Method and apparatus for predicting destinations in a navigation context based upon observed usage patterns

作者: Christopher Minson , Jack Jia , Robert Bradshaw , Scott Brave

DOI:

关键词:

摘要: The invention comprises a set of complementary techniques that dramatically improve enterprise search and navigation results. core the is an expertise or knowledge index, called UseRank tracks behavior website visitors. expertise-index designed to focus on four key discoveries attributes: Subject Authority, Work Patterns, Content Freshness, Group Know-how. produces useful, timely, cross-application, expertise-based In contrast, traditional Information Retrieval technologies such as inverted NLP, taxonomy tackle same problem with opposite attributes than what needs: Population, Word Existence, Statistical Trends. Overall, emcompasses Baynote Search—a enhancement over existing IR searches, Guide—a community-driven navigations, Insights—aggregated views visitor interests trends content gaps.

参考文章(52)
Philip Shi-lung Yu, Edith H. Stern, David P. Greene, Barry E. Willner, Method and apparatus for facilitating the providing of content ,(2001)
Christopher C Vogt, Garrison W Cottrell, Richard K Belew, Brian T Bartell, None, Using relevance to train a linear mixture of experts text retrieval conference. pp. 503- 515 ,(1996)
Philip K. Chan, Constructing Web User Profiles: A Non-invasive Learning Approach Web Usage Analysis and User Profiling. pp. 39- 55 ,(2000) , 10.1007/3-540-44934-5_3
Ian Ruthven, Incorporating Aspects of Information Use into Relevance Feedback Information Retrieval. ,vol. 2, pp. 83- 88 ,(2000) , 10.1023/A:1009998002873
Mounia Lalmas, P. Vakkari, Ian Ruthven, P. Ingwersen, T. Aparac, T. Saracevic, Selective relevance feedback using term characteristics conceptions of library and information sciences. ,(1999)