13
Rule Responder: An Intelligent Rule Responder: An Intelligent Multi-Agent System for Multi-Agent System for Collaborative Teams and Virtual Collaborative Teams and Virtual Communities Communities Benjamin Craig Benjamin Craig Harold Boley Harold Boley Institute for Information Institute for Information Technology Technology National Research Council, National Research Council, Canada Canada Fredericton, NB, Canada Fredericton, NB, Canada New Brunswick Innovation Forum New Brunswick Innovation Forum St. John New Brunswick St. John New Brunswick October 28-29, 2008 October 28-29, 2008

Rule Responder: An Intelligent Multi-Agent System for Collaborative Teams and Virtual Communities Benjamin Craig Harold Boley

  • Upload
    alec

  • View
    29

  • Download
    0

Embed Size (px)

DESCRIPTION

Rule Responder: An Intelligent Multi-Agent System for Collaborative Teams and Virtual Communities Benjamin Craig Harold Boley. Institute for Information Technology National Research Council, Canada Fredericton, NB, Canada New Brunswick Innovation Forum St. John New Brunswick - PowerPoint PPT Presentation

Citation preview

Page 1: Rule Responder:  An Intelligent  Multi-Agent System for Collaborative Teams and Virtual Communities Benjamin Craig Harold Boley

Rule Responder: An IntelligentRule Responder: An Intelligent Multi-Agent System for Collaborative Multi-Agent System for Collaborative

Teams and Virtual CommunitiesTeams and Virtual Communities Benjamin CraigBenjamin Craig

Harold BoleyHarold BoleyInstitute for Information TechnologyInstitute for Information TechnologyNational Research Council, Canada National Research Council, Canada

Fredericton, NB, CanadaFredericton, NB, Canada

New Brunswick Innovation ForumNew Brunswick Innovation ForumSt. John New Brunswick St. John New Brunswick

October 28-29, 2008October 28-29, 2008

Page 2: Rule Responder:  An Intelligent  Multi-Agent System for Collaborative Teams and Virtual Communities Benjamin Craig Harold Boley

22

EA: External Agent

OA PA1

PA2

PA3

PA4

PA5

Expert5

Expert4

Expert3

Expert2

Expert1

Star-Like Star-Like Rule Rule Responder Responder Architecture Architecture

Spoke PA: Personal AgentHub OA: Organizational Agent

VirtualOrganization

Page 3: Rule Responder:  An Intelligent  Multi-Agent System for Collaborative Teams and Virtual Communities Benjamin Craig Harold Boley

33

Existing Auto-RespondersExisting Auto-Responders Mail Clients can act as auto-responders Mail Clients can act as auto-responders

when people are unreachable, as when people are unreachable, as illustrated by “Vacation Programs”illustrated by “Vacation Programs”

Other auto-responders engage users in Other auto-responders engage users in interaction sequences, e.g. to check user interaction sequences, e.g. to check user identity when subscribing/unsubscribingidentity when subscribing/unsubscribingto/from a mailing listto/from a mailing list

Rule Responder extends such auto-Rule Responder extends such auto-responders to intelligent, distributed rule responders to intelligent, distributed rule systems such as for symposium planningsystems such as for symposium planning

Page 4: Rule Responder:  An Intelligent  Multi-Agent System for Collaborative Teams and Virtual Communities Benjamin Craig Harold Boley

44

Overview of Rule ResponderOverview of Rule Responder Rule Responder is a pRule Responder is a prototypicalrototypical

multi-agent system for virtual multi-agent system for virtual communitiescommunities

Supports rule-based collaboration Supports rule-based collaboration between the distributed members of between the distributed members of communitycommunity

Members are assisted by semi-Members are assisted by semi-automated automated rule-basedrule-based agents, which agents, which use rules to describe the decision and use rules to describe the decision and behavioral logicbehavioral logic

Page 5: Rule Responder:  An Intelligent  Multi-Agent System for Collaborative Teams and Virtual Communities Benjamin Craig Harold Boley

55

Deployed Use Case: Deployed Use Case: Symposium Planner Symposium Planner

RuleML-20xy SymposiaRuleML-20xy Symposia An organizational agent acts as the single An organizational agent acts as the single

point of entry to point of entry to assistassist with symposium with symposium planning:planning:

Currently, query answering about the symposium Currently, query answering about the symposium Ultimately, preparing and running the symposium Ultimately, preparing and running the symposium

Personal agents have supported Personal agents have supported symposium chairs since 2007 (deployed symposium chairs since 2007 (deployed as Q&A in 2008)as Q&A in 2008)

General Chair, Program Chair, Panel Chair, General Chair, Program Chair, Panel Chair, Publicity Chair, etcPublicity Chair, etc..

