Flow bandwidth intelligent distribution optimization method and system

Abstract

The invention provides a flow bandwidth intelligent distribution optimization method and system, and relates to the technical field of flow bandwidth intelligent distribution optimization, and the method comprises the steps: constructing an information transmission network, obtaining a node information transmission path, analyzing flow change data, and obtaining a path risk node; obtaining path intersection node information, generating intersection risk nodes, obtaining risk feature data, and constructing a multi-level traffic risk network; calculating a first-level abnormal coefficient and a second-level abnormal coefficient, comparing the first-level abnormal coefficient and the second-level abnormal coefficient with a first-level preset threshold value and a second-level preset threshold value respectively, and then performing traffic abnormality judgment to obtain a traffic abnormality judgment result; according to the method and the system, the problems that in the prior art, flow management is lack of flexibility, intelligence and comprehensive evaluation are solved, and the like.

Description

Technical Field

[0001] The present invention proposes a method and system for optimizing intelligent allocation of traffic bandwidth, and relates to the technical field of intelligent allocation optimization of traffic bandwidth. Background Art

[0002] Traditional traffic management methods are often based on fixed bandwidth allocation strategies, lack flexibility, and are difficult to cope with sudden traffic changes and risk events in the network. In the existing technology, although there are some means of traffic monitoring and bandwidth management, most of them only focus on the network status at a single level, such as monitoring only node traffic or only considering bandwidth allocation at the path level, and lack a multi-level, all-round assessment of the overall network traffic risk. This makes it difficult for network managers to quickly and accurately locate the root cause of the problem and take effective countermeasures when traffic anomalies or risk events occur. Traditional bandwidth allocation methods often rely on manual experience and fixed threshold settings, lacking adaptability and intelligence. When network traffic patterns change or new risk types are encountered, these methods may not be able to make adjustments in time, resulting in network performance degradation or resource waste. Summary of the invention

[0003] The present invention provides a method and system for optimizing intelligent allocation of traffic bandwidth to solve the above problems:

[0004] The present invention proposes a method and system for intelligently allocating and optimizing traffic bandwidth, wherein the method comprises:

[0005] S1. Build an information transmission network, obtain information transmission nodes, and then obtain node information transmission paths, generate path node traffic packets, analyze traffic change data, and obtain path risk nodes;

[0006] S2. Obtain path intersection node information based on node information transmission path information, generate intersection risk nodes, obtain risk feature data, mark first-level risks and second-level risks, and build a multi-level traffic risk network;

[0007] S3, calculating the first-level abnormality coefficient and the second-level abnormality coefficient, comparing the first-level abnormality coefficient and the second-level abnormality coefficient with the first-level preset threshold and the second-level preset threshold, respectively, and then performing flow abnormality determination to obtain a flow abnormality determination result;

[0008] S4. Calculate the flow bandwidth allocation coefficients of the path nodes and the intersection nodes respectively, and then adjust the flow bandwidth allocation.

[0009] Furthermore, the S1 includes:

[0010] Obtaining network information transmission requirements, and building an information transmission network according to the network information transmission requirements;

[0011] Acquire information transmission nodes of the information transmission network, and acquire node flow information and node information transmission path of each information transmission node;

[0012] Acquire node flow information on the node information transmission path, and generate multiple path node flow packets corresponding to the node information transmission path;

[0013] Generate a traffic packet group corresponding to the node information transmission path according to the multiple path node traffic packets;

[0014] Obtaining flow change data of the flow packet group, comparing the flow change data with a preset change threshold, and obtaining a change comparison result;

[0015] According to the change comparison result, the information transmission node is judged as an abnormal node to obtain the path risk node.

[0016] Further, the S2 includes:

[0017] Acquire multiple node information transmission path information, and acquire path intersection node information according to the node information transmission path information;

[0018] Obtain path risk nodes of path intersection node information and generate intersection risk nodes;

[0019] Obtain risk characteristic data of path risk nodes, and obtain path node risk characteristic data;

[0020] Obtain risk characteristic data of the intersection risk nodes, and obtain risk characteristic data of the intersection nodes;

[0021] Marking the path node risk characteristic data as first-level risk;

[0022] The risk characteristic data of the intersection nodes are marked as second-level risks; and a multi-level traffic risk network is constructed based on the first-level risk information and the second-level risk information.

[0023] Further, the S3 includes:

[0024] Obtain multi-level traffic risk network information to calculate the first-level anomaly coefficient;

[0025] Compare the first-level abnormality coefficient with the first-level preset threshold to obtain a first-level comparison result;

[0026] Performing flow anomaly determination on the first-level flow according to the first-level comparison result to obtain a first flow anomaly determination result;

[0027] Calculate the second-level abnormality coefficient based on the first-level flow abnormality determination;

[0028] Compare the second-level abnormality coefficient with the second-level preset threshold to obtain a second-level comparison result;

[0029] A flow anomaly determination is performed on the second-level flow according to the second-level comparison result to obtain a second flow anomaly determination result.

[0030] Further, the S4 includes:

[0031] When the first traffic anomaly determination result is an abnormal determination result, the traffic bandwidth allocation coefficient of the corresponding path risk node is calculated according to the first-level abnormality coefficient combined with the path node risk feature data;

[0032] When the second traffic anomaly determination result is an anomaly determination, the traffic bandwidth allocation coefficient of the corresponding intersection risk node is calculated according to the second-level anomaly coefficient combined with the intersection node risk feature data;

[0033] Obtain node anomaly data after traffic bandwidth allocation for continuous monitoring and adjustment.

[0034] Furthermore, the allocation optimization system comprises:

[0035] The network risk node determination module is used to build an information transmission network, obtain information transmission nodes, and then obtain node information transmission paths, generate path node traffic packets, analyze traffic change data, and obtain path risk nodes;

[0036] The intersection node determination module is used to obtain the path intersection node information according to the node information transmission path information, generate the intersection risk node, obtain the risk characteristic data, mark the first level risk and the second level risk, and build a multi-level traffic risk network;

[0037] The multi-layer anomaly analysis module is used to calculate the first-layer anomaly coefficient and the second-layer anomaly coefficient, compare the first-layer anomaly coefficient and the second-layer anomaly coefficient with the first-layer preset threshold and the second-layer preset threshold respectively, and then make a flow anomaly determination to obtain a flow anomaly determination result;

[0038] The allocation module is used to calculate the flow bandwidth allocation coefficients of the path nodes and the intersection nodes respectively, and then to adjust the flow bandwidth allocation.

