1 / 25

Ontology Aware Software Service Agents: Meeting Ordinary User Needs on the Semantic Web

Ontology Aware Software Service Agents: Meeting Ordinary User Needs on the Semantic Web. Muhammed Al-Muhammed. Supported in part by NSF. The Challenge. Reduce information overload Find and use services.

kenton
Download Presentation

Ontology Aware Software Service Agents: Meeting Ordinary User Needs on the Semantic Web

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. Ontology Aware Software Service Agents: Meeting Ordinary User Needs on the Semantic Web Muhammed Al-Muhammed Supported in part by NSF

  2. The Challenge • Reduce information overload • Find and use services I want to see a dermatologist next week; any day would be ok for me, at 4:00 p.m. The dermatologist must be within 20 miles from my home and must accept my insurance.

  3. Approach • Task ontology • Domain ontology • Process ontology • Characteristics • Task specification: Free-form text • Request recognition: find best task ontology • Task execution • Specialize task ontology processes • Execute generated code

  4. Domain Ontology Time Textual representation: “[d][d]?\s*([:]\s* [d][d]?)?\s* ([A|a|P|p]\s* [.]?\s* [M|m]\s* [.]?)” … end;

  5. Task Recognition

  6. Appointment … context keywords/phrase: “appointment |want to see a |…” Dermatologist … context keywords/phrases: “([D|d]ermatologist) | …” I want to see a dermatologist next week; any day would be ok for me, at 4:00 p.m. The dermatologist must be within 20 miles from my home and must accept my insurance.

  7. Appointment … context keywords/phrase: “appointment |want to see a |…” Dermatologist … context keywords/phrases: “([D|d]ermatologist) | …”  I want to see a dermatologist next week; any day would be ok for me, at 4:00 p.m. The dermatologist must be within 20 miles from my home and must accept my insurance.

  8. Appointment … context keywords/phrase: “appointment |want to see a |…” Dermatologist … context keywords/phrases: “([D|d]ermatologist) | …”   I want to see adermatologist next week; any day would be ok for me, at 4:00 p.m. The dermatologist must be within 20 miles from my home and must accept my insurance.

  9. Appointment … context keywords/phrase: “appointment |want to see a |…” Dermatologist … context keywords/phrases: “([D|d]ermatologist) | …”       I want to see adermatologist next week; any day would be ok for me, at 4:00 p.m. The dermatologist must be within 20 miles from my home and must accept my insurance.

  10. Process Ontology

  11. Task Execution • Domainindependent subprocesses • Coded once • Specialized for a domain • A domaindependent subprocess • Domain execution • Automatically generated

  12. Domainindependent subprocesses Task View Creation      

  13. Domainindependent subprocesses Task View Creation

  14. Domainindependent subprocesses Task Constraints Creation Date … NextWeek(d1: Date, d2: Date) returns (Boolean{T,F}) context keywords/phrases: next week | week from now | … Distance internal representation : real; input (s: String) context keywords/phrases: miles | mile | mi | kilometers | kilometer | meters | meter | centimeter | … Within(d1: Distance, “20”) returns (Boolean {T or F}) context keywords/phrases: within | not more than |  | … return (d1d2) … end;

  15. Domainindependent subprocesses Task Constraints Creation Taskimposed constraints: NextWeek(d1: Date, d2: Date) Person(x) is at Address(a1) and Dermatologist(y) is at Address(a2) and Within(DistanceBetween(a1, a2), “20”)  i2 (Dermatologist(y) accepts Insurance(i2 ) and Equal(“IHC”, i2))

  16. Domainindependent subprocesses Obtaining Information from the System

  17. Domainindependent subprocesses Obtaining Information from the System

  18. Domainindependent subprocesses Obtaining Information from a User

  19. Domainindependent subprocesses Obtaining Information from a User

  20. Domainindependent subprocesses Constraint Satisfaction

  21. Domainindependent subprocesses Constraint Satisfaction

  22. Domainindependent subprocesses Constraint Satisfaction

  23. Domainindependent subprocesses Negotiation

  24. DomainDependent Subprocess Date(“28 Dec 04”) and NextWeek(“28 Dec 04”, “5 Jan 05”) Person(Person100) is at Address(“Provo 300 State St.”) and Dermatologist(Dermatologist0) is at Address(“Orem 600 State St.”) and Within(DistanceBetween(“Provo 300 State St.”, “Orem 600 State St.”), “22”)  i2 (Dermatologist(Dermatologist0) accepts Insurance(i2) andEqual(“IHC”, i2))

  25. Contributions • Simplification of everyday task execution • Domainindependent subprocesses • Task ontology based system extension

More Related