmission link based on the multiple link performance data and the corresponding weight values; dividing the backup transmission link into multiple sub-transmission paths based on the pairwise adjacent transmission nodes within the backup transmission link; acquiring historical fault data of each of the sub-transmission paths and analyzing the historical fault data of each of the sub-transmission paths using a neural network model to obtain the fault probability of each of the sub-transmission paths; and determining the link fault probability of the backup transmission link based on the fault probabilities of each of the sub-transmission paths within the backup transmission link.

8. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores a computer program, wherein the device containing the non-volatile storage medium executes the network optimization method according to any one of claims 1 to 6 by running the computer program.

9. A computer program product, characterized in that, include: A computer program, wherein when executed by a processor, the computer program implements the network optimization method according to any one of claims 1 to 6.

Images