[0039] Furthermore, the network risk node determination module includes:

[0040] A network construction module, used to obtain network information transmission requirements and construct an information transmission network according to the network information transmission requirements;

[0041] A path acquisition module is used to acquire information transmission nodes of the information transmission network, and acquire node flow information and node information transmission path of each information transmission node;

[0042] A flow change comparison module, used to obtain the node flow information on the node information transmission path, and generate a plurality of path node flow packets corresponding to the node information transmission path;

[0043] Generate a traffic packet group corresponding to the node information transmission path according to the multiple path node traffic packets;

[0044] Obtaining flow change data of the flow packet group, comparing the flow change data with a preset change threshold, and obtaining a change comparison result;

[0045] The risk determination module is used to determine abnormal nodes of information transmission nodes according to the change comparison result to obtain path risk nodes.

[0046] Furthermore, the intersection node determination module includes:

[0047] An intersection node generation module is used to obtain multiple node information transmission path information, and obtain path intersection node information according to the node information transmission path information;

[0048] Obtain path risk nodes of path intersection node information and generate intersection risk nodes;

[0049] A feature data acquisition module is used to acquire risk feature data of path risk nodes and obtain path node risk feature data;

[0050] Obtain risk characteristic data of the intersection risk nodes, and obtain risk characteristic data of the intersection nodes;

[0051] A multi-layer network monitoring module, used to mark the path node risk characteristic data as a first-level risk;

[0052] Marking the risk characteristic data of the intersection node as a second-level risk;

[0053] A multi-level traffic risk network is constructed based on the first-level risk information and the second-level risk information.

[0054] Furthermore, the network risk node determination module includes:

[0055] A first calculation and determination module is used to obtain multi-level traffic risk network information and calculate a first-level abnormality coefficient;

[0056] Compare the first-level abnormality coefficient with the first-level preset threshold to obtain a first-level comparison result;

[0057] Performing flow anomaly determination on the first-level flow according to the first-level comparison result to obtain a first flow anomaly determination result;

[0058] A second calculation and determination module, used for calculating a second-level abnormality coefficient according to the first-level flow abnormality determination;

[0059] Compare the second-level abnormality coefficient with the second-level preset threshold to obtain a second-level comparison result;

[0060] A flow anomaly determination is performed on the second-level flow according to the second-level comparison result to obtain a second flow anomaly determination result.

[0061] Furthermore, the allocation module includes:

[0062] A first calculation allocation module, configured to calculate a flow bandwidth allocation coefficient of a corresponding path risk node according to the first-level abnormality coefficient combined with path node risk feature data when the first flow abnormality determination result is an abnormal determination result;

[0063] A second calculation allocation module, configured to calculate a flow bandwidth allocation coefficient of a corresponding intersection risk node according to the second-level anomaly coefficient combined with the intersection node risk feature data when the second flow anomaly determination result is an anomaly determination;

[0064] The monitoring module is used to obtain node abnormality data after traffic bandwidth allocation for continuous monitoring and adjustment.

[0065] Beneficial effects of the present invention: By identifying risky nodes and intelligently allocating traffic bandwidth, the risk of network failure can be effectively reduced and the stability and reliability of the network can be improved. By allocating bandwidth according to the risk level of the node and the actual needs, network resources can be used more reasonably to avoid waste and over-concentration of resources. By optimizing the allocation of traffic bandwidth, the delay and packet loss rate of data transmission can be reduced, and the efficiency and quality of data transmission can be improved. This method can adapt to network environments of different scales and complexities, and provide strong support for network expansion and upgrading. Through the automated risk identification and bandwidth allocation process, the cost and complexity of manual intervention can be reduced, and intelligent and automated network management can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 A schematic diagram of a method for intelligently allocating and optimizing traffic bandwidth;

[0067] Figure 2 Figure 1 is a schematic diagram of a multi-level traffic risk network. DETAILED DESCRIPTION

[0068] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0069] In one embodiment of the present invention, a method and system for intelligently allocating and optimizing traffic bandwidth are provided. The allocation optimization method includes:

[0070] S1. Build an information transmission network, obtain information transmission nodes, and then obtain node information transmission paths, generate path node traffic packets, analyze traffic change data, and obtain path risk nodes;

[0071] S2. Obtain path intersection node information based on node information transmission path information, generate intersection risk nodes, obtain risk feature data, mark first-level risks and second-level risks, and build a multi-level traffic risk network;

[0072] S3, calculating the first-level abnormality coefficient and the second-level abnormality coefficient, comparing the first-level abnormality coefficient and the second-level abnormality coefficient with the first-level preset threshold and the second-level preset threshold, respectively, and then performing flow abnormality determination to obtain a flow abnormality determination result;

[0073] S4. Calculate the flow bandwidth allocation coefficients of the path nodes and the intersection nodes respectively, and then adjust the flow bandwidth allocation, such as Figure 1 shown.

[0074] The working principle of the above technical solution is as follows: construct an information transmission network, which consists of multiple information transmission nodes and connection paths between nodes. Identify each node in the network and determine the information transmission path between nodes. Generate path node traffic packets, which represent the data traffic in the network. By analyzing the traffic change data, identify the nodes that may be at risk in the path. The nodes are interrupted or delayed in data transmission due to various reasons (such as equipment failure, network congestion, etc.). According to the node information transmission path information, obtain the path intersection node information, that is, those nodes shared by multiple paths in the network. Generate intersection risk nodes. Since these nodes are located at the intersection of multiple paths, their failure can have a greater impact on the entire network. Obtain risk feature data, including node traffic changes, delays, packet loss rates, etc., to assess the risk level of the node. According to the risk feature data, mark the first-level risk and the second-level risk. The first-level risk usually refers to the risk that directly affects a single path, while the second-level risk may involve the intersection of multiple paths and have a greater impact on the entire network. Build a risk network containing multiple levels to more comprehensively understand the risk distribution in the network. Calculate the anomaly coefficients of the first and second levels, which reflect the degree of deviation of the nodes of the first level from the normal state in the current state. Compare the calculated anomaly coefficient with the preset threshold. If the anomaly coefficient exceeds the threshold, it is determined to be a traffic anomaly. According to the judgment results, potential problems in the network can be discovered in time, and corresponding measures can be taken to intervene. Calculate the traffic bandwidth allocation coefficients of the path nodes and the intersection nodes respectively. It reflects the relative importance of the nodes in the network and the bandwidth resources required by them. According to the calculated allocation coefficient, the traffic bandwidth is allocated and adjusted. For nodes with higher risks, their bandwidth resources can be appropriately increased to improve the stability and efficiency of data transmission.

