CLICK-THROUGH LOG MINING

• US 20080208841A1
• Filed: 10/10/2007
• Published: 08/28/2008
• Est. Priority Date: 02/22/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Li, Hua, Chen, Zheng, Wang, Jian, Hu, Jian, Zeng, Huajun
• Granted Patent: US 8,321,448 B2
• Time in Patent Office: Days
• US Class Current: 707/5
• 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

Abstract

Click-through log mining is described. Raw search click-through log data is processed to generate ordered query keywords, utilizing an algorithm to expand user-submitted keywords to include high frequency user queries, managing the keywords for a keyword expansion file, analyzing the algorithm performance on a bidding criteria, and identifying related phrases with similar page-click behaviors for advertisements.

Claims

1. A method for providing keyword searches, implemented at least in part by a computing device, the method comprising

processing raw search click-through log data to generate ordered query keywords for click-through log;

utilizing an algorithm to expand the keywords to include high frequency user queries;

managing the keywords for a keyword expansion file;

analyzing the algorithm performance on a bidding criteria; and

identifying related phrases with similar page-click behaviors for advertisements.

2. The method of claim 1, wherein the algorithm comprises constructing a bipartite graph with a first set of vertices corresponding to queries and a second set of vertices corresponding to web pages.

3. The method of claim 2, wherein the algorithm further comprises determining a relationship between the queries and the web pages by;

determining a similarity between the queries that have visited similar web pages;

determining the similarity between the web pages that have visited by similar queries; and

iteratively computing the similarity between the queries and the web pages until a fixed point is reached.

4. The method of claim 1, further comprising using the similarities between the queries to look up ad keywords within a click-through log to get a top number (N) most similar query.

5. The method of claim 1, wherein:

the algorithm comprises a query-uniform resource locator (URL) correlation learned from a query-URL mapping file; and

the algorithm calculates the keywords based on a correlated URL.

6. The method of claim 1, wherein the algorithm further comprises ranking related keywords with a relevance score.

7. The method of claim 1, wherein the bidding criteria comprises at least one of a click-through rate or a revenue per search.

8. The method of claim 1, further comprising sorting query-URL word pairs according to a query alphabet.

9. The method of claim 1, further comprising filtering query-URL word pairs.

10. The method of claim 1, further comprising selecting at least one option to amend the keyword expansion file or to replace the keyword expansion file.

11. A computer-readable storage media comprising computer-readable instructions executed on a computing device, the computer-readable instructions comprising instructions for:

processing raw search click-through log data to generate ordered query keywords for click-through log;

utilizing an algorithm to expand the keywords to include high frequency user queries;

managing the keywords for a keyword expansion file;

analyzing the algorithm performance on a bidding criteria; and

identifying related phrases with similar page-click behaviors for advertisements.

12. The computer-readable storage media of claim 11, wherein the algorithm comprises constructing a bipartite graph with a first set of vertices corresponding to queries and a second set of vertices corresponding to web pages.

13. The computer-readable storage media of claim 11, wherein the algorithm further comprises determining a relationship between the queries and the web pages by;

determining a similarity between the queries that have visited similar web pages;

determining the similarity between the web pages that have visited by similar queries; and

iteratively computing the similarity between the queries and the web pages until a fixed point is reached.

14. The computer-readable storage media of claim 11, further comprising using the similarities between the queries to look up ad keywords within a click-through log to get a top number (N) most similar queries.

15. The computer-readable storage media of claim 11, wherein:

the algorithm comprises a query-uniform resource locator (URL) correlation learned from a query-URL mapping file; and

the algorithm calculates the keywords based on a correlated URL.

16. A keyword suggestion system, comprising:

a processor;

a memory coupled to the processor, wherein the processor is configured for;

processing raw search click-through log data to generate ordered query keywords for click-through log;

utilizing an algorithm to expand the keywords to include high frequency user queries;

managing the keywords for a keyword expansion file;

analyzing the algorithm performance on a bidding criteria, wherein the bidding criteria comprises at least one of a click-through rate or a revenue per search; and

identifying related phrases with similar page-click behaviors for advertisements.

17. The system of claim 16, wherein the algorithm further comprises constructing a bipartite graph with a first set of vertices corresponding to queries and a second set of vertices corresponding to web pages.

18. The system of claim 16, wherein the algorithm further comprises identifying a relationship between the queries and the web pages by;

determining a similarity between the queries that have visited similar web pages;

determining the similarity between the web pages that have visited by similar queries; and

iteratively computing the similarity between the queries and the web pages until a fixed point is reached.

19. The system of claim 16, further comprising using the similarities between the queries to look up ad keywords within a click-through log to get a top number (N) most similar queries;

20. The system of claim 16, further comprising selecting at least one option to amend the keyword expansion file or to replace the keyword expansion file.