Method, apparatus and storage medium for wake up processing of application

1. A method for a wake-up processing of an application, comprising:

collecting a first voice data input by a user;

recognizing the first voice data;

performing a wake-up operation on a target application each time when it is recognized that a wake-up word of the target application is comprised in the first voice data, wherein the wake-up word of the target application appears more times in the first voice data;

controlling the target application to stop a voice recognition operation performed on a voice data before the wake-up word when the wake-up word is recognized the i th time in the first voice data.

2. The method according to claim 1 , wherein when the wake-up word of the target application appears more times in the first voice data, the method further comprises:

performing the wake-up operation on the target application each time when it is recognized that a partial wake-up word of the target application is comprised in the first voice data, wherein a first M words of the wake-up word with N words are set as the partial wake-up word according to parameters of a length N of the wake-up word, a content, or a user's speech rate.

3. The method according to claim 1 , wherein the method further comprises:

performing the voice recognition operation on the voice data after the wake-up word in the first voice, after performing the wake-up operation on the wake-up word which appears the i th times in the first voice data, wherein the i is a positive integer greater than or equal to 2.

4. The method according to claim 3 , wherein performing the voice recognition operation on the voice data after the wake-up word in the first voice, comprises:

sending the voice data after the wake-up word to a server, so that the server recognizes the voice data after the wake-up word.

5. The method according to claim 4 , wherein the method further comprises:

determining a starting position of the voice data after the wake-up word in the first voice as an end position of the wake-up word in the first voice data.

6. The method according to claim 5 , wherein the method further comprises:

determining the end position of the recognized wake-up word in the first voice data and a length information of the recognized wake-up word;

determining, according to the end position and the length information, a starting position of the recognized wake-up word in the first voice data;

determining the starting position as a clipped starting position.

7. The method according to claim 6 , wherein the method further comprises:

transmitting the length information and/or the recognized wake-up word to the server, wherein the length information and/or the recognized wake-up word are used to instruct the server to determine the voice data to be recognized from the first voice data.

8. The method according to claim 7 , wherein the method further comprises:

determining a weight value according to an environment information when the first voice data is collected, wherein the weight value indicates reliability of the first voice data;

sending the weight value to the server, wherein the weight value is used to instruct the server to determine whether the recognized wake-up word needs to be recognized the second time; wherein when the weight value judged in the server is greater than 50%, the server determines the recognized wake-up word does not need to be recognized the second time.

9. An apparatus for a wake-up processing of an application, comprising:

a collecting module, configured to collect a first voice data input by a user;

a recognition module, configured to recognize the first voice data;

a wake-up module, configured to perform a wake-up operation on a target application each time when it is recognized that a wake-up word of the target application is comprised in the first voice data, wherein the wake-up word of the target application appears more times in the first voice data, control the target application to stop a voice recognition operation performed on a voice data before the wake-up word when the wake-up word is recognized the i th time in the first voice data.

10. An apparatus for a wake-up processing of an application, comprises a processor and a non-transitory computer-readable medium for storing program codes, which, when executed by the processor, cause the processor to:

collect a first voice data input by a user;

recognize the first voice data;

perform a wake-up operation on a target application each time when it is recognized that a wake-up word of the target application is comprised in the first voice data, wherein the wake-up word of the target application appears more times in the first voice data;

control the target application to stop a voice recognition operation performed on a voice data before the wake-up word when the wake-up word is recognized the i th time in the first voice data.

11. The apparatus according to claim 10 , wherein when the wake-up word of the target application appears more times in the first voice data, wherein the program codes further cause the processor to:

perform the wake-up operation on the target application each time when it is recognized that a partial wake-up word of the target application is comprised in the first voice data, wherein a first M words of the wake-up word with N words are set as the partial wake-up word according to parameters of a length N of the wake-up word, a content, or a user's speech rate.

12. The apparatus according to claim 10 , wherein the program codes further cause the processor to:

perform the voice recognition operation on the voice data after the wake-up word in the first voice, after performing the wake-up operation on the wake-up word which appears the i th times in the first voice data, wherein the i is a positive integer greater than or equal to 2.

13. The apparatus according to claim 12 , wherein the program codes further cause the processor to:

send the voice data after the wake-up word to a server, so that the server recognizes the voice data after the wake-up word.

14. The apparatus according to claim 13 , wherein the program codes further cause the processor to:

determine a starting position of the voice data after the wake-up word in the first voice as an end position of the wake-up word in the first voice data.

15. The apparatus according to claim 14 , wherein the program codes further cause the processor to:

determine the end position of the recognized wake-up word in the first voice data and a length information of the recognized wake-up word;

determine, according to the end position and the length information, a starting position of the recognized wake-up word in the first voice data;

determine the starting position as a clipped starting position.

16. The apparatus according to claim 15 , wherein the program codes further cause the processor to:

transmit the length information and/or the recognized wake-up word to the server, wherein the length information and/or the recognized wake-up word are used to instruct the server to determine the voice data to be recognized from the first voice data.

17. The apparatus according to claim 16 , wherein the program codes further cause the processor to:

determine a weight value according to an environment information when the first voice data is collected, and the weight value indicates reliability of the first voice data;

send the weight value to the server, and the weight value is used to instruct the server to determine whether the recognized wake-up word needs to be recognized the second time; wherein when the weight value judged in the server is greater than 50%, the server determines the recognized wake-up word does not need to be recognized the second time.

18. A non-transitory electronic device readable storage medium, comprising: a program, when the program is running on an electronic device, causing the electronic device to perform the method according to claim 1 .