Intelligent Software Agent Technology by Dr. Thomas E. Potok Collaborative Technologies Group Leader Computer Science and Mathematics Division Oak Ridge National Laboratory Research Team Mark Elmore, Joel Reed, Nagiza Samatova, Jim Treadwell

Posted on at


Intelligent Software Agent
Technology
Dr. Thomas E. Potok
Collaborative Technologies Group Leader
Computer Science and Mathematics Division
Oak Ridge National Laboratory
Research Team
Mark Elmore, Joel Reed, Nagiza Samatova, Jim Treadwell
2
Oak Ridge National Laboratory
 Established in 1943 for the World War II
Manhattan Project.
 ORNL today pioneers the development
of new energy sources, technologies,
and materials and the advancement of
knowledge in the biological, chemical,
computational, engineering,
environmental, physical, and social
sciences.
 Budget: $870 million, 80% Department of
Energy, 20% work for others.
 3800 employees, 1500 scientists and
engineers
3
Agent Technology Trend
Face to Face
Telephone
Internet
“The Semantic Web… will open up the knowledge and workings of
humankind to meaningful analysis by software agents, providing a
new class of tools by which we can live, work and learn together”
Tim Berners-Lee, James Hendler, Ora Lassila
“The Semantic Web” Scientific American 5/2001
4
Successful Projects
Collaborative Management Environment
Knowledge-based Computer Systems Calibration
Knowledge-based Systems for Constructability
Neural Nets for Material Mix Optimization
Knowledge-based Systems - Manufacturing Advisors
Neural Nets for Spring-back Prediction
Neural Nets for Resistance. Spot Welding
Neural Nets for Recovery Boiler Control
Neural Nets for Bankruptcy Prediction
Genetic Algorithms for Chemical Synthesis
Design and Analysis of Computer Experiments
Collaborative Design System
Manufacturing Emulation Agent System
Supply Chain Management Agent System
We have extensive expertise in
agent development
Began working with agent
technologies in 1980s
Over 10 successful projects
within the last 5 years
Collaborations with leading
agent experts
1985 1990 1995 2000
Scientific Data Management
VIPAR Knowledge Discovery
5
Collaborative Management Environment

(proposal |
staff-resources |
funds-resources |
equipment-resources |
budget-attachment |
equipment-attachment |
major-cost-attachment |
time |
milestone-task |
doe-program |
doe-program-manager |
oo-reviewer |
pi |
proposal-manager |
hq-organization |
operations-office |
attachment |
contractor |
funds-actual |
cost-actual |
report-requirements
)+>
(ben |
work-prop-no |
work-prop-title |
rev-no |
inst-plan-flag |
work-prop-desc |
fwp-rpt-rqmt
)+>











19980727115540408

ERKJE09


Collaborative Management Environment


0


Y


The Collaborative Management Environment (CME) is a joint
research project between the Oak Ridge National
Laboratory (ORNL) and Lawrence Berkely National
Laboratory (LBNL) that is funded by the U.S. Department
of Energy (DOE). CME is designed to support …


Results will be reported in periodic highlights to DOE
and in peer-reviewed journals and conference proceedings.





Original Document XML tagged Document
Field level query Financial Summary
Managing heterogeneous information
6
Portfolio Management Environment
 Dr. Ernest Moniz, Under Secretary of
Energy, approves
 Portfolio Management Environment (PME)
 Based on the ORNL Collaborative Management
Environment (CME) project
 Estimated 5-year implementation cost
 $17 million total investment
 Producing approximately $39 million annual
productivity gains for DOE
7
Agents in Scientific Data
Management
Astrophysics
Climate
Genomic
Simulations
Scientific
Analysis
And
Discovery
Probe
HPSS
Parallel
Agent
Distributed
Clustering
SDM
center
3 year $9M Center to manage massive scientific data
DOE Labs: Argonne, Berkeley, Livermore, Oak Ridge
Universities: Georgia Tech, NC State, Northwestern, SDSC
8
...Software entities that assist people and act on their behalf - IBM
Traditional Software
What are Agents?
Behavior
State
Client Server Messaging
Agents
Social
Model
Reactive
Model
Peer to Peer Messaging
Knowledge
Model
9
...Software entities that assist people and act on their behalf - IBM
Traditional Software
What are Agents?
Behavior
State
Client Server Messaging
Agents
Social
Model
Reactive
Model
Peer to Peer Messaging
Knowledge
Model
10
Simple Agent Example
Agent,
find me the book
“War and Peace,”
and I need it
tomorrow
Does the
agent
understand
buying
books?
Form a plan
to buy the
book
Amazon
Barnes and
Nobel
B. Dalton
2 Days
$18.50
1 Day
$21.75
1 Day
$20.25
Dedicated
Agents
11
Simple Agent Example
Agent,
find me the book
“War and Peace,”
and I need it
tomorrow
Does the
agent
understand
buying
books?
Form a plan
to buy the
book
Amazon
Barnes and
Nobel
B. Dalton
2 Days
$18.50
1 Day
$21.75
1 Day
$20.25
Dedicated
Agents
Execute the
plan
Library 1 Day
Free
eBay 1 Day
$12.50
Agent
Communities
On-Line
www.online-literature.com
Now
Free
Use of Intelligent Agents at US
Pacific Command
VIPAR
13
USPACOM Command Virtual Information Center
Inside China
Russia Today
Jakarta Post
Unorganized Newspaper
Articles
Analysts Summary
CINC Summary
Manually gather
Information from
20–30 newspapers
Manually Organize
Information
Manually Analyze
And Summarize
Information
• Only 10% of available newspapers scanned
• Entirely manual operation
14
New Intelligent Agent Approach
Article
Retrieval
Agents
Organize and
summarize
Articles
Inside China
Russia Today
Jakarta Post
CINC Summary
Manually Analyze
And Summarize
Information
Automatically Gather,
Organize, and Summarize
Thousands of articles
Analysts Summary
• Capable of organizing 10,000 article per day
• Requires only a desktop computer
15
RDF Ontologies
VIPAR Architecture Overview
Multi-agent ORMAC Framework
Information
Agents

