A Contextual Computing approach towards Personalized Search Jim
- Slides: 7
A Contextual Computing approach towards Personalized Search Jim Pitkow August 2002 Confidential Information © 2002 Outride Inc.
Contextual Computing The enhancement of a user’s interactions by understanding: • the user, • their context, • and the applications/information being used, • across a wide set of user goals. Actively adapting the computational environment, for each and every user, at each point of computation • Not just about modeling the user’s preferences and behavior or embedding computation everywhere Confidential Information © 2000 Outride Inc. CONFIDENTIAL INFORMATION © 1999 -2000 GROUPFIRE INC.
Evolution: Information Retrieval Methods of Applying Relevance Multidimensional Inferencing User Model Based + Popularity (Direct. Hit, most search engines after 1999/2000) Popularity Based Link Analysis (Google, search engines after 1999/2000) + Content Based Vector Space (Verity, search engine companies till 98) Boolean (Library and legal systems, Lexis-Nexis, West Law) Accessibility of Information/Volume Confidential Information © 2000 Outride Inc. CONFIDENTIAL INFORMATION © 1999 -2000 GROUPFIRE INC.
Personal Search Architecture User Query Outride Personalized Search System Query Augmentation Search Enterprise Search: Web Demographics Click Stream Result Processing Contextualized Client Interface Result Search History Commerce: Retail Application Usage Commerce: B 2 B Outride Schema User x Content x History x Demographics Search Engine Schema Keyword by Doc IDs by Link Rank Confidential Information © 2000 Outride Inc. CONFIDENTIAL INFORMATION © 1999 -2000 GROUPFIRE INC.
Confidential Information © 2000 Outride Inc. CONFIDENTIAL INFORMATION © 1999 -2000 GROUPFIRE INC.
End-User Benefits: Be More Productive SOURCE: ZDLabs/e. Testing, Inc. October 2000 % Increase from Outride Enabled Search Engine 93. 7% more time 107. 9% more time 114. 5% more time 130. 2% more time Time in Seconds Confidential Information © 2000 Outride Inc. CONFIDENTIAL INFORMATION © 1999 -2000 GROUPFIRE INC.
Average Time to Complete Task Novice versus Expert Gains User Skill Level Confidential Information © 2000 Outride Inc. CONFIDENTIAL INFORMATION © 1999 -2000 GROUPFIRE INC.