Query rewriting with entity detection

• US 20050222977A1
• Filed: 03/31/2004
• Published: 10/06/2005
• Est. Priority Date: 03/31/2004
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Schmitt, Michael, Zhou, Hong, Bharat, Krishna, Curtiss, Michael, Mayer, Marissa
• Granted Patent: US 7,536,382 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/90335 Query processing
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A system receives a search query, determines whether the received search query includes an entity name, and determines whether the entity name is associated with a common word or phrase. When the entity name is associated with a common word or phrase, the system generates a link to a rewritten query, performs a search based on the received search query to obtain first search results, and provides the first search results and the link to the rewritten query. When the entity name is not associated with a common word or phrase, the system rewrites the received search query to include a restrict identifier associated with the entity name, generates a link to the received search query, performs a search based on the rewritten search query to obtain second search results, and provides the second search results and the link to the received search query.

Claims

1. A method, comprising:

receiving a search query;

determining whether the received search query includes an entity name;

determining whether the entity name is associated with a common word or phrase;

selectively rewriting the received search query based on whether the entity name is determined to be associated with a common word or phrase;

performing a search based on the received search query or the rewritten search query to obtain search results; and

presenting the search results.

2. The method of claim 1, further comprising:

providing a link to the received search query when the search is performed based on the rewritten search query.

3. The method of claim 2, further comprising:

receiving selection of the link to the received search query; and

performing a search based on the received search query.

4. The method of claim 1, further comprising:

providing a link to the rewritten search query when the search is performed based on the received search query.

5. The method of claim 4, further comprising:

receiving selection of the link to the rewritten search query; and

performing a search based on the rewritten search query.

6. The method of claim 1, further comprising:

determining whether a word near the entity name in the received search query forms a common phrase with the entity name; and

performing a search based on the received search query when it is determined that a word near the entity name forms a common phrase with the entity name.

7. The method of claim 1, wherein determining whether the entity name is associated with a common word or phrase comprises:

comparing the entity name to a dictionary of words or phrases.

8. The method of claim 1, wherein determining whether the entity name is associated with a common word or phrase comprises:

using an inverse document frequency weighting technique or a linguistic modeling technique to identify whether the entity name is associated with a common word or phrase.

9. The method of claim 1, wherein determining whether the entity name is associated with a common word or phrase comprises:

generating a table of entity names that are associated with common words or phrases, and

determining whether the entity name is associated with a common word or phrase based on the table.

10. The method of claim 1, wherein selectively rewriting the received search query comprises:

modifying the received search query to include a restrict identifier associated with the entity name when the entity name is determined not to be associated with a common word or phrase.

11. The method of claim 1, wherein determining whether the received search query includes an entity name comprises:

identifying a plurality of variations of a plurality entity names, and

determining whether the received search query includes one of the variations of the entity names.

12. The method of claim 1, wherein performing a search comprises:

searching based on the received search query when the entity name is determined to be associated with a common word or phrase.

13. The method of claim 1, wherein performing a search comprises:

searching based on the rewritten search query when the entity name is determined not to be associated with a common word or phrase.

14. A system, comprising:

means for receiving a search query;

means for determining whether the received search query includes an entity name;

means for determining whether the entity name is associated with a common word or phrase;

means for rewriting the received search query when it is determined that the entity name is associated with a common word or phrase;

means for performing a search based on the rewritten search query to obtain search results; and

means for providing the search results.

15. The system of claim 14, further comprising:

means for providing a link to the received search query.

16. The system of claim 15, further comprising:

means for receiving selection of the link to the received search query; and

means for performing a search based on the received search query.

17. A system, comprising:

a memory; and

a processor connected to the memory to;

receive a search query,

determine whether the received search query includes an entity name, and

selectively rewrite the received search query to obtain a rewritten search query when it is determined that the received search query includes an entity name.

18. A method, comprising:

determining a plurality of entity names;

determining whether each of the entity names is associated with a common word or phrase; and

generating a table of the entity names that are associated with common words or phrases.

19. The method of claim 18, wherein determining whether each of the entity names is associated with a common word or phrase comprises:

comparing each of the entity names to a dictionary of words or phrases.

20. The method of claim 18, wherein determining whether each of the entity names is associated with a common word or phrase comprises:

using an inverse document frequency weighting technique or a linguistic modeling technique to identify whether each of the entity names is associated with a common word or phrase.

21. A system, comprising:

a processor to;

identify a plurality of entity names,

determine whether each of the entity names is associated with a common word or phrase, and

generate a table that comprises ones of the entity names that are associated with common words or phrases; and

a memory to store the table.

22. A method, comprising:

receiving a search query;

determining whether the received search query includes an entity name;

determining whether the entity name is associated with a common word or phrase;

when the entity name is associated with a common word or phrase,

generating a link to a rewritten query,

performing a search based on the received search query to obtain first search results, and

providing the first search results and the link to the rewritten query; and

when the entity name is not associated with a common word or phrase,

rewriting the received search query to include a restrict identifier associated with the entity name,

generating a link to the received search query,

performing a search based on the rewritten search query to obtain second search results, and

providing the second search results and the link to the received search query.