Predicting content popularity

Patent metadata

Field	Value
Publication number	US-2016353144-A1
Application number	US-201514727717-A
Country	US
Kind code	A1
Filing date	Jun 1, 2015
Priority date	Jun 1, 2015
Publication date	Dec 1, 2016
Grant date	—

Abstract

A method includes receiving media data corresponding to a media content item. The method further includes analyzing the media data to determine characteristics of the media content item based on first visual information contained in the media content item. The method further includes analyzing the characteristics of the media content item based on a media popularity model to generate a prediction of whether the media content item is likely to exceed a popularity threshold within a particular period of time. The method further includes determining, at the computing device, a network location at which to store the media content item based on the prediction.

First claim

1 . A method comprising:
receiving, at a computing device, media data corresponding to a media content item; analyzing, at the computing device, the media data to determine characteristics of the media content item based on first visual information contained in the media content item; analyzing, at the computing device, the characteristics of the media content item based on a media popularity model to generate a prediction of whether the media content item is likely to exceed a popularity threshold within a particular period of time; and determining a network location at which to store the media content item based on the prediction.

2 . The method of claim 1 , wherein the media popularity model is determined by:
determining a first set of surfaces based on second visual information contained in a first set of media content items that have exceeded the popularity threshold; determining a second set of surfaces based on third visual information contained in a second set of media content items that have not exceeded the popularity threshold; and generating a boundary condition based on the first set of surfaces and the second set of surfaces.

3 . The method of claim 2 , wherein the first visual information corresponds to spatio-temporal features of the media content item, and wherein determining whether the media content item is likely to exceed the popularity threshold comprises:
determining a particular surface based on the first visual information; and comparing the particular surface to the boundary condition.

4 . The method of claim 3 , further comprising generating a suggested content change to the media content item in response to determining that the media content item is not likely to exceed the popularity threshold.

5 . The method of claim 4 , wherein generating the suggested content change comprises:
determining a first average of the first set of surfaces; determining a second average of the second set of surfaces; determining a transformation that moves the second average toward the first average; applying the transformation to the particular surface to generate a transformed surface; identifying a particular media content item in the first set of media content items based on the transformed surface; and generating the suggested content change based on content of the particular media content item.

6 . The method of claim 5 , wherein the first average corresponds to a first Karcher mean of the first set of surfaces, and wherein the second average corresponds to a second Karcher mean of the second set of surfaces.

7 . The method of claim 2 , wherein the surfaces of the first set of surfaces correspond to curves or surfaces in a multidimensional space with axes corresponding to particular visual information characteristics of the second visual information, and wherein the surfaces of the second set of surfaces correspond to curves or surfaces in the multidimensional space.

8 . (canceled)

9 . The method of claim 1 , further comprising transmitting the media content item from the computing device to the network location, wherein the network location is determined based further on subject matter of the content media item being determined to be popular in a geographic location associated with the network location.

10 . (canceled)

11 . A computer-readable storage device storing instructions that, when executed by a processor, cause the processor to perform operations comprising:
receiving media data corresponding to a media content item; analyzing the media data to determine characteristics of the media content item based on first visual information contained in the media content item; and analyzing the characteristics of the media content item based on a media popularity model to generate a prediction of whether the media content item is likely to exceed a popularity threshold within a particular period of time.

12 . The computer-readable storage device of claim 11 , wherein the first visual information corresponds to spatio-temporal features of the media content item.

13 . The computer-readable storage device of claim 11 , wherein determining the media popularity model comprises:
determining a first set of surfaces based on second visual information contained in a first set of media content items that have exceeded the popularity threshold; determining a second set of surfaces based on third visual information contained in a second set of media content items that have not exceeded the popularity threshold; and generating a boundary condition based on the first set of surfaces and the second set of surfaces.

14 . The computer-readable storage device of claim 13 , wherein the first set of surfaces corresponds to curves or surfaces in a multidimensional space with axes corresponding to particular visual information characteristics of the second visual information, and wherein the second set of surfaces corresponds to curves or surfaces in the multidimensional space.

15 . The computer-readable storage device of claim 13 , wherein determining whether the media content item is likely to exceed the popularity threshold comprises:
determining a particular surface based on the first visual information; and comparing the particular surface to the boundary condition.

16 . An apparatus comprising:
a processor; and a memory configured to store instructions that, when executed by the processor, cause the processor to perform operations comprising:
receiving media data corresponding to a media content item;
analyzing the media data to determine characteristics of the media content item based on first visual information contained in the media content item;
analyzing the characteristics of the media content item based on a media popularity model to generate a prediction of whether the media content item is likely to exceed a popularity threshold within a particular period of time;
determining a network location at which to store the media content item based on the prediction; and
generating a suggested content change in response to determining that the media content item is not likely to exceed the popularity threshold.

17 . The apparatus of claim 16 , wherein the first visual information corresponds to spatio-temporal features of the media content item.

18 . The apparatus of claim 16 , wherein determining the media popularity model comprises:
determining a first set of surfaces based on second visual information contained in a first set of media content items that have exceeded the popularity threshold; determining a second set of surfaces based on third visual information contained in a second set of media content items that have not exceeded the popularity threshold; and generating a boundary condition based on the first set of surfaces and the second set of surfaces.

19 . The apparatus of claim 18 , wherein the first set of surfaces corresponds to curves or surfaces in a multidimensional space with axes corresponding to particular visual information characteristics of the second visual information, and wherein the second set of surfaces corresponds to curves or surfaces in the multidimensional space.

20 . The apparatus of claim 18 , wherein determining whether the media content item is likely to exceed the popularity threshold comprises:
determining a particular surface based on the first visual information; and comparing the particular surface to the boundary condition.

21 . The method of claim 1 , wherein the visual information

Assignees

• At & T Ip I Lp

Inventors

• Gopalan Raghuraman

Classifications

• H04N21/23418

  involving operations for analysing video streams, e.g. detecting features or characteristics (television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59) · CPC title

• H04N21/6175

  involving transmission via Internet (broadcast-related systems characterised by the transmission system being the Internet H04H60/82) · CPC title

• H04L67/1095

  Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes · CPC title

• H04N21/4667

  Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections · CPC title

• H04N21/23103

  using load balancing strategies, e.g. by placing or distributing content on different disks, different memories or different servers (storage management G06F3/0604; allocation of resources considering the load in multiprogramming arrangements G06F9/505; techniques for rebalancing the load in a distributed system G06F9/5083; access to distributed or replicated servers, e.g. load balancing, in data networks H04L67/1001) · CPC title