A spatial–temporal hypergraph based method for service recommendation in the Mobile Internet of Things-enabled service platform

Abstract

With the rapid progress of Mobile Internet of Things (MIoT), Location-Based Services (LBSs) have become widely popular due to the deployment of diverse devices and facilities. The utilization of spatial–temporal information has led to a considerable improvement in service recommendation in the MIoT-enabled service platform. In practical scenarios, the interaction between the user and the service is often initiated by the joint effect of previous service invocations. Many-to-many and high-order spatial–temporal relations exist among services, which are inadequately reflected by prevailing methods that rely on ordinary graphs and consider spatial–temporal relations among services as pairwise connections. Additionally, most methods indiscriminately conflate the separate influences of spatial and temporal information on user preferences, which can lead to suboptimal service recommendation performance. To this end, we propose an approach powered by spatial–temporal hypergraphs (STH) for personalized service recommendation in the MIoT-enabled service platform, which is inspired by the deep learning paradigm. Specifically, we first construct spatial and temporal hypergraphs based on spatial–temporal information. Then, we develop the spatial–temporal hypergraph neural network-based encoders to learn spatial and temporal representations of services. Finally, we introduce an auxiliary task to differentiate between distinct spatial–temporal effects for improved service recommendations. We conduct extensive experiments on four real-world datasets, and the results demonstrate the effectiveness of STH. Thus, STH not only enhances the user experience but also improves service management in the MIoT-enabled service platform.