Referent based search suggestions

• US 9,779,179 B2
• Filed: 01/05/2015
• Issued: 10/03/2017
• Est. Priority Date: 10/05/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Nordstrom, Paul, Whitelaw, Casey Stuart
• Primary Examiner(s): Alam, Hosain
• Assistant Examiner(s): ALLEN, NICHOLAS E
• Application Number:
  US14/589,852
• Publication Number:
  US 20150154214A1
• Time in Patent Office: 1,002 Days
• Field of Search: 707767
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06F 16/90328 using search space presentation or visualization, e.g. category or range presentation and selection
• CPC Class Codes: G06F 16/90335 Query processing
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries

Abstract

Computer-implemented methods for providing suggestions for a search based on previously viewed content are provided. In one aspect, a method includes receiving information on previously viewed content, and receiving a request to enter a query into a search field subsequent to receiving the information on the previously viewed content. The method also includes identifying, based on the content, at least one entity referred to in the content, and providing an identifier of the at least one entity for display with the search field. Systems and machine-readable storage media are also provided.

Claims

1. A computer-implemented method comprising:

receiving content information on content electronically viewed by a user;

receiving contextual data indicating a context in which the content was electronically viewed by the user;

identifying, based on both the content information and the contextual data, a plurality of predetermined entities referred to in the content viewed by the user;

assigning a weight value for each entity based on the contextual data or a relevance of the entity to the user, the weight value representing a likelihood that the entity is a referent of the content;

receiving, via a computing device of the user and subsequent to receiving the content information, an indication that a search query was initiated in a search field; and

providing, in response to the indication, an identifier of at least one of the predetermined entities that is associated with a weight value exceeding a threshold weight value for display with the search field in a suggestions list.

2. The computer-implemented method of claim 1, wherein the contextual data includes at least one of:

a user location when the content was electronically viewed by the user, a previous use of the content by the user or another user, a previous search query of the user, and an application in which the content was electronically viewed by the user.

3. The computer-implemented method of claim 2, wherein the contextual data includes the user location and wherein identifying, based on both the content information and the contextual data, the entity referred to in the content comprises:

identifying a physical entity location of the entity; and

identifying the entity based on proximity of the physical entity location to the user location.

4. The computer-implemented method of claim 3, wherein the weight value for each entity is based on proximity of the physical entity location to the user location.

5. The computer-implemented method of claim 1, further comprising:

identifying, for display with the search field, an action associated with the entity; and

providing an identifier of the action for display with the search field.

6. The computer-implemented method of claim 5, further comprising:

identifying a weight assigned to the action for the entity;

wherein identifying the action associated with the entity is based on the weight.

7. The computer-implemented method of claim 6, wherein identifying the action associated with the entity is further based on the contextual data.

8. The computer-implemented method of claim 7, wherein the contextual data includes a user location when the content was electronically viewed by the user and further comprising:

determining a distance between an entity location for the entity and a location of the user when the content was electronically viewed by the user;

wherein identifying the action associated with the entity is based on the distance.

9. The method of claim 1, wherein the search field is displayed on the computing device without simultaneous display of the content;

and

wherein providing the identifier of the entity for display with the search field comprises providing the identifier of the entity for display with the search field without simultaneous display of the content.

10. The method of claim 9, wherein the search field is displayed with a first webpage and wherein the content is a previously visited webpage that is not displayed or loaded at the computing device concurrent with the first webpage.

11. The method of claim 9, wherein the search field is displayed with a first application and wherein the content was electronically viewed by the user in a second application.

12. A system comprising:

a memory comprising content information of content electronically viewed by a user and contextual data indicating a context in which the content was electronically viewed by the user, wherein the content information comprises an address of the content, pointer to the content, or a copy of the content; and

a processor configured to;

identify, based on both the content information and the contextual data, a plurality of predetermined entities referred to in the content viewed by the user;

assigning a weight value for each entity based on the contextual data or a relevance of the entity to the user, the weight value representing a likelihood that the entity is a referent of the content;

receive an indication that a search query was initiated in a search field; and

provide, in response to the indication, an identifier of at least one of the predetermined entities that is associated with a weight value exceeding a threshold weight value for display with the search field in a suggestions list.

13. The system of claim 12, wherein the contextual data includes at least one of:

a user location when the content was electronically viewed by the user, a previous use of the content by the user or another user, a previous search query of the user, and an application in which the content was electronically viewed by the user.

14. The system of claim 12, wherein the contextual data includes a user location of the user and wherein the processor being configured to identify, based on both the content information and the contextual data, the entity referred to in the content comprises the processor being configured to:

identify a physical entity location of the entity; and

identify the entity based on proximity of the physical entity location to the user location.

15. The system of claim 14, wherein the weight value for each entity is based on proximity of the physical entity location to the user location.

16. The system of claim 12, wherein the processor is further configured to:

identify, for display with the search field, an action associated with the entity; and

provide an identifier of the action for display with the search field.

17. The system of claim 16, wherein the processor is further configured to:

identify a weight assigned to the action for the entity;

wherein identifying the action associated with the entity is based on the weight.

18. The system of claim 17, wherein identifying the action associated with the entity is further based on the contextual data.

19. The system of claim 18, wherein the contextual data includes a user location when the content was electronically viewed by the user and the processor is further configured to:

determine a distance between an entity location for the entity and a location of the user when the content was electronically viewed by the user;

wherein identifying the action associated with the entity is based on the distance.

20. A non-transitory machine-readable storage medium comprising machine-readable instructions for causing a processor to execute a method for providing suggestions for a search based on viewed content, the method comprising:

receiving content information on content electronically viewed by a user;

receiving contextual data indicating a context in which the content was electronically viewed by the user;

identifying, based on both the content information and the contextual data, a plurality of predetermined entities referred to in the content viewed by the user;

assigning a weight value for each entity based on the contextual data or a relevance of the entity to the user, the weight value representing a likelihood that the entity is a referent of the content;

receiving, via a computing device of the user and subsequent to receiving the content information, an indication that a search query was initiated in a search field; and

providing, in response to the indication, an identifier of at least one of the predetermined entities that is associated with a weight value exceeding a threshold weight value for display with the search field in a suggestions list.