Granted Patent B2

US 12,739,479 · App. 19/028,130 · Granted Sep 15, 2026

Inventors: Ben Avi Ingel (Binyamina, IL); Ron Zass (Kiryat Tivon, IL)

H04N21/8126G06F40/58G10L13/00G10L13/033G10L13/086G10L13/10H04N21/2668H04N21/458H04N21/4755

Abstract

Claims (39)

1 . A computer program product for generating personalized videos with selective replacement of characters, the computer program product embodied in a non-transitory computer-readable medium and including instructions that when executed by at least one processor cause the at least one processor to execute a method, the method comprising:

obtaining an input video including at least a depiction of two or more persons;

obtaining a personalized profile associated with a user;

analyzing the input video to determine at least one property for each person of a group of at least two persons of the two or more persons depicted in the input video;

using the personalized profile and the determined properties to select a first person of the group of at least two persons, where the group of at least two persons also includes a second person; and

in response to the selection of the first person, using the input video to generate an output video including the depiction of the second person and a depiction of an avatar replacing at least part of the depiction of the first person.

2 . The computer program product of claim 1 , wherein the method further comprises:

using an artificial neural network to analyze the input video to determine the at least one property for each person of a group of at least two persons; and

using the artificial neural network to generate the output video using the input video.

3 . The computer program product of claim 1 , wherein the method further comprises:

analyzing the input video to detect the depiction of the first person; and

replacing the detected depiction of the first person with a depiction of an avatar to generate the output video.

4 . The computer program product of claim 1 , wherein the at least one property of the first person is a first color, the at least one property of the second person is a second color, and the selection of the first person is based on the first color.

5 . The computer program product of claim 1 , wherein the at least one property of the first person is a size associated with the first person, the at least one property of the second person is a size associated with the second person, and the selection of the first person is based on at least one of the size associated with the first person or the size associated with the second person.

6 . The computer program product of claim 5 , wherein the size associated with the first person is a size of a body part of the first person, and the size associated with the second person is a size of a body part of the second person.

7 . The computer program product of claim 1 , wherein the at least one property of the first person is a texture of a clothing item of the first person, the at least one property of the second person is a texture of a clothing item of the second person, and the selection of the first person is based on at least one of the texture of the clothing item of the first person or the texture of the clothing item of the second person.

8 . The computer program product of claim 1 , wherein the at least one property of the first person is a gender associated with the first person, the at least one property of the second person is a gender associated with the second person, and the selection of the first person is based on at least one of the gender associated with the first person or the gender associated with the second person.

9 . The computer program product of claim 1 , wherein the at least one property of the first person is a shape of at least part of the first person, the at least one property of the second person is a shape of at least part of the second person, and the selection of the first person is based on at least one of the shape of the at least part of the first person or the shape of the at least part of the second person.

10 . The computer program product of claim 1 , wherein the at least one property of the first person is a property of a voice of the first person, the at least one property of the second person is a property of a voice of the second person, and the selection of the first person is based on at least one of the property of the voice of the first person or the property of the voice of the second person.

11 . The computer program product of claim 1 , wherein the at least one property of the first person is an age of the first person, the at least one property of the second person is an age of the second person, and the selection of the first person is based on at least one of the age of the first person or the age of the second person.

12 . The computer program product of claim 1 , wherein the at least one property of the first person is a modesty level associated with the first person, the at least one property of the second person is a modesty level associated with the second person, and the selection of the first person is based on at least one of the modesty level associated with the first person or the modesty level associated with the second person.

13 . The computer program product of claim 1 , wherein the at least one property of the first person is an emotional state associated with the first person, the at least one property of the second person is an emotional state associated with the second person, and the selection of the first person is based on at least one of the emotional state associated with the first person or the emotional state associated with the second person.

14 . The computer program product of claim 1 , wherein at least one characteristic of the avatar is based on the personalized profile.

15 . The computer program product of claim 14 , wherein the personalized profile is based on a geographical destination associated with the user, and the at least one characteristic of the avatar is based on the geographical destination associated with the user.

16 . The computer program product of claim 14 , wherein the personalized profile is based on a cultural tradition associated with the user, and the at least one characteristic of the avatar is based on the cultural tradition.

17 . The computer program product of claim 14 , wherein the personalized profile is based on a socioeconomic status of the user, and the at least one characteristic of the avatar is based on the socioeconomic status.

18 . The computer program product of claim 14 , wherein the personalized profile is based on an emotional state of the user, and the at least one characteristic of the avatar is based on the emotional state.

19 . A system for generating personalized videos with selective replacement of characters, the system comprising at least one processor configured to:

obtain an input video including at least a depiction of two or more persons;

obtain a personalized profile associated with a user;

analyze the input video to determine at least one property for each person of a group of at least two persons of the two or more persons depicted in the input video;

use the personalized profile and the determined properties to select a first person of the group of at least two persons, where the group of at least two persons also includes a second person; and

in response to the selection of the first person, use the input video to generate an output video including the depiction of the second person and a depiction of an avatar replacing at least part of the depiction of the first person.

20 . A method for generating personalized videos with selective replacement of characters, the method comprising:

obtaining an input video including at least a depiction of two or more persons;

obtaining a personalized profile associated with a user;

analyzing the input video to determine at least one property for each person of a group of at least two persons of the two or more persons depicted in the input video;

using the personalized profile and the determined properties to select a first person of the group of at least two persons, where the group of at least two persons also includes a second person; and

in response to the selection of the first person, using the input video to generate an output video including the depiction of the second person and a depiction of an avatar replacing at least part of the depiction of the first person.

Assignments (1)

Continuity (8)

References Cited (156)