Page - 180 - in Intelligent Environments 2019 - Workshop Proceedings of the 15th International Conference on Intelligent Environments

AMethod forGeneratingMultipleTour RoutesBalancingUserSatisfactionand ResourceConsumption YODAIHIRANOa,b, HIROHIKOSUWAa,b and KEIICHIYASUMOTOa,b aNara InstituteScienceandTechnology,Nara630-0192, Japan bRIKEN,Center forAdvanced IntelligenceProject,Tokyo103-0027, Japan Abstract. In general, it is a complicated and time-consuming task for a tourist to plan a satisfactory sightseeing tour, because he/shemust take into account var- ious factors and constraints (e.g., budget, available time, etc) at the same time. This difficulty comes from the fact that there is a trade-off between the satisfac- tion/experienceobtainedby thesightseeing tourand the resourceconsumedfor the tour, hence theoptimal solution isnotunique.Tohelpdecisionmaking, it is desir- able to show the tourist a varietyof solutions (i.e., tours) considering the trade-off in various ways, but to the best of our knowledge, no existingmethods/systems providesuchawidevarietyofsolutions. In thispaper,weformulate thesightseeing tour recommendation as amulti-objectiveoptimizationproblemwithmoney, time andstaminaconsumptionofa touristandsatisfactiondegreeobtainedbythetourist as independentvariables.Since thisproblem isNP-hard,weproposeaheuristical- gorithm toquicklyobtainsemi-paretooptimalsolutionsbasedongeneticalgorithm NSGA-II.We applied the proposedmethod to planning tours targeting 30 tourist spots inHigashiyama-areaofKyoto, Japan.Asaresult,ouralgorithmcouldoutput semi-paretooptimal solutions in reasonable time. Keywords. tourplanner,multi-objectiveGA, route search,decisionmaking 1. Introduction Thanksto thewide-spreadofsmartdeviceswithGPS,navigationsystems thatnavigatea user from thecurrent location to thedestination locationarenowwidelyavailable.Such a navigation system likeGoogleMaps has a route planning function that helps a user decide his/her satisfactory route in terms ofmonetary and/or temporal constraints, by showingmultiple routeswith (possibly combination of)multiple transportationmeans (trains, buses, taxis, etc). Most of the existing route planning functions/systems, however, are suffering from its usability that a user needs to specify detailed conditions to get his/her satisfactory route.Amoreeasy-to-use routeplanningsystemwhich takes intoaccountuser’scontext andpreference isdesired. In the domain of tourism, there is a route planning system called the tour planner suchasNAVITIMETRAVEL1.The tourplanner suggestsausera tourplanconsidering 1https://travel.navitime.com/ja/ Intelligent Environments 2019 A. Muñoz et al. (Eds.) © 2019 The authors and IOS Press. This article is published online with Open Access by IOS Press and distributed under the terms of the Creative Commons Attribution Non-Commercial License 4.0 (CC BY-NC 4.0). doi:10.3233/AISE190040 180