Generating a stream of content for a channel
First Claim
1. A computer-implemented method for generating a stream of content for each of a plurality of channels, the method comprising:
- generating, with one or more processors, a model for a user comprising an interest of the user and prior interaction of the user with heterogeneous data sources;
computing, with the one or more processors, an interestingness score for each content item received from the heterogeneous data sources by summing properties of each content item over single-attribute properties using the model and based upon interestingness of each content item to the user and an extent to which the content item'"'"'s popularity has increased within a geographic area associated with the user;
categorizing, with the one or more processors, content items received from the heterogeneous data sources by annotating each content item with a dynamic feature including the interestingness score;
identifying, with the one or more processors, a first channel category for the user based on a historical trend and the prior interaction of the user with the heterogeneous data sources, the historical trend including a change in a number of content items categorized under the first channel category;
receiving an input through a user interface specifying a second channel category;
querying the content items based on the first channel category, the second channel category and at least one channel attribute;
in response to the query, receiving candidate content items that include the first channel category, the second channel category and the at least one channel attribute and comparing the interestingness score for each candidate content item with a threshold for the first channel category and the second channel category to determine the candidate content items that have an interestingness score that exceeds the threshold; and
generating the stream of content from the candidate content items that have an interestingness score that exceeds the threshold.
2 Assignments
0 Petitions
Accused Products
Abstract
A system and method for generating a stream of content for a channel. The channel application includes a content categorizer, a scoring engine and a channel engine. The content categorizer categorizes new content items received from heterogeneous data sources. The channel engine identifies a channel category for a user based at least in part on at least one of a historical trend and a user activity. The scoring engine queries the new content items based on the channel category and at least one other channel attribute. The scoring engine retrieves candidate content items that include the channel category and the other channel attribute. The scoring engine then generates a stream of content from the candidate content items for the channel.
-
Citations
20 Claims
-
1. A computer-implemented method for generating a stream of content for each of a plurality of channels, the method comprising:
-
generating, with one or more processors, a model for a user comprising an interest of the user and prior interaction of the user with heterogeneous data sources; computing, with the one or more processors, an interestingness score for each content item received from the heterogeneous data sources by summing properties of each content item over single-attribute properties using the model and based upon interestingness of each content item to the user and an extent to which the content item'"'"'s popularity has increased within a geographic area associated with the user; categorizing, with the one or more processors, content items received from the heterogeneous data sources by annotating each content item with a dynamic feature including the interestingness score; identifying, with the one or more processors, a first channel category for the user based on a historical trend and the prior interaction of the user with the heterogeneous data sources, the historical trend including a change in a number of content items categorized under the first channel category; receiving an input through a user interface specifying a second channel category; querying the content items based on the first channel category, the second channel category and at least one channel attribute; in response to the query, receiving candidate content items that include the first channel category, the second channel category and the at least one channel attribute and comparing the interestingness score for each candidate content item with a threshold for the first channel category and the second channel category to determine the candidate content items that have an interestingness score that exceeds the threshold; and generating the stream of content from the candidate content items that have an interestingness score that exceeds the threshold. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A system for generating a stream of content for a plurality of channels, the system comprising:
-
one or more processors; a model generation engine stored on a memory and executed by the one or more processors, the model generation engine for generating a model for a user comprising an interest of the user and prior interaction of the user with heterogeneous data sources; a content categorizer stored on the memory and coupled to the model generation engine, the content categorizer for categorizing content items received from the heterogeneous data sources by annotating each content item with a dynamic feature including an interestingness score; a channel engine coupled to the content categorizer, the channel engine for identifying a first channel category for the user based on a historical trend and the prior interaction of the user with the heterogeneous data sources, the historical trend including a change in a number of the content items categorized under the first channel category; a user interface engine coupled to the channel engine, the user interface engine for providing the user with a user interface for customizing the plurality of channels with a second channel category; and a scoring engine coupled to the model generation engine, the content categorizer, the channel engine and the user interface engine, the scoring engine for computing the interestingness score for each candidate content item received from the heterogeneous data sources 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, receiving an input through the user interface specifying the second channel category, querying the content items based on the first channel category, the second channel category and at least one channel attribute, in response to the query, receiving candidate content items that include the first channel category, the second channel category and the at least one channel attribute and comparing the interestingness score for each candidate content item with a threshold for the first channel category and the second channel category to determine the candidate content items that have an interestingness score that exceeds the threshold, and generating the stream of content from the candidate content items that have an interestingness score that exceeds the threshold. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18, 19)
-
-
20. 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:
-
generate a model for a user comprising an interest of the user and prior interaction of the user with heterogeneous data sources; compute an interestingness score for each content item received from the heterogeneous data sources by summing properties of each content item over single-attribute properties using the model and based upon interestingness of each content item to the user and an extent to which the content item'"'"'s popularity has increased within a geographic area associated with the user; categorize content items received from the heterogeneous data sources by annotating each content item with a dynamic feature including the interestingness score; identify a first channel category for the user based on a historical trend and the prior interaction of the user with the heterogeneous data sources, the historical trend including a change in a number of content items categorized under the first channel category; receive an input through a user interface specifying a second channel category; query the content items based on the first channel category, the second channel category and at least one channel attribute; in response to the query, receive candidate content items that include the first channel category, the second channel category and the at least one channel attribute and compare the interestingness score for each candidate content item with a threshold for the first channel category and the second channel category to determine the candidate content items that have an interestingness score that exceeds the threshold; and generate a stream of content from the candidate content items that have an interestingness score that exceeds the threshold.
-
Specification