IP Library › Granted Patent US 12671881
Granted Patent B2
US 12671881 · App. 18/968,042 · Granted Jun 30, 2026

Systems, methods, and computer-readable media for personalized media content alteration

Inventors: Jean-Yves Couleaud (Mission Viejo, CA); Tao Chen (Palo Alto, CA); Ning Xu (Irvine, CA)
Assignee: Adeia Guides Inc.
H04N21/85
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12671881
App. No.
18/968,042
Granted
Jun 30, 2026
Kind
B2
Abstract

An appearance of a character depicted in a media asset may be altered, for example, by a trained machine learning model, based on demographic attributes of a consumer of the media asset, such as the age or ethnicity of the consumer. A character alteration rule may limit some types of alteration, for example, re-aging a character that would depict a minor in some situation. Altering the appearance of one or more characters depicted in the media asset may also entail altering the appearance of a first character based on demographics of the consumer and automatically altering the appearance of a second character based on the second character's relationship with the first character. The re-aging the second character may be proportional to the re-aging of the first character.

Claims (59)

1 . A computer-implemented method comprising:

receiving a selection of a media asset, wherein the selection is associated with a device;

identifying one or more characters depicted in the media asset;

accessing one or more demographic attributes in a user profile associated with the device or entered via user input;

determining a character alteration rule by accessing a data structure indicating one or more of: a character age parameter of the one or more characters; an ethnic parameter of the one or more characters; or a relationship between two or more characters of the one or more characters, wherein the character alteration rule is based at least in part on a storyline of the media asset, and sets an age threshold for re-aging the one or more characters;

generating an altered appearance of the one or more characters depicted in the media asset by altering, using one or more trained machine learning models, an appearance of the one or more characters depicted in the media asset based at least in part on the one or more demographic attributes and on the determined character alteration rule; and

generating for display the media asset or a notification about the media asset such that the media asset or the notification about the media asset comprises the altered appearance of the one or more characters depicted in the media asset.

2 . The method of claim 1 , wherein the generating of the altered appearance of the one or more characters depicted in the media asset comprises:

altering the appearance of a first character of the one or more characters based at least in part on the one or more demographic attributes, such that the altered appearance of the first character reflects a target demographic; and

altering the appearance of a second character depicted in the media asset based at least in part on the target demographic.

3 . The method of claim 2 , wherein an apparent age difference between the altered appearance of the first character and an unaltered depiction of the first character in the media asset is a first apparent age difference, and

wherein the apparent age difference between the altered appearance of the second character and an unaltered depiction of the second character in the media asset is a second apparent age difference, and the second apparent age difference is not equal to the first apparent age difference.

4 . The method of claim 3 , wherein the second apparent age difference is proportional to the first apparent age difference.

5 . The method of claim 1 , further comprising:

retrieving a reference image of at least one character of the one or more characters depicted in the media asset,

wherein the generating of the altered appearance of the one or more characters depicted in the media asset comprises providing as input the reference image to the one or more trained machine learning models.

6 . The method of claim 1 , further comprising:

determining, based on the user profile associated with the device, a user preference for an altered character appearance of a first demographic type,

wherein the generating the altered appearance of the one or more characters depicted in the media asset is based at least in part on the user preference for the altered character appearance of the first demographic type.

7 . The method of claim 1 , wherein the data structure is generated based at least in part on at least one of metadata associated with the media asset or using the one or more trained machine learning models.

8 . The method of claim 1 , wherein the determining the character alteration rule comprises accessing the data structure indicating the ethnic parameter of the one or more characters, and wherein the generating the altered appearance of the one or more characters depicted in the media asset comprises:

determining an ethnic appearance of the one or more characters depicted in the media asset,

wherein the character alteration rule prohibits altering the ethnic appearance of the one or more characters.

9 . The method of claim 1 , wherein the character alteration rule indicates at least one of the character age parameter or the relationship between the two or more characters, and the age threshold corresponds to the at least one of the character age parameter or the relationship between the two or more characters.

10 . The method of claim 1 , wherein the character alteration rule based at least in part on the storyline of the media asset is determined before the accessing of the data structure.

