Virtual agent communication for electronic device

• US 10,154,070 B2
• Filed: 08/09/2013
• Issued: 12/11/2018
• Est. Priority Date: 08/10/2012
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Phillips, Michael Stuart, Nguyen, John, Leonard, Thomas Jay, Grannan, David
• Primary Examiner(s): Taylor, Nicholas R
• Assistant Examiner(s): Robinson, Christopher B
• Application Number:
  US13/963,316
• Publication Number:
  US 20140047001A1
• Time in Patent Office: 1,950 Days
• Field of Search: None
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: H04L 65/403 Arrangements for multi-party communication, e.g. for conferences data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15
• CPC Class Codes: H04L 67/141 Setup of application sessions admission control or resource allocation in data switching networks H04L47/70
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04W 4/00 Services specially adapted for wireless communication networks; Facilities therefor

Abstract

Methods and apparatus for communicating between virtual agents associated with users of electronic devices connected via at least one network. A first user may instruct an associated first virtual agent to invoke a communication session with a second virtual agent associated with a second user. To invoke the communication session, the first virtual agent may send an outgoing communication to the second virtual agent and the outgoing communication may instruct the second virtual agent to perform at least one action on behalf of the first user. Virtual agents associated with different users may alternatively communicate with each other in the absence of user interaction to perform a collaborative action.

Claims

1. A method of establishing a communication session between a first virtual agent executing on a first electronic device and a second virtual agent executing on a second electronic device, wherein each of the first and second virtual agents is associated with a user, the method comprising:

receiving, by a first electronic device on which the first virtual agent is executing, speech input from a first user;

processing, with a speech recognition engine associated with the first electronic device, the speech input to determine a speech recognition result;

identifying a second user based, at least in part, on the speech recognition result;

determining whether the second user is associated with a second virtual agent executing on a second electronic device, wherein determining whether the second user is associated with a second virtual agent comprises sending a first outgoing communication from the first electronic device to the second electronic device;

determining, by the first virtual agent associated with the first user, whether to invoke a communication session with the second virtual agent associated with the second user when it is determined that the second user is associated with the second virtual agent, wherein determining whether to invoke the communication session is based, at least in part, on the speech recognition result and contextual data selected from the group consisting of a time of day, a location of the first user, and history information describing one or more past interactions of the first user with the first electronic device; and

sending over at least one network a second outgoing communication from the first electronic device to the second electronic device on which the second virtual agent is executing in response to determining to invoke the communication session, wherein the second outgoing communication, at least in part, invokes the communication session.

2. The method of claim 1, further comprising:

receiving, from the second virtual agent, a response to the second outgoing communication.

3. The method of claim 2, wherein the response to the second outgoing communication received from the second virtual agent includes a request to coordinate a new appointment;

and wherein the method further comprises;

sending a third outgoing communication to the second virtual agent to coordinate the new appointment, wherein the third outgoing communication is sent to the second virtual agent without input from the first user.

4. The method of claim 1, wherein determining whether to invoke a communication session based, at least in part, on the speech recognition result comprises determining whether the speech recognition result includes one or more trigger terms.

5. The method of claim 1, further comprising:

aggregating user data for the first user, wherein the user data is aggregated from multiple information sources;

storing the aggregated user data; and

accessing by the first virtual agent, at least a portion of the stored aggregated user data.

6. The method of claim 5, wherein at least some content of the second outgoing communication is determined based, at least in part, on the aggregated user data.

7. The method of claim 1, wherein identifying the second user comprises:

identifying the second user based, at least in part, on user data for the first user.

8. The method of claim 7, wherein the user data includes a contact list associated with the first user.

9. The method of claim 1, further comprising:

determining a preferred mode of communication for the second user; and

sending the second outgoing communication using the preferred mode of communication.

10. The method of claim 1, wherein the second outgoing communication includes a request for the second virtual agent to perform at least one action on behalf of the first user.

11. The method of claim 10, wherein the at least one action includes sending a response communication to the first virtual agent.

17. The method of claim 1, wherein the first virtual agent is configured to control at least one function of the electronic device.

18. The method of claim 1, wherein the second outgoing communication includes:

an indication that the first virtual agent could not interpret one or more terms in the speech recognition result; and

a request to the second virtual agent for the second virtual agent to interpret at least one of the one or more terms.

12. A non-transitory computer-readable medium encoded with a plurality of instructions that, when executed by at least one computer, perform a method of establishing a communication session between a first virtual executing on a first electronic device and second virtual agent executing on a second electronic device, wherein each of the first and second virtual agents is associated with a user, the method comprising:

receiving, by a first electronic device on which the first virtual agent is executing, speech input from a first user;

processing, with a speech recognition engine associated with the first electronic device, the speech input to determine a speech recognition result;

identifying a second user based, at least in part, on the speech recognition result;

determining whether the second user is associated with a second virtual agent executing on a second electronic device, wherein determining whether the second user is associated with a second virtual agent comprises sending a first outgoing communication from the first electronic device to the second electronic device;

determining, by the first virtual agent associated with the first user, whether to invoke a communication session with the second virtual agent associated with the second user when it is determined that the second user is associated with the second virtual agent, wherein determining whether to invoke the communication session is based, at least in part, on the speech recognition result and contextual data selected from the group consisting of a time of day, a location of the first user, and history information describing one or more past interactions of the first user with the first electronic device; and

sending over at least one network a second outgoing communication from the first electronic device to the second electronic device on which the second virtual agent is executing in response to determining to invoke the communication session, wherein the second outgoing communication, at least in part, invokes the communication session.

13. The computer-readable medium of claim 12, wherein determining whether to invoke a communication session comprises determining whether the speech recognition result includes one or more trigger terms or relevant contextual data.

14. The computer-readable medium of claim 12, wherein the method further comprises:

aggregating user data for the first user, wherein the user data is aggregated from multiple information sources;

storing the aggregated user data; and

accessing by the first virtual agent, at least a portion of the stored aggregated user data;

wherein at least some content of the second outgoing communication is determined based, at least in part, on the aggregated user data.

15. The computer-readable medium of claim 12, wherein the method further comprises:

determining a preferred mode of communication for the second user; and

sending the second outgoing communication using the preferred mode of communication.

16. An electronic device, comprising:

a communication interface configured to receive speech input from a first user;

a speech recognition engine configured to process the speech input to determine a speech recognition result; and

a first virtual agent executing on the electronic device, wherein the first virtual agent is configured to;

identify a second user based, at least in part, on the speech recognition result;

determine whether the second user is associated with a second virtual agent executing on another electronic device, wherein determining whether the second user is associated with a second virtual agent comprises sending a first outgoing communication from the electronic device to the another electronic device;

determine whether to invoke a communication session with the second virtual agent associated with the second user when it is determined that the second user is associated with the second virtual agent, wherein determining whether to invoke the communication session is based, at least in part, on the speech recognition result and contextual data selected from the group consisting of a time of day, a location of the first user, and history information describing one or more past interactions of the first user with the first electronic device; and

send, over at least one network, a second outgoing communication from the first electronic device to the another electronic device on which the second virtual agent is executing in response to determining to invoke the communication session, wherein the second outgoing communication, at least in part, invokes the communication session, wherein the second outgoing communication includes a request for the second virtual agent to perform at least one action on behalf of the first user.