US 12,462,208 B2
Risk probability assessment for cargo shipment operations and methods of use thereof
Chris Kalinski, Oxford, MD (US)
Assigned to Redkik, LLC, Oxford, MD (US)
Filed by Redkik, LLC, Oxford, MD (US)
Filed on Aug. 22, 2023, as Appl. No. 18/236,872.
Application 18/236,872 is a continuation of application No. 17/738,396, filed on May 6, 2022, granted, now 11,734,634.
Claims priority of provisional application 63/185,593, filed on May 7, 2021.
Prior Publication US 2023/0394411 A1, Dec. 7, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 10/00 (2023.01); G06F 18/00 (2023.01); G06F 18/21 (2023.01); G06F 18/2415 (2023.01); G06N 20/00 (2019.01); G06Q 10/0635 (2023.01); G06Q 10/083 (2023.01)
CPC G06Q 10/0635 (2013.01) [G06F 18/2193 (2023.01); G06F 18/2415 (2023.01); G06N 20/00 (2019.01); G06Q 10/083 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving, by a processor, a plurality of policy parameters associated with a provider of a plurality of providers from a plurality of pre-generated databases;
dynamically enriching, by the processor, input data associated with the plurality of policy parameters and a plurality of identified data records,
wherein enriched input data is utilized to train a machine learning model associated with the identified data record;
training, by the processor, a machine learning model with at least one data feedback loop by introducing training data as a plurality of variables to generate a first plurality of scenarios in real-time,
dynamically simulating, by the processor, the first plurality of scenarios in real time to optimize a first respective dynamic probability risk value generated by a respective dynamic data model using the trained machine learning model;
automatically updating, by the processor, the at least one feedback loop associated with the trained machine learning model;
dynamically generating, by the processor, a second plurality of scenarios in real-time based on the at least one feedback loop associated with the trained machine learning model;
dynamically determining, by the processor, a predetermined policy risk threshold for the identified data record based on the second plurality of scenarios; and
automatically modifying, by the processor, the predetermined policy risk threshold associated with a qualified provider of the plurality of providers based on a respective model risk probability value to generate a modified policy risk threshold associated with the identified data record.