Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

PMSE:Personalized Mobile Search Engine


Published on

Published in: Engineering
  • Be the first to comment

PMSE:Personalized Mobile Search Engine

  1. 1. Project Guide:- Miss. Jayashree Patade Head Of Department:- Mrs. Geeta Atkar Prepared By:- Mr. Dawange Santosh Kailas.(46) Mr. Ghadge Akshay Sanjay.(47) Mr. Gire Sanket Ramesh.(48) Mr. Talekar Vikas Dilip.(49)
  2. 2.  Introduction  Proposed System  Existing System  Modules  Mobile Client  PMSE Server  Re-Rank Search Results  Ontology update and Click-through collection  Conclusion
  3. 3.  We propose a personalized mobile search engine (PMSE) that captures the users’ preferences in the form of concepts by mining their click through data.  Due to the importance of location information in mobile search, PMSE classifies these concepts into content concepts and location concepts.  In addition, users’ locations (positioned by GPS) are used to supplement the location concepts in PMSE.
  4. 4.  The user preferences are organized in an ontology-based, multifaceted user profile, which are used to adapt a personalized ranking function for rank adaptation of future search results.  We prototype PMSE on the Google Android platform. Experimental results show that PMSE significantly improves the precision comparing to the baseline.
  5. 5.  Most of the previous work assumed that all concepts are of the same type.
  6. 6.  Observing the need for different types of concepts, In particular, recognizing the importance of location information in mobile search, we separate concepts into location concepts and content concepts.
  7. 7.  Mobile Client  PMSE Server  Re-Rank Search Results  Ontology update and Click-through collection
  8. 8.  In the PMSE’s client-server architecture, PMSE clients are responsible for the user click-through and the ontologies derived from the PMSE server.  The PMSE client would only need to submit a query together with the feature vectors to the PMSE server, and the server would automatically return a set of re-ranked search results according to the preferences stated in the feature vectors.
  9. 9.  Heavy tasks, such as RSVM training and re-ranking of search results, are handled by the PMSE server.
  10. 10.  The search results are then re-ranked according to the weight vectors obtained from the RSVM training.
  11. 11.  When the user clicks on a search result, the click-through data together with the associated content and location concepts are stored in the click-through database on the client.  The click-through are stored on the PMSE clients, so the PMSE server does not know the exact set of documents that the user has clicked on. This design allows user privacy to be preserved in certain degree.
  12. 12.  The average time taken to fetch standard search results, re-rank & display them is less than 2 seconds, which is acceptable & almost real-time on a mobile device.  We also proposed two privacy parameters, min-Distance and exp-Ratio, to address privacy issues in PMSE by allowing users to control the amount of personal information exposed to the PMSE server.
  13. 13. THANK YOU!!!