Font Size: a A A

NKI Knowledge Interface: Realizing Dialogue Between People And Knowledge

Posted on:2002-05-27Degree:MasterType:Thesis
Country:ChinaCandidate:D H FengFull Text:PDF
GTID:2178360185495611Subject:Computer application technology
Abstract/Summary:PDF Full Text Request
Compared to an industrial society, need of knowledge from enterprises, families and persons in a knowledge-driven one is increasing greatly. A National Knowledge Infrastructure (NKI for short) is being built to provide an effective knowledge service for people in general and a knowledge foundation for hi-tech products in particular. The main purpose of this work is to design and implement a knowledge interface between people and knowledge in NKI.Because NKI will contain knowledge from the Chinese encyclopedia consisting of 71 disciplines within 74 volumes, we encounter the following three difficulties in realizing the knowledge interface:First, how to make the knowledge interface independent of disciplines? Knowledge requests from people may involve a specific discipline. We cannot afford to design a knowledge interface for each discipline. Therefore, our knowledge interface must be general-purpose, and must understand requests of knowledge from different disciplines and respond to them properly.Second, how to provide people with the sufficient freedom of query? Communicating in natural language is very important from the standpoint of people. However, natural language queries may be too complicated and ambiguous that they may not be properly understood and processed by the knowledge interface.Third, how to search the huge NKI knowledge base for the right answers? NKI is extraordinarily large, and knowledge about a concept, fact or statement may appear in different forms. Therefore, the knowledge interface should be able to retrieve and differentiate the right knowledge from several possibilities.This thesis contributes in the following aspects:A compact knowledge model, called Concept-Relation Model (or CR model for...
Keywords/Search Tags:National knowledge infrastructure, knowledge interface, fuzzy pattern matching, knowledge retrieval, semantics checking, knowledge reconstruction
PDF Full Text Request
Related items