US 12,112,572 B2
Systems and methods for alerting a user to published undesirable images depicting the user
Gyanveer Singh, Bihar (IN); Charishma Chundi, Andhra Pradesh (IN); and Sriram Ponnuswamy, TamilNadu (IN)
Assigned to Rovi Guides, Inc., San Jose, CA (US)
Filed by Rovi Guides, Inc., San Jose, CA (US)
Filed on Nov. 30, 2020, as Appl. No. 17/106,900.
Application 17/106,900 is a continuation of application No. 15/924,928, filed on Mar. 19, 2018, granted, now 10,885,315.
Prior Publication US 2021/0081655 A1, Mar. 18, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 40/16 (2022.01); G06N 20/00 (2019.01); G06V 20/00 (2022.01); G06V 20/40 (2022.01); H04L 67/55 (2022.01); H04N 21/454 (2011.01); H04N 21/488 (2011.01)
CPC G06V 40/172 (2022.01) [G06N 20/00 (2019.01); G06V 20/35 (2022.01); G06V 20/41 (2022.01); G06V 40/174 (2022.01); H04L 67/55 (2022.05); H04N 21/4542 (2013.01); H04N 21/4882 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A method for warning a user that media assets associated with another user depict the user in a state undesirable to the user, the method comprising:
determining that a media asset of a plurality of media assets associated with a first user includes a visual or auditory depiction of a second user;
accessing, at a remote server, an undesired visual or auditory depiction data structure comprising one or more undesired visual or auditory depiction entries, wherein each undesired visual or auditory depiction entry represents at least one undesirable visual expression of the second user;
extracting, from the media asset, the visual or auditory depiction of the second user;
comparing the visual or auditory depiction of the second user with each of the one or more undesired visual or auditory depiction entries;
determining, based on the comparing, whether any of the one or more undesired visual or auditory depiction entries match the visual or auditory depiction of the second user;
in response to determining that any of the undesired visual or auditory depiction entries matches the visual or auditory depiction of the second user, storing an indication of the visual or auditory depiction of the second user that matches any of the undesired visual or auditory depiction entries by:
determining whether a first visual or auditory depiction of a plurality of visual or auditory depictions that matches a first entry of the one or more undesired visual or auditory depiction entries is associated with a media asset comprising video;
in response to determining that the first visual or auditory depiction of the plurality of visual or auditory depictions that matches a first undesired visual or auditory depiction entry of the one or more undesired visual or auditory depiction entries is associated with a media asset comprising video, identifying a set of visual or auditory depictions in the media asset comprising video, wherein each visual or auditory depiction in the set matches the one or more undesired visual or auditory depiction entries; and
storing, in a data structure for each visual or auditory depiction in the set of visual or auditory depictions, a start time of the visual or auditory depiction within the video, an end time of the visual or auditory depiction within the video, and an identifier of a matching undesired visual or auditory depiction entry of the one or more undesired visual or auditory depiction entries;
generating a notification to the second user indicating that a visual or auditory depiction of the second user in the plurality of media assets match an undesired visual or auditory depiction entry;
in response to determining a pre-determined action that the second user indicated to be performed in response to determining that one or more visual or auditory depictions of the second user in the plurality of media assets match the one or more undesired visual or auditory depiction entries, performing the pre-determined action on the visual or auditory depiction of the second user that matches any of the one or more undesired visual or auditory depiction entries; and
in response to determining that the second user did not indicate one or more predetermined actions to be performed based on determining that a visual or auditory depiction of the second user matches any of the one or more undesired visual or auditory depiction entries, generating for display one or more actions that the second user may select to be performed.