Methods and systems for improving a search ranking using related queries

• US 7,505,964 B2
• Filed: 09/12/2003
• Issued: 03/17/2009
• Est. Priority Date: 09/12/2003
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Tong, Simon, Brin, Sergey, Pearson, Mark
• Primary Examiner(s): Pardo; Thuy N
• Application Number:
  US10/661,748
• Publication Number:
  US 20050060311A1
• Time in Patent Office: 2,013 Days
• Field of Search: 707/3, 707/4, 707/5, 707/6, 707/500, 707/10, 707/101, 707/102, 707/103.R, 707/104.1, 704/270
• US Class Current: 1/1
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99942 Manipulating data structure, e.g. compression, compaction, compilation
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99944 Object-oriented database structure
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

Systems and methods that improve search rankings for a search query by using data associated with queries related to the search query are described. In one aspect, a search query is received, a related query related to the search query is determined, an article (such as a web page) associated with the search query is determined, and a ranking score for the article based at least in part on data associated with the related query is determined. Several algorithms and types of data associated with related queries useful in carrying out such systems and methods are described.

Claims

1. A computer-implemented method comprising:

receiving a first search query;

receiving a second search query;

identifying a relationship between the first search query and the second search query based at least in part on a criterion;

determining a first article associated with the second search query;

determining a first ranking score for the first article based at least in part on data associated with the first search query, wherein the data associated with the first search query comprises a total selection score for the first search query, wherein the total selection score comprises a total number of users that selected a result returned for a search for the first search query; and

outputting a search result comprising the first article.

2. The computer-implemented method of claim 1, wherein the total selection score for the first search query comprises selections made in search results for the first search query in a context of the second search query.

3. The computer-implemented method of claim 1, wherein the data associated with the first search query comprises a second selection score for a second article associated with the first search query.

4. The computer-implemented method of claim 1, wherein the first article comprises a representation of the first article.

5. The computer-implemented method of claim 4, wherein the representation of the first article comprises a uniform resource locator.

6. The computer-implemented method of claim 1, further comprising:

determining a second article associated with the second search query; and

determining a second ranking score for the second article based at least in part on data associated with the first search query.

7. The computer-implemented method of claim 6, further comprising ranking the first article and the second article based at least in part on the first ranking score and the second ranking score.

8. The computer-implemented method of claim 6, further comprising providing a search result for the second search query having the first article and the second article ranked according at least in part to the first ranking score and the second ranking score.

9. The computer-implemented method of claim 6, further comprising receiving a third search query;

and determining a relationship between the third search query and the second search query, and wherein determining the first ranking score for the first article is further based at least in part on data associated with the third search query.

10. The computer-implemented method of claim 1, wherein receiving the first search query further comprises determining a query previously made consecutively with the second query.

11. The computer-implemented method of claim 1, wherein the criterion is at least one of an order of submission, a time period, a misspelling relationship, a synonym relationship, an antonym relationship, or an acronym relationship.

12. A computer-implemented method comprising:

receiving a first search query;

receiving a second search query;

identifying a relationship between the first search query and the second search query based at least in part on a criterion;

determining a first article associated with the second search query;

determining a first ranking score for the first article based at least in part on data associated with the first search query, wherein the data associated with the first search query comprises an instance score for the first search query, wherein the instance score comprises a number of instances the first article was shown in a search result for the first search query; and

outputting a search result comprising the first article.

13. The computer-implemented method of claim 12, wherein the instance score for the first search query comprises selections made in search results for the first search query in a context of the second search query.

14. The computer-implemented method of claim 12, wherein the number of instances the first article was shown in a search result for the first search query comprises instances included in a context of the second search query.

15. A computer-implemented method comprising:

receiving a first search query;

receiving a second search query;

identifying a relationship between the first search query and the second search query based at least in part on a criterion;

determining a first article associated with the second search query, wherein determining the first article associated with the second search query comprises determining the first article associated with the second search query and with the first search query;

determining a first selection score for the first article when associated with the first search query;

determining a first ranking score for the first article based at least in part on data associated with the first search query, wherein determining the first ranking score for the first article based at least in part on data associated with the first search query comprises determining the first ranking score for the first article based at least in part on the first selection score; and

outputting a search result comprising the first article.

16. The computer-implemented method of claim 15, wherein determining the first article associated with the second search query and with the first search query comprises:

determining an initial search result for the second search query, the initial search result comprising the first article; and

determining that a search result for the first search query comprises the first article.

17. The computer-implemented method of claim 15, wherein determining the first ranking score for the first article comprises:

determining a first initial ranking score for the first article when associated with the second search query; and

calculating a mathematical function comprising the first initial ranking score and the first selection score.

18. The computer-implemented method of claim 17, wherein calculating the mathematical function comprising the first initial ranking score and the first selection score comprises combining the first initial ranking score and the first selection score, weighted with at least one weighting factor.

19. The computer-implemented method of claim 18, wherein calculating the mathematical function comprising the first initial ranking score and the first selection score comprises combining the first initial ranking score and the first selection score, normalized with at least one normalization factor.

20. A computer-implemented method comprising:

receiving a first search query;

receiving a second search query;

identifying a relationship between the first search query and the second search query based at least in part on a criterion;

determining a first article associated with the second search query;

determining a first ranking score for the first article based at least in part on data associated with the first search query, wherein determining the first ranking score for the first article based at least in part on data associated with the first search query comprises determining a number of times the first article was selected when included in search results for the first search query, wherein determining the number of times the first article was selected when included in search results for the first search query comprises determining a number of clickthroughs for the first article when presented in search results for the first search query; and

outputting a search result comprising the first article.

21. A computer-implemented method comprising:

in a system configured to receive search queries from client devices and provide search results that are responsive to corresponding received search queries, receiving, during a first time period, a plurality of instances of a first search query and a plurality of instances of a second search query that is different than the first search query;

identifying a relationship between the first search query and the second search query, and storing an indication of the relationship;

during the first time period, tracking and storing user data associated with search results that are provided in response to the second search query;

receiving, subsequent to the first time period, the first search query, and determining a plurality search results that are responsive to the first search query;

employing the stored indication of the relationship to access the stored user data and ranking results within the plurality of search results based at least in part on the accessed user data; and

outputting the ranked plurality of search results.

22. A computer-readable storage medium comprising:

a server process to receive a first search query and a second search query;

a search engine to identify a relationship between the first search query and the second search query based at least in part on a criterion;

a related query processor to determine a first article associated with the second search query;

a ranking processor to determine a first ranking score for the first article based at least in part on data associated with the first search query, wherein determining the first ranking score for the first article based at least in part on data associated with the first search query comprises determining a number of times the first article was selected when included in search results for the first search query, wherein determining the number of times the first article was selected when presented in search results for the first search query comprises determining a number of clickthroughs for the first article when presented in search results for the first search query; and

the server process to output a search result comprising the first article.

23. A computer-readable storage medium comprising:

a server process to receive search queries from client devices and provide search results that are responsive to corresponding received search queries, wherein the server process, during a first time period, receives a plurality of instances of a first search query and a plurality of instances of a second search query that is different than the first search query;

the server process further comprising;

a search engine to identify a relationship between the first search query and the second search query, and storing an indication of the relationship,

a related query processor to track and store, during the first time period, user data associated with search results that are provided in response to the second search query,

a document locator to receive the first search query subsequent to the first time period and determine a plurality search results that are responsive to the first search query, and

a ranking processor to employ the stored indication of the relationship to access the stored user data and ranking results within the plurality of search results based at least in part on the accessed user data; and

wherein the server process outputs the ranked plurality results.