[0075] The technical effect of the above technical solution is: by identifying risk nodes and intelligently allocating traffic bandwidth, the risk of network failure can be effectively reduced and the stability and reliability of the network can be improved. By allocating bandwidth according to the risk level of the node and the actual needs, network resources can be used more reasonably to avoid waste and excessive concentration of resources. By optimizing the allocation of traffic bandwidth, the delay and packet loss rate of data transmission can be reduced, and the efficiency and quality of data transmission can be improved. This method can adapt to network environments of different scales and complexities, and provide strong support for network expansion and upgrading. Through the automated risk identification and bandwidth allocation process, the cost and complexity of manual intervention can be reduced, and the intelligent and automated network management can be realized.

[0076] In one embodiment of the present invention, the S1 includes:

[0077] Obtaining network information transmission requirements, and building an information transmission network according to the network information transmission requirements;

[0078] Acquire information transmission nodes of the information transmission network, and acquire node flow information and node information transmission path of each information transmission node;

[0079] Acquire node flow information on the node information transmission path, and generate multiple path node flow packets corresponding to the node information transmission path;

[0080] Generate a traffic packet group corresponding to the node information transmission path according to the multiple path node traffic packets;

[0081] Obtaining flow change data of a flow packet group, comparing the flow change data with a preset change threshold, and obtaining a change comparison result; the flow change data is a flow difference between every two adjacent nodes;

[0082] According to the change comparison result, the information transmission node is judged as an abnormal node to obtain the path risk node.

[0083] When the flow change data is greater than the preset change threshold, the node with relatively large flow in the flow difference is the path risk node.

[0084] The working principle of the above technical solution is: according to business needs or network planning, the specific requirements of network information transmission, such as the amount of data transmitted, transmission speed, transmission stability, etc., are clarified. According to the network information transmission requirements, the corresponding information transmission network is constructed. This network consists of multiple information transmission nodes and connection paths between nodes. In the constructed information transmission network, the node traffic information of each information transmission node is identified and obtained, which includes the data sending amount and receiving amount of the node. The information transmission path of each node, that is, the path of data flow between nodes, is obtained. For each node information transmission path, multiple path node traffic packets are generated according to the traffic information of the nodes on the path. These traffic packets represent the data transmission volume between different nodes on the path. Multiple path node traffic packets on the same path are combined into a traffic packet group. The traffic change data of the traffic packet group is obtained, which is mainly to calculate the traffic difference between each two adjacent nodes, that is, the change in the data transmission volume between adjacent nodes. The calculated traffic change data is compared with the preset traffic change threshold. If the traffic change data is greater than the preset change threshold, it means that the data transmission volume between adjacent nodes has changed significantly, and there may be anomalies. Nodes with relatively large traffic in the traffic difference are determined to be path risk nodes. This is because nodes with larger traffic volumes may be more prone to transmission bottlenecks or failures, thus affecting data transmission along the entire path.

[0085] The technical effect of the above technical solution is: by real-time monitoring of traffic changes between nodes, abnormal situations in the network can be discovered in time, improving the accuracy and timeliness of network monitoring. By identifying path risk nodes, these nodes can be monitored and optimized, thereby improving the performance and stability of the entire network. Timely discovery and processing of path risk nodes can reduce the risk of network failures, and reduce problems such as business interruption and data loss caused by network failures. By analyzing and monitoring node traffic information, network resources can be allocated more reasonably, improving resource utilization and efficiency.

[0086] In one embodiment of the present invention, S2 includes:

[0087] Acquire multiple node information transmission path information, and acquire path intersection node information according to the node information transmission path information;

[0088] Obtain path risk nodes of path intersection node information and generate intersection risk nodes;

[0089] The risk characteristic data of the path risk node is obtained, and the path node risk characteristic data is obtained; the path node risk characteristic data is the flow characteristic data of the path node.

[0090] The risk characteristic data of the intersection risk node is obtained, and the intersection node risk characteristic data is obtained; the intersection node risk characteristic data is the data of the flow characteristic of the intersection node.

[0091] The path node risk feature data is labeled as the first level risk; the first level risk is the risk labeling of all path risk nodes in the network.

[0092] The risk characteristic data of the intersection nodes are marked as second-level risks; the second-level risks are risk labels for all the intersection risk nodes in the network.

[0093] Based on the first-level risk information and the second-level risk information, a multi-level traffic risk network is constructed, such as Figure 2 As shown, this figure is only a schematic diagram, and the specific node position is determined by the data.

[0094] The working principle of the above technical solution is: obtain information of multiple node information transmission paths through network monitoring or data analysis tools, which includes nodes on the path and the connection relationship between nodes. According to these path information, identify the path intersection nodes, that is, the nodes located at the intersection of multiple paths in the network. For each path, obtain the path risk node information on it. Path risk nodes may be nodes with potential risks determined based on previous traffic analysis, fault history or other indicators. Extract the risk nodes located at the intersection of the paths and generate a list of intersection risk nodes. Since these nodes are located at the intersection of multiple paths, their failures may have a greater impact on the entire network. For path risk nodes and intersection risk nodes, obtain their risk feature data respectively. These feature data are mainly based on the traffic characteristics of the nodes, such as traffic size, traffic change rate, packet loss rate, delay, etc. By analyzing these feature data, the risk level of the node can be evaluated. The feature data of the path risk node is marked as the first level risk. This level of risk mainly reflects the potential risk of nodes on each path in the network. The feature data of the intersection risk node is marked as the second level risk. This level of risk focuses more on the risks of intersection nodes in the network, because the failure of these nodes may have a simultaneous impact on multiple paths. Based on the risk information of the first and second levels, a risk network with multiple levels is constructed. This network not only shows the risk level of each node in the network, but also reveals how the risk propagates and spreads in the network. Through this multi-level traffic risk network, we can have a more comprehensive understanding of the risk distribution and potential threats in the network.

[0095] The technical effect of the above technical solution is: by building a multi-level traffic risk network, it is possible to more accurately identify and evaluate potential risks in the network and improve the ability of network risk management. By focusing on monitoring and optimizing risk nodes, the risk of network failure can be reduced and the stability and performance of the network can be improved. This method is suitable for network environments of different scales and complexities, and can support the expansion and upgrade of the network to ensure that the network remains efficient and secure during continuous development. Through the automated risk identification and labeling process, the cost and complexity of manual intervention can be reduced, and the efficiency and quality of network maintenance can be improved. By timely discovering and handling potential risk nodes, the security of the network can be enhanced to prevent problems such as network paralysis and data leakage caused by node failures or attacks.

