« PreviousContinue »
(12) United States Patent ao) Patent No.: us 6,304,864 Bi
Liddy et al. (45) Date of Patent: Oct. 16,2001
(54) SYSTEM FOR RETRIEVING MULTIMEDIA INFORMATION FROM THE INTERNET USING MULTIPLE EVOLVING INTELLIGENT AGENTS
(75) Inventors: Elizabeth D. Liddy, Syracuse;
Edmund Szu-Li Yu, Dewitt, both of
(73) Assignee: Textwise LLC, Syracuse, NY (US)
( * ) Notice: Subject to any disclaimer, the term of this patent is extended or adjusted under 35 U.S.C. 154(b) by 0 days.
(21) Appl. No.: 09/295,190
(22) Filed: Apr. 20, 1999
(51) Int. C I. G06F 9 445
(52) U.S. C I 706/15
(58) Field of Search 707/4; 706/20,
(56) References Cited
U.S. PATENT DOCUMENTS
5,086,479 2/1992 Takenaga et al. .
5,140,530 8/1992 Guha et al. .
(List continued on next page.)
FOREIGN PATENT DOCUMENTS
0845748A2 6/1998 (EP) . WO 96/23265 8/1996 (WO) . WO 98/02825 1/1998 (WO) .
Intelligent Software Agents on the Internet, by Bjorn Hermans vol. 2 No. 3—Mar. 3rd, 1997 www.google.com.* Using an Intelligent Agent to Enhance Search Engine Performance, by James Jansen www.google.com.*
(List continued on next page.)
Primary Examiner—Mark R. Powell
Assistant Examiner—Michael B. Holmes
(74) Attorney, Agent, or Firm—Kenneth J. LuKacher (57) ABSTRACT
A system for retrieving multimedia information is provided using a computer coupled to a computer-based network, such as the Internet, and particularly the World Wide Web (WWW). The system includes a web browser, a graphic user interface enabled through the web browser to allow a user to input a query representing the information the user wishes to retrieve, and an agent server for producing, training, and evolving first agents and second agents. Each of the first agents retrieves documents (Web page) from the network at a different first network address and at other addresses linked from the document at the first network address. Each of the second agents executes a search on different search engines on the network in accordance with the query to retrieve documents at network addresses provided by the search engine. The system includes a natural language processor which determines the subject categories and important terms of the query, and of the text of each agent retrieved document. The agent server generates and trains an artificial neural network in accordance with the natural language processed query, and embeds the trained artificial neural network in each of the first and second agents. During the search, the first and second agents process through their artificial neural network the subject categories and important terms of each document they retrieve to determine a retrieval value for the document. The graphic user interface displays to the user the addresses of the retrieved documents which are above a threshold retrieval value. The user manually, or the agent server automatically, selects which of the retrieved documents are relevant. Periodically, the artificial neural network of the first and second agents is expanded and retrained by the agent server in accordance with the selected relevant documents to improve their ability to retrieve documents which may be relevant to the query. Further, the agent server can evolve an artificial neural network based on the current artificial neural network, the retrieved documents, and their selected relevancy, by iteratively producing, training, and testing several generations of neural networks to produce an evolved agent. The artificial neural network of the evolved agent then replaces the current artificial neural network used by the agents to search the Internet. One or more concurrent search of the Internet may be provided.
24 Claims, 8 Drawing Sheets
Excerpts from A. Clark, Being There, MIT Press, 1997.* Sheth, B. et al., Evolving Agents for Personalized Information Filtering, Proc. of the 9th Conf. on Artificial Intelligence for Applications, Mar. 1993, pp. 345-352. E.B. Baum and D. Haussler, What size net gives valid generalization? Neural Computation, vol. 1; pp. 151-160, 1989.
E. Carmel, S. Crawford, & H. Chen, Browsing in hypertext: A cognitive study, IEEE Transactions on Systems, Man and Cybernetics, vol. 22, pp. 865-884, 1992. Y. Chauvin and D.E. Rumelhart (eds.) ackpropagation: theory, architectures, and applications, Lawrence Erlbaum Associates, Hillsdale, N.J., pp. 1-34, 1995. H. Chen, Y. Chung, and M. Ramsey, Asmart itsy bitsy spider for the Web, Journal of the American Society for Information Science, vol. 49, No. 7, pp. 604-618, 1998. L. Chen and K. Sycara, Webate: A personal agent for browsing and searching, Proceedings of Autonomous Agents 98, pp. 132-138, 1998.
