1 / 27

Service agents

Service agents. Publish “white page” services description content and register the services at a “yellow page” site Understand ontology and answer queries Link with the semantic web server and push information to other agents. Features.

tyanne
Télécharger la présentation

Service agents

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. Service agents • Publish “white page” services description content and register the services at a “yellow page” site • Understand ontology and answer queries • Link with the semantic web server and push information to other agents

  2. Features • Distributed: no centralized agent who has to search all web pages and understand every ontology • The best agent to ask questions can be easily located: a good amendment to the web services discovery and the agent services searching • The non-semantic web site joins the semantic world by linking to a service agent • The non-agent program can be wrapped with a service agent shell • Trustworthy: Owned by the semantic web site

  3. Function Level • Provide the requested semantic web page • Answers simple questions about the semantic web pages: The inference in this level is based on local rules, limited semantic pages and local ontologies • Answer complicated questions about the semantic web pages: The inference in this level involves multiple ontologies, multiple semantic web sites and multiple agents • Validates trust and delegation

  4. OWL as a Semantic Language • Well-defined model-theoretic semantics • Unambiguously computer-interpretable • Facilitates a higher-level of interoperability between the agents By agreeing on how meaning is conveyed, applications can share meaningful content easily and naturally

  5. OWL as ACL Content Language • OWL’s expressive power is adequate for many needs of current agent based systems • OWL offers better support for using terms drawn from multiple namespaces and multiple ontologies than existing ACL content languages • OWL provides improved support in modeling, maintaining and sharing ontologies • OWL is designed to fit into and integrate with web-based information and web services • OWL has the potential to be a widely accepted and used representation language, enhancing the potential for interoperability among many systems

  6. Semantic Web in FIPA • FIPA is the most widely used MAS framework • Well developed and documents standards • Good open source software • RDF is one of FIPA’s standard content languages • OWL is widely used for publishing ontologies within the FIPA community, for example, agentcities and openNet

  7. FIPA Standards Overview IDLXMLbit-eff EnvelopeEncodingScheme IIOPHTTP TransportProtocol Owl for publishing communicative acts Envelope isTransmittedOver 1 1 1 1 1 contains StringXMLbit-eff ACLEncodingScheme isExpressedIn 1..* 1..* ACL ACL Message Owl as a content language 1 1 1 1 1 String contains CLEncodingScheme Owl for publishing protocols 1 1 isExpressedIn request, query, request-whencontract-net, iterated-contract-netbrokering, recruitingsubscribe, propose ContentLanguage SL Content Owl for ontologies 1 1 1 1 1 1 contains fipa-agent-management 0..* 0..* InteractionProtocol belongsTo Symbol Ontology 1..* 1..* 1 1 --Tim Finin 2003

  8. software A A AMS DF ACC IIOP internal platform message transport FIPA Agent Platform Owl for user models and profiles Owl for representation and reasoning Agents belong to one or more agent platforms which provide basic services. Owl for authorization policies Owl for service descriptions --Tim Finin 2003

  9. Outline Part 1: Thesis and Contribution Part 2: Background Part 3: Research Question Part 4: Agent-Based Services Part 5: TAGA and F-OWL Part 6: Conclusion

  10. Why TAGA ? • Need a big and complicated system to evaluate the ideas • Agentcities provides a robust global agent services platform • TAC is a successful travel market simulation system

  11. Trading Agent Competition • The Trading Agent Competitionproposed (1999) and first run (2000) by Michael Wellman and Peter Wurman • Goal: promote and encourage research in markets involving autonomous trading agents; • Methods: trading agents operate within a travel market scenario; • International competitions in 2000, 2001 and 2002 were based on a simple travel scenario

  12. Problems • TAC classic assumes that agents interact via a few centralized markets. • Technology is basically client-server with well defined APIs and simple XML encoding. • Real word interactions are varied and rich • Customers can chose to interact with travel agencies, dynamic markets, or directly with service providers • Choices are governed by value, speed, reputation • Rich information exchange abounds -- customers have complex interests and preferences, service providers have detailed descriptions, etc. • Common ontologies are important • Trust and reputations are important.

