Scoring stream items in real time

• US 9,858,275 B1
• Filed: 09/01/2015
• Issued: 01/02/2018
• 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, Sivakumar, Dandapani, Sung, Sangsoo, Kosslyn, Justin, Jackson, Todd, Rohe, Andre, Luo, Ya, Bunner, Andrew, Sobol, Alexander, de Alfaro, Luca
• Primary Examiner(s): HASAN, SYED HAROON
• Application Number:
  US14/842,554
• Time in Patent Office: 854 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 real-time stream of content from heterogeneous data sources and a real-time index. The heterogeneous data sources include search, entertainment, social activity and activity on third-party sites. A fetching unit retrieves recent content that is indexed in the real-time index according to keywords. A model generation engine generates a model based on user activities. The mixer compares candidate content items from the heterogeneous data sources and the real-time index to the model to generate scores for each item and generates a stream of content based on the scores.

Claims

1. A computer-implemented method comprising:

generating a first global score for a content item obtained from heterogeneous data sources, the first global score being independent from users and indicating popularity or importance of the content item within a source stream that produced the content item;

generating a second global score by normalizing the first global score across a plurality of source streams;

determining a first candidate user for the content item based on the second global score and by querying a social graph using metadata associated with the content item;

computing, based on a model, a first user score for a pair of the first candidate user and the content item to evaluate a probability that the content item appears in a stream of content of the first candidate user;

determining whether a threshold is satisfied based on a volume and a quality of other content items on a same topic as the content item; and

determining whether to present the content item in the stream of content of the first candidate user based on the first user score and whether the threshold is satisfied.

2. The computer-implemented method of claim 1, further comprising:

determining a second candidate user for the content item based on the second global score and a social connection of the second candidate user to the content item;

computing, based on the model, a second user score for a pair of the second candidate user and the content item to evaluate a probability that the content item shows in a stream of content of the second candidate user; and

determining whether to present the content item in the stream of content of the second candidate user based on the second user score.

3. The computer-implemented method of claim 1, further comprising generating the model using a log of activities from the heterogeneous data sources.

4. The computer-implemented method of claim 1, wherein the model includes information about user consumption patterns, user preferences for freshness of content items and user statistics for resharing the content items.

5. The computer-implemented method of claim 1, further comprising receiving content items from a stream of content of other users with whom the first candidate user has a relationship and generating additional content items for the stream of content of the first candidate user based on the received content items.

6. The computer-implemented method of claim 5, wherein generating the additional content items comprises weighting the additional content items based on user interactions between the first candidate user and the other users.

7. The computer-implemented method of claim 1, further comprising generating an expandable explanation for the content item in the stream of content of the first candidate user.

8. 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 first global score for a content item obtained from heterogeneous data sources, the first global score being independent from users and indicating popularity or importance of the content item within a source stream that produced the content item;

generate a second global score by normalizing the first global score across a plurality of score streams;

determine a first candidate user for the content item based on the second global score and by querying a social graph using metadata associated with the content item;

compute, based on a model, a first user score for a pair of the first candidate user and the content item to evaluate a probability that the content item shows in a stream of content of the first candidate user;

determine whether a threshold is satisfied based on a volume and a quality of other content items on a same topic as the content item; and

determine whether to present the content item in the stream of content of the first candidate user based on the first user score and whether the threshold is satisfied.

9. The computer program product of claim 8, wherein the computer readable program when executed on the computer also causes the computer to:

determine a second candidate user for the content item based on the second global score and a social connection of the second candidate user to the content item;

compute, based on the model, a second user score for a pair of the second candidate user and the content item to evaluate a probability that the content item shows in a stream of content of the second candidate user; and

determine whether to present the content item in the stream of content of the second candidate user based on the second user score.

10. The computer program product of claim 8, wherein the computer readable program when executed on the computer also causes the computer to generate the model using a log of activities from the heterogeneous data sources.

11. The computer program product of claim 8, wherein the model includes information about user consumption patterns, user preferences for freshness of content items and user statistics for resharing the content items.

12. The computer program product of claim 8, wherein the computer readable program when executed on the computer also causes the computer to receive content items from a stream of content of other users with whom the first candidate user has a relationship and generate additional content items for the stream of content of the first candidate user based on the received content items.

13. The computer program product of claim 12, wherein generating the additional content items comprises weighting the additional content items based on user interactions between the first candidate user and the other users.

14. The computer program product of claim 8, wherein the computer readable program when executed on the computer also causes the computer to generate an expandable explanation for the content item in the stream of content of the first candidate user.

15. A system comprising:

one or more processors; and

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

generate a first global score for a content item obtained from heterogeneous data sources, the first global score being independent from users and indicating popularity or importance of the content item within a source stream that produced the content item;

generate a second global score by normalizing the first global score across a plurality of source streams;

determine a first candidate user for the content item based on the second global score and by querying a social graph using metadata associated with the content item;

compute, based on a model, a first user score for a pair of the first candidate user and the content item to evaluate a probability that the content item shows in a stream of content of the first candidate user;

determine whether a threshold is satisfied based on a volume and a quality of other content items on a same topic as the content item; and

determine whether to present the content item in the stream of content of the first candidate user based on the first user score and whether the threshold is satisfied.

16. The system of claim 15, wherein the system is further configured to:

determine a second candidate user for the content item based on the second global score and a social connection of the second candidate user to the content item;

compute, based on the model, a second user score for a pair of the second candidate user and the content item to evaluate a probability that the content item shows in a stream of content of the second candidate user; and

determine whether to present the content item in the stream of content of the second candidate user based on the second user score.

17. The system of claim 15, wherein the system is further configured to generate the model using a log of activities from the heterogeneous data sources.

18. The system of claim 15, wherein the model includes information about user consumption patterns, user preferences for freshness of content items and user statistics for resharing the content items.

19. The system of claim 15, wherein the system is further configured to receive content items from a stream of content of other users with whom the first candidate user has a relationship and generate additional content items for the stream of content of the first candidate user based on the received content items.

20. The system of claim 19, wherein generating the additional content items comprises weighting the additional content items based on user interactions between the first candidate user and the other users.

21. The system of claim 15, wherein the system is further configured to generate an expandable explanation for the content item in the stream of content of the first candidate user.