Scoring stream items with models based on user interests
First Claim
Patent Images
1. A computer-implemented method for generating a stream of content for a first user, the method comprising:
- determining, with one or more processors, that the first user has a social connection with a second user;
identifying, with the one or more processors, a first interest associated with the second user;
receiving input from the first user to add the first interest to a model;
generating, with the one or more processors, the model that includes the first interest associated with the second user and a second interest associated with the first user based on at least one prior action performed by the first user with reference to a group of heterogeneous data sources, wherein the at least one prior action is used to identify inferred interests, wherein the at least one prior action includes a search term used in a search engine and wherein the inferred interests include a subject corresponding to the search term;
receiving candidate content items from a friend of the first user, the received candidate content items being from a content stream of the friend;
generating, with the one or more processors, a set of candidate content items that are each associated with at least one of the first interest, the second interest and the candidate content items from the friend of the first user;
computing, with the one or more processors, a score for each candidate content item in the set using the model and based upon interestingness of each candidate content item to the first user and a probability that the candidate content item will be present in the first user'"'"'s stream, wherein the interestingness includes social relevance to the first user and an interest match of the candidate content item to the first user;
generating the stream of content from selected content items using the score of each candidate content item;
generating an explanation for at least one selected content item in the stream of content; and
distributing the stream of content and the explanation for display alongside the at least one selected content item in a social network.
2 Assignments
0 Petitions
Accused Products
Abstract
A system and method for generating a stream of content includes a content stream module that generates a model based on user input and/or prior activities using heterogeneous data sources. The heterogeneous data sources include search, entertainment, social activity and activity on third-party sites. The content stream module retrieves candidate content items that have interests that are similar to the user. The candidate content items are compared to the model and scored based upon interestingness of the content item to the user. The content stream module generates the stream of content from the candidate content items.
-
Citations
9 Claims
-
1. A computer-implemented method for generating a stream of content for a first user, the method comprising:
-
determining, with one or more processors, that the first user has a social connection with a second user; identifying, with the one or more processors, a first interest associated with the second user; receiving input from the first user to add the first interest to a model; generating, with the one or more processors, the model that includes the first interest associated with the second user and a second interest associated with the first user based on at least one prior action performed by the first user with reference to a group of heterogeneous data sources, wherein the at least one prior action is used to identify inferred interests, wherein the at least one prior action includes a search term used in a search engine and wherein the inferred interests include a subject corresponding to the search term; receiving candidate content items from a friend of the first user, the received candidate content items being from a content stream of the friend; generating, with the one or more processors, a set of candidate content items that are each associated with at least one of the first interest, the second interest and the candidate content items from the friend of the first user; computing, with the one or more processors, a score for each candidate content item in the set using the model and based upon interestingness of each candidate content item to the first user and a probability that the candidate content item will be present in the first user'"'"'s stream, wherein the interestingness includes social relevance to the first user and an interest match of the candidate content item to the first user; generating the stream of content from selected content items using the score of each candidate content item; generating an explanation for at least one selected content item in the stream of content; and distributing the stream of content and the explanation for display alongside the at least one selected content item in a social network. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A system for generating a stream of content for a first user, the system comprising:
-
one or more processors; a model generation engine stored on a memory and executable by the one or more processors, the model generation engine configured to determine that the first user has a social connection with a second user, identify a first interest associated with the second user, receive input from the first user to add the first interest to a model, generate the model that includes the first interest associated with the second user and a second interest associated with the first user based on at least one prior action performed by the first user with reference to a group of heterogeneous data sources, wherein the at least one prior action is used to identify inferred interests, wherein the at least one prior action includes a search term used in a search engine and wherein the inferred interests include a subject corresponding to the search term; a scoring engine stored on the memory and executable by the one or more processors, the scoring engine configured to receive candidate content items from a friend of the first user, the received candidate content items being from a content stream of the friend, generate a set of candidate content items that are each associated with at least one of the first interest, the second interest and the candidate content items from the friend of the first user, compute a score for each candidate content item in the set using the model and based upon interestingness of each candidate content item to the first user and a probability that the candidate content item will be present in the first user'"'"'s stream, wherein the interestingness includes social relevance to the first user and an interest match of the candidate content item to the first user, generate the stream of content from selected content items using the score of each candidate content item, generate an explanation for at least one selected content item in the stream of content and distribute the stream of content and the explanation for display alongside the at least one selected content item in a social network. - View Dependent Claims (8)
-
-
9. A computer program product comprising a non-transitory computer useable medium including a computer readable program, wherein the computer readable program when executed on a computer causes the computer to:
-
determine that the first user has a social connection with a second user; identify a first interest associated with the second user; receive input from the first user to add the first interest to a model; generate the model that includes the first interest associated with the second user and a second interest associated with the first user based on at least one prior action performed by the first user with reference to a group of heterogeneous data sources, wherein the at least one prior action is used to identify inferred interests, wherein the at least one prior action includes a search term used in a search engine and wherein the inferred interests include a subject corresponding to the search term; receive candidate content items from a friend of the first user, the received candidate content items being from a content stream of the friend; generate a set of candidate content items that are each associated with at least one of the first interest, the second interest and the candidate content items from the friend of the first user; compute a score for each candidate content item in the set using the model and based upon interestingness of each candidate content item to the first user and a probability that the candidate content item will be present in the first user'"'"'s stream, wherein the interestingness includes social relevance to the first user and an interest match of the candidate content item to the first user; generate the stream of content from selected content items using the score of each candidate content item; generate an explanation for at least one selected content item in the stream of content; and distribute the stream of content and the explanation for display alongside the at least one selected content item in a social network.
-
Specification