Personalized Shopping Assistance Service at Ubiquitous Shop Space

We have been developing an experimental prototype system - ubiquitous shop space, an application of personal information assistance in a shopping context, (1) to find items of users´ interest and/or preferences through data observed from users´ behaviors in a ubiquitous information environment, (2) to automatically build a user preference model, and (3) to apply the model and provide suitable information service in the real world. In this paper, we study personal behavior from a log file that has been recorded by RFID and camera sensors. Utilizing ubiquitous sensors, we apply three types of observation scopes to model each user´s preference. They are microscopic, mezzoscopic, and macroscopic observation scopes. We have proposed the behavior analysis, algorithms, and combines content-based and collaborative filtering to retrieve information. We provide consumer-friendly services which based on personal behavior log data. Our system can inject suitable and controlled messages to a user to build up his precise preference model without putting any stress on him.