1 / 8

Personalization

DB. WWW. User Models. Personalization. Traditional System. Personalized System. 3. User/Profile Detection. User Profiling. Content Personalization. Presentation Personalization. ooo. Content. Presentation. ooo. 2. User Profiles. 1. DB. WWW. Context Models.

milek
Télécharger la présentation

Personalization

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. DB WWW User Models Personalization Traditional System Personalized System 3 User/ProfileDetection UserProfiling Content Personalization Presentation Personalization ooo Content Presentation ooo 2 User Profiles 1

  2. DB WWW Context Models Contextualization Traditional System Contextualized System 3 Context/ProfileDetection ContextProfiling Content Contextualization Presentation Contextualization ooo Content Presentation ooo 2 Context Profiles 1

  3. 3 User/ProfileDetection UserProfiling Content Personalization Presentation Personalization ooo Content Presentation ooo 2 User profiles DB WWW Models 1 Models • Characteristics captured in Models are tied to the • features of DMSs being personalized • Query structures • Search patterns • Similarity measures • Optimization dimensions, risk-averseness • The work done in the context of Information • Retrieval Systems or the web not enough

  4. 3 User/ProfileDetection Profiling Content Personalization Presentation Personalization ooo Content Presentation ooo 2 Profiles DB WWW Models 1 Profiling • Specialized data mining • Specific Profiling techniques • particularly suited for populating • User Models for DMSs • Can db usage logs be mined in • the same ways as logs from, • say, web usage?

  5. UserProfiling 2 User profiles DB WWW Models 1 Detection and Use • Particular uses of profiles in • DM envs not found in other • apps • Query opt affected by • profiles: both processes • need reconsideration • Personalized queries • amenable to special • processing • Any particular difficulties • in context detection in DMS? 3 Detection ooo Content ……alization ooo Content Profiles

  6. 3 User/ProfileDetection UserProfiling Content Personalization Presentation Personalization ooo Content Presentation ooo 2 User profiles DB WWW Models 1 DM Technology Contributions • Traditional data management technologies has much • to offer that might be useful for general issues of • personalization/contextualization • Specialized indexing or stream mgmt for massive web-based recommendations • Heterogeneous profile integration • Several things are not in the hands • of AI, the semantic web, etc.

  7. 3 User/ProfileDetection UserProfiling Content Personalization Presentation Personalization ooo Content Presentation ooo 2 User profiles DB WWW Models 1 Personalization/Contextualizationin New DM Environments • Exciting times and research opportunities for DM • Major changes in computing environments • Huge amounts and great diversity of data • Innovative applications • Important role of personalization/contextualization

More Related