Information Agents RETSINA & WebMate CS525M Multi Agent Systems, WPI Presented by: Jian, Jinhui.

Slides:



Advertisements
Similar presentations
1DAML PI meeting, October DAML and Agents DAML and Agents Breakout Session DAML PI Meeting 17 October 2002 Tim Finin.
Advertisements

A platform of for knowledge and services sharing Fernando Ferri IRPPS-CNR.
UCLA : GSE&IS : Department of Information StudiesJF : 276lec1.ppt : 5/2/2015 : 1 I N F S I N F O R M A T I O N R E T R I E V A L S Y S T E M S Week.
A Successful RHIO Implementation
1 Intelligent Agents Software analog to human agents real estate agent, librarian, salesperson Perform tasks individually, or in collaboration Static and.
0 General information Rate of acceptance 37% Papers from 15 Countries and 5 Geographical Areas –North America 5 –South America 2 –Europe 20 –Asia 2 –Australia.
Effective Coordination of Multiple Intelligent Agents for Command and Control The Robotics Institute Carnegie Mellon University PI: Katia Sycara
Adding Organizations and Roles as Primitives to the JADE Framework NORMAS’08 Normative Multi Agent Systems, Matteo Baldoni 1, Valerio Genovese 1, Roberto.
Latest techniques and Applications in Interprocess Communication and Coordination Xiaoou Zhang.
Notes to the presenter. I would like to thank Jim Waldo, Jon Bostrom, and Dennis Govoni. They helped me put this presentation together for the field.
Rheeve: A Plug-n-Play Peer- to-Peer Computing Platform Wang-kee Poon and Jiannong Cao Department of Computing, The Hong Kong Polytechnic University ICDCSW.
Intelligent Software Agents Lab The Robotics Institute Carnegie Mellon University 5000 Forbes Avenue Pittsburgh, PA (U.S.A.)
Joseph A. Giampapa Octavio H. Juarez-Espinosa Katia P. Sycara The Robotics Institute Carnegie Mellon University 5000 Forbes Avenue Pittsburgh, PA
Modern Information Retrieval Chapter 2 Modeling. Can keywords be used to represent a document or a query? keywords as query and matching as query processing.
Las Vegas 1999Katia Sycara1 Effective Coordination of Multiple Intelligent Agents for Command and Control The Robotics Institute Carnegie Mellon University.
OCT1 Principles From Chapter One of “Distributed Systems Concepts and Design”
Interoperability of Future Information Systems Daniel Siewiorek, Katia Sycara (PI’s) Joseph Giampapa, Ritika Sanghi, Aaron Steinfeld School of Computer.
Operational Capability: We are developing and testing search munition control strategies using both a high fidelity 6-dof simulation of the LOCAAS and.
ReQuest (Validating Semantic Searches) Norman Piedade de Noronha 16 th July, 2004.
RETSINA: A Distributed Multi-Agent Infrastructure for Information Gathering and Decision Support The Robotics Institute Carnegie Mellon University PI:
Developing Intelligent Agents and Multiagent Systems for Educational Applications Leen-Kiat Soh Department of Computer Science and Engineering University.
What is adaptive web technology?  There is an increasingly large demand for software systems which are able to operate effectively in dynamic environments.
University of Kansas Data Discovery on the Information Highway Susan Gauch University of Kansas.
Personalized Ontologies for Web Search and Caching Susan Gauch Information and Telecommunications Technology Center Electrical Engineering and Computer.
Knowledge Portals and Knowledge Management Tools
DISTRIBUTED PROCESS IMPLEMENTAION BHAVIN KANSARA.
Web-based Portal for Discovery, Retrieval and Visualization of Earth Science Datasets in Grid Environment Zhenping (Jane) Liu.
Web Programming Language Dr. Ken Cosh Week 1 (Introduction)
1 Introduction to Web Development. Web Basics The Web consists of computers on the Internet connected to each other in a specific way Used in all levels.
Chapter 10 Architectural Design
1 Vector Space Model Rong Jin. 2 Basic Issues in A Retrieval Model How to represent text objects What similarity function should be used? How to refine.
