Virtual assistant team customization

• US 9,830,044 B2
• Filed: 06/02/2014
• Issued: 11/28/2017
• 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
• Primary Examiner(s): SAX, STEVEN PAUL
• Application Number:
  US14/293,586
• Publication Number:
  US 20150186154A1
• Time in Patent Office: 1,275 Days
• Field of Search: 715706, 715708-714, 715821-823, 715963, 715808-809
• 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:

analyzing, by a computing device, a previous conversation with a first virtual assistant to identify a topic that has been discussed in the previous conversation more than a predetermined number of times;

identifying a second virtual assistant that is not currently associated with an account of a user and that is configured to perform one or more tasks that are relevant to the topic that has been discussed in the previous conversation more than the predetermined number of times;

providing, to a device associated with the user, a suggestion to add the second virtual assistant to a group of virtual assistants that are associated with the account of the user, the group of virtual assistants being configured with different personas;

receiving user input indicating a selection of the second virtual assistant to be added to the group of virtual assistants; and

based at least in part on the user input, adding, by the computing device, the second virtual assistant to the group of virtual assistants by associating the second virtual assistant with the account of the user.

2. The method of claim 1, further comprising:

automatically creating a new group of virtual assistants to be associated with at least one of the user or the device associated with the user.

3. The method of claim 1, further comprising:

updating an existing group of virtual assistants to include a third virtual assistant, the existing group of virtual assistants being associated with at least one of the user or the device associated with the user.

4. The method of claim 1, wherein:

the identifying the second virtual assistant is based at least in part on a task that was performed during the previous conversation.

5. The method of claim 1, wherein:

the analyzing further includes analyzing content output history describing content that has been output to the user during the previous conversation with the user; and

the identifying the second virtual assistant is based at least in part on a task that is related to the content output history.

6. The method of claim 1, wherein:

the analyzing further includes analyzing calendar information describing an event associated with the user; and

the identifying the second virtual assistant is based at least in part on a task that is related to the event.

7. The method of claim 1, wherein:

the analyzing further includes analyzing location information describing a previous or future location of the device associated with the user; and

the identifying the second virtual assistant is based at least in part on a task that is related to the location information.

8. The method of claim 1, wherein:

the analyzing further includes analyzing preference information describing a preference of the user; and

the identifying the second virtual assistant is based at least in part on a task that is related to the preference of the user.

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

analyzing a previous conversation with a first virtual assistant to identify a topic that has been discussed in the previous conversation more than a predetermined number of times;

identifying a second virtual assistant that is not currently associated with an account of a user and that is configured to perform one or more tasks that are relevant to the topic that has been discussed in the previous conversation more than the predetermined number of times;

providing, to a device associated with the user, a suggestion to add the second virtual assistant to a group of virtual assistants that are associated with the account of the user, the group of virtual assistants being configured with different personas;

receiving user input indicating a selection of the second virtual assistant to be added to the group of virtual assistants; and

based at least in part on the user input, adding the second virtual assistant to the group of virtual assistants by associating the second virtual assistant with the account of the user.

10. The one or more non-transitory computer storage media of claim 9, wherein the identifying the second virtual assistant is based at least in part on a task that was performed during the previous conversation.

11. The one or more non-transitory computer storage media of claim 9, wherein the operations further comprise:

analyzing content output history describing content that has been output to the user during the previous conversation;

wherein the identifying the second virtual assistant is based at least in part on the analysis of the content output history.

12. The one or more non-transitory computer storage media of claim 9, wherein the operations further comprise:

analyzing calendar information describing an event associated with the user;

wherein the identifying the second virtual assistant is based at least in part on the analysis of the calendar information.

13. The one or more non-transitory computer storage media of claim 9, wherein the operations further comprise:

analyzing location information describing a previous or future location of the device associated with the user;

wherein the identifying the second virtual assistant is based at least in part on the analysis of the location information.

14. The one or more non-transitory computer storage media of claim 9, wherein the operations further comprise:

analyzing preference information describing a preference of the user;

wherein the identifying the second virtual assistant is based at least in part on the analysis of the preference information.

15. 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;

analyzing a previous conversation with a first virtual assistant to identify a topic that has been discussed in the previous conversation more than a predetermined number of times;

identifying a second virtual assistant that is not currently associated with an account of a user and that is configured to perform one or more tasks that are relevant to the topic that has been discussed in the previous conversation more than the predetermined number of times;

providing, to a device associated with the user, a suggestion to add the second virtual assistant to a group of virtual assistants that are associated with the account of the user, the group of virtual assistants being configured with different personas;

receiving user input indicating a selection of the second virtual assistant to be added to the group of virtual assistants; and

based at least in part on the user input, associating the second virtual assistant with the account of the user.

16. The system of claim 15, wherein the identifying the second virtual assistant is based at least in part on a task that was performed during the previous conversation.

17. The system of claim 15, wherein the acts further comprise:

analyzing content output history describing content that has been output to the user during the previous conversation with the user;

wherein the identifying the second virtual assistant is based at least in part on the analysis of the content output history.

18. The system of claim 15, wherein the acts further comprise:

analyzing calendar information describing an event associated with the user;

wherein the identifying the second virtual assistant is based at least in part on the analysis of the calendar information.

19. The system of claim 15, wherein the acts further comprise:

analyzing location information describing a previous or future location of the device associated with the user;

wherein the identifying the second virtual assistant is based at least in part the analysis of the location information.

20. The system of claim 15, wherein the acts further comprise:

analyzing preference information describing a preference of the user;

wherein the identifying the second virtual assistant is based at least in part on the analysis of the preference information.