Method and system for ranking web pages in a search engine based on direct evidence of interest to end users

• US 9,230,024 B2
• Filed: 04/17/2013
• Issued: 01/05/2016
• Est. Priority Date: 06/27/2008
• Status: Active Grant

• Current Assignee: Walmart Apollo, LLC (WalMart Inc.)
• Original Assignee: Wal Mart Stores Inc (WalMart Inc.)
• Inventors: Young, David L., Pavlidis, Ioannis, Watler, William Randall, Musk, Kimbal J., Newcomb, Peter J., Reich, Robert
• Primary Examiner(s): HASAN, SYED HAROON
• Application Number:
  US13/865,087
• Publication Number:
  US 20130290288A1
• Time in Patent Office: 993 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

A method and system for ranking Web pages in a Web search engine is described. One illustrative embodiment receives a Web search query from a particular user, the query including at least one keyword; identifies one or more Web pages that contain the at least one keyword; determines, for each of the one or more Web pages, a raw page ranking; adjusts the raw page ranking of each of at least one Web page among the one or more Web pages based on direct evidence of how interesting that Web page is to users to produce an adjusted page ranking, the direct evidence being derived from clickstream data collected from the users; and presents, as search results, the at least one Web page to the particular user in accordance with the adjusted page rankings.

Claims

1. A computer implemented method comprising:

a computer server receiving a search query from a user;

the computer server identifying one or more result pages that pertain to the search query;

the computer server determining, for each of the one or more result pages, a raw page ranking;

the computer server determining a metric of direct evidence of user interest for at least one result page of the one or more result pages which is a result of a mathematical function which expresses how many users historically have visited the at least one result page subtracted from how many users have recently visited the at least one result page all divided by how many users historically have visited the at least one result page;

the computer server adjusting the raw page ranking of the at least one result page among the one or more result pages based on the metric of direct evidence of user interest for the at least one result page to produce an adjusted page ranking for the at least one result page; and

the computer server presenting, as search results, the at least one result page to the user in accordance with the adjusted page ranking;

wherein;

determining the metric of direct evidence of user interest for the at least one result page further comprises determining a measure of how often users traverse to or from the at least one result page while browsing.

2. The method of claim 1, wherein a combination of how many users have recently visited the at least one result page and how many users historically have visited the at least one result page is given greater weight than the measure of how often users traverse to or from the at least one result page while browsing.

3. The method of claim 1, wherein a combination of how many users have recently visited the at least one result page and how many users historically have visited the at least one result page is given greater weight than the measure of how often users traverse to or from the at least one result page while browsing by a factor of at least 10.

4. The method of claim 1, wherein the measure of how often users traverse to or from the at least one result page while browsing includes a correlation coefficient that is strengthened by additional user traversals to the at least one result page from other result pages and that is weakened by an absence, over time, of additional user traversals to the at least one result page from other result pages.

5. The method of claim 1, wherein adjusting the raw page ranking of the at least one result page among the one or more result pages based on the metric of direct evidence of user interest for the at least one result page to produce the adjusted page ranking includes scaling a number of user traversals to the at least one result page from other result pages.

6. The method of claim 1, wherein the metric of direct evidence of user interest for the at least one result page is more specifically a mathematical function which expresses how many users historically have visited the at least one result page in a predetermined length of time subtracted from how many users have recently visited the at least one result page in the predetermined length of time all divided by how many users historically have visited the at least one result page in the predetermined length of time.

7. The method of claim 1, wherein the raw page ranking of the at least one result page is adjusted in real time in response to the search query.

8. The method of claim 1, wherein the raw page ranking of the at least one result page is based, at least in part, on how frequently a search query keyword occurs in the at least one result page.

9. The method of claim 1, wherein the search query is a web search query and wherein the one or more result pages are one or more web pages.

10. The method of claim 9, wherein the metric of direct evidence of user interest for the at least one result page is derived from clickstream data collected from users.

11. A computer system comprising:

a computer processor;

computer memory connected to the computer processor, the computer memory storing a page rank module programmed to;

receive a search query from a user;

identify one or more result pages that pertain to the search query;

determine, for each of the one or more result pages, a raw page ranking;

determine a metric of direct evidence of user interest for at least one result page of the one or more result pages by which is a result of a mathematical function which expresses how many users historically have visited the at least one result page subtracted from how many users have recently visited the at least one result page all divided by how many users historically have visited the at least one result page;

adjust the raw page ranking of the at least one result page among the one or more result pages based on the metric of direct evidence of user interest for the at least one result page to produce an adjusted page ranking for the at least one result page; and

present, as search results, the at least one result page to the user in accordance with the adjusted page ranking;

wherein;

determine the metric of direct evidence of user interest for the at least one result page by determining a measure of how often users traverse to or from the at least one result page while browsing.

12. The system of claim 11, wherein page rank module is programmed to:

determine the metric of direct evidence of user interest for the at least one result page by giving greater weight to a combination of how many users have recently visited the at least one result page and how many users have historically visited the at least one result page than the measure of how often users traverse to or from the at least one result page while browsing.

13. The system of claim 11, wherein the page rank module is more specifically programmed to:

determine the metric of direct evidence of user interest for the at least one result page by giving greater weight to a combination of how many users have recently visited the at least one result page and how many users have historically visited the at least one result page than the measure of how often users traverse to or from the at least one result page while browsing by a factor of at least 10.

14. The system of claim 11, wherein the page rank module is programmed to:

determine the measure of how often users traverse to or from the at least one result page while browsing by including a correlation coefficient that is strengthened by additional user traversals to the at least one result page from other result pages and that is weakened by an absence, over time, of additional user traversals to the at least one result page from other result pages.

15. The system of claim 11, wherein page rank module is programmed to:

adjust the raw page ranking of the at least one result page among the one or more result pages based on the metric of direct evidence of user interest for the at least one result page to produce the adjusted page ranking by scaling a number of user traversals to the at least one result page from other result pages.

16. The system of claim 11, wherein the page rank module is more specifically programmed to:

determine the metric of direct evidence of user interest for the at least one result page which is the result of a mathematical function which expresses how many users historically have visited the at least one result page in a predetermined length of time subtracted from how many users have recently visited the at least one result page in the predetermined length of time all divided by how many users historically have visited the at least one result page in the predetermined length of time.

17. The system of claim 11, wherein the page rank module is programmed to:

adjust the raw page ranking of the at least one result page in real time in response to the search query.

18. The system of claim 11, wherein the search query is a web search query and wherein the one or more result pages are web pages, and wherein the metric of direct evidence of user interest for the at least one result page is derived from clickstream data collected from users.