G. Cybenko, Approximation by superposition of a sigmoidal function, Mathematics of Control, Signals and Systems, vol. 2, pp. 303-314, 1989.
Scott Deerwester, Next Generation of Search Engines and Find Their Feet. Financial Times (London Edition), Financial Times: London, England, pp. 14, Aug. 26, 1996.
H. Funahashi, On the approximate realization of continuous mapping by neural networks. Neural Networks, vol. 2, pp. 183-192, 1989.
H. Funahashi, Multilayer neural networks and Bayes decision theory, Neural Networks, vol. 11, pp. 209-213, 1998 W.B. Frakes and R. Baeza-Yates (eds.), Information retrieval: data structures & algorithms, Prentice Hall, Englewood Cliff, N.J., pp. 113-116, 151-160, 1992. V. Harmandas, M. Sanderson, and M.D. Dunlop, Image retrieval by hypertext links, Proceedings of ACM SIGIR '97 conference,, pp. 296-303, 1997.
K. Hornik, Multilayer feedforward networks are universal approximators, Neural Networks, vol. 2, pp. 359-366,1989. T. Joachims, D. Freitag, and T. Mitchell, Web Watcher: A tour guide for the World Wide Web, Proceedings of IJCAI 97, 1998.
E.D. Lindy, W. Paik, E.S. Yu, and M. McKenna, A Natural Language Text Retrieval System with Relevance Feedback Proceedings of the 16th National Online Meeting, pp. 259-261, 1995.
E.D. Liddy, W. Paik, E.S. Yu, and M.E. McKenna, Docu-
ment retrieval using linguistic knowledge. Proceedings of
RIAO '94 Conference, pp. 106-114, 1994.
E.D. Liddy, W. Paik, and E.S. Yu, Text catergorization for
multiple user based on semantic Information from a MRD,
ACM Transactions on Information Systems, vol. 12, No. 3,
pp. 278-295, 1994.
M. Mitchell, An introduction to genetic algorithms, MIT
Press, Cambridge, MA, pp. 8-10, 27-31, 65-79, 1996.
D. Michie, D.J. Spiegelhalter, and C.C. Taylor (eds.),
Machine Learning, Neural and Statistical Classification,
Ellis Horwood, Ltd., pp. 131-146, 152-154, 1994.
H.S. Nwana and D.T Ndumu, An introduction to agent
technology, Software Agents and Soft Computing, Springer,
Berlin, pp. 3-26, 1997.
H.S. Nwana, Software agents: an overview, Knowledge
Engineering Review, vol. 11, No. 3, pp. 205-244, 1996.
M. Pazzani and D. Billsus, Learning and revising user
profiles: the identification of interesting Web sites. Machine
learning, vol. 27, 313-331, 1997.
M. Pazzani, J. Muramatzu, D. Billsus, Syskill & webert: identifying interesting web sites. Proceedings of AAAI conference, 1996.
H. Schutze, D.A. Hull, and J.O. Pedersen, A Comparison of Classifiers and Document Representations for the Routing Problem. Proceedings of ACM SIGIR '95 conference, pp. 229-237, 1995.
Laura Smith, Search Tool Time, PC Week, PC Week: New York, NY, pp. 22, Jul. 15, 1996.
H. White, Connectionist nonparametric regression: multilayer feedforward networks can learn arbitrary mappings, Neural Networks, vol. 3, pp. 535-549, 1990.
Autonomy, Inc. website at www.agentware.com, printed Jul. 1999.
Metabot Search Engine web page at metabot.kinetoscope.com/docs/docs.html, printed Jul. 1999.
Wise Wire Corp. Website at www.wisewire.com, printed Jul. 1999.
Autonomy Agentware Technology White Paper, Autonomy Inc., 1998.
Smart Agents Outsmart Search Engines, Newsbytes News Network, Apr. 9, 1998.
EVA Evolving intelligent text-based Agents for geospatial information, at www. textwise.com/eva.html, Jul. 1997.
Jeffrey M. Bradshaw, Software Agents, AAAI Press/The MIT Press, Menlo Park, Calif., Chapter I.
Agents Technologies Introduces Industry's Most Extensive Professional Search Tool, Business Editors & Computer Writers, Business Wire, Mar. 11, 1998.
* cited by examiner