The invention provides a community classification method in complex network, a plurality of different nodes having partial influences are taken as the cores, the influences of the nodes are caused to evenly diffuse from the core outwards layer by layer, finally the node having the greatest influence becomes the core, the influences of the nodes in layer-by-layer expansion continuously attenuate, the interconnection of the nodes form a local region which expands until the method stops, the influences of the nodes are slight and can reach the edge of the network of the local region. For a large-scale unordered complex network, the positions of the nodes having different importance degrees can be rapidly located, a great deal of more fine-granularity information is dug out, simultaneously the original structural character of the network is kept unchanged, and the original large-scale complex network is simplified and downsized, so that not only the efficiency of search can be improved, but also the structure of the large-scale network from macroscopic view can be more clearly analyzed.