System and method for determining alternate search queries

• US 20070038621A1
• Filed: 08/10/2005
• Published: 02/15/2007
• Est. Priority Date: 08/10/2005
• Status: Active Grant

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Jones, Rosie, Rey, Benjamin, Weyand, Tina
• Granted Patent: US 7,634,462 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3338 Query expansion
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing
• 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 707/99937 Sorting

Abstract

A system and method for receiving a query and determining candidate alternate queries. A query may be parsed into concepts and then candidates for alternate terms may be determined for either the whole query or the determined concepts. Candidates are scored for their respective similarity to the original query. After scoring, at least one candidate is chosen and may be used as a possible alternate query choice for a user or used to serve bidded advertisements to the user.

Claims

1. A method for processing a search query, the search query comprising one or more first search terms for searching for documents, the method comprising:

identifying one or more alternative search terms to the one or more first search terms;

scoring each of the alternative search terms to produce a score for each alternative search term; and

ranking the alternative search terms based on the scores.

2. The method of claim 1, comprising searching for documents based on the alternative search terms.

3. The method of claim 2, wherein searching for documents comprises searching an index.

4. The method of claim 2, comprising searching for documents based on the alternative search terms and the first search terms.

5. The method of claim 1, wherein identifying one or more alternative search terms comprises identifying candidates for alternative search terms and selecting one or more candidates as alternative search terms.

6. The method of claim 5, comprising computing a probability score for each candidate alternative search term to define a probability that the candidate alternative search term will find documents intended to be found by the received search terms.

7. The method of claim 6, wherein identifying one or more alternative search terms comprises comparing the probability score for each candidate against a probability score threshold to select candidates as alternative search terms.

8. The method of claim 6, wherein ranking comprises ranking based on the computed probability score for each alternative search term.

9. The method of claim 5, wherein identifying one or more alternative search terms comprises using a log likelihood ratio test to select candidates as alternative search terms.

10. The method of claim 5, wherein identifying one or more alternative search terms comprises using a point-wise mutual information test to select candidates as alternative search terms.

11. The method of claim 1, wherein the one or more first search terms comprise a segment of a whole query, and wherein the one or more alternative search terms are alternatives for the received segment.

12. The method of claim 1, comprising storing a database of alternative search terms and wherein identifying one or more alternative search terms comprises searching the database.

13. A method for building a database of alternative search terms, the method comprising:

receiving one or more first search terms for searching documents;

receiving one or more second search terms for searching documents;

associating the first and second received search terms to define a relationship that the one or more second search terms can be substituted as one or more alternative search terms for the first one or more search terms in a query; and

storing the one or more first search terms and the one or more second search terms in a database according to their association.

14. The method of claim 13, wherein associating comprises associating the first and second one or more first and second search terms if they are received from one user.

15. The method of claim 13, wherein associating comprises associating the first and second one or more first and second search terms if they are both received within a defined period of time.

16. A method for building a database of alternative search terms, the method comprising:

selecting a sample set of documents from a database of searchable documents;

selecting one or more first document terms and one or more second document terms that appear together in documents of the sample set a statistically significant number of times;

associating the one or more first document terms with the one or more second document terms such that the one or more second document terms represent alternative search terms to the one or more first document terms when the one or more first document terms appear in a search query; and

storing the one or more first document terms and the one or more second document terms in a database according to their association.

17. The method of claim 16, wherein the step of selecting is performed further based on a spatial arrangement of the first and second one or more document terms that appear together in the document.

18. The method of claim 17, wherein the spatial arrangement comprises a same paragraph within a document.

19. The method of claim 17, wherein the spatial arrangement comprises a single sentence within a document.