Dialog Flow Management In Hierarchical Task Dialogs

• US 20160042735A1
• Filed: 08/11/2014
• Published: 02/11/2016
• Est. Priority Date: 08/11/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Goussard, Jacques-Olivier, Beaufort, Richard J., Vibbert, Mitchell, Monnahan, Benjamin P.
• Granted Patent: US 9,767,794 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 9/4843 by program, e.g. task dispatcher, supervisor, operating system
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/222 Barge in, i.e. overridable guidance for interrupting prompts
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

Methods and systems for managing multiple tasks using a dialog are presented. In some embodiments, a processor may parse a first natural language user input received at a user device to extract task related information from the first natural language user input. In response to identifying that the first natural language user input comprises a request to perform a first task, the processor may initiate execution of the first task. The user device may receive a second natural language user input after execution of the first task has been initiated which requests execution of a second task. The processor may initiate execution of the second task before execution of the first task is complete.

Claims

1. A method comprising:

identifying, by a computing device, that a first natural language user input, received at the computing device, comprises a request to perform a first dialog task;

responsive to identifying a request to perform a first dialog task, initiating execution, by the computing device, of a first plurality of task agents comprised by the first dialog task according to a first hierarchical order by which task agents in the first plurality of task agents are arranged for execution;

responsive to a determination that a second natural language user input, received at the computing device during execution of the first dialog task, comprises a request to perform a second dialog task, determining, by the computing device, that the second dialog task is to be executed before execution of the first dialog task is completed; and

initiating execution, by the computing device prior to completion of the first dialog task, of a second plurality of task agents comprised by the second dialog task in an order based on a second hierarchical order by which task agents in the second plurality of task agents are scheduled for execution.

2. The method of claim 1, further comprising:

responsive to the second natural language user input requesting execution of a second dialog task, suspending execution, by the computing device, of the first dialog task; and

preserving, by the computing device, a state of a natural language dialog and user inputs received during execution of the first dialog task.

3. The method of claim 2, further comprising:

responsive to determining that execution of the second dialog task has completed;

retrieving, by the computing device, the state of the natural language dialog and user inputs received during execution of the first dialog task; and

resuming execution, by the computing device, of the first dialog task from a point at which the first dialog task was suspended.

4. The method of claim 1, wherein execution of at least one task agent of the first plurality of task agents engages a user in a natural language dialog to extract information, from the second natural language user input received during execution of the first dialog task, required for the execution of the first dialog task.

5. The method of claim 1, wherein initiating execution of the first plurality of task agents further comprises scheduling for execution, by the computing device, each task agent of the first plurality of task agents in an order based on the first hierarchical order of arrangement of the first plurality of task agents, and wherein initiating execution of the second plurality of task agents further comprises scheduling for execution, by the computing device, each task agent of the second plurality of task agents in an order based on the second hierarchical order of arrangement of the second plurality of task agents.

6. The method of claim 1, further comprising:

responsive to receiving the request to perform a second dialog task, determining, by the computing device, whether execution of the second dialog task should be prevented.

7. The method of claim 1, further comprising identifying, by the computing device, which dialog task is to be executed based on at least one of the second natural language user input and information in the first plurality of task agents.

8. The method of claim 1, wherein the first dialog task and the second dialog task are managed simultaneously, the method further comprising:

switching, by the computing, between different dialog tasks based on a natural language dialog between the user and the computing device.

9. The method of claim 1, wherein execution of the first dialog task further comprises:

generating, by the computing device, a list of parameters that each of the first plurality of task agents expects to identify from the natural language dialog;

responsive to parsing the natural language dialog, associating, by the computing device, at least one user input value from the natural language dialog with each parameter in the list of parameters; and

executing, by the computing device, the first plurality of task agents using the at least one user input value.

10. The method of claim 1, further comprising:

determining, by the computing device, that the second natural language user input comprises instructions to modify the first dialog task, currently being executed, by adding additional task agents to the first hierarchical order; and

scheduling for execution, by the computing device, the additional task agents to the first dialog task currently being executed according to the first hierarchical order.

11. An apparatus, comprising:

at least one processor; and

at least one memory storing computer-readable instructions that, when executed by the at least one processor, cause the apparatus to;

identify that a first natural language user input, received at the computing device, comprises a request to perform a first dialog task;

initiate execution of a first plurality of task agents comprised by the first dialog task according to a first hierarchical order by which task agents in the first plurality of task agents are arranged for execution;

responsive to a determination that a second natural language user input, received during execution of the first dialog task, comprises a request to perform a second dialog task, determine that the second dialog task is to be executed before execution of the first dialog task is completed; and

initiate execution, prior to completion of the first dialog task, of a second plurality of task agents comprised by the second dialog task in an order based on a second hierarchical order by which task agents in the second plurality of task agents are scheduled for execution.

12. The apparatus of claim 11, wherein the instructions, when executed by the at least one processor, cause the apparatus to:

suspend execution of the first dialog task in response to the second natural language user input requesting execution of a second dialog task; and

preserve a state of a natural language dialog and user inputs received during execution of the first dialog task.

13. The apparatus of claim 12, wherein the instructions, when executed by the at least one processor, cause the apparatus to:

retrieve the state of the natural language dialog and user inputs received during execution of the first dialog task; and

resume execution of the first dialog task from a point at which the first dialog task was suspended.

14. The apparatus of claim 11, wherein execution of at least one task agent of the first plurality of task agents engages a user in a natural language dialog to extract information, from the second natural language user input received during execution of the first dialog task, required for the execution of the first dialog task.

15. The apparatus of claim 11, wherein initiating execution of the first plurality of subtasks further causes the apparatus to schedule execution of each task agent of the first plurality of task agents in an order based on the first hierarchical order of arrangement of the first plurality of task agents, and wherein initiating execution of the second plurality of task agents further causes the apparatus to schedule execution of each task agent of the second plurality of task agents in an order based on the second hierarchical order of arrangement of the second plurality of task agents.

16. The apparatus of claim 11, wherein the instructions, when executed by the at least one processor, cause the apparatus to determine whether execution of the second dialog task should be prevented.

17. The apparatus of claim 11, wherein the instructions, when executed by the at least one processor, cause the apparatus to identify which dialog task is to be executed based on at least one of the second natural language user input and information in the first plurality of task agents.

18. The apparatus of claim 11, wherein the first dialog task and the second dialog task are managed simultaneously, and wherein the instructions, when executed by the at least one processor, cause the apparatus to switch between different dialog tasks based on a natural language dialog between the user and the apparatus.

19. The apparatus of claim 18, wherein the instructions, when executed by the at least one processor, cause the apparatus to:

generate a list of parameters that each of the first plurality of task agents expects to identify from a natural language dialog user input received at the apparatus;

associate at least one user input value from the natural language dialog user input with each parameter in the list of parameters upon parsing the natural language dialog user input; and

execute the first plurality of task agents using the at least one user input value.

20. The apparatus of claim 11, wherein the instructions, when executed by the at least one processor, cause the apparatus to:

determine that a natural language dialog user input, received at the apparatus, comprises instructions to modify the first dialog task, currently being executed, by adding additional task agents to the first hierarchical order; and

schedule, for execution, the additional task agents to the first dialog task currently being executed according to the first hierarchical order.