PRIMA 2005: Multi-Agent Systems for Society pp 22-32 | Cite as
A Co-operative Intelligent Assisting Agent Architecture for Web Searching and Desktop Management
Abstract
The rapid growth in technology has made the computer a vital tool for a wide variety of applications. Software that aids the common user in performing routine computing chores have now become commonplace. With the Internet growing rapidly, numerous new sites are coming into existence each day. This necessarily means that a user has to spend more time and energy to search for a particular piece of information. The need of the day is to develop software that can act more like a human assistant, understanding and learning a user’s behavior to emulate and aid him to carry out his task in a simpler and easier manner. Presented in this paper is one such architecture wherein agents inhabit the desktop, monitor user behavior and over a period of time learn to adapt and take over routine tasks. Embedded on the Microsoft Windows 2000 desktop, the agents in this architecture work co-operatively with one another to provide desktop management and intelligent web surfing support.
Keywords
User Profile User Feedback Virtual Space Agent Architecture Agent ApplicationPreview
Unable to display preview. Download preview PDF.
References
- 1.Brenner, W., Zarnekow, R., Wittig, H.: Intelligent Software Agents, Foundations and Applications, pp. 19–53. Springer, Heidelberg (1998)CrossRefMATHGoogle Scholar
- 2.Aas, K.: A Survey on Personalized Information Filtering Systems for the World Wide Web, Report no. 992, Norwegian Computing Center (December 1997), http://www.nr.no/~kjersti/agent.html
- 3.Microsoft Agents, http://www.microsoft.com/msagent/
- 4.Chen, L., Sycara, K.: A Personal Agent for Browsing and Searching. The Robotics Institute Carnegie Mellon University Pittsburgh, PA. 15213 (September 2001)Google Scholar
- 5.Hoffmann, F.: Machine-Learning. Lecture Notes, Course no- 2D5362, Fall 2000, NADA, Stockholm University (2000)Google Scholar
- 6.Harmon, M.E., Harmon, S.S.: Reinforcement Learning. A Tutorial. Wright State University (1996), http://citeseer.nj.nec.com/harmon96reinforcement.html
- 7.Reinforcement Learning Repository at Umass, Amherst, http://www-anw.cs.umass.edu/rlr/
- 8.Sheth, B.D.: A learning approach to Personalized Information Filtering, Masters Thesis, Dept of Electrical Engineering and Computer Science, M.I.T, 994, http://www.dfki.de/~allen/People/Stu/Sheth/
- 9.Kuflik, T., Shoval, P.: User Profile Generation for Intelligent Information Agents. In: Proc. of 23rd annual International ACM SIGIR Conference on research and development in IR, Athens, Greece, pp. 313–315 (2000)Google Scholar
- 10.Rao, A.S., Georgeff, M.P.: BDI Agents: From Theory to Practice., Australian Artificial Intelligence Institute, Technical Note 56 (April 1995)Google Scholar
- 11.Lashkari, Y., Metral, M., Maes, P.: Collaborative Interface Agents. In: Proc. of 12 th National Conference on Artificial Intelligence, vol. 2, pp. 444–449. AAAI Press, Menlo Park (1994)Google Scholar
- 12.Cohen, P.R., Cheyer, A., Wang, M., Baeg, C.S.: An Open Agent Architecture. In: Proc. of the AAA1 Spring Symposium Series on Software Agents, pp. 1–8. Stanford University (1994)Google Scholar
- 13.Wood, A.: Towards a Medium for Agent-Based Interaction, Thesis Proposal PR-9415, University of Bermingham (October 12, 1994)Google Scholar
- 14.Abu–Mostafa, Y.S.: Machine that learns from hints. Scientific American 272(4), 64–69 (1995)CrossRefGoogle Scholar
- 15.Guerre Ercolini, D.A., Kokar, M.M.: Desktop Agent Manager (DAM) Decision Mechanism. International Journal of Human-Computer Interaction 9(2), 133–149 (1997)CrossRefGoogle Scholar
- 16.Grosof, B.N.: Conflict Resolution in Advice Taking and Instruction for Learning Agents., IBM Research Report RC 20123Google Scholar
- 17.Zadeh, L.A.: Fuzzy Logic, neural network and soft computing. Communications of the ACM 37(3), 77–84 (1994)CrossRefGoogle Scholar