Organizing a stream of content

• US 9,900,358 B1
• Filed: 01/26/2015
• Issued: 02/20/2018
• Est. Priority Date: 12/18/2010
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Tomkins, Andrew, Jackson, Todd, Modi, Shaun, Su, Ray, Kosslyn, Justin Lewis, Spiro, Robert, Ko, Jessica, Adams, Cameron
• Primary Examiner(s): Wei, Siren
• Application Number:
  US14/605,476
• Time in Patent Office: 1,121 Days
• Field of Search: None
• 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 stream of content with candidate content items associated with a likelihood of being interesting to a user. A model generation engine generates a model for a user. A scoring engine obtains candidate content items and compares candidate content items to a model to determine the most interesting content items. A user interface engine organizing first and second content items in a first direction and a third content item in a second direction. The user interface engine receives feedback that includes a request for additional content items or a request to remove an interest associated with a selected content item from the model. The model generation engine updates the model in response to feedback.

Claims

1. A computer-implemented method, comprising:

obtaining, with one or more processors, a first stream of candidate content items based on a request from a user;

generating, with the one or more processors, a model stored in a memory coupled to the one or more processors based on an interest of the user and a prior interaction of the user;

computing, with the one or more processors, an interestingness score for each of the candidate content items based upon a comparison of each of the candidate content items to the model stored in the memory, a quality of each candidate content item, and information relating to relationships of users from a social graph of the user, wherein the interestingness score represents similarities between attributes of the candidate content item and the model stored in the memory and the quality of each candidate content item is based on at least one of a popularity, an importance and a relevance of the respective candidate content item;

determining a threshold for the first stream of candidate content items based on an extent to which the popularity of the candidate content items has changed in a user'"'"'s location;

comparing, with the one or more processors, the interestingness score of each of the candidate content items with the threshold to determine which candidate content items have an interestingness score that exceeds the threshold;

organizing a first content item and a second content item that have the interestingness score that exceeds the threshold in a second stream of content; and

providing the second stream of content along with an explanation for why the first content item and the second content item are included in the second stream of content for display on a user interface of a client device associated with the user that submitted the request, wherein the user interface includes at least one button associated with each of the first content item and the second content item, which, once selected by the user, causes the one or more processors to receive a feedback to the explanation and to automatically update the model and the second stream of content based on the feedback.

2. The method of claim 1 further comprising:

selecting the candidate content items with a global score that exceeds a global score threshold from the first stream of candidate content items, the global score indicating the popularity of the candidate content items; and

computing the interestingness score for each of the selected candidate content items using the model.

3. The method of claim 1, wherein the second content item is associated with a marker, the marker for requesting a third content item related to the second content item.

4. The method of claim 3, wherein the second stream of content is presented to the user in a first direction, the second and the third items are organized in a third stream of content, and the third stream of content is presented in a second direction to the user.

5. The method of claim 4, wherein the first direction is vertical and the second direction is horizontal.

6. The method of claim 1 further comprising:

providing a button for requesting additional content items for a first type of interest;

receiving a selection of the button for requesting the additional content items; and

adding the first type of interest to the model.

7. The method of claim 1 further comprising:

providing a button for removing a first type of interest from the model;

receiving a selection of the button for removing the first type of interest from the model; and

removing the first type of interest from the model.

8. A system, comprising:

a processor;

a memory storing instructions that, when executed by the processor, cause the system to;

obtain a first stream of candidate content items based on a request from a user;

generate a model based on an interest of the user and a prior interaction of the user;

compute an interestingness score for each of the candidate content items based upon a comparison of each of the candidate content items to the model, a quality of each candidate content item, and information relating to relationships of users from a social graph of the user, wherein the interestingness score represents similarities between attributes of the candidate content item and the model and the quality of each candidate content item is based on at least one of a popularity, an importance and a relevance of the respective candidate content item;

determine a threshold for the first stream of candidate content items based on an extent to which the popularity of the candidate content items has changed in a user'"'"'s location;

