Exploiting user behavior learning for personalized trajectory recommendations

Abstract

With increasing popularity of mobile devices and flourish of social networks, a large number of trajectory data is accumulated. Trajectory data contains a wealth of information, including spatiality, time series, and other external descriptive attributes (i.e., travelling mode, activities, etc.). Trajectory recommendation is especially important to users for finding the routes meeting the user’s travel needs quickly. Most existing trajectory recommendation works return the same route to different users given an origin and a destination. However, the users’ behavior preferences can be learned from users’ historical multi-attributes trajectories. In this paper, we propose two novel personalized trajectory recommendation methods, i.e., user behavior probability learning based on matrix decomposition and user behavior probability learning based on Kernel density estimation. We transform the route recommendation problem to a shortest path problem employing Bayesian probability model. Combining the user input (i.e., an origin and a destination), the trajectory query is performed on a behavior graph based on the learned behavior probability automatically. Finally, a series of experiments on two real datasets validate the effectiveness of our proposed methods.

Graphical abstract

Keywords

trajectory recommendation / big trajectory data / trajectory computing / geo-social networks

References

[1] Hu J, Yang B, Guo C, Jensen C S, Xiong H. Stochastic origin-destination matrix forecasting using dual-stage graph convolutional, recurrent neural networks. In: Proceedings of the 36th international Conference on Data Engineering.2020, 1417−1428

[2] Yang K , Ding X , Zhang Y , Chen L , Gao Y . Distributed similarity queries in metric spaces. Data Science and Engineering, 2019, 4( 2): 93– 108

[3] Zheng B , Su H , Hua W , Zheng K , Zhou X , Li G . Efficient clue-based route search on road networks. IEEE Transactions on Knowledge Data Engineering, 2017, 29( 9): 1846– 1859

[4] Zhao L , Mao J , Pu M , Liu G , Chai H . Automatic calibration of road intersection topology using trajectories, In: Proceedings of the 36th International Conference on Data Engineering. 2020, 1633, 1644

[5] Gionis A, Lappas T, Pelechrinis K, Terzi E. Customized tour recommendations in urban areas. In: Proceedings of the 7th ACM international conference on Web search and data mining. 2014, 313–322

[6] Gao H , Liu H . Data analysis on location based social networks. Computational Social Sciences book series, 2013,

[7] Li G, Sun L, Zhang Z, Ji P, Yu P S. MC2: unsupervised multiple social network alignment. In: Proceedings of the International Conference on Bigdata. 2008, 1151−1156

[8] Delling D, Goldverg A V, Pajor T, Werneck R F. Customizable route planning in road networks. In: Proceedings of the 10th International Symposium on Experimental Algorithms. 2011, 376−387

[9] Dai J , Liu C , Xu J , Ding Z . On personalized and sequenced route planning. Journal of World Wide Web, 2016, 19 : 679– 705

[10] Chen C , Chen X , Wang Z , Wang Y , Zhang D . ScenicPlanner: planning scenic travel routes leveraging heterogeneous user-generated digital footprints. Front of Computer Science, 2017, 11( 1): 61– 74

[11] Xu J , Chen J , Zhou R , Fang J , Liu C . On workflow aware location-based service composition for personal trip planning. Future generation computer systems, 2019, 98 : 274– 285

[12] Zheng K , Zhao Y , Lian D , Zheng B , Zhou X . Reference-based framework for spatio-temporal trajectory compression and query processing. IEEE Transactions on Knowledge Data Engineering, 2020, 32( 11): 2227– 2240

[13] Lim K H, Chan J, Leckie C, Karunasekera S. Personalized tour recommendation based on user interests and points of interest visit durations. In: Proceedings of the 24th International Conference on Artificial Intelligence. 2015, 1778–1784

[14] Wan L, Hong Y, Huang Z, Peng X, Li R. A hybrid ensemble learning method for tourist route recommendations based on geo-tagged social networks. International Journal of Geographical Information Science, 2018: 1−22

[15] Zhu X , Hao R , Chi H , Du X . FineRoute: personalized and time-aware route recommendation based on check-ins. IEEE Transactions on Vehicular Technology, 2017, 66( 11): 10461– 10469

[16] Chen W , Zhao L , Xu J , Liu G , Zheng K , Zhou X . Trip oriented search on activity trajectory. Journal of Computer Science and Technology, 2015, 30( 4): 745– 761

[17] Chen L , Cong G , Jensen C S , Wu D M . Spatial keyword query processing: an experimental evaluation. In: proceedings of the VLDB Endowment, 2013, 6( 3): 217– 228

[18] Cong G, Jensen C S. Querying geo-textual data: spatial keyword queries and beyond. In: proceedings of SIGMOD. 2016: 2207−2212

