Multi-device control system and method and non-transitory computer-readable medium storing component for executing the same

1. A multi-device control method comprising:

performing a voice recognition operation on a voice command generated from a sound source;

identifying distances between each of a plurality of devices and the sound source by determining the distances based on decibel information output from each of the plurality of devices, wherein the output decibel information corresponds to a magnitude of the voice command;

correcting the distances based on a context-specific correction score of each device corresponding to the voice command, wherein the context-specific correction score is determined based on score base information related to each of the devices for the voice command, wherein the score base information comprises always-on characteristic information, device on/off information, device control state information, user usage pattern information for a device, and usage environment information;

assigning response rankings to the devices by combining the context-specific correction score of each device corresponding to the voice command and the corrected distances, wherein the corrected distances are compared among each other such that devices with smaller corrected distances are ranked with a higher response ranking; and

selecting a device to respond to the voice command from among the devices according to the response rankings.

2. The method of claim 1 , wherein identifying the distances between each of the plurality of devices and the sound source comprises:

identifying a voice signal metric value received from each of the plurality of devices, wherein the distances are determined based on the voice signal metric values.

3. The method of claim 2 , wherein the voice signal metric values comprise a signal-to-noise ratio, a voice spectrum, and a voice energy for the voice command.

4. The method of claim 1 , wherein the context-specific correction score of each device corresponding to the voice command is defined in a database.

5. The method of claim 1 , wherein the context-specific correction score of each device corresponding to the voice command is updated according to a specific voice command and a device context.

6. The method of claim 4 , wherein the database is constructed through a deep learning-based base learning model.

7. The method of claim 5 , wherein the context-specific correction score of each device corresponding to the voice command is updated through an artificial intelligent (AI) agent training module according to a specific voice command and a device context.