Product Image Recommendation with Transformer Model Using Deep Reinforcement Learning

Abstract

A product image recommendation algorithm with transformer model using deep reinforcement learning is proposed. First, the product image recommendation architecture is designed to collect users’ historical product image clicking behaviors through the log information layer. The recommendation strategy layer uses collaborative filtering algorithm to calculate users’ long-term shopping interest and gated recurrent unit to calculate users’ short-term shopping interest, and predicts users’ long-term and short-term interest output based on users’ positive and negative feedback sequences. Second, the prediction results are fed into the transformer model for content planning to make the data format more suitable for subsequent content recommendation. Finally, the planning results of the transformer model are input to Deep Q-Leaning Network to obtain product image recommendation sequences under the learning of this network, and the results are transmitted to the data result layer, and finally presented to users through the presentation layer. The results show that the recommendation results of the proposed algorithm are consistent with the user’s browsing records. The average accuracy of product image recommendation is 97.1%, the maximum recommended time is 1.0[Formula: see text]s, the coverage and satisfaction are high, and the practical application effect is good. It can recommend more suitable products for users and promote the further development of e-commerce.