Waes2105 S10


Published on

Published in: Business, Technology
  • Be the first to comment

  • Be the first to like this

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Waes2105 S10

  1. 1. WEEK 10 Intelligent (Software) Agents
  2. 2. Case Scenario <ul><li>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. </li></ul>
  3. 3. Intelligent Agents <ul><li>Intelligent Agent (IA): Computer program that helps a user with routine computer tasks. </li></ul><ul><li>Other Names: </li></ul><ul><ul><li>Software agents </li></ul></ul><ul><ul><li>Wizards </li></ul></ul><ul><ul><li>Knowbots </li></ul></ul><ul><ul><li>Intelligent software robots </li></ul></ul><ul><ul><li>Softbots </li></ul></ul><ul><li>Agent : Someone employed to act on one’s behalf. </li></ul>
  4. 4. Definitions of Intelligent Agent <ul><li>“ 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”) </li></ul>
  5. 5. Intelligent Agent Characteristics <ul><li>Autonomy (empowerment) </li></ul><ul><li>Agent takes initiative, exercises control over its actions </li></ul><ul><ul><li>Goal-oriented </li></ul></ul><ul><ul><li>Collaborative </li></ul></ul><ul><ul><li>Flexible </li></ul></ul><ul><ul><li>Self-starting </li></ul></ul><ul><li>Mobility (operates in the background) </li></ul><ul><ul><li>Mobile agents </li></ul></ul>
  6. 6. Agent Classification and Types Autonomous agents Software agents Computational agents Task-specific agents Artificial life agents Robotic agents Biological agents Entertainment agents Viruses
  7. 7. Why Intelligent Agents? <ul><li>Information Overload!! </li></ul><ul><li>Data doubles annually (in large enterprises) </li></ul><ul><ul><li>Can analyze only about 5% </li></ul></ul><ul><ul><li>Most efforts: discover patterns, not meaning, not what to do </li></ul></ul><ul><ul><li>Reduces decision making capabilities by 50% </li></ul></ul><ul><li>Much caused by the Internet/Web </li></ul><ul><ul><li>How to filter data </li></ul></ul><ul><ul><li>How to identify relevant sources of data </li></ul></ul><ul><li>Intelligent agents can assist searching (information) </li></ul><ul><li>Save time: agents decide what is relevant to the user </li></ul>
  8. 8. Classification by Application Area <ul><li>Assist in workflow and administrative management </li></ul><ul><li>Collaborate with other agents and individuals </li></ul><ul><li>Support electronic commerce </li></ul><ul><li>Support desktop applications </li></ul><ul><li>Assist in information access and management </li></ul><ul><li>Process mail and messages </li></ul><ul><li>Manage systems and networks </li></ul>
  9. 9. Internet-based Software Agents <ul><li>Software Robots or Softbots </li></ul><ul><li>Major Categories: </li></ul><ul><li>E-mail agents (mailbots) </li></ul><ul><li>Web browsing assisting agents </li></ul><ul><li>Frequently asked questions (FAQ) agents </li></ul><ul><li>Intelligent search (or Indexing) agents </li></ul><ul><li>Internet softbot for finding information </li></ul><ul><li>Network Management and Monitoring </li></ul>
  10. 10. Electronic Commerce Agents <ul><li>Need identification </li></ul><ul><li>Product brokering </li></ul><ul><li>Merchant brokering </li></ul><ul><li>Negotiation </li></ul><ul><li>Purchase and delivery </li></ul><ul><li>Product/service evaluation </li></ul>
  11. 11. Other Agents <ul><li>Operating systems agents </li></ul><ul><li>Spreadsheet agents </li></ul><ul><li>Workflow and administrative management agents </li></ul><ul><li>Software development agents </li></ul><ul><li>Data mining / Web mining agents </li></ul><ul><li>Monitoring and alerting agents </li></ul><ul><li>Collaboration agents </li></ul>
  12. 12. Monitoring and Alerting: NewsAlert <ul><li>Monitors data by personalized rules </li></ul><ul><li>Automatically delivers alerts to the user’s desktop into personalized newspapers </li></ul><ul><li>Organizes alerts by user-specified subject areas </li></ul><ul><li>Provides smart tools so users can investigate the context of an alert and communicate findings to others </li></ul>
  13. 13. Distributed AI, Multiagents, and Communities of Agents <ul><li>Software agents must communicate , cooperate and negotiate with each other </li></ul><ul><li>Refine requests and queries through evolving dialogue </li></ul><ul><li>Intelligent agents work together in multiple agent systems </li></ul><ul><li>Agents can communicate , cooperate and/or negotiate </li></ul><ul><li>Easy to build agents with small specialized knowledge </li></ul><ul><li>Agents need to share their knowledge </li></ul>
  14. 14. A Multi-Agent System for Travel Arrangements
  15. 15. Agents Portal <ul><li>AgentLand </li></ul><ul><ul><li>http://www.agentland.com </li></ul></ul><ul><li>BotSpot </li></ul><ul><ul><li>http://www.botspot.com/index2.html </li></ul></ul><ul><li>AgentWeb </li></ul><ul><ul><li>http://agents.umbc.edu </li></ul></ul>
  16. 16. Intelligence Density Dimension <ul><li>Flexibility </li></ul><ul><li>Embeddedability </li></ul><ul><li>Ease of use </li></ul><ul><li>Speed / reliability of response time </li></ul>