New concept mining method based on serialization learning, relation mining and time sequence analysis

The invention discloses a new concept mining method based on serialized learning, relationship mining and time sequence analysis. Syntax dependence analysis and POS annotation can be carried out; semantic extraction is carried out on possible concepts in the text; through analysis of a time sequence...

Full description

Saved in:
Bibliographic Details
Main Authors LI XURI, HU ZHANZHAN, HE YUXUAN, MOU HAO, XU YABO
Format Patent
LanguageChinese
English
Published 11.10.2019
Subjects
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:The invention discloses a new concept mining method based on serialized learning, relationship mining and time sequence analysis. Syntax dependence analysis and POS annotation can be carried out; semantic extraction is carried out on possible concepts in the text; through analysis of a time sequence, whether the concepts change from few to many and from nothing to nothing in the time dimension ornot is judged and recognized, the knowledge graph is constructed through the mutual relation between the different concepts, the effect of quick associative query is achieved, and the requirement thatoriginal data volume text data need to be checked manually in traditional product research and development is greatly lowered; the identification of the new concept can effectively help enterprises to find new opportunity points in the production process, so that the research and development dynamics of competitors and the hot concepts related to product development can be quickly discovered. 本发明公开了一种基于序列化学习、关系挖掘、时序分析的新概念
Bibliography:Application Number: CN201910280639