Machine-learning-driven supply chain out-of-stock inventory resolution and contract negotiation

Patent metadata

Field	Value
Publication number	US-12379729-B2
Application number	US-202318525816-A
Country	US
Kind code	B2
Filing date	Nov 30, 2023
Priority date	Nov 5, 2019
Publication date	Aug 5, 2025
Grant date	Aug 5, 2025

Abstract

A VCN process may receive, by a computing device, information associated with a set of value chain network entities of a value chain network, the information generated by at least one of: a set of sensors of the set of value chain network entities, a set of IoT devices configured to collect data relating to the set of value chain network entities, or a set of APIs configured to publish data relating to the set of value chain network entities. A VCN process may provide the information to a set of Artificial Intelligence (AI)-based learning models. A VCN process may determine a procurement action to be taken in the value chain network based upon, at least in part, an output of the set of AI-based learning models. A VCN process may execute the procurement action.

First claim

What is claimed is:

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.

2. The computer-implemented method of claim 1 , further comprising:
providing an alert describing the procurement action that was executed,
wherein the alert includes (i) information that was used to determine the procurement action and (ii) an intended result of executing the procurement action.

3. The computer-implemented method of claim 1 , further comprising providing real-time information on supplier performance.

4. The computer-implemented method of claim 1 , further comprising monitoring for compliance of suppliers and procurement teams.

5. The computer-implemented method of claim 1 , further comprising automatically generating purchase orders associated with the procurement action.

6. The computer-implemented method of claim 1 , further comprising automatically performing invoice processing associated with the procurement action.

7. The computer-implemented method of claim 1 , further comprising unifying data associated with warehouse management, inventory management, order management, and analytics to optimize an omnichannel fulfillment.

8. The computer-implemented method of claim 1 , wherein executing the procurement action includes predicting when to place an order based upon, at least in part, upstream data.

9. The computer-implemented method of claim 1 , wherein the set of value chain network entities includes at least one of: suppliers, producers, manufacturers, retailers, businesses, owners, operators, operating facilities, customers, consumers, workers, mobile devices, wearable devices, distributors, resellers, supply chain infrastructure facilities, supply chain processes, logistics processes, reