1. Intelligent Agents on the Internet and Web BY ROHIT SINGH MANHAS 070919048 M.C.A 4TH SEM. Dept. of I&CT, MIT, Manipal

2. Agents Intelligent Agents Characteristics of Intelligent Agents Classes of Intelligent Agents Classification and Application of Intelligent Agents Agent Services Conclusion References

3. Dept. of I&CT, MIT, Manipal An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through its effectors to maximize progress towards its goals. Human agent: eyes, ears, and other organs for sensors; hands, legs, mouth, and other body parts for actuators Robotic agent: cameras and infrared range finders for sensors; various motors for actuators Agents

4. Dept. of I&CT, MIT, Manipal Agents interact with environments through sensors and effectors

5. Dept. of I&CT, MIT, Manipal Intelligent Agent (IA) An intelligent agent (IA) is a self-contained, autonomous software module that could perform certain tasks on behalf of its users with some degree of independence or autonomy, and in so doing, employ some knowledge or representation of the user's goals or desires. Intelligent Agent The term agent is derived from the concept of agency, referring to employing someone to act on your behalf.

6. Dept. of I&CT, MIT, Manipal Characteristics of Intelligent Agents Autonomy or empowerment – An agent that takes initiative and exercises control over its own actions have these characteristics: Goal oriented Collaborative Flexible Self-starting

7. Dept. of I&CT, MIT, Manipal Communication (interactivity) – Many agents are designed to interact with other agents, humans, or software programs Automating repetitive tasks – An agent is designed to perform narrowly defined tasks, which it can do over and over without getting bored or sick or going on strike

8. Dept. of I&CT, MIT, Manipal Reactivity – Agents perceive their environment and respond in a timely fashion to changes that occur in it Proactiveness (or persistence) – Agents are able to exhibit goal-directed behavior by taking initiative Temporal continuity – Agents are continuously running processes that can be temporarily inactive while waiting for something to occur

9. Dept. of I&CT, MIT, Manipal Why Intelligent Agents? Information overload – A major value of intelligent agents is that they are able to assist in searching through all the data – Intelligent agents save time by making decisions about what is relevant to the user on its behalf Reasons for the success of agents – Decision support – Frontline decision support – Repetitive office activities – Mundane personal activity – Search and retrieval – Domain experts

10. Dept. of I&CT, MIT, Manipal Classes of intelligent agents Simple Reflex agents Model-based reflex agents Goal-based agents Utility-based agents

11. Dept. of I&CT, MIT, Manipal Simple Reflex Agents Simple reflex agents acts only on the basis of the current percept. The agent function is based on the condition-action rule: if condition then action rule

12. Dept. of I&CT, MIT, Manipal Percepts: location and contents, e.g., [A, Dirty] Actions: Left, Right, Suck. Vacuum-cleaner world Function REFLEX-VACUUM-AGENT ([location, status]) returns action if status = Dirty then return Suck else if location = A then return Right else if location = B then return Left

13. Dept. of I&CT, MIT, Manipal Model-Based Reflex Agents A model-based reflex agent keeps track of the current state of the world using an internal model. It then chooses an action in the same way as the reflex agent.

14. Dept. of I&CT, MIT, Manipal Function REFLEX-AGENT-WITH-STATE (percept) returns an action static: state, a description of the current world state rules, a set of condition-action rules action, the most recent action, initially none state  UPDATE-STATE (state, action, percept) rule  RULE-MATCH(state, rules) action  RULE-ACTION[rule] return action

15. Dept. of I&CT, MIT, Manipal Goal-Based Agents Goal-based agents are model-based agents which store information regarding situations that are desirable. This allows the agent a way to choose among multiple possibilities, selecting the one which reaches a goal state.

16. Dept. of I&CT, MIT, Manipal Utility-Based Agents Goal-based agents only distinguish between goal states and non-goal states. It is possible to define a measure of how desirable a particular state is. This measure can be obtained through the use of a utility function which maps a state to a measure of the utility of the state.

17. Dept. of I&CT, MIT, Manipal Utility-Based Agents

18. Dept. of I&CT, MIT, Manipal Classification of Intelligent Agents 1.Mobile Agents 2.Interface Agents 3.Multi-Agent System (MAS) 4.Information/Internet Agents 5.Learning Agents

19. Dept. of I&CT, MIT, Manipal APPLICATIONS OF INTELLIGENT AGENTS ON THE INTERNET AND WEB Agent-Based Information Retrieval 1.Information Explosion 2.Interfaces 3.Mediated Searches and Information Brokers 4.Information Filtering Agents

20. Dept. of I&CT, MIT, Manipal Agents in Electronic Commerce Helping the user decide which products to buy Finding specifications and reviews of them. Making recommendations Comparison shopping to find the best price for the desired product. Watching for and-intimating user about special offers and discounts.

21. Dept. of I&CT, MIT, Manipal Agent Services Announcement Agents Book Agents Business Information Monitoring Agents Classified Agents Job Agents Financial Service Agents Entertainment Agents

22. Dept. of I&CT, MIT, Manipal CONCLUSION Intelligent agents on the Internet and Web will grow dramatically in the next few years and they would be put into use in a variety of new applications and services. The following quotes aptly highlight the prospects of intelligent agents. “Agents are here to stay... because of their diversity, their wide range of applicability and the broad spectrum of companies investing in them.” “In the future, it [agent] is going to be the only way to search the Internet, because no matter how much, better the Internet is going to be organised, it can’t keep pace with information.”

23. Dept. of I&CT, MIT, Manipal REFERENCES AND RESOURCES 1.Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig, 1995 Prentice-Hall, Inc. 2.Bradshaw, J. M (ed.,), 1997. Software Agents, Menlo Park, CA: AAAI/MIT Press, 1997 3.IEEE Internet Computing, Vol. I, No. 3, July –August 1997, Special Issue on Internet-Based Agents. 4.Communications of the ACM Journal "Intelligent Agents"Vo1.37, No.7, July 1994 5.Comm. of the ACM 1994, Special Issue on Intelligent Agents, July 1994. 6.http://en.wikipedia.org/wiki/Encyclopedia

24. Dept. of I&CT, MIT, Manipal THANK YOU !!!