US 12,254,486 B1
Interactive voice capabilities for prospect digital acquisition
Neha Arya, New York, NY (US); Xiangzhen Kong, Hoboken, NJ (US); Hemalatha Krishnamurthy, Phoenix, AZ (US); Venkatesh Nagarajan, Scottsdale, AZ (US); Andy Ruan, San Francisco, CA (US); Robert Santoro, Phoenix, AZ (US); and Maheshwar Singh, Phoenix, AZ (US)
Assigned to AMERICAN EXPRESS TRAVEL RELATED SERVICES COMPANY, INC., New York, NY (US)
Filed by American Express Travel Related Services Company, Inc., New York, NY (US)
Filed on Dec. 30, 2021, as Appl. No. 17/646,494.
Int. Cl. G06Q 30/0207 (2023.01); G10L 15/22 (2006.01); G10L 15/30 (2013.01)
CPC G06Q 30/0236 (2013.01) [G10L 15/22 (2013.01); G10L 15/30 (2013.01); G10L 2015/223 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, via at least one computing device associated with an assistant web service, a first utterance from a voice-enabled service, the first utterance comprising a command and the first utterance being associated with a voice-enabled application identifier;
querying, via the at least one computing device associated with the assistant web service, a dialogue model associated with the voice-enabled service to determine an audio prompt for requesting personal information of a user based at least in part on the command and the voice-enabled application identifier, the dialogue model being associated with the voice-enabled application identifier and comprising a dialogue template for identifying the audio prompt based at least in part on the first utterance, the audio prompt being in an audio format associated with the dialogue template;
transmitting, via at least one computing device associated with the assistant web service, the audio prompt for playback to the voice-enabled service, the audio prompt comprising a request for the personal information of the user;
receiving, via the at least one computing device, a second utterance from the voice-enabled service, the second utterance comprising the personal information;
authenticating, via the at least one computing device, the second utterance for a user account based at least in part on a comparison between the second utterance and a verified utterance stored in association with the user account, the comparison comprising an extraction of vocal characteristics from the second utterance;
verifying, via the at least one computing device, the second utterance includes the personal information required for a content request associated with opening a transaction account based at least in part on the dialogue model associated with the voice-enabled application identifier;
generating, via the at least one computing device, the content request for opening the transaction account by modifying data elements associated with the personal information to comply with a format associated with a transact account service;
transmitting, via the at least one computing device, the content request for opening the transaction account to a computing environment associated with a transaction account service based at least in part on the authentication of the second utterance, the content request comprising the personal information;
receiving, via the at least one computing device, content for opening the transaction account from the computing environment, the content being selected based at least in part on a credit profile associated with the personal information;
generating, via the at least one computing device, audio content for playback in the audio format of the dialogue model based at least in part on the content received from the computing environment; and
transmitting, via the at least one computing device, the audio content for playback to the voice-enabled service.