[0096] In one embodiment of the present invention, S3 includes:

[0097] Obtain multi-level traffic risk network information to calculate the first-level anomaly coefficient;

[0098] The calculation formula of the first-level abnormality coefficient is:

[0099]

[0100] Among them, YC is the first-level network anomaly coefficient, w is the total number of paths in the information transmission network, f is the total number of path risk nodes in the path, and L i is the flow data of the i-th path risk node, L i-1 is the i-1th path node of the i-th path risk node, (L i -L i-1 ) o is the total amount of abnormal traffic changes of the path risk nodes of the oth path of the information transmission network, y is the total number of path nodes in the path, L x is the flow data of the x-th path node, L x-1 is the x-1th path node of the xth path node, (L x -L x-1 ) o is the total amount of abnormal traffic change of the oth path of the path node of the information transmission network;

[0101] Compare the first-level abnormality coefficient with the first-level preset threshold to obtain a first-level comparison result;

[0102] Performing flow anomaly determination on the first-level flow according to the first-level comparison result to obtain a first flow anomaly determination result;

[0103] Calculate the second-level abnormality coefficient based on the first-level flow abnormality determination;

[0104] When the first-level determination result is abnormal, the calculation of the second-level abnormality coefficient begins.

[0105] The calculation formula of the second-level abnormality coefficient is:

[0106]

[0107] Among them, RC is the second-level network anomaly coefficient, w is the total number of paths in the information transmission network, j is the total number of intersecting risk nodes in the path, L a is the flow data of the ath intersection risk node, (L a ) o is the traffic anomaly of the ath intersection risk node of the oth path of the information transmission network, f is the total number of path risk nodes in the path, L i is the flow data of the i-th path risk node, (L i ) o is the traffic anomaly of the ath intersection risk node of the oth path of the information transmission network;

[0108] Compare the second-level abnormality coefficient with the second-level preset threshold to obtain a second-level comparison result;

[0109] A flow anomaly determination is performed on the second-level flow according to the second-level comparison result to obtain a second flow anomaly determination result.

[0110] The working principle of the above technical solution is: calculate the first-level network anomaly coefficient, which comprehensively considers the risk node traffic data of all paths in the information transmission network, the total amount of abnormal traffic changes between adjacent nodes, and the total number of nodes in the path. Each variable in the formula represents different network traffic characteristics, such as L i and L i-1 Represent the flow data of the i-th path risk node and its previous node respectively, (L i -L i-1 ) o represents the total amount of abnormal traffic change at the ith risk node in the oth path. Similarly, L x and L x-1 and (L x -L x-1 ) o Represents the traffic data and total amount of abnormal changes of the path nodes. By calculating these data, a coefficient reflecting the degree of abnormality of the first-level network can be obtained. Compare the calculated first-level abnormality coefficient with the preset first-level threshold. If the abnormality coefficient exceeds the threshold, it is determined that the first-level traffic is abnormal, otherwise it is determined to be normal. If the first-level judgment result is abnormal, the second-level network abnormality coefficient is further calculated. This coefficient is also based on a series of traffic feature data, but it focuses more on the abnormal amount of traffic at the intersection risk nodes. L in the formula a represents the flow data of the ath intersection risk node, (L a ) o represents the abnormal flow volume of the ath intersection risk node in the oth path. At the same time, the flow data of the path risk node (L i ) o ; Compare the calculated second-level abnormality coefficient with the preset second-level threshold value. According to the comparison result, determine whether the second-level traffic is abnormal.

[0111] The technical effect of the above technical solution is: by calculating the anomaly coefficient in a hierarchical manner, the degree of anomaly in the network can be evaluated more carefully and the accuracy of detection can be improved. By real-time monitoring and calculating the anomaly coefficient, potential problems in the network can be discovered in a timely manner. The hierarchical anomaly detection mechanism helps to better identify and manage risk points in the network. Through the automated anomaly detection and judgment process, the cost and complexity of manual intervention can be reduced, and the efficiency of network maintenance can be improved. This method is suitable for network environments of different scales and complexities, and can support network expansion and upgrading, ensuring that the network remains efficient and secure in its continuous development.

[0112] In one embodiment of the present invention, the S4 includes:

[0113] When the first traffic anomaly determination result is an abnormal determination result, the traffic bandwidth allocation coefficient of the corresponding path risk node is calculated according to the first-level abnormality coefficient combined with the path node risk feature data;

[0114] The calculation formula of the traffic bandwidth allocation coefficient corresponding to the path risk node is:

[0115]

[0116] Among them, FP1 is the traffic bandwidth allocation coefficient of the corresponding path risk node, YC is the first-level abnormality coefficient, and L d is the path node risk characteristic data corresponding to the path risk node, L z is the path node risk characteristic data of all path risk nodes, DK z It is the total traffic bandwidth data;

[0117] When the second traffic anomaly determination result is an anomaly determination, the traffic bandwidth allocation coefficient of the corresponding intersection risk node is calculated according to the second-level anomaly coefficient combined with the intersection node risk feature data;

[0118] The calculation formula of the traffic bandwidth allocation coefficient corresponding to the intersection risk node is:

[0119]

[0120] Among them, FP2 is the traffic bandwidth allocation coefficient corresponding to the intersection risk node, RC is the second-level network anomaly coefficient, and J d is the intersection node risk characteristic data of the current intersection risk node, J z is the intersection node risk characteristic data of all intersection risk nodes, DK z It is the total traffic bandwidth data;

[0121] Obtain node anomaly data after traffic bandwidth allocation for continuous monitoring and adjustment.

[0122] The working principle of the above technical solution is: when the first flow anomaly judgment result is abnormal, it means that there is a flow anomaly of the path risk node in the network. At this time, it is necessary to calculate the flow bandwidth allocation coefficient based on the first-level anomaly coefficient and the risk characteristic data of the corresponding path risk node. The calculation formula takes into account the first-level anomaly coefficient (reflecting the severity of the network anomaly), the risk characteristic data of the corresponding path risk node (reflecting the specific risk status of the node) and the total flow bandwidth data (indicating the total bandwidth that can be allocated to the network). Through this formula, a reasonable bandwidth can be allocated to each path risk node to cope with the pressure brought by its flow anomaly. When the second flow anomaly judgment result is abnormal, it means that there is a flow anomaly of the intersection risk node in the network. At this time, it is necessary to calculate the flow bandwidth allocation coefficient based on the second-level anomaly coefficient and the risk characteristic data of the current intersection risk node). The calculation formula also takes into account the second-level anomaly coefficient (reflecting the severity of the intersection node anomaly), the risk characteristic data of the intersection risk node and the total flow bandwidth data. Through this formula, a reasonable bandwidth can be allocated to each intersection risk node to alleviate the impact of its flow anomaly on the overall performance of the network. After allocating traffic bandwidth, it is necessary to continuously monitor the abnormal data of the nodes, including traffic changes, delays, packet loss rates and other indicators. Based on the monitoring results, the bandwidth allocation coefficient can be dynamically adjusted to optimize network performance and reduce abnormal risks.

