Beruflich Dokumente
Kultur Dokumente
By
Anand Kumar
1
Intelligent Software Agents:
An Overview
Intelligent Agent (IA): Computer program that helps a user
with routine computer tasks
New Technology
Other Names
Software agents
Wizards
Knowbots
Intelligent software robots
Softbots
Bots
2
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”)
3
More Definitions
A persistent software entity dedicated to a specific purpose.
“Persistent” distinguishes agents from subroutines; agents have
their own ideas about how to accomplish tasks, e.g., their own
agenda. “Special purpose” distinguishes them from entire
multifunction applications; agents are typically much smaller”
(Smith et al., 1994)
4
Introduction
Little bit history.
5
Introduction
Agents
Many definitions:
6
Introduction
Categories of agents (just one of them)
Autonomous Agents
Task-specific Agents
Entertainment Agents Viruses
7
Types of Software Agents
Static (Computer Bound)
Stationary agents do not roam around the online world
but use embedded knowledge to assist in filtering and
processing the volume of incoming information.
Agent becomes dormant until the next event arri
Mobile
Execute commands while living on a remote server,
reporting back to home page when given task is
accomplished
Carry out transactions without further input from the
consumer .
8
Why Software Agents
Managing the information overload
Decision support
Repetitive office activity
Mundane personal activity
Search and retreival
Domain experts
9
Properties of mobile software agents
Programming
Safety
Resource usage
Navigation
Privacy
Communication
10
General characteristics of Software
Agents
Independent Agency
Agent learning
Agent cooperation
Agent reasoning capability
Rule based approach
Knowledge based approach
Learning approach
Agent interface
11
Technology behind Software Agents
Components of a software agent
Owner
Author
Lifetime
Account
Goal
Subject description
Background
12
Technology behind Software Agents
Components of the agent computing
environment
User preferences
Knowledge of what is where
13
Technology behind Software Agents
Telescript
Agent Language
SAFE-TCL (Tool Command Language)
14
Software agents in action
Software advisors
Customer service help desk
Event monitors
System and Network Management
Work-flow assistants and Smart Messaging
Software Agents and Resource Discovery
Scale of problem
Need for cooperative brokerages
Need for resource planning
15
Why Intelligent Agents?
Information Overload
Data doubles annually (in large enterprises (1998))
Can analyze only about 5%
Most efforts: discover patterns, not meaning, not what to do
Reduces decision making capabilities by 50%
16
Internet-based Software Agents
Software Robots or Softbots
Major Categories
17
Network Management and Monitoring
18
Electronic Commerce Agents
Need identification
Product brokering
Merchant brokering
Negotiation
Purchase and delivery
Product/service evaluation
19
Other Agents
Operating systems agents
Supply chain management agents
Spreadsheet agents
Workflow and administrative management
agents
Competitive intelligence agents
Software development agents
Data mining / Web mining agents
Monitoring and alerting agents
Collaboration agents
20
Operating Systems Agents
Wizards in Microsoft Windows NT Operating Systems
Add user accounts
Group management
Managing file and folder access
Add printer
Add/remove programs
Network client administrator
Licenses
Install new modems
Spreadsheet agents: make software more friendly
21
Workflow and Administrative
Management Agents
Example - FlowMark
Software development
Many routine tasks can be done or supported by agents
22
A Multiagent System for Travel Arrangements
Buyer Sellers
Car Rental
Companies
Airlines
Hotels
Hotel Agents
23
Managerial Issues
Cost Justification
Security
Privacy
Industrial Intelligence and Ethics
Other Ethical Issues
Agent Learning
Agent Accuracy
Heightened Expectations
System Acceptance
System Technology
Strategic Information Systems
24
Conclusions
Agents can simplify our use of computers
25
But: Danger!
Agents are unlike other technological advances
26
Can Eliminate Such Problems
Develop rules for well-behaving agents
27