Conversation user interface

• US 10,379,712 B2
• Filed: 12/28/2015
• Issued: 08/13/2019
• Est. Priority Date: 04/18/2012
• Status: Active Grant

• Current Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Original Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Inventors: Brown, Fred A, Snavely, Eli D., Miller, Tanya M, Wooters, Charles C, Culley, Bryan Michael
• Primary Examiner(s): To, Jennifer N
• Assistant Examiner(s): Hoang, Amy P
• Application Number:
  US14/980,388
• Publication Number:
  US 20160110071A1
• Time in Patent Office: 1,324 Days
• CPC Class Codes: G06F 3/04812 Interaction techniques based on cursor appearance or behaviour, e.g. being affected by the presence of displayed objects
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06F 3/165 Management of the audio stream, e.g. setting of volume, audio stream path
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: H04L 51/04 Real-time or near real-time messaging, e.g. instant messaging [IM]

Abstract

A conversation user interface enables users to better understand their interactions with computing devices, particularly when speech input is involved. The conversation user interface conveys a visual representation of a conversation between the computing device, or virtual assistant thereon, and a user. The conversation user interface presents a series of dialog representations that show input from a user (verbal or otherwise) and responses from the device or virtual assistant. Associated with one or more of the dialog representations are one or more graphical elements to convey assumptions made to interpret the user input and derive an associated response. The conversation user interface enables the user to see the assumptions upon which the response was based, and to optionally change the assumption(s). Upon change of an assumption, the conversation GUI is refreshed to present a modified dialog representation of a new response derived from the altered set of assumptions.

Claims

1. A computing device, comprising:

one or more processors;

a display communicatively coupled to the one or more processors; and

memory storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising;

causing display of a conversation graphical user interface (GUI) via the display, the conversation GUI including;

an entry portion to receive user input; and

an area to present a user dialog representation associated with the user input and a device dialog representation associated with a response from a virtual assistant for the user input;

mapping the user input to a context to determine an intent associated with the user input;

selecting and utilizing a communication channel between the display and the virtual assistant based on the context;

causing display of, via the conversation GUI, a control for at least one of the user dialog representation or the device dialog representation, wherein the control includes options for displaying and hiding an assumption used to determine the response;

receiving a selection of the control; and

based at least in part on the selection of the control, causing the conversation GUI to either display or hide the assumption used to determine the response, wherein the assumption includes at least some content that is different than content of the response, and wherein causing display of the control comprises causing display of the control in an overlaid manner on at least one of the user dialog representation and the device dialog representation.

2. The computing device of claim 1, wherein the user input comprises audio input and the assumption comprises a parameter used to process the audio input during speech recognition.

3. The computing device of claim 1, wherein the assumption comprises a language model that is employed by natural language processing to interpret the user input.

4. The computing device of claim 1, wherein the assumption comprises logic used by natural language processing to interpret the user input.

5. The computing device of claim 1, wherein the assumption comprises a profile for a user that is associated with the computing device.

6. The computing device of claim 1, wherein the assumption comprises a learned behavior of a user that is associated with the computing device.

7. The computing device of claim 1, wherein the causing display of the control comprises causing display of the control in an overlaid manner on at least one of the user dialog representation or the device dialog representation.

8. The computing device of claim 1, wherein the acts further comprise:

receiving a modification to the assumption;

determining a revised response based at least in part on the modification to the assumption; and

causing display of the revised response in the conversation GUI.

9. A method comprising:

displaying a conversation graphical user interface (GUI) associated with a virtual assistant;

receiving user input via the conversation GUI;

mapping the user input to a context to determine an intent associated with the user input;

selecting and utilizing a communication channel between the display and the virtual assistant based on the context as mapped;

displaying, via the conversation GUI, a first visual representation for the user input;

identifying a response to the user input;

displaying, via the conversation GUI, a second visual representation for the response, the response indicating that an action was performed at least in part by the virtual assistant;

displaying, via the conversation GUI, a control for at least one of the first visual representation or and the second visual representation, wherein the control includes options for displaying and hiding an assumption used to determine the response;

receiving a selection of the control; and

based at least in part on the selection of the control, causing the conversation GUI to either display or hide an assumption used to determine the response, wherein the assumption includes at least some content that is different than content of the response, and wherein displaying the control comprises displaying the control in an overlaid manner on at least one of the user dialog representation and the device dialog representation.

10. The method of claim 9, wherein the acts further comprise:

displaying, via the conversation GUI, an alternative assumption to the assumption;

receiving a selection of the alternative assumption; and

displaying a revised response in the conversation GUI.

11. The method of claim 9, wherein the acts further comprise:

receiving a modification to the assumption; and

based at least in part on receiving the modification to the assumption;

removing the second visual representation from the conversation GUI; and

displaying, via the conversation GUI, a third visual representation for a revised response from the virtual assistant, the revised response being based at least in part on the modification to the assumption.

12. The method of claim 9, wherein the user input comprises audio input and the assumption comprises a parameter used to process the audio input during speech recognition.

13. The method of claim 9, wherein the assumption comprises at least one of a language model or logic that is employed by natural language processing to interpret the user input.

14. One or more non-transitory computer-readable media storing computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform acts comprising:

presenting a conversation graphical user interface (GUI) associated with a virtual assistant to facilitate a conversation between a virtual assistant and a user;

presenting, within the conversation GUI, dialog representations that are each associated with at least one of user input from the user or and a response from the virtual assistant;

mapping parsed portions of the conversation to a context to determine an intent associated with the conversation;

selecting and utilizing a communication channel between the display and the virtual assistant based on the context;

enabling the user to view data that was used to formulate any response from the virtual assistant;

causing display of, via the conversation GUI, a control for at least one of a user dialog representation or a device dialog representation, wherein the control includes options for displaying and hiding an assumption used to determine the response;

receiving a selection of the control; and

based at least in part on the selection of the control, causing the conversation GUI to either display or hide the assumption used to determine the response, wherein the assumption includes at least some content that is different than content of the response, and wherein displaying the control comprises displaying the control in an overlaid manner on at least one of the user dialog representation and the device dialog representation.

15. The one or more non-transitory computer-readable media of claim 14, wherein the enabling comprises providing a control to reveal, upon actuation, how the response from the virtual assistant was determined.

16. The one or more non-transitory computer-readable media of claim 14, wherein the acts further comprise:

learning a characteristic of the user, the characteristic comprising at least one of a speech feature, a preference of the user, a behavior of the user, a pattern associated with the user, or a navigation history associated with the user.

17. The one or more non-transitory computer-readable media of claim 14, wherein the data that was used to formulate the response is based at least in part on the characteristic of the user.

18. The one or more non-transitory computer-readable media of claim 14, wherein the acts further comprise restarting the conversation from a particular one of the dialog representations, the restarting including removing the particular one of the dialog representations and presenting a dialog representation associated with an updated response from the virtual assistant.

19. The one or more non-transitory computer-readable media of claim 14, wherein the data that was used to formulate the response comprises a profile for the user.

20. The one or more non-transitory computer-readable media of claim 14, wherein the data that was used to formulate the response comprises a learned behavior of the user.