VIRTUAL ASSISTANT TEAM IDENTIFICATION

• US 20150185996A1
• Filed: 06/02/2014
• Published: 07/02/2015
• Est. Priority Date: 12/31/2013
• Status: Active Grant

• Current Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Original Assignee: Next IT Corporation (Verint Systems Incorporated)
• Inventors: Brown, Fred A., Miller, Tanya M.
• Granted Patent: US 9,823,811 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/04817 using icons graphical or visual programming using iconic symbols G06F8/34
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 9/453 Help systems
• CPC Class Codes: G06N 3/006 based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/016 After-sales
• CPC Class Codes: G06Q 50/20 Education
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages

Abstract

Techniques and architectures for implementing a team of virtual assistants are described herein. The team may include multiple virtual assistants that are configured with different characteristics, such as different functionality, base language models, levels of training, visual appearances, personalities, and so on. The characteristics of the virtual assistants may be configured by trainers, end-users, and/or a virtual assistant service. The virtual assistants may be presented to end-users in conversation user interfaces to perform different tasks for the users in a conversational manner. The different virtual assistants may adapt to different contexts. The virtual assistants may additionally, or alternatively, interact with each other to carry out tasks for the users, which may be illustrated in conversation user interfaces.

Claims

1. A method comprising:

causing display of a virtual assistant, from among multiple virtual assistants, via a conversation user interface, the virtual assistant being displayed with a dialog representation representing a communication from the virtual assistant, the multiple virtual assistants being configured with different characteristics;

identifying, by a smart device, another virtual assistant of the multiple virtual assistants to display via the conversation user interface; and

causing the other virtual assistant to be displayed via the conversation user interface to perform a task for a user, the conversation user interface being displayed via a display of the smart device, the other virtual assistant being displayed with a dialog representation representing a communication from the other virtual assistant.

2. The method of claim 1, wherein the different characteristics of the multiple virtual assistants comprise at least one of different task mappings, different base language models, different types of functionality, different visual appearances, different audible manners of output, different levels of security, different levels of training, or different languages in which the multiple virtual assistants communicate.

3. The method of claim 1, wherein the identifying the other virtual assistant comprises:

determining a concept of a conversation between the user and the virtual assistant of the multiple virtual assistants; and

identifying the other virtual assistant of the multiple virtual assistants that is configured to perform a task that is related to the concept of the conversation.

4. The method of claim 1, wherein the identifying the other virtual assistant comprises:

determining a location of the smart device; and

identifying the other virtual assistant of the multiple virtual assistants that is configured to perform a task that is related to the location of the smart device.

5. The method of claim 1, wherein the identifying the other virtual assistant comprises:

identifying content that has been output via the smart device during a conversation between the user and the virtual assistant of the multiple virtual assistants; and

identifying the other virtual assistant of the multiple virtual assistants that is configured to perform a task that is related to the content that has been output via the smart device during the conversation.

6. The method of claim 1, wherein the identifying the other virtual assistant comprises:

identifying a calendar event associated with the user of the smart device; and

identifying the other virtual assistant of the multiple virtual assistants that is configured to perform a task that is related to the calendar event that is associated with the user.

7. The method of claim 1, wherein the identifying the other virtual assistant comprises:

determining a current orientation of the smart device; and

identify the other virtual assistant of the multiple virtual assistants that is configured to be displayed when the smart device is oriented according to the current orientation.

8. One or more computer storage media storing computer-readable instructions that, when executed, instruct one or more processors to perform operations comprising:

outputting a first virtual assistant via a smart device to facilitate a conversation with a user and outputting a communication via the smart device from the first virtual assistant;

identifying a second virtual assistant to be output via the smart device, the second virtual assistant being configured with a different characteristic than the first virtual assistant; and

in response to identifying the second virtual assistant, outputting the second virtual assistant via the smart device to continue the conversation with the user and outputting a communication via the smart device from the second virtual assistant.

9. The one or more computer storage media of claim 8, wherein the second virtual assistant is identified based at least in part on a context that is associated with at least one of the user or the smart device.

10. The one or more computer storage media of claim 9, wherein the context that is associated with at least one of the user or the smart device comprises at least one of:

input that is received from the user while interacting with the smart device or another smart device;

or

input that is received from the user during the conversation of the user with the first virtual assistant.

11. The one or more computer storage media of claim 9, wherein the context that is associated with at least one of the user or the smart device comprises at least one of a current location of the smart device or a destination location of the smart device, the second virtual assistant being configured to perform a task that is related to at least one of the current location of the smart device or the destination location of the smart device.

12. The one or more computer storage media of claim 9, wherein the context that is associated with at least one of the user or the smart device comprises a message that has been sent by the user via a messaging service, the second virtual assistant being configured to perform a task that is related to content of the message.

13. The one or more computer storage media of claim 9, wherein the context that is associated with at least one of the user or the smart device comprises content that has been viewed or posted via a social networking service, the second virtual assistant being configured to perform a task that is related to the content that has been viewed or posted.

14. The one or more computer storage media of claim 9, wherein the context that is associated with at least one of the user or the smart device comprises search input that is received from the user to initiate a search of content, the second virtual assistant being configured to perform a task that is related to the search input.

15. The one or more computer storage media of claim 9, wherein the context that is associated with at least one of the user or the smart device comprises content that has been output to the user via another smart device, the second virtual assistant being configured to perform a task that is related to the content that has been output via the other smart device.

16. The one or more computer storage media of claim 9, wherein the context that is associated with at least one of the user or the smart device comprises a current time of day, the second virtual assistant being configured to perform a task that has been performed previously at the current time of day.

17. A system comprising:

one or more processors; and

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

causing a first virtual assistant of a group of virtual assistants to be output to a user along with a communication from the first virtual assistant;

obtaining contextual information related to a conversation between a user and the first virtual assistant;

analyzing the contextual information to identify a second virtual assistant of the group of virtual assistants to continue the conversation, the second virtual assistant being configured to perform a different task than the first virtual assistant and being associated with a different persona than the first virtual assistant; and

causing the second virtual assistant to be output to the user along with a communication from the second virtual assistant to continue the conversation.

18. The system of claim 17, wherein the contextual information comprises at least one of conversation information describing the conversation or a previous conversation, content output history describing content that has been output to the user, messaging information describing a message that has been sent by the user via a messaging service, social media information describing content that has been viewed or posted via a social networking service, calendar information describing one or more events associated with the user, preference information describing one or more preferences of the user, or location information indicating a location of a device through which the first virtual assistant is output.

19. The system of claim 17, wherein the acts further comprise:

upon identifying the second virtual assistant, causing a suggestion to be presented to the user suggesting that the user converse with the second virtual assistant; and

receiving user input that includes a selection of the second virtual assistant,

wherein the second virtual assistant is caused to be output based at least in part on the selection from the user.

20. The system of claim 17, wherein the first virtual assistant is configured to dispatch the conversation among the group of virtual assistants to a virtual assistant that is configured to perform a task related to a current context of the conversation.