11 . A system comprising:

a memory; and

control circuitry configured to:

receive a selection of a media asset, wherein the selection is associated with a device;

identify one or more characters depicted in the media asset;

access one or more demographic attributes in a user profile associated with the device or entered via user input;

determine a character alteration rule by accessing a data structure in the memory indicating one or more of: a character age parameter of the one or more characters; an ethnic parameter of the one or more characters; or a relationship between two or more characters of the one or more characters, wherein the character alteration rule is based at least in part on a storyline of the media asset, and sets an age threshold for re-aging the one or more characters;

generate an altered appearance of the one or more characters depicted in the media asset by altering, using one or more trained machine learning models, an appearance of the one or more characters depicted in the media asset based at least in part on the one or more demographic attributes and on the determined character alteration rule; and

generate for display the media asset or a notification about the media asset such that the media asset or the notification about the media asset comprises the altered appearance of the one or more characters depicted in the media asset.

12 . The system of claim 11 , wherein the generating of the altered appearance of the one or more characters depicted in the media asset comprises:

altering the appearance of a first character of the one or more characters based at least in part on the one or more demographic attributes, such that the altered appearance of the first character reflects a target demographic; and

altering the appearance of a second character depicted in the media asset based at least in part on the target demographic.

13 . The system of claim 12 , wherein an apparent age difference between the altered appearance of the first character and an unaltered depiction of the first character in the media asset is a first apparent age difference, and

wherein the apparent age difference between the altered appearance of the second character and an unaltered depiction of the second character in the media asset is a second apparent age difference, and the second apparent age difference is not equal to the first apparent age difference.

14 . The system of claim 13 , wherein the second apparent age difference is proportional to the first apparent age difference.

15 . The system of claim 11 , wherein the system is configured to:

retrieve a reference image of at least one character of the one or more characters depicted in the media asset,

wherein the generating of the altered appearance of the one or more characters depicted in the media asset comprises providing as input the reference image to the one or more trained machine learning models.

16 . The system of claim 11 , wherein the system is configured to:

determine, based on the user profile associated with the device, a user preference for an altered character appearance of a first demographic type,

wherein the generating the altered appearance of the one or more characters depicted in the media asset is based at least in part on the user preference for the altered character appearance of the first demographic type or using the one or more trained machine learning models.

17 . The system of claim 11 , wherein determining the character alteration rule comprises accessing the data structure indicating the ethnic parameter of the one or more characters, and wherein the generating the altered appearance of the one or more characters depicted in the media asset comprises:

determining an ethnic appearance of the one or more characters depicted in the media asset,

wherein the character alteration rule prohibits altering the ethnic appearance of the one or more characters.

18 . The system of claim 11 , wherein the character alteration rule indicates at least one of the character age parameter or the relationship between the two or more characters, and the age threshold corresponds to the at least one of the character age parameter or the relationship between the two or more characters.

19 . A computer-implemented method comprising:

receiving a selection of a media asset, wherein the selection is associated with a device;

identifying a first character depicted in the media asset and a second character depicted in the media asset;

accessing one or more demographic attributes in a user profile associated with the device or entered via user input;

determining a character alteration rule by accessing a data structure indicating one or more of: a character age parameter of the first character; an ethnic parameter of the first character; or a relationship between the first character and the second character; and

generating an altered appearance of the first character by altering, using one or more trained machine learning models, an appearance of the first character based at least in part on the one or more demographic attributes and on the determined character alteration rule; and

generating an altered appearance of the second character by altering, using the one or more trained machine learning models, an appearance of the second character based at least in part on the determined character alteration rule,

wherein an apparent age difference between the altered appearance of the first character and an unaltered depiction of the first character in the media asset is a first apparent age difference, and wherein the apparent age difference between the altered appearance of the second character and an unaltered depiction of the second character in the media asset is a second apparent age difference, and the second apparent age difference is not equal to the first apparent age difference.

20 . The method of claim 19 , wherein the second apparent age difference is proportional to the first apparent age difference.