Introduction To Computer System
Agent Model for Interaction with Semantic Web Services Ivo Mihailovic.
* * 0 OWL-S: Ontology Web Language For Services Reyhan AYDOĞAN Emre YILMAZ 21/12/2005OWL-S: Ontology Web Language for Services.
Implicit An Agent-Based Recommendation System for Web Search Presented by Shaun McQuaker Presentation based on paper Implicit:
Web Services Kanda Runapongsa Dept. of Computer Engineering Khon Kaen University.
1 Introduction to Middleware. 2 Outline What is middleware? Purpose and origin Why use it? What Middleware does? Technical details Middleware services.
Distributed Information Retrieval Using a Multi-Agent System and The Role of Logic Programming.
Advanced Computer Networks Topic 2: Characterization of Distributed Systems.
©Ferenc Vajda 1 Semantic Grid Ferenc Vajda Computer and Automation Research Institute Hungarian Academy of Sciences.
An Architecture for Emergent Semantics Sven Herschel, Ralf Heese, and Jens Bleiholder Humboldt-Universität zu Berlin/ Hasso-Plattner-Institut.
Search Engine Architecture
Evaluation of Agent Building Tools and Implementation of a Prototype for Information Gathering Leif M. Koch University of Waterloo August 2001.
Christoph F. Eick University of Houston Organization 1. What are Ontologies? 2. What are they good for? 3. Ontologies and.
Internet Architecture and Governance
Introduction to Semantic Web Service Architecture ► The vision of the Semantic Web ► Ontologies as the basic building block ► Semantic Web Service Architecture.
World Wide Web “WWW”, "Web" or "W3". World Wide Web “WWW”, "Web" or "W3"
Enabling the Future Service-Oriented Internet (EFSOI 2008) Supporting end-to-end resource virtualization for Web 2.0 applications using Service Oriented.
Introduction to Grids By: Fetahi Z. Wuhib [CSD2004-Team19]
Multiagent System Katia P. Sycara 일반대학원 GE 랩 성연식.
Service Brokering Yu-sik Park. Index Introduction Brokering system Ontology Services retrieval using ontology Example.
An Overview of Scientific Workflows: Domains & Applications Laboratoire Lorrain de Recherche en Informatique et ses Applications Presented by Khaled Gaaloul.
Providing web services to mobile users: The architecture design of an m-service portal Minder Chen - Dongsong Zhang - Lina Zhou Presented by: Juan M. Cubillos.
A System for Automatic Personalized Tracking of Scientific Literature on the Web Tzachi Perlstein Yael Nir.
User Interfaces and Information Retrieval Dina Reitmeyer WIRED (i385d)
EEL 5937 Mobile agents EEL 5937 Multi Agent Systems Lotzi Bölöni.
A Multi-Agent and Service-Oriented Architecture for Developing Integrated and Intelligent WBES Computing and Information Systems Oscar Lin Peter Holt.
Communities and Portals Lan Zhang School of Information University of Texas at Austin.
Exercises for Chapter 1: Characterization of Distributed Systems From Coulouris, Dollimore and Kindberg Distributed Systems: Concepts and Design Edition.
Building Preservation Environments with Data Grid Technology Reagan W. Moore Presenter: Praveen Namburi.
1 © 2004 Cisco Systems, Inc. All rights reserved. Session Number Presentation_ID Cisco Technical Support Seminar Using the Cisco Technical Support Website.
E-commerce Architecture Ayşe Başar Bener. Client Server Architecture E-commerce is based on client/ server architecture –Client processes requesting service.
Effective Coordination of Multiple Intelligent Agents for Command and Control The Robotics Institute Carnegie Mellon University PI: Katia Sycara
GCI Architecture GEOSS Information System Meeting 20 September 2013, ESA/ESRIN (Frascati, Italy) M.Albani (ESA), D.Nebert (USGS/FGDC), S.Nativi (CNR)
The Robotics Institute Carnegie Mellon University PI: Katia Sycara
Search Engine Architecture
Personal Assistants for the Web: An MIT Perspective
Introduction of Week 11 Return assignment 9-1 Collect assignment 10-1
Search Engine Architecture
AGENT FRAMEWORK By- Arpan Biswas Rahul Gupta.
Presentation transcript:

