Command handling method, apparatus, and system

• US 9,704,503 B2
• Filed: 10/22/2014
• Issued: 07/11/2017
• Est. Priority Date: 08/09/2012
• Status: Active Grant

• Current Assignee: Huawei Device Company Limited (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Huawei Device Company Limited (Huawei Investment & Holding Co., Ltd.)
• Inventors: Mei, Jingqing, Xue, Guodong
• Primary Examiner(s): Serrou, Abdelali
• Application Number:
  US14/520,575
• Publication Number:
  US 20150039319A1
• Time in Patent Office: 993 Days
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 21/00 Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility G10L19/00 takes precedence

Abstract

A command handling method, apparatus, and system. The method includes receiving multiple voice instructions sent by a voice parsing server, where the multiple voice instructions are generated after the voice parsing server parses source voice commands that are from different voice control devices; separately determining whether any two voice instructions in the multiple voice instructions are similar instructions, where the similar instructions are voice instructions corresponding to source voice commands that are obtained by the different voice control devices by collecting same voice information; and when two voice instructions that are similar instructions exist in the multiple voice instructions, discarding one voice instruction in the two similar voice instructions. The embodiments of the present invention further provide a command handling apparatus and system. The embodiments eliminate a control error caused by repeated execution of a command.

Claims

1. A command handling method comprising:

receiving multiple voice instructions sent by a voice parsing server, wherein the multiple voice instructions are generated after the voice parsing server parses source voice commands from different voice control devices, and wherein the multiple voice instructions separately carry collection time information of a source voice command corresponding to each voice instruction and instruction content of each voice instruction;

separately determining, according to the collection time information of the source voice commands corresponding to the multiple voice instructions, whether the collection time information of the source voice commands corresponding to any two voice instructions in the multiple voice instructions overlaps;

separately determining, according to the instruction content of the multiple voice instructions, whether content of the any two voice instructions in the multiple voice instructions is repeated;

determining that the any two voice instructions are similar instructions when the collection time information of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions overlaps and the content of the any two voice instructions in the multiple voice instructions is repeated, wherein the similar instructions are voice instructions corresponding to the source voice commands obtained by the different voice control devices by collecting same voice information;

discarding one voice instruction in the any two voice instructions when the any two voice instructions that are similar instructions exist in the multiple voice instructions; and

executing an operation indicated by a remaining voice instruction from the any two voice instructions.

2. The method according to claim 1, further comprising:

recording, when a new voice instruction is received from the voice parsing server, collection time information of the new voice instruction;

comparing the collection time information of the new voice instruction with a collection time information of a previously recorded voice instruction;

determining a related voice instruction of which a difference between the collection time information of the previously recorded voice instruction and the collection time information of the new voice instruction is smaller than a predetermined threshold; and

using the new voice instruction and the related voice instruction as the multiple voice instructions.

3. The method according to claim 1, wherein separately determining, according to the collection time information of the source voice commands corresponding to the multiple voice instructions, whether the collection time information of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions overlaps comprises:

separately determining, according to initial time stamps and end time stamps of the source voice commands corresponding to the multiple voice instructions, whether a difference of initial time stamps of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions and a difference of end time stamps of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions are both smaller than a preset threshold; and

determining that the collection time information of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions overlaps when the difference of the initial time stamps and the difference of the end time stamps are both smaller than the preset threshold.

4. The method according to claim 1, wherein separately determining, according to the collection time information of the source voice commands corresponding to the multiple voice instructions, whether the collection time information of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions overlaps comprises:

separately acquiring a duration of the multiple voice instructions according to initial time stamps and end time stamps of the source voice commands corresponding to the multiple voice instructions;

determining whether the duration of the any two voice instructions in the multiple voice instructions overlaps; and

determining that the collection time of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions overlaps when the duration overlaps.

5. The method according to claim 1, wherein the multiple voice instructions further separately carry a priority parameter of the source voice command corresponding to each voice instruction, wherein the method further comprises determining a voice instruction with a higher priority in the any two similar voice instructions and a voice instruction with a lower priority in the any two similar voice instructions according to the priority parameter of the source voice command corresponding to the voice instruction, and wherein discarding one voice instruction in the any two voice instructions when the any two voice instructions that are similar instructions exist in the multiple voice instructions comprises:

returning the voice instruction with the higher priority in the two similar voice instructions to a corresponding voice control device when the any two voice instructions that are the similar instructions exist in the multiple voice instructions; and

discarding the voice instruction with the lower priority.

