US 12,254,868 B2
Method and system for smart interaction in a multi voice capable device environment
Vishal Shashikant Patil, Bengaluru (IN); Gulprit Singh, Bengaluru (IN); and Rajeev Gupta, Mumbai (IN)
Assigned to JIO PLATFORMS LIMITED, Ahmedabad (IN)
Filed by JIO PLATFORMS LIMITED, Ahmedabad (IN)
Filed on Jun. 1, 2021, as Appl. No. 17/335,786.
Claims priority of application No. 202021022821 (IN), filed on May 31, 2020.
Prior Publication US 2021/0375267 A1, Dec. 2, 2021
Int. Cl. G10L 15/07 (2013.01); G10L 15/22 (2006.01); G10L 15/34 (2013.01)
CPC G10L 15/07 (2013.01) [G10L 15/22 (2013.01); G10L 15/34 (2013.01); G10L 2015/223 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A method for providing a custom response to a voice command of a specific user, the method comprising:
receiving, at a transceiver of a cloud server from a user device, a custom voice response preference setting associated with the specific user;
receiving, at the transceiver of the cloud server, a voice command trigger from the specific user through one or more voice capable devices present in a vicinity of the specific user;
identifying, by a processor of the cloud server, a first target device, from the one or more voice capable devices present in the vicinity of the specific user to continue receiving voice commands from the specific user, wherein the first target device is identified based on at least one of a real time global positioning system (GPS) location data associated with the one or more voice capable devices, a device identification (ID) of the one or more voice capable devices, a voice command trigger timestamp associated with the one or more voice capable devices, a signal to noise ratio (SNR) associated with the one or more voice capable devices, and a Quality parameter (QoS) associated with the one or more voice capable devices;
in response to receiving the voice commands, generating, by the processor of the cloud server, a custom response to the voice commands of the specific user based at least on the custom voice response preference setting associated with said specific user, wherein the custom voice response preference setting comprises a customized voice identity, including a specific user preferred voice type and a specific user preferred voice age, and predicting, by the processor of the cloud server, a likelihood that the voice command of the specific user will evolve into a conversation mode, wherein the prediction is based on at least previous contextual information of the specific user;
identifying, by the processor of the cloud server, based on the predicted likelihood, a second target device to transmit the generated custom response including the specific user preferred voice type and the specific user preferred voice age to the second target device; and
providing the generated custom response including the specific user preferred voice type and the specific user preferred voice age to the specific user via the identified second target device.