Selecting content formats for additional content to be presented along with video content to a user based on predicted likelihood of abandonment

• US 9,451,306 B2
• Filed: 01/03/2012
• Issued: 09/20/2016
• Est. Priority Date: 01/03/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Sarukkai, Ramesh R., Thompson, Kevin O., Huston, Jacob E., Farhi, Philippe
• Primary Examiner(s): Vu, Kieu
• Assistant Examiner(s): Weber, Joy M
• Application Number:
  US13/342,862
• Publication Number:
  US 20130174045A1
• Time in Patent Office: 1,722 Days
• Field of Search: 715/744, 725/32, 725/51
• US Class Current: 1/1
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: H04N 21/23439 for generating different versions
• CPC Class Codes: H04N 21/2358 for generating different versions, e.g. for different recipient devices
• CPC Class Codes: H04N 21/25808 Management of client data terminal profiles in network data switching protocols H04L67/303
• CPC Class Codes: H04N 21/25866 Management of end-user data customer care in data networks H04L41/5077

Abstract

Methods, systems, and computer program products are provided for selecting content formats based on predicted user interest. One example method includes receiving a request to present additional content to a user in association with the user viewing a video content item during a session, identifying one or more candidate content formats, predicting a likelihood that the user will abandon the session for each candidate content format, selecting a format based at least in part on the predicting, determining when to present the additional content to the user, and presenting the additional content in accordance with the selected format.

Claims

1. A computer-implemented method comprising:

receiving, at one or more processors of a computing server from a client device, a request for advertising content to present to the client device during playback of video content;

identifying, by the one or more processors, a first candidate content item format type and a second candidate content item format type, the first candidate content item format type and the second candidate content item format type selected from a group consisting of pre-video, post-video, in stream, overlay, and banner advertising format types;

identifying, by the one or more processors, a user disposition for a current video viewing session based on historical data of previous advertising content presented to the client device, the current video viewing session comprising the playback of the video content and presentation of the advertising content;

predicting, by the one or more processors, for the first candidate content item format type based on the user disposition, a first likelihood that a user of the client device will abandon the current video viewing session prior to completion of the current video viewing session in response to presentation of advertising content of the first candidate content item format type;

predicting, by the one or more processors, for the second candidate content item format type based on the user disposition, a second likelihood that the user of the client device will abandon the current video viewing session prior to completion of the current video viewing session in response to presentation of advertising content of the second candidate content item format type;

determining, by the one or more processors, that the first likelihood is less than the second likelihood;

selecting, by the one or more processors based on the determination, the first candidate advertising format type for presentation of a content item to the client device; and

presenting, by the one or more processors, the content item to the client device in accordance with the first candidate advertising format type.

2. The computer-implemented method of claim 1, further comprises determining that the first likelihood is below a predetermined threshold.

3. The computer-implemented method of claim 2, further comprising determining to withhold a second content item of the second candidate format type based on a determination that the second likelihood is greater than the predetermined threshold.

4. The computer-implemented method of claim 2, wherein determining that the first likelihood is below the predetermined threshold includes determining that the first candidate content item format type is not likely to cause the user to abandon the current video viewing session.

5. The computer-implemented method of claim 1, wherein selecting the content item of the first candidate advertising format type is based on the video content.

6. The computer-implemented method of claim 1, wherein identifying the user disposition is further based on current and historical session data including data related to previous video content presented to the client device, interaction by the user with the previous video content presented to the client device, previous advertising content presented to the client device, interaction by the user with the previous advertising content, and abandonment of previous video viewing sessions by the user.

7. The method of claim 1, further comprising:

identifying, by the one or more processors, a second user disposition for the current video viewing session based on historical data of previous advertising content presented to the client device;

predicting, by the one or more processors, for the first candidate content item format type based on the second user disposition, a third likelihood that the user will abandon the current video viewing session prior to completion of the current video viewing session in response to presentation of advertising content of the first candidate content item format type;

predicting, by the one or more processors, for the second candidate content item format type based on the second user disposition, a fourth likelihood that the user will abandon the current video viewing session prior to completion of the current video viewing session in response to presentation of advertising content of the second candidate content item format type;

selecting, by the one or more processors based on the third likelihood exceeding the fourth likelihood, the second candidate advertising format type for presentation of a second content item to the client device; and

presenting, by the one or more processors, the second content item to the client device in accordance with the second candidate advertising format type.

