IDENTIFICATION AND USE OF WEB SEARCHER EXPERTISE

• US 20080319976A1
• Filed: 06/23/2007
• Published: 12/25/2008
• Est. Priority Date: 06/23/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: White, Ryen William, Morris, Daniel Scott
• Granted Patent: US 7,996,400 B2
• Time in Patent Office: Days
• US Class Current: 707/5
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

A search expertise level system and method for determining a search expertise level of a search engine user and then using that information to improve the searcher'"'"'s experience. The search expertise level system and method identifies the search expertise level of the searcher based on query behavior, post-query browsing behavior, and other behaviors of the searcher. One simple and important behavior that indicates a skilled searcher is the use of advanced query syntax and operators in the query. Once the search expertise level of a searcher is known, the search engine user interface can be modified and tailored to the needs of both skilled and novice searchers. The search expertise level also can be used to rank search results, such that search results for a novice searcher are ranked differently than those for a skilled searcher. The search expertise level also can be used in advertising and marketing.

Claims

1. A method for improving an implementation of a search engine, comprising:

identifying a level of search expertise of a searcher that is using the search engine; and

using the search expertise level to improve the experience that the searcher has with the search engine when performing a search.

2. The method of claim 1, further comprising identifying the search expertise level based on a query behavior of the searcher.

3. The method of claim 2, further comprising:

statistically correlating at least one of a plurality of query behavior features with the search expertise level of the searcher;

identifying if and how the searcher uses advanced query syntax as a query behavior feature; and

identifying if and how the searcher uses advanced query operators as a query behavior feature.

4. The method of claim 3, further comprising:

identifying a number of queries that are constructed by the searcher during a search session as a query behavior feature; and

identifying a number of queries submitted during a time period by the searcher as a query behavior feature.

5. The method of claim 3, further comprising:

identifying a length of each query composed by the searcher during a search session as a query behavior feature; and

identifying a propensity of the searcher to click on a search result in a search results list as a query behavior feature.

6. The method of claim 3, further comprising:

identifying a location of where the searcher clicks in search results as a query behavior feature; and

identifying how often the searcher repeats a query as a query behavior feature.

7. The method of claim 1, further comprising identifying the search expertise level based on a post-query browsing behavior, which is browsing behavior of the searcher after a query has been submitted to the search engine and a search results list has been returned to the searcher.

8. The method of claim 7, further comprising:

statistically correlating at least one of a plurality of post-query browsing behavior features with the search expertise level of the searcher; and

identifying a number of times the searcher revisits pages in a search trail as a post-query browsing behavior feature.

9. The method of claim 8, further comprising:

identifying an amount of time the searcher spends traversing the search trails as a post-query browsing behavior feature; and

identifying how long the searcher spends viewing each document in a search results list as a post-query browsing behavior feature.

10. The method of claim 8, further comprising:

identifying a number of steps in the search trail that is followed by the searcher as a post-query browsing behavior feature; and

identifying a frequency at which the searcher branches as a post-query browsing behavior feature.

11. The method of claim 1, further comprising:

identifying the search expertise level based on additional behaviors of the searcher;

statistically correlating at least one of a plurality of additional behavior features with the search expertise level of the searcher; and

identifying at least one of the following as an additional behavior feature;

(a) a number of different search engines used by the searcher;

(b) a number of different Web browsers using by the searcher;

(c) whether the searcher uses Web browser tabs;

(d) specific operating systems, Web browsers, or other software packages known to be used by skilled searchers;

(e) whether a searcher navigates to Web sites that attract expert users in a field or highly informed users.

12. The method of claim 1, further comprising

identifying the searcher as a skilled searcher;

displaying a higher number of search results per page than normally displayed;

displaying a more advanced search user interface automatically without a need for the searcher to click on an “

advanced search”

button; and

displaying detailed information about how and why each search result received it ranking in the search results list.

13. The method of claim 12, further comprising

displaying a shorter amount of text describing each search result than is normally provided such that the amount of text describing each search result is inversely proportional to the search expertise level;

displaying available keyboard shortcuts in a user interface that can be used to navigate a search results list containing the search results; and

displaying a personal Web search history to the searcher such that a previously executed search can be easily repeated by the searcher.

14. The method of claim 1, further comprising

identifying the searcher as a novice searcher;

displaying alternate query suggestions to the novice searcher to aid the searcher in refining an initial query, wherein the alternate query suggestions are based on queries performed by skilled searchers; and

displaying a tutorial and description of how advanced query syntax and operators would affect the initial query.

15. The method of claim 14, further comprising

displaying a “

help”

button that the novice searcher can click on to receive help with formulating a query; and

displaying examples of strategies used by skilled searchers when looking for topics related to the initial query, including examples of the skilled searchers query and post-query browsing behaviors.

16. A computer-readable medium having computer-executable instructions for using a search expertise level in displaying data in a search engine, comprising:

identifying the search expertise level of a searcher using the search engine based on a query behavior of the searcher;

obtaining a search results list containing search results; and

displaying the search results list to the searcher using a user interface such that the order of search results is dependent on the search expertise level.

17. The computer-readable medium of claim 16, further comprising ranking the search results based on the search expertise level.

18. The computer-readable medium of claim 17, further comprising ranking the search results based on how often skilled searchers visit a page represented by a search result, such that a first page visited by a skilled searcher more frequently than a second page is ranked higher in the search results than the second page.

19. The computer-readable medium of claim 16, further comprising evaluating performance of the search engine by determining how well the search engine returns in the search results pages that skilled searchers visit.

20. A computer-implemented process for displaying advertisements to a searcher using a search engine, comprising:

identifying a search expertise level of the searcher; and

displaying advertisements to the searcher through a search engine user interface based on the search expertise level of the searcher.