Temporal search query personalization

• US 8,463,775 B2
• Filed: 03/15/2010
• Issued: 06/11/2013
• Est. Priority Date: 07/06/2006
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Sidhu, Kulraj, Chowdhury, Abdur R.
• Primary Examiner(s): VU, BAI DUC
• Application Number:
  US12/723,778
• Publication Number:
  US 20100235375A1
• Time in Patent Office: 1,184 Days
• Field of Search: None
• US Class Current: 707/725
• CPC Class Codes: G06F 16/2428 Query predicate definition using graphical user interfaces, including menus and forms G06F16/2423 takes precedence
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

A user is made able to configure a search query to be responsive to temporal factors in order to adjust the search query to more accurately reflect the user'"'"'s true information need. By adjusting the search query in this way, the user is more likely to receive satisfactory search results.

Claims

1. A method comprising:

monitoring electronic document browsing behavior of a user;

storing browsing information descriptive of content accessed by the user, wherein the browsing information comprises one or more words identified from one or more electronic documents browsed by the user in association with an indication of when the one or more electronic documents were browsed by the user;

receiving a request for content from the user, the request being associated with a time period corresponding to relevant electronic document browsing behavior of the user;

accessing, from the stored browsing information descriptive of content accessed by the user, information descriptive of content accessed by the user during the time period, the accessed information including at least a portion of the one or more words identified from the one or more electronic documents browsed by the user;

using at least a portion of the accessed information descriptive of content accessed by the user during the time period to identify content to provide in response to the request for content, wherein identifying content to provide in response to the request for content comprises;

identifying a plurality of results responsive to the request, wherein the plurality of results fall into a plurality of potential content classifications;

determining, based on the at least a portion of the accessed information descriptive of content accessed by the user during the time period, that the user is likely to be interested in results related to a particular content classification within the plurality of potential content classifications; and

prioritizing the results related to the particular content classification over results related to other content classifications within the plurality of potential content classifications; and

providing the prioritized results in response to the request for content.

2. The method of claim 1:

wherein receiving the request for content from the user comprises receiving a search query from the user;

wherein using at least a portion of the accessed information descriptive of content accessed by the user during the time period content to identify content to provide in response to the request for content comprises;

adjusting the received search query to include the at least a portion of the accessed information descriptive of content accessed by the user during the time period, the at least a portion of the accessed information including at least one word identified as being descriptive of overall content included in an electronic document browsed by the user during the time period, and

identifying search results using the adjusted search query; and

wherein providing the prioritized results in response to the request for content comprises providing the identified search results responsive to the adjusted search query.

3. The method of claim 2 wherein adjusting the received search query to include the at least a portion of the accessed information descriptive of content accessed by the user during the time period comprises:

identifying at least one additional search term that is not included in the received search query and that is included in the accessed information descriptive of content accessed by the user during the time period; and

adjusting the received search query to include the identified at least one additional search term.

4. The method of claim 1 further comprising:

generating a feature vector for electronic documents accessed by the user during the electronic document browsing; and

storing the generated feature vector.

5. The method of claim 4:

further comprising identifying one or more words descriptive of overall content included in the one or more electronic documents based on relative frequency of occurrence of the one or more words in the one or more electronic documents by identifying, from at least one electronic document browsed by the user, a word appearing most frequently; and

wherein generating the feature vector for electronic documents accessed by the user during the electronic document browsing comprises including the word in the feature vector as being representative of the at least one electronic document.

6. The method of claim 5 wherein generating the feature vector further comprises including a time indication in the feature vector, the time indication indicating a time frame during which the at least one electronic document was accessed by the user, and including a classification of the at least one electronic document in the feature vector, the classification indicating a type of information included in the at least one electronic document.

7. The method of claim 1 wherein using at least a portion of the accessed information descriptive of content accessed by the user during the time period to identify content to provide in response to the request for content comprises excluding content that does not correspond to the accessed information descriptive of content accessed by the user during the time period.

8. A system comprising:

at least one processor; and

at least one non-transitory computer-readable medium coupled to the at least one processor having instructions stored thereon which, when executed by the at least one processor, causes the at least one processor to perform steps comprising;

monitoring electronic document browsing behavior of a user;

storing browsing information descriptive of content accessed by the user, wherein the browsing information comprises one or more words identified from one or more electronic documents browsed by the user in association with an indication of when the one or more electronic documents were browsed by the user;

receiving a request for content from the user, the request being associated with a time period corresponding to relevant electronic document browsing behavior of the user;

accessing, from the stored browsing information descriptive of content accessed by the user, information descriptive of content accessed by the user during the time period, the accessed information including at least a portion of the one or more words identified from the one or more electronic documents browsed by the user;

using at least a portion of the accessed information descriptive of content accessed by the user during the time period to identify content to provide in response to the request for content, wherein identifying content to provide in response to the request for content comprises;

identifying a plurality of results responsive to the request, wherein the plurality of results fall into a plurality of potential content classifications;

determining, based on the at least a portion of the accessed information descriptive of content accessed by the user during the time period, that the user is likely to be interested in results related to a particular content classification within the plurality of potential content classifications; and

prioritizing the results related to the particular content classification over results related to other content classifications within the plurality of potential content classifications; and

providing the prioritized results in response to the request for content.

9. The system of claim 8:

wherein receiving the request for content from the user comprises receiving a search query from the user;

wherein using at least a portion of the accessed information descriptive of content accessed by the user during the time period to identify content to provide in response to the request for content comprises;

adjusting the received search query to include at least a portion of the accessed information descriptive of content accessed by the user during the time period, the at least a portion of the accessed information including at least one word identified as being descriptive of overall content included in an electronic document browsed by the user during the time period, and

identifying search results using the adjusted search query; and

wherein providing the prioritized results in response to the request for content comprises providing the identified search results responsive to the adjusted search query.

10. The system of claim 9 wherein adjusting the received search query to include at least a portion of the accessed information descriptive of content accessed by the user during the time period comprises:

identifying at least one additional search term that is not included in the received search query and that is included in the accessed information descriptive of content accessed by the user during the time period; and

adjusting the received search query to include the identified at least one additional search term.

11. The system of claim 8 the steps further comprising:

generating a feature vector for electronic documents accessed by the user during the electronic document browsing; and

storing the generated feature vector.

12. The system of claim 11:

the steps further comprising identifying, from each of one or more electronic documents browsed by the user, one or more words descriptive of overall content included in the one or more electronic document based on relative frequency of occurrence of the one or more words in the one or more electronic documents by identifying, from at least one electronic document browsed by the user, a word appearing most frequently; and

wherein generating the feature vector for electronic documents accessed by the user during the electronic document browsing comprises including the word in the feature vector as being representative of the at least one electronic document.

13. The system of claim 12 wherein generating the feature vector further comprises including a time indication in the feature vector, the time indication indicating a time frame during which the at least one electronic document was accessed by the user, and including a classification of the at least one electronic document in the feature vector, the classification indicating a type of information included in the at least one electronic document.

14. The system of claim 8 wherein using at least a portion of the accessed information descriptive of content accessed by the user during the time period to identify content to provide in response to the request for content comprises excluding content that does not correspond to the accessed information descriptive of content accessed by the user during the specified time period.