[19] Pan X , Ang M , Zhang J , Wu L . Approximate similarity measurements on multi-attributes trajectories data. IEEE Access, 2019, ( 7): 10905– 10915

[20] Pan X, Nie S, Hu H, Yu P S, Guo J. Reverse nearest neighbor search in semantic trajectories for Location based Services, IEEE Transactions on Services Computing, 2020,

[21] Liu H, Xu J, Zheng K, Liu C, Xian W. Semantic-aware query processing for activity trajectory. In: Proceedings of the Tenth ACM International Conference on Web Search and Data Mining. 2017, 283–292

[22] Kurashima T, Iwata T, Irie G, Fujimura K. Travel route recommendation using geotags in photo sharing sites. In: Proceedings of the Conference on Information and Knowledge Management. 2010, 579–588

[23] Liu S , Wang S . Trajectory community discovery and recommendation by multi-source diffusion modeling. IEEE Transactions on Knowledge and Data Engineering, 2017, 29( 4): 898– 911

[24] Bao J , Zheng Y , Wilkie D , Mokbel M . Recommendations in location-based social networks: a survey. GeoInformatica, 2015, 19( 3): 525– 565

[25] Lian D, Zhao C, Xie X, Sun G, Chen E, Rui Y. GeoMF: joint geographical modeling and matrix factorization for point-of-interest recommendation. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. 2014, 831–840

[26] Ogundele T J, Chow C Y, Zhang J D. SoCaST: exploiting social, categorical and spatio-temporal preferences for personalized event recommendations. In: Proceedings of 14th International Conference on International Symposium on Pervasive Systems. 2017, 38−45

[27] Yuan Q, Cong G, Sun A. Graph-based point-of-interest recommendation with geographical and temporal influences. In: Proceedings of Conference on Information and Knowledge Management. 2014, 659–668

[28] Zhang J, Chow C Y. GeoSoCa: exploiting geographical, social and categorical correlations for point-of-interest recommendations categories and subject descriptors. In: Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2015, 443–452

[29] Baraglia R, Muntean C I, Nardini F M, Silvestri F. LearNext: learning to predict tourists movements. In: proceedings of Conference on Information and Knowledge Management. 2013, 751–756

[30] Liu Q, Wu S, Wang L, Tan T. Predicting the next location: a recurrent model with spatial and temporal contexts. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence. 2016, 194−200

[31] Qiao S , Shen D , Wang X , Han N , Zhu W . A self-adaptive parameter selection trajectory prediction approach via hidden markov models. IEEE Transactions on Intelligent Transportation Systems, 2015, 16( 1): 284– 296

[32] Zhang W, Wang J. Location and time aware social collaborative retrieval for new successive point-of-interest recommendation. In: Proceedings of Conference on Information and Knowledge Management. 2015, 1221–1230

[33] He J, Qi J, Ramamohanarao K. A joint context-aware embedding for trip recommendations. In: proceedings of IEEE International Conference on Data Engineering. 2019, 292−303

[34] Hu Q , Wang M , Li Q . Urban hot spot and commercial area exploration with check-in data. Acta Geodaetica Et Cartographica Sinica, 2014, 43( 3): 314– 321

[35] Yuan J, Zheng Y, Xie X. Discovering regions of different functions in a city using human mobility and POIs. In: Proceedings of ACM International Conference on Knowledge Discovery and Data Mining. 2012, 186−194

[36] Jing Y , Jiang W , Su G , Zhou Z , Wang Y . A learning automata-based singular value decomposition and its application in recommendation system. In: Proceedings of International Conference on Intelligent Computing, 2014, 26– 32

[37] Cui G , Luo J , Wang X . Personalized travel route recommendation using collaborative filtering based on GPS trajectories. International Journal of Digital Earth, 2017, 1– 24

[38] Huang X , Zhao W , Wang B , Lv H , Yang M . Recommendation system and deep learning. Tsinghua University Press, 2018, 42– 101

[39] Silverman B W . Density estimation for statistics and data analysis. Chapman and Hall, 1986,

[40] Wei L Y, Zheng Y, Peng W C. Constructing popular routes from uncertain trajectories. In: Proceedings of 18th ACM International Conference on Knowledge Discovery and Data Mining. 2012, 195−203

[41] Chen D W, Ong C S, Xie L X. Learning points and routes to recommend trajectories. In: Proceedings of the 25th ACM International on Conference on Information and Knowledge Management. 2016, 2227–2232

[42] Sommer C . Shortest-path queries in static networks. ACM Computing Surveys, 2014, 46( 4): 31–

[43] Vaira G, Kurasova O. Parallel Bidirectional Dijkstra's Shortest Path Algorithm. In: Proceedings of Conference on Databases & Information Systems Vi: Selected Papers from the Ninth International Baltic Conference. 2011, 422–435

RIGHTS & PERMISSIONS

Higher Education Press