Back to results
US 10,764,380 B2Granted
Clustering content items based on a social affinity between users associated with the content items
AssigneeFacebook, Inc.
InventorsChen Zheng, Thomas Frederick Dimson, Linji Yang
Life of this patent
Estimating the term…
Abstract
Systems, methods, and non-transitory computer-readable media can generate a set of candidate content items from a plurality of content items that are available in the social networking system, wherein one or more of the candidate content items are to be included in a personalized content stream for a first user. A corresponding score for each of the candidate content items can be generated with respect to the first user. A first set of content items can be determined from the set of candidate content items based at least in part on the respective scores, wherein content items in the first set are included in the personalized content stream.
Claims15
A computer-implemented method comprising:
- obtaining, by a social networking system, information describing a personalized content stream of a first user, the personalized content stream including a set of content items to be presented to the first user based at least in part on an initial ordering;
- determining, by the social networking system, a different ordering for presenting the set of content items based on one or more criteria, wherein the determining further comprises:
- clustering, by the social networking system, content items in the set based on the one or more criteria, wherein each content item is assigned to a cluster in a plurality of clusters;
- and
- determining, by the social networking system, an order in which to present each cluster of content items in the personalized content stream, the determining further comprising:
- ordering, by the social networking system, the plurality of clusters based on their respective distance scores, wherein a distance score between a first cluster and a second cluster measures a similarity between the first cluster and the second cluster, and wherein the distance score for the first cluster and the second cluster is determined based at least in part on a social affinity between users associated with content items included in the first cluster and users associated with content items included in the second cluster;
- determining, by the social networking system, the different ordering for presenting the set of content items based at least in part on the order in which to present the clusters of content items;
- and
- modifying, by the social networking system, the initial ordering of the personalized content stream to correspond to the different ordering in which to present each cluster of content items included in the plurality of clusters.
6 more elements
A system comprising:
- at least one processor;
- and
- a memory storing instructions that, when executed by the at least one processor, cause the system to perform:
- obtaining information describing a personalized content stream of a first user, the personalized content stream including a set of content items to be presented to the first user based at least in part on an initial ordering;
- determining a different ordering for presenting the set of content items based on one or more criteria, wherein the determining further comprises:
- clustering content items in the set based on the one or more criteria, wherein each content item is assigned to a cluster in a plurality of clusters;
- and
- determining an order in which to present each cluster of content items in the personalized content stream, the determining further comprising:
- ordering the plurality of clusters based on their respective distance scores, wherein a distance score between a first cluster and a second cluster measures a similarity between the first cluster and the second cluster, and wherein the distance score for the first cluster and the second cluster is determined based at least in part on a social affinity between users associated with content items included in the first cluster and users associated with content items included in the second cluster;
- determining the different ordering for presenting the set of content items based at least in part the order in which to present the clusters of content items;
- and
- modifying the initial ordering of the personalized content stream to correspond to the different ordering in which to present each cluster of content items included in the plurality of clusters.
9 more elements
A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:
- obtaining information describing a personalized content stream of a first user, the personalized content stream including a set of content items to be presented to the first user based at least in part on an initial ordering;
- determining a different ordering for presenting the set of content items based on one or more criteria, wherein the determining further comprises:
- clustering content items in the set based on the one or more criteria, wherein each content item is assigned to a cluster in a plurality of clusters;
- and
- determining an order in which to present each cluster of content items in the personalized content stream, the determining further comprising:
- ordering the plurality of clusters based on their respective distance scores, wherein a distance score between a first cluster and a second cluster measures a similarity between the first cluster and the second cluster, and wherein the distance score for the first cluster and the second cluster is determined based at least in part on a social affinity between users associated with content items included in the first cluster and users associated with content items included in the second cluster;
- determining the different ordering for presenting the set of content items based at least in part the order in which to present the clusters of content items;
- and
- modifying the initial ordering of the personalized content stream to correspond to the different ordering in which to present each cluster of content items included in the plurality of clusters.
6 more elements
Dependencies are inferred from the claim text.