Title:
RECOMMENDATION SYSTEM TRAINING METHOD AND APPARATUS, AND COMPUTER DEVICE AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2020/143186
Kind Code:
A1
Abstract:
Disclosed in embodiments of the present application are a recommendation system training method and apparatus, and a computer device and a storage medium. The method relates to an artificial intelligence technology. The method comprises: performing word segmentation processing on a search word sample and an answer word sample to obtain a search word sample segmented word set and an answer word sample segmented word set; performing word vector training on the search word sample segmented word set and the answer word sample segmented word set to obtain a search word sample word vector set and an answer word sample word vector set; inputting the search word sample word vectors in the search word sample word vector set into a knowledge graph to obtain an input word vector set; training a recommendation system by means of the input word vector set and the answer word sample word vector set; and if receiving retrieval information input by a user, providing a recommendation result for the user according to the trained recommendation system.
Inventors:
JIN GE (CN)
XU LIANG (CN)
XU LIANG (CN)
Application Number:
PCT/CN2019/093138
Publication Date:
July 16, 2020
Filing Date:
June 27, 2019
Export Citation:
Assignee:
PING AN TECH SHENZHEN CO LTD (CN)
International Classes:
G06K9/62; G06F16/36; G06F16/951
Foreign References:
CN109858528A | 2019-06-07 | |||
CN104156359A | 2014-11-19 | |||
CN105989040A | 2016-10-05 | |||
CN108427707A | 2018-08-21 | |||
US20070299824A1 | 2007-12-27 |
Attorney, Agent or Firm:
SHENZHEN TALENT PATENT SERVICE (CN)
Download PDF: