System, method and medium for utilizing current and historical device context information to determine content item recommendations

• US 10,515,399 B1
• Filed: 12/15/2014
• Issued: 12/24/2019
• Est. Priority Date: 12/15/2014
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Durham, Brandon Scott, Latin-Stoermer, Toby Ray, Malek, Darren Levi, McGilliard, Christopher Lon
• Primary Examiner(s): Smith, Jeffrey A.
• Assistant Examiner(s): Duraisamygurusamy, Lalith M
• Application Number:
  US14/571,180
• Time in Patent Office: 1,835 Days
• Field of Search: 705 267
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

The present disclosure provides computer-implemented systems and processes for augmenting user ratings of items, such as a rating of a song playing on a user device, by analyzing contextual information, such as user and/or device activity data associated with the device. The contextual information may be used to determine an associated intensity of the rating or feedback. The determined intensity levels can be used to weigh the associated rating events and improve the quality of item recommendations that are based on such ratings. Contextual information may indicate whether the user transitioned from another application to rate an item, device status information, and so on. In one embodiment, contextual information can be used to assess how intensely the user feels about a music item and to provide improved music recommendations, such as songs to provide in a playlist or radio station, based on the intensity.

Claims

1. A computer-implemented method comprising:

under control of specific computer-executable instructions;

generating current contextual information associated with playback of a song being streamed from a network-based music service,

wherein generating current contextual information comprises;

monitoring information detected via sensors of a consumer computing device, and

determining, based on the monitored information, information indicative of a physical activity being performed by a user of the consumer computing device,

and wherein the current contextual information is generated during playback of the song via a music application installed on the consumer computing device of the user;

identifying, based on the generated current contextual information, the physical activity being performed by the user;

determining one or more songs previously played by the user while performing the identified physical activity;

ranking a plurality of candidate songs, the candidate songs comprising, at least, the determined songs, and the determined songs receiving boosts in the ranking based on being played by the user while performing the identified physical activity;

causing a next song selected based on the ranking to be played by the music application.

2. The computer-implemented method of claim 1, further comprising analyzing the contextual information to determine a predicted intensity indicative of a degree to which the user may like the next song.

3. The computer-implemented method of claim 1, wherein the music application is a mobile application installed on the consumer computing device.

4. The computer-implemented method of claim 1,

wherein monitoring information obtained from sensors comprises one or more of:

obtaining motion sensor data detected via an accelerometer of the consumer computing device, the motion sensor data indicating whether the device was in motion during playback of the song, or

obtaining location data detected via a global positioning system sensor;

and wherein for a particular physical activity associated with running, determining information indicative of the particular physical activity comprises determining, based on the motion sensor data, whether the device was in motion corresponding to running and/or determining, based on the location data, whether a speed associated with the consumer computing device corresponds to running.

5. The computer-implemented method of claim 1, wherein selecting the next song for the user is based at least in part on a similarity rating between the song previously listened to by the user while performing the physical activity to the plurality of candidate next songs.

6. A system comprising:

an electronic data store configured to at least store user activity data for a plurality of users of an electronic catalog, the user activity data including contextual information associated with user activity with respect to one or more music items available from the electronic catalog accessed by the plurality of users; and

a computing system comprising one or more hardware computing devices, said computing system in communication with the electronic data store and configured to at least;

receive, from a consumer computing device, current contextual information associated with a user listening to a music item, said current contextual information identifying an activity engaged in by the user during playback of the music item on the consumer computing device, wherein the consumer computing device generates the current contextual information based on monitoring information detected via sensors of the consumer computing device;

access, from the electronic data store, historical user activity information associated with the user, the historical user activity information indicating a plurality of music items previously listened to by the user and historical contextual information associated with playback of at least some of the plurality of music items,

wherein the historical contextual information indicates respective activities performed by the user during playback of the at least some of the music items;

determine, based on a comparison of the identified activity and the historical contextual information, one or more music items previously played by the user while engaged in the activity;

ranking a plurality of candidate music item recommendations, the candidate music item recommendations comprising, at least, the determined music items, and the determined music items receiving boosts in the ranking; and

provide a music item recommendation selected based on the ranking for presentation via the consumer computing device.

7. The system of claim 6, wherein the music item is a song, an audiobook, or an audiovisual media item.

8. The system of claim 6, wherein the contextual information is received from a music application installed on the consumer computing device.

9. The system of claim 6, wherein the music item is streamed to the consumer computing device from a network-based music service as part of a radio station or a playlist.

10. The system of claim 6, wherein the contextual information includes information indicative of what the user was doing in a different application installed on the consumer computing device during playback of the music item.

11. The system of claim 6, wherein ranking the candidate music item recommendations is based at least in part on a comparison of (1) an intensity of a user rating associated with the music item previously listened to by the user while engaged in the activity to (2) intensity of user ratings associated with the plurality of candidate music item recommendations.

12. The system of claim 11, wherein the intensity of the user rating of the music item previously listened to by the user is determined at least in part by a measure of the effort expended by the user to provide a rating for the music item.

13. The system of claim 6, wherein the information detected via sensors includes motion sensor data associated with the consumer computing device indicating whether the device was stationary or in motion during playback of the music item.

14. The system of claim 6, wherein the contextual information includes screen display state information indicating whether a screen display associated with the consumer computing device was on within a predetermined period of time associated with playback of the music item.

15. The system of claim 6, wherein the information detected via sensors includes location information of the consumer computing device.

16. The system of claim 6, wherein the music item recommendation is provided in a web page for display in a web browser application installed on the consumer computing device.

17. Non-transitory physical computer storage comprising computer-executable instructions stored thereon that, when executed by a hardware processor, are configured to perform operations comprising:

determining an intensity of a user rating of an audiovisual content item available from a music service based at least in part on contextual information associated with playback of the audiovisual content item via a consumer computing device, said contextual information identifying a physical user activity engaged in during playback of the audiovisual content item, and said contextual information being determined based on monitoring sensor information associated with the consumer computing device;

accessing listening history information associated with the user, the listening history information identifying, at least, a plurality of audiovisual content items and respective physical user activities engaged in during playback of the audiovisual content items;

ranking a plurality of candidate audiovisual content items, the candidate audiovisual content items comprising particular audiovisual content items played during engagement of the physical user activity, and the particular audiovisual content items receiving boosts in the ranking; and

providing an audiovisual content item recommendation selected based on the ranking for presentation via the consumer computing device.

18. The non-transitory physical computer storage of claim 17, wherein the audiovisual content item recommendation is determined based at least in part on historical contextual information and intensity of user ratings for audiovisual content items previously accessed by the user.

19. The non-transitory physical computer storage of claim 17, wherein the audiovisual content item is a song, an audiobook, or a video.

20. The non-transitory physical computer storage of claim 17, wherein the contextual information is gathered by a mobile application installed on the consumer computing device.

21. The non-transitory physical computer storage of claim 17, wherein the audiovisual content item recommendation is provided in a web page for display in a web browser application installed on the consumer computing device.

22. The non-transitory physical computer storage of claim 17, wherein the contextual information includes one or more of:

motion sensor data associated with the consumer computing device indicating whether the consumer computing device was stationary or in motion during playback of the audiovisual content item, screen display state information indicating whether a screen display associated with the consumer computing device was on playback of the audiovisual content item, or a location of the consumer computing device.