Domain expertise determination

• US 8,930,357 B2
• Filed: 11/06/2012
• Issued: 01/06/2015
• Est. Priority Date: 10/06/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: White, Ryen W., Dumais, Susan T., Teevan, Jaime
• Primary Examiner(s): Spieler, William
• Application Number:
  US13/669,455
• Publication Number:
  US 20130060756A1
• Time in Patent Office: 791 Days
• Field of Search: 707/732
• US Class Current: 707/732
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

A user'"'"'s domain expertise may be estimated through several factors by monitoring different aspects of a user'"'"'s interaction with a web browser. Based on the user'"'"'s domain expertise, search results may be presented to the user that is commensurate with their expertise, resulting in a more efficient and productive on line session. A user'"'"'s expertise in a knowledge domain may be determined from the user'"'"'s behavior, including analyzing search queries, monitoring how the user navigates between and through websites, and analyzing the specific cites visited. As a user interacts with a browser, the user'"'"'s estimated domain expertise may be updated and used to provide appropriate and useful search results. In many embodiments, a user may have different expertise levels for different technical domains.

Claims

1. A method comprising:

monitoring a web browser session by a user, including;

identifying a search query submitted by the user, the search query generating a search results page, the search results page including links to web sites in a technical domain;

during the web browser session, monitoring the user'"'"'s interaction with one or more web pages of the linked websites, including;

determining the branchiness of the user'"'"'s interaction with the search results page; and

identifying one or more technical words in said one or more web pages; and

determining an expertise of the user within the technical domain based on the determined branchiness of the user'"'"'s interaction and by comparing the one or more technical words to a mapping of technical words to expertise for the technical domain.

2. The method of claim 1, wherein determining the branchiness of the user'"'"'s interaction with the search results page comprises analyzing at least part of a session log to determine how many branches were performed by the user.

3. The method of claim 1, wherein determining the branchiness of the user'"'"'s interaction with the search results page comprises determining branchiness for a plurality of sessions related to the search results page, the plurality of sessions including the web browser session.

4. The method of claim 3, wherein determining branchiness for a plurality of sessions comprises aggregating web interactions from different instances of web browsers.

5. The method of claim 1, further comprising accessing a session length for the web browser session.

6. The method of claim 5, wherein determining an expertise of the user within the technical domain comprises using the session length to determine a user expertise level.

7. The method of claim 1, further comprising storing the determined user expertise level.

8. A method comprising:

determining a user expertise level of a user within a technical domain;

identifying a website selected by the user;

determining an expertise level and an associated technical domain for the website by associating the user expertise level and the technical domain with the website; and

storing the expertise level and the associated technical domain for the website.

9. The method of claim 8, wherein determining a user expertise level comprises accessing a stored user expertise level for the user.

10. The method of claim 9, wherein accessing a stored user expertise level for the user comprises accessing a cookie that contains the user'"'"'s expertise level for one or more specific technology domains, including the technical domain.

11. The method of claim 8, further comprising returning search results for a search query that are tailored to the user expertise level within the technical domain, including:

accessing search results for the search query; and

modifying the search results for the submitted search query to match the user expertise level within the technical domain prior to returning the search results.

12. The method of claim 11, wherein returning search results for the search query that are tailored to the user expertise level within the technical domain comprises making one of query or site suggestions based on the user expertise level within the technical domain.

13. The method of claim 11, wherein determining a user expertise level of the user within the technical domain comprises determining that the user is an expert within the technical domain based on one or more technical words included in the search query;

and

wherein returning search results for the search query that are tailored to the user expertise level within the technical domain comprises organizing search results for the search query so that more technical results are ranked higher than less technical results.

14. The method as recited in claim 11, wherein returning search results for the search query that are tailored to the user expertise level within the technical domain comprises adjusting the technical sophistication of the search results based on the user expertise level within the technical domain.

15. A method comprising:

accessing search results returned in response to a search query;

identifying one or more technical words from the search results;

accessing a mapping of technical words to expertise; and

determining an expertise of a user based on the one or more technical words by comparing the one or more technical words to the mapping.

16. The method of claim 15, wherein identifying one or more technical words from the search results comprises identifying a set of technical words from the search results;

and

wherein determining an expertise of the user based on the one or more technical words comprises determining an expertise of the user based on the set of technical words.

17. The method of claim 15, wherein determining an expertise of the user based on the one or more technical words comprises determining an expertise of the user based on a set of technical words.

18. The method of claim 15, wherein determining the branchiness of the user'"'"'s interaction with the search results based on one or more of:

a number of times the user selects a search result from the search page and then returns to the search page and considering browsing through websites that are not related to a search engine.

19. The method of claim 18, wherein determining an expertise of the user based on the one or more technical words comprises determining the expertise of the user based on the determined branchiness of the users interaction with the search results.