DETERMINING AN INVITATIONAL CONTENT ITEM TYPE BASED ON PREDICTED USER ATTENTION

• US 20140215086A1
• Filed: 01/29/2013
• Published: 07/31/2014
• Est. Priority Date: 01/29/2013
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Pitschel, Donald W., Chaudhri, Imran A., Newman, Lucas
• Granted Patent: US 9,426,242 B2
• Time in Patent Office: Days
• US Class Current: 709/231
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0267 Wireless devices
• CPC Class Codes: H04L 65/1089 by adding media; by removing media
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04L 67/55 Push-based network services
• CPC Class Codes: H04W 4/027 using movement velocity, acceleration information
• CPC Class Codes: H04W 48/04 based on user or terminal location or mobility data, e.g. moving direction, speed

Abstract

A media channel can include a mix of media items and invitational content items. At some point during the playback of the media channel an invitational content item can be presented. In some cases, the invitational content items eligible for presentation can be of differing types, such as video and audio. In can be advantageous to restrict presentation of video invitational content items to times when a user is likely to view the screen of the client device during playback of the invitational content item. To accomplish this one or more heuristics or rules can be applied to client device data to predict a user attention level. The user attention level can then be correlated to an invitational content item type, which can then be used to select an invitational content item for playback.

Claims

1. A computer-implemented method comprising:

determining an existence of a plurality of invitational content item types including at least audio and video;

predicting a user attention level by applying at least one attention predicting rule to client device data;

designating an invitational content item type preference based on the predicted user attention level; and

selecting an invitational content item based at least in part on the invitational content item type preference.

2. The method of claim 1, wherein predicting a user attention level further comprises:

predicting a user attention level of visual attentive when the client device data includes screen unlocked and media player application open in foreground.

3. The method of claim 1, wherein predicting a user attention level further comprises:

predicting a user attention level of visual attentive when the client device data includes device type portable and device stationary.

4. The method of claim 1, wherein predicting a user attention level further comprises:

predicting a user attention level of visual attentive when the client device data includes connected to peripheral, device stationary, and at least one of connected to video display or gyroscope data indicates device propped in dock.

5. The method of claim 1, wherein predicting a user attention level further comprises:

predicting a user attention level of visual attentive when the client device data includes media station type is soundtrack.

6. The method of claim 1, wherein predicting a user attention level further comprises:

predicting a user attention level of audio attentive when the client device data includes media station type is fitness or road trip.

7. The method of claim 1, wherein predicting a user attention level further comprises:

predicting a user attention level of visual attentive when the client device data includes at least one of media station entry detected, new media station initiated, or media item skip detected.

8. A computer-implemented method comprising:

predicting, via a processor, a user attention level by applying one or more user attention predicting rules to client device data;

designating an invitational content item type based on the predicted user attention level; and

presenting an invitational content item matching the designated invitational content type within a media stream.

9. The method of claim 8, wherein predicting a user attention level occurs in response to detecting an invitational content item triggering event during playback of the media stream.

10. The method of claim 8, wherein the invitational content item type is selected from a set consisting of an audio type and a video type.

11. The method of claim 8, wherein client device state data includes at least one of device type, accelerometer data, gyroscope data, compass data, media player state data, media stream state data, ambient light data, device lock state, or device peripheral connection data.

12. The method of claim 8, wherein a video invitational content item is selected when user attention level is identified as visually attentive.

13. A manufacture comprising:

a non-transitory computer-readable storage medium; and

a computer executable instruction stored on the non-transitory computer-readable storage medium which, when executed by a computing device, causes the computing device to perform a method comprising;

applying one or more user attention heuristics to a set of device data items to predict a user attention level, the user attention level indicating a likelihood that a user will view an invitational content item presented on a device;

assigning an invitational content item type of video when the predicted user attention level is visual attentive; and

selecting an invitational content item based on the invitational content item type, the invitational content item selected for presentation within a media stream of content items and invitational content items.

14. The manufacture of claim 13, wherein each user attention heuristic in the one or more user attention heuristics is assigned a weight, and overriding the invitational content item type of video when all device data items are below a predefined threshold weight.

15. The manufacture of claim 13, further comprising:

overriding the assigned invitational content item type of video based on an analysis of a second set of device data items.

16. The manufacture of claim 13, further comprising:

overriding the assigned invitational content item type of video based on a media stream sponsor preference.

17. The manufacture of claim 13, further comprising:

overriding the assigned invitational content item type of video based on invitational content campaign preferences.

18. The manufacture of claim 13, further comprising:

assigning a confidence score to the predicted user attention level.

19. The manufacture of claim 13, wherein selecting an invitational content item further comprises:

prioritizing a plurality of invitational content items based on the invitational content item type.

20. A system comprising:

a processor;

a first module configured to control the processor to detect an invitational content item triggering event during playback of a media stream;

a second module configured to control the processor to predict a user attention level by applying at least one attention predicting rule to client device data;

a third module configured to control the processor to set an invitational content item type based on the predicted user attention level, wherein the predicted user attention level is one of visual attentive or audio attentive; and

a fourth module configured to control the processor to select an invitational content item based on the invitational content item type.

21. The system of claim 20, wherein the invitational content item type is selected from a set comprising an audio type and a video type.

22. The system of claim 21, wherein an invitational content item with a type of audio is assigned a lower cost than an invitational content item with a type of video.

23. The system of claim 21, wherein selecting an invitational content item further comprises:

selecting an invitational content item having an audio type when the predicted user attention level is audio attentive; and

selecting an invitational content item having a video type when the predicted attention level is visually attentive.

24. A computer-implemented method comprising:

applying, via a processor, a first set of attention predicting rules to a first set of device data items to predict a user attention level;

designating an invitational content item type based on the predicted user attention level;

analyzing a second set of device data items to generate a user attention level override value; and

selecting an invitational content item for presentation within a media stream, the selecting based at least in part on the invitational content item type and the user attention level override value.

25. The method of claim 24, wherein the first set of device state data items includes at least one of device type, accelerometer data, gyroscope data, compass data, media player state data, media stream state data, device lock state, or device peripheral connection data, and the second set of device state data items includes at least one of battery level or ambient light.

26. The method of claim 24, wherein the predicted user attention is visual attentive, the second set of device state data includes a battery level below a predefined threshold, the user attention level override value is override video, and the selected invitational content item type is audio.

27. The method of claim 24, wherein the predicted user attention is visual attentive, the second set of device state data includes ambient light data below a predefined threshold, the user attention level override value is override video, and the selected invitational content item type is audio.

28. The method of claim 24, wherein selecting an invitational content item further comprises prioritizing a plurality of invitational content items based on the invitational content item type.