Collaborative filtering recommendation method and device based on graph convolutional network

• Main Authors: DU CHENHAO, LIU YE, SU BINGBING, LIU HUI, TIAN YUANRONG, SHEN DIE, REN HUILING, YANG XIN
• Format: Patent
• Language: Chinese; English
• Published: 14.06.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a collaborative filtering recommendation method, and particularly relates to a collaborative filtering recommendation method and device based on a graph convolutional network. The method comprises the following steps: coding users and items in a data set to obtain a first coding matrix and a second coding matrix, and constructing a first adjacency matrix of a weighted user-item graph and a second adjacency matrix of the weighted user-user graph based on the data set; embedding the user and the project to obtain a user embedding matrix and a project embedding matrix; performing message transmission based on the user embedding matrix, the first adjacent matrix, the second adjacent matrix and the project embedding matrix to obtain a final representation of the user and a final representation of the project; calculating a positive and negative sample prediction score pair based on the final representation of the user and the final representation of the item, the positive and negative sampl