Stream of content for a channel

• US 8,990,352 B1
• Filed: 12/17/2011
• Issued: 03/24/2015
• Est. Priority Date: 12/18/2010
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Kosslyn, Justin Lewis, Tomkins, Andrew, Rohe, Andre, Dulitz, Daniel
• Primary Examiner(s): Phillips, Hassan
• Assistant Examiner(s): RAHGOZAR, OMEED DANIEL
• Application Number:
  US13/329,278
• Time in Patent Office: 1,193 Days
• Field of Search: None
• US Class Current: 709/219
• CPC Class Codes: G06F 12/06 Addressing a physical block of locations, e.g. base addressing, module addressing, memory dedication G06F12/08 takes precedence
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 16/435 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/438 Presentation of query results
• CPC Class Codes: G06F 16/487 using geographical or spatial information, e.g. location
• CPC Class Codes: G06F 16/489 using time information
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06N 5/00 Computing arrangements using knowledge-based models
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: H04L 65/60 Network streaming of media packets
• CPC Class Codes: H04L 65/762 at the source reformatting of additional data in video distribution servers H04N21/2355
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/60 Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources admission control or resource allocation H04L47/70

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.

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.

2. The method of claim 1, wherein the feedback is an approval or disapproval of at least one of the content items.

3. The method of claim 1, wherein modifying the model based at least in part on the feedback comprises generating a second topic for the channel in response to receiving disapproval of at least one content item that is associated with the first topic that is less correlated to a type than the second topic.

4. The method of claim 1, wherein modifying the model based on the feedback comprises generating a second topic for the channel in response to receiving approval of content items associated with the second topic than approval of content items associated with the first topic that is less correlated to a type than the second topic.

5. The method of claim 1, further comprising determining the first topic based on querying the heterogeneous data sources.

6. The method of claim 1, further comprising:

receiving an activity of the user that is associated with the channel; and

assigning a reputation to the user based at least in part on the activity.

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.

8. The system of claim 7, wherein the feedback is an approval or disapproval of at least one of the content items.

9. The system of claim 7, wherein modifying the model based at least in part on the feedback comprises generating a second topic for the channel in response to receiving disapproval of at least one content item that is associated with the first topic that is less correlated to a type than the second topic.

10. The system of claim 7, wherein modifying the model based on the feedback comprises generating a second topic for the channel in response to receiving approval of content items associated with the second topic than approval of content items associated with the first topic that is less correlated to a type than the second topic.

11. The system of claim 7, wherein the channel generator determines the first topic based on querying the heterogeneous data sources.

12. The system of claim 7, further comprising an authority analyzer coupled to the channel populator, wherein the authority analyzer is configured to receive an activity of the user that is associated with the channel and assign a reputation to the user based at least in part on the activity.

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.

14. The method of claim 13, further comprising:

generating a personalized stream of content for the user based on the model;

comparing the second stream of content to the personalized stream of content; and

removing the content items from the second stream of content that are duplicates of the content items in the personalized stream of content.

15. The method of claim 13, further comprising providing the second stream of content to another user that has subscribed to the personalized stream of content.

16. The method of claim 13, further comprising deleting obsolete candidate content items from the first stream of content that are older than a threshold amount of time.

17. The method of claim 13, wherein the candidate content items are retrieved from the heterogeneous data sources that are outside of a social network application.

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.

19. The system of claim 18, wherein the scoring engine generates a personalized stream of content for the user based on the model, compares the second stream of content to the personalized stream of content and removes the content items from the second stream of content that are duplicates of the content items in the personalized stream of content.

20. The system of claim 18, wherein the scoring engine provides the second stream of content to another user that has subscribed to the personalized stream of content.

21. The system of claim 18, wherein the channel engine deletes obsolete candidate content items from the first stream of content that are older than a threshold amount of time.

22. The system of claim 18, wherein the channel engine retrieves candidate content items from the heterogeneous data sources that are outside of a social network application.