Personalized commodity recommendation method and system based on multilayer heterogeneous graph convolution model

The invention discloses a personalized commodity recommendation method and system based on a multilayer heterogeneous graph convolution model, and belongs to the technical field of artificial intelligence. The method comprises the following steps: firstly, constructing an e-commerce network into a multi-layer heterogeneous attribute network, and modeling a plurality of interactive behaviors between a user and a commodity; secondly, in consideration of different influences of different types of interaction between the user and the commodity, self-adaptive adjustment parameters are set to capture the size of the influences; then, a multilayer graph convolution module is designed, and meta-path information of different lengths crossing multiple relations in the multilayer heterogeneous attribute network can be automatically captured to obtain representation of nodes; and finally, personalized commodity recommendation is carried out on the user by utilizing cosine similarity. According to the method, various inte