公开(公告)号：US20230368048A1

公开(公告)日：2023-11-16

申请号：US17741748

申请日：2022-05-11

Applicant: The Toronto-Dominion Bank

Inventor： Dan Ni Yang ,  Méliné Nikoghossian ,  Elham Hajarian ,  Behjat Soltanifar ,  Karishma Harshal Patel

IPC: G06N5/04 ,  G06F16/22

CPC classification number: G06N5/04 ,  G06F16/221

Abstract: Systems and methods for optimizing multi-stage data machine learning model processing, by providing an intermediate processing step to identify or filter records in voluminous inference data that meet a predetermined threshold. Multiple downstream processes can be optimized by applying multiple thresholds to the voluminous inference data.

公开(公告)号：US20230401192A1

公开(公告)日：2023-12-14

申请号：US17838539

申请日：2022-06-13

Applicant: The Toronto-Dominion Bank

Inventor： Dan Ni Yang ,  Méliné Nikoghossian ,  Elham Hajarian ,  Behjat Soltanifar ,  Karishma Harshal Patel

IPC: G06F16/22 ,  G06F16/27 ,  G06F16/21 ,  G06F16/25 ,  G06N20/00

CPC classification number: G06F16/2282 ,  G06F16/27 ,  G06F16/21 ,  G06F16/252 ,  G06N20/00

Abstract: Systems and methods for preprocessing large inference files in a cluster environment prior to transmission to one or more downstream applications. The inference files are processed using templates that correspond to particular downstream applications, allowing for optimized transmission and optimized processing by each downstream application.