compare the interestingness score for each of the candidate content items with the threshold to determine which candidate content items have an interestingness score that exceeds the threshold;

organize a first content item and a second content item that have the interestingness score that exceeds the threshold in a second stream of content; and

provide the second stream of content along with an explanation for why the first content item and the second content item are included in the second stream of content for display on a user interface of a client device associated with the user that submitted the request, wherein the user interface includes at least one button associated with each of the first content item and the second content item, which, once selected by the user, causes the one or more processors to receive a feedback to the explanation and to automatically update the model and the second stream of content based on the feedback.

9. The system of claim 8, wherein the system is further configured to:

select the candidate content items with a global score that exceeds a global score threshold from the first stream of candidate content items, the global score indicating the popularity of the candidate content items; and

compute the interestingness score for each of the selected candidate content items using the model.

10. The system of claim 8, wherein the second content item is associated with a marker, the marker for requesting a third content item related to the second content item.

11. The system of claim 10, wherein the second stream of content is presented to the user in a first direction, the second and the third items are organized in a third stream of content and the third stream of content is presented in a second direction to the user.

12. The system of claim 11, wherein the first direction is vertical and the second direction is horizontal.

13. The system of claim 8, wherein the system is further configured to:

provide a button for requesting additional content items for a first type of interest;

receive a selection of the button for requesting the additional content items; and

add the first type of interest to the model.

14. The system of claim 8, wherein the system is further configured to:

provide a button for removing a first type of interest from the model;

receive a selection of the button for removing the first type of interest from the model; and

remove the first type of interest from the model.

15. 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:

obtain a first stream of candidate content items based on a request from a user;

generate a model based on an interest of the user and a prior interaction of the user;

compute an interestingness score for each of the candidate content items based upon a comparison of each of the candidate content items to the model, a quality of each candidate content item, and information relating to relationships of users from a social graph of the user, wherein the interestingness score represents similarities between attributes of the candidate content item and the model and the quality of each candidate content item is based on at least one of a popularity, an importance and a relevance of the respective candidate content item;

determine a threshold for the first stream of candidate content items based on an extent to which the popularity of the candidate content items has changed in a user'"'"'s location;

compare the interestingness score for each of the candidate content items with the threshold to determine which candidate content items have an interestingness score that exceeds the threshold;

organize a first content item and a second content item that have the interestingness score that exceeds the threshold in a second stream of content; and

provide the second stream of content along with an explanation for why the first content item and the second content item are included in the second stream of content for display on a user interface of a client device associated with the user that submitted the request, wherein the user interface includes at least one button associated with each of the first content item and the second content item, which, once selected by the user, causes the one or more processors to receive a feedback to the explanation and to automatically update the model and the second stream of content based on the feedback.

16. The computer program product of claim 15, wherein the computer readable program when executed on the computer further causes the computer to:

select the candidate content items with a global score that exceeds a global score threshold from the first stream of candidate content items, the global score indicating the popularity of the candidate content items; and

compute the interestingness score for each of the selected candidate contents item using the model.

17. The computer program product of claim 15, wherein the second content item is associated with a marker, the marker for requesting a third content item related to the second content item.

18. The computer program product of claim 17, wherein the second stream of content is presented to the user in a first direction, the second and the third items are organized in a third stream of content and the third stream of content is presented in a second direction to the user.

19. The computer program product of claim 18, wherein the first direction is vertical and the second direction is horizontal.

20. The computer program product of claim 15, the computer readable program when executed on the computer further causes the computer to:

provide a button for requesting additional content items for a first type of interest; and

receive a selection of the button for requesting the additional content items;

add the first type of interest to the model.

21. The computer program product of claim 15, the computer readable program when executed on the computer further causes the computer to:

provide a button for removing a first type of interest from the model; and

receive a selection of the button for removing the first type of interest from the model;

remove the first type of interest from the model.