Methods and systems for improving a search ranking using location awareness

• US 20050065916A1
• Filed: 12/31/2003
• Published: 03/24/2005
• Est. Priority Date: 09/22/2003
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Egnor, Daniel, Singhal, Amit, Smith, Adam, Parmar, Abhishek, Hamon, Elizabeth, Ge, Xianping
• Granted Patent: US 7,606,798 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: Y10S 707/99931 Database or file accessing
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99937 Sorting

Abstract

Systems and methods improve search rankings for a search query by using location data associated with queries and documents related to the search query. In one aspect, a search query is received, a location score is determined, a topical score is determined, and an ordering of documents related to the search query is determined based, at least in part, on the location score and the topical score.

Claims

1. A method for ordering documents, comprising:

receiving a search query;

determining a location associated with the query;

determining topical scores for a plurality of documents based, at least in part, on the query;

selecting a set of documents from the plurality of documents;

determining a distance score for each document in the set of documents using a document location associated with the document and the location associated with the query; and

ordering the set of documents as a function of both the topical scores of the set of documents and the distance scores of the set of documents.

2. The method of claim 1, wherein the set of documents includes the plurality of documents.

3. The method of claim 1, wherein the function depends on the topical score and the distance score of each document in the set of documents.

4. The method of claim 1, wherein the topical score is higher for more relevant ones of the documents and a distance score is higher for ones of the documents with a document location nearer to the location associated with the query.

5. The method of claim 4, wherein the function is a monotonic function of the topical scores and a monotonic function of the distance scores.

6. The method of claim 1, wherein determining a distance score for a document includes calculating a distance from the document location to the location associated with the query, and wherein the distance score is a monotonic function of the calculated distance.

7. The method of claim 1, wherein the ordering the set of documents further comprises weighting the topical scores and the distance scores.

8. The method of claim 7, wherein a topic weight is applied to the topical scores and a distance weight is applied to the distance scores.

9. The method of claim 8, wherein the topic weights vary for different ones of the topical scores and the distance weights vary for different ones of the distance scores.

10. The method of claim 9, wherein at least some of the weights vary based, at least in part, on the search query.

11. The method of claim 9, wherein at least some of the weights vary based, at least in part, on one of a topic and a keyword associated with the search query.

12. The method of claim 1, wherein a first document in the set of documents includes a corresponding first topical score and first distance score, a second document in the set of documents includes a corresponding second topical score higher than the first topical score and second distance score lower than the first distance score, a third document in the set of documents includes a corresponding third topical score higher than the first topical score and third distance score lower than the first distance score;

and

wherein the ordering the set of documents includes ordering the second document higher than the first document and the third document lower than the first document.

13. The method of claim 1, wherein a first document in the set of documents includes a corresponding first topical score and first distance score, a second document in the set of documents includes a corresponding second topical score lower than the first topical score and second distance score higher than the first distance score, a third document in the set of documents includes a corresponding third topical score lower than the first topical score and third distance score higher than the first distance score;

and

wherein the ordering the set of documents includes ordering the second document higher than the first document and the third document lower than the first document.

14. The method of claim 1, wherein the ordering the set of documents includes:

generating an overall score for each of the documents in the set of documents based, at least in part, on the topical score and the distance score, and

ordering the set of documents based, at least in part, on the overall scores.

15. The method of claim 1, wherein the distance score is based, at least in part, on a location sensitivity.

16. The method of claim 14, wherein the location sensitivity depends, at least in part, on at least one of a keyword, a topic, the query, the location associated with the query, and a user issuing the query.

17. The method of claim 1, wherein the documents are web pages.

18. The method of claim 1, wherein the documents are advertisements.

19. A system for ordering documents, comprising:

means for determining a location associated with a query;

means for determining topical scores for a plurality of documents based, at least in part, on the query;

means for identifying one or more documents from the plurality of documents;

means for determining a distance score for each of the identified documents using document locations associated with the identified documents and the location associated with the query;

means for generating an overall score for each of the identified documents based, at least in part, on the topical score and the distance score; and

means for arranging the identified documents based, at least in part, on the overall scores.

20. A server, comprising:

a document locator configured to;

receive a search query, and

identify a set of documents based, at least in part, on the search query;

a location component configured to determine a location associated with the search query; and

a ranking component configured to;

determine topical scores for the set of documents based, at least in part, on the search query,

determine distance scores for the set of documents using document locations associated with the set of documents and the location associated with the search query, and

rank the set of documents based, at least in part, on the topical scores for the set of documents and the distance scores for the set of documents.

21. The server of claim 20, wherein the ranking component is further configured to order the set of documents based, at least in part, on the ranking of the set of documents.

22. A method for ranking documents, comprising:

receiving a search query;

identifying a topic relating to the search query;

determining a location sensitivity of the identified topic;

identifying a set of documents based, at least in part, on the search query;

determining a location associated with at least one document in the set of documents; and

ranking the at least one document in the set of documents based, at least in part, on the location associated with the at least one document when the identified topic is determined to be location sensitive.

23. The method of claim 22, wherein the determining a location sensitivity of the identified topic includes determining a degree to which location is relevant for the identified topic.

24. The method of claim 22, wherein the location sensitivity of the identified topic is determined based, at least in part, on user behavior with regard to prior search results.

25. The method of claim 22, further comprising:

determining a geographic range for the identified topic when the identified topic is determined to be location sensitive.

26. The method of claim 25, wherein the ranking at least one document in the set of documents is based, at least in part, on the location associated with the at least one document and the geographic range for the identified topic when the identified topic is determined to be location sensitive.

27. A system, comprising:

at least one server configured to;

receive a search query,

determine a location sensitivity of the search query,

identify a set of documents based, at least in part, on the search query,

determine a location associated with each document in the set of documents, and

score each document in the set of documents based, at least in part, on the location associated with the document when the search query is determined to be location sensitive.

28. A method for presenting advertisements relevant to a target document, comprising:

analyzing the target document to identify a topic for the target document and a location associated with the target document;

identifying targeting information for a plurality of advertisements;

comparing the targeting information to the topic to identify a set of potential advertisements;

determining a distance score for at least one advertisement in the set of potential advertisements using an advertiser location associated with the one advertisement and the location associated with the target document;

ordering the set of potential advertisements based, at least in part, on the distance score of the at least one advertisement; and

presenting at least some of the ordered set of potential advertisements.

29. The method of claim 28, further comprising:

ranking the set of potential advertisements based, at least in part, on the comparing; and

wherein the ordering the set of potential advertisements includes re-ranking at least some of the set of potential advertisements.

30. The method of claim 28, wherein the location associated with the target document is based, at least in part, on a user that accesses the target document.

31. A system for presenting advertisements relevant to a target document, comprising:

means for identifying a topic for the target document;

means for identifying a location associated with the target document;

means for identifying targeting information for a plurality of advertisements;

means for identifying a set of potential advertisements based, at least in part, on the targeting information and the topic for the target document;

means for determining a distance score for at least one advertisement in the set of potential advertisements using an advertiser location associated with the at least one advertisement and the location associated with the target document;

means for ranking the set of potential advertisements based, at least in part, on the distance score of the at least one advertisement; and

means for presenting at least one of the ranked set of potential advertisements in association with the target document.