IP Library Granted Patent US 12701295
Granted Patent B2
US 12701295 · App. 18/394,645 · Granted Aug 4, 2026

Methods, systems, and apparatuses for determining viewership

Inventors: Robert Alan Bress (New Providence, NJ); Christopher Paul Whitely (Summit, NJ); Zhao Xing (Philadelphia, PA)
Assignee: Comcast Cable Communications, LLC
H04N21/4666G06N3/061G06N3/08G06N7/01H04N21/44204H04N21/4524H04N21/4667
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 12701295
App. No.
18/394,645
Granted
Aug 4, 2026
Kind
B2
Abstract

Methods, systems, and apparatuses for determining viewership of a content item are described herein. Machine learning techniques may be used to determine which user(s) among a user group at a multi-user location is consuming a content item. A machine learning model may be trained using demographic attributes and content attributes associated with a plurality of single-user locations. A probability engine may train a machine learning model using the demographic attributes and content attributes and one or more machine learning algorithms. The trained machine learning model may be used to determine which user(s) among at least two users is consuming a content item at a multi-user location at which multiple people reside.

Claims (45)

1 . A method comprising:

receiving, by a computing device, a plurality of demographic attributes associated with at least two users at a user location;

determining, by a trained machine learning model based on the plurality of demographic attributes, an initial viewing probability score of a content item being presented at the user location for each of the at least two users;

adjusting, based on a plurality of received network data associated with the at least two users, the initial viewing probability score for each of the at least two users; and

sending, based on the adjusted viewing probability score for each of the at least two users, a second content item to be presented at the user location.

2 . The method of claim 1 , wherein the plurality of demographic attributes comprises one or more of age, gender, race, religion, income, or language spoken.

3 . The method of claim 1 , further comprising receiving content metadata associated with the content item being presented at the user location, wherein the initial viewing probability score is further based on the content metadata.

4 . The method of claim 1 , wherein the initial viewing probability score indicates a percentage level of confidence that a particular user of the at least two users is viewing the content item.

5 . The method of claim 1 , further comprising receiving a plurality of network data associated with the at least two users and the user location.

6 . The method of claim 1 , wherein the plurality of received network data comprises one or more of network data associated with a user device, network data associated with a date or time the content item was viewed, natural language processing data received by a voice-enabled user device at the user location, or account activity for a user device associated with one or more of the at least two users.

7 . An apparatus, comprising:

one or more processors; and

a memory storing processor-executable instructions, that when executed by the one or more processors, cause the apparatus to:

receive a plurality of demographic attributes associated with at least two users at a user location;

determine, by a trained machine learning model based on the plurality of demographic attributes, an initial viewing probability score of a content item being presented at the user location for each of the at least two users;

adjust, based on a plurality of received network data associated with the at least two users, the initial viewing probability score for each of the at least two users; and

send, based on the adjusted viewing probability score for each of the at least two users, a second content item to be presented at the user location.

8 . The apparatus of claim 7 , wherein the plurality of demographic attributes comprises one or more of age, gender, race, religion, income, or language spoken.

9 . The apparatus of claim 7 , wherein the processor-executable instructions, when executed by the one or more processors, further cause the apparatus to receive content metadata associated with the content item being presented at the user location, wherein the initial viewing probability score is further based on the content metadata.

10 . The apparatus of claim 7 , wherein the initial viewing probability score indicates a percentage level of confidence that a particular user of the at least two users is viewing the content item.

11 . The apparatus of claim 7 , wherein the processor-executable instructions, when executed by the one or more processors, further cause the apparatus to receive a plurality of network data associated with the at least two users and the user location.

12 . The apparatus of claim 7 , wherein the plurality of received network data comprises one or more of network data associated with a user device, network data associated with a date or time the content item was viewed, natural language processing data received by a voice-enabled user device at the user location, or account activity for a user device associated with one or more of the at least two users.

13 . One or more non-transitory computer-readable media storing processor-executable instructions that, when executed by at least one processor, cause the at least one processor to:

receive a plurality of demographic attributes associated with at least two users at a user location;

determine, by a trained machine learning model based on the plurality of demographic attributes, an initial viewing probability score of a content item being presented at the user location for each of the at least two users;

adjust, based on a plurality of received network data associated with the at least two users, the initial viewing probability score for each of the at least two users; and

send, based on the adjusted viewing probability score for each of the at least two users, a second content item to be presented at the user location.

14 . The one or more non-transitory computer-readable media of claim 13 , wherein the plurality of demographic attributes comprises one or more of age, gender, race, religion, income, or language spoken.

15 . The one or more non-transitory computer-readable media of claim 13 , wherein the processor-executable instructions, when executed by the at least one processor, further cause the at least one processor to receive content metadata associated with the content item being presented at the user location, wherein the initial viewing probability score is further based on the content metadata.

16 . The one or more non-transitory computer-readable media of claim 13 , wherein the initial viewing probability score indicates a percentage level of confidence that a particular user of the at least two users is viewing the content item.

17 . The one or more non-transitory computer-readable media of claim 13 , wherein the processor-executable instructions, when executed by the at least one processor, further cause the at least one processor to receive a plurality of network data associated with the at least two users and the user location.

18 . The one or more non-transitory computer-readable media of claim 13 , wherein the plurality of received network data comprises one or more of network data associated with a user device, network data associated with a date or time the content item was viewed, natural language processing data received by a voice-enabled user device at the user location, or account activity for a user device associated with one or more of the at least two users.

19 . A system comprising:

a first computing device configured to:

receive a plurality of demographic attributes associated with at least two users at a user location;

determine, by a trained machine learning model based on the plurality of demographic attributes, an initial viewing probability score of a content item being presented at the user location for each of the at least two users;

adjust, based on a plurality of received network data associated with the at least two users, the initial viewing probability score for each of the at least two users; and

send, based on the adjusted viewing probability score for each of the at least two users, a second content item to be presented at the user location; and

a second computing device configured to:

receive the second content item.

20 . The system of claim 19 , wherein the plurality of demographic attributes comprises one or more of age, gender, race, religion, income, or language spoken.

21 . The system of claim 19 , wherein the first computing device is further configured to receive content metadata associated with the content item being presented at the user location, wherein the initial viewing probability score is further based on the content metadata.

22 . The system of claim 19 , wherein the initial viewing probability score indicates a percentage level of confidence that a particular user of the at least two users is viewing the content item.

23 . The system of claim 19 , wherein the first computing device is further configured to receive a plurality of network data associated with the at least two users and the user location.

24 . The system of claim 19 , wherein the plurality of received network data comprises one or more of network data associated with a user device, network data associated with a date or time the content item was viewed, natural language processing data received by a voice-enabled user device at the user location, or account activity for a user device associated with one or more of the at least two users.