  13. TAGA Features • Open Market Framework • Auction Services • OWL Message Content • Travel Market Ontology • Global Agent Community • Goal: test bed for experimenting with Agents, Semantic Web and Web Services

  14. Airline WS Hotel WS TA CA A Typical Scenario 4 6 Market Oversight Agent 3 Bulletin Board Auction Service 1 2a 2b 5

  15. Entertainment Web Service Customer Agents …. TAGA Agents (1) One CA joins the Game every 30 Sec. • Find travel arrangements • Save $$ • Organize travel • Maximize profits TA-1 (AAP) TA-2 (AAP) TA-4 (JADE) • sell “goods” • Maximize profits Airline Web Service Hotel Web Service

  16. TAGA Agents (2) • Helps CA find one or more TA Bulletin Board Agent • Operates the auctions markets: English, Dutch, Priceline and Hotwire. Auction Service Agent • Manage the financial records • Announces the winning TA Market Oversight Agent

  17. Dynamic Contract Protocol

  18. Priceline Auction Protocol

  19. Technology • System Infrastructure: • Agentcities + AAP + JADE • Travel and Auction Ontologies: OWL • Web Services: WSDL • Web technology: • Apache, MySQL • Java Web Start • Agent Communication: • FIPA (OWL as the content language) • Service registration: OWL-S

  20. Simulation Design • Game running continuously • Travel Agent • Direct Buy or Bid • Acquire resource before or after win customer • Penalty, reputation • Auction Service Agent • English & Dutch auction • “Name your price” auction (priceline.com & hotwire.com)

  21. Report Direct Buy Transactions Report Contract Report Auction Transactions Market Oversight Agent Request CFP Report Travel Package Bid Bid Bulletin Board Agent Auction Service Agent Customer Agent Proposal Direct Buy Travel Agents Web Service Agents Travel Agent Game in Agentcities Motivation • Market dynamics • Auction theory (TAC) • Semantic web • Agent collaboration (FIPA & Agentcities) Features • Open Market Framework • Auction Services • OWL message content • OWL Ontologies • Global Agent Community Technologies • FIPA (JADE, April Agent Platform) • Semantic Web (RDF, OWL) • Web (SOAP,WSDL,DAML-S) • Internet (Java Web Start ) Ontologieshttp://taga.umbc.edu/ontologies/ • travel.owl – travel concepts • fipaowl.owl – FIPA content lang. • auction.owl – auction services • tagaql.owl – query language Owl for contract enforcement Owl for publishing communicative acts Owl for negotiation Owl for representation and reasoning Owl for service descriptions Owl for modeling trust Owl as a content language FIPA platform infrastructure services, including directory facilitators enhanced to use OWL-S for service discovery http://taga.umbc.edu/

  22. ACL Content • Statements: the price of this hotel in day 3 is $100/night; • Requests: create an airline auction instance; • Contracts: if the Travel Agent TA1 successful organized the travel package, customer Joe will pay $400 to TA1, else, TA1 pay $200 compensation to Joe. • Policies: to win the contract of the customer Joe, the travel agent must have reputation better than average

  23. Ontologies • ACL http://taga.umbc.edu/ontologies/fipaowl.owl • Auction http://taga.umbc.edu/ontologies/auction.owl • Travel http://taga.umbc.edu/ontologies/travel.owl Submitted to DAML ontology library

  24. Multiple Ontologies Support • NewInstance • OntologyQuery • OntologyShare • OntologyRelation NewInstance Agent A Agent B OntologyQuery Agent A Agent B OntologyShare OntologyQuery Agent A Agent B OntologyRelation

  25. TAGE Home Page http://taga.umbc.edu TAGA on Agentcities network (UMBCTac.agentcities.net) Baltimore, MD USA http://www.agentcities.net/ Download the latest TAGA pkg and docs http://taga.umbc.edu/taga/download/ TAGA in Action Create a TAGA game online TAGA supports heterogeneous agent platform. A FIPA-JADE agent can interact with a FIPA-AAP agent

  26. Conclusion (1) • A rich framework for exploring agent-based approaches to e-commerce applications. • Auction services are developed to enrich the Agentcities environment • The use of Semantic Web languages (OWL) improves agent interoperability • OWL-S is employed to support agent service registration, discovery and invocation • A sourceforge project

  27. Conclusion (2) • Won the Best Student Entry in the Agentcities sponsored Agent Technology Competition held at Barcelona in Feb. 2003 • TAGA platforms have been running in Agentcity.Net for more than 16 months. • Invited to Intelligent System Demonstrations at IJCAI 2003 and AAMAS 2004 • Used by people from US, Korea, Romania, etc.

More Related