Query modification based on textual resource context

• US 9,811,592 B1
• Filed: 06/24/2014
• Issued: 11/07/2017
• Est. Priority Date: 06/24/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Bakir, Gokhan H., Csalogany, Karoly, Behzadi, Behshad
• Primary Examiner(s): Hasan, Syed Haroon
• Application Number:
  US14/313,519
• Time in Patent Office: 1,232 Days
• Field of Search: None
• CPC Class Codes: G06F 16/332 Query formulation

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for modifying a query based on textual resource content. In one aspect, a method includes receiving, from a user device, a query including a plurality of terms; determining an active textual resource displayed in an application environment on the user device; determining to modify the query received from the user device, and in response: determining, based on the textual resource, modification data for the query, generating a set of modified queries based on the query and the modification data, scoring the modified queries according to one or more scoring criteria, selecting one of the modified queries based on the scoring, and providing, to the user device, search results responsive to the selected modified query.

Claims

1. A method implemented in a data processing apparatus, the method comprising:

receiving, from a user device displaying an active textual resource in an active window of an application environment on the user device, a query including a plurality of terms, the query input by a user on the user device displaying the active textual resource when the user input the query;

determining that the query is an ambiguous query and that the user device is displaying, in the text of the active textual resource, entity text that describes entities and that the active textual resource was displayed when the query was input, and in response;

identifying the entities described by entity text in the text of the active textual resource displayed in the active window of the application environment on the user device prior to receiving the query input by the user;

automatically determining, for each entity described by the entity text in the text of the active textual resource displayed on the user device prior to receiving the query input by the user, modification data for each entity described by the entity text for the query;

automatically generating, for each modification data for each entity described by the entity text in the text of the active textual resource, a set of modified queries based on the query and the modification data;

automatically scoring the modified queries according to one or more scoring criteria;

automatically selecting one of the modified queries based on the scoring; and

providing, to the user device, search results responsive to the selected modified query.

2. The method of claim 1, wherein identifying an active textual resource displayed in an application on the user device comprises:

determining an application context to which the query belongs, the application context corresponding to an application instantiated on the user device; and

determining an active textual resource displayed in an application environment of the application.

3. The method of claim 1, wherein determining to modify the query received from the user device comprises determining that the query is a question query.

4. The method of claim 1, wherein determining to modify the query received from the user device comprises:

determining that the query is a question query; and

determining that the question query includes an ambiguous referring term.

5. The method of claim 1, wherein generating a modified query based on the query and the entity text describing the entity comprises concatenating the modified query with the entity text.

6. The method of claim 1, wherein generating a modified query based on the query and the entity text describing the entity comprises revising one or more terms of the query based on the entity text describing the entity.

7. The method of claim 1, wherein generating a modified query based on the query and the entity text describing the entity comprises:

determining a similarity of the text of the query and the entity text to each of a plurality of prior queries stored in a query log; and

selecting, form the query log, prior queries for which the similarity measure meets a threshold similarity value.

8. The method of claim 1, wherein scoring the modified queries according to one or more scoring criteria comprises, for each modified query:

receiving, from a search process, search data describing relevance scores of resources that are determined to be relevant to the modified query; and

generating, from the search data, a score for the modified query.

9. The method of claim 8, wherein generating, from the search data, a score for the modified query comprises:

determining, for each resource, a quality score for the resource, the quality score being an indicator of quality of the resources relative to other resources; and

generating the score for the modified query based, at least in part, on the quality scores.

10. A system, comprising:

one or more data processing apparatus; and

one or more data stores in communication with the one or more data processing apparatus and storing instructions that upon execution cause the one or more data processing apparatus to perform operations comprising;

receiving, from a user device displaying an active textual resource in an active window of an application environment on the user device, a query including a plurality of terms, the query input by a user on the user device displaying the active textual resource when the user input the query;

determining that the query is an ambiguous query and that the user device is displaying, in the text of the active textual resource, entity text that describes entities and that the active textual resource was displayed when the query was input, and in response;

identifying the entities described by entity text in the text of the active textual resource displayed in the active window of the application environment on the user device prior to receiving the query input by the user;

automatically determining, for each entity described by the entity text in the text of the active textual resource displayed on the user device prior to receiving the query input by the user, modification data for each entity described by the entity text for the query;

automatically generating for each modification data for each entity described by the entity text in the text of the active textual resource, a set of modified queries based on the query and the modification data;

automatically scoring the modified queries according to one or more scoring criteria;

automatically selecting one of the modified queries based on the scoring; and

providing, to the user device, search results responsive to the selected modified query.

11. The system of claim 10, wherein identifying an active textual resource displayed in an application on the user device comprises:

determining an application context to which the query belongs, the application context corresponding to an application instantiated on the user device; and

determining an active textual resource displayed in an application environment of the application.

12. The system of claim 10, wherein determining to modify the query received from the user device comprises determining that the query is a question query.

13. The system of claim 10, wherein determining to modify the query received from the user device comprises:

determining that the query is a question query; and

determining that the question query includes an ambiguous referring term.

14. The system of claim 10, wherein generating a modified query based on the query and the entity text describing the entity comprises concatenating the modified query with the entity text.

15. The system of claim 10, wherein generating a modified query based on the query and the entity text describing the entity comprises revising one or more terms of the query based on the entity text describing the entity.

16. The system of claim 10, wherein generating a modified query based on the query and the entity text describing the entity comprises:

determining a similarity of the text of the query and the entity text to each of a plurality of prior queries stored in a query log; and

selecting, form the query log, prior queries for which the similarity measure meets a threshold similarity value.

17. The system of claim 10, wherein scoring the modified queries according to one or more scoring criteria comprises, for each modified query:

receiving, from a search process, search data describing relevance scores of resources that are determined to be relevant to the modified query; and

generating, from the search data, a score for the modified query.

18. A non-transitory computer storage medium encoded with instructions that when executed by one or more data processing apparatus cause the one or more data processing apparatus to perform operations comprising:

receiving, from a user device displaying an active textual resource in an active window of an application environment on the user device, a query including a plurality of terms, the query input by a user on the user device displaying the active textual resource when the user input the query;

determining that the query is an ambiguous query and that the user device is displaying, in the text of the active textual resource, entity text that describes entities and that the active textual resource was displayed when the query was input, and in response;

identifying the entities described by entity text in the text of the active textual resource displayed in the active window of the application environment on the user device prior to receiving the query input by the user;

automatically determining, for each entity described by the entity text in the text of the active textual resource displayed on the user device prior to receiving the query input by the user, modification data for each entity described by the entity text for the query;

automatically generating, for each modification data for each entity described by the entity text in the text of the active textual resource, a set of modified queries based on the query and the modification data;

automatically scoring the modified queries according to one or more scoring criteria;

automatically selecting one of the modified queries based on the scoring; and

providing, to the user device, search results responsive to the selected modified query.