公开(公告)号：US20170011117A1

公开(公告)日：2017-01-12

申请号：US15274320

申请日：2016-09-23

Applicant: Huawei Technologies Co., Ltd.

Inventor： Qiang Jiang ,  Hang Li ,  Shan He

IPC: G06F17/30 ,  G06F17/21 ,  G06F17/27

CPC classification number: G06F16/35 ,  G06F9/453 ,  G06F16/3328 ,  G06F16/3344 ,  G06F17/218 ,  G06F17/274 ,  G06F17/278 ,  G06F17/2785 ,  G06F17/2795 ,  G10L15/00

Abstract: A help processing method and device based on semantic recognition are presented. The method includes receiving, by user equipment, a search request entered by a user, where the search request includes information about a problem statement described in a natural language; performing semantic recognition processing on the information about the problem statement, to obtain information about a search intention of the user; and searching a database using the information about the search intention as a search term, to obtain help content needed by the user.

Abstract translation: 提出了一种基于语义识别的帮助处理方法和设备。 该方法包括由用户设备接收由用户输入的搜索请求，其中搜索请求包括关于以自然语言描述的问题陈述的信息; 对关于问题陈述的信息执行语义识别处理，以获得关于用户的搜索意图的信息; 并使用关于搜索意图的信息作为搜索项搜索数据库，以获得用户所需的帮助内容。

公开(公告)号：US11449678B2

公开(公告)日：2022-09-20

申请号：US16369579

申请日：2019-03-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Zhengdong Lu ,  Shan He ,  Qiang Jiang

IPC: G06F40/30 ,  G06F16/00 ,  G06N99/00 ,  G06F40/35 ,  G06F40/56 ,  G06F40/216 ,  G06F16/2455 ,  G06N3/08

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.