公开(公告)号：US11042553B2

公开(公告)日：2021-06-22

申请号：US15819050

申请日：2017-11-21

Applicant: GOOGLE LLC

Inventor： Balakrishnan Varadarajan ,  George Dan Toderici ,  Apostol Natsev ,  Weilong Yang ,  John Burge ,  Sanketh Shetty ,  Omid Madani

IPC: G06F16/00 ,  G06F16/2457 ,  G06F16/28 ,  G06F16/78 ,  G06F40/169 ,  G06F40/295

Abstract: Facilitating of content entity annotation while maintaining joint quality, coverage and/or completeness performance conditions is provided. In one example, a non-transitory computer-readable medium comprises computer-readable instructions that, in response to execution, cause a computing system to perform operations. The operations include aggregating information indicative of initial entities for content and initial scores associated with the initial entities received from one or more content annotation sources and mapping the initial scores to respective values to generate calibrated scores. The operations include applying weights to the calibrated scores to generate weighted scores and combining the weighted scores using a linear aggregation model to generate a final score. The operations include determining whether to annotate the content with at least one of the initial entities based on a comparison of the final score and a defined threshold value.

公开(公告)号：US20180089200A1

公开(公告)日：2018-03-29

申请号：US15819050

申请日：2017-11-21

Applicant: GOOGLE LLC

Inventor： Balakrishnan Varadarajan ,  George Dan Toderici ,  Apostol Natsev ,  Weilong Yang ,  John Burge ,  Sanketh Shetty ,  Omid Madani

IPC: G06F17/30 ,  G06F17/24 ,  G06F17/27

CPC classification number: G06F16/24578 ,  G06F16/285 ,  G06F16/78 ,  G06F17/241 ,  G06F17/278

Abstract: Facilitating of content entity annotation while maintaining joint quality, coverage and/or completeness performance conditions is provided. In one example, a non-transitory computer-readable medium comprises computer-readable instructions that, in response to execution, cause a computing system to perform operations. The operations include aggregating information indicative of initial entities for content and initial scores associated with the initial entities received from one or more content annotation sources and mapping the initial scores to respective values to generate calibrated scores. The operations include applying weights to the calibrated scores to generate weighted scores and combining the weighted scores using a linear aggregation model to generate a final score. The operations include determining whether to annotate the content with at least one of the initial entities based on a comparison of the final score and a defined threshold value.