公开(公告)号：US20190228070A1

公开(公告)日：2019-07-25

申请号：US16369579

申请日：2019-03-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Zhengdong LU ,  Shan HE ,  Qiang JIANG

IPC: G06F17/27 ,  G06N3/08 ,  G06F16/2455

Abstract: A deep learning based dialog method, apparatus, and device are provided and belong to the field of artificial intelligence. The method includes: obtaining a to-be-replied statement, encoding the to-be-replied statement to obtain a first vector , where the first vector is a representation of the to-be-replied statement; obtaining dialog history information corresponding to the to-be-replied statement, and the attention vector is used to represent search intent; making each dialog statement interact with the attention vector, so as to extract information related to the search intent from the dialog statement to obtain a plurality of result vectors, generating a to-be-decoded vector based on the plurality of result vectors, and decoding the to-be-decoded vector to obtain a next word in the reply statement. In the method, the reply statement refers to a dialog history.