System and method for recommending content based on search history and trending topics

• US 10,776,431 B2
• Filed: 10/26/2011
• Issued: 09/15/2020
• Est. Priority Date: 10/26/2011
• Status: Active Grant

• Current Assignee: Yahoo Assets LLC
• Original Assignee: Oath Inc. (Verizon Communications Inc.)
• Inventors: Su, Hang, Gurumurthy, Siva, Wu, Huming
• Primary Examiner(s): Oberly, Van H
• Application Number:
  US13/282,017
• Publication Number:
  US 20130110823A1
• Time in Patent Office: 3,247 Days
• 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 implemented on a machine having at least one processor, storage, and a communication platform connected to a network for providing content to a user, comprising:

obtaining, in response to a user logging into a web site, a search history of the user, wherein the search history comprises prior searches performed by the user;

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

determining one or more trending topics associated with real-time content;

determining, in absence of a current query entered by the user when logging into the web site, at least one of the one or more interests that matches the one or more trending topics by;

identifying concepts and named entities from the search history,

determining one or more of the identified concepts and named entities that match the one or more trending topics,

for each of the one or more of the identified concepts and named entities that match the one or more trending topics;

summing probabilities assigned to the one or more of the identified concepts and named entities, wherein each of the one or more identified concepts and named entities has an associated probability for each of the one or more trending topics that represents a likelihood of the corresponding identified concept and named entity belonging to a respective topic of the one or more trending topics, and

weighting the probabilities based on a user interest level in the corresponding identified concepts and named entities,

computing a relevance value for each of the one or more of the identified concepts and named entities based on the weighted probabilities, wherein the relevance value is indicative of a level of relevance between a corresponding concept and named entity and a respective one of the one or more trending topics, and

selecting at least one of the one or more of the identified concepts and named entities based on a relevance criterion as the at least one of the one or more interests in accordance with the relevance value for the at least one of the one or more of the identified concepts and named entities;

retrieving trending content related to each of the at least one of the one or more interests; and

providing the trending content to the user.

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

3. The method of claim 1, wherein determining the one or more trending topics comprises:

segmenting the real-time content, received from one or more real-time content sources, into concepts and entities.

4. The method of claim 1, wherein determining the at least one of the one or more interests comprises:

segmenting the search history to identify the concepts and named entities;

determining the user interest level in each of the identified concepts and named entities;

determining the one or more of the identified concepts and named entities that are matched to the one or more trending topics by determining at least one match between the identified concepts and named entities and concepts and named entities identified from the one or more trending topics, wherein selecting the at least one of the one or more of the identified concepts and named entities based on the relevance criterion comprises;

comparing each of the relevance values to a threshold value, wherein the at least one of the one or more of the identified concepts and named entities is selected based on a corresponding relevance value satisfying 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 the retrieving comprises:

generating a topic index for one or more documents associated with the real-time content;

accessing the topic index to locate the one or more documents based on the at least one of the one or more interests;

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

returning at least one document of the one or more documents based on a determination that a corresponding relevance value of a document is greater than a predetermined threshold level.

7. The method of claim 1, wherein the trending content is delivered to the user by providing the trending content on a home page of the user in response to the user logging into the web site.

8. The method of claim 1, wherein the one or more trending topics are identified from one or more real-time content sources.

9. The method of claim 1, wherein the trending content is provided to the user without receiving a search request from the user.

10. The method of claim 1, wherein determining the one or more trending topics comprises:

segmenting the real-time content into one or more additional concepts and named entities for a given time interval; and

applying a probabilistic topic model to the one or more additional concepts and named entities to determine a volume calculation.

11. The method of claim 1, wherein determining the at least one of the one or more interests comprises:

segmenting the search history to identify the concepts and named entities;

determining the user interest level for each of the one or more of the identified concepts and the named entities; and

determining a weight with respect to an age of each of the prior searches in the search history such that the user interest level is lowered as the age of a corresponding prior search increases.

12. The method of claim 1, wherein the real-time content is received during a first time interval, the method further comprising:

determining that the first time interval has expired;

receiving additional real-time content during a second time interval; and

determining one or more additional trending topics associated with the additional real-time content such that new trending topics are identified periodically.