6. The method according to claim 5, further comprising discarding the new voice instruction when a received new voice instruction and a voice instruction that has been returned to other voice control devices are similar instructions.

7. The method according to claim 1, further comprising:

performing, by the voice parsing server, time synchronization with the voice control devices; and

separately receiving, by the voice parsing server, the source voice commands sent by the voice control devices.

8. The method according to claim 1, further comprising:

performing, by a local voice control gateway, time synchronization with the voice control devices;

separately receiving, by the local voice control gateway, the source voice commands sent by the voice control devices; and

sending, by the local voice control gateway, the source voice commands to the voice parsing server.

9. A command handling apparatus comprising:

a memory configured to store a program instruction;

a receiver configured to receive multiple voice instructions sent by a voice parsing server, wherein the multiple voice instructions are generated after the voice parsing server parses source voice commands that are from different voice control devices, and wherein the multiple voice instructions received by the receiver separately carry collection time information of a source voice command corresponding to each voice instruction and instruction content of each voice instruction; and

a processor coupled to the memory and the receiver and configured to;

separately determine, according to the collection time information of the source voice commands corresponding to the multiple voice instructions, whether the collection time information of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions overlaps;

separately determine, according to the instruction content of the multiple voice instructions, whether content of the any two voice instructions in the multiple voice instructions is repeated;

determine that the any two voice instructions are similar instructions when the collection time information of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions overlaps and the content of the any two voice instructions in the multiple voice instructions is repeated, wherein the similar instructions are voice instructions corresponding to the source voice commands that are obtained by the different voice control devices by collecting same voice information;

discard one voice instruction in the any two voice instructions when the any two voice instructions that are similar instructions exist in the multiple voice instructions; and

execute an operation indicated by a remaining voice instruction from the any two voice instructions.

10. The apparatus according to claim 9, wherein the processor is further configured to:

record collection time information of the new voice instruction when a new voice instruction is received from the voice parsing server;

compare the collection time information of the new voice instruction with a collection time information of a previously recorded voice instruction;

determine a related voice instruction of which a difference between the collection time information of the previously recorded voice instruction and the collection time information of the new voice instruction is smaller than a predetermined threshold; and

use the new voice instruction and the related voice instruction as the multiple voice instructions.

11. The apparatus according to claim 9, wherein the processor is configured to:

separately determine, according to initial time stamps and end time stamps of the source voice commands corresponding to the multiple voice instructions, whether a difference of initial time stamps of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions and a difference of end time stamps of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions are both smaller than a preset threshold; and

determine that the collection time information of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions overlaps when the difference of the initial time stamps and the difference of the end time stamps are both smaller than the preset threshold.

12. The apparatus according to claim 9, Wherein the processor is configured to:

separately acquire a duration of the multiple voice instructions according to initial time stamps and end time stamps of the source voice commands corresponding to the multiple voice instructions;

determine whether the duration of the any two voice instructions in the multiple voice instructions overlaps; and

determine that the collection time of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions overlaps when the duration overlaps.

13. The apparatus according to claim 9, wherein the multiple voice instructions received by the receiver further separately carry a priority parameter of the source voice command corresponding to each voice instruction, and wherein the processor is further configured to:

determine a voice instruction with a higher priority in the two similar voice instructions and a voice instruction with a lower priority in the any two voice instructions according to the priority parameter of the source voice command corresponding to the voice instruction;

return the voice instruction with the higher priority in the two similar voice instructions to a corresponding voice control device when the any two voice instructions that are similar instructions exist in the multiple voice instructions; and

discard the voice instruction with the lower priority.

14. The apparatus according to claim 9, wherein the processor is further configured to discard the new voice instruction when a received new voice instruction and a voice instruction that has been returned to other voice control devices are similar instructions.

