Knowledge discovery device based on path migration of RDF (Resource Description Framework) picture and method

Abstract

The invention discloses a knowledge discovery device based on path migration of an RDF (Resource Description Framework) picture. The device comprises an input module, a link data RDF module, a reasoning module and an output module. The link data RDF module can perform modeling for link data with multiple conceptions and complicated relationships to construct the RDF picture, migrates by steps inside sub pictures and skip among the sub pictures to find a new path and is combined with the reasoning module to reason new knowledge so as to find more hidden knowledge in mass and complicated link data. The device provided by the invention has wide value in actual application. The invention further discloses a method based on path migration of the RDF picture. The method comprises the steps of: performing RDF modeling for the link data; controlling steps of an intelligent agent in sub pictures and skip among sub pictures while finding new knowledge and updating new RDF pictures according to a knowledge reasoning rule dynamically. Therefore, the method provided by the invention has stronger flexibility and variability.

Description

technical field [0001] The invention relates to the field of knowledge discovery oriented to link data, in particular to a knowledge discovery device and method based on RDF graph path walk. Background technique [0002] In recent years, the Internet is undergoing tremendous changes, and its development trend is gradually developing from the file Internet to the data Internet. The inventor of the World Wide Web, Tim Berners-Lee, called on governments and individuals to develop their own data and post it online so that others could relate and use it. Linked data doesn't add semantics to the information, but it can better carry the semantic information you already have. Therefore, although linking data is not semantic, linking at the data level will be able to lay a solid foundation for creating a true semantic web. [0003] Linked data, as a new medium of data expression, emphasizes the relationship between data resources, so it is more machine-readable, enabling machines t...

AI Technical Summary

Problems solved by technology

[0005] The knowledge discovery method based on graph walk has become an important method of knowledge discovery for linked data. The traditional knowledge discovery method based on linked data mainly focuses on a single subgraph, often ignoring the relationship between multiple subgraphs. Therefore, the derived knowledge that can be inferred is very limited

There are also some methods that comprehensively consider the association relationship between multiple subgraphs, but because the association mode of these methods about subgraphs is fixed, they cannot realize the dynamic construction and reorganization of independent subgraphs, and lack sufficient flexibility and Variability, which makes some implicit knowledge difficult to be discovered and excavated

Images