8. A computer-implemented method comprising:

identifying, by one or more processors of a computing server, a first candidate content item format type and a second candidate content item format type for advertising content to be presented to a client device during playback of video content, the first candidate content item format type and the second candidate content item format type selected from a group consisting of pre-video, post-video, in stream, overlay, and banner advertising format types;

identifying, by the one or more processors, a user disposition for a current video viewing session based on historical data of previous advertising content presented to the client device, the current video session comprising the playback of the video content and presentation of the advertising content;

predicting, by the one or more processors, for the first candidate content item format type based on the user disposition, a first likelihood that a user of the client device will abandon the current video viewing session prior to completion of the current video viewing session in response to presentation of the advertising content of the first candidate content item format type;

predicting, by the one or more processors, for the second candidate content item format type based on the user disposition, a second likelihood that the user of the client device will abandon the current video viewing session prior to completion of the current video viewing session in response to presentation of the advertising content of the second candidate content item format type;

determining, by the one or more processors, that the first likelihood is below a predetermined threshold;

determining, by the one or more processors, that the second likelihood is above the predetermined threshold; and

presenting, by the one or more processors in response to the determination that the first likelihood is below the predetermined threshold and the second likelihood is above the predetermined threshold, a content item to the client device in accordance with the first candidate advertising format type.

9. The method of claim 8, wherein determining that the first likelihood is below the predetermined threshold includes determining that the candidate content item format type is not likely to cause the user to abandon the current video viewing session.

10. A non-transitory computer storage medium encoded with a computer program, the computer program comprising instructions that when executed by one or more processors of a computer server cause the one or more processors to perform operations comprising:

receiving, at the one or more processors from a client device, a request for advertising content to present to the client device during playback of video content;

identifying, by the one or more processors, a first candidate content item format type and a second candidate content item format type, the first candidate content item format type and the second candidate content item format type selected from a group consisting of pre-video, post-video, in stream, overlay, and banner advertising format types;

identifying, by the one or more processors, a user disposition for a current video viewing session based on historical data of previous advertising content presented to the client device, the current video viewing session comprising the playback of the video content and presentation of the advertising content;

predicting, by the one or more processors, for the first candidate content item format type based on the user disposition, a first likelihood that a user of the client device will abandon the current video viewing session prior to completion of the current video viewing session in response to presentation of advertising content of the first candidate content item format type;

predicting, by the one or more processors, for the second candidate content item format type based on the user disposition, a second likelihood that the user of the client device will abandon the current video viewing session prior to completion of the current video viewing session in response to presentation of advertising content of the second candidate content item format type;

determining, by the one or more processors, that the first likelihood is less than the second likelihood;

selecting, by the one or more processors based on the determination, the first candidate advertising format type for presentation of a content item to the client device; and

presenting, by the one or more processors, the content item to the client device in accordance with the first candidate advertising format type.

11. A system comprising:

a device, comprising a network interface in communication with a client device, and a processor executing a session manager, a user disposition identifier, a user behavior predictor, an advertising format type selector, and a content presentation system,

wherein the session manager is configured to;

receive, from the client device via the network interface, a request for advertising content to present to the client device during playback of video content, and

identify a first candidate content item format type and a second candidate content item format type, the first candidate content item format type and the second candidate content item format type selected from a group consisting of pre-video, post-video, in stream, overlay, and banner advertising format types;

wherein the user disposition identifier is configured to identify a user disposition for a current video viewing session based on historical data of previous advertising content presented to the client device, the current video viewing session comprising the playback of the video content and presentation of the advertising content;

wherein the user behavior predictor is configured to;

predict, for the first candidate content item format type based on the user disposition, a first likelihood that a user of the client device will abandon the current video viewing session prior to completion of the current video viewing session in response to presentation of advertising content of the first candidate content item format type;

predict, for the second candidate content item format type based on the user disposition, a second likelihood that the user of the client device will abandon the current video viewing session prior to completion of the current video viewing session in response to presentation of advertising content of the second candidate content item format type;

wherein the advertising format type selector is configured to select, based on a determination that the first likelihood is less than the second likelihood, the first candidate advertising format type for presentation of a content item to the client device; and

wherein the content presentation system is configured to present, via the network interface the content item to the client device in accordance with the first candidate advertising format type.

