US 11,836,168 B1
Systems and methods for generating dynamic human-like conversational responses using a modular architecture featuring layered data models in non-serial arrangements with gated neural networks
Joenteny David Martinez Gutierrez, Clute, TX (US)
Assigned to Citibank, N.A., New York, NY (US)
Filed by Citibank, N.A., New York, NY (US)
Filed on Feb. 27, 2023, as Appl. No. 18/175,205.
Int. Cl. G06F 16/00 (2019.01); G06F 16/332 (2019.01); G06F 11/34 (2006.01); G06F 40/40 (2020.01)
CPC G06F 16/3325 (2019.01) [G06F 11/3409 (2013.01); G06F 16/3329 (2019.01); G06F 40/40 (2020.01)] 16 Claims
OG exemplary drawing
 
1. A system for generating dynamic human-like conversational responses using layered data models with gated neural networks, the system comprising:
one or more processors; and
a non-transitory computer-readable media comprising of instructions that, when executed by the one or more processors, cause operations comprising:
receiving, at an Application Programming Interface endpoint layer, a dynamic human-like conversational request for a database query, wherein the dynamic human-like conversational request comprises an input to a chatbot application;
determining, at the Application Programming Interface endpoint layer, a database request for the database query based on the dynamic human-like conversational request;
comparing a threshold requirement for database requests to the database request;
in response to comparing the threshold requirement for database requests to the database request, determining that the database request corresponds to the threshold requirement for database requests;
in response to determining that the database request corresponds to the threshold requirement for database requests, processing the database request by:
receiving a first portion of non-normalized source layer data for a first data model, wherein the first data model comprises an aggregated subset of additional data models;
receiving a second portion of the non-normalized source layer data for a second data model, wherein the second data model is trained on a first set of training data;
receiving a third portion of the non-normalized source layer data for a third data model, wherein the third data model is trained on a second set of training data;
determining, by processing each respective portion through a first normalization layer, a first feature input for the first data model based on the first portion, a second feature input for the second data model based on the second portion, and a third feature input for the third data model based on the third portion;
inputting the first feature input into the first data model, the second feature input into the second data model, and the third feature input into the third data model to generate a respective outputs;
retrieving a first configuration file for a gating network from a first configuration layer, wherein the first configuration file defines one or more parameters for normalizing the gating network;
inputting the respective outputs into the gating network to generate a normalized gating network output based on the one or more parameters;
determining, based on the normalized gating network output, the database query; and
generating a dynamic human-like conversational response based on the database query, wherein the dynamic human-like conversational response comprises an output from the chatbot application.