Implicit rating of retrieved information in an information search system

作者: Douglas K. Warner , Michael A. Myer

DOI:

关键词:

摘要: An information retrieval system allows a user to search database of informational items for desired item, and presents the result in form matching index entries order relevance. The accordance with principles present invention assigns relevance rating each without requiring an explicit input from respect usefulness or retrieved corresponding respective entries. When selects retrieves item through list presented by system, as search, selected is increased predetermined amount. further adjusted based on any actions takes subsequent initial selection if act indicates that may be less than what reflected increase Ratings are determined implicit suggestions usage rather input. In another aspect invention, ratings allowed decay over time minimize tendencies historical biased rating, provide more temporally accurate ratings. most recently accessed compared stale access threshold, older decreased reflect dated nature contained within item.

参考文章(16)
Kevin Tiene, Jeremy J. Bornstein, Daniel E. Rose, Dulce B. Ponceleon, System for directing relevance-ranked data objects to computer users ,(1994)
Michael J. Schiegg, Gray Watson, David L. Andre, Richard M. Green, Sangam Pant, Computer system with user-controlled relevance ranking of search results ,(1997)
Rajeev Motwani, Terry Winograd, Lawrence Page, Sergey Brin, The PageRank Citation Ranking : Bringing Order to the Web the web conference. ,vol. 98, pp. 161- 172 ,(1999)
Alan J. Wecker, Hypertext display system ,(1993)
Stephen Gray Stair, Ricky Lee Poston, Christopher Robbins Nielsen, I-Hsing Tsao, System and method for displaying the contents of a web page based on a user's interests ,(1997)