Content recommendation system with weighted metadata annotations

Patent metadata

Field	Value
Publication number	US-10191990-B2
Application number	US-201615357722-A
Country	US
Kind code	B2
Filing date	Nov 21, 2016
Priority date	Nov 21, 2016
Publication date	Jan 29, 2019
Grant date	Jan 29, 2019

Abstract

Systems and methods are described for improving content classifications and metadata for a plurality of content items. The content items may comprise various forms of media content. A content recommendation processing system may automatically annotate and/or classify content items with a plurality of metadata tag information describing content items. The disclosed system and methods may also determine and/or assign applicability scores indicating a level or degree of suitability for annotating a content item with particular metadata tag information, and may utilize applicability scores to provide content to calibrate metadata information for a plurality of content items, and further to provide content recommendations to users.

First claim

We claim:

1. A method, implemented by one or more computing devices, comprising:
receiving a first input indicating a first content item;
receiving a second input indicating a threshold applicability score;
receiving a first set of metadata tags associated with the first content item;
determining applicability scores for the first set of metadata tags;
determining that an applicability score for a first metadata tag, of the first set of metadata tags, satisfies the threshold applicability score;
receiving user feedback data relating to the first metadata tag of the first set of meta data tags and the first content item;
adjusting the applicability score for the first metadata tag, of the first set of metadata tags, based on the received feedback data;
comparing the adjusted applicability score for the first metadata tag, of the first set of metadata tags, to the threshold applicability score; and
modifying a metadata field of the first content item to remove the first metadata tag based on the comparing the adjusted applicability score to the threshold applicability score.

2. The method of claim 1 , further comprising:
determining a plurality of other metadata tags associated with the first content item;
determining a second meta data tag, of the plurality of other metadata tags, comprising an applicability score satisfying the threshold applicability score; and
modifying the metadata field of the first content item to replace the first metadata tag of the first set of metadata tags with the second metadata tag of the plurality of other metadata tags.

3. The method of claim 1 , wherein each metadata tag in the first set of metadata tags has been assigned to at least a threshold number of other content items.

4. The method of claim 3 , wherein the threshold number of other content items comprises a number of content items within a range of four content items to sixteen content items.

5. The method of claim 3 , further comprising:
receiving, via an input device, a third input indicating a content query;
determining a second metadata tag, wherein the second metadata tag is associated with the content query;
determining a plurality of content items associated with the second metadata tag;
determining applicability scores for one or more content items in the plurality of content items; and
determining, by applicability score, rankings for the plurality of content items associated with the second metadata tag.

6. The method of claim 5 , further comprising:
in response to receiving the content query, transmitting a content recommendation based on the determined rankings for the plurality of content items.

7. The method of claim 1 , further comprising:
determining, by a processor, a history of metadata tag removal for one or more content items;
adjusting, based on the history of metadata tag removal, a recommendation value for the one or more content items; and
transmitting a content recommendation for a second content item based on the recommendation value.

8. An apparatus comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the apparatus to:
receive a first input indicating a first content item;
receive a second input indicating a threshold applicability score;
receive a first set of metadata tags associated with the first content item;
determine applicability scores for the first set of metadata tags;
determine that an applicability score for a first metadata tag, of the first set of metadata tags, satisfies the threshold applicability score;
receive user feedback data relating to the first metadata tag of the first set of metadata tags and the first content item;
adjust the applicability score for the first metadata tag, of the first set of metadata tags, based on the received feedback data;
compare the adjusted applicability score for the first metadata tag, of the first set of metadata tags, to the threshold applicability score; and
modify a metadata field of the first content item to remove the first metadata tag based on the comparing the adjusted applicability score to the threshold applicability score.

9. The apparatus of claim 8 , wherein the instructions, when executed by the one or more processors, further cause the apparatus to:
determine a plurality of other metadata tags associated with the first content item;
determine a second metadata tag, of the plurality of other metadata tags, comprising an applicability score satisfying the threshold applicability score; and
modify the metadata field of the first content item to replace the first metadata tag of the first set of metadata tags with the second metadata tag of the plurality of other metadata tags.

10. The apparatus of claim 8 , wherein each metadata tag in the first set of metadata tags has been assigned to at least a threshold number of other content items.

11. The apparatus of claim 10 , wherein the threshold number of other content items comprises a number of content items within a range of four content items to sixteen content items.

12. The apparatus of claim 10 , further comprising an input device, wherein the instructions, when executed by the one or more processors, further cause the apparatus to:
receive, via the input device, a third input indicating a content query;
determine a second metadata tag, wherein the second metadata tag is associated with the content query;
determine a plurality of content items associated with the second metadata tag;
determine applicability scores for one or more content items in the plurality of content items; and
determine, by applicability score, rankings for the plurality of content items associated with the second metadata tag.

13. The apparatus of claim 12 , wherein the instructions, when executed by the one or more processors, further cause the apparatus to:
in response to receiving the content query, transmit a content recommendation based on the determined rankings for the plurality of content items.

14. The apparatus of claim 8 , wherein the instructions, when executed by the one or more processors, further cause the apparatus to:
determine a history of metadata tag removal for one or more content items;
adjust, based on the history of metadata tag removal, a recommendation value for the one or more content items; and
transmit a content recommendation for a second content item based on the recommendation value.

15. One or more non-transitory computer readable media storing instructions that, when executed by an apparatus, cause the apparatus to:
receive a first input indicating a first content item; receive a second input indicating a threshold applicability score;
receive a first set of metadata tags associated with the first content item;
determine applicability scores for the first set of metadata tags;
determine that an applicability score for a first metadata tag, of the first set of metadata tags, satisfies the threshold applicability score;
receive user feedback data relating to the first metadata tag of the first set of metadata tags and the first content item;
adjust the applicability score for the first metadata tag, of the first set of metadata tags, based on the received feedback data;
compare the adjusted applicability score for the first metadata tag, of the first set of metadata tags, to the threshold applicability score; and
modify a metadata field of the first content item to remove the first metadata tag based on the comparing the adjusted applicability score to the threshold applicability score.

16. The one or more

Assignees

• Comcast Cable Comm Llc

Inventors

• Sayyadi-Harikandehei Hassan
• Jojic Oliver

Classifications

• H04N21/25

  Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies {(maintenance or administration in data networks H04L41/00)} · CPC title

• G06F7/026

  Magnitude comparison, i.e. determining the relative order of operands based on their numerical value, e.g. window comparator · CPC title

• H04N21/231

  Content storage operation, e.g. caching movies for short term storage, replicating data over plural servers, prioritizing data for deletion · CPC title

• G06F16/40 Primary

  of multimedia data, e.g. slideshows comprising image and additional audio data (retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70) · CPC title

• G06F17/30017

  Physics · mapped topic