Granted Patent B2

US 12,309,440 · App. 16/230,830 · Granted May 20, 2025

Inventors: Basil Badawiyeh (Parker, CO); Vipul Patel (Great Falls, VA); Gary Schanman (Cherry Hills Village, CO)

Assignee: CHARTER COMMUNICATIONS OPERATING, LLC

H04N21/23424G06N20/00G06Q30/0269H04N21/2353H04N21/45457

Abstract

Claims (47)

1. A method for dynamic advertising insertion for a user, comprising:

obtaining a video program comprising a sequence of segments;

generating metadata describing at least a specific one of the segments of the video program;

building an enhanced user profile of the user based on the generated metadata;

based at least in part on the generated metadata describing the specific segment and the enhanced user profile built based on the generated metadata, selecting advertising content corresponding to the specific segment; and

generating an output video stream comprising the sequence of segments, wherein the selected advertising content is displayed to the user in connection with the specific segment;

wherein generating the metadata comprises at least scene detection using at least one of artificial intelligence and machine learning; and

wherein the selected advertising content is inserted into the output video stream between the specific segment and another segment;

further comprising determining, using the generated metadata, a preference of said user to watch said specific segment of the video program as opposed to the entire video program, wherein the profile is updated based at least in part on the preference and the specific segment is selected based on the preference of said user to watch said specific segment as opposed to the entire video program.

2. The method of claim 1 , wherein at least the specific segment comprises an image corresponding to a point of time within the video program.

3. The method of claim 1 , wherein at least the specific segment comprises a scene corresponding to a period of time within the video program.

4. The method of claim 1 , wherein the metadata indicates at least one object, person, location, event, or action shown within at least a portion of the specific segment.

5. The method of claim 1 , wherein the metadata indicates at least one sentiment or emotion corresponding to at least a portion of the specific segment.

6. The method of claim 1 , wherein selecting the advertising content comprises using the profile of the given user to anticipate an emotional response of the given user to the specific segment.

7. The method of claim 1 , wherein the profile of the given user comprises a probability that the given user supports a first team, further comprising selecting the advertising content to be favorable to the first team, despite the given user being geographically located in a region associated with a second team different than the first team.

8. The method of claim 1 , wherein the video program further comprises respective cues between the segments, and wherein a cue between the specific segment and another segment is replaced in the output video stream with the selected advertising content corresponding to the specific segment.

9. The method of claim 1 , wherein extracting the metadata describing at least the specific segment comprises determining a time within the video program at which the specific segment ends.

10. The method of claim 9 , further comprising inserting a cue corresponding to the specific segment within the video program at the determined time at which the specific segment ends, wherein generating the output video stream comprises replacing the cue corresponding to the specific segment with the selected advertising content corresponding to the specific segment.

11. The method of claim 1 , wherein selecting the advertising content corresponding to the specific segment comprises determining that at least a portion of the advertising content shows at least one object, person, or location which is also shown in at least a portion of the specific segment.

12. A system for dynamic advertising insertion for a user, comprising:

a memory; and

at least one processor coupled to the memory, the processor being operative:

to obtain a video program comprising a sequence of segments;

to generate metadata describing at least a specific one of the segments of the video program;

to build an enhanced user profile of the user based on the generated metadata;

based at least in part on the generated metadata describing the specific segment and the enhanced user profile built based on the generated metadata, to select advertising content corresponding to the specific segment; and

to generate an output video stream comprising the sequence of segments, wherein the selected advertising content is displayed to the user in connection with the specific segment;

wherein generating the metadata comprises at least scene detection using at least one of artificial intelligence and machine learning; and

wherein the selected advertising content is inserted, by the processor, into the output video stream between the specific segment and another segment;

wherein the at least one processor is further operative to determine, using the generated metadata, a preference of said user to watch said specific segment of the video program as opposed to the entire video program, wherein the profile is updated based at least in part on the preference and the specific segment is selected based on the preference of said user to watch said specific segment as opposed to the entire video program.

13. A computer program product comprising a non-transitory machine-readable storage medium having machine-readable program code for dynamic advertising insertion for a user embodied therewith, said machine-readable program code comprising machine-readable program code configured:

to obtain a video program comprising a sequence of segments;

to generate metadata describing at least a specific one of the segments of the video program;

to build an enhanced user profile of the user based on the generated metadata;

based at least in part on the generated metadata describing the specific segment and the enhanced user profile built based on the generated metadata, to select advertising content corresponding to the specific segment; and

to generate an output video stream comprising the sequence of segments, wherein the selected advertising content is displayed to the user in connection with the specific segment;

wherein generating the metadata comprises at least scene detection using at least one of artificial intelligence and machine learning; and

wherein the selected advertising content is inserted, by the processor, into the output video stream between the specific segment and another segment;

wherein the machine-readable program code is further configured to determine, using the generated metadata, a preference of said user to watch said specific segment of the video program as opposed to the entire video program, wherein the profile is updated based at least in part on the preference and the specific segment is selected based on the preference of said user to watch said specific segment as opposed to the entire video program.

14. The method of claim 10 , wherein the inserted cue includes the generated metadata, and wherein the metadata indicates at least one of:

at least one object, person, location, event, or action shown within at least a portion of the specific segment; and

at least one sentiment or emotion corresponding to at least a portion of the specific segment.

15. The method of claim 10 , wherein the inserted cue does not include the generated metadata, but includes an identifier permitting lookup of the metadata, and wherein the metadata indicates at least one of:

at least one object, person, location, event, or action shown within at least a portion of the specific segment; and

at least one sentiment or emotion corresponding to at least a portion of the specific segment.

16. The method of claim 10 , wherein said scene detection comprises marking said specific segment with a content taxonomy, wherein selecting advertising content corresponding to the specific segment comprises using at least one of artificial intelligence and machine learning to select said advertising content based on matching said content taxonomy.

17. The method of claim 16 , further comprising augmenting said inserted cue with said content taxonomy.

Assignments (5)

Continuity (1)

References Cited (72)