Query classification based on query click logs

• US 7,877,404 B2
• Filed: 03/05/2008
• Issued: 01/25/2011
• Est. Priority Date: 03/05/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Achan, Kannan, Tsaparas, Panayiotis, Fuxman, Ariel, Agrawal, Rakesh
• Primary Examiner(s): NGUYEN, CAM LINH T
• Application Number:
  US12/042,531
• Publication Number:
  US 20090228353A1
• Time in Patent Office: 1,056 Days
• Field of Search: 707 1- 7, 707/10, 707100-102, 707/103.Y, 707/103.Z, 707/104.1, 707/602, 707/603, 707/672, 707/713, 707/737, 707/740, 707/768
• US Class Current: 707/768
• CPC Class Codes: G06F 16/3326 using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages
• CPC Class Codes: G06F 16/3338 Query expansion
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0256 User search

Abstract

Methods are provided for the classification of search engine queries and associated documents based on search engine query click logs. One or more seed documents or queries are provided that contain content that is representative of a category. A query click log containing information regarding queries entered by at least one user into the search engine and documents subsequently clicked in search engine results corresponding with the queries is analyzed to determine which one or more queries resulted in clicks on the seed documents. Information is stored associating the one or more queries with the category if they resulted in clicks on the seed documents.

Claims

1. One or more computer-readable media having computer-executable instructions embodied thereon that, when executed, facilitate a method of determining that a query is relevant to a category of information, the method comprising:

associating a seed document with the category, wherein the seed document is trusted to be relevant to the category;

receiving an identification of a query that was previously input to a search engine, wherein, when a search-result document was presented in response to the query, the search-result document was selected;

determining that the search-result document matches the seed document; and

based on the search-result document matching the seed document, inferring that the query is relevant to the category.

2. The one or more computer-readable media of claim 1, the method further comprising:

receiving a search query submitted by a user;

determining that the search query matches another query deemed relevant to the category; and

based on the search query matching the other query, classifying the search query under the category.

3. The one or more computer-readable media of claim 2, wherein the method further comprises, based on the classifying the search query under the category, inferring that a search result associated with the category is relevant to the search query, and wherein the search result is provided in response to the search query.

4. The one or more computer-readable media of claim 2, wherein the method further comprises:

identifying one or rules for ranking search results based on the category; and

providing ranked search results for the search query based on the one or more rules.

5. The one or more computer-readable media of claim 2, wherein the method further comprises:

providing search results for the search query, wherein at least a portion of the search results correspond with one or more documents associated with the category.

6. The one or more computer-readable media of claim 1, wherein the method further comprises:

determining, from a query log of the query, another search-result document that was selected; and

determining that the other search-result document matches another seed document known to be relevant to the category.

7. The one or more computer-readable media of claim 6, wherein the method further comprises:

receiving a search query submitted by a user;

determining that the search query matches another query deemed relevant to the category; and

based on the search query matching the other query, providing the other search-result document as a search result.

8. The one or more computer-readable media of claim 1, wherein the method further comprises:

generating a list of keywords for the category, wherein the keywords include the query.

9. One or more computer-readable media having computer-executable instructions embodied thereon that, when executed, facilitate a method of determining that a query is relevant to a category of information, the method comprising

associating a seed document with the category, wherein the seed document is trusted to be relevant to the category;

receiving an identification of a query that was previously input to a search engine, wherein, when a search-result document was presented in response to the query, the search-result document was selected;

determining that the search-result document matches the seed document;

based on the search-result document matching the seed document, deeming the query to be relevant to the category;

receiving a request to provide a keyword that is relevant to the category; and

providing the query as the keyword that is relevant to the category.

10. The one or more computer-readable media of claim 9, wherein the seed document contains content that describes the category, which an entity desires to have its message displayed in conjunction with.

11. The method of claim 10, wherein the entity is an advertiser and the message is an advertisement.

12. The one or more computer-readable media of claim 11, wherein the keyword is provided to the advertiser.

13. The one or more computer-readable media of claim 12, wherein the advertiser purchases rights to have its advertisement displayed to a user when the user enters a search query containing the keyword.

14. The one or more computer-readable media of claim 13, wherein the search query entered by a user is received.

15. The one or more computer-readable media of claim 14, wherein the advertisement is displayed to the user in conjunction with search results returned by the search engine.

16. One or more computer-readable media having computer-executable instructions embodied thereon that, when executed, facilitate a method of determining that a query is relevant to a category of information, the method comprising:

associating a set of seed documents with the category, wherein each seed document of the set of seed documents is trusted to be relevant to the category;

receiving an identification of a query that was previously input to a search engine, wherein, when search-result documents were presented in response to the query, a portion of the search-result documents were selected;

determining that a percentage of the portion includes a search-result document that matches a seed document; and

when the percentage exceeds a threshold percentage, deeming the query to be relevant to the category.