Intelligent agents
|
|
Intelligent Agents (Bots) are software elements that work without the assistance of users by making choices. Choices are based on rules that software developers have identified and built into the software. It is expected that Intelligent Agents will be a strong focus for AI development in years to come, in order to help automate simple tasks.
There are several different classes of intelligent agents.
| Contents |
Buyer Agents (Shopping Bots)
These bots help internet surfers find products and services they are searching for. For example, when a person surfs for an item on eBay (http://www.ebay.com), at the bottom of the page there is a list of similiar products that other customers who did the same search looked at. This is because it is assumed the user tastes are relatively similar and they will be interested in the same products.
User Agents (Personal Agents)
These agents are carry out tasks automatically for the user. For example, some bots sort emails according to the user's order of preference, assemble customized news reports (e.g. newshub (http://www.newshub.com)), or fill out webpage forms with the user's stored information.
Monitoring-and-surveillance (Predictive) Agents
These agents are used to observe and report on equipment, usually computer systems. For example, the agents keep track of company inventory levels, observe competitors' prices and relay them back to the company, watch stock manipulation by insider trading and rumors, etc.
Data Mining Agents
This agent uses information technology to find trends and patterns in an abundance of information from many different sources. The user can sort through this information in order to find whatever information they are seeking. An example of this class of bot would be a data mining agent that detects market conditions and changes and relays them back to a user/company so that the user/company can make decisions accordingly. For example, the agent may detect a decline in the construction industry for an economy; based on this relayed information construction companies will be able to make intelligent decisions regarding the hiring/firing of employees or the purchase/lease of equipment in order to best suit their firm.
Other examples
Some other examples of current Intelligent Agents include some spam filters, game bots, and server monitoring tools. Search engine indexing bots also qualify as intelligent agents. More examples can be found at BotSpot (http://www.botspot.com).
Outline of an agent
--- the following content is based on Ch2 of "An introduction to multiagent systems" by Michael Wooldridge ---
- Definition of Agent:
"An agent is a computer system that is situated in some environment, and that is capable of autonomous action in this environment in order to meet its design objectives". (Wooldridge & Jennings, 1995)
- capabilities of Intelligent agents
* reactivity: perceive their environment and respond to surrounding changes * proactiveness: goal-directed behaviour * social ability:interact with other agents
- Agents vs. Objects
* agents are more autonomous than object, decide what to do to achieve a goal * agents have flexible behaviour: reactive, proactive, social. * agents have at least one thread of control
- Agents vs. Expert Systems
* expert systems are not coupled to their environment * Agents are capable of reactive, proactive behaviour. * Expert systems do not consider social ability