Task redirection by a voice assistant

Patent metadata

Field	Value
Publication number	US-11538483-B2
Application number	US-202016829193-A
Country	US
Kind code	B2
Filing date	Mar 25, 2020
Priority date	Mar 25, 2020
Publication date	Dec 27, 2022
Grant date	Dec 27, 2022

Abstract

Disclosed are various aspects of postponing or migrating tasks from a first assistant device to another assistant device. In some examples, an assistant device can facilitate task completion. Tasks can be recommended for postponement based upon the complexity of the task, a historical user profile, or the location of the assistant device.

First claim

The invention claimed is:

1. A system, comprising:
at least one computing device comprising at least one processor; and
at least one memory comprising executable instructions, wherein the instructions, when executed by the at least one processor, cause the at least one computing device to at least:
identify a task to be performed using a voice assistant on a first assistant device;
identify a set of capabilities of the first assistant device;
generate a suggestion signal that the task should be completed on the second assistant device based upon the set of capabilities, a past user interaction, or a complexity of the task;
cause the first assistant device to play back a first message including a query to postpone the task in response to determining that the first assistant device lacks a hardware capability to complete the task to be performed using the voice assistant and in response to determining that the second assistant device possesses the hardware capability;
save a completion state of the task in association with a user account of the user in response to a request to postpone the task;
cause the task to be redirected to the second assistant device, wherein the hardware capability comprises a touchscreen display device; and
cause the task to be resumed on the second assistant device using the completion state of the task saved in association with the user account.

2. The system of claim 1 , wherein the instructions identify the second assistant device by identifying a second assistant device in proximity to a location of the first assistant device with a different set of capabilities than the first assistant device.

3. The system of claim 1 , wherein the instructions further cause the at least one computing device to at least:
obtain a request to authenticate the user account on a second assistant device;
authenticate the user account on the second device;
identify a postponed task associated with the user account;
determine that the second assistant device has a different set of capabilities than the first assistant device, the different set of capabilities facilitating completion of the task; and
cause the second assistant device to play back a second message including a query to complete the task.

4. The system of claim 3 , wherein the instructions further cause the at least one computing device to at least:
obtain a request to resume the task on behalf of the user;
retrieve the completion state of the task from the user account;
populate one or more fields associated with the task based upon the completion state; and
cause the second assistant device to play back a third message including a prompt comprising a status of the task.

5. The system of claim 1 , wherein the suggestion signal is based upon a historical error rate associated at least one past user interaction corresponding to the user account, wherein the historical error rate indicates an error rate that exceeds an error threshold.

6. The system of claim 1 , wherein the suggestion signal is based upon a location of the first assistant device, wherein the location is associated with a noise level that exceeds a noise threshold.

7. The system of claim 1 , wherein the suggestion signal is based the first assistant device lacking a display or keyboard to complete the task.

8. A non-transitory computer-readable medium comprising executable instructions, wherein the instructions, when executed by at least one processor, cause at least one computing device to at least:
identify a task to be performed using a voice assistant on a first assistant device;
identify a set of capabilities of the first assistant device;
generate a suggestion signal that the task should be completed on the second assistant device based upon the set of capabilities, a past user interaction, or a complexity of the task;
cause the first assistant device to play back a first message including a query to postpone the task in response to determining that the first assistant device lacks a hardware capability to complete the task to be performed using the voice assistant and in response to determining that the second assistant device possesses the hardware capability;
save a completion state of the task in association with a user account of the user in response to a request to postpone the task;
cause the task to be redirected to the second assistant device, wherein the hardware capability comprises a touchscreen display device; and
cause the task to be resumed on the second assistant device using the completion state of the task saved in association with the user account.

9. The non-transitory computer-readable medium of claim 8 , wherein the instructions identify the second assistant device by identifying a second assistant device in proximity to a location of the first assistant device with a different set of capabilities than the first assistant device.

10. The non-transitory computer-readable medium of claim 8 , wherein the instructions further cause the at least one computing device to at least:
obtain a request to authenticate the user account on a second assistant device;
authenticate the user account on the second device;
identify a postponed task associated with the user account;
determine that the second assistant device has a different set of capabilities than the first assistant device, the different set of capabilities facilitating completion of the task; and
cause the second assistant device to play back a second message including a query to complete the task.

11. The non-transitory computer-readable medium of claim 10 , wherein the instructions further cause the at least one computing device to at least:
obtain a request to resume the task on behalf of the user;
retrieve the completion state of the task from the user account;
populate one or more fields associated with the task based upon the completion state; and
cause the second assistant device to play back a third message including a prompt comprising a status of the task.

12. The non-transitory computer-readable medium of claim 8 , wherein the suggestion signal is based upon a historical error rate associated at least one past user interaction corresponding to the user account, wherein the historical error rate indicates an error rate that exceeds an error threshold.

13. The non-transitory computer-readable medium of claim 8 , wherein the suggestion signal is based upon a location of the first assistant device, wherein the location is associated with a noise level that exceeds a noise threshold.

14. The non-transitory computer-readable medium of claim 8 , wherein the suggestion signal is based the first assistant device lacking a display or keyboard to complete the task.

15. A method comprising:
identifying a task to be performed using a voice assistant on a first assistant device;
identifying a set of capabilities of the first assistant device;
generating a suggestion signal that the task should be completed on the second assistant device based upon the set of capabilities, a past user interaction, or a complexity of the task;
causing the first assistant device to play back a first message including a query to postpone the task in response to determining that the first assistant device lacks a hardware capability to complete the task to be performed using the voice assistant and in response to determining that the second assistant device possesses the hardware capability;
saving a completion state of the task in association with a user account of the user in response to a request to postpone the task;
cause the task to be redirected to the second assistant dev

Assignees

• Vmware Inc

Inventors

• Shetty Rohit Pradeep
• Aluvala Suman

Classifications

• H04L67/306

  User profiles · CPC title

• G10L2015/225

  Feedback of the input speech · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• H04W12/63

  Location-dependent; Proximity-dependent · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title