SEMANTIC AGENT SYSTEMS

Towards a Reference Architecture for Semantic Agent Systems Applied to Symposium

PlanningChaudhry Usman Ali

UNB FCS ,Fredericton, NB1

Outline

2

BackgroundAgent ScenarioVirtual OrganizationOrganizational DesignsSemantic Agent SystemsEvaluation/ComparisonConclusion

Semantic Web Vision

3

Agent Scenario

Consider a Web-enabled method for saving the doomed crew of The Perfect Storm.

How could Web agents have helped?4

 James Hendler: Agents and the Semantic Web. IEEE Intelligent Systems Journal (March/April 2001). http://www.cs.rpi.edu/~hendler/AgentWeb.html

Virtual Organization

"Virtual Organizations are a set of individuals and institutions that need to co-ordinate resources and services across institutional boundaries".

5

 N. Criado, E. Argente, V. Juli´an, V. Botti: Designing Virtual Organizations. 440-449, In: Demazeau, Y.; Pavón, J.; Corchado, J.M.; Bajo, J. (Eds.): 7th International Conference on Practical Applications of Agents and Multi-Agent Systems (PAAMS'09), Series: Advances in Intelligent and Soft Computing, Vol. 55, 2009.

Software Personal Assistants

Software personal assistants (SPA) are an active research area that one day might change the face of our human organizations.

                                Organizational Structures

                       Star                                                 Ring                                          Mixed/Random  

Overload Speed

6

Towards Agent-Oriented Conceptualization and Implementation / Pratik K. Biswashttp://www.igi-global.com/bookstore/titledetails.aspx?titleid=76

Agent Centered Versus Organization Centered Approach

Agent Centered

States of an agent and of the relation between these states and its overall behaviour.

Organization Centered

Concepts of ‘organizations’, ‘groups’, ‘communities’, ‘roles’, ‘functions’, etc. play an important role.Classical New Approach

7

 Jacques Ferber, Olivier Gutknecht, and Fabien Michel: From Agents to Organizations: an Organizational View of Multi-Agent Systems. Agent-Oriented Software Engineering (AOSE) IV, P. Giorgini, Jörg Müller, James Odell, eds, Melbourne, July 2003, LNCS 2935, pp. 214-230, 2004

Organization Design

Open Agent Architecture (OAA):

 Flexible, dynamic communities of distributed software agents.  Human users and software agents, in an OAA, express their requests in terms of, “What will be done?” rather than“How will it be done?”

8

In a distributed software architecture, sharing information or interaction has to be predefined which makes it a rigid distributed architecture environment.

Tools?

http://www.ai.sri.com/oaa/ {Open Agent Architecture: Technical White Paper}

Semantic Agent Systems

9

Semantic Agent Systems use rules and Ontologies for creating virtual organizations as multi-agent systems that can support collaborative teams on the Semantic Web.

They provide the infrastructure for rule- and ontology-based collaboration between the distributed members of such a virtual organization.

Multi Agent Frameworks

Academic World                        Business World

Presentation

SEARCHABLE10

EMERALD

11

 Kalliopi Kravari, Taylor Osmun, Harold Boley and Nick Bassiliades, Cross-Community Interoperation Between the EMERALD and Rule Responder Multi-Agent Systems.

RULE RESPONDER

12http://ruleml.org/RuleResponder/

Organizational Agent

The organizational agent represents the goals and strategies shared by each committee chair.

It contains rule sets that describe the policies and regulations of the RuleML Symposium.

Delegates incoming queries to the chair’s PAs. 13

Personal Agent

• A personal agent assists a single chair

of the symposium,(semi-autonomously)

acting on his/her behalf.• Each personal agent contains a rule-base FOAF-like profile.

• It contains a FOAF*-like fact profile

plus

FOAF-extending rules to encode

selected knowledge of its human owner.14

External Agent

• External agents exchange messages with the OA. They submit queries and receive answers.

• End users, as external agents, interact with the OA using a Web (HTTP) interface to the Symposium Planner.

• Support for simultaneous external agents. Many EAs can communicate with the OA.

15

Rule Engines

Prova is mainly used to realize the organizational agents of Rule Responder

It implements Reaction RuleML for agent interaction (event-condition-action rules)

16

OO jDREW is used to realize the personal agents of Rule Responder

It implements Hornlog RuleML for agent reasoning (Horn logic rules)

Supports rules in two formats:POSL: Positional Slotted presentation syntaxRuleML: XML interchange syntax

COMMUNICATION MIDDLEWARE

Mule Enterprise Service Bus (ESB)

 Mule is used to create communication end points at each personal and organizational agent of Rule Responder. Mule supports various transport protocols(i.e. http, JMS, soap) Rule Responder uses http and JMS as transport protocols.

17

MULE ENTERPRISE SERVICE BUS

18

Reaction RuleML

Reaction RuleML is a branch of the RuleML family that supports actions and events.

When two agents want to communicate, with each other Reaction RuleML messages are sent through the ESB.

The ESB carries RuleML queries (requests), answers (results), and rule bases to/from agents. 19

20

Online Use Case Demo

http://www.defeasible.org/ruleml2011ijcai/?q=node/25

http://de.dbpedia.org/redirects/ruleml/ACE2ReactionRuleML/index.jsp

21

22

23

Evaluation of Semantic Agent Systems

24

RR EM

Separate rule and ontology languages, or combine them in a hybrid or homogeneous manner

Distinguish a performative (pragmatic) layer from a content (semantic) layer

Organise agent communication in a hierarchical (client-server) or networked (peer-2-peer) or reconfigurable (dynamic) fashion.

Can be built on a multi-agent platform such as JADE or be based on an Enterprise Service Bus such as Mule.

Can be used to define autonomous agents or semi-autonomous agents.Can operate on a private intranet, a cross-organisational extranet or the open Internet.Can realise virtual organisations in which agents solve various kinds of tasks, including document retrieval, question answering, and information integration.

Rule Responder uses both Ontologies and Rules.

Rule Responder uses FIPA and Reaction RuleML.Emerald uses (D)R-DEVICE RuleML.

Rule Responder uses hierarchical architecture.

Rule Responder uses Mule ESB.Emerald uses JADE.

Rule Responder and Emerald provide semi autonomous agents.

Rule Responder can operate locally as all resources are local. Emerald has to access third party resources.

Rule Responder provides agents (OA, PA, EA, CA) to perform different tasks. Emerald provides Knowledge Customizable (KC)-Agents.

ConclusionSymposiumPlanner