发明名称 Cross media type recommendations for media items based on identified entities
摘要 Recommendations for a media item associated with a primary entity are based on co-interaction information gathered from other media content items of several different media types that are also associated with the primary entity. Co-interaction information can include, for example, co-click data for websites, co-watch data for videos, or co-purchase data for purchases. The co-interaction data is processed to determine a co-interaction score between primary media items and secondary media items. From the co-interaction scores, secondary entities associated with the secondary media items are determined. A relatedness score is determined for these secondary entities based on the aggregation of the co-interaction scores of the secondary media items they are associated with. The relatedness score indicates a determination of how related one entity is to another. The secondary entities are ranked according to relatedness score in order to determine secondary entities most relevant to the primary entity.
申请公布号 US8856111(B1) 申请公布日期 2014.10.07
申请号 US201313914069 申请日期 2013.06.10
申请人 Google Inc. 发明人 Clancy Daniel J.;Goodrow Cristos J.;He Yu;Zhang Kun
分类号 G06F17/30 主分类号 G06F17/30
代理机构 Fenwick & West LLP 代理人 Fenwick & West LLP
主权项 1. A method comprising: storing a plurality of entities including a primary entity and a plurality of secondary entities, wherein the entities are text descriptors; storing a plurality of videos; storing a plurality of web pages; matching the primary entity to a primary video subset of the stored videos and a primary web page subset of the stored web pages; determining a first set of co-interaction scores between the primary video subset and a secondary video subset of the stored videos; determining a second set of co-interaction scores between the primary web page subset and a secondary web page subset of the stored web pages; matching the secondary video subset and the secondary web page subset to the secondary entities; determining a relatedness score between the primary entity and each of the secondary entities, the relatedness scores based on the first and second sets of co-interaction scores; and ranking the secondary entities according to their respective relatedness scores.
地址 Mountain View CA US