[0123] The technical effects of the above technical solution are as follows: through hierarchical anomaly determination and bandwidth allocation coefficient calculation, abnormal traffic in the network can be quickly identified and responded to, thereby improving the stability and reliability of the network. Dynamically allocating bandwidth resources according to the risk characteristics and degree of abnormality of the node can more effectively utilize network resources and improve the overall performance of the network. By continuously monitoring and adjusting the abnormal data of the node, potential network risk points can be discovered and handled in a timely manner, reducing the risk of network failure. The automated anomaly detection and bandwidth allocation process can reduce the cost and complexity of manual intervention and improve the efficiency and accuracy of network maintenance. This method is suitable for network environments of different scales and complexities, and can support the expansion and upgrade of the network, ensuring that the network remains efficient and secure during continuous development.

[0124] In one embodiment of the present invention, the allocation optimization system comprises:

[0125] The network risk node determination module is used to build an information transmission network, obtain information transmission nodes, and then obtain node information transmission paths, generate path node traffic packets, analyze traffic change data, and obtain path risk nodes;

[0126] The intersection node determination module is used to obtain the path intersection node information according to the node information transmission path information, generate the intersection risk node, obtain the risk characteristic data, mark the first level risk and the second level risk, and build a multi-level traffic risk network;

[0127] The multi-layer anomaly analysis module is used to calculate the first-layer anomaly coefficient and the second-layer anomaly coefficient, compare the first-layer anomaly coefficient and the second-layer anomaly coefficient with the first-layer preset threshold and the second-layer preset threshold respectively, and then make a flow anomaly determination to obtain a flow anomaly determination result;

[0128] The allocation module is used to calculate the flow bandwidth allocation coefficients of the path nodes and the intersection nodes respectively, and then to adjust the flow bandwidth allocation.

[0129] The working principle of the above technical solution is as follows: construct an information transmission network, which consists of multiple information transmission nodes and connection paths between nodes. Identify each node in the network and determine the information transmission path between nodes. Generate path node traffic packets, which represent the data traffic in the network. By analyzing the traffic change data, identify the nodes that may be at risk in the path. The nodes are interrupted or delayed in data transmission due to various reasons (such as equipment failure, network congestion, etc.). According to the node information transmission path information, obtain the path intersection node information, that is, those nodes shared by multiple paths in the network. Generate intersection risk nodes. Since these nodes are located at the intersection of multiple paths, their failure can have a greater impact on the entire network. Obtain risk feature data, including node traffic changes, delays, packet loss rates, etc., to assess the risk level of the node. According to the risk feature data, mark the first-level risk and the second-level risk. The first-level risk usually refers to the risk that directly affects a single path, while the second-level risk may involve the intersection of multiple paths and have a greater impact on the entire network. Build a risk network containing multiple levels to more comprehensively understand the risk distribution in the network. Calculate the anomaly coefficients of the first and second levels, which reflect the degree of deviation of the nodes of the first level from the normal state in the current state. Compare the calculated anomaly coefficient with the preset threshold. If the anomaly coefficient exceeds the threshold, it is determined to be a traffic anomaly. According to the judgment results, potential problems in the network can be discovered in time, and corresponding measures can be taken to intervene. Calculate the traffic bandwidth allocation coefficients of the path nodes and the intersection nodes respectively. It reflects the relative importance of the nodes in the network and the bandwidth resources required by them. According to the calculated allocation coefficient, the traffic bandwidth is allocated and adjusted. For nodes with higher risks, their bandwidth resources can be appropriately increased to improve the stability and efficiency of data transmission.

[0130] The technical effect of the above technical solution is: by identifying risk nodes and intelligently allocating traffic bandwidth, the risk of network failure can be effectively reduced and the stability and reliability of the network can be improved. By allocating bandwidth according to the risk level of the node and the actual needs, network resources can be used more reasonably to avoid waste and excessive concentration of resources. By optimizing the allocation of traffic bandwidth, the delay and packet loss rate of data transmission can be reduced, and the efficiency and quality of data transmission can be improved. This method can adapt to network environments of different scales and complexities, and provide strong support for network expansion and upgrading. Through the automated risk identification and bandwidth allocation process, the cost and complexity of manual intervention can be reduced, and the intelligent and automated network management can be realized.

[0131] In one embodiment of the present invention, the network risk node determination module includes:

[0132] A network construction module, used to obtain network information transmission requirements and construct an information transmission network according to the network information transmission requirements;

[0133] A path acquisition module is used to acquire information transmission nodes of the information transmission network, and acquire node flow information and node information transmission path of each information transmission node;

[0134] A flow change comparison module, used to obtain the node flow information on the node information transmission path, and generate a plurality of path node flow packets corresponding to the node information transmission path;

[0135] Generate a traffic packet group corresponding to the node information transmission path according to the multiple path node traffic packets;

[0136] Obtaining flow change data of a flow packet group, comparing the flow change data with a preset change threshold, and obtaining a change comparison result; the flow change data is a flow difference between every two adjacent nodes;

[0137] The risk determination module is used to determine abnormal nodes of information transmission nodes according to the change comparison result to obtain path risk nodes.

[0138] When the flow change data is greater than the preset change threshold, the node with relatively large flow in the flow difference is the path risk node.

[0139] The working principle of the above technical solution is: according to business needs or network planning, the specific requirements of network information transmission, such as the amount of data transmitted, transmission speed, transmission stability, etc., are clarified. According to the network information transmission requirements, the corresponding information transmission network is constructed. This network consists of multiple information transmission nodes and connection paths between nodes. In the constructed information transmission network, the node traffic information of each information transmission node is identified and obtained, which includes the data sending amount and receiving amount of the node. The information transmission path of each node, that is, the path of data flow between nodes, is obtained. For each node information transmission path, multiple path node traffic packets are generated according to the traffic information of the nodes on the path. These traffic packets represent the data transmission volume between different nodes on the path. Multiple path node traffic packets on the same path are combined into a traffic packet group. The traffic change data of the traffic packet group is obtained, which is mainly to calculate the traffic difference between each two adjacent nodes, that is, the change in the data transmission volume between adjacent nodes. The calculated traffic change data is compared with the preset traffic change threshold. If the traffic change data is greater than the preset change threshold, it means that the data transmission volume between adjacent nodes has changed significantly, and there may be anomalies. Nodes with relatively large traffic in the traffic difference are determined to be path risk nodes. This is because nodes with larger traffic volumes may be more prone to transmission bottlenecks or failures, thus affecting data transmission along the entire path.

