US 12,379,729 B2
Machine-learning-driven supply chain out-of-stock inventory resolution and contract negotiation
Charles H. Cella, Pembroke, MA (US); Andrew Cardno, San Diego, CA (US); Jenna Parenti, Denver, CO (US); Andrew S. Locke, Farmington, MI (US); Brad Kell, Seattle, WA (US); Teymour S. El-Tahry, Detroit, MI (US); Leon Fortin, Jr., Providence, RI (US); Andrew Bunin, Lakewood Ranch, FL (US); Kunal Sharma, Mumbai (IN); Taylor Charon, Troy, MI (US); Hristo Malchev, Alta Loma, CA (US); Eric P. Vetter, Cary, NC (US); David Stein, Fairfax, VA (US); and Benjamin D. Goodman, Los Angeles, CA (US)
Assigned to STRONG FORCE VCN PORTFOLIO 2019, LLC, Fort Lauderdale, FL (US)
Filed by Strong Force VCN Portfolio 2019, LLC, Fort Lauderdale, FL (US)
Filed on Nov. 30, 2023, as Appl. No. 18/525,816.
Application 18/525,816 is a continuation of application No. PCT/US2023/036158, filed on Oct. 27, 2023.
Claims priority of provisional application 63/381,545, filed on Oct. 28, 2022.
Prior Publication US 2024/0144139 A1, May 2, 2024
Int. Cl. G06N 20/00 (2019.01); G05B 19/4155 (2006.01); G05D 1/00 (2024.01); G05D 1/223 (2024.01); G06N 3/08 (2023.01); G06Q 10/06 (2023.01); G06Q 10/0635 (2023.01); G06Q 10/0637 (2023.01); G06Q 10/0833 (2023.01); G06Q 10/087 (2023.01)
CPC G05D 1/0297 (2013.01) [G05B 19/4155 (2013.01); G05D 1/223 (2024.01); G06N 3/08 (2013.01); G06N 20/00 (2019.01); G06Q 10/06 (2013.01); G06Q 10/0635 (2013.01); G06Q 10/06375 (2013.01); G06Q 10/0833 (2013.01); G06Q 10/087 (2013.01); G05B 2219/50391 (2013.01)] 24 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving, by a computing device, information associated with a set of value chain network entities of a value chain network,
wherein the set of value chain network entities includes a product and at least one of: a warehouse, a distribution center, a fulfillment center, a hauling facility, or a port infrastructure facility,
wherein the information is generated by a set of sensors of the set of value chain network entities, and
wherein the information includes past behavior data, historical data, and current data for the set of value chain network entities;
providing, by the computing device, the information to a set of machine learning models,
wherein the set of machine learning models includes a modular neural network,
wherein the modular neural network includes a set of independent neural networks moderated by an intermediary, and
wherein each neural network of the set of independent neural networks is associated with a respective value chain network entity of the set of value chain network entities;
training the set of machine learning models to create a trained set of machine learning models by training, by the computing device, each machine learning model of the set of machine learning models on a training data set including the past behavior data and the historical data of a respective value chain network entity for pattern recognition,
wherein the pattern recognition includes recognizing a condition or a state of the respective value chain network entity, and
wherein the trained set of machine learning models is executed by the computing device;
determining, by the trained set of machine learning models, a first set of data types that is present in the information;
determining, by the trained set of machine learning models, a second set of data types to use in a digital twin simulation;
selecting a portion of the information based on the first and second sets of data types;
generating, by the trained set of machine learning models, simulation data based on the selected portion of the information;
executing, by a value chain network digital twin, the digital twin simulation using the simulation data to generate a prediction associated with a disruption or a risk in the value chain network, wherein the value chain network digital twin is executed by the computing device;
determining, by the computing device, a procurement action to resolve an out-of-stock situation of the product based on the prediction;
in response to the generating the prediction and the determining the procurement action, automatically generating, by the computing device, a notification, wherein the notification includes data associated with the prediction and data associated with the procurement action;
transmitting, by the computing device, the notification to a user device of a specified user;
receiving, at the computing device, feedback associated with the notification from the user device; and
in response to receiving the feedback:
refining, by the computing device, at least one machine learning model of the set of machine learning models based on the feedback; and
executing the procurement action by:
automatically generating, by the computing device, a suggestion on a user interface to negotiate a contract with a supplier identified as possessing the product; and
in response to executing the contract, automatically building an inventory buffer of the product, wherein automatically building the inventory buffer includes:
providing, by the computing device, an instruction for executing a task to a smart machine;
in response to receiving the instruction, transporting, by the smart machine, a set of additional products to at least one entity of the set of value chain network entities;
gathering, by the smart machine, real-time data associated with the execution of the task;
providing, by the smart machine, the real-time data to the computing device; and
updating, by the computing device, the value chain network digital twin based on the real-time data.