TripPlanner: Personalized Trip Planning Leveraging Heterogeneous Crowdsourced Digital Footprints

Abstract

Planning an itinerary before traveling to a city is one of the most important travel preparation activities. In this paper, we propose a novel framework called TRIPPLANNER, leveraging a combination of location-based social network (i.e., LBSN) and taxi GPS digital footprints to achieve personalized, interactive, and traffic-aware trip planning. First, we construct a dynamic point-of-interest network model by extracting relevant information from crowdsourced LBSN and taxi GPS traces. Then, we propose a two-phase approach for personalized trip planning. In the route search phase, TRIPPLANNER works interactively with users to generate candidate routes with specified venues. In the route augmentation phase, TRIPPLANNER applies heuristic algorithms to add user's preferred venues iteratively to the candidate routes, with the objective of maximizing the route score while satisfying both the venue visiting time and total travel time constraints. To validate the efficiency and effectiveness of the proposed approach, extensive empirical studies were performed on two real-world data sets from the city of San Francisco, which contain more than 391 900 passenger delivery trips generated by 536 taxis in a month and 110 214 check-ins left by 15 680 Foursquare users in six months.

Urban Impedance Computing Based on Check-In Records

“…Fu et al [14] predicted the rankings of residential real estate in a city at a future time according to their potential values inferred from a variety of data sources, such as human mobility data and urban geography, currently observed around the real estate. Chen et al [15] leveraged a combination of location-based social networks and taxi GPS digital footprints to achieve personalized, interactive, and traffic-aware trip planning. Yu et al [16] recommended personalized travel package with multiple points of interest based on crowd sourced user footprints.…”

Utility-Aware Social Event-Participant Planning

“…For each u ∈ U , it is associated with a location lu that is the initial and also the final location of the user, and a travel budget bu. We take bu as an input parameter, following the assumptions of other planning problems [6] [24][8] [4]. We denote Su = {v u 1 , v u 2 , ..., v u |Su| } as the schedule of arranged events in increasing time order for user u.…”

“…µ r o (v i,k , u j ) = µ r (v i,k , ur) (j = r) or (j > r and v i,k ∈Ŝu r ) 0 otherwise (6) Consider an arbitrary feasible planning A = ∪j{S u j } w.r.t. µ r o , and we have…”

“…Second, travel cost is the fundamental constraint in a planning problem. [6] indicates that venue constraints (e.g. loca- …”

Learning Points and Routes to Recommend Trajectories

“…The algorithm needs to take into account location desirability (as indicated by node size) and transition compatibility (as indicated by edge width), and compare route hypotheses such as A-D-B-C and A-E-D-C. Existing work in this area either uses heuristic combination of locations and routes [18,14,17], or formulates an optimisation problem that is not informed or evaluated by behaviour history [9,3]. We note, however, that two desired qualities are still missing from the current solutions to trajectory recommendation.…”