Towards Efficient Selection of Activity Trajectories based on Diversity and Coverage

With the prevalence of location based services, activity trajectories are being generated at a rapid pace. The activity trajectory data enriches traditional trajectory data with semantic activities of users, which not only shows where the users have been, but also the preference of users. However, the large volume of data is expensive for people to explore. To address this issue, we study the problem of Diversity-aware Activity Trajectory Selection (DaATS). Given a region of interest for a user, it finds a small number of representative activity trajectories that can provide the user with a broad coverage of different aspects of the region. The problem is challenging in both the efficiency of trajectory similarity computation and subset selection. To tackle the two challenges, we propose a novel solution by: (1) exploiting a deep metric learning method to speedup the similarity computation; and (2) proving that DaATS is an NP-hard problem, and developing an efficient approximation algorithm with performance guarantees. Experiments on two real-world datasets show that our proposal significantly outperforms state-of-the-art baselines. 2019; Chen et al. 2020], which augments traditional trajectory data with "activity" features. In this kind of data, each location point is associated with a keyword that semantically describes the venue of a performed activity, e.g., shop, restaurant, bank. From activity trajectory data, we can know not only where users have been, but also the main preferences of users by looking over the semantic descriptions. However, the availability of such large scale data makes the information prohibitively expensive to explore. In many real-world applications, it is of great significance to provide support for users to perform data exploration on their interested regions. For instance, users would like to browse a small number of representative tourist routes when planning trips to some tourism attractions. Another example is the online map system [Ward, Grinstein, and Keim 2010] . For specified geographical area, users want to get intuitive information on various type of