Method and apparatus for voice control

• US 10,573,303 B2
• Filed: 03/29/2016
• Issued: 02/25/2020
• Est. Priority Date: 03/30/2015
• Status: Active Grant

• Current Assignee: Banma Zhixing Network (Hongkong) Co., Limited
• Original Assignee: Alibaba Group Holding Ltd.
• Inventors: Shi, Shanwen, Zhang, Boxue, Cai, Lijuan
• Primary Examiner(s): Sarpong, Akwasi M
• Application Number:
  US15/083,778
• Publication Number:
  US 20160293164A1
• Time in Patent Office: 1,428 Days
• Field of Search: 704206, 704207, 704 9, 704 8
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context

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.

Claims

1. A method for voice controlling applications, the method comprising:

receiving a voice command;

transforming the voice command into a number of words;

determining a command type with a processor that matches one or more words of the number of words to one or more preset words of a plurality of preset words that are associated with a plurality of command types to determine the command type;

determining an unlaunched application with the processor by determining which unlaunched application has a number of associated words that are related to one or more words of the number of words when the command type is an initial command, and a launched application with the processor by determining which launched application has a number of associated words that are related to one or more words of the number of words when the command type is a procedural command; and

launching with the processor the unlaunched application;

wherein the number of words is a phrase;

wherein determining a command type comprises;

determining a meaning or semantic of the phrase; and

determining whether the meaning of the phrase matches one or more preset command meanings.

2. The method of claim 1, wherein determining a launched application when the command type is the procedural command comprises:

determining whether one or more words of the number of words are related to a number of words associated with an application in a foreground; and

when one or more words of the number of words are related to the application in the foreground, sending the procedural command to the application in the foreground.

3. The method of claim 2, wherein determining a launched application when one or more words of the number of words are unrelated to the application in the foreground comprises:

determining an application in a background that has a number of associated words that are related to the one or more words of the number of words; and

sending the procedural command to the application in the background.

4. The method of claim 2, wherein:

the number of words comprises one or more keywords; and

when a plurality of first applications are simultaneously running in the foreground, the plurality of first applications have a plurality of interfaces such that each first application has an interface, each interface having one or more associated keywords,

further comprising;

generating a plurality of preset set stacks for the plurality of interfaces of the plurality of first applications such that each preset set stack has an interface of a first application of the plurality of first applications;

searching the preset set stacks for a matching set stack that has an interface with associated keywords that match the one or more keywords;

identifying a corresponding application that corresponds to the matching set stack; and

selecting the corresponding application as the first application of the plurality of first applications that is related to the voice command.

5. The method of claim 1, wherein:

the number of words have a meaning or semantic; and

when a plurality of first applications are simultaneously running in the foreground, the plurality of first applications have a plurality of interfaces such that each first application has an interface, each interface having one or more associated semantics,

further comprising;

generating a plurality of preset set stacks for the plurality of interfaces of the plurality of first applications such that each preset set stack has an interface of a first application of the plurality of first applications;

searching the preset set stacks for a matching set stack that has an interface with associated semantics that match a semantic of the number of words;

identifying a corresponding application that corresponds to the matching set stack; and

selecting the corresponding application as the first application of the plurality of first applications that is related to the voice command.

6. The method of claim 2, further comprising:

receiving a launching command;

starting a timer in response to receiving the launching command;

displaying a prompt window in response to receiving the launching command;

displaying the number of words in the prompt window in response to transforming the voice command; and

cancelling the launching command if the timer expires without receiving the voice command.

7. The method of claim 6, wherein the prompt window:

displays information suggesting that a user input the voice command;

displays the voice command when the voice command is received;

displays an execution result when an execution result is sent from the first application that received the procedural command after the first application that received the procedural command has executed the procedural command; and

hides when receiving a hide command, or when no voice command input by the user is received during a first preset time interval.

8. The method of claim 7, wherein the prompt window is a floating window that occupies a portion of an entire display screen.

9. The method of claim 7, further comprising displaying hint information to suggest an error when no execution result is sent from the first application that received the procedural command during a time interval that begins after the procedural command has been sent.

10. The method of claim 1, wherein the one or more words of the number of words is a number of keywords.

11. The method of claim 10, wherein:

determining a command type comprises determining whether one or more keywords of the number of words matches one or more stored command keywords.

12. An apparatus for voice controlling applications, the apparatus comprising:

a main memory that stores instructions; and

a processor coupled to the main memory, the processor to execute the instructions stored in the main memory to;

receive a voice command,

transform the voice command into a number of words;

determine a command type by matching one or more words of the number of words to one or more preset words of a plurality of preset words that are associated with a plurality of command types to determine the command type;

determine an unlaunched application by determining which unlaunched application has a number of associated words that are related to one or more words of the number of words when the command type is an initial command, and a launched application by determining which launched application has a number of associated words that are related to one or more words of the number of words when the command type is a procedural command; and

launch the unlaunched application;

wherein the number of words is a phrase;

wherein determine a command type comprises;

determine a meaning or semantic of the phrase; and

determine whether the meaning of the phrase matches one or more preset command meanings.

13. The apparatus of claim 12, wherein when the command type is the procedural command, the processor to further:

determine whether one or more words of the number of words are related to a number of words associated with an application in a foreground; and

when one or more words of the number of words are related to the number of words associated with an application in the foreground, send the procedural command to the application in the foreground.

14. The apparatus of claim 13, wherein when one or more words of the number of words are unrelated to the application in the foreground, the processor to further:

determine an application in a background that has a number of associated words that are related to the one or more words of the number of words; and

send the procedural command to the application in the background.

15. A non-transitory computer-readable storage device and comprising instructions that when executed by a processor perform a method of voice controlling applications, the method comprising:

receiving a voice command;

transforming the voice command into a number of words;

determining a command type that matches one or more words of the number of words to one or more preset words of a plurality of preset words that are associated with a plurality of command types to determine the command type;

determining an unlaunched application by determining which unlaunched application has a number of associated words that are related to one or more words of the number of words when the command type is an initial command, and a launched application by determining which launched application has a number of associated words that are related to one or more words of the number of words when the command type is a procedural command; and

launching the unlaunched application;

wherein the number of words is a phrase;

wherein determining a command type comprises;

determining a meaning or semantic of the phrase; and

determining whether the meaning of the phrase matches one or more preset command meanings.

16. The method of claim 15, wherein determining a launched application when the command type is the procedural command comprises:

determining whether one or more words of the number of words are related to a number of words associated with an application in a foreground; and

when one or more words of the number of words are related to the application in the foreground, sending the procedural command to the application in the foreground.

17. The method of claim 15, wherein the method further comprises:

receiving a launching command;

starting a timer in response to receiving the launching command;

displaying a prompt window in response to receiving the launching command;

displaying the number of words in the prompt window in response to transforming the voice command; and

cancelling the launching command if the timer expires without receiving the voice command.

18. The method of claim 16, wherein determining a launched application when one or more words of the number of words are unrelated to the application in the foreground comprises:

determining an application in a background that has a number of associated words that are related to the one or more words of the number of words; and

sending the procedural command to the second application in the background.