13. A system for providing content 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;

obtain, in response to a user logging into a web site, a search history of the user, wherein the search history comprises prior searches performed by the user,

determine one or more interests of the user based on the search history,

determine one or more trending topics associated with real-time content, and

determine, in absence of a current query entered by the user when logging into the web site, at least one of the one or more interests that matches the one or more trending topics by;

identifying concepts and named entities from the search history,

determining one or more of the identified concepts and named entities that match the one or more trending topics,

for each of the one or more of the identified concepts and named entities that match the one or more trending topics;

summing probabilities assigned to the one or more of the identified concepts and named entities, wherein each of the one or more identified concepts and named entities has an associated probability for each of the one or more trending topics that represents a likelihood of the corresponding identified concept and named entity belonging to a respective topic of the one or more trending topics, and

weighting the probabilities based on a user interest level in the corresponding identified concepts and named entities,

computing a relevance value for each of the one or more of the identified concepts and named entities based on the weighted probabilities, wherein the relevance value is indicative of a level of relevance between a corresponding concept and named entity and a respective one of the one or more trending topics, and

selecting at least one of the one or more of the identified concepts and named entities based on a relevance criterion as the at least one of the one or more interests in accordance with the relevance value for the at least one of the one or more of the identified concepts and named entities; and

a content retriever module, at least partially implemented by at least one of the one or more processors, that is configured to;

retrieve trending content related to each of the at least one of the one or more interests, and

provide the trending content to the user.

14. The system of claim 13, wherein the search history comprises a history of one or more documents previously accessed by the user.

15. The system of claim 13, wherein the one or more trending topics being determined comprises the interest detection module being further configured to:

segment the real-time content, received from one or more real-time content sources, into concepts and named entities.

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

generate a topic index for one or more documents associated with the real-time content;

access the topic index to locate the one or more documents based on the at least one of the one or more interests;

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

return at least one document of the one or more documents based on a determination that a corresponding relevance value of a document is greater than a predetermined threshold level.

17. The system of claim 13, 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.

18. The system of claim 13, wherein the trending content is provided on a home page of the user in response to the user logging into the web site.

19. A machine-readable tangible and non-transitory medium having information recorded thereon, wherein the information, when read by the machine, causes the machine to perform the following:

obtaining, in response to a user logging into a web site, a search history of the user, wherein the search history comprises prior searched performed by the user;

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

determining one or more trending topics associated with real-time content;

determining, in absence of a current query entered by the user when logging into the web site, at least one of the one or more interests that matches the one or more trending topics by;

identifying concepts and named entities from the search history,

determining one or more of the identified concepts and named entities that match the one or more trending topics,

for each of the one or more of the identified concepts and named entities that match the one or more trending topics;

summing probabilities assigned to the one or more of the identified concepts and named entities, wherein each of the one or more identified concepts and named entities has an associated probability for each of the one or more trending topics that represents a likelihood of the corresponding identified concept and named entity belonging to a respective topic of the one or more trending topics, and

weighting the probabilities based on a user interest level in the corresponding identified concepts and named entities,

computing a relevance value for each of the one or more of the identified concepts and named entities based on the weighted probabilities, wherein the relevance value is indicative of a level of relevance between a corresponding concept and named entity and a respective one of the one or more trending topics, and

selecting at least one of the one or more of the identified concepts and named entities based on a relevance criterion as the at least one of the one or more interests in accordance with the relevance value for the at least one of the one or more of the identified concepts and named entities;

retrieving trending content related to the at least one of the one or more interests; and

providing the trending content to the user.

20. The medium of claim 19, wherein the search history comprises a history of one or more documents previously accessed by the user.

21. The medium of claim 19, wherein the information, when read by the machine, further causes the machine to perform the following:

generating a topic index for one or more documents associated with the real-time content;

accessing the topic index to locate the one or more documents based on the at least one of the one or more interests;

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

returning at least one document of the one or more documents based on a determination that a corresponding relevance value of a document is greater than a predetermined threshold level.

22. The medium of claim 19, wherein the one or more real-time content sources comprise at least one of:

a microblog, a social networking, a news organization, and a current events web site.

23. The medium of claim 19, wherein the search history received is limited to a predetermined time interval.

24. The medium of claim 19, wherein the trending content is provided on a home page of the user in response to the user logging into the web site.