PREDICTING CONTENT CONSUMPTION

• US 20160335645A1
• Filed: 05/12/2015
• Published: 11/17/2016
• Est. Priority Date: 05/12/2015
• Status: Active Grant

• Current Assignee: Yahoo AD Tech LLC
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Bentley, Frank Richard, Holz, Christian, Farahat, Ayman
• Granted Patent: US 10,692,098 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 10/067 Enterprise or organisation modelling
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data

Abstract

Methods and systems for predicting content consumption are provided herein. An application log of a user, comprising a user'"'"'s application data, and a viewing log of the user, comprising the user'"'"'s viewing data (e.g., television programs watched by the user), may be evaluated over a time period to construct a model. The model may comprise a correlation between the viewing log and the application log during the time period (e.g., what applications the user interacts with while watching a program). Second application data, regarding application usage of a second user, may be extracted. The model may be applied to the second application data to identify an expected viewing action of the second user (e.g., what program the second user is likely to watch during the time period based upon applications used by the second user). The second user may be provided with content related to the expected viewing action.

Claims

1. A system for predicting content consumption, comprising:

a content consumption component configured to;

extract viewing data regarding viewing actions of a user on a viewing device;

extract application data regarding application usage of the user on a client device;

generate a viewing log, for the user, based upon the viewing data;

generate an application log, for the user, based upon the application data;

evaluate the viewing log and the application log over a time period to construct a model comprising a correlation between the viewing log and the application log during the time period;

extract second application data regarding application usage of a second user; and

apply the model to the second application data to identify an expected viewing action of the second user.

2. The system of claim 1, the content consumption component configured to:

provide the second user with content related to the expected viewing action.

3. The system of claim 1, the content consumption component configured to:

identify the user based upon the viewing device and the client device sharing an identifier.

4. The system of claim 1, the content consumption component configured to:

identify a program specified in the viewing log;

identify a timestamp in the program;

identify an application that the user utilizes during a time specified by the timestamp; and

responsive to the expected viewing action indicating the second user is viewing the program, provide the second user with an application recommendation, comprising a recommendation of the application, based upon the timestamp.

5. The system of claim 4, the timestamp corresponding to an event comprising at least one of an advertisement, a song, a catchphrase, a performance, or an appearance of an actor or actress during the program.

6. The system of claim 1, the content consumption component configured to:

extract the viewing data by utilizing at least one of audio fingerprinting, watermarking, visual matching, logging within a video playing application, or closed caption data.

7. The system of claim 1, the content consumption component configured to:

identify a time during a program when a probability indicates the second user is not viewing the program.

8. The system of claim 1, the content consumption component configured to:

apply external data about a program and a second program available to the viewing device during the time period; and

responsive to the external data indicating a greater number of users are viewing the program as compared to the second program, construct the model to assign a higher likelihood score to the program relative to the second program.

9. The system of claim 1, the content consumption component configured to:

responsive to identifying the expected viewing action comprising an identification of a program, add information about the program to a user interest profile of the second user.

10. A method for predicting content consumption, comprising:

extracting viewing data regarding viewing actions of a user on a viewing device;

extracting application data regarding application usage of the user on a client device;

generating a viewing log, for the user, based upon the viewing data;

generating an application log, for the user, based upon the application data;

evaluating the viewing log and the application log over a time period to construct a model comprising a correlation between the viewing log and the application log during the time period;

extracting second viewing data regarding viewing actions of a second user; and

apply the model to the second viewing data to identify an expected application usage of the second user.

11. The method of claim 10, comprising:

providing the second user with an application recommendation related to the expected application usage.

12. The method of claim 10, comprising:

identifying the user based upon the viewing device and the client device sharing at least one of login credentials, account information, an IP address, or a communication connection.

13. The method of claim 10, comprising:

identifying a program specified in the viewing log;

identifying a timestamp in the program;

identifying an application that the user utilizes during a time specified by the timestamp; and

responsive to an occurrence of the time, recommending the application to the second user.

14. The method of claim 13, the timestamp corresponding to an event comprising at least one of an advertisement, a song, a catchphrase, a performance, or an appearance of an actor or actress during the program.

15. The method of claim 10, comprising:

extracting the viewing data by utilizing at least one of audio fingerprinting, watermarking, visual matching, logging within a video playing application, or closed caption data.

16. The method of claim 10, comprising:

identifying a time during a program when a probability indicates the second user is not viewing the program because the second user is utilizing an application.

17. The method of claim 10, comprising:

responsive to identifying the expected application usage comprising an identification of an application, adding information about the application to a user interest profile of the second user.

18. A system for predicting content consumption, comprising:

a content consumption component configured to;

extract viewing data regarding viewing actions of a user on a viewing device;

extract application data regarding application usage of the user on a client device;

generate a viewing log, for the user, based upon the viewing data;

generate an application log, for the user, based upon the application data;

evaluate the viewing log and the application log over a time period to construct a model comprising a correlation between the viewing log and the application log during the time period;

extract second application data regarding application usage of a second user;

apply the model to the second application data to identify an expected viewing action of the second user; and

provide the second user with content related to the expected viewing action.

19. The system of claim 18, the content consumption component configured to:

identify the user based upon the viewing device and the client device sharing an identifier, the identifier comprising at least one of login credentials, account information, an IP address, or a communication connection.

20. The system of claim 18, the content consumption component configured to:

identify an application that the user utilizes during a time specified by a timestamp in a program specified in the viewing log; and

responsive to identifying viewing the program as the expected viewing action, provide the second user with an application recommendation comprising recommending the application based upon the timestamp.