Manufacturing cloud service recommendation model based on deep feature learning and user preference perception

Abstract

ABSTRACT The manufacturing cloud service recommendation model is a key technology for users to quickly discover and obtain the personalized services they need from the increasingly expanding manufacturing cloud; however, the manufacturing cloud service recommendation model faces problems, such as difficulty in representing deep features of services and too sparse user preference models. To address the above problems, this paper proposes a manufacturing cloud service recommendation model framework based on deep feature learning and user preference perception and investigates the key technologies involved. On the one hand, a Convolutional Neural Network (CNN)-based deep feature extraction method for manufacturing cloud services is proposed by combining the Latent Dirichlet Allocation (LDA) topic model and word2vec. On the other hand, the concept of a category is introduced through the method of label clustering to perceive user behavior, efficiently build user preference models, and solve the sparse problem of the user-service matrix. Based on this, the execution process of the recommendation model for manufacturing cloud services is analyzed by fusing the deep features of services and user preference models. The experimental results on the actual dataset prove that the method greatly improves the recommendation effect.