Maintaining context for voice processes

Patent metadata

Field	Value
Publication number	US-11061644-B2
Application number	US-202016894229-A
Country	US
Kind code	B2
Filing date	Jun 5, 2020
Priority date	Sep 21, 2016
Publication date	Jul 13, 2021
Grant date	Jul 13, 2021

Abstract

A system capable of generating and storing progress data associated with third party services. A voice enabled device may receive voice commands and the system may perform natural language understanding (NLU) to interpret the voice commands, determine a corresponding process and send instructions to a third party server associated with the process. In order to resume the process after the process is interrupted, the system may save and/or cause the third party server to save progress data and/or a checkpoint corresponding to a status of the process at the time that the process is interrupted. The system may use the progress data to resume the process at a later point based on the status. In addition, the system may track processes associated with saved progress data/checkpoints and may interpret incoming voice commands based on the tracked processes.

First claim

What is claimed is:

1. A computer-implemented method, the method comprising:
receiving first input data corresponding to a natural language processing system;
performing natural language processing on the first input data to generate natural language understanding (NLU) output data;
based at least in part on the NLU output data, selecting an application from a plurality of applications;
operating the application;
determining an active task associated with the application;
determining, based at least in part on the active task, first status data corresponding to the application;
determining, based at least in part on the active task, an expiration time associated with the first status data;
storing an association between the first status data, the expiration time, and the application; and
halting operation of the application.

2. The computer-implemented method of claim 1 , wherein determining the first status data further comprises:
determining a first step in a series of steps associated with the application;
determining that the first step is followed by another step in the series of steps; and
determining the first status data corresponding to the first step.

3. The computer-implemented method of claim 1 , further comprising:
receiving, prior to halting the operation of the application, a notification of a first step in a series of steps associated with the application,
wherein determining the first status data further comprises determining the first status data based on the first step.

4. The computer-implemented method of claim 1 , further comprising:
receiving, prior to halting the operation of the application, second status data;
receiving, after receiving the second status data but prior to halting the operation of the application, the first status data; and
determining to halt the operation of the application,
wherein determining the first status data further comprises determining that the first status data is most recent status data received during the operation of the application.

5. The computer-implemented method of claim 1 , wherein determining the first status data further comprises:
sending a request to a first device to create and send the first status data;
receiving the first status data from the first device; and
storing the first status data.

6. The computer-implemented method of claim 1 , further comprising:
sending a first request to a device to create and store second status data corresponding to the first status data.

7. The computer-implemented method of claim 6 further comprising:
receiving second input data corresponding to the natural language processing system;
determining that the second input data corresponds to a request to operate the application;
determining that the application is associated with the first status data;
sending the first status data to the device, the first status data comprising at least one of a reference location or a current step of a series of steps associated with the application; and
sending a second request to the device to resume operating the application based on the first status data.

8. The computer-implemented method of claim 1 , wherein receiving the first input data further comprises:
receiving, from a device, audio data corresponding to an utterance,

wherein performing the natural language processing to generate NLU output data further comprises:
performing speech recognition on the audio data to determine text data;
determining a command corresponding to the text data;
determining that the command is associated with the application; and
generating, based on the command and the application, the NLU output data.

9. The computer-implemented method of claim 1 , further comprising:
receiving, from a device, second input data corresponding to the natural language processing system;
determining that the second input data corresponds to a request to operate the application;
determining that the application is associated with the first status data;
sending, to the application, the first status data; and
sending, to the application, a request to resume the operation of the application based on the first status data.

10. The computer-implemented method of claim 1 , further comprising:
receiving, from a device, second input data corresponding to the natural language processing system;
determining that the second input data corresponds to a request to operate the application;
determining that the application is associated with the first status data;
determining, using the first status data, a status of the operation of the application;
generating audio data indicating the status; and
sending, to the device, the audio data.

11. The computer-implemented method of claim 1 , further comprising:
determining that a duration of time has elapsed since halting the operation of the application;
generating, using the first status data, a reminder indicating a status of the operation of the application;
generating audio data corresponding to the reminder; and
sending, to a device associated with the first input data, the audio data.

12. A system comprising:
at least one processor; and
memory including instructions operable to be executed by the at least one processor to cause the system to:
obtain input data corresponding to a natural language processing system;
determine a plurality of applications that are associated with status data;
determine that the input data is associated with an application of the plurality of applications;
identify a user profile associated with the input data;
determine first status data indicating a status of a session associated with the user profile and with the application; and
cause the application to resume the session based on the first status data.

13. The system of claim 12 , wherein the memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
prior to obtaining the input data, determine association data, wherein determining the association data further comprises:
determining an identity of the application;
determining an active task associated with the application;
determining a task type of the active task; and
determining a session identification associated with the session,

wherein determining the status data is based at least in part on the association data.

14. The system of claim 12 , wherein the memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine, during a time period prior to obtaining the input data, to halt the session;
determine that the application is capable of using the status data to represent the status of the session;
determine the first status data corresponding to the application, wherein the first status data includes information about the status of the session during the time period;
store an association between the first status data and an identity of the application in the user profile;
add the identity of the application to a list of the plurality of applications associated with the status data; and
cause the session associated with the application to be halted.

15. The system of claim 12 , wherein the memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
send, during a time period prior to obtaining the input data, to a device associated with the application, a first request to create and store second status data that corresponds to the first status data; and
determine, during the time

Assignees

• Amazon Tech Inc

Inventors

• Kelly Eric
• Utter Kevin

Classifications

• G06F3/167 Primary

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title