Title:
METHOD FOR ANALYZING ENTITY ASSOCIATION RELATIONSHIP, AND RELATED APPARATUS
Document Type and Number:
WIPO Patent Application WO/2019/174422
Kind Code:
A1
Abstract:
Disclosed are a method for analyzing an entity association relationship, and a related apparatus; in the method for analyzing an entity association relationship, after a word segmentation process is performed on predicted text to obtain a part-of-speech sequence of a text to be predicted, a vector of each word segment in the part-of-speech sequence of said text to be predicted is obtained; a vector of each word segment in the part-of-speech sequence of the text to be predicted is predicted by a prediction model of the entity association relationship, and thus a prediction result of the association relationship between the entity and the corresponding attribute in the text to be predicted can be obtained. In the described process, a word segmentation process is performed on the text to be predicted so as to obtain a part-of-speech sequence, and the vector of each word segment in the part-of-speech sequence is obtained, rather than word selection and word feature extraction being done manually; thus the problem of words being manually selected and word features being manually provided affecting the accuracy of test results concerning the association relationship between entities and attributes is resolved.
Inventors:
WANG TIANYI (CN)
Application Number:
PCT/CN2019/073664
Publication Date:
September 19, 2019
Filing Date:
January 29, 2019
Export Citation:
Assignee:
BEIJING GRIDSUM TECHNOLOGY CO (CN)
International Classes:
G06F40/20
Foreign References:
| CN106886516A | 2017-06-23 | |||
| CN106970981A | 2017-07-21 | |||
| US20160314121A1 | 2016-10-27 |
Attorney, Agent or Firm:
UNITALEN ATTORNEYS AT LAW (CN)
Download PDF: