Stream of content for a channel
First Claim
1. A computer-implemented method comprising:
- generating a channel for distributing content in a social network, wherein the content is related to a first topic;
retrieving candidate content items related to the first topic from heterogeneous data sources;
generating, with one or more processors, a model for a user comprising an interest of the user and prior interaction of the user with the heterogeneous data sources, wherein the interest includes the first topic;
computing, with the one or more processors, an interestingness score for each candidate content item by summing properties of each candidate content item over single-attribute properties using the model and based upon interestingness of each candidate content item to the user and an extent to which the candidate content item'"'"'s popularity has increased within a geographic area associated with the user;
comparing the interestingness score for each candidate content item with a threshold for the first topic to determine which candidate content items have an interestingness score that exceeds the threshold for the first topic;
generating a stream of content with content items that have an interestingness score that exceeds the threshold;
populating the channel with the stream of content and providing the stream of content to the user associated with the channel;
receiving feedback for the content items; and
modifying the model based at least in part on the feedback.
2 Assignments
0 Petitions
Accused Products
Abstract
A system and method for generating a channel includes a channel engine that retrieves candidate content items based on a topic from heterogeneous data sources. The channel engine generates a stream of content with selected content items and populates the stream of content for the channel and providing the stream of content to users associated with the channel. In response to receiving feedback, the channel engine modifies the at least one topic based at least in part on the feedback. The scoring engine generates a second stream of content from the first stream of content that is personalized for the first user based at least in part on a model. Other users can subscribe to the second stream.
-
Citations
22 Claims
-
1. A computer-implemented method comprising:
-
generating a channel for distributing content in a social network, wherein the content is related to a first topic; retrieving candidate content items related to the first topic from heterogeneous data sources; generating, with one or more processors, a model for a user comprising an interest of the user and prior interaction of the user with the heterogeneous data sources, wherein the interest includes the first topic; computing, with the one or more processors, an interestingness score for each candidate content item by summing properties of each candidate content item over single-attribute properties using the model and based upon interestingness of each candidate content item to the user and an extent to which the candidate content item'"'"'s popularity has increased within a geographic area associated with the user; comparing the interestingness score for each candidate content item with a threshold for the first topic to determine which candidate content items have an interestingness score that exceeds the threshold for the first topic; generating a stream of content with content items that have an interestingness score that exceeds the threshold; populating the channel with the stream of content and providing the stream of content to the user associated with the channel; receiving feedback for the content items; and modifying the model based at least in part on the feedback. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A system comprising:
-
a processor; a channel generator stored on a memory and executable by the processor, the channel generator configured to generate a channel for distributing content in a social network, wherein the content is related to a first topic; a content retriever coupled to the channel generator, the content retriever configured to retrieve candidate content items related to the first topic from heterogeneous data sources; a model generation engine coupled to the channel generator, the model generation engine configured to generate a model for a user comprising an interest of the user and prior interaction of the user with the heterogeneous data sources, wherein the interest includes the first topic; a scoring engine coupled to the model generation engine, the scoring engine configured to compute an interestingness score for each candidate content item by summing properties of each candidate content item over single-attribute properties using the model and based upon interestingness of each candidate content item to the user and an extent to which the candidate content item'"'"'s popularity has increased within a geographic area associated with the user, and compare the interestingness score for each candidate content item with a threshold for the first topic to determine which candidate content items have an interestingness score that exceeds the threshold for the first topic; a channel populator stored on the memory and coupled to the channel generator, the channel populator configured to generate a stream of content with content items that have an interestingness score that exceeds the threshold, populate the channel with the stream of content and provide the stream of content to the user associated with the channel; and wherein the channel generator is configured to receive feedback for the content items and the model generation engine is configured to modify the model based at least in part on the feedback. - View Dependent Claims (8, 9, 10, 11, 12)
-
-
13. A computer-implemented method comprising:
-
generating a channel for distributing content in a social network, wherein the content is related to a first topic; retrieving candidate content items related to the first topic from heterogeneous data sources; generating a first stream of content with the candidate content items; generating a model for a user comprising an interest of the user and prior interaction of the user with the heterogeneous data sources, wherein the interest includes the first topic; computing an interestingness score for each candidate content item in the first stream of content by summing properties of each candidate content item over single-attribute properties using the model and based upon interestingness of each candidate content item to the user and an extent to which the candidate content item'"'"'s popularity has increased within a geographic area associated with the user; generating a second stream of content from the first stream of content that is personalized for the user based at least in part on selecting candidate content items in the first stream of content that have an interestingness score that exceeds an interestingness threshold for the first topic; and providing the second stream of content to the user. - View Dependent Claims (14, 15, 16, 17)
-
-
18. A system comprising:
-
a processor; a channel engine stored on a memory and executable by the processor, the channel engine configured to generate a channel for distributing content in a social network, wherein the content is related to a first topic, retrieve candidate content items related to the first topic from heterogeneous data sources, and generate a first stream of content with the candidate content items; a model generation engine stored on the memory and coupled to the channel engine, the model generation engine configured to generate a model for a user comprising an interest of the user and prior interaction of the user with the heterogeneous data sources, wherein the interest includes the first topic; and a scoring engine stored on the memory and coupled to the channel engine, the scoring engine configured to compute an interestingness score for each candidate content item in the first stream of content by summing properties of each candidate content item over single-attribute properties using the model and based upon interestingness of each candidate content item to the user and an extent to which the candidate content item'"'"'s popularity has increased within a geographic area associated with the user, generate a second stream of content from the first stream of content that is personalized for the user based at least in part on selecting candidate content items in the first stream of content that have an interestingness score that exceeds an interestingness threshold for the first topic, and provide the second stream of content to the user. - View Dependent Claims (19, 20, 21, 22)
-
Specification