A dialogue based mobile virtual assistant for tourists: The SpaceBook Project

摘要: Abstract Ubiquitous mobile computing offers innovative approaches in the delivery of information that can facilitate free roaming city, informing and guiding tourist as city unfolds before them. However making frequent visual reference to devices be distracting, user having interact via a small screen thus disrupting explorative experience. This research reports on an EU funded project, SpaceBook, explored utility hands-free, eyes-free virtual tour guide, could answer questions through spoken dialogue interface notify interesting features view while various destinations. Visibility modelling was carried out real-time based LiDAR sourced digital surface model, fused with variety map crowd datasets (e.g. Ordnance Survey, OpenStreetMap, Flickr, Foursquare) establish most landmarks visible from user's location at any given moment. A number variations SpaceBook system were trialled Edinburgh (Scotland). The highlighted pleasure derived this novel form interaction revealed complexity prioritising route guidance instruction alongside identification, description embellishment landmark – there being delicate balance between level ‘pushed’ user, requests for further information. Among challenges, issues regarding fidelity spatial data positioning required pedestrian systems much greater freedom movement than vehicles.