Systems and methods for guided user actions

• US 9,519,408 B2
• Filed: 12/31/2013
• Issued: 12/13/2016
• Est. Priority Date: 12/31/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Shoemaker, Garth, Aiello, Michael Eugene
• Primary Examiner(s): Hailu, Tadeese
• Application Number:
  US14/145,596
• Publication Number:
  US 20150185995A1
• Time in Patent Office: 1,078 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 3/0484 for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
• CPC Class Codes: G06F 3/04886 by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04M 1/72448 with means for adapting the functionality of the device according to specific conditions

Abstract

Systems and methods for guided user actions are described, including detecting a first action performed by a user; gathering information associated with the first action; retrieving a predictive model based on the information; determining an applicability level of the predictive model to the first action, the predictive model suggests a second action; providing the second action in a user interface when the applicability level meets a threshold level; and receiving input from the user selecting the second action or a third action.

Claims

1. A computer-implemented method, comprising:

detecting a first action performed by a user;

gathering information associated with the first action;

applying machine learning to generate a predictive model and a privacy preference of the user, based on the information and a past sharing action associated with the information, wherein the machine learning is applied as a black box that receives the information and outputs the predictive model, and wherein a plurality of pipelines are provided for a plurality of respective domains, each of the pipelines applying the machine learning;

determining an applicability level of the predictive model to the first action, wherein the predictive model suggests a second action;

providing the second action in a user interface for the applicability level exceeding a first threshold level associated with a degree of sharing of content associated with the first action;

receiving input from the user selecting the second action or a third action for the applicability level exceeding the first threshold level and not exceeding a second threshold level that exceeds the first threshold level; and

for the applicability level exceeding the second threshold level, automatically selecting the second action or the third action based on the provided second action without receiving the input from the user.

2. The method of claim 1, wherein the first action comprises browsing one or more online sites in an open mode, and the second action comprises predicting a user preference to browse in a private mode based on an identity of the one or more online sites, and providing the user with an option to switch from the open mode to a private mode, wherein the machine learning is applied to fine-tune the system based on the input of the user associated with the provided option.

3. The method of claim 1, wherein the first action comprises identifying content and the second action comprises selecting an application to process the content.

4. The method of claim 1, wherein the first action comprises accessing a website and the second action comprises selecting a mode of a browser to access the website.

5. The method of claim 1, wherein the plurality of pipelines comprise a first pipeline associated with browsing activity, a second pipeline associated with sharing activity on an online social circle of a social network, and a third pipeline associated with email communication.

6. The method of claim 1, wherein the determining the applicability level of the predictive model to the first action comprises:

performing a weighted calculation of attributes associated with the predictive model; and

determining a combination of at least some of the weighted calculation of the attributes meet the first threshold level.

7. The method of claim 1, wherein input from the user selecting the second action or a third action modifies the predictive model.

8. A non-transitory computer readable medium having stored therein computer executable instructions for:

detecting a first action performed by a user;

gathering information associated with the first action;

applying machine learning to generate a predictive model and a privacy preference of the user, based on the information and a past sharing action associated with the information, wherein the machine learning is applied as a black box that receives the information and outputs the predictive model, and wherein a plurality of pipelines are provided for a plurality of respective domains, each of the pipelines applying the machine learning;

determining an applicability level of the predictive model to the first action, wherein the predictive model suggests a second action;

providing the second action in a user interface for the applicability level exceeding a first threshold level associated with a degree of sharing of content associated with the first action;

receiving input from the user selecting the second action or a third action for the applicability level exceeding the first threshold level and not exceeding a second threshold level that exceeds the first threshold level; and

for the applicability level exceeding the second threshold level, automatically selecting the second action or the third action based on the provided second action without receiving the input from the user.

9. The medium of claim 8, wherein the first action comprises browsing one or more online sites in an open mode, and the second action comprises predicting a user preference to browse in a private mode based on an identity of the one or more online sites, and providing the user with an option to switch from the open mode to a private mode, wherein the machine learning is applied to fine-tune the system based on the input of the user associated with the provided option.

10. The medium of claim 8, wherein the first action comprises identifying content and the second action comprises selecting an application to process the content.

11. The medium of claim 8, wherein the first action comprises accessing a website and the second action comprises selecting a mode of a browser to access the website.

12. The medium of claim 8, wherein the plurality of pipelines comprise a first pipeline associated with browsing activity, a second pipeline associated with sharing activity on an online social circle of a social network, and a third pipeline associated with email communication.

13. The medium of claim 8, wherein the determining the applicability level of the predictive model to the first action comprises:

performing a weighted calculation of attributes associated with the predictive model; and

determining a combination of at least some of the weighted calculation of the attributes meet the first threshold level.

14. At least one computing device comprising storage and a processor configured to perform:

detecting a first action performed by a user;

gathering information associated with the first action;

applying machine learning to generate a predictive model and a privacy preference of the user, based on the information and a past sharing action associated with the information, wherein the machine learning is applied as a black box that receives the information and outputs the predictive model, and wherein a plurality of pipelines are provided for a plurality of respective domains, each of the pipelines applying the machine learning;

determining an applicability level of the predictive model to the first action, wherein the predictive model suggests a second action;

providing the second action in a user interface for the applicability level exceeding a first threshold level associated with a degree of sharing of content associated with the first action;

receiving input from the user selecting the second action or a third action for the applicability level exceeding the first threshold level and not exceeding a second threshold level that exceeds the first threshold level; and

for the applicability level exceeding the second threshold level, automatically selecting the second action or the third action based on the provided second action without receiving the input from the user.

15. The at least one computing device of claim 14, wherein the first action comprises browsing one or more online sites in an open mode, and the second action comprises predicting a user preference to browse in a private mode based on an identity of the one or more online sites, and providing the user with an option to switch from the open mode to a private mode, wherein the machine learning is applied to fine-tune the system based on the input of the user associated with the provided option.

16. The at least one computing device of claim 14, wherein the first action comprises identifying content and the second action comprises selecting an application to process the content.

17. The at least one computing device of claim 14, wherein the first action comprises accessing a website and the second action comprises selecting a mode of a browser to access the website.

18. The at least one computing device of claim 14, wherein the plurality of pipelines comprise a first pipeline associated with browsing activity, a second pipeline associated with sharing activity on an online social circle of a social network, and a third pipeline associated with email communication.

19. The at least one computing device of claim 14, wherein the determining the applicability level of the predictive model to the first action comprises:

performing a weighted calculation of attributes associated with the predictive model; and

determining a combination of at least some of the weighted calculation of the attributes meet the first threshold level.

20. The at least one computing device of claim 14, wherein input from the user selecting the second action or a third action modifies the predictive model.