公开(公告)号：US20210232714A1

公开(公告)日：2021-07-29

申请号：US17164297

申请日：2021-02-01

Applicant: Facebook, Inc.

Inventor： Fabiana Meira Pires de Azevedo ,  Marc Thomas Cruz ,  Matthew Miklasevich ,  Arvin Aminpour ,  Bonan Dong ,  Jason Rose

IPC: G06F21/84 ,  G06F21/62 ,  G06N20/00

Abstract: Systems, methods, and non-transitory computer readable media are configured to determine a likelihood of a user choosing to reveal a given content item when contents of the content item are obscured. The likelihood can be determined based at least in part on a trained machine learning model. An extent by which to obscure the content item based at least in part on the likelihood can be determined. Subsequently, an obscured version of the content item can be provided for display. The content item can be obscured based at least in part on the determined extent.

公开(公告)号：US20190188421A1

公开(公告)日：2019-06-20

申请号：US15844033

申请日：2017-12-15

Applicant: Facebook, Inc.

Inventor： Fabiana Meira Pires de Azevedo ,  Marc Thomas Cruz ,  Matthew Miklasevich ,  Arvin Aminpour ,  Bonan Dong ,  Jason Rose

IPC: G06F21/84 ,  G06F21/62 ,  G06N99/00

CPC classification number: G06F21/84 ,  G06F21/6218 ,  G06N20/00

Abstract: Systems, methods, and non-transitory computer readable media are configured to determine a likelihood of a user choosing to reveal a given content item when contents of the content item are obscured. The likelihood can be determined based at least in part on a trained machine learning model. An extent by which to obscure the content item based at least in part on the likelihood can be determined. Subsequently, an obscured version of the content item can be provided for display. The content item can be obscured based at least in part on the determined extent.