The invention discloses an intelligent efficient
virtual network mapping algorithm based on an attention mechanism, and relates to the technical field of
network virtualization, and the
algorithm comprises the following steps: extracting feature vectors of physical nodes by using a GCN model, and enhancing node feature representation by aggregating neighbor node features; a Transfomer architecture is adopted to form an
encoder system, a GRU model forms a decoder
system, and an
encoder model comprises an embedded layer, a multi-head attention layer, a connection layer, a feedforward
network layer, a connection layer and a linear transformation layer; according to the method, a Transfomer model is used for forming an
encoder, more comprehensive feature vectors are generated for all physical nodes through multiple composition structures in the Transfomer model, in the GRU decoding process, in combination with the attention mechanism thought, attention weight is calculated, node mapping is selected, in the link mapping stage, link
pruning is adopted firstly, links which do not meet the requirement are removed, and then a GRU decoding process is carried out. And then link mapping is carried out, so that the success rate of link mapping is improved.