Transcript Intelligent Agents

WEEK 10
Intelligent (Software) Agents
1
Case Scenario
Every year, ABC Enterprise will conduct annual general meeting
(AGM) to report company performance to their shareholders.
However, before the meeting is carry out, the CEO of the
company; Mr. Ridzuan would like to know what other agendas
that should be bring forward. Unfortunately, the job which is
usually performed by his secretary is on leave due to illness.
Thus, Mr. Ridzuan is thinking whether there is any system that
can be built to replace its secretary job in contacting and
collecting agendas information through email from their
shareholders. The system also must be able to summarize all the
agendas suggested by their shareholders and presented it to the
CEO in the report form.
2
Intelligent Agents

Intelligent Agent (IA): Computer program
that helps a user with routine computer
tasks.

Other Names:






Software agents
Wizards
Knowbots
Intelligent software robots
Softbots
Agent: Someone employed to act on one’s behalf.
3
Definitions of Intelligent Agent

“Intelligent agents are software entities that
carry out some set of operations on behalf of
a user or another program, with some degree
of independence or autonomy and in so doing,
employ some knowledge or representation of
the user’s goals or desires.” (“The IBM
Agent”)
4
Intelligent Agent Characteristics

Autonomy (empowerment)
Agent takes initiative, exercises control over its actions





Goal-oriented
Collaborative
Flexible
Self-starting
Mobility (operates in the background)

Mobile agents
5
Agent Classification and Types
Autonomous agents
Biological agents
Robotic agents
Software agents
Task-specific agents
Computational agents
Artificial life agents
Entertainment agents
Viruses
6
Why Intelligent Agents?
Information Overload!!

Data doubles annually (in large enterprises)




Much caused by the Internet/Web




Can analyze only about 5%
Most efforts: discover patterns, not meaning, not what to do
Reduces decision making capabilities by 50%
How to filter data
How to identify relevant sources of data
Intelligent agents can assist searching (information)
Save time: agents decide what is relevant to the user
7
Classification by Application Area







Assist in workflow and administrative
management
Collaborate with other agents and individuals
Support electronic commerce
Support desktop applications
Assist in information access and management
Process mail and messages
Manage systems and networks
8
Internet-based Software Agents
Software Robots or Softbots
Major Categories:






E-mail agents (mailbots)
Web browsing assisting agents
Frequently asked questions (FAQ) agents
Intelligent search (or Indexing) agents
Internet softbot for finding information
Network Management and Monitoring
9
Electronic Commerce Agents






Need identification
Product brokering
Merchant brokering
Negotiation
Purchase and delivery
Product/service evaluation
10
Other Agents







Operating systems agents
Spreadsheet agents
Workflow and administrative management
agents
Software development agents
Data mining / Web mining agents
Monitoring and alerting agents
Collaboration agents
11
Monitoring and Alerting:
NewsAlert


Monitors data by personalized rules
Automatically delivers alerts to the user’s desktop into
personalized newspapers

Organizes alerts by user-specified subject areas

Provides smart tools so users can investigate the context
of an alert and communicate findings to others
12
Distributed AI, Multiagents, and
Communities of Agents






Software agents must communicate, cooperate and
negotiate with each other
Refine requests and queries through evolving dialogue
Intelligent agents work together in multiple agent systems
Agents can communicate, cooperate and/or negotiate
Easy to build agents with small specialized knowledge
Agents need to share their knowledge
13
A Multi-Agent System for Travel Arrangements
Buyer
Sellers
Car Rental
Companies
Car Rental Agents
Airlines
User
Agent
Airline Agents
Hotels
Hotel Agents
14
Agents Portal

AgentLand


BotSpot


http://www.agentland.com
http://www.botspot.com/index2.html
AgentWeb

http://agents.umbc.edu
15
Intelligence Density Dimension




Flexibility
Embeddedability
Ease of use
Speed / reliability of response time
16