SYSTEM AND METHOD FOR RECOMMENDING CONTENT BASED ON SEARCH HISTORY AND TRENDING TOPICS

• US 20130110823A1
• Filed: 10/26/2011
• Published: 05/02/2013
• Est. Priority Date: 10/26/2011
• Status: Active Grant

• Current Assignee: Yahoo Assets LLC
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Su, Hang, Gurumurthy, Siva, Wu, Huming
• Granted Patent: US 10,776,431 B2
• Time in Patent Office: Days
• US Class Current: 707/723
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering

Abstract

Systems and methods for providing content associated with trending topics relevant to a user are described. An interest detection module identifies topics trending in one or more real-time content sources that are relevant to a user. The real-time content source(s) may include, for example, a source of microblog posts or other user-generated data, a news feed, or the like. The topics trending that are relevant to the user are identified by comparing a search history of the user with one or more trending topics stored in a database. A content retriever module is configured to return one or more documents to the user in response to identifying the one or more topics trending that are relevant to the user.

Claims

1. A method for providing content associated with trending topics relevant to a user, comprising:

obtaining a search history of a user;

determining one or more interests of the user based on the search history;

accessing a database that includes one or more trending topics that are identified from one or more real-time content sources including real-time, user-generated content;

determining whether a match exists between the determined one or more interests of the user and the one or more of the trending topics included in the database; and

in response to determining that a match exists, retrieving content associated with the one or more trending topics matched with the determined one or more interests of the user for delivery to the user.

2. The method of claim 1, wherein the search history comprises at least one of a history of one or more search queries previously made by the user or a history of one or more documents previously accessed by the user.

3. The method of claim 1, wherein the one or more trending topics are identified by concepts and named entities determined by segmenting documents received from the one or more real-time content sources.

4. The method of claim 3, wherein determining whether a match exists comprises:

segmenting the obtained search history into concepts and named entities;

determining a user interest level for each of the concepts and named entities obtained from the search history;

determining a match between the concepts and named entities that are associated with the search history and concepts and named entities that are associated with the one or more trending topics;

for each matched concept and named entity;

summing probabilities assigned to the matched concept and named entity, each concept and named entity having an associated probability for each of the one or more trending topics, each probability indicating that the concept and named entity belongs to a respective topic of the one or more trending topics;

weighting the summed probabilities by the user interest level for the matched concept and named entity to determine a relevance value for the matched concept and named entity;

comparing each of the relevance values to a threshold value; and

selecting matched concepts and named entities associated with relevance values that satisfy the threshold value.

5. The method of claim 1, wherein the search history comprises records of search-related activities of the user during a predetermined time interval.

6. The method of claim 1, wherein retrieving content associated with the one or more trending topics matched with the determined one or more interests of the user for delivery to the user comprises:

generating a topic index for one or more documents located in one or more content sources;

accessing the topic index to locate one or more documents located in the one or more content sources based on the one or more trending topics matched with the determined one or more interests of the user;

generating a relevance value for each of the one or more documents located; and

returning the one or more documents having a relevance value greater than a predetermined threshold level.

7. The method of claim 1, wherein the retrieved content is delivered to the user by presenting the retrieved content on a home page of the user.

8. A system for providing content associated with trending topics relevant to a user, comprising:

one or more processors;

an interest detection module, at least partially implemented by at least one of the one or more processors, that is configured to identify topics trending in one or more real-time content sources including real-time, user-generated content that are relevant to a user, wherein the topics trending that are relevant to the user are identified by comparing a search history of the user with one or more trending topics stored in a database; and

a content retriever module, at least partially implemented by at least one of the one or more processors, that is configured to return one or more documents to the user in response to identifying the one or more topics trending that are relevant to the user.

9. The system of claim 8, wherein the search history comprises at least one of a history of one or more search queries previously made by the user or a history of one or more documents previously accessed by the user.

10. The system of claim 8, wherein the database storing the one or more trending topics includes concepts and named entities associated with the one or more trending topics.

11. The system of claim 10, wherein documents located in the one or more real-time content sources are segmented to determine the concepts and named entities associated with the one or more trending topics.

12. The system of claim 11, wherein the interest detection module is further configured to:

determine a match between concepts and named entities associated with one or more trending topics and the concepts and named entities associated with the search history;

access a topic index to locate one or more documents located in one or more content sources based on the matched concepts and named entities;

generate a relevance value for each of the one or more documents located; and

return one or more documents having a relevance value greater than a predetermined threshold level.

13. The system of claim 8, wherein the search history that is compared with the one or more trending topics stored in a database is limited to a predetermined time interval.

14. The method of claim 8, wherein the one or more documents returned to the user is presented on a home page of the user.

15. A computer program product comprising a computer-readable storage device having computer program logic recorded thereon, which, when executed by a processor, performs a form providing content associated with trending topics relevant to a user, the method comprising:

receiving a search history;

matching contents of the search history to one or more trending topics stored within a database, the trending topics being identified based on an analysis of real-time, user-generated content of one or more real-time content sources;

retrieving one or more documents that are relevant to the user based on the matched one or more trending topics; and

returning the retrieved one or more documents to the user.

16. The computer-program product of claim 15, wherein the search history comprises at least one of a history of one or more search queries previously made by the user and a history of one or more documents previously accessed by the user.

17. The computer-program product of claim 15, wherein retrieving one or more documents that are relevant to the user based on the matched one or more trending topics comprises:

accessing a topic index to locate the one or more documents to be retrieved that are relevant to the user;

generating a relevance value for each of the one or more documents so located; and

retrieving one or more documents having a relevance value greater than a predetermined threshold level;

18. The computer-program product of claim 15, wherein the one or more documents are retrieved from at least one of:

a source of microblog posts;

a source of social networking messages;

a source of news articles;

or

a source of information from a current events Web site.

19. The computer-program product of claim 15, wherein the search history received is limited to a predetermined time interval.

20. The computer-program product of claim 15, wherein the one or more documents returned to the user is presented on a home page of the user.