Title:
TRAINING METHOD AND APPARATUS, DIALOGUE PROCESSING METHOD AND SYSTEM, AND MEDIUM
Document Type and Number:
WIPO Patent Application WO/2020/228636
Kind Code:
A1
Abstract:
Disclosed are a reinforcement learning model training method and apparatus, a dialogue processing method and a dialogue system, and a computer-readable storage medium. The reinforcement learning model training method comprises: acquiring unlabelled data and labelled data which are used for training a reinforcement learning model; on the basis of the unlabelled data, generating, with reference to the labelled data, an experience pool for training the reinforcement learning model; and using the experience pool to train the reinforcement learning model.
Inventors:
ZHU HONGWEN (CN)
ZHOU LI (CN)
DAI YAFEI (CN)
CHEN XUE (CN)
ZOU SHENGPENG (CN)
SONG YIPING (CN)
ZHANG MING (CN)
ZHANG ZIHAN (CN)
QU WEI (CN)
ZHOU LI (CN)
DAI YAFEI (CN)
CHEN XUE (CN)
ZOU SHENGPENG (CN)
SONG YIPING (CN)
ZHANG MING (CN)
ZHANG ZIHAN (CN)
QU WEI (CN)
Application Number:
PCT/CN2020/089394
Publication Date:
November 19, 2020
Filing Date:
May 09, 2020
Export Citation:
Assignee:
BOE TECHNOLOGY GROUP CO LTD (CN)
UNIV BEIJING (CN)
UNIV BEIJING (CN)
International Classes:
G06F16/332
Foreign References:
CN107342078A | 2017-11-10 | |||
CN108600379A | 2018-09-28 | |||
CN109710741A | 2019-05-03 | |||
CN107911299A | 2018-04-13 |
Attorney, Agent or Firm:
LIU, SHEN & ASSOCIATES (CN)
Download PDF: