Method and apparatus for voice control

Patent metadata

Field	Value
Publication number	US-2016293164-A1
Application number	US-201615083778-A
Country	US
Kind code	A1
Filing date	Mar 29, 2016
Priority date	Mar 30, 2015
Publication date	Oct 6, 2016
Grant date	—

Abstract

The present invention provides a voice control method and apparatus that increases the efficiency of voice control. In one exemplary method, a voice system receives a voice command input by a user and determines if the voice command is related to a foreground application. If the voice command is determined to relate to the foreground application, a control command corresponding to the voice command is sent to the foreground application to cause the foreground application to execute the control command. If the voice command is determined to not relate to the foreground application, a background application is identified and the control command corresponding to the voice command is sent to the identified background application to cause the background application to execute the control command.

First claim

What is claimed is:

1 . A method for voice control, comprising:
receiving a voice command input by a user using a voice system; determining if the voice command is related to a foreground application; sending a control command, corresponding to the voice command, to the foreground application to cause the foreground application to execute the control command when the voice command is determined to be related to the foreground application; and identifying a background application which is related to the voice command and sending the control command corresponding to the voice command to the background application to cause the background application to execute the control command when the voice command is not determined to relate to the foreground application.

2 . The method of claim 1 , wherein determining if the voice command is related to the foreground application further comprises:
identifying, from a preset set of command types, a command type matching the voice command; and determining if the voice command is related to the foreground application based on the command type.

3 . The method of claim 1 , wherein when the voice command is determined not to relate to the foreground application or the background application, the method further comprises:
identifying an unlaunched application related to the voice command from a set of unlaunched applications;
switching the foreground application to run on the background, launching the application related to the voice command, and causing it to run in the foreground; and
sending the control command corresponding to the voice command to the foreground application to cause it to execute the control command.

4 . The method of claim 2 , wherein the preset command types comprise:
a first command type not related to an interface content or the background applications; a second command type related to the interface content; and a third command type related to the set of background applications, wherein identifying the command type that matches the voice commands further comprises:
identifying a semantic of the voice command;
searching preset semantic sets corresponding to each of the command types for a semantic which matches the semantic of the voice command; and
identifying the command type of the semantics set that matches the command type of the voice command.

5 . The method of claim 4 , wherein the determining if the voice command is related to the foreground application based on the command type further comprises:
determining that the command type is not related to the foreground application or the background applications when the command type that matches the voice command comprises the first command type; or determining that the voice command is related to the foreground application or the background application when the command type that matches the voice command does not comprise the first command type; or determining that the voice command is related to the foreground application when the command type that matches the voice command comprises the second command type; or determining that the voice command is not related to the foreground application when the command type that matches the voice command does not comprise the second command type; or determining that the voice command is related to the background application when the command type that matches the voice command comprises the third command type; or determining that the voice command is not related to the background applications when the voice command does not comprise the third command type.

6 . The method of claim 1 , further comprising:
monitoring a running foreground application; adding an interface of the foreground application to a set stack corresponding to the foreground application; and removing the interface from the set stack when the foreground application is removed from the foreground; wherein determining if the voice command is related to the foreground application, comprises:
searching the preset set stacks for a matching set stack that matches the voice command;
identifying a corresponding application that corresponds to the matching set stack; and
selecting the corresponding application as the foreground application that is related to the voice command.

7 . The method of claim 1 , wherein prior to receiving the voice command input by the user, the method further comprises:
receiving a launching command, not sent from an application, and waiting for the user to input the voice command.

8 . The method of claim 1 , further comprising:
receiving a launching command sent from an application and waiting for the user to input the voice command; and sending the control command corresponding to the voice command to the application that sent the launching command to cause the application to execute the control command.

9 . The method of claim 7 , further comprising:
displaying a prompt window when a launching command is received, wherein the prompt window displays information suggesting that the user input the voice command; displaying the voice command in the prompt window when the voice command is received; displaying, an execution result in the prompt window when an execution result is sent from the application after the application has executed the control command; hiding the prompt window when receiving a hide command for the prompt window; or hiding the prompt window when no voice command input by the user is received during a first preset time interval.

10 . The method of claim 9 , wherein the prompt window is a floating window that occupies a portion of an entire display screen.

11 . The method of claim 1 , further comprising displaying hint information to the user when no execution result is sent from the application during a second time interval, wherein the second time interval begins after the control command is sent to the application.

12 . The method of claim 1 , wherein after the application related to the voice command is identified, the method further comprises:
displaying the voice command received by the voice system and/or an execution result sent from the foreground application after the foreground application executes the control command in an interface of the foreground application.

13 . The method of claim 1 , wherein the voice system is a voice operated system, wherein the voice operated system can control applications of the voice system to execute the control command.

14 . An apparatus for voice control, comprising:
a main memory; and a processor coupled to the main memory that receives a voice command input by a user, determines if the voice command is related to a foreground application, sends a control command corresponding to the voice command to the foreground application to cause the foreground application to execute the control command when the voice command is determined to be related to the foreground application, and determines a background application related to the voice command from a set of background applications when the voice command is determined to not be related to the foreground application, and sends the control command corresponding to the voice command to the background application related to the voice command to cause the background application to execute the control command.

15 . The apparatus of claim 14 , wherein the processor identifies a matching command type that matches the voice command from a preset set of command types, and determines if the voice command is related to the foreground application based on the command type of the voice command.

Assignees

• Alibaba Group Holding Ltd

Inventors

• Shi Shanwen
• Zhang Boxue
• Cai Lijuan

Classifications

• G10L15/22 Primary

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

• G10L15/1815

  Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title

• G10L2015/228

  of application context · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G06F3/167

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