On route planning by inferring visiting time, modeling user preferences, and mining representative trip patterns

Cheng Te Li, Hsin Yu Chen, Ren Hao Chen, Hsun Ping Hsieh

研究成果: Article同行評審

3 引文 斯高帕斯(Scopus)


Location-based services allow users to perform check-in actions, which record the geo-spatial activities and provide a plentiful source to do more accurate and useful geographical recommendation. In this paper, we present a novel PreferredTime-aware Route Planning (PTRP) problem, which aims to recommend routes whose locations are not only representative but also need to satisfy users’ preference. The central idea is that the goodness of visiting locations along a route is significantly affected by the visiting time and user preference, and each location has its own proper visiting time due to its category and population. We develop a four-stage preference-based time-aware route planning framework. First, since there is usually either noise time on existing locations or no visiting information on new locations, we devise an inference method, LocTimeInf, to predict the location visiting time on routes. Second, considering the geographical, social, and temporal information of users, we propose the GST-Clus method to group users with similar location visiting preferences. Third, we find the representative and popular time-aware location-transition behaviors by proposing Time-aware Transit Pattern Mining (TTPM) algorithm. Finally, based on the mined time-aware transit patterns, we develop a Preferred Route Search (PR-Search) algorithm to construct the final time-aware routes. Experiments on Gowalla and Foursquare check-in data exhibit the promising effectiveness and efficiency of the proposed methods, comparing to a series of competitors.

頁(從 - 到)581-611
期刊Knowledge and Information Systems
出版狀態Published - 2018 九月 1

All Science Journal Classification (ASJC) codes

  • Software
  • Information Systems
  • Human-Computer Interaction
  • Hardware and Architecture
  • Artificial Intelligence

指紋 深入研究「On route planning by inferring visiting time, modeling user preferences, and mining representative trip patterns」主題。共同形成了獨特的指紋。