公开(公告)号：US20190066675A1

公开(公告)日：2019-02-28

申请号：US16054970

申请日：2018-08-03

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Yichuan LIANG ,  Guang LING ,  Yingzhan LIN ,  Wenmin WANG ,  Zeying XIE ,  Yin ZHANG ,  Wei XU ,  Chao ZHOU

IPC: G10L15/22 ,  G10L15/193 ,  G10L15/06 ,  G06F3/16 ,  G06F15/18

Abstract: Embodiments of the present disclosure disclose an artificial intelligence based method and apparatus for classifying a voice-recognized text. A specific embodiment of the method includes: acquiring a current interactive text of a voice query from a user; analyzing the current interactive text using a lexical analyzer to obtain a current lexical structure; determining whether the current lexical structure matches a template of a category in a classifier; and classifying, if the current lexical structure matches the template of the category in the classifier, the current interactive text corresponding to the current lexical structure into the category belonging to the matched template. The embodiment can fast classify texts, effectively reduce the magnitude of manually annotated texts, and improve the annotation efficiency in intelligent voice interaction services.

公开(公告)号：US20180365258A1

公开(公告)日：2018-12-20

申请号：US16008603

申请日：2018-06-14

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

Inventor： Yongxiang HUANG ,  Chao ZHOU ,  Yin ZHANG ,  Wei XU

IPC: G06F17/30 ,  G06N5/02

Abstract: The present disclosure provides an artificial intelligence-based searching method and apparatus, a device and a computer-readable storage medium. In embodiments of the present disclosure, the search demand type is obtained according to the search keyword provided by the user, then the demand keyword is obtained according to the search keyword and the search pattern of the search demand type so that the search result can be obtained according to the demand keyword, and be output. Since the search operation is performed not completely depending on the search keyword provided by the user, but performed in conjunction with the demand keyword obtained according to the search demand type to which the search keyword belongs, the search result substantially satisfies the user's real intention.