Scoring stream items with models based on user interests

• US 9,979,777 B1
• Filed: 04/03/2014
• Issued: 05/22/2018
• Est. Priority Date: 12/18/2010
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Tomkins, Andrew, Sivakumar, Dandapani, Sung, Sangsoo, Kosslyn, Justin, Jackson, Todd, Rohe, Andre, Luo, Ya, Bunner, Andrew, Sobol, Alexander, de Alfaro, Luca
• Primary Examiner(s): Wei, Siren
• Application Number:
  US14/244,821
• Time in Patent Office: 1,510 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 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.

Claims

1. A method comprising:

determining, using one or more processors, an inferred interest for a first user;

generating, using the one or more processors, a model based on the inferred interest of the first user and storing the model in a non-transitory storage medium;

generating, using the one or more processors, a set of candidate content items using an item from a second user with a similarity to the first user;

determining, using the one or more processors, a first attribute and a second attribute associated with a candidate content item in the set of candidate content items;

determining, using the one or more processors, a first score associated with the first attribute for the candidate content item based on the model of the first user and a first number of candidate content items having the first attribute in the set of candidate content items;

determining, using the one or more processors, a second score associated with the second attribute for the candidate content item based on the model of the first user and a second number of candidate content items having the second attribute in the set of candidate content items;

computing, using the one or more processors, a third score for the candidate content item in the set of candidate content items by summing the first score associated with the first attribute and the second score associated with the second attribute;

selecting, using the one or more processors, content items for a stream of content associated with the first user from the set of candidate content items based on the third score of the content items;

generating, using the one or more processors, an explanation for a first content item in the selected content items, the explanation indicating a reason for presenting the first content item to the first user; and

transmitting, using the one or more processors, an instruction to a device that causes the device to present for display the stream of content to the first user with the explanation alongside the first content item, the explanation including a selectable graphic element for the first user to access an expanded explanation.

2. The method of claim 1, comprising distributing the stream of content in a social network;

and sharing at least one selected content item with a friend of the first user.

3. The method of claim 1, comprising receiving candidate content items from a friend of the first user, the received candidate content items being generated from a content stream of the friend.

4. The method of claim 1, comprising receiving an update to the model based upon an interaction of the first user with a website, the interaction of the first user including providing at least one of a user preference, a user interest, a comment, a tag and a search.

5. The method of claim 1, wherein selecting the content items for the stream of content includes selecting candidate content items that have the third score exceeding a threshold score.

6. The method of claim 1, wherein the model is generated based on a prior action from a group of heterogeneous data sources, the heterogeneous data sources including at least one of a log of activities on a social network, a search history, a blog post, a news article, a news feed, a video, a map, a message, an email message, an instant message, a microblog, a text-based post, a phone call and an activity on site.

7. The method of claim 1, comprising:

receiving a request for the stream of content;

determining context information from the request, the context information including one of a geographic location of the user, time of day, and contextual clues associated with the request; and

using the context information in generating the stream of content.

8. The method of claim 1, comprising:

receiving from the first user an indication that one of the selected content items in the stream of content is interesting; and

selecting additional content items that are related to the selected content item.

9. The method of claim 1, wherein the selected content items of the stream of content are displayed with at least one tag that indicates a subject matter of the selected content items.

10. The method of claim 1, wherein the expanded explanation of the first content item is presented to the first user as a decision tree organized from broad to narrow topics.

11. A system comprising:

a processor; and

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

determine an inferred interest for a first user;

generate a model based on the inferred interest of the first user and store the model in the memory;

generate a set of candidate content items using an item from a second user with a similarity to the first user;

determine a first attribute and a second attribute associated with a candidate content item in the set of candidate content items;

determine a first score associated with the first attribute for the candidate content item based on the model of the first user and a first number of candidate content items having the first attribute in the set of candidate content items;

determine a second score associated with the second attribute for the candidate content item based on the model of the first user and a second number of candidate content items having the second attribute in the set of candidate content items;

compute a third score for the candidate content item in the set of candidate content items by summing the first score associated with the first attribute and the second score associated with the second attribute;

select content items for a stream of content associated with the first user from the set of candidate content items based on the third score of the content items;

generate an explanation for a first content item in the selected content items, the explanation indicating a reason for presenting the first content item to the first user; and

transmit an instruction to a device that causes the device to present for display the stream of content to the first user with the explanation alongside the first content item, the explanation including a selectable graphic element for the first user to access an expanded explanation.

12. The system of claim 11, wherein the memory also stores instructions that, when executed, cause the system to distribute the stream of content in a social network;

and share at least one selected content item with a friend of the first user.

