Modeling Long- and Short-Term Service Recommendations with a Deep Multi-Interest Network for Edge Computing

Edge computing platforms enable application developers and content providers to provide context-aware services(such as service recommendations)using real-time wireless access network information.How to recommend the most suitable candidate from these numerous available services is an urgent task.Click-through rate(CTR)prediction is a core task of traditional service recommendation.However,many existing service recommender systems do not exploit user mobility for prediction,particularly in an edge computing environment.In this paper,we propose a model named long and short-term user preferences modeling with a multi-interest network based on user behavior.It uses a logarithmic network to capture multiple interests in different fields,enriching the representations of user short-term preferences.In terms of long-term preferences,users'comprehensive preferences are extracted in different periods and are fused using a nonlocal network.Extensive experiments on three datasets demonstrate that our model relying on user mobility can substantially improve the accuracy of service recommendation in edge computing compared with the state-of-the-art models.