Wrapper generation for semi-structured Internet sources
ACM SIGMOD Record
Database techniques for the World-Wide Web: a survey
ACM SIGMOD Record
A hierarchical approach to wrapper induction
Proceedings of the third annual conference on Autonomous Agents
Artificial Intelligence - Special issue on Intelligent internet systems
Introduction to Modern Information Retrieval
Introduction to Modern Information Retrieval
ICDE '95 Proceedings of the Eleventh International Conference on Data Engineering
A Real-Time Evolutionary Algorithm for Web Prediction
WI '03 Proceedings of the 2003 IEEE/WIC International Conference on Web Intelligence
A Generalized Site Ranking Model for Web IR
WI '03 Proceedings of the 2003 IEEE/WIC International Conference on Web Intelligence
Full-Coverage Web Prediction based on Web Usage Mining and Site Topology
WI '04 Proceedings of the 2004 IEEE/WIC/ACM International Conference on Web Intelligence
A Web based Conversational Case-Based Recommender System for Ontology aided Metadata Discovery
GRID '04 Proceedings of the 5th IEEE/ACM International Workshop on Grid Computing
Online Sequential Prediction via Incremental Parsing: The Active LeZi Algorithm
IEEE Intelligent Systems
Ontology-supported FAQ processing and ranking techniques
Journal of Intelligent Information Systems
How to combine CBR and RBR for diagnosing multiple medical disorder cases
ICCBR'05 Proceedings of the 6th international conference on Case-Based Reasoning Research and Development
Hi-index | 0.00 |
This paper discusses how ontology helps Web information processing in a multi-agent system to provide better Web services. We propose the ontology-supported solution integration and proxy techniques for Web information processing, which not only helps the user find out proper, integrated query results in accordance with his/her proficiency level or satisfaction degree, i.e., user-oriented solution, but supports proxy access of query solutions through a multi-agent system with a four-tier solution finding process. Our experiment shows around 79.1% of the user queries can be answered by Proxy Agent for solution application, leaving about 20.9% of the queries for the information preparation of Answerer Agent to take care, which not only can effectively alleviate the overloading problem that usually associated with a backend server, but can improve precision rate and produce better query solutions.