SEMANTIC AGENT SYSTEMS
Towards a Reference Architecture for Semantic Agent Systems Applied to
Symposium Planning
Usman AliFredericton, NB
1
Outline
BackgroundOrganizationVirtual OrganizationOrganizational DesignsAgent ScenariosMulti Agent System FrameworksConclusion
2
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
Organization
"An organization provides a framework for activity and interaction through the definition of roles, behavioural expectations and authorityrelationships (e.g. control)."
5
Virtual Organization
"Virtual Organizations are a set of individuals and institutions that need to co-ordinate resources and services across institutional boundaries".
6
Linked Data
Current Web
Documents
Semantic Web
Formal Ontologies
Middle way between formalism of Ontologies and information of documents.
Linked Data
7
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
8
Agent based Computing
Agent based computing merges two technologies, namely Artificial Intelligence (AI) and object-oriented distributed computing.In distributed object computing, objects can be located across a variety of platforms and in different processes and can communicate transparently with each other (by issuing method requests) as if they were located on a single machine.
9
Importance of Agent oriented thinking
As real-world applications are becoming significantly more complex than before. Agent-oriented techniques provide a natural way for modelling complex systems, by decomposing its problem space into autonomous agents and their interactions.
10
Agent Centered Versus Organisation Centered Approach
Agent Centered
States of an agent and of the relation between these states and its overall behaviour.
Organisation Centered
Concepts of ‘organizations’, ‘groups’, ‘communities’, ‘roles’, ‘functions’, etc. play an important role.
Classical New Approach
11
Organization Design
In a distributed software architecture, sharing information or interaction has to be predefined which makes it a rigid distributed architecture environment.
Open Agent Architecture (OAA):Flexible, dynamic communities of distributed software agents.Human users and software agents, in an OAA, express their requestsin terms of,“What will be done?”rather than "How will it be done?” Tools?
12
Agent Oriented Modelling and Design
Scenario
A situation in a application involving actors and activities.
Structured Thinking
Agents start with an overall plan to solve the problem.
Unstructured Thinking
Actors can start from anywhere and build up a solution.
Actors can play roles based on their perception (mental states).
Agent oriented modelling and design.13
Multi Agent Frameworks
Academic World Business World
PresentationSEARCHABLE
14
EMERALD
15
RULE RESPONDER
16
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.
17
Personal Agent
• A personal agent assists a single chairof 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 plusFOAF-extending rules to encode selected knowledge of its human owner.
18
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.
19
Query Delegation
Publicity Chair
AgentsSponsoring
Publicity Chair
...
Liaison Chair
General Chair
....
..
Challenge Chair
Challenge
Demos
Media Partners
Sponsors
Responsible
Accountable
Press Release
Challenge Chair
Liaison Chair
General Chair
Metatopics ...
...
...
Registration
Visa Letter
...
Program Chair
...
...
Program Chair
Submissions
Presentations...
Properties:20
Rule Engines
Prova: Prolog + Java
OO jDREW: Object Oriented java Deductive Reasoning Engine for the Web
OO jDREW is used to realize thepersonal agents of Rule Responder
It implements Hornlog RuleML for agent reasoning (Horn logic rules)Supports rules in two formats:POSL: Positional Slotted presentation syntax
RuleML: XML interchange syntax
Prova is mainly used to realize the organizational agents of Rule Responder
It implements Reaction RuleML for agent interaction (event-condition-action rules)
21
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
22
MULE ENTERPRISE SERVICE BUS
23
Reaction RuleML
Reaction RuleML is a branch of the RuleML family that supports actions and events.
When two agents want to communicate, each others’ Reaction RuleML messages are sent through the ESB.
The ESB carries RuleML queries (requests), answers (results), and rule bases to/from agents.
24
RuleResponder versus Emerald
25
Multi Agent System Interoperation
26
REFERENCE ARCHITECTURE OF SYMPOSIUMPLANNER
27
28
Online Use Case Demo
http://www.defeasible.org/ruleml2011ijcai/?q=node/25
http://de.dbpedia.org/redirects/ruleml/ACE2ReactionRuleML/index.jsp
29
30
31
Conclusion
• The SymposiumPlanner and many other applications like it, can truly provide the basis for gradual transformation of our workplace into an efficient and productive environment.
32