Extending media annotations using collective knowledge
AssigneeYahoo! Inc.
InventorsBorkur Sigurbjornsson, Roelof van Zwol
Life of this patent
Estimating the term…
Abstract
The present invention is directed towards systems and methods for extending media annotations using collective knowledge. The method according to one embodiment of the present invention comprises receiving a plurality of content items and associated annotations. The method further normalizes the plurality of associated annotations and calculates pair frequencies for the plurality of associated annotations. The method then retrieves a plurality of alternative annotations and provides the plurality of alternative annotations.
Claims24
A method for extending media annotations using collective knowledge, the method comprising:
- receiving a plurality of content items and associated annotations;
- normalizing the plurality of associated annotations;
- identifying pairs of co-occurring annotations in the plurality of content items;
- calculating a frequency with which each pair of co-occurring annotations occur in the plurality of content items;
- retrieving one or more alternative annotations from the pairs of annotations based on the calculated frequency;
- providing the one or more alternative annotations;
- and
- retrieving one or more additional content items based on the one or more alternative annotations.
A system for extending media annotations using collective knowledge, the system comprising:
- a content server computer coupled over a network to one or more client devices, the content server computer operative to receive a plurality of content items and associated annotations;
- an annotation aggregation component operative to normalize the plurality of associated annotations, identifying pairs of co-occurring annotations in the plurality of content items, and calculate a frequency with which each pair of co-occurring annotations occur in the plurality of content items;
- a co-occurrence database operative to store alternative annotations from the pairs of annotations and frequencies of co-occurring annotation pairs which occur across the plurality of content items;
- and
- an annotation extension component operative to retrieve one or more alternative annotations stored in the co-occurrence database based on the stored frequencies, provide the one or more alternative annotations and retrieve one or more additional content items based on the one or more alternative annotations.
Dependencies are inferred from the claim text.