公开(公告)号：US11321370B2

公开(公告)日：2022-05-03

申请号：US17031502

申请日：2020-09-24

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Zhenyu Jiao ,  Shuqi Sun ,  Ke Sun ,  Tingting Li

IPC: G06F16/332 ,  G06F16/38 ,  G06F16/35 ,  G06N5/04

Abstract: The present disclosure discloses a method for generating a question answering robot, relates to the field of robotics. The specific implementation includes: obtaining field information input by a user, obtaining a field-specific robot from a robot library based on the field information; obtaining a template list corresponding to the field-specific robot, providing the template list to the user, the template list including a plurality of templates; receiving the plurality of templates filled in by the user, the templates filled in by the user including at least one question and an answer corresponding to the at least one question; expanding the at least one question filled in by the user based on a question semantic database to form a combination of questions corresponding to the answer, the answer and the combination of questions forming a question-answer pair; and generating a question answering robot based on the question-answer pair.

公开(公告)号：US12026966B2

公开(公告)日：2024-07-02

申请号：US17476177

申请日：2021-09-15

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Hongjie Guo ,  Hongyang Zhang ,  Zhenyu Jiao ,  Shuqi Sun ,  Yue Chang ,  Tingting Li

IPC: G10L15/18 ,  G06F18/22 ,  G06F40/284 ,  G06F40/295 ,  G06F40/30 ,  G06V30/262

CPC classification number: G06V30/274 ,  G06F18/22 ,  G06F40/284 ,  G06F40/295 ,  G06F40/30 ,  G10L15/1822

Abstract: A method for recognizing a dialogue intention, an electronic device and a storage medium are provided. The solution includes: obtaining a sample sentence with an intention category to be predicted and a plurality of supporting sentences each labeled with an intention category; and inputting the sample sentence and the plurality of supporting sentences into a trained intention recognition model, in which the trained intention recognition model is configured to generate a sample sentence vector corresponding to the sample sentence and category vectors corresponding to the plurality of supporting sentences based on the sample sentence and the plurality of supporting sentences, calculate matching degrees between the sample sentence vector and the category vectors, and obtain a predicted intention category of the sample sentence based on the matching degrees.