Recommendation method and device based on quaternion graph convolutional neural network

The embodiment of the invention discloses a recommendation method and device based on a quaternion graph convolutional neural network. The method comprises the following steps: acquiring historical interaction data of a plurality of users; according to the historical interaction data of the multiple users, an interaction matrix is constructed, and the interaction matrix is used for representing the interaction relation between the multiple users and the multiple objects; determining an initial quaternion vector representation of each user and each object; inputting the initial quaternion vector representations of the interaction matrix, the plurality of users and the plurality of objects into a graph convolutional neural network for processing in a quaternion space to obtain vector representations of each user and each object; determining the preference degree of each user to each object according to the vector representation of each user and each object; and selecting at least one target object from the plur