A predictive location model for location-based services

TLDR

Location‑based services rely on users’ current positions, and predicting future locations can extend system resources and improve reliability, but existing models use regular cells that are unsuitable for on‑road services requiring precise road‑level granularity. This work introduces the Predictive Location Model (PLM) to forecast users’ future positions with road‑level precision for LBSs. PLM achieves this by applying geometrical and topological techniques that enable timely, accurate service delivery along specific roads.

Abstract

Location-Based Services (LBSs) utilize information about users' locations through location-aware mobile devices to provide services, such as nearest features of interest, they request. This is a common strategy in LBSs and although it is needed and benefits the users, there are additional benefits when future locations (e.g., locations at later times) are predicted. One major advantage of location prediction is that it provides LBSs with extended resources, mainly time, to improve system reliability which in return increases the users' confidence and the demand for LBSs. However, much of the current location prediction research is focused on generalized location models, where the geographic extent is divided into regular-shape cells. These models are not suitable for certain LBSs whose objective is to compute and present on-road services, because a cell may contain several roads while the computation and delivery of a service may require the exact road on which the user is driving. We propose a new model, called Predictive Location Model (PLM), to predict locations in LBSs with road-level granularities. The premise of PLM is geometrical and topological techniques allowing users to receive timely and desired services.