Systems and methods for generating personalized content items

Patent metadata

Field	Value
Publication number	US-2022414754-A1
Application number	US-202117362703-A
Country	US
Kind code	A1
Filing date	Jun 29, 2021
Priority date	Jun 29, 2021
Publication date	Dec 29, 2022
Grant date	—

Abstract

Systems, methods, and non-transitory computer-readable media can be configured to determine a content item template that includes a placeholder character. A personalized character can be generated based on the placeholder character and user preference information of a user. A personalized content item can be generated for the user based on the content item template and the personalized character.

First claim

1 . A computer-implemented method comprising:
determining, by a computing system, a content item template that includes a placeholder character, wherein the content item template includes a specified range associated with an appearance characteristic associated with the placeholder character; generating, by the computing system, a personalized character with a personalized appearance characteristic that satisfies the specified range based on the placeholder character and user preference information of a user; and generating, by the computing system, a personalized content item for the user based on the content item template and the personalized character.

2 . The computer-implemented method of claim 1 , wherein the user preference information is based on engagement information associated with the user and the engagement information indicates at least one of: a content item with which the user interacted, a type of interaction, or an amount of time associated with an interaction.

3 . The computer-implemented method of claim 1 , wherein the generating the personalized character is further based on parameters associated with the content item template, wherein the parameters specify a required color to be applied to the personalized character.

4 . The computer-implemented method of claim 1 , wherein personalized appearance characteristics associated with the personalized character are maintained for a specified period of time.

5 . The computer-implemented method of claim 1 , wherein the user preference information is determined based on a machine learning model.

6 . The computer-implemented method of claim 5 , further comprising:
training the machine learning model based on training data that includes user features associated with users and content features associated with content items with which the users interact.

7 . The computer-implemented method of claim 6 , wherein the content features include appearance characteristics of people appearing in the content items.

8 . The computer-implemented method of claim 6 , further comprising:
refining the machine learning model based on engagement information associated with the user.

9 . The computer-implemented method of claim 5 , wherein the machine learning model generates a score associated with an appearance characteristic and the score indicates a likelihood the user has a preference for the appearance characteristic.

10 . The computer-implemented method of claim 1 , wherein the user preference information includes preferences for appearance characteristics and the appearance characteristics include at least one of: hair color, hair style, facial features, facial expression, facial accessories, age, gender, body type, and body pose.

11 . A system comprising:
at least one processor; and a memory storing instructions that, when executed by the at least one processor, cause the system to perform:
determining a content item template that includes a placeholder character wherein the content item template includes a specified range associated with an appearance characteristic associated with the placeholder character;
generating a personalized character with a personalized appearance characteristic that satisfies the specified range based on the placeholder character and user preference information of a user; and
generating a personalized content item for the user based on the content item template and the personalized character.

12 . The system of claim 11 , wherein the user preference information is based on engagement information associated with the user and the engagement information indicates at least one of: a content item with which the user interacted, a type of interaction, or an amount of time associated with an interaction.

13 . The system of claim 11 , wherein the generating the personalized character is further based on parameters associated with the content item template, wherein the parameters specify a required color to be applied to the personalized character.

14 . The system of claim 11 , wherein personalized appearance characteristics associated with the personalized character are maintained for a specified period of time.

15 . The system of claim 11 , wherein the user preference information is determined based on a machine learning model.

16 . A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform:
determining a content item template that includes a placeholder character, wherein the content item template includes a specified range associated with an appearance characteristic associated with the placeholder character; generating a personalized character with a personalized appearance characteristic that satisfies the specified range based on the placeholder character and user preference information of a user; and generating a personalized content item for the user based on the content item template and the personalized character.

17 . The non-transitory computer-readable storage medium of claim 16 , wherein the user preference information is based on engagement information associated with the user and the engagement information indicates at least one of: a content item with which the user interacted, a type of interaction, or an amount of time associated with an interaction.

18 . The non-transitory computer-readable storage medium of claim 16 , wherein the generating the personalized character is further based on parameters associated with the content item template, wherein the parameters specify a required color to be applied to the personalized character.

19 . The non-transitory computer-readable storage medium of claim 16 , wherein personalized appearance characteristics associated with the personalized character are maintained for a specified period of time.

20 . The non-transitory computer-readable storage medium of claim 16 , wherein the user preference information is determined based on a machine learning model.

Assignees

• Meta Platforms Inc

Inventors

• Afshar Jaleh

Classifications

• G06Q30/0643 Primary

  graphically representing goods, e.g. 3D product representation · CPC title

• G06Q30/0251

  Targeted advertisements · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F16/906

  Clustering; Classification · CPC title

• G06Q30/0631

  Recommending goods or services · CPC title