US 11,902,469 B1
Method for managing call queues for recurring customer questions
Rudolph L. Mappus, IV, Plano, TX (US); Sri Harsha Pothukuchi, Brambleton, VA (US); Angel Vincent, Milford, OH (US); Peter Kutchen, Bear, DE (US); Owen Churchill, Columbus, OH (US); and Jose Burgos, Dallas, TX (US)
Assigned to JPMORGAN CHASE BANK, N.A., New York, NY (US)
Filed by JPMorgan Chase Bank, N.A., New York, NY (US)
Filed on Sep. 1, 2022, as Appl. No. 17/901,036.
Int. Cl. H04M 3/523 (2006.01); H04M 3/51 (2006.01); G10L 15/18 (2013.01); G10L 15/187 (2013.01)
CPC H04M 3/5235 (2013.01) [G10L 15/187 (2013.01)] 13 Claims
OG exemplary drawing
 
1. A method for handling a telephone call, the method being implemented by at least one processor, the method comprising:
receiving, by the at least one processor, a first incoming telephone call from a person;
capturing, by the at least one processor from the first incoming telephone call, an audio signal that corresponds to a voice of the person;
analyzing, by the at least one processor, the captured audio signal; and
determining, by the at least one processor based on a result of the analyzing, whether an inquiry articulated by the person during the first incoming telephone call has been adequately addressed,
wherein the analyzing of the captured audio signal comprises detecting at least one phonetic intonation included in the audio signal and applying at least one digital filter to the at least one phonetic intonation, and
wherein the determining comprises using a result of the applying of the at least one digital filter to the at least one phonetic intonation to determine when the at least one phonetic intonation corresponds to a statement being made by the person and to determine when the at least one phonetic intonation corresponds to a question being asked by the person, and
wherein the method further comprises:
obtaining call data that relates to the first incoming telephone call; and
executing a first artificial intelligence (AI) algorithm that implements a machine learning technique and uses the result of the applying of the at least one digital filter to the at least one phonetic intonation and the obtained call data as inputs in order to generate an output that indicates a sentiment of the person.