The invention relates to the technical field of network self-optimization management, in particular to a high-performance
intelligent management method and
system for
network congestion self-optimization, and the method comprises the steps: obtaining a network
topological graph, recognizing a plurality of key path nodes from the network
topological graph, carrying out the collection module configuration of the key path nodes, obtaining configured nodes, and carrying out the collection module configuration of the configured nodes; obtaining node network parameters and node association influence characteristic values, determining
root cause congestion nodes, recovered nodes or normal nodes, if the type of
root cause congestion equipment is a
core router, taking the
root cause congestion nodes as path optimization nodes, performing routing
path switching optimization operation on the path optimization nodes to obtain optimized nodes, and performing routing
path switching optimization operation on the optimized nodes; and if the type of the root cause congestion equipment is network switching equipment, taking a root cause congestion node as a node to be subjected to load balancing, and performing load balancing optimization operation on the node to be subjected to load balancing to obtain an optimized node. According to the invention, the stability of network operation and the
resource utilization efficiency can be comprehensively improved.