US 12,282,746 B2
Display method, electronic device, and storage medium
Haifeng Wang, Beijing (CN); Zhanyi Liu, Beijing (CN); Zhongjun He, Beijing (CN); Hua Wu, Beijing (CN); Zhi Li, Beijing (CN); Xing Wan, Beijing (CN); Jingxuan Zhao, Beijing (CN); Ruiqing Zhang, Beijing (CN); Chuanqiang Zhang, Beijing (CN); Fengtao Huang, Beijing (CN); Hanbing Song, Beijing (CN); Wei Di, Beijing (CN); Shuangshuang Cui, Beijing (CN); and Yongzheng Xin, Beijing (CN)
Assigned to Beijing Baidu Netcom Science Technology Co., Ltd., Beijing (CN)
Filed by Beijing Baidu Netcom Science Technology Co., Ltd., Beijing (CN)
Filed on Aug. 18, 2022, as Appl. No. 17/820,765.
Claims priority of application No. 202110951952.1 (CN), filed on Aug. 18, 2021.
Prior Publication US 2022/0391602 A1, Dec. 8, 2022
Int. Cl. G06F 40/58 (2020.01)
CPC G06F 40/58 (2020.01) 11 Claims
OG exemplary drawing
 
1. A method for displaying a translation result of a speech in a conference, comprising:
acquiring the translation result of translating the speech from a source language into a target language, and an association image related to the speech, wherein the association image is a screen picture of a speaker giving the speech in the conference;
extracting at least one target term from the translation result using a term extraction rule;
acquiring an annotation information for the at least one target term, responsive to an extraction of the at least one target term; and
displaying the annotation information for the at least one target term and the translation result,
wherein the extracting the at least one target term from the translation result using the term extraction rule comprises:
performing an optical character recognition on a text information in the association image to obtain an association image recognition result, wherein the text information comprises a subtitle on the screen picture corresponding to the translation result; and
extracting at least one candidate term among a plurality of candidate terms as the at least one target term, responsive to a determination that the association image recognition result contains the at least one candidate term, wherein the plurality of candidate terms and candidate term annotation information for the plurality of candidate terms are pre-determined based on a written speech of the speaker and/or a reference material of the speaker using the term extraction rule.