Command Handling Method, Apparatus, and System

• US 20150039319A1
• Filed: 10/22/2014
• Published: 02/05/2015
• 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: Xue, Guodong, Mei, Jingqing
• Granted Patent: US 9,704,503 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• 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;

separately determining whether any two voice instructions in the multiple voice instructions are similar instructions, wherein the similar instructions are voice instructions corresponding to source voice commands obtained by the different voice control devices by collecting same voice information; and

discarding, when two voice instructions that are similar instructions exist in the multiple voice instructions, one voice instruction in the two similar voice instructions.

2. The method according to claim 1, 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, and wherein separately determining whether any two voice instructions in the multiple voice instructions are similar instructions comprises:

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

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

determining that the two voice instructions are similar instructions when the collection time 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.

3. The method according to claim 2 further comprising:

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

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

determining a related voice instruction of which a difference between the collection time and the collection time 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.

4. The method according to claim 2, wherein separately determining, according to collection time information of source voice commands corresponding to the multiple voice instructions, whether collection time of 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, when the difference of the initial time stamps and the difference of the end time stamps are both smaller than the preset threshold, that the collection time of the source voice commands corresponding to the any two voice instructions in the multiple voice instructions overlaps.

5. The method according to claim 2, wherein separately determining, according to collection time information of source voice commands corresponding to the multiple voice instructions, whether collection time of source voice commands corresponding to the any two voice instructions in the multiple voice instructions overlaps, comprises:

separately acquiring 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 duration of the any two voice instructions in the multiple voice instructions overlaps; and

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

6. 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 two similar voice instructions and a voice instruction with a lower priority in the two similar voice instructions according to the priority parameter of the source voice command corresponding to the voice instruction, and wherein discarding, when two voice instructions that are similar instructions exist in the multiple voice instructions, one voice instruction in the two similar 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 two voice instructions that are the similar instructions exist in the multiple voice instructions; and

discarding the voice instruction with the lower priority.

7. The method according to claim 6 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.

8. 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.

9. The method according to claim 1 further comprising:

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

separately receiving, by the local voice control gateway, the source voice commands sent by the voice control devices and sending the source voice commands to the voice parsing server.

10. A command handling apparatus comprising:

a memory;

a receiver; and

a processor, wherein the receiver is 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, wherein the memory is configured to store a program instruction, coupled with the memory and the receiver, and wherein the processor is configured to;

separately determine, according to the program instruction in the memory, whether any two voice instructions in the multiple voice instructions received by the receiver 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

discard one voice instruction in the two similar voice instructions when two voice instructions that are similar instructions exist in the multiple voice instructions.

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

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

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

determine that the two voice instructions are similar instructions when the collection time 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.

12. The apparatus according to claim 11, 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 collection time of the new voice instruction with collection time of a previously recorded voice instruction;

determine a related voice instruction of which a difference between the collection time and the collection time 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.

13. The apparatus according to claim 11, 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 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.

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

separately acquire 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 duration of the any two voice instructions in the multiple voice instructions overlaps; and

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

15. The apparatus according to claim 10, 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 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 two similar voice instructions to a corresponding voice control device when two voice instructions that are similar instructions exist in the multiple voice instructions; and

discard the voice instruction with the lower priority.

16. The apparatus according to claim 10, 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.

17. A command handling system comprising:

a voice parsing server;

multiple voice control devices; and

a command handling apparatus comprising a memory, a receiver, and a processor, wherein the receiver is 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, wherein the memory is configured to store a program instruction, coupled with the memory and the receiver, wherein the processor is configured to;

separately determine, according to the program instruction in the memory, whether any two voice instructions in the multiple voice instructions received by the receiver 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

discard one voice instruction in the two similar voice instructions when two voice instructions that are similar instructions exist in the multiple 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.

18. The system according to claim 17, 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 wherein the processor is configured to:

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

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

determine that the two voice instructions are similar instructions when the collection time 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.

19. The system according to claim 17, 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 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 two similar voice instructions to a corresponding voice control device when two voice instructions that are similar instructions exist in the multiple voice instructions; and

discard the voice instruction with the lower priority.

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

21. 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, a receiver, and a processor, wherein the receiver is 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, wherein the memory is configured to store a program instruction, coupled with the memory and the receiver, wherein the processor is configured to;

separately determine, according to the program instruction in the memory, whether any two voice instructions in the multiple voice instructions received by the receiver 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

discard one voice instruction in the two similar voice instructions when two voice instructions that are similar instructions exist in the multiple 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.

22. The system according to claim 21, 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 wherein the processor is configured to:

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

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

determine that the two voice instructions are similar instructions when the collection time 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.

23. The system according to claim 21, 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 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 two similar voice instructions to a corresponding voice control device, and discard the voice instruction with the lower priority when two voice instructions that are similar instructions exist in the multiple voice instructions.

24. The system according to claim 21, wherein the local voice control gateway is further configured to perform time synchronization with the multiple voice control devices.