An Approach for Context-aware Service Discovery and Recommendation<br />service recommendation<br />service discovery<br />
Outline<br />Introduction<br />Our Approach<br />Experiment<br />Conclusion<br />
Outline<br />Introduction<br />Our Approach<br />Experiment<br />Conclusion<br />
Introduction<br />                          Context type  location, time<br />Context<br />                          Conte...
Problems<br />Limited support for dynamic adaption to newly added context types <br />Manually define all the context type...
Outline<br />Introduction<br />Our Approach<br />Experiment<br />Conclusion<br />
Overview of our approach<br />
Overview of our approach<br />
Ontology<br />Class: abstract description of a group of concepts with similar characteristics<br />Individual: instance of...
Steps of find relevant ontologies<br />Search with the  context value<br />YES<br />NO<br />Remove the first adj/adv, then...
Overview of our approach<br />
Identifing context relations<br />Relations between two Context Values<br />Intersection<br />Complement<br />Equivalence<...
Identifing context relations<br />Multiple Context Values: E-R model<br />For each relation of two context values<br />Con...
Steps of building integrated E-R model<br />Filter out independence relations<br />Remove equivalence relations<br />Set t...
Steps of building integrated E-R model<br />Intersect<br />Travel<br />Los<br />Angeles<br />Tourist<br />Attractions<br /...
Steps of building integrated E-R model<br />Intersect<br />Travel<br />Los<br />Angeles<br />Intersect<br />Los Angeles La...
Steps of building integrated E-R model<br />
Overview of our approach<br />
Generating searching criteria<br />Suppose                       are entities in the integrated E-R model. SharedElementsS...
Generating searching criteria<br />Apply the rules on the E-R model<br />Obtain a SharedElementSet<br />Group the entities...
Outline<br />Introduction<br />Our Approach<br />Experiment<br />Conclusion<br />
Experiment	<br />Objective<br />Evaluation of the detected context relations<br />Evaluation of Service Recommendation<br ...
Evaluation of the detected context relations<br />Five context scenarios<br />Manually examine its context and identify th...
Evaluation of Service Recommendation<br />Use the keywords in each group as searching criteria to search for online resour...
Outline<br />Introduction<br />Our Approach<br />Experiment<br />Conclusion<br />
Conclusion<br />Use ontologies to enhance the meaning of a user’s context values<br />The SharedElementSet reflects user’s...
Upcoming SlideShare
Loading in …5
×

An approach for Context-aware Service Discovery and Recommendation

642 views

Published on

An approach for Context-aware Service Discovery and Recommendation

Published in: Technology, Education
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
642
On SlideShare
0
From Embeds
0
Number of Embeds
59
Actions
Shares
0
Downloads
11
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

An approach for Context-aware Service Discovery and Recommendation

  1. 1. An Approach for Context-aware Service Discovery and Recommendation<br />service recommendation<br />service discovery<br />
  2. 2. Outline<br />Introduction<br />Our Approach<br />Experiment<br />Conclusion<br />
  3. 3. Outline<br />Introduction<br />Our Approach<br />Experiment<br />Conclusion<br />
  4. 4. Introduction<br /> Context type location, time<br />Context<br /> Context value New York<br />Context-aware system: react to a user’s context without their intervention<br />
  5. 5. Problems<br />Limited support for dynamic adaption to newly added context types <br />Manually define all the context types<br />Manually establish the relation between the sensed context scenario and the corresponding services in the form of if-then rules<br />
  6. 6. Outline<br />Introduction<br />Our Approach<br />Experiment<br />Conclusion<br />
  7. 7. Overview of our approach<br />
  8. 8. Overview of our approach<br />
  9. 9. Ontology<br />Class: abstract description of a group of concepts with similar characteristics<br />Individual: instance of a class<br />Property: describes an attribute of class or individual<br />Relation: ways classes or individuals associate with each other <br />
  10. 10. Steps of find relevant ontologies<br />Search with the context value<br />YES<br />NO<br />Remove the first adj/adv, then search<br />Annotated the ontology to the context<br />YES<br />NO<br />String is empty<br />Annotated the ontology to the context, convert the remove adj/adv to constraints<br />Use synonyms of the context value<br />
  11. 11. Overview of our approach<br />
  12. 12. Identifing context relations<br />Relations between two Context Values<br />Intersection<br />Complement<br />Equivalence<br />Independence<br />
  13. 13. Identifing context relations<br />Multiple Context Values: E-R model<br />For each relation of two context values<br />Convert the two context values into two entities in E-R model<br />Convert the relation type into a relationship node<br />
  14. 14. Steps of building integrated E-R model<br />Filter out independence relations<br />Remove equivalence relations<br />Set the integrated E-R model as empty<br />For each relation in the remainder relation list<br />Convert the relation into an independent E-R model<br />Add the independent E-R model to the integrated E-R model<br />If exist similarity or equivalence entities, merge them by keeping the one with the richer information<br />If exist subset or complement relations, add a relation ship node in the integrated E-R model <br />If two relationship nodes contain the same relation type and relationship attributes, we merge them into one relationship node<br />
  15. 15. Steps of building integrated E-R model<br />Intersect<br />Travel<br />Los<br />Angeles<br />Tourist<br />Attractions<br />Integrated E-R model<br />
  16. 16. Steps of building integrated E-R model<br />Intersect<br />Travel<br />Los<br />Angeles<br />Intersect<br />Los Angeles Lakers<br />Tourist<br />Attractions<br />NBA<br />Integrated E-R model<br />
  17. 17. Steps of building integrated E-R model<br />
  18. 18. Overview of our approach<br />
  19. 19. Generating searching criteria<br />Suppose are entities in the integrated E-R model. SharedElementsSetrepresents the set of a user’s needs. <br />
  20. 20. Generating searching criteria<br />Apply the rules on the E-R model<br />Obtain a SharedElementSet<br />Group the entities in SharedElementSet<br />Each entity in SharedElementSet is treated as a group<br />If the entities in one group are a subset of the entities in another group, we combine these two groups together.<br />Repeat until no groups can be combined<br />Extract keywords from each group as searching criteria<br />
  21. 21. Outline<br />Introduction<br />Our Approach<br />Experiment<br />Conclusion<br />
  22. 22. Experiment <br />Objective<br />Evaluation of the detected context relations<br />Evaluation of Service Recommendation<br />Precision,Recall<br />
  23. 23. Evaluation of the detected context relations<br />Five context scenarios<br />Manually examine its context and identify the potential needs of the user<br />Use our prototype to automatically find user’s needs<br />
  24. 24. Evaluation of Service Recommendation<br />Use the keywords in each group as searching criteria to search for online resources.<br />Use Google and Seekda as the search engine to search for Web pages and Web services<br />
  25. 25. Outline<br />Introduction<br />Our Approach<br />Experiment<br />Conclusion<br />
  26. 26. Conclusion<br />Use ontologies to enhance the meaning of a user’s context values<br />The SharedElementSet reflects user’s needs<br />Experiment is not clear..<br />

×