Social network abnormal user detection method and device based on heterogeneous graph neural network

The invention discloses a social network abnormal user detection method and device based on a heterogeneous graph neural network, and the social network abnormal user detection method based on the heterogeneous graph neural network comprises: collecting user information for a social network, and carrying out the feature extraction of the collected user information; on the basis of the extracted features, constructing a heterogeneous information network based on the social network, and designing corresponding meta-paths and meta-graphs by utilizing relation attributes of the social network; on the basis of the heterogeneous information network, the meta-path and the meta-graph, according to the intimacy and the similarity between the users, determining the representation of the users in the social network; and based on the representation of the user in the social network, detecting a user type to determine an anomalous user. Rich user features are integrated, user information is summarized based on a real soci