Knowledge-Enriched Route Computation

Directions and paths, as commonly provided by navigation systems, are usually derived considering absolute metrics, e.g., finding the shortest or the fastest path within an underlying road network. With the aid of Volunteered Geographic Information (VGI), i.e., geo-spatial information contained in user generated content, we aim at obtaining paths that do not only minimize distance but also lead through more popular areas. Based on the importance of landmarks in Geographic Information Science and in human cognition, we extract a certain kind of VGI, namely spatial relations that define closeness (nearby, next to) between pairs of points of interest (POIs), and quantify them following a probabilistic framework. Subsequently, using Bayesian inference we obtain a crowd-based closeness confidence score between pairs of PoIs. We apply this measure to the corresponding road network based on an altered cost function which does not exclusively rely on distance but also takes crowdsourced geo-spatial information into account. Finally, we propose two routing algorithms on the enriched road network. To evaluate our approach, we use Flickr photo data as a ground truth for popularity. Our experimental results – based on real world datasets – show that the paths computed w.r.t. our alternative cost function yield competitive solutions in terms of path length while also providing more “popular” paths, making routing easier and more informative for the user.