Real-Time Recommendations and Personalization

Patent metadata

Field	Value
Publication number	US-2016274744-A1
Application number	US-201615073214-A
Country	US
Kind code	A1
Filing date	Mar 17, 2016
Priority date	Mar 17, 2015
Publication date	Sep 22, 2016
Grant date	—

Abstract

According to some aspects described herein, content and service providers in a media delivery network may provide improved recommendations and/or personalize a user's experience based on the real-time activity of that user as well as other users. In this way, ever increasing amounts of content may be optimally managed in a way that provides users with the improved and/or personalized experience.

First claim

We claim:

1 . A method comprising:
determining, by a computing device, one or more trends for individual user-clusters of a plurality of user-clusters based on usage events associated with users in each user-cluster of the plurality of user-clusters; determining, by the computing device, a set of user-clusters associated with a first user; receiving, by the computing device, a first trend associated with a first user-cluster of the set of user-clusters; generating, by the computing device, a recommendation for the first user based on the first trend associated with the first user-cluster of the set of user-clusters; and causing output of the recommendation to the first user.

2 . The method of claim 1 , wherein causing output of the recommendation to the first user comprises:
generating a notification operative to allow the first user to accept the recommendation; and causing the notification to be displayed to the first user.

3 . The method of claim 1 , wherein causing output of the recommendation to the first user comprises one or more of:
adding one or more content items to a list of items; removing one or more content items from the list of items; or adjusting a position of one or more content items in the list of items.

4 . The method of claim 1 , further comprising receiving a request for a media content item from the first user, wherein causing output of the recommendation to the first user comprises:
selecting an alternate version of the media content item based on the first trend; and causing the alternate version of the media content item to be displayed to the first user.

5 . The method of claim 1 , wherein causing output of the recommendation to the first user comprises causing adjustment of a presentation of a media content item being viewed by the first user.

6 . The method of claim 5 , wherein causing adjustment of the presentation of the media content item comprises causing adjustment of a volume level of the media content item being viewed by the first user.

7 . The method of claim 5 , wherein causing adjustment of the presentation of the media content item comprises visually altering the presentation of the media content item.

8 . The method of claim 5 , further comprising:
generating an indication that the presentation of the media content item has been adjusted; and causing the indication to be displayed to the first user.

9 . The method of claim 1 , wherein generating the recommendation for the first user is further based on a second trend associated with a second user-cluster of the set of user-clusters.

10 . The method of claim 9 , wherein generating the recommendation for the first user is further based on a first weight assigned to the first user-cluster and a second weight assigned to the second user-cluster, wherein the first weight and the second weight are assigned based on a similarity of a user profile of the first user and the respective user-cluster.

11 . A method comprising:
receiving, by a computing device, usage event data from a plurality of users associated with a first cluster of users; determining, by the computing device, a control trend corresponding to a media content item and associated with the first cluster based on the usage event data; determining, by the computing device, that a first user is a member of the first cluster and is viewing the media content item; and generating, by the computing device, a recommended adjustment for the first user based on the control trend.

12 . The method of claim 11 , wherein determining the control trend comprises determining that a threshold number of users in the first cluster of users have initiated a particular command while viewing the media content item.

13 . The method of claim 11 , wherein determining the control trend comprises determining that a rate of change of a number of users in the first cluster of users initiating a particular command while viewing the media content item satisfies a threshold value.

14 . The method of claim 11 , wherein the control trend comprises a volume down command.

15 . The method of claim 11 , wherein the control trend comprises a channel change command or a selection of a media content item from a menu.

16 . The method of claim 11 , further comprising:
causing the recommended adjustment to be applied to the media content item being viewed by the first user, wherein the recommended adjustment comprises one or more of a channel change command or a volume up command.

17 . The method of claim 11 , wherein the first user is a member of more than one cluster.

18 . A method comprising:
receiving, by a computing device, usage event data from a plurality of users associated with a first cluster of users; determining, by the computing device, a control trend corresponding to a media content item and associated with the first cluster based on the usage event data; determining, by the computing device, that a first user is viewing the media content item; computing, by the computing device, a match score for the first user and the first cluster; and in response to determining that the match score satisfies a threshold value, generating a recommended adjustment for the first user based on the control trend.

19 . The method of claim 18 , wherein computing the match score comprises comparing a plurality of attributes associated with a user profile of the first user with a plurality of attributes associated with the first cluster of users.

20 . The method of claim 18 , wherein computing the match score comprises comparing a usage history of the first user with usage characteristics associated with the first cluster of users.

Assignees

• Comcast Cable Comm Llc

Inventors

• Neumann Jan
• Alla Sridhar
• Jojic Oliver
• Agrawal Shekhar
• Younessian Ehsan
• Bagga Amit

Classifications

• H04N21/252

  Processing of multiple end-users' preferences to derive collaborative data · CPC title

• H04N21/25891

  being end-user preferences (retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18) · CPC title

• H04N21/47202

  for requesting content on demand, e.g. video on demand · CPC title

• H04N21/4668 Primary

  for recommending content, e.g. movies · CPC title

• G06F3/0482 Primary

  Interaction with lists of selectable items, e.g. menus · CPC title