US 11,601,693 B2Granted

Automatic adaptation of digital content

AssigneeKyndryl, Inc.

InventorsMarco Aurelio Stelmar Netto, Maryana Zanetti, Roberto Guarda, Marcio Rogerio Luccas, Jyulian Kyohei Kuroba Kumeda, Thiago Rodrigues de Souza Costa

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

Embodiments of the present invention provide methods, computer program products, and systems for adapting digital content. Embodiments of the present invention can be used to identify one or more entities in media content. Embodiments of the present invention can determine that an identified entity of the one more identified entities is associated with sensitive material. Embodiments of the present invention can, in response to determining that the identified entity of the one or more identified entities is sensitive, determine a contextual impact of the identified entity. Embodiments of the present invention can also be used to modify the media content based on the determined contextual impact of the identified entity.

Claims8

Dependent claims

A computer-implemented method comprising:

identifying one or more entities in media content;
determining, based on a user profile of a user, that an identified entity of the one more identified entities is associated with sensitive material to which the user has an adverse reaction, as indicated by the user profile of the user;
in response to determining that the identified entity of the one or more identified entities is associated with sensitive material, determining a contextual impact of the identified entity based, at least in part, on an identified media type associated with the media content, a calculated percentage of time the identified entity is displayed in the media content, and determined relevancy, wherein the determining the contextual impact of the identified entity comprises:
identifying the media type associated with the media content;
in response to identifying that the media type associated with the media content is a video, calculating the percentage of time the identified entity is displayed in the video;
and
performing processing based on the calculating, wherein the performing processing comprises one selected from the group consisting of:
in response to determining that the calculated percentage of time the identified entity is displayed exceeds one percent of a duration of total time for the video and further in response to determining that an average number of frames the identified entity is displayed in exceeds thirty frames per second, identifying contextual impact of the identified entity in the video as being relevant, and
in response to determining that the calculated percentage of time the identified entity is displayed does not exceed one percent of a duration of total time for the video and further in response to determining that an average number of frames the identified entity is displayed in does not exceed thirty frames per second, identifying contextual impact of the identified entity in the video as being non relevant;
and
automatically modifying, by a content adaptor executing on a hardware processing device, the media content based on the determined contextual impact of the identified entity, the modifying comprising performing an ameliorative action identified based on the user profile, wherein the media content comprises at least one digital image and the identified entity appears adjacent at least one other entity in the at least one digital image, and wherein the modifying automatically modifies the identified entity in the at least one digital image and retains the at least one other entity in the at least one digital image to produce a modified version of the media content for presentation to the user.

8 more elements

A computer program product comprising:

one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising:
program instructions to identify one or more entities in media content;
program instructions to determine, based on a user profile of a user, that an identified entity of the one more identified entities is associated with sensitive material to which the user has an adverse reaction, as indicated by the user profile of the user;
program instructions to, in response to determining that the identified entity of the one or more identified entities is associated with sensitive material, determine a contextual impact of the identified entity based, at least in part, on an identified media type associated with the media content, a calculated percentage of time the identified entity is displayed in the media content, and determined relevancy, wherein the program instructions to determe the contextual impact of the identified entity comprise:
program instructions to identify the media type associated with the media content;
program instructions to, in response to identifying that the media type associated with the media content is a video, calculate the percentage of time the identified entity is displayed in the video;
and
program instructions to performing processing based on the calculating, wherein the program instructions to perform processing comprise at least one selected from the group consisting of:
program instructions to, in response to determining that the calculated percentage of time the identified entity is displayed exceeds one percent of a duration of total time for the video and further in response to determining that an average number of frames the identified entity is displayed in exceeds thirty frames per second, identify contextual impact of the identified entity in the video as being relevant;
and
program instructions to, in response to determining that the calculated percentage of time the identified entity is displayed does not exceed one percent of a duration of total time for the video and further in response to determining that an average number of frames the identified entity is displayed in does not exceed thirty frames per second, identifying contextual impact of the identified entity in the video as being non relevant;
and
program instructions to automatically modify, by a content adaptor executing on a hardware processing device, the media content based on the determined contextual impact of the identified entity, the program instructions to modify comprising program instructions to perform an ameliorative action identified based on the user profile, wherein the media content comprises at least one digital image and the identified entity appears adjacent at least one other entity in the at least one digital image, and wherein the modifying automatically modifies the identified entity in the at least one digital image and retains the at least one other entity in the at least one digital image to produce a modified version of the media content for presentation to the user.

10 more elements

A computer system comprising:

one or more computer processors;
one or more computer readable storage media;
and
program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising:
program instructions to identify one or more entities in media content;
program instructions to determine, based on a user profile of a user, that an identified entity of the one more identified entities is associated with sensitive material to which the user has an adverse reaction, as indicated by the user profile of the user;
program instructions to, in response to determining that the identified entity of the one or more identified entities is associated with sensitive material, determine a contextual impact of the identified entity based, at least in part, on an identified media type associated with the media content, a calculated percentage of time the identified entity is displayed in the media content, and determined relevancy, wherein the program instructions to determe the contextual impact of the identified entity comprise:
program instructions to identify the media type associated with the media content;
program instructions to, in response to identifying that the media type associated with the media content is a video, calculate the percentage of time the identified entity is displayed in the video;
and
program instructions to performing processing based on the calculating, wherein the program instructions to perform processing comprise at least one selected from the group consisting of:
program instructions to, in response to determining that the calculated percentage of time the identified entity is displayed exceeds one percent of a duration of total time for the video and further in response to determining that an average number of frames the identified entity is displayed in exceeds thirty frames per second, identify contextual impact of the identified entity in the video as being relevant;
and
program instructions to, in response to determining that the calculated percentage of time the identified entity is displayed does not exceed one percent of a duration of total time for the video and further in response to determining that an average number of frames the identified entity is displayed in does not exceed thirty frames per second, identifying contextual impact of the identified entity in the video as being non relevant;
and
program instructions to automatically modify, by a content adaptor executing on a hardware processing device, the media content based on the determined contextual impact of the identified entity, the program instructions to modify comprising program instructions to perform an ameliorative action identified based on the user profile, wherein the media content comprises at least one digital image and the identified entity appears adjacent at least one other entity in the at least one digital image, and wherein the modifying automatically modifies the identified entity in the at least one digital image and retains the at least one other entity in the at least one digital image to produce a modified version of the media content for presentation to the user.

13 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/587,136Filed 30 Sep 2019
Published: US 2021/0097287 A11 Apr 2021
Granted: 7 Mar 2023
Term ends: Not estimatedThe source records don’t support an estimate.

Classification11 codes

H04N 21/23418
Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs: involving operations for…
G06F 18/22
Analysing: matching criteria, e.g. proximity measures
G06V 20/40
Scenes; Scene-specific elements: in video content
G06V 20/41
In video content: higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian…