Selecting Diverse, Relevant Content From Multiple Content Feeds

• US 20150169744A1
• Filed: 12/11/2014
• Published: 06/18/2015
• Est. Priority Date: 12/12/2013
• Status: Active Application

• Current Assignee: Flipboard Incorporated
• Original Assignee: Flipboard Incorporated
• Inventors: Walkingshaw, Andrew David, Aleksandrovsky, Boris Lev, Doll, Evan R., Weskamp, Marcos, Hilhorst, Didier, McCue, Michael S., Lappin, Todd, Wei, Eugene, Fei, Xiaoyu Suzanne, Quittner, Joshua, Ying, Charles Hugo, Partridge, Christopher Hamamoto
• Application Number:
  US14/567,840
• Publication Number:
  US 20150169744A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/972 Access to data in other repository systems, e.g. legacy data or dynamic Web page generation
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A digital magazine server creates cover pages identifying relevant content items relevant to a user. Candidate feeds of content items are identified from various sources, such as user-defined sections of content items, social networking systems, external content providers, and recommended content. The digital magazine server retrieves content items from the candidate feeds and generates clusters including retrieved content items based at least in part on the content elements contained in the content items. The content items in various clusters are scored, and one or more content items are selected from each cluster. The selected content items are placed in a consolidated feed, which is used to create a cover page describing a digital magazine for presentation to a digital magazine server user.

Claims

1. A method for recommending content items to a user of a digital magazine server, the method comprising:

identifying a plurality of candidate feeds based on the user, each candidate feed comprising one or more content items each having content elements;

retrieving candidate content items from the one or more content items in each of the candidate feeds;

sorting the candidate content items into one or more clusters of content items based at least in part on the content elements of the candidate content items;

determining scores of the candidate content items based at least in part on characteristics of the user and the content elements of the candidate content items;

selecting content items for inclusion into a consolidated feed from the candidate content items based at least in part on the determined scores and the clusters, the consolidated feed including candidate content items from a plurality of clusters; and

sending the consolidated feed to a client device for presentation to the user via a digital magazine provided by the digital magazine server.

2. The method of claim 1, wherein selecting content items for inclusion into the consolidated feed from the candidate content items based at least in part on the determined scores and the clusters comprises:

selecting at least one candidate content item from each cluster for inclusion in the consolidated feed based at least in part on the determined scores.

3. The method of claim 2, wherein selecting at least one candidate content item from each cluster for inclusion in the consolidated feed based at least in part on the determined scores comprises:

for each cluster, selecting a candidate content item having a maximum score within a cluster for inclusion in the consolidated feed.

4. The method of claim 1, wherein selecting content items for inclusion into the consolidated feed from the candidate content items based at least in part on the determined scores and the clusters comprises:

selecting at least one candidate content item from at least a threshold number of clusters for inclusion in the consolidated feed based at least in part on the determined scores.

5. The method of claim 1, wherein sending the consolidated feed to the client device for presentation to the user via the digital magazine provided by the digital magazine server comprises:

determining measures of similarity between pairs of content items within the consolidated feed;

determining positions of content items within the consolidated feed relative to each other based at least in part on the measures of similarity; and

sending the consolidated feed including information specifying positions of content items within the feed relative to each other to the client device for presentation to the user.

6. The method of claim 1, wherein sending the consolidated feed to the client device for presentation to the user via the digital magazine provided by the digital magazine server comprises:

selecting a page template maintained by the digital magazine server, the page template including one or more slots, each slot associated with a position and configured to present a content item;

associating content items included in the consolidated feed with slots included in the page template; and

sending the consolidated feed, the page template, and the associations between content items included in the consolidated feed with slots included in the page template to the client device for presentation.

7. The method of claim 6, wherein the associating content items included in the consolidated feed with slots included in the page template is based at least in part on one or more selected from a group consisting of:

content elements included in various content items included in the consolidated feed, characteristics of the user, and any combination thereof.

8. The method of claim 1, wherein a candidate feed is selected from a group consisting of:

content items selected for presentation to the user, content items selected for presentation to one or more digital magazine server users satisfying one or more criteria, content items selected for presentation to any user of the digital magazine server, and any combination thereof.

9. The method of claim 1, wherein sending the consolidated feed to the client device for presentation to the user via the digital magazine provided by the digital magazine server comprises:

sorting content items included in the consolidated feed into one or more clusters based at least in part on content elements of the content items included in the consolidated feed;

determining scores of the content items included in the consolidated feed, a score for a content item included in the consolidated feed based at least in part on characteristics of the user and content elements of the content item included in the consolidated feed;

selecting content items for inclusion into a further consolidated feed from the content items included in the consolidated feed based at least in part on the determined scores of the content items included in the consolidated feed and the clusters including content items included in the consolidated feed; and

sending the further consolidated feed to the client device for presentation to the user.

10. The method of claim 1, wherein sorting the candidate content items into one or more clusters of content items based at least in part on the content elements of the candidate content items comprises:

generating one or more topics associated with each of the candidate content items, the one or more topics associated with a candidate content item based at least in part on the content elements of the candidate content item;

generating a vector for each candidate content item, the vector for the candidate content item based at least in part on the one or more topics associated with the candidate content item, the vector having one or more dimensions each associated with a topic associated with the candidate content item; and

generating the one or more clusters based at least in part on the generated vectors.

11. A computer program product comprising a computer readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to:

identify a plurality of candidate feeds based on the user, each candidate feed comprising one or more content items each having content elements;

retrieve candidate content items from the one or more content items in each of the candidate feeds;

sort the candidate content items into one or more clusters of content items based at least in part on the content elements of the candidate content items;

determine scores of the candidate content items based at least in part on characteristics of the user and the content elements of the candidate content items;

select content items for inclusion into a consolidated feed from the candidate content items based at least in part on the determined scores and the clusters, the consolidated feed including candidate content items from a plurality of clusters; and

send the consolidated feed to a client device for presentation to the user via a digital magazine provided by the digital magazine server.

12. The computer program product of claim 11, wherein select content items for inclusion into the consolidated feed from the candidate content items based at least in part on the determined scores and the clusters comprises:

select at least one candidate content item from each cluster for inclusion in the consolidated feed based at least in part on the determined scores.

13. The computer program product of claim 12, wherein select at least one candidate content item from each cluster for inclusion in the consolidated feed based at least in part on the determined scores comprises:

for each cluster, select a candidate content item having a maximum score within a cluster for inclusion in the consolidated feed.

14. The computer program product of claim 11, wherein select content items for inclusion into the consolidated feed from the candidate content items based at least in part on the determined scores and the clusters comprises:

select at least one candidate content item from at least a threshold number of clusters for inclusion in the consolidated feed based at least in part on the determined scores.

15. The computer program product of claim 11, wherein send the consolidated feed to the client device for presentation to the user via the digital magazine provided by the digital magazine server comprises:

determine measures of similarity between pairs of content items within the consolidated feed;

determine positions of content items within the consolidated feed relative to each other based at least in part on the measures of similarity; and

send the consolidated feed including information specifying positions of content items within the feed relative to each other to the client device for presentation to the user.

16. The computer program product of claim 11, wherein send the consolidated feed to the client device for presentation to the user via the digital magazine provided by the digital magazine server comprises:

select a page template maintained by the digital magazine server, the page template including one or more slots, each slot associated with a position and configured to present a content item;

associate content items included in the consolidated feed with slots included in the page template; and

send the consolidated feed, the page template, and the associations between content items included in the consolidated feed with slots included in the page template to the client device for presentation.

17. The computer program product of claim 16, wherein associate content items included in the consolidated feed with slots included in the page template is based at least in part on one or more selected from a group consisting of:

content elements included in various content items included in the consolidated feed, characteristics of the user, and any combination thereof.

18. The computer program product of claim 11, wherein a candidate feed is selected from a group consisting of:

content items selected for presentation to the user, content items selected for presentation to one or more digital magazine server users satisfying one or more criteria, content items selected for presentation to any user of the digital magazine server, and any combination thereof.

19. The computer program product of claim 11, wherein send the consolidated feed to the client device for presentation to the user via the digital magazine provided by the digital magazine server comprises:

sort content items included in the consolidated feed into one or more clusters based at least in part on content elements of the content items included in the consolidated feed;

determine scores of the content items included in the consolidated feed, a score for a content item included in the consolidated feed based at least in part on characteristics of the user and content elements of the content item included in the consolidated feed;

select content items for inclusion into a further consolidated feed from the content items included in the consolidated feed based at least in part on the determined scores of the content items included in the consolidated feed and the clusters including content items included in the consolidated feed; and

send the further consolidated feed to the client device for presentation to the user.

20. The computer program product of claim 11, wherein sort the candidate content items into one or more clusters of content items based at least in part on the content elements of the candidate content items comprises:

generate one or more topics associated with each of the candidate content items, the one or more topics associated with a candidate content item based at least in part on the content elements of the candidate content item;

generate a vector for each candidate content item, the vector for the candidate content item based at least in part on the one or more topics associated with the candidate content item, the vector having one or more dimensions each associated with a topic associated with the candidate content item; and

generate the one or more clusters based at least in part on the generated vectors.