Multiple choice decision engine for an electronic personal assistant

• US 9,904,892 B2
• Filed: 08/05/2016
• Issued: 02/27/2018
• Est. Priority Date: 01/25/2011
• Status: Active Grant

• Current Assignee: Telepathy Labs, Inc.
• Original Assignee: Telepathy Labs, Inc.
• Inventors: Stolarz, Damien Phelan, Diaz, David Joseph, Rossfeld, James, Raven, Scott, O'Malley, Christopher, Kurpinski, Christopher
• Primary Examiner(s): Pulliam, Christyann
• Assistant Examiner(s): Tran, Mai T
• Application Number:
  US15/229,902
• Publication Number:
  US 20160358092A1
• Time in Patent Office: 571 Days
• CPC Class Codes: G06F 16/242 Query formulation
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 2203/011 Emotion or mood input determined on the basis of sensed human body parameters such as pulse, heart rate or beat, temperature of skin, facial expressions, iris, voice pitch, brain activity patterns
• CPC Class Codes: G06F 3/01 Input arrangements or combined input and output arrangements for interaction between user and computer G06F3/16 takes precedence
• CPC Class Codes: G06F 3/012 Head tracking input arrangements
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/14 Digital output to display device ; Cooperation and interconnection of the display device with other functional units
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

To simplify assisting a user in their day-to-day activities, a communication for performing an action may be sent to a user in the form of a query, where the query includes the most likely set of choices for the action arranged in a group of dichotomous (e.g., yes/no) or multiple choice answers. In this manner, a user may respond to the query by simply selecting one of the dichotomous or multiple choice answers. Historical logs of past actions, responses, queries, and so forth, may be used to predict future user actions or needs, and to formulate future queries for sending to the user. These techniques may be implemented, for example, through a remote coordination server or directly through a user'"'"'s personal electronics device.

Claims

1. A method comprising:

receiving a notification at a remote server from an electronics device;

analyzing, at the remote server, a database having a user data source associated with a user of the electronics device to determine a set of choices in response to the notification, the user data source including information pertaining to the user selected from one of a web-based email, a contact database, data stored on a social networking web-site, an online retail transaction, and combinations thereof, the set of choices including associated actions that the user is predicted to take in relation to the notification;

creating, at the remote server, a query based on the set of choices, the query including dichotomous or multiple choice questions arranged in a hierarchical structure to select among the set of choices, the hierarchical structure having a plurality of levels, where a top level of the hierarchical structure corresponds to at least one of the set of choices, and lower levels of the hierarchical structure correspond to the associated actions that the user is predicted to take in relation to the notification;

sending the query to the electronics device for presentation to the user;

receiving, from the electronics device at the remote server, answers in response to a plurality of the dichotomous or multiple choice questions;

traversing, at the remote server, the hierarchical structure, based on the answers in response to the plurality of the dichotomous or multiple choice questions, to reduce the set of choices to a first choice from the set of choices and to identify a first associated action that the user is predicted to take where the first associated action is associated with the first choice; and

performing the first associated action, thereby to improve operation of the remote server to predict and implement a selection from the set of choices.

2. The method of claim 1 wherein the database includes a historical log of actions selected by the user.

3. The method of claim 1 further comprising adapting a future query based on one or more additional responses to one or more earlier queries.

4. The method of claim 3 wherein the future query is used to determine whether unsolicited information in an earlier query is useful.

5. The method of claim 1 wherein the user data source is analyzed based on a current location of the user.

6. The method of claim 1 wherein the query sent to the electronics device is responded to using a neural input device responsive to physical movements of the user.

7. The method of claim 1 wherein the performed first associated action augments organization of the associated actions by the electronics device.

8. The method of claim 1 wherein sending the query includes sending the user a sequence of queries, each query successively narrowing the selection made by the user for performing the first associated actions.

9. The method of claim 1 wherein one of the dichotomous or multiple choice questions permits the user to postpone performing the first associated action.

10. A computer program product comprising non-transitory computer executable code embodied in a non-transitory computer readable medium configured to:

receive a notification at a remote server from an electronics device;

analyze, at the remote server, a database having a user data source associated with a user of the electronics device to determine a set of choices in response to the notification, the user data source including information pertaining to the user selected from one of a web-based email, a contact database, data stored on a social networking web-site, an online retail transaction, and combinations thereof, the set of choices including associated actions that the user is predicted to take in relation to the notification;

create, at the remote server, a query based on the set of choices, the query including dichotomous or multiple choice questions arranged in a hierarchical structure to select among the set of choices, the hierarchical structure having a plurality of levels, where a top level of the hierarchical structure corresponds to at least one of the set of choices, and lower levels of the hierarchical structure correspond to the associated actions that the user is predicted to take in relation to the notification;

send the query to the electronics device for presentation to the user;

receive, from the electronics device at the remote server, answers in response to a plurality of the dichotomous or multiple choice questions;

traverse, at the remote server, the hierarchical structure, based on the answers in response to the plurality of the dichotomous or multiple choice questions, to reduce the set of choices to a first choice from the set of choices and to identify a first associated action that the user is predicted to take where the first associated action is associated with the first choice; and

perform the first associated action, thereby to improve operation of the remote server to predict and implement a selection from the set of choices.

11. The computer program product of claim 10 wherein the database includes a historical log of actions selected by the user.

12. The computer program product of claim 10 wherein the computer executable code is further configured to adapt a future query based on one or more additional responses to one or more earlier queries.

13. The computer program product of claim 12 wherein the future query is used to determine whether unsolicited information in an earlier query is useful.

14. The computer program product of claim 10 wherein the user data source is analyzed based on a current location of the user.

15. The computer program product of claim 10 wherein the query sent to the electronics device is responded to using a neural input device responsive to physical movements of the user.

16. The computer program product of claim 10 wherein the performed first associated action augments organization of the associated actions using the electronics device.

17. The computer program product of claim 10 wherein sending the query includes sending the user a sequence of queries, each query successively narrowing the selection made by the user for performing the first associated action.

18. The computer program product of claim 10 wherein one of the dichotomous or multiple choice questions permits the user to postpone performing the first associated action.

19. A system comprising:

a processor and a memory connected to a communications interface for establishing communication with an electronics device, the processor executing a task configured to

receive a notification from the electronics device,

analyze a database having a user data source associated with a user of the electronics device to determine a set of choices in response to the notification, the user data source including information pertaining to the user selected from one of a web-based email, a contact database, data stored on a social networking web-site, an online retail transaction, and combinations thereof, the set of choices including associated actions that the user is predicted to take in relation to the notification,

create a query based on the set of choices, the query including dichotomous or multiple choice questions arranged in a hierarchical structure to select among the set of choices, the hierarchical structure having a plurality of levels, where a top level of the hierarchical structure corresponds to at least one of the set of choices, and lower levels of the hierarchical structure correspond to the associated actions that the user is predicted to take in relation to the notification,

send the query to the electronics device for presentation to the user,

receive answers in response to a plurality of the dichotomous or multiple choice questions,

traverse the hierarchical structure, based on the answers in response to the plurality of the dichotomous or multiple choice questions, to reduce the set of choices to a first choice from the set of choices and to identify a first associated action that the user is predicted to take where the first associated action is associated with the first choice, and

perform the first associated action, thereby to improve operation of the processor executing the task to predict and implement a selection from the set of choices.

20. The system of claim 19 wherein the database includes a historical log of actions selected by the user.