公开(公告)号：US10664660B2

公开(公告)日：2020-05-26

申请号：US16128410

申请日：2018-09-11

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

Inventor： Shuangjie Li ,  Yabing Shi ,  Haijin Liang ,  Yang Zhang ,  Jingfeng Li

IPC: G06F17/27 ,  G06F40/295 ,  G06N3/08 ,  G06F40/211 ,  G06F40/216 ,  G06F40/284

Abstract: A method and device for extracting entity relation based on deep learning and a server are provided. The method includes: preprocessing a text to be mined, to obtain a sentence with entities in the text to be mined; determining an entity pair in the sentence according to the entities, wherein the entity pair includes at least two entities, and determining candidate relations between entities in the entity pair; and determining an entity relation between the entities in the entity pair from the candidate relations.

公开(公告)号：US20190155898A1

公开(公告)日：2019-05-23

申请号：US16128410

申请日：2018-09-11

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

Inventor： Shuangjie Li ,  Yabing Shi ,  Haijin Liang ,  Yang Zhang ,  Jingfeng Li

IPC: G06F17/27 ,  G06N3/08

Abstract: A method and device for extracting entity relation based on deep learning and a server are provided. The method includes: preprocessing a text to be mined, to obtain a sentence with entities in the text to be mined; determining an entity pair in the sentence according to the entities, wherein the entity pair includes at least two entities, and determining candidate relations between entities in the entity pair; and determining an entity relation between the entities in the entity pair from the candidate relations.