12. The system of claim 11, wherein the user behavior predictor is further configured to determine that the first candidate content item format type is not likely to cause the user to abandon the current video viewing session.

13. The system of claim 11, wherein the advertising format type selector is further configured to withhold a second content item of the second candidate format type based on a determination that the second likelihood is greater than a predetermined threshold.

14. The system of claim 11, wherein the advertising format type selector is further configured to select the content item of the first candidate advertising format type based additionally on the video content.

15. The system of claim 11, wherein the user disposition identifier is further configured to identify the user disposition based on current and historical session data including data related to previous video content presented to the client device, interaction by the user with the previous video content presented to the client device, previous advertising content presented to the client device, interaction by the user with the previous advertising content, and abandonment of previous video viewing sessions by the user.

16. The system of claim 11,

wherein the user disposition identifier is further configured to identify a second user disposition for the current video viewing session based on historical data of previous advertising content presented to the client device;

and

wherein the user behavior predictor is further configured to;

predict, for the first candidate content item format type based on the second user disposition, a third likelihood that the user will abandon the current video viewing session prior to completion of the current video viewing session in response to presentation of advertising content of the first candidate content item format type, and

predict, for the second candidate content item format type based on the second user disposition, a fourth likelihood that the user will abandon the current video viewing session prior to completion of the current video viewing session in response to presentation of advertising content of the second candidate content item format type;

wherein the advertising format type selector is further configured to;

select, based on the third likelihood exceeding the fourth likelihood, the second candidate advertising format type for presentation of a second content item to the client device; and

wherein the content presentation system is further configured to present the second content item to the client device in accordance with the second candidate advertising format type.

17. The system of claim 11, wherein the user behavior predictor is further configured determine that the first likelihood is below a predetermined threshold.

18. The system of claim 17, wherein determining that the first likelihood is below the predetermined threshold includes determining that the first candidate content item format type is not likely to cause the user to abandon the current video viewing session.

19. A system comprising:

a device, comprising a network interface in communication with a client device, and a processor executing a session manager, a user disposition identifier, a user behavior predictor, an advertising format type selector, and a content presentation system,

wherein the session manager is configured to identify a first candidate content item format type and a second candidate content item format type for advertising content to be presented, via the network interface, to the client device during playback of video content, the first candidate content item format type and the second candidate content item format type selected from a group consisting of pre-video, post-video, in stream, overlay, and banner advertising format types;

wherein the user disposition identifier is configured to identify a user disposition for a current video viewing session based on historical data of previous advertising content presented to the client device, the current video session comprising the playback of the video content and presentation of the advertising content;

wherein the user behavior predictor is configured to;

predict, for the first candidate content item format type based on the user disposition, a first likelihood that a user of the client device will abandon the current video viewing session prior to completion of the current video viewing session in response to presentation of the advertising content of the first candidate content item format type,

predict, for a second candidate content item format type based on the user disposition, a second likelihood that the user of the client device will abandon the current video viewing session prior to completion of the current video viewing session in response to presentation of the advertising content of the second candidate content item format type,

determine that the first likelihood is below a predetermined threshold;

determine that the second likelihood is above the predetermined threshold; and

wherein the content presentation system is configured to present, in response to the determination that the first likelihood is below the predetermined threshold and the second likelihood is above the predetermined threshold, a content item to the client device, via the network interface, in accordance with the first candidate advertising format type.

20. The system of claim 19, wherein determining that the first likelihood is below the predetermined threshold includes determining that the first candidate content item format type is not likely to cause the user to abandon the current video viewing session.