Query Processing For Large-scale Semantic Trajectories

In recent years,with the widespread use of smart phones,users from social networks like Tweets,Flickr and Weibo have generated massive geo-tagged records,which reveal not only spatio-temporal dynamics of users,but also their activities in the physical world at specific time and location,and these informative records form large amounts of trajectories associated with activity information,called semantic trajectory.Existing trajectory data management studies mainly focus on analyzing the spatio-temporal properties of the trajectories,while leaving the understanding of their activities largely untouched.In this paper,we study the problem of efficient similarity search on large-scale semantic trajectory database,which incorporates the semantic analysis of the activity information embedded in trajectories into query modelling and processing,with the aim of providing end users more accurate and meaningful trip recommendations.To this end,we propose a novel User-oriented Trajectory Similarity Query(UTSQ)which not only considers the location proximity but also,more importantly,leverages probabilistic topic modelling to capture the semantic relevance of the activity information between trajectory data and query.To support efficient query processing,we design a novel locality sensitive hashing(LSH)based “spatial-topic”synergic index structure,namely ST-tree,to organize the trajectory points hierarchically,which enables us to prune the search space by spatial closeness and semantic relevance simultaneously.The results of our extensive experiments on real datasets demonstrate the efficiency and scalability of the proposed index structure and search algorithms.