15. A command handling system comprising:

a voice parsing server;

multiple voice control devices; and

a command handling apparatus comprising;

a receiver configured to receive multiple voice instructions sent by the voice parsing server, where the multiple voice instructions are generated after the voice parsing server parses source voice commands that are from different voice control devices, and wherein the multiple voice instructions received by the receiver separately carry collection time information of a source voice command corresponding to each voice instruction and instruction content of each voice instruction,

a memory configured to store a program instruction;

a processor coupled to the memory and the receiver and configured to;

separately determine, according to the collection time information of the source voice commands corresponding to the multiple voice instructions, whether the collection time information of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions overlaps;

separately determine, according to the instruction content of the multiple voice instructions, whether content of the any two voice instructions in the multiple voice instructions is repeated;

determine that the any two voice instructions are similar instructions when the collection time information of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions overlaps and the content of the any two voice instructions in the multiple voice instructions is repeated, wherein the similar instructions are voice instructions corresponding to source voice commands that are obtained by the different voice control devices by collecting same voice information;

discard one voice instruction in the any two voice instructions when the any two voice instructions that are similar instructions exist in the multiple voice instructions; and

execute an operation indicated by a remaining voice instruction from the any two voice instructions,

wherein the multiple voice control devices are configured to;

separately collect multiple source voice commands; and

separately send the multiple source voice commands to the voice parsing server, and

wherein the voice parsing server is configured to;

receive the multiple source voice commands sent by the multiple voice control devices;

generate multiple voice instructions corresponding to the multiple source voice commands after parsing the multiple source voice commands; and

separately send the multiple voice instructions to the command handling apparatus.

16. The system according to claim 15, wherein the multiple voice instructions received by the receiver further separately carry a priority parameter of the source voice command corresponding to each voice instruction, and wherein the processor is further configured to:

determine a voice instruction with a higher priority in the any two similar voice instructions and a voice instruction with a lower priority in the any two similar voice instructions according to the priority parameter of the source voice command corresponding to the voice instruction;

return the voice instruction with the higher priority in the any two similar voice instructions to a corresponding voice control device when the any two voice instructions that are similar instructions exist in the multiple voice instructions; and

discard the voice instruction with the lower priority.

17. The system according to claim 15, wherein the voice parsing server is further configured to perform time synchronization with the multiple voice control devices.

18. A command handling system comprising:

a voice parsing server;

multiple voice control devices; and

a local voice control gateway comprising a command handling apparatus, wherein the command handling apparatus comprises;

a memory configured to store a program instruction;

a receiver configured to receive multiple voice instructions sent by a voice parsing server, where the multiple voice instructions are generated after the voice parsing server parses source voice commands that are from different voice control devices, and wherein the multiple voice instructions received by the receiver separately carry collection time information of a source voice command corresponding to each voice instruction and instruction content of each voice instruction; and

a processor coupled to the memory and the receiver and configured to;

separately determine, according to the collection time information of the source voice commands corresponding to the multiple voice instructions, whether the collection time information of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions overlaps;

separately determine, according to the instruction content of the multiple voice instructions, whether content of the any two voice instructions in the multiple voice instructions is repeated;

determine that the any two voice instructions are similar instructions when the collection time information of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions overlaps and the content of the any two voice instructions in the multiple voice instructions is repeated, wherein the similar instructions are voice instructions corresponding to the source voice commands that are obtained by the different voice control devices by collecting same voice information;

discard one voice instruction in the any two similar voice instructions when the any two voice instructions that are similar instructions exist in the multiple voice instructions; and

execute an operation indicated by a remaining voice instruction from the any two voice instructions,

wherein the multiple voice control devices are configured to;

separately collect multiple source voice commands; and

separately send the multiple source voice commands to the local voice control gateway, and

wherein the voice parsing server is configured to;

separately receive the multiple source voice commands sent by the local voice control gateway;

generate multiple voice instructions corresponding to the multiple source voice commands after parsing the multiple source voice commands; and

separately return the multiple voice instructions to the local voice control gateway.

19. The system according to claim 18, wherein the multiple voice instructions received by the receiver further separately carry a priority parameter of the source voice command corresponding to each voice instruction, and wherein the processor is further configured to:

determine a voice instruction with a higher priority in the any two similar voice instructions and a voice instruction with a lower priority in the any two similar voice instructions according to the priority parameter of the source voice command corresponding to the voice instruction; and

return the voice instruction with the higher priority in the any two similar voice instructions to a corresponding voice control device; and

discard the voice instruction with the lower priority when the any two voice instructions that are similar instructions exist in the multiple voice instructions.

20. The system according to claim 18, wherein the local voice control gateway is further configured to perform time synchronization with the multiple voice control devices.