System and method for ranking search results based on tracked user preferences

• US 7,562,068 B2
• Filed: 06/30/2004
• Issued: 07/14/2009
• Est. Priority Date: 06/30/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Naam, Ramez
• Primary Examiner(s): Rones; Charles
• Assistant Examiner(s): ORTIZ DITREN, BELIX M
• Application Number:
  US10/879,046
• Publication Number:
  US 20060004711A1
• Time in Patent Office: 1,840 Days
• Field of Search: None
• US Class Current: 1/1
• 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
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

A method and system are provided for ranking search results based on user preferences. The method includes monitoring user selections in response to user receipt of search results and tracking metadata related to user selections for user selections that exhibit a threshold satisfaction level. The method additionally includes storing the tracked metadata as user preferences and adjusting a ranking mechanism to increase the weight of user preferences in order to increase a ranking for search results that exhibit user preferences. The method additionally includes storing the user selections and the keyword search upon determining that the user selections exceed a threshold satisfaction level. The method may utilize the stored user selections and keyword search upon receiving a repeat search to alter presentation of new search results to the user.

Claims

1. One or more computer-storage media storing computer-useable instructions that, when used by a computing device, cause the computing device to perform a method for ranking search results based on individual user selections and user preferences for a user, the method comprising:

monitoring user selections of one or more search results from a first set of search results received in response to a first user search query;

identifying at least one search result from the one or more search results that meets a threshold satisfaction level based on satisfaction indicators associated with user selection of the at least one search result deviating from statistical satisfaction indicator norm data;

storing the at least one search result in association with the first user search query within the user preferences for the user;

tracking metadata associated with the at least one search result, wherein at least some of the tracked metadata comprises page attribute data, the page attribute data comprising at least one selected from the following;

website root domain, page language, document type, and document length;

storing the tracked metadata within the user preferences for the user;

receiving a second user search query, the second user search query matching the first user search query;

providing a second set of search results in response to the second user search query, wherein ranking of the at least one search result is increased in the second set of search results based on the second user search query matching the first user search query and the at least one search result being stored in association with the first user search query within the user preferences for the user;

receiving a third user search query, the third user search query not matching the first user search query; and

providing a third set of search results in response to the third user search query by adjusting a ranking mechanism used to rank one or more search results within the third set of search results by increasing a weighting assigned to page attributes associated with the one or more search results within the third set of search results corresponding with the tracked metadata stored within the user preferences for the user.

2. The computer- storage media of claim 1, wherein storing the tracked metadata comprises storing data describing file attributes of user selections.

3. The computer-storage media of claim 1, further comprising altering a user display to provide past search data separately from current search results.

4. The computer-storage media of claim 1, further comprising communicating the increased ranking to a core search engine.

5. The computer-storage media of claim 1, wherein a satisfaction indicator comprises at least one factor of the number of times a user selects a website link or the length of time a user spends viewing a website.

6. A computerized system for ranking search results based on individual user preferences, the computerized system including a processor and one or more computer-storage media comprising:

a search satisfaction tracker for monitoring user selections of one or more search results from a first set of search results received in response to a first user search query and tracking user satisfaction of at least one search result from the one or more search results where the at least one search result meets a threshold satisfaction level based on satisfaction indicators associated with the user selection of the at least one search result deviating from statistical satisfaction indicator norm data, wherein at least some metadata tracked comprises page attribute data, the page attribute data comprising at least one selected from the following;

website root domain, page language, document type, and document length, and wherein the search satisfaction tracker stores the at least one search result in association with the first user search query within the user preferences for the user and, further, stores the tracked metadata within the user preferences for the user; and

a personalization ranker for ranking search results for the user based on the tracked user satisfaction by increasing a weighting of one or more search results to increase a ranking for the search results that exhibit individual user preferences, wherein the weighting is based on a deviation of the individual user preferences from a statistical norm for a searching population, the strength of the deviation correlating to the strength of the weighting, the personalization tracker providing a second set of search results in response to a second user search query, wherein ranking of the at least one search result is increased in the second set of search results based on the second user search query matching the first user search query and the at least one search result being stored in association with the first user search query within the user preferences for the user, and the personalization tracker further providing a third set of search results in response to a third user search query by adjusting a ranking mechanism used to rank one or more search results within the third set of search results by increasing a weighting assigned to page attributes associated with the one or more search results within the third set of search results corresponding with the tracked metadata stored within the user preferences for the user.

7. The computerized system of claim 6, wherein the search satisfaction tracker comprises a past searches area for storing past searches and corresponding user selections exceeding a-preset preset satisfaction threshold.

8. The computerized system of claim 6, further comprising a variation detector for determining the deviation of the satisfaction level from the statistical norm.

9. The computerized system of claim 6, wherein the personalization ranker comprises a communication mechanism for receiving information from the search satisfaction tracker and a ranking mechanism for recommending result rankings based on the received information.

10. The computerized system of claim 6, wherein a satisfaction indicator comprises at least one factor of the number of times a user selects a website link or the length of time a user spends viewing a website.

11. The computerized system of claim 6, wherein the personalization ranker communicates the increased ranking to a core search engine.

12. The computerized system of claim 6, wherein the personalization ranker alters a user display to provide past search data separately from current search results.

15. The computerized system of claim 6, wherein the tracked metadata stored by the search satisfaction tracker comprises storing data describing file attributes of user selections.

13. A computing device having a processor and one or more computer- storage media storing computer-useable instructions that, when used by the computing device, cause the computing device to perform a method for ranking search results based on individual user selections and user preferences for a user, the method comprising:

monitoring user selections of one or more search results from a first set of search results received in response to a first user search query;

identifying at least one search result from the one or more search results that meets a threshold satisfaction level based on satisfaction indicators associated with user selection of the at least one search result deviating from statistical satisfaction indicator norm data;

storing the at least one search result in association with the first user search query within the user preferences for the user;

tracking metadata associated with the at least one search result, wherein at least some of the tracked metadata comprises page attribute data, the page attribute data comprising at least one selected from the following;

website root domain, page language, document type, and document length;

storing the tracked metadata within the user preferences for the user;

receiving a second user search query, the second user search query matching the first user search query;

providing a second set of search results in response to the second user search query, wherein ranking of the at least one search result is increased in the second set of search results based on the second user search query matching the first user search query and the at least one search result being stored in association with the first user search query within the user preferences for the user;

receiving a third user search query, the third user search query not matching the first user search query; and

providing a third set of search results in response to the third user search query by adjusting a ranking mechanism used to rank one or more search results within the third set of search results by increasing a weighting assigned to page attributes associated with the one or more search results within the third set of search results corresponding with the tracked metadata stored within the user preferences for the user.

14. The computing device of claim 13, wherein storing the tracked metadata comprises storing data describing file attributes of user selections.

16. The computing device of claim 13, further comprising altering the presentation of search results by changing an ordering of the presented results.

17. The computing device of claim 13, further comprising altering a user display to provide past search data separate from current search results.

18. The computing device of claim 13 wherein a satisfaction indicator comprises at least one factor of the number of times a user selects a website link or the length of time a user spends viewing a website.