Using geographic data to identify correlated geographic synonyms

• US 8,527,538 B1
• Filed: 12/08/2011
• Issued: 09/03/2013
• Est. Priority Date: 10/24/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Upstill, Trystan G., Baker, Steven D.
• Primary Examiner(s): Coby, Frantz
• Application Number:
  US13/315,229
• Time in Patent Office: 635 Days
• Field of Search: 707/769, 707/706, 707/707, 707/708, 707/758, 707/759, 707/919
• US Class Current: 707/769
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/332 Query formulation
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: Y10S 707/919 Geographic

Abstract

One embodiment of the present invention provides a system that uses geographic data to identify correlated geographic synonyms in search queries. A correlated geographic synonym occurs when two terms that are possible synonyms should not be considered synonyms because they are associated with related geographic context. During operation, the system receives a term and a possible synonym for the term. The system then determines whether the term and the possible synonym are both present in a geographic data set. If so, the system uses the geographic data set to determine whether the possible synonym is a correlated geographic synonym for the term.

Claims

1. A computer-implemented method comprising:

receiving a query that includes a first geographic entity name;

determining that a second geographic entity name that was identified as a substitute term for the first geographic entity name by a first substitution framework, was also identified as not a substitute term for the first geographic entity name by a second substitution framework;

revising the query using the second geographic entity name to generate a revised query;

obtaining search results that satisfy the revised query; and

demoting a score of an obtained search result that corresponds to a document that includes the second geographic entity name based at least in part on determining that the second geographic entity name that was identified as a substitute term for the first geographic entity name by a first substitution framework was also identified as not a substitute term for the first geographic entity name by the second substitution framework.

2. The method of claim 1, wherein the demotion in score for a city-to-city relationship is less than a country-to-country relationship.

3. The method of claim 1, wherein demoting a score of an obtained search result that corresponds to a document that includes the second geographic entity name comprises:

determining that the document includes the second geographic entity name; and

omitting occurrences of the second geographic entity name in the document when computing the score for the corresponding search result.

4. The method of claim 1, comprising:

determining a relationship between the first geographic entity name and the second geographic entity name in a geographic data set that includes a plurality of names of geographic entities and respective relationships between pairs of geographic entities,

wherein determining that the second geographic entity name is identified as not a substitute term for the first geographic entity name by the second substitution framework is based at least in part on the determined relationship.

5. The method of claim 4, wherein the geographic data set is a tree structure wherein different positions in the tree structure that share a same level correspond to different geographic locations that share a same geographic region type.

6. The method of claim 5, wherein determining a relationship between the first geographic entity name and the second geographic entity name comprises determining that a first position for the first geographic entity name in the tree structure and a second position for the second geographic entity name in the tree structure share a parent in the tree structure.

7. The method of claim 5, wherein determining a relationship between the first geographic entity name and the second geographic entity name comprises determining that a first position for the first geographic entity name in the tree structure and a second position for the second geographic entity name in the tree structure are at a same level in the tree structure.

8. The method of claim 5, wherein determining a relationship between the first geographic entity name and the second geographic entity name comprises determining that a first position for the first geographic entity name in the tree structure is an ancestor of a second position for the second geographic entity name in the tree structure.

9. The method of claim 5, wherein determining a relationship between the first geographic entity name and the second geographic entity name comprises determining that a second position for the second geographic entity name in the tree structure is an ancestor of a first position for the first geographic entity name in the tree structure.

10. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

receiving a query that includes a first geographic entity name;

determining that a second geographic entity name that was identified as a substitute term for the first geographic entity name by a first substitution framework, was also identified as not a substitute term for the first geographic entity name by a second substitution framework;

revising the query using the second geographic entity name to generate a revised query;

obtaining search results that satisfy the revised query; and

demoting a score of an obtained search result that corresponds to a document that includes the second geographic entity name based at least in part on determining that the second geographic entity name that was identified as a substitute term for the first geographic entity name by a first substitution framework was also identified as not a substitute term for the first geographic entity name by the second substitution framework.

11. The system of claim 10, wherein the demotion in score for a city-to-city relationship is less than a country-to-country relationship.