[0140] The technical effect of the above technical solution is: by real-time monitoring of traffic changes between nodes, abnormal situations in the network can be discovered in time, improving the accuracy and timeliness of network monitoring. By identifying path risk nodes, these nodes can be monitored and optimized, thereby improving the performance and stability of the entire network. Timely discovery and processing of path risk nodes can reduce the risk of network failures, and reduce problems such as business interruption and data loss caused by network failures. By analyzing and monitoring node traffic information, network resources can be allocated more reasonably, improving resource utilization and efficiency.

[0141] In one embodiment of the present invention, the intersection node determination module includes:

[0142] An intersection node generation module is used to obtain multiple node information transmission path information, and obtain path intersection node information according to the node information transmission path information;

[0143] Obtain path risk nodes of path intersection node information and generate intersection risk nodes;

[0144] The characteristic data acquisition module is used to acquire the risk characteristic data of the path risk node, and obtain the path node risk characteristic data; the path node risk characteristic data is the data of the flow characteristics of the path node.

[0145] The risk characteristic data of the intersection risk node is obtained, and the intersection node risk characteristic data is obtained; the intersection node risk characteristic data is the data of the flow characteristic of the intersection node.

[0146] The multi-layer network monitoring module is used to mark the path node risk feature data as the first-level risk; the first-level risk is the risk mark of all path risk nodes in the network.

[0147] The risk characteristic data of the intersection nodes are marked as second-level risks; the second-level risks are risk labels for all the intersection risk nodes in the network.

[0148] A multi-level traffic risk network is constructed based on the first-level risk information and the second-level risk information.

[0149] The working principle of the above technical solution is: obtain information of multiple node information transmission paths through network monitoring or data analysis tools, which includes nodes on the path and the connection relationship between nodes. According to these path information, identify the path intersection nodes, that is, the nodes located at the intersection of multiple paths in the network. For each path, obtain the path risk node information on it. Path risk nodes may be nodes with potential risks determined based on previous traffic analysis, fault history or other indicators. Extract the risk nodes located at the intersection of the paths and generate a list of intersection risk nodes. Since these nodes are located at the intersection of multiple paths, their failures may have a greater impact on the entire network. For path risk nodes and intersection risk nodes, obtain their risk feature data respectively. These feature data are mainly based on the traffic characteristics of the nodes, such as traffic size, traffic change rate, packet loss rate, delay, etc. By analyzing these feature data, the risk level of the node can be evaluated. The feature data of the path risk node is marked as the first level risk. This level of risk mainly reflects the potential risk of nodes on each path in the network. The feature data of the intersection risk node is marked as the second level risk. This level of risk focuses more on the risks of intersection nodes in the network, because the failure of these nodes may have a simultaneous impact on multiple paths. Based on the risk information of the first and second levels, a risk network with multiple levels is constructed. This network not only shows the risk level of each node in the network, but also reveals how the risk propagates and spreads in the network. Through this multi-level traffic risk network, we can have a more comprehensive understanding of the risk distribution and potential threats in the network.

[0150] The technical effect of the above technical solution is: by building a multi-level traffic risk network, it is possible to more accurately identify and evaluate potential risks in the network and improve the ability of network risk management. By focusing on monitoring and optimizing risk nodes, the risk of network failure can be reduced and the stability and performance of the network can be improved. This method is suitable for network environments of different scales and complexities, and can support the expansion and upgrade of the network to ensure that the network remains efficient and secure during continuous development. Through the automated risk identification and labeling process, the cost and complexity of manual intervention can be reduced, and the efficiency and quality of network maintenance can be improved. By timely discovering and handling potential risk nodes, the security of the network can be enhanced to prevent problems such as network paralysis and data leakage caused by node failures or attacks.

[0151] In one embodiment of the present invention, the network risk node determination module includes:

[0152] A first calculation and determination module is used to obtain multi-level traffic risk network information and calculate a first-level abnormality coefficient;

[0153] The calculation formula of the first-level abnormality coefficient is:

[0154]

[0155] Among them, YC is the first-level network anomaly coefficient, w is the total number of paths in the information transmission network, f is the total number of path risk nodes in the path, and L i is the flow data of the i-th path risk node, L i-1 is the i-1th path node of the i-th path risk node, (L i -L i-1 ) o is the total amount of abnormal traffic changes of the path risk nodes of the oth path of the information transmission network, y is the total number of path nodes in the path, L x is the flow data of the x-th path node, L x-1 is the x-1th path node of the xth path node, (L x -L x-1 ) o is the total amount of abnormal traffic change of the oth path of the path node of the information transmission network;

[0156] Compare the first-level abnormality coefficient with the first-level preset threshold to obtain a first-level comparison result;

[0157] Performing flow anomaly determination on the first-level flow according to the first-level comparison result to obtain a first flow anomaly determination result;

[0158] A second calculation and determination module, used for calculating a second-level abnormality coefficient according to the first-level flow abnormality determination;

[0159] When the first-level determination result is abnormal, the calculation of the second-level abnormality coefficient begins.

[0160] The calculation formula of the second-level abnormality coefficient is:

[0161]

[0162] Among them, RC is the second-level network anomaly coefficient, w is the total number of paths in the information transmission network, j is the total number of intersecting risk nodes in the path, L a is the flow data of the ath intersection risk node, (L a ) o is the traffic anomaly of the ath intersection risk node of the oth path of the information transmission network, f is the total number of path risk nodes in the path, L i is the flow data of the i-th path risk node, (L i ) o is the traffic anomaly of the ath intersection risk node of the oth path of the information transmission network;

[0163] Compare the second-level abnormality coefficient with the second-level preset threshold to obtain a second-level comparison result;

[0164] A flow anomaly determination is performed on the second-level flow according to the second-level comparison result to obtain a second flow anomaly determination result.

