Method for determining response device, device, and server

1 . A method for determining a response device, comprising:

obtaining a target probability value of a device as a response device based on a preset probability value strategy subsequent to receiving a voice control signal, the probability value strategy being determined based on response state information of the device to the voice control signal;

determining a target signal-to-noise ratio based on the target probability value and a signal-to-noise ratio of the received voice control signal; and

determining whether the device is a response device to the voice control signal based on the target signal-to-noise ratio.

2 . The method according to claim 1 , wherein:

the probability value strategy comprises a determination mode of a probability value corresponding to each time interval; and

said obtaining the target probability value of the device as the response device comprises:

obtaining reception time of the voice control signal; and

determining the target probability value based on a determination mode corresponding to a time interval in which the reception time is located.

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

calculating a similarity between a keyword in the voice control signal and a preset standard word to obtain confidence information; and

disallowing said determining whether the device is a response device to the voice control signal when the confidence information is smaller than a preset confidence threshold, the confidence threshold being determined based on the target probability value.

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

recording a number of times that the device is used as a response device to obtain response state information;

sending the response state information; and

receiving update information of a probability value strategy corresponding to the response state information.

5 . A non-transitory computer-readable storage medium, having a computer program stored thereon, wherein the computer program is executable by one or more processors to implement the method according to claim 1 .

6 . A device comprising:

a memory storing a computer program; and

one or more processors, wherein the one or more processors are configured to, when executing the computer program, implement the method according to claim 1 .

7 . A method for determining a response device, comprising:

obtaining response state information of a device to a voice control signal, the response state information comprising a number of times that the device is used as a response device;

determining a probability value strategy of the device based on the number of times in the response state information;

sending the probability value strategy to the device; and

determining, based on the probability value strategy, whether the device is the response device to the voice control signal.

8 . The method according to claim 7 , wherein the probability value strategy comprises a determination mode corresponding to each time interval, when the response state information comprises a number of times that the device is used as a response device in each time interval.

9 . The method according to claim 8 , wherein when the response state information further comprises validity information about the device being used as a response device each time, a determination mode in each time interval is determined based on a valid number of times Ti and/or an invalid number of times Fi in each time interval, i being a positive integer indicating a sequence number for the time interval.

10 . The method according to claim 9 , wherein a probability value for an i-th time interval is determined by: when the validity information is invalid, obtaining a maximum invalid number of times and/or a minimum invalid number of times from the invalid numbers of times in all time intervals, performing a calculation on the invalid number of times Fi and at least one of the maximum invalid number of times and the minimum invalid number of times to obtain a second value, and obtaining a third value as a probability value for the i-th time interval based on a difference between a preset standard value and the second value.

11 . The method according to claim 9 , wherein a probability value for an i-th time interval is determined by: when the validity information is valid, obtaining a maximum valid number of times and/or a minimum valid number of times from the valid numbers of times in all time intervals, and performing a calculation on the valid number of times Ti and at least one of the maximum valid number of times and the minimum valid number of times to obtain a first value as a probability value for the i-th time interval.

12 . The method according to claim 11 , wherein a probability value for an i-th time interval is determined by: when the validity information is invalid, obtaining a maximum invalid number of times and/or a minimum invalid number of times from the invalid numbers of times in all time intervals, performing a calculation on the invalid number of times Fi and at least one of the maximum invalid number of times and the minimum invalid number of times to obtain a second value, and obtaining a third value as a probability value for the i-th time interval based on a difference between a preset standard value and the second value.

13 . The method according to claim 12 , wherein a probability value for an i-th time interval is determined by: when one part of the validity information is valid and the other part of the validity information is invalid, determining the first value corresponding to the valid number of times for the device and the second value corresponding to the invalid number of times for the device, respectively, and obtaining a fourth value as a probability value for the i-th time interval based on a difference between the first value and the second value.

14 . The method according to claim 12 , wherein a probability value for an i-th time interval is determined by: when one part of the validity information is valid and the other part of the validity information is invalid, determining the first value corresponding to the valid number of times for the device and the second value corresponding to the invalid number of times for the device, respectively, and obtaining a fourth value as a probability value for the i-th time interval based on a difference between the first value and the second value.

15 . A non-transitory computer-readable storage medium, having a computer program stored thereon, wherein the computer program is executable by one or more processors to implement the method according to claim 7 .

16 . A server comprising:

a memory storing a computer program; and

one or more processors, wherein the one or more processors are configured to, when executing the computer program, implement the method according to claim 7 .