Wake-up method and apparatus for smart device, storage medium, and electronic device

A wake-up apparatus for a smart device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to:

• select, from a plurality of smart devices, at least one smart device that is allowed to be awakened by a wake-up signal as at least one candidate device among multiple candidate devices, wherein the plurality of smart devices are devices that detect the wake-up signal in a target scenario;
• determine a target wake-up angle and target wake-up energy corresponding to each of the multiple candidate devices, wherein the target wake-up angle corresponding to the candidate device is used for indicating a direction of a sound source position of the wake-up signal relative to the candidate device, the target wake-up energy corresponding to the candidate device is used for indicating energy received by the candidate device from the wake-up signal, and the processor, when configured to determine the target wake-up angle corresponding to each of the multiple candidate devices, is configured to:
• construct a search function for a wake-up angle variable of each of the multiple candidate devices based on the wake-up signal and the wake-up angle variable of each of the multiple candidate devices;
• and perform an optimization search on the search function to obtain an optimal solution of the wake-up angle variable of each of the multiple candidate devices as the target wake-up angle corresponding to each of the multiple candidate devices, wherein the processor, when configured to construct a search function for a wake-up angle variable of each of the multiple candidate devices based on the wake-up signal and the wake-up angle variable of each of the multiple candidate devices, is configured to:
• construct a covariance matrix of the wake-up angle variable of each of the multiple candidate devices based on the wake-up signal;
• construct a directional derivative for the wake-up angle variable of each of the multiple candidate devices based on the wake-up angle variable of each of the multiple candidate devices;
• and construct, based on the covariance matrix and the directional derivative, a maximum likelihood function for the wake-up angle variable of each of the multiple candidate devices as the search function, wherein the maximum likelihood function for the wake-up angle variable is Aml(θ)=Σf=flfhRxx(f)*PA(θ,f), wherein PA(θ,f) is the direction derivative of the wake-up angle variable;
• Rxx(f) is the covariance matrix;
• and
• determine a target device from the multiple candidate devices according to the target wake-up angle and the target wake-up energy, wherein the target device is used for responding to the wake-up signal.

A non-transitory computer-readable storage medium, wherein the computer-readable storage medium stores a program, and the program, when running on a processor, causes the processor to execute following operations:

• selecting, from a plurality of smart devices, at least one smart device that is allowed to be awakened by a wake-up signal as at least one candidate device among multiple candidate devices, wherein the plurality of smart devices are devices that detect the wake-up signal in a target scenario;
• determining a target wake-up angle and target wake-up energy corresponding to each of the multiple candidate devices, wherein the target wake-up angle corresponding to the candidate device is used for indicating a direction of a sound source position of the wake-up signal relative to the candidate device, the target wake-up energy corresponding to the candidate device is used for indicating energy received by the candidate device from the wake-up signal, and determining the target wake-up angle corresponding to each of the multiple candidate devices comprises:
• constructing a search function for a wake-up angle variable of each of the multiple candidate devices based on the wake-up signal and the wake-up angle variable of each of the multiple candidate devices;
• and performing an optimization search on the search function to obtain an optimal solution for the wake-up angle variable of each of the multiple candidate devices as the target wake-up angle corresponding to each of the multiple candidate devices, wherein constructing the search function for the wake-up angle variable of each of the multiple candidate devices based on the wake-up signal and the wake-up angle variable of each of the multiple candidate devices comprises:
• constructing a covariance matrix of the wake-up angle variable of each of the multiple candidate devices based on the wake-up signal;
• constructing a directional derivative for the wake-up angle variable of each of the multiple candidate devices based on the wake-up angle variable of each of the multiple candidate devices;
• and constructing, based on the covariance matrix and the directional derivative, a maximum likelihood function for the wake-up angle variable of each of the multiple candidate devices as the search function, wherein the maximum likelihood function for the wake-up angle variable is Aml(θ)=Σf=flfhRxx(f)*PA(θ,f), wherein PA(θ,f) is the direction derivative of the wake-up angle variable;
• Rxx(f) is the covariance matrix;
• and
• determining a target device from the multiple candidate devices according to the target wake-up angle and the target wake-up energy, wherein the target device is used for responding to the wake-up signal.