A proposal on automatic adaptive metadata for personalized audio-visual contents

At the present, audio-visual searching technology is only to filter information from almost infinite amount of contents according to the static user preferences. However, the user preferences are dynamically changed, and it is not convenient to input such varied preferences information every time when the user preferences changed. In this paper, we propose a method to make the preference information be updated and generated automatically in the terminal side, using user's viewing history as feed-back metadata, and implement the system with optimized parameters. In our implementation, TV-Anytime forum's metadata and MPEG-7 user preferences description are utilized for the proposed system on audio-visual contents searching and filtering. For renewal user preferences information, a basic user preference tool ("preferenceValueType") of MPEG-7 User preferences description is adopted to adapt user aspects. In addition the requirements are summarized, and necessary functional components for implementing the proposed system are designed as well as data generation process to use for experiment. The components are audio-visual contents metadata filtering, data structure transformation, and preferences value weighting system. Finally, parameters that are defined in the paper are optimized according to experimental results. It is shown that the optimized value makes the proposed system more effective.