US 12,455,906 B2
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 Oct. 18, 2024, as Appl. No. 18/920,538.
Application 18/920,538 is a continuation of application No. 18/526,944, filed on Dec. 1, 2023, granted, now 12,124,486.
Application 18/526,944 is a continuation of application No. 18/175,205, filed on Feb. 27, 2023, granted, now 11,836,168, issued on Dec. 5, 2023.
Prior Publication US 2025/0045307 A1, Feb. 6, 2025
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/00 (2019.01); G06F 11/34 (2006.01); G06F 16/332 (2019.01); G06F 16/3329 (2025.01); 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)] 18 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;
determining, at the Application Programming Interface endpoint layer, a first database request based on the dynamic human-like conversational request;
retrieving a threshold requirement, wherein the threshold requirement is used to determine whether to process received database requests;
comparing the threshold requirement to the first database request;
in response to determining that the first database request corresponds to the threshold requirement, 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;
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 and a second feature input for the second data model based on the second portion;
inputting the first feature input into the first data model and the second feature input into the second data model to generate a first data model output and a second data model output;
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 the gating network;
selecting, based on the one or more parameters, the first data model output or the second data model output for inputting into the gating network to generate a gating network output;
determining, based on the gating network output, the database query; and
generating a dynamic human-like conversational response based on the database query.