Predicting content consumption

• US 10,692,098 B2
• Filed: 05/12/2015
• Issued: 06/23/2020
• Est. Priority Date: 05/12/2015
• Status: Active Grant

• Current Assignee: Yahoo AD Tech LLC
• Original Assignee: Oath Inc. (Verizon Communications Inc.)
• Inventors: Holz, Christian, Bentley, Frank Richard, Farahat, Ayman
• Primary Examiner(s): Elchanti, Tarek
• Application Number:
  US14/710,096
• Publication Number:
  US 20160335645A1
• Time in Patent Office: 1,869 Days
• Field of Search: 705 729, 707624, 726 26, 706 46, 709203, 455418, 719328
• 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 processor; and

memory comprising processor-executable instructions that when executed by the processor cause implementation of a content consumption component configured to;

extract viewing data regarding viewing actions on a viewing device, wherein the viewing actions comprise a first viewing action;

extract application data regarding application usage on a client device, the client device different than the viewing device, wherein the application usage comprises a first application usage;

responsive to determining that the viewing device and the client device share a common login credential or address, determine that the viewing device and the client device are both associated with a first user;

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

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

generate a model based upon (i) the viewing log corresponding to the viewing data regarding the viewing actions on the viewing device and (ii) the application log corresponding to the application data regarding the application usage on the client device, the model indicative of a plurality of correlations between one or more viewing actions on the viewing device and one or more application usages on the client device, wherein the plurality of correlations includes a first correlation between the first viewing action on the viewing device and the first application usage on the client device;

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

responsive to identifying a similarity between at least some of the application usage of the second user and the first application usage associated with the first user based upon the model, identify the first viewing action correlated with the first application usage as an expected viewing action of the second user; and

control transmission of content to a remote device of the second user based upon the expected viewing action.

2. The system of claim 1, the remote device of the second user different than the client device and different than the viewing device.

3. The system of claim 1, the address comprising an IP address.

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 first 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; 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 on a viewing device, wherein the viewing actions comprise a first viewing action;

extracting application data regarding application usage on a client device, the client device different than the viewing device, wherein the application usage comprises a first application usage;

responsive to determining that the viewing device and the client device share a common login credential or address, determining that the viewing device and the client device are both associated with a first user;

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

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

generating a model based upon the viewing log and the application log, the model indicative of a plurality of correlations between one or more viewing actions and one or more application usages, wherein the plurality of correlations includes a first correlation between the first viewing action and the first application usage;

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

responsive to identifying a similarity between at least some of the viewing actions of the second user and the first viewing action associated with the first user based upon the model, identifying the first application usage correlated with the first viewing action as an expected application usage of the second user; and

controlling transmission of content to a remote device of the second user based upon the expected application usage.

11. The method of claim 10, the content comprising an application recommendation related to the expected application usage.

12. The method of claim 10, the address comprising

an IP address.

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 first 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 processor; and

memory comprising processor-executable instructions that when executed by the processor cause implementation of a content consumption component configured to;

extract viewing data regarding viewing actions of a user on a viewing device, wherein the viewing actions comprise a first viewing action;

extract application data regarding application usage of the user on a client device, wherein the application usage comprises a first application usage;

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

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

generate a model based upon (i) the viewing log corresponding to the viewing data regarding the viewing actions of the user on the viewing device and (ii) the application log corresponding to the application data regarding the application usage of the user on the client device, the model indicative of a plurality of correlations between one or more viewing actions on the viewing device and one or more application usages on the client device, wherein the plurality of correlations includes a first correlation between the first viewing action on the viewing device and the first application usage on the client device;

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

responsive to identifying a similarity between at least some of the application usage of the second user and the first application usage associated with the user based upon the model, identify the first viewing action correlated with the first application usage as an expected viewing action of the second user; and

control transmission of content to a remote device of the second user based upon 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.