Privacy-enhanced Intelligent Automatic Form Filling for Context-aware Services on Mobile Devices

In this paper we describe our approach to intelligent automatic form filling in the context of mobile services based on user data. In a small study we show that manual form filling is slow and perceived a stressful task. And hence it is not surprising that most current mobile services provide primary information, more complex interactions such as ordering a specific product are often very complicate and time consuming tasks or are even not provided. In our approach the individual forms elements are preset based on the content and context of the form, existing rules and the user’s preferences. Our work is grounded in an analysis of requirements. We investigated popular current WAP based mobile services and their characteristics. Through an analysis of conventional HTML based services we concluded which data a user has to type in when filling out a form. Furthermore we analyzed the behavior of people during filling out forms. Based on these observations and additional interviews, we present an overall architecture. A prototype, taking into account these findings is outlined at the end of the paper.