13. The system of claim 11, wherein the memory also stores instructions that, when executed, cause the system to receive candidate content items from a friend of the first user, the received candidate content items being generated from a content stream of the friend.

14. The system of claim 11, wherein the memory also stores instructions that, when executed, cause the system to receive an update to the model based upon an interaction of the first user with a website, the interaction of the first user including providing at least one of a user preference, a user interest, a comment, a tag and a search.

15. The system of claim 11, wherein the selection of the content items for the stream of content includes selecting candidate content items that have the third score exceeding a threshold score.

16. The system of claim 11, wherein the model is generated based on a prior action from a group of heterogeneous data sources, the heterogeneous data sources including at least one of a log of activities on a social network, a search history, a blog post, a news article, a news feed, a video, a map, a message, an email message, an instant message, a microblog, a text-based post, a phone call and an activity on site.

17. The system of claim 11, wherein the memory also stores instructions that, when executed, cause the system to:

receive a request for the stream of content;

determine context information from the request, the context information including one of a geographic location of the user, time of day, and contextual clues associated with the request; and

use the context information in generating the stream of content.

18. The system of claim 11, wherein the memory also stores instructions that, when executed, cause the system to:

receive from the first user an indication that one of the selected content items in the stream of content is interesting; and

select additional content items that are related to the selected content item.

19. The system of claim 11, wherein the selected content items of the stream of content are displayed with at least one tag that indicates a subject matter of the selected content items.

20. The system of claim 11, wherein the expanded explanation of the first content item is presented to the first user as a decision tree organized from broad to narrow topics.

21. A computer program product comprising a non-transitory computer usable medium including a computer readable program, wherein the computer readable program when executed on a computer causes the computer to:

determine an inferred interest for a first user;

generate a model based on the inferred interest of the first user and store the model in the non-transitory computer usable medium;

generate a set of candidate content items using an item from a second user with a similarity to the first user;

determine a first attribute and a second attribute associated with a candidate content item in the set of candidate content items;

determine a first score associated with the first attribute for the candidate content item based on the model of the first user and a first number of candidate content items having the first attribute in the set of candidate content items;

determine a second score associated with the second attribute for the candidate content item based on the model of the first user and a second number of candidate content items having the second attribute in the set of candidate content items;

compute a third score for the candidate content item in the set of candidate content items by summing the first score associated with the first attribute and the second score associated with the second attribute;

select content items for a stream of content associated with the first user from the set of candidate content items based on the third score of the content items;

generate an explanation for a first content item in the selected content items, the explanation indicating a reason for presenting the first content item to the first user; and

transmit an instruction to a device that causes the device to present for display the stream of content to the first user with the explanation alongside the first content item, the explanation including a selectable graphic element for the first user to access an expanded explanation.

22. The computer program product of claim 21 wherein the computer readable program when executed on a computer also causes the computer to distribute the stream of content in a social network;

and share at least one selected content item with a friend of the first user.

23. The computer program product of claim 21, wherein the computer readable program when executed on a computer also causes the computer to receive candidate content items from a friend of the first user, the received candidate content items being generated from a content stream of the friend.

24. The computer program product of claim 21, wherein the computer readable program when executed on a computer also causes the computer to receive an update to the model based upon an interaction of the first user with a website, the interaction of the first user including providing at least one of a user preference, a user interest, a comment, a tag and a search.

25. The computer program product of claim 21, wherein the selection of the content items for of the stream of content includes selecting candidate content items that have the third score exceeding a threshold score.

26. The computer program product of claim 21, wherein the model is generated based on a prior action from a group of heterogeneous data sources, the heterogeneous data sources including at least one of a log of activities on a social network, a search history, a blog post, a news article, a news feed, a video, a map, a message, an email message, an instant message, a microblog, a text-based post, a phone call and an activity on site.

27. The computer program product of claim 21, wherein the computer readable program when executed on a computer also causes the computer to:

receive a request for the stream of content;

determine context information from the request, the context information including one of a geographic location of the user, time of day, and contextual clues associated with the request; and

use the context information in generating the stream of content.

28. The computer program product of claim 21, wherein the computer readable program when executed on a computer also causes the computer to:

receive from the first user an indication that one of the selected content items in the stream of content is interesting; and

select additional content items that are related to the selected content item.

29. The computer program product of claim 21, wherein the selected content items of the stream of content are displayed with at least one tag that indicates a subject matter of the selected content items.

30. The computer program product of claim 21, wherein the expanded explanation of the first content item is presented to the first user as a decision tree organized from broad to narrow topics.