Knowledge network semi-automatic generation method

Abstract

The invention discloses a knowledge network semi-automatic generation method. The method comprises the following steps: (1) firstly forming a knowledge network kernel; (2) utilizing single text knowledge discovering and extracting unit to receive a nonstructural document, discovering knowledge points to be concerned from nonstructural text data by virtue of a participle and named entity recognition technology, and extracting the knowledge points; (3) placing new knowledge in corresponding positions to serve as candidate knowledge after carrying out knowledge discovery and extraction on a plurality of documents; and (4) submitting the candidate knowledge to a corresponding expert system by a knowledge network operation platform to determine the correlativity, selecting the candidate knowledge with the determination result of yes as the confirmed knowledge, and discarding the candidate knowledge with the determination result of no. Starting from a small knowledge network kernel, the knowledge network semi-automatic generation method provided by the invention can be used for automatically discovering, extracting and organizing the knowledge from massive data from the internet througha computer so as to rapidly and effectively construct the knowledge network structure after the knowledge is confirmed by the expert system.

Description

technical field [0001] The invention relates to a method for semi-automatically generating a knowledge network (Knowledge Network) facing massive text data, and belongs to the technical field of text information processing. Background technique [0002] Text is the most basic and commonly used information carrier. With the increasing popularity of the Internet, text information expands rapidly. For example, hundreds of thousands of web pages are updated every day on the Internet, and millions of new web pages are added, making the information on the Internet rich and complex. On the other hand, new knowledge is constantly appearing (such as "Influenza A H1N1"), old knowledge is constantly disappearing (such as "Walkman"), and existing knowledge is constantly changing its meaning (such as "push-ups"). Therefore, how to effectively organize and manage this information, and quickly, accurately, and comprehensively find the information that users need is a major challenge in t...

AI Technical Summary

Problems solved by technology

[0007] However, the above-mentioned patent application can only solve the structural problem of massive text data to a certain extent, and does not have the ability to directly generate knowledge networks

At present, if people want to generate a knowledge network, they must rely on the intellectual judgment of the human brain, so it takes a long time and the work efficiency is low

Especially in the face of massive text data, relying solely on manpower to generate knowledge networks is difficult to meet the actual needs of users

Images