Scoring stream items with models based on user interests

• US 8,719,347 B1
• Filed: 09/14/2012
• Issued: 05/06/2014
• Est. Priority Date: 12/18/2010
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Tomkins, Andrew, Sivakumar, Dandapani, Jackson, Todd, Rohe, Andre, Luo, Ya, de Alfaro, Luca, Sung, Sangsoo, Kosslyn, Justin, Bunner, Andrew, Sobol, Sasha
• Primary Examiner(s): Phillips, Hassan
• Assistant Examiner(s): RAHGOZAR, OMEED DANIEL
• Application Number:
  US13/619,695
• Time in Patent Office: 599 Days
• Field of Search: 709/204
• US Class Current: 709/204
• 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 computer-implemented method for generating a stream of content for a first user, the method comprising:

determining, with one or more processors, that the first user has a social connection with a second user;

identifying, with the one or more processors, a first interest associated with the second user;

receiving input from the first user to add the first interest to a model;

generating, with the one or more processors, the model that includes the first interest associated with the second user and a second interest associated with the first user based on at least one prior action performed by the first user with reference to a group of heterogeneous data sources, wherein the at least one prior action is used to identify inferred interests, wherein the at least one prior action includes a search term used in a search engine and wherein the inferred interests include a subject corresponding to the search term;

receiving candidate content items from a friend of the first user, the received candidate content items being from a content stream of the friend;

generating, with the one or more processors, a set of candidate content items that are each associated with at least one of the first interest, the second interest and the candidate content items from the friend of the first user;

computing, with the one or more processors, a score for each candidate content item in the set using the model and based upon interestingness of each candidate content item to the first user and a probability that the candidate content item will be present in the first user'"'"'s stream, wherein the interestingness includes social relevance to the first user and an interest match of the candidate content item to the first user;

generating the stream of content from selected content items using the score of each candidate content item;

generating an explanation for at least one selected content item in the stream of content; and

distributing the stream of content and the explanation for display alongside the at least one selected content item in a social network.

2. The method of claim 1, further comprising receiving an update to the model based upon an interaction of the first user with a website.

3. The method of claim 2, wherein the interaction of the first user with the website includes providing at least one of a user preference, a user interest, a comment, a tag and a search.

4. The method of claim 1, wherein generating the set of candidate content items comprises applying collaborative filtering to obtain the candidate content items that are socially relevant to the stream of content from a person who has a relationship with the first user.

5. The method of claim 1, wherein generating the set of candidate content items comprises applying collaborative filtering to obtain the candidate content items based on shared similarities between the first user and other users.

6. The method of claim 1, further comprising:

receiving a confirmation or a rejection of at least one candidate content item from the first user; and

updating the model based on the received confirmation or rejection.

7. A system for generating a stream of content for a first user, the system comprising:

one or more processors;

a model generation engine stored on a memory and executable by the one or more processors, the model generation engine configured to determine that the first user has a social connection with a second user, identify a first interest associated with the second user, receive input from the first user to add the first interest to a model, generate the model that includes the first interest associated with the second user and a second interest associated with the first user based on at least one prior action performed by the first user with reference to a group of heterogeneous data sources, wherein the at least one prior action is used to identify inferred interests, wherein the at least one prior action includes a search term used in a search engine and wherein the inferred interests include a subject corresponding to the search term;

a scoring engine stored on the memory and executable by the one or more processors, the scoring engine configured to receive candidate content items from a friend of the first user, the received candidate content items being from a content stream of the friend, generate a set of candidate content items that are each associated with at least one of the first interest, the second interest and the candidate content items from the friend of the first user, compute a score for each candidate content item in the set using the model and based upon interestingness of each candidate content item to the first user and a probability that the candidate content item will be present in the first user'"'"'s stream, wherein the interestingness includes social relevance to the first user and an interest match of the candidate content item to the first user, generate the stream of content from selected content items using the score of each candidate content item, generate an explanation for at least one selected content item in the stream of content and distribute the stream of content and the explanation for display alongside the at least one selected content item in a social network.

8. The system of claim 7, wherein the model generation engine receives an update to the model based upon an interaction of the first user with a website.

9. 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:

determine that the first user has a social connection with a second user;

identify a first interest associated with the second user;

receive input from the first user to add the first interest to a model;

generate the model that includes the first interest associated with the second user and a second interest associated with the first user based on at least one prior action performed by the first user with reference to a group of heterogeneous data sources, wherein the at least one prior action is used to identify inferred interests, wherein the at least one prior action includes a search term used in a search engine and wherein the inferred interests include a subject corresponding to the search term;

receive candidate content items from a friend of the first user, the received candidate content items being from a content stream of the friend;

generate a set of candidate content items that are each associated with at least one of the first interest, the second interest and the candidate content items from the friend of the first user;

compute a score for each candidate content item in the set using the model and based upon interestingness of each candidate content item to the first user and a probability that the candidate content item will be present in the first user'"'"'s stream, wherein the interestingness includes social relevance to the first user and an interest match of the candidate content item to the first user;

generate the stream of content from selected content items using the score of each candidate content item;

generate an explanation for at least one selected content item in the stream of content; and

distribute the stream of content and the explanation for display alongside the at least one selected content item in a social network.