	US 12,243,555 B2
	System and method for determining and processing user temperament
Barath Jayaraman, Fort Mill, SC (US)
Assigned to TRUIST BANK, Charlotte, NC (US)
Filed by Truist Bank, Charlotte, NC (US)
Filed on Oct. 19, 2022, as Appl. No. 18/047,767.
Prior Publication US 2024/0135957 A1, Apr. 25, 2024 Prior Publication US 2024/0233749 A9, Jul. 11, 2024
Int. Cl. H04M 3/58 (2006.01); G10L 25/63 (2013.01); H04M 3/22 (2006.01)

CPC G10L 25/63 (2013.01) [H04M 3/2281 (2013.01); H04M 3/58 (2013.01)]

16 Claims

1. A system for determining user temperament comprising:

at least one processor;

a communication interface communicatively coupled to the at least one processor; and

a memory device storing executable code that, when executed, causes the at least one processor to:

(a′) train an algorithm, via machine learning and using a set of training data, the algorithm configured to determine user temperament, the training comprising:

(i) iteratively predicting a ranking of the user temperament, based on the set of training data, the set of training data comprising volume data, content data, inflection data, and pitch data;

(ii) testing and comparing the ranking of the user temperament predicted during each iteration against a target variable; and

(iii) indicating, via a feedback loop, for each iteration whether modifications to weights assigned to certain training data are necessary to improve predictability of the ranking of the user temperament:

(a) receive an incoming call from a user;

(b) receive audible language from the user;

(d) input the volume, the content, the inflection, and the pitch of step (c), into the algorithm;

(e) receive an output, from the algorithm of step (d), wherein the output comprises a ranking of the temperament of the user;

(f) transfer the incoming call of step (a) to an entity representative, and

(g) relay the ranking of the temperament of the user, from step (e), to the entity representative.