Query rewriting with entity detection

• US 9,773,055 B2
• Filed: 05/29/2015
• Issued: 09/26/2017
• Est. Priority Date: 03/31/2004
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Pfleger, Karl
• Primary Examiner(s): Hasan, Syed
• Application Number:
  US14/725,499
• Publication Number:
  US 20150261848A1
• Time in Patent Office: 851 Days
• Field of Search: None
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/24534 Query rewriting; Transformation
• CPC Class Codes: G06F 16/3325 Reformulation based on results of preceding query
• CPC Class Codes: G06F 16/3326 using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques

Abstract

A system determines whether a received search query includes an entity name, determines whether to rewrite the received search query based on information relating to prior searches involving the entity name, and rewrites the received search query when it is determined that the received search query should be rewritten. The system further determines whether to provide a suggestion of rewriting the received search query, as a rewriting suggestion, based on information relating to prior searches involving the entity name when it is determined that the received search query should not be rewritten. The system also generates the rewriting suggestion when it is determined that the rewriting suggestion should be provided. The system performs a search based on one of the received search query and the rewritten search query to obtain search results, presents the search results, and presents the rewriting suggestion when it is determined that the rewriting suggestion should be provided.

Claims

1. A method, comprising:

receiving a search query;

determining that the received search query includes an entity name;

determining whether to rewrite the received search query based on information relating to prior searches involving the entity name;

in response to determining to rewrite the received search query;

rewriting the received search query;

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

generating a query link to the received search query; and

responsive to the received search query, presenting the search results for the rewritten search query and presenting the query link along with the search results for the rewritten search query,

wherein selection of the presented query link causes another search to be performed using the received search query.

2. The method of claim 1, further comprising:

in response to determining not to rewrite the received search query;

determining whether to provide a suggestion of rewriting the received search query, as a rewriting suggestion, based on information relating to prior searches involving the entity name; and

generating the rewriting suggestion when it is determined that the rewriting suggestion should be provided;

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

presenting the received search query search results and presenting the rewriting suggestion along with the received search query search results.

3. The method of claim 2, wherein the rewriting suggestion includes a link to a rewritten search query.

4. The method of claim 2, wherein the determining whether to provide a suggestion of rewriting the received search query comprises:

identifying entity identifiers associated with documents that were selected in connection with the prior searches involving the entity name,

determining a total number of selections for each of the identified entity identifiers, and

determining that the rewriting suggestion should be provided when an entity identifier associated with the entity name receives a total number of selections greater than other ones of the identified entity identifiers.

5. The method of claim 1, wherein the determining whether to rewrite the received search query comprises:

identifying entity identifiers associated with documents that were selected in connection with the prior searches involving the entity name,

determining a total number of selections for each of the identified entity identifiers, and

determining that the received search query should be rewritten when an entity identifier associated with the entity name receives a total number of selections greater than other ones of the identified entity identifiers.

6. The method of claim 5, wherein the determining whether to rewrite the received search query further comprises:

determining whether the total number of selections for the entity identifier associated with the entity name is greater than a threshold, and

determining that the received search query should not be rewritten when the total number of selections for the entity identifier associated with the entity name is not greater than the threshold.

7. The method of claim 1, wherein the determining whether to rewrite the received search query comprises:

identifying entity identifiers associated with documents that were selected in connection with the prior searches involving the entity name,

determining a distribution of a total number of selections for each of the identified entity identifiers, and

determining that the received search query should be rewritten when the distribution indicates that the total number of selections for an entity identifier associated with the entity name is peaked compared to the total number of selections for a subset of other ones of the identified entity identifiers.

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

modifying the received search query to include a restrict identifier associated with the entity name.

9. The method of claim 1, wherein the performing a search based on the received search query comprises:

searching a repository of documents using the rewritten search query.

10. A system, comprising:

means for receiving a search query;

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

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

means for rewriting the received search query in response to determining to rewrite the received search query;

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

means for generating a query link to the received search query; and

means for, responsive to the received search query, providing the search results for the rewritten search query and providing the query link along with the search results for the rewritten search query

wherein selection of the provided query link causes another search to be performed using the received search query.

11. A system, comprising:

a memory to store information relating to prior searches; and

a processor to;

receive a search query,

determine that the received search query includes an entity name,

determine whether to rewrite the received search query based on the information in the memory that involves the entity name,

in response to determining to rewrite the received search query;

rewrite the received search query,

perform a search based on the rewritten search query to obtain search results for the rewritten search query,

generate a query link to the received search query, and

responsive to the received search query, present the search results for the rewritten search query and present the query link along with the search results for the rewritten search query

wherein selection of the query link causes another search to be performed using the received search query.