Information Agents RETSINA & WebMate CS525M Multi Agent Systems, WPI Presented by: Jian, Jinhui

2 Name Matters zRETSINA: Reusable Environment for Task-Structured Intelligent Networked Agents zRetsina: the wine of Greek Gods

3 Outline zRETSINA yThe Functional Architecture yThe Agent Architecture yThe MAS Architecture zWebMate zConclusion

4 What is RETSINA zRETSINA is a domain-independent and reusable infrastructure on which MAS systems, services, and components live, communicate, and interact. zRETSINA is an architecture for developing distributed intelligent software agents that cooperate asynchronously to perform goal-directed information retrieval and information integration in support of a variety of decision making tasks. zRETSINA is project done in the Robotics Institute, CMU

5 The Functional Architecture

6 The Functional Architecture (cont.) zInterface agents -- interact with users, receive user input, and display results. zTask agents -- help users perform tasks, formulate problem- solving plans and carry out these plans by coordinating and exchanging information with other software agents. zInformation agents -- provide intelligent access to a heterogeneous collection of information sources. zMiddle agents -- help match agents that request services with agents that provide services.

7 Another Functional Architecture to compare with Info. Site Descriptor Match-Maker Info. Req. Facilitator Use Agent Info Prov. Facilitator Extractor Source Agent Info Prov. Facilitator Extractor Source Agent Extractor Source Agent Extractor Source Agent Info. Site

8 The Agent Architecture

9 Reusable Modules Inside an Agent zThe Communication and Coordination module accepts and interprets messages and requests from other agents. zThe Planning module takes as input a set of goals and produces a plan that satisfies the goals. zThe Scheduling module uses the task structure created by the planning module to order the tasks. zThe Execution module monitors this process and ensures that actions are carried out in accordance with computational and other constraints.

10 The MAS Architecture

11 Operating Environment zPlatform independent: yany platform that runs Windows, Linux, or Sun OS yPalmPilots zMultiple language support: Java, C/C++, Python, LISP, and Perl zNetwork support: TCP/IP, wireless, infrared, and serial connections

12 Communication Infrastructure zPeer to Peer: Message Transfer (A2A) ysynchronous or asynchronous ymultithreaded communication zMulticast: Discovery Process (finding the infrastructure components) yinfrastructure components announce the presence yagents register themselves

13 Agent Communication Language zKQML based yThe envelop yThe content zShared Dictionary: Ontology ydomain-specific taxonomies of concepts from the WordNet yterm similarity measurement

14 MAS Management Services zMonitor yLogger: records the activity of the agents (e.g. entering/exiting, agent states, transitions, etc) yLogger Module: voluntarily provided by the agent zDebug y Activity Visualizer zLaunch yLauncher: configures and starts infrastructure components and agents (enable single point control)

15 Performance Services zNo performance services support yet (only failure monitoring) zbut agents can do it by themselves : yself-monitoring yclone: task sharing

16 Security zFunctionality yAgent authentication yCommunication security yComponent integrity zMechanism ySSL (public/ private keys) yunique Agent Id as the private key

17 Name to Location Mapping zRETSINA ANS (Agent Naming Services) yAgent Id --> Address mapping ymultiple and redundant ANS for robustness

18 Middle agents (the matchmakers) zProvide a registry of services yadvertisement yrequest zService matching using the LARKS matching engine yboth syntactic and semantic analysis yboth exact and partial matches

19 MAS Inter-operation zThere are more than one agent architectures ydifferent communication languages ydifferent MAS architectures zOOA-RETSINA inter-operation support only (RETSINA-OOA InterOperator) yhelp finding each other yhelp talking to each other

20 The Applications Based on RETSINA zShow up!Show up!

21 WebMate an information agent example zWebMate is a personal agent for World- Wide Web browsing that enhances searches and learns user interests.

22 The Missions zProvides URL recommendations based on a continuously updated user profile zOffers ever more relevant web documents based on the "Trigger Pairs Model" approach to keyword refinement zResponds to user feedback by selecting features from documents the user finds relevant and incorporating these features into the context of new queries zCompiles a daily personal newspaper with links to documents of interest to the user (“pull”)

23 The Architecture

24 Learning User Preference zTF-IDF Value yTF (Term Frequency): measures how many times a word appears in a document. yIDF (Inverse Document Frequency): measures the number of documents containing a word zVector Space Model yrepresent each document as a vector in a vector space so that documents with similar content have similar vectors. yeach dimension of the vector space represents a word and its weight, which is a TF-IDF value. zMultiple TF-IDF Vector Model yuse multiple vectors to capture user’s multiple preferences

25 Refining the User Query zTrigger Pairs Model yfind the word pairs that occur together yone word in the pair trigger the other (enlarging the user query) zUsing the user feedback yuser may give a “relevant” rating to a page ythe system will analyze the page using the context of keyword (i.e. the words near by) ythe system finds out the relevant keywords yenlarge the user query using the relevant keywords

26 Pulling Relevant Contents zUse spider agents to grab data from different sites zUse Vector Space Model to measure relevance (using the user profile) zReturn only the relevant pages

27 Conclusion zA good MAS infrastructure should support agents for different tasks, from different domains, and with different originalities. zThere are lots we can do beyond web search engines: yuser preference learning yuser query refinement

28 Reference zKatia Sycara, Massimo Paolucci, Joseph Giampapa; “The RETSINA MAS Infrastructure”; TechReport CMU-RI-TR ; 2001 zKiren Chen, Katia Sycaca; “WebMate: A Personal Agent for Browsing and Searching”; The Robotics Institute, Carnegie Mellon University; 1998 zK. L. Clarc, V.S. Lazarou; “A Multiagent System for Distributed Information Retrieval on the World Wide Web”; 1997

29 Questions to Ask for a MAS Infrastructure zWhat constitutes a MAS infrastructure zWhat functionality it supports zWhat characteristics it should have to enable value- added abilities zWhat its possible relation with and requirements it may impose on the design and structure of single agents

30 The Principle in mind zThere are more than one MAS systems in the world (seems trivial, but…) yAgents of different kinds should be able to enter the system yAgents’ internal structure should be transparent to the system yAgents’ business should be left alone ( the ways to coordinate, negotiate, etc)