Training, inference and user interface for guiding the caching of media content on local stores

摘要

The present invention is related to caching data by employing probabilistic predictive techniques. The invention has particular application to multimedia systems for providing local storage of a subset of available viewing selections by assigning a value to a selection and retaining selections in the cache depending on the value and size of the selection. The value assigned to an item can represent the time-dependent likelihood that a user will review an item at some time in the future. An initial value of an item can be based on the user's viewing habits, the user's or a group of user's viewing habit over particular time segment. A value assigned to a selection dynamically changes according to a set of cache retention policies. A selection's value may be reduced based upon age, changes on a user's viewing habits, changes in time segments or a user's modification of the cache retention policies.