Searching activity trajectory with keywords

Driven by the advances in location positioning techniques and the popularity of location sharing services, semantic enriched trajectory data has become unprecedentedly available. While finding relevant Point-of-Interests (PoIs) based on users’ locations and query keywords has been extensively studied in the past years, it is, however, largely untouched to explore the keyword queries in the context of activity trajectory database. In this paper, we study the problem of searching activity trajectories by keywords. Given a set of query keywords, a keyword-oriented query for activity trajectory (KOAT) returns k trajectories that contain the most relevant keywords to the query and yield the least travel effort in the meantime. The main difference between KOAT and conventional spatial keyword queries is that there is no query location in KOAT, which means the search area cannot be localized. To capture the travel effort in the context of query keywords, a novel score function, called spatio-textual ranking function, is first defined. Then we develop a hybrid index structure called GiKi to organize the trajectories hierarchically, which enables pruning the search space by spatial and textual similarity simultaneously. Finally an efficient search algorithm and fast evaluation of the value of spatio-textual ranking function are proposed. In addition, we extend the proposed techniques of KOAT to support range-based query and order sensitive query, which can be applied for more practical applications. The results of our empirical studies based on real check-in datasets demonstrate that our proposed index and algorithms can achieve good scalability.