Location-Aware POI Recommendation for Indoor Space by Exploiting WiFi Logs

Abstract

Indoor shopping trajectories provide us with a new approach to understanding user's behaviour pattern in urban shopping mall, which can be derived from user-generated WiFi logs using indoor localization technology. In this paper, we propose a locationaware Point-of-Interest (POI) recommendation service in urban shopping mall that offers a user a set of indoor POIs by considering both personal interest and location preference. The POI recommendation service cannot only improve user's shopping experience but also help the store owner better understand user's shopping preference and intent. Specifically, the proposed method consists of two phases: offline modelling and online recommendation. The offline modelling phase is designed to learn user preference by mining his/her historical shopping trajectories. The online recommendation phase automatically produces top-recommended POIs based on the learnt preference. To demonstrate the utility of our proposed approach, we have performed a comprehensive experiment evaluation on a real-world dataset collected by 468 users over 33 days. The experimental results show that the proposed recommendation service achieves much better recommendation performance than several existing benchmark methods.

Developing a Data Model of Indoor Points of Interest to Support Location-Based Services

“…Spatial relationships between the Indoor POI and the indoor spaces abstracted with topological data provided by IndoorGML are defined to provide an indoor patrol service. Also, in an indoor setting, [25] proposed a location-aware POI recommender system based on user preferences mined from social networking data. Indoor POIs have also been used to build an indoor facility information and visualization system [26], annotators to denote user visits in urban areas [27], generating large scale maps [28] and in labeling objects and spaces in AR platforms [29] and navigation systems [30][31][32].…”

“…In both outdoors [1] and indoors, POI data is essential for ontologybased recommender systems in different applications. Studies have used Indoor POIs in recommender systems utilizing shopping trajectories to model user behavior and preferences [25,27]. Literature also cites that having an alias database management system would increase the efficiency of POI data, that is, obtaining the same level of richness of information even with a significantly smaller size of dataset [55].…”

How Computer Vision Provides Physical Retail with a Better View on Customers

“…Based on the visited stores, an accompanying mobile app provides contextual information and recommendations like products from specific categories or of particular brands to customers. Similar approaches are taken in [16] and [17], performing case studies in one and two shopping centers, respectively. While Chen et al [17] also pursue the recommendation of stores, Zheng et al [16] extend the set of possible applications by recommending indoor points of interest considering a user's preferences.…”

Developing a Data Fusion Strategy Between Omnidirectional Image and Indoorgml Data

“…Nowadays, spatial applications move towards the indoors and as these spaces continue to be more complex the interest in applications (Giudice et al, 2010). Together with the pervasiveness of mobile technology and social media (Zheng et al, 2017), more efficient and effective representations are warranted to ensure timely, accurate, and relevant information is delivered to users.…”