AUTOCOMPLETE USING SOCIAL ACTIVITY SIGNALS

• US 20140280000A1
• Filed: 12/20/2013
• Published: 09/18/2014
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Subramanian Karthik, Venkateswaran
• Granted Patent: US 9,852,233 B2
• Time in Patent Office: Days
• US Class Current: 707/706
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06F 16/904 Browsing; Visualisation therefor for navigating the web G06F16/954; browsing optimisation for the web G06F16/957

Abstract

A system and method of providing autocomplete features using social activity signals. In some embodiments, social activity signals associated with a user are received. User-entered text is received from the user in a search field for a search engine. Predicted queries are determined based on the user-entered text and the social activity signals. Each one of the predicted queries comprises predicted text and at least a portion of the user-entered text. The predicted text is absent from the user-entered text. The predicted queries are caused to be displayed in an autocomplete user interface element of the search field. In some embodiments, the social activity signals comprise at least one of a like of content, a share of content, a follow of content, and a comment on content.

Claims

1. A computer-implemented method comprising:

receiving social activity signals associated with a user;

receiving, from the user, user-entered text in a search field for a search engine;

determining, by a machine having a memory and at least one processor, predicted queries based on the user-entered text and the social activity signals, each one of the predicted queries comprising predicted text and at least a portion of the user-entered text, the predicted text being absent from the user-entered text; and

causing the predicted queries to be displayed in an autocomplete user interface element of the search field.

2. The computer-implemented method of claim 1, wherein determining the predicted queries comprises:

determining potential predicted queries based on the user-entered text;

assigning a corresponding predicted query value to each one of the potential predicted queries based on a determination for each potential predicted query of whether the potential predicted query corresponds to one of the social activity signals; and

selecting the predicted queries from the potential predicted queries based on the predicted query values of the potential predicted queries.

3. The computer-implemented method of claim 2, further comprising determining a display position for each of predicted queries within the user interface element of the search field based on the predicted query values of the corresponding predicted queries.

4. The computer-implemented method of claim 2, further comprising storing a mapping of social activity types to weights, each social activity type having a corresponding weight, wherein assigning the corresponding predicted query value to each one of the potential predicted queries comprises:

for each potential predicted query determined to correspond to one of the social activity signals, determining the corresponding social activity type of the one of the social activity signals; and

for each potential predicted query determined to correspond to one of the social activity signals, calculating the corresponding predicted query value based on the corresponding weight of the corresponding social activity type.

5. The computer-implemented method of claim 4, wherein the social activity types comprise at least one of a like of content, a share of content, a follow of content, a comment on content, a status update, and a calendar event.

6. The computer-implemented method of claim 1, wherein the social activity signals comprise at least one of a like of content, a share of content, a follow of content, a comment on content, a status update, and a calendar event.

7. The computer-implemented method of claim 1, wherein the social activity signals are received from at least one social networking service.

8. The computer-implemented method of claim 1, wherein the search engine is part of an e-commerce website.

9. The computer-implemented method of claim 1, wherein the autocomplete user interface element comprises an autocomplete box extending from the search field.

10. A system comprising:

a machine having a memory and at least one processor; and

an autocomplete module, executable by the at least one processor, configured to;

receive social activity signals associated with a user;

receiving, from the user, user-entered text in a search field for a search engine;

determine predicted queries based on the user-entered text and the social activity signals, each one of the predicted queries comprising predicted text and at least a portion of the user-entered text, the predicted text being absent from the user-entered text; and

cause the predicted queries to be displayed in an autocomplete user interface element of the search field.

11. The system of claim 10, wherein determining the predicted queries comprises:

determining potential predicted queries based on the user-entered text;

assigning a corresponding predicted query value to each one of the potential predicted queries based on a determination for each potential predicted query of whether the potential predicted query corresponds to one of the social activity signals; and

selecting the predicted queries from the potential predicted queries based on the predicted query values of the potential predicted queries.

12. The system of claim 11, wherein the autocomplete module is further configured to determine a display position for each of predicted queries within the user interface element of the search field based on the predicted query values of the corresponding predicted queries.

13. The system of claim 11, wherein the autocomplete module is further configured to store a mapping of social activity types to weights, each social activity type having a corresponding weight, wherein assigning the corresponding predicted query value to each one of the potential predicted queries comprises:

for each potential predicted query determined to correspond to one of the social activity signals, determining the corresponding social activity type of the one of the social activity signals; and

for each potential predicted query determined to correspond to one of the social activity signals, calculating the corresponding predicted query value based on the corresponding weight of the corresponding social activity type.

14. The system of claim 13, wherein the social activity types comprise at least one of a like of content, a share of content, a follow of content, a comment on content, a status update, and a calendar event.

15. The system of claim 10, wherein the social activity signals comprise at least one of a like of content, a share of content, a follow of content, a comment on content, a status update, and a calendar event.

16. The system of claim 10, wherein the autocomplete module is configured to receive the social activity signals from at least one social networking service.

17. The system of claim 10, wherein the search engine is part of an e-commerce website.

18. The system of claim 10, wherein the autocomplete user interface element comprises an autocomplete box extending from the search field

19. A non-transitory machine-readable storage medium storing a set of instructions that, when executed by at least one processor, causes the at least one processor to perform a set of operations comprising:

receiving social activity signals associated with a user;

receiving, from the user, user-entered text in a search field for a search engine;

determining predicted queries based on the user-entered text and the social activity signals, each one of the predicted queries comprising predicted text and at least a portion of the user-entered text, the predicted text being absent from the user-entered text; and

causing the predicted queries to be displayed in an autocomplete user interface element of the search field.

20. The storage medium of claim 19, wherein determining the predicted queries comprises:

determining potential predicted queries based on the user-entered text;

assigning a corresponding predicted query value to each one of the potential predicted queries based on a determination for each potential predicted query of whether the potential predicted query corresponds to one of the social activity signals; and

selecting the predicted queries from the potential predicted queries based on the predicted query values of the potential predicted queries.