Page 6: Rule Responder:  An Intelligent  Multi-Agent System for Collaborative Teams and Virtual Communities Benjamin Craig Harold Boley

66

Personal AgentsPersonal Agents Each PA acts as a Personal Each PA acts as a Personal

Assistant to a human in the Assistant to a human in the organizationorganization

These agents are softbotsThese agents are softbotsthat help you in workingthat help you in workingand networkingand networking

You define the rules howYou define the rules howyour agent shall assist youyour agent shall assist you

In our deployed use case, In our deployed use case, symposium chairs are assistedsymposium chairs are assistedby PAsby PAs

Page 7: Rule Responder:  An Intelligent  Multi-Agent System for Collaborative Teams and Virtual Communities Benjamin Craig Harold Boley

77

Organizational AgentOrganizational Agent The Organizational Agent interconnects The Organizational Agent interconnects

all the Personal Agents in ourall the Personal Agents in ourStar-Like Star-Like Rule Responder Rule Responder ArchitectureArchitecture

The OA channels the right The OA channels the right informationinformationto the right to the right agentagent at the right at the right timetime

The OA acts as a Mediator,The OA acts as a Mediator,Middleman, or FacilitatorMiddleman, or Facilitator

In our deployed use case, the OA In our deployed use case, the OA contains general policies & regulations contains general policies & regulations of the RuleML-2008 Symposiumof the RuleML-2008 Symposium

Page 8: Rule Responder:  An Intelligent  Multi-Agent System for Collaborative Teams and Virtual Communities Benjamin Craig Harold Boley

88

External AgentsExternal Agents External agents supports clients outsideExternal agents supports clients outside

your organization who want to interact your organization who want to interact with the organizationwith the organization

An External Agent links clientsAn External Agent links clientswith the OA of your organizationwith the OA of your organization

The OA will find for them the rightThe OA will find for them the rightPA and Expert for each problem at handPA and Expert for each problem at hand

Mediated by the OA,Mediated by the OA,the Expert, their PA, or both the Expert, their PA, or both togethertogetherwill solve your problemwill solve your problem

Page 9: Rule Responder:  An Intelligent  Multi-Agent System for Collaborative Teams and Virtual Communities Benjamin Craig Harold Boley

99

Competing/Complementary Competing/Complementary WorkWork

Intelligent Agents:Intelligent Agents: ISI’s Electric Elves (ISI’s Electric Elves (e-Elvese-Elves)) SRI’s Open Agent ArchitectureSRI’s Open Agent ArchitectureTMTM ( (OAAOAA)) FIPA’s Agent Communication Language (FIPA’s Agent Communication Language (ACLACL)) JADE-Board’s Java Agent Development JADE-Board’s Java Agent Development

Framework (JADE) Framework (JADE) Web Services:Web Services: PublishPublish: W3C’s Web Services Description : W3C’s Web Services Description

Language (Language (WSDLWSDL)) Find: OASIS’ Universal Description Discovery

& Integration (UDDI)

Page 10: Rule Responder:  An Intelligent  Multi-Agent System for Collaborative Teams and Virtual Communities Benjamin Craig Harold Boley

1010

Page 11: Rule Responder:  An Intelligent  Multi-Agent System for Collaborative Teams and Virtual Communities Benjamin Craig Harold Boley

1111

OA PA1

PA2

PA3

PA4

PA5

Expert5

Expert4

Expert3

Expert2

Expert5EA

Page 12: Rule Responder:  An Intelligent  Multi-Agent System for Collaborative Teams and Virtual Communities Benjamin Craig Harold Boley

1212

ConclusionConclusion Created Created Star-Like Star-Like Rule Responder Rule Responder

ArchitectureArchitecture Deployed Deployed Symposium Planning Use CaseSymposium Planning Use Case

can be adapted to organizing other meetingscan be adapted to organizing other meetingsand assisting other virtual communitiesand assisting other virtual communities

Further deployed use cases include theFurther deployed use cases include theHHealth ealth CCare and are and LLife ife SScience Rule cience Rule Responder (HCLS)Responder (HCLS)

Thanks to RuleML’s int’l Thanks to RuleML’s int’l Rule ResponderRule ResponderTechnical Group with Technical Group with Adrian PaschkeAdrian Paschke,,Alexander Kozlenkov, and Nick BassiliadesAlexander Kozlenkov, and Nick Bassiliades

Page 13: Rule Responder:  An Intelligent  Multi-Agent System for Collaborative Teams and Virtual Communities Benjamin Craig Harold Boley

1313

Rule Responder Rule Responder OpportunitiesOpportunities

Status of the Business Idea:Status of the Business Idea: Open Source Prototype with Deployed Use Open Source Prototype with Deployed Use

Cases:Cases:http://www.ruleml.org/RuleML-2008/RuleResponder/http://www.ruleml.org/RuleML-2008/RuleResponder/http://ibis.in.tum.de/projects/paw/hcls/http://ibis.in.tum.de/projects/paw/hcls/

Desired CooperationsDesired Cooperations Partnership for Your Intelligent Agents Partnership for Your Intelligent Agents Partnership for Your Use CasesPartnership for Your Use Cases

COME TO OUR BOOTH!COME TO OUR BOOTH!