12. The system of claim 10, wherein demoting a score of an obtained search result that corresponds to a document that includes the second geographic entity name comprises:

determining that the document includes the second geographic entity name; and

omitting occurrences of the second geographic entity name in the document when computing the score for the corresponding search result.

13. The system of claim 10, wherein the operations comprise:

determining a relationship between the first geographic entity name and the second geographic entity name in a geographic data set that includes a plurality of names of geographic entities and respective relationships between pairs of geographic entities,

wherein determining that the second geographic entity name is identified as not a substitute term for the first geographic entity name by the second substitution framework is based at least in part on the determined relationship.

14. The system of claim 13, wherein the geographic data set is a tree structure wherein different positions in the tree structure that share a same level correspond to different geographic locations that share a same geographic region type.

15. The system of claim 14, wherein determining a relationship between the first geographic entity name and the second geographic entity name comprises determining that a first position for the first geographic entity name in the tree structure and a second position for the second geographic entity name in the tree structure share a parent in the tree structure.

16. The system of claim 14, wherein determining a relationship between the first geographic entity name and the second geographic entity name comprises determining that a first position for the first geographic entity name in the tree structure and a second position for the second geographic entity name in the tree structure are at a same level in the tree structure.

17. The system of claim 14, wherein determining a relationship between the first geographic entity name and the second geographic entity name comprises determining that a first position for the first geographic entity name in the tree structure is an ancestor of a second position for the second geographic entity name in the tree structure.

18. The system of claim 14, wherein determining a relationship between the first geographic entity name and the second geographic entity name comprises determining that a second position for the second geographic entity name in the tree structure is an ancestor of a first position for the first geographic entity name in the tree structure.

19. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

receiving a query that includes a first geographic entity name;

determining that a second geographic entity name that was identified as a substitute term for the first geographic entity name by a first substitution framework, was also identified as not a substitute term for the first geographic entity name by a second substitution framework;

revising the query using the second geographic entity name to generate a revised query;

obtaining search results that satisfy the revised query; and

demoting a score of an obtained search result that corresponds to a document that includes the second geographic entity name based at least in part on determining that the second geographic entity name that was identified as a substitute term for the first geographic entity name by a first substitution framework was also identified as not a substitute term for the first geographic entity name by the second substitution framework.

20. The computer-readable medium of claim 19, wherein the demotion in score for a city-to-city relationship is less than a country-to-country relationship.

21. The computer-readable medium of claim 19, wherein demoting a score of an obtained search result that corresponds to a document that includes the second geographic entity name comprises:

determining that the document includes the second geographic entity name; and

omitting occurrences of the second geographic entity name in the document when computing the score for the corresponding search result.

22. The computer-readable medium of claim 19, wherein the operations comprise:

determining a relationship between the first geographic entity name and the second geographic entity name in a geographic data set that includes a plurality of names of geographic entities and respective relationships between pairs of geographic entities,

wherein determining that the second geographic entity name is identified as not a substitute term for the first geographic entity name by the second substitution framework is based at least in part on the determined relationship.

23. The computer-readable medium of claim 22, wherein the geographic data set is a tree structure wherein different positions in the tree structure that share a same level correspond to different geographic locations that share a same geographic region type.

24. The computer-readable medium of claim 23, wherein determining a relationship between the first geographic entity name and the second geographic entity name comprises determining that a first position for the first geographic entity name in the tree structure and a second position for the second geographic entity name in the tree structure share a parent in the tree structure.

25. The computer-readable medium of claim 23, wherein determining a relationship between the first geographic entity name and the second geographic entity name comprises determining that a first position for the first geographic entity name in the tree structure and a second position for the second geographic entity name in the tree structure are at a same level in the tree structure.

26. The computer-readable medium of claim 23, wherein determining a relationship between the first geographic entity name and the second geographic entity name comprises determining that a first position for the first geographic entity name in the tree structure is an ancestor of a second position for the second geographic entity name in the tree structure.

27. The computer-readable medium of claim 23, wherein determining a relationship between the first geographic entity name and the second geographic entity name comprises determining that a second position for the second geographic entity name in the tree structure is an ancestor of a first position for the first geographic entity name in the tree structure.