Vertical search expansion, disambiguation, and optimization of search queries

• US 7,805,441 B2
• Filed: 03/06/2006
• Issued: 09/28/2010
• Est. Priority Date: 03/06/2006
• Status: Expired due to Fees

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Carinio, Matthew, Madhavan, Anand, Kantak, Darshan
• Primary Examiner(s): Trujillo; James
• Assistant Examiner(s): Moser; Bruce M
• Application Number:
  US11/370,258
• Publication Number:
  US 20070208724A1
• Time in Patent Office: 1,667 Days
• Field of Search: 707/4, 707/5, 707/3, 707/999.003, 707/999.004, 707/999.005, 707/713, 707/728, 707/731
• US Class Current: 707/728
• CPC Class Codes: G06F 16/3332 Query translation

Abstract

A system and method to facilitate expansion, disambiguation, and optimization of search queries over a network wherein an original query received from a user is parsed to obtain at least one query term. A plurality of keywords related contextually to one or more query terms are further retrieved from a database. Finally, a set of modified queries is generated, each modified query further comprising at least one query term and at least one retrieved keyword.

Claims

1. A method comprising:

parsing, in a computer, an original search query received from a user over a network through a query web page to obtain at least one query term;

retrieving a plurality of keywords from a database related contextually to a category of said query web page and said at least one query term;

generating, in a computer, a set of modified queries, each modified query comprising said at least one query term and at least one keyword of said plurality of keywords;

retrieving, in a computer, a plurality of advertising offers for each modified query and for said original query;

removing, in a computer, any advertising offer that is not related contextually to said category of said query web page; and

ranking, in a computer, the advertising offers not removed based on at least one predetermined parameter.

2. The method according to claim 1, wherein each keyword and said at least one query term pertain to a common subject matter related to said page category.

3. The method according to claim 1, further comprising:

selecting advertising offers related contextually to said at least one query term and said plurality of keywords; and

filtering said set of modified queries and said original query to generate a plurality of filtered queries, each filtered query corresponding to at least one selected advertising offer.

4. The method according to claim 1, wherein:

said at least one predetermined parameter further comprises a “

pay-per-click”

(PPC) categorization parameter.

5. The method according to claim 1, wherein:

said at least one predetermined parameter further comprises a combination between a “

pay-per-click”

(PPC) categorization parameter and a “

click-through-rate”

(CTR) categorization parameter.

6. The method according to claim 1, wherein:

said at least one predetermined parameter further comprises a relevance categorization parameter.

7. A system comprising:

a server, comprising a processor and memory, for;

parsing an original search query received from a user over a network through a query web page to obtain at least one query term;

retrieving a plurality of keywords from a database related contextually to a category of said query web page and said at least one query term;

generating a set of modified queries, each modified query further comprising said at least one query term and at least one keyword of said plurality of keywords;

retrieving a plurality of advertising offers for each modified query and for said original query;

removing, in a computer, any advertising offer that is not related contextually to said category of said query web page; and

ranking, in a computer, the advertising offers not removed based on at least one predetermined parameter.

8. The system according to claim 7, wherein each keyword and said at least one query term pertain to a common subject matter related to said page category.

9. The system according to claim 7, said server further for:

selecting advertising offers related contextually to said at least one query term and said plurality of keywords; and

filtering said set of modified queries and said original query to generate a plurality of filtered queries, each filtered query corresponding to at least one selected advertising offer.

10. The system according to claim 7, wherein:

said at least one predetermined parameter further comprises a “

pay-per-click”

(PPC) categorization parameter.

11. The system according to claim 7, wherein:

said at least one predetermined parameter further comprises a combination between a “

pay-per-click”

(PPC) categorization parameter and a “

click-through-rate”

(CTR) categorization parameter.

12. A computer readable medium containing executable instructions, which, when executed in a processing system, cause the processing system to perform a method comprising:

parsing an original search query received from a user over a network through a query web page to obtain at least one query term;

retrieving a plurality of keywords from a database related contextually to a category of said query web page and said at least one query term;

generating a set of modified queries, each modified query further comprising said at least one query term and at least one keyword of said plurality of keywords;

retrieving a plurality of advertising offers for each modified query and for said original query;

removing, in a computer, any advertising offer that is not related contextually to said category of said query web page; and

ranking, in a computer, the advertising offers not removed based on at least one predetermined parameter.

13. The computer readable medium according to claim 12, wherein each keyword and said at least one query term pertain to a common subject matter related to said page category.

14. The computer readable medium according to claim 12, further comprising:

selecting advertising offers related contextually to said at least one query term and said plurality of keywords; and

filtering said set of modified queries and said original query to generate a plurality of filtered queries, each filtered query corresponding to at least one selected advertising offer.

15. The computer readable medium according to claim 12, wherein:

said at least one predetermined parameter further comprises a “

pay-per-click”

(PPC) categorization parameter.

16. The computer readable medium according to claim 12, wherein:

said at least one predetermined parameter further comprises a combination between a “

pay-per-click”

(PPC) categorization parameter and a “

click-through-rate”

(CTR) categorization parameter.

17. The computer readable medium according to claim 12, wherein:

said at least one predetermined parameter further comprises a relevance categorization parameter.