Virtual assistant conversations

Patent metadata

Field	Value
Publication number	US-10088972-B2
Application number	US-201414293673-A
Country	US
Kind code	B2
Filing date	Jun 2, 2014
Priority date	Dec 31, 2013
Publication date	Oct 2, 2018
Grant date	Oct 2, 2018

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.

First claim

What is claimed is:

1. A method comprising:
under control of a service computing device configured with executable instructions,
obtaining an input from a first user of a first computing device;
determining, based at least in part on contextual information associated with at least one of the input or the first computing device:
a first virtual assistant via the first computing device, the first virtual assistant being associated with the first user and a first set of attributes;
a task to be performed associated with the user input or the first computing device; and
a second virtual assistant that is associated with a second user further associated with performance of the task, the second virtual assistant being associated with a second set of attributes;

sending a message on behalf of the first virtual assistant to the second virtual assistant requesting authorization for the first virtual assistant to communicate with the second virtual assistant;
determining that the second user has authorized the first virtual assistant to communicate with the second virtual assistant;
based at least in part on determining that the second user has authorized the first virtual assistant to communicate with the second virtual assistant, causing the first virtual assistant and the second virtual assistant to communicate;
providing a first dialog representation in a conversation user interface via the first computing device;
providing a second dialog representation in the conversation user interface via the second computing device, at least one of the first dialog representation or the second dialog representation including a natural language representation of a communication from at least one of the first virtual assistant or the second virtual assistant;
providing the natural language representation of the communication to a virtual assistant trainer interface via a third computing device that is used by a trainer of the first or second virtual assistants to submit feedback on the communication;
receiving the feedback submitted in the virtual assistant trainer interface at the service computing device; and
reconfiguring the respective attributes of the first or second virtual assistant based on the feedback.

2. The method of claim 1 , wherein the first and second dialog representations are provided over a period of time in a back-and-forth manner to emulate a human conversation.

3. The method of claim 1 , wherein at least one of the first dialog representation or the second dialog representation includes a summary conversation item that represents an entirety of communications between the first virtual assistant and the second virtual assistant.

4. The method of claim 1 , wherein the contextual information comprises location information describing a location of the first computing device.

5. The method of claim 1 , wherein the contextual information comprises calendar information describing an event associated with the first user.

6. The method of claim 1 , wherein the contextual information comprises message information describing a message that has been sent by the first user.

7. The method of claim 1 , wherein the first set of attributes and the second set of attributes contain at least one of a specific persona, a functionality, a visual appearance, or an audible manner of output.

Assignees

• Verint Americas Inc

Inventors

• Brown Fred A
• Miller Tanya M

Classifications

• G06Q30/016

  After-sales · CPC title

• G06Q50/20

  Education · CPC title

• G06N3/006

  based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] · CPC title

• G06F3/04817 Primary

  using icons (graphical or visual programming using iconic symbols G06F8/34) · CPC title

• G06F9/453

  Help systems · CPC title