Weighting user feedback events based on device context

• US 10,083,232 B1
• Filed: 12/15/2014
• Issued: 09/25/2018
• 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): Peng, Huawen A
• Application Number:
  US14/571,132
• Time in Patent Office: 1,380 Days
• CPC Class Codes: G06F 16/639 using playlists
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: H04N 21/251 Learning process for intelligent management, e.g. learning user preferences for recommending movies details of learning user preferences for the retrieval of video data in a video database G06F16/739; computer systems using learning methods G06N3/08
• CPC Class Codes: H04N 21/44218 Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program methods or arrangements for recognising human body or animal bodies or body parts G06V40/10; methods or arrangements for acquiring or recognising human faces, facial parts, facial sketches, facial expressions G06V40/16; methods or arrangements for recognising movements or behaviour G06V40/20; arrangements for identifying users in broadcast systems H04H60/45
• CPC Class Codes: H04N 21/4756 for rating content, e.g. scoring a recommended movie
• CPC Class Codes: H04N 21/4826 using recommendation lists, e.g. of programs or channels sorted out according to their score
• CPC Class Codes: H04N 21/6582 Data stored in the client, e.g. viewing habits, hardware capabilities, credit card number arrangements where receivers interact with the broadcast H04H20/38
• CPC Class Codes: H04N 21/8113 comprising music, e.g. song in MP3 format

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 system comprising:

an electronic data store configured to at least store ratings data for one or more music items available from an electronic catalog and contextual information associated with respective user ratings, said ratings data submitted from a plurality of users of the electronic catalog; 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;

access, from the electronic data store, rating data indicative of a user rating of a music item in association with a music service provided through the electronic catalog;

access, from the electronic data store, contextual information associated with the user rating, said contextual information being automatically generated by a mobile device of the user based on (1) monitored user interactions, outside of interactions associated with the user rating of the music item, with the mobile device or (2) based on information detected via one or more sensors of the mobile device, the accessed contextual information being generated during a time period associated with the user providing the user rating, the mobile device being used by the user to provide the user rating, and said contextual information collected at a time when the user provided the user rating;

determine an intensity of the user rating of the music item based at least in part on the contextual information;

determine a music item recommendation for the user based at least in part on the provided user rating and the determined intensity; and

provide the music item recommendation to the mobile device for presentation to the user with a user-selectable display element selectable to initiate streaming, thereby enabling the mobile device to stream the music item recommendation.

2. The system of claim 1, wherein the music item is a song, an audiobook, or an audiovisual media item.

3. The system of claim 1, wherein the rating data and the contextual information are received from a mobile music application installed on the mobile device.

4. The system of claim 1, wherein to determine an intensity of the user rating of the music item based at least in part on the contextual information the computing system is further configured to:

determine that the user was interacting with the mobile device during playback of the music item before the user rating was provided; and

decrease the intensity of the user rating, relative to a different intensity of the user rating if the user was not interacting with the mobile device during playback of the music item before the user rating was provided.

5. The system of claim 1, wherein to determine an intensity of the user rating of the music item based at least in part on the contextual information the computing system is further configured to:

determine that the user was not interacting with the mobile device during playback of the music item before the user rating was provided; and

increase the intensity of the user rating.

6. The system of claim 1, wherein the contextual information includes information indicative of what the user was doing in a different application installed on the mobile device before the user rating was provided.

7. The system of claim 1, wherein the contextual information includes accelerometer data associated with the mobile device indicating whether the mobile device was stationary or in motion when the user rating was provided.

8. The system of claim 1, wherein the contextual information includes one or more of:

data describing how long the user has been listening to music in the current or past listening sessions, other music items the user may have listened to and/or skipped in the current or past listening sessions, and/or a progress indication of how much of the music item was played before the user rating was provided.

9. The system of claim 1, wherein the music item recommendation is provided in a web page for display in a web browser application installed on the mobile device.

10. The system of claim 1, wherein the contextual information includes, screen display state information indicating whether a screen display associated with the mobile device was on during the time period, or a location of the mobile device.

11. A computer-implemented method comprising:

accessing, from an electronic data store, rating data indicative of a user rating of a music item in association with a music service provided by the electronic catalog,

said electronic data store configured to at least store ratings data for one or more music items available from an electronic catalog and contextual information associated with respective user ratings, said ratings data submitted from a plurality of users of the electronic catalog;

accessing, from the electronic data store, contextual information associated with the user rating, said contextual information being automatically generated by a mobile device of the user based on (1) monitored user interactions, outside of interactions associated with the user rating of the music item, with the mobile device or (2) based on information detected via one or more sensors of the mobile device, the accessed contextual information being generated during a time period associated with the user providing the user rating, the mobile device being used by the user to provide the user rating, and said contextual information collected at a time when the user provided the user rating;

determining an intensity of the user rating of the music item based at least in part on the contextual information;

determining a music item recommendation for the user based at least in part on the provided user rating and the determined intensity; and

providing the music item recommendation to the mobile device for presentation to the user.

12. The computer-implemented method of claim 11, wherein the music item is a song, an audiobook, or an audiovisual media item.

13. The computer-implemented method of claim 11, wherein the rating data and the contextual information are received from a mobile music application installed on the mobile device.

14. The computer-implemented method of claim 11, wherein the intensity of the user rating of the music item is determined at least in part by generating a measure of the effort expended by the user to rate the music item.

15. The computer-implemented method of claim 11, wherein the intensity of the user rating of the music item is determined at least in part by generating a measure of a degree to which the user modified activity to rate the music item.

16. The computer-implemented method of claim 11, wherein determining an intensity of the user rating of the music item based at least in part on the contextual information further comprises:

determining whether the user was interacting with the mobile device during playback of the music item before the user rating was provided; and

in response to determining that the user was not interacting with the mobile device during playback of the music item before the user rating was provided, increasing the intensity of the user rating;

or

in response to determining that the user was interacting with the mobile device during playback of the music item before the user rating was provided, decreasing the intensity of the user rating, relative to a different intensity of the user rating if the user was not interacting with the mobile device during playback of the music item before the user rating was provided.

17. The computer-implemented method of claim 11, wherein the contextual information includes one or more of:

data describing how long the user has been listening to music item in the current or past listening sessions, other music items the user may have listened to and/or skipped in the current or past listening sessions, and/or a progress indication of how much of the music item was played before the user rating was provided.

18. The computer-implemented method of claim 11, wherein the contextual information includes one or more of accelerometer data associated with the mobile device indicating whether the device was in motion and whether the user discontinued such motion just before the user rating was provided, screen display state information indicating whether a screen display associated with the mobile device was on during the time period, or a location of the mobile device.