Resumen
The dual-channel graph collaborative filtering recommendation algorithm (DCCF) suppresses the over-smoothing problem and overcomes the problem of expansion in local structures only in graph collaborative filtering. However, DCCF has the following problems: the fixed threshold of transfer probability leads to a decrease in filtering effect of neighborhood information; the K-means clustering algorithm is prone to trapping clustering results into local optima, resulting in incomplete global interaction graphs; and the impact of time factors on the predicted results was not considered. To solve these problems, a dual-channel feature enhanced collaborative filtering recommendation algorithm (DCFECF) is proposed. Firstly, the self-attention mechanism and weighted average method are used to calculate the threshold of neighborhood transition probability for each order in local convolutional channels; secondly, the K-means++ clustering algorithm is used to determine the clustering center in the global convolutional channel, and the fuzzy C-means clustering algorithm is used for clustering to solve the local optimal problem; then, time factor is introduced to further improve predicted results, making them more accurate. Comparative experiments using normalized discounted cumulative gain (NDCG) and recall as evaluation metrics on three publicly available datasets showed that DCFECF improved by up to 2.3% and 4.1% on two metrics compared to DCCF.