Whiteboard Agent
Cluster
Agent
Information
Agents
Information
Agents
Internet
Database
Agent
Communities
D1: D2: D3:
T1: 1 0 0
T2: 1 0 1
T3: 0 0 1
T4: 0 1 0
T5: 1 1 1
T6: 0 1 1
T7: 1 0 1
Text Analysis
Agent
Java Java RMI FIPA ACL
Agent
Communities
16
Clustering: A Simple Example
Document Title Key Terms
D1:
China Intercepts U.S.
Military Aircraft
China US Aircraft
Military
D2:
Russia to Extend Life of
Nuclear Military Fleet
Russia Nuclear Military
Fleet
D3:
U.S. -Based Chinese Military
Expert Denied Release
US China Military
Expert Release
T1: Aircraft
T2: China
T3: Expert
T4: Fleet
T5: Military
T6: Russia
T7: US
D1
D3
D2
1. Original and Parsed Documents 2. Terms Dictionary
7. Phylips tree representation
T
i j i j
T
i j
T
i j
Sij
( )( ) ( )( )
( )( )
     
 
  

     
 
D1: D2: D3:
T1: 1 0 0
T2: 1 0 1
T3: 0 0 1
T4: 0 1 0
T5: 1 1 1
T6: 0 1 1
T7: 1 0 1
3. Vector Space Model
4. Document Similarity
6. Agglomerative Hierarchical Clustering
1 2 3 4 8 6 7

 
k d
k 1
2
De(υ  i, υ  j) (υik υ jk)
5. Euclidean Distance
17
VIPAR “Nuclear Weapons” Search - 9/21/00
 Wen Ho Lee Spends First Day Savoring Home
Delights
 Lee Case Points up Scientists' Attitude
on Security
 India and Pakistan: Troubled relations
 U.S. China Trade Vote Milestone on Rocky
Road
 Troops die in Kashmir clashes
 Clinton Concerned Over Lee Case - Reno On
Defensive
 IAEA Supports Putin Nuclear Power
Initiative
 China Rejects Moves to Tighten Regulation
of Nuclear Materials
 Clinton Calls For Review Of Lee Secrets
Case
 Asian-Americans Demand White House Action
on Lee
How are these articles organized?
18
Manual Organization
“Business as Usual”
 Wen Ho Lee
1. Wen Ho Lee Spends First Day Savoring Home Delights
2. Clinton Calls For Review Of Lee Secrets Case
3. Clinton Concerned Over Lee Case - Reno On Defensive
4. Asian-Americans Demand White House Action on Lee
5. Lee Case Points up Scientists' Attitude on Security
 India and Pakistan
6. India and Pakistan: Troubled relations
7. Troops die in Kashmir clashes
 IAEA Meeting
8. IAEA Supports Putin Nuclear Power Initiative
9. China Rejects Moves to Tighten Regulation of Nuclear Materials
 U.S. China Trade
10. U.S. China Trade Vote Milestone on Rocky Road
19
VIPAR Automatic Organization
Same as manual
 Wen Ho Lee
1. Wen Ho Lee Spends First Day Savoring Home
Delights
2. Clinton Calls For Review Of Lee Secrets Case
3. Clinton Concerned Over Lee Case - Reno On
Defensive
4. Asian-Americans Demand White House
Action on Lee
5. Lee Case Points up Scientists' Attitude on
Security
 India and Pakistan
6. India and Pakistan: Troubled relations
7. Troops die in Kashmir clashes
 IAEA Meeting
8. IAEA Supports Putin Nuclear Power Initiative
9. China Rejects Moves to Tighten Regulation of
Nuclear Materials
 U.S. China Trade
10. U.S. China Trade Vote Milestone on Rocky
Road
1
3 2
4
5 6
7
8
9
10
Wen Ho Lee
India/Pakistan
IAEA Meeting
US China Trade
20
Endorsements
 US Pacific Command’s CINC Admiral Blair
 “A tremendously successful project”
 “Software agents … lead to substantially
improved analytical products.”
 Science and Technology Advisor
 “a grand slam home run!”
 “first time we've seen information discovery
and knowledge management software working
at HQ USCINCPAC operationally.”
21
Enhanced VIPAR Performance
 The Phylips Tree
representation of the
clustering of 1015
articles
 Required almost 360
second (6 minutes)
and 241 MB of
memory to compute
22
Battelle Funded VIPAR Upgrades
 Memory
 Evaluated caching of document title and
collection
 Optimized internal data structures
 Experimented with clustering partial articles.
 Applied Porter’s Stemming Algorithm
 Clustering Performance
 Clustering algorithm “Clusters in place”
 Hybrid clustering approach to large article sets
23
Result
 The Phylips Tree
representation of
the clustering of
9461 articles
 Required 2.5
minutes (137
seconds) and 495
MB of memory to
compute
24
Summary
 Intelligent agents are a significant future
technology direction
 We have a significant progression of
deployed agent systems and research to
our credit
 We have ringing endorsements regarding
the success of our systems and research
 We look forward to the next step…
25
Contact Information
Tom Potok
PotokTE@ornl.gov
865-574-0834
Mark Elmore
ElmoreMT@ornl.gov
865-241-6372
Jim Treadwell
JZT@ornl.gov
865-574-3350


About the author

160