[0165] The working principle of the above technical solution is: calculate the first-level network anomaly coefficient, which comprehensively considers the risk node traffic data of all paths in the information transmission network, the total amount of abnormal traffic changes between adjacent nodes, and the total number of nodes in the path. Each variable in the formula represents different network traffic characteristics, such as L i and L i-1 Represent the flow data of the i-th path risk node and its previous node respectively, (L i -L i-1 ) o represents the total amount of abnormal traffic change at the ith risk node in the oth path. Similarly, L x and L x-1 and (L x -L x-1 ) oRepresents the traffic data and total amount of abnormal changes of the path nodes. By calculating these data, a coefficient reflecting the degree of abnormality of the first-level network can be obtained. Compare the calculated first-level abnormality coefficient with the preset first-level threshold. If the abnormality coefficient exceeds the threshold, it is determined that the first-level traffic is abnormal, otherwise it is determined to be normal. If the first-level judgment result is abnormal, the second-level network abnormality coefficient is further calculated. This coefficient is also based on a series of traffic feature data, but it focuses more on the abnormal amount of traffic at the intersection risk nodes. L in the formula a represents the flow data of the ath intersection risk node, (L a ) o represents the abnormal flow volume of the ath intersection risk node in the oth path. At the same time, the flow data of the path risk node (L i ) o ; Compare the calculated second-level abnormality coefficient with the preset second-level threshold value. According to the comparison result, determine whether the second-level traffic is abnormal.

[0166] The technical effect of the above technical solution is: by calculating the anomaly coefficient in a hierarchical manner, the degree of anomaly in the network can be evaluated more carefully and the accuracy of detection can be improved. By real-time monitoring and calculating the anomaly coefficient, potential problems in the network can be discovered in a timely manner. The hierarchical anomaly detection mechanism helps to better identify and manage risk points in the network. Through the automated anomaly detection and judgment process, the cost and complexity of manual intervention can be reduced, and the efficiency of network maintenance can be improved. This method is suitable for network environments of different scales and complexities, and can support network expansion and upgrading, ensuring that the network remains efficient and secure in its continuous development.

[0167] In one embodiment of the present invention, the allocation module comprises:

[0168] A first calculation allocation module, configured to calculate a flow bandwidth allocation coefficient of a corresponding path risk node according to the first-level abnormality coefficient combined with path node risk feature data when the first flow abnormality determination result is an abnormal determination result;

[0169] The calculation formula of the traffic bandwidth allocation coefficient corresponding to the path risk node is:

[0170]

[0171] Among them, FP1 is the traffic bandwidth allocation coefficient of the corresponding path risk node, YC is the first-level abnormality coefficient, and L d is the path node risk characteristic data corresponding to the path risk node, L z is the path node risk characteristic data of all path risk nodes, DK z It is the total traffic bandwidth data;

[0172] A second calculation allocation module, configured to calculate a flow bandwidth allocation coefficient of a corresponding intersection risk node according to the second-level anomaly coefficient combined with the intersection node risk feature data when the second flow anomaly determination result is an anomaly determination;

[0173] The calculation formula of the traffic bandwidth allocation coefficient corresponding to the intersection risk node is:

[0174]

[0175] Among them, FP2 is the traffic bandwidth allocation coefficient corresponding to the intersection risk node, RC is the second-level network anomaly coefficient, and J d is the intersection node risk characteristic data of the current intersection risk node, J z is the intersection node risk characteristic data of all intersection risk nodes, DK z It is the total traffic bandwidth data;

[0176] The monitoring module is used to obtain node abnormality data after traffic bandwidth allocation for continuous monitoring and adjustment.

[0177] The working principle of the above technical solution is: when the first flow anomaly judgment result is abnormal, it means that there is a flow anomaly of the path risk node in the network. At this time, it is necessary to calculate the flow bandwidth allocation coefficient based on the first-level anomaly coefficient and the risk characteristic data of the corresponding path risk node. The calculation formula takes into account the first-level anomaly coefficient (reflecting the severity of the network anomaly), the risk characteristic data of the corresponding path risk node (reflecting the specific risk status of the node) and the total flow bandwidth data (indicating the total bandwidth that can be allocated to the network). Through this formula, a reasonable bandwidth can be allocated to each path risk node to cope with the pressure brought by its flow anomaly. When the second flow anomaly judgment result is abnormal, it means that there is a flow anomaly of the intersection risk node in the network. At this time, it is necessary to calculate the flow bandwidth allocation coefficient based on the second-level anomaly coefficient and the risk characteristic data of the current intersection risk node). The calculation formula also takes into account the second-level anomaly coefficient (reflecting the severity of the intersection node anomaly), the risk characteristic data of the intersection risk node and the total flow bandwidth data. Through this formula, a reasonable bandwidth can be allocated to each intersection risk node to alleviate the impact of its flow anomaly on the overall performance of the network. After allocating traffic bandwidth, it is necessary to continuously monitor the abnormal data of the nodes, including traffic changes, delays, packet loss rates and other indicators. Based on the monitoring results, the bandwidth allocation coefficient can be dynamically adjusted to optimize network performance and reduce abnormal risks.

[0178] The technical effects of the above technical solution are as follows: through hierarchical anomaly determination and bandwidth allocation coefficient calculation, abnormal traffic in the network can be quickly identified and responded to, thereby improving the stability and reliability of the network. Dynamically allocating bandwidth resources according to the risk characteristics and degree of abnormality of the node can more effectively utilize network resources and improve the overall performance of the network. By continuously monitoring and adjusting the abnormal data of the node, potential network risk points can be discovered and handled in a timely manner, reducing the risk of network failure. The automated anomaly detection and bandwidth allocation process can reduce the cost and complexity of manual intervention and improve the efficiency and accuracy of network maintenance. This method is suitable for network environments of different scales and complexities, and can support the expansion and upgrade of the network, ensuring that the network remains efficient and secure during continuous development.

[0179] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for optimizing intelligent allocation of traffic bandwidth, characterized in that: The allocation optimization method comprises: S1. Build an information transmission network, obtain information transmission nodes, and then obtain node information transmission paths, generate path node traffic packets, analyze traffic change data, and obtain path risk nodes; S2. Obtain path intersection node information based on node information transmission path information, generate intersection risk nodes, obtain risk feature data, mark first-level risks and second-level risks, and build a multi-level traffic risk network; S3, calculating the first-level abnormality coefficient and the second-level abnormality coefficient, comparing the first-level abnormality coefficient and the second-level abnormality coefficient with the first-level preset threshold and the second-level preset threshold, respectively, and then performing flow abnormality determination to obtain a flow abnormality determination result; S4. Calculate the flow bandwidth allocation coefficients of the path nodes and the intersection nodes respectively, and then adjust the flow bandwidth allocation.

2. According to claim 1, a method for optimizing intelligent allocation of traffic bandwidth is characterized in that: The S1 includes: Obtaining network information transmission requirements, and building an information transmission network according to the network information transmission requirements; Acquire information transmission nodes of the information transmission network, and acquire node flow information and node information transmission path of each information transmission node; Acquire node flow information on the node information transmission path, and generate multiple path node flow packets corresponding to the node information transmission path; Generate a traffic packet group corresponding to the node information transmission path according to the multiple path node traffic packets; Obtaining flow change data of the flow packet group, comparing the flow change data with a preset change threshold, and obtaining a change comparison result; According to the change comparison result, the information transmission node is judged as an abnormal node to obtain the path risk node.

3. According to claim 1, a method for optimizing intelligent allocation of traffic bandwidth is characterized in that: The S2 includes: Obtaining multiple node information transmission path information, and obtaining path intersection node information according to the node information transmission path information; Obtain path risk nodes of path intersection node information and generate intersection risk nodes; Obtain risk characteristic data of path risk nodes, and obtain path node risk characteristic data; Obtain risk characteristic data of the intersection risk nodes, and obtain risk characteristic data of the intersection nodes; Marking the path node risk characteristic data as first-level risk; Marking the risk characteristic data of the intersection node as a second-level risk; A multi-level traffic risk network is constructed based on the first-level risk information and the second-level risk information.

4. According to claim 1, a method for optimizing intelligent allocation of traffic bandwidth is characterized in that: The S3 includes: Obtain multi-level traffic risk network information to calculate the first-level anomaly coefficient; Compare the first-level abnormality coefficient with the first-level preset threshold to obtain a first-level comparison result; Performing flow anomaly determination on the first-level flow according to the first-level comparison result to obtain a first flow anomaly determination result; Calculate the second-level abnormality coefficient based on the first-level flow abnormality determination; Compare the second-level abnormality coefficient with the second-level preset threshold to obtain a second-level comparison result; A flow anomaly determination is performed on the second-level flow according to the second-level comparison result to obtain a second flow anomaly determination result.

5. According to claim 1, a method for optimizing intelligent allocation of traffic bandwidth is characterized in that: The S4 includes: When the first traffic anomaly determination result is an abnormal determination result, the traffic bandwidth allocation coefficient of the corresponding path risk node is calculated according to the first-level abnormality coefficient combined with the path node risk feature data; When the second traffic anomaly determination result is an anomaly determination, the traffic bandwidth allocation coefficient of the corresponding intersection risk node is calculated according to the second-level anomaly coefficient combined with the intersection node risk feature data; Obtain node anomaly data after traffic bandwidth allocation for continuous monitoring and adjustment.

6. A traffic bandwidth intelligent allocation optimization system, characterized in that: The distribution optimization system comprises: The network risk node determination module is used to build an information transmission network, obtain information transmission nodes, and then obtain node information transmission paths, generate path node traffic packets, analyze traffic change data, and obtain path risk nodes; The intersection node determination module is used to obtain the path intersection node information according to the node information transmission path information, generate the intersection risk node, obtain the risk characteristic data, mark the first level risk and the second level risk, and build a multi-level traffic risk network; The multi-layer anomaly analysis module is used to calculate the first-layer anomaly coefficient and the second-layer anomaly coefficient, compare the first-layer anomaly coefficient and the second-layer anomaly coefficient with the first-layer preset threshold and the second-layer preset threshold respectively, and then make a flow anomaly determination to obtain a flow anomaly determination result; The allocation module is used to calculate the flow bandwidth allocation coefficients of the path nodes and the intersection nodes respectively, and then to adjust the flow bandwidth allocation.

7. A traffic bandwidth intelligent allocation optimization system according to claim 6, characterized in that: The network risk node determination module includes: A network construction module, used to obtain network information transmission requirements and construct an information transmission network according to the network information transmission requirements; A path acquisition module is used to acquire information transmission nodes of the information transmission network, and acquire node flow information and node information transmission path of each information transmission node; A flow change comparison module, used to obtain the node flow information on the node information transmission path, and generate a plurality of path node flow packets corresponding to the node information transmission path; Generate a traffic packet group corresponding to the node information transmission path according to the multiple path node traffic packets; Obtaining flow change data of the flow packet group, comparing the flow change data with a preset change threshold, and obtaining a change comparison result; The risk determination module is used to determine abnormal nodes of information transmission nodes according to the change comparison result to obtain path risk nodes.

8. According to claim 6, a traffic bandwidth intelligent allocation optimization system is characterized in that: The intersection node determination module includes: An intersection node generation module is used to obtain multiple node information transmission path information, and obtain path intersection node information according to the node information transmission path information; Obtain path risk nodes of path intersection node information and generate intersection risk nodes; A feature data acquisition module is used to acquire risk feature data of path risk nodes and obtain path node risk feature data; Obtain risk characteristic data of the intersection risk nodes, and obtain risk characteristic data of the intersection nodes; A multi-layer network monitoring module, used to mark the path node risk characteristic data as a first-level risk; Marking the risk characteristic data of the intersection node as a second-level risk; A multi-level traffic risk network is constructed based on the first-level risk information and the second-level risk information.

9. The traffic bandwidth intelligent allocation optimization system according to claim 6 is characterized in that: The network risk node determination module includes: A first calculation and determination module is used to obtain multi-level traffic risk network information and calculate a first-level abnormality coefficient; Compare the first-level abnormality coefficient with the first-level preset threshold to obtain a first-level comparison result; Performing flow anomaly determination on the first-level flow according to the first-level comparison result to obtain a first flow anomaly determination result; A second calculation and determination module, used for calculating a second-level abnormality coefficient according to the first-level flow abnormality determination; Compare the second-level abnormality coefficient with the second-level preset threshold to obtain a second-level comparison result; A flow anomaly determination is performed on the second-level flow according to the second-level comparison result to obtain a second flow anomaly determination result.

10. The traffic bandwidth intelligent allocation optimization system according to claim 6, characterized in that: The allocation module comprises: A first calculation allocation module, configured to calculate a flow bandwidth allocation coefficient of a corresponding path risk node according to the first-level abnormality coefficient combined with path node risk feature data when the first flow abnormality determination result is an abnormal determination result; The second calculation allocation module is used to calculate the traffic bandwidth allocation coefficient of the corresponding intersection risk node according to the second-level abnormality coefficient combined with the risk characteristic data of the intersection node when the second traffic anomaly judgment result is an abnormal judgment; the monitoring module is used to obtain the node abnormality data after the traffic bandwidth is allocated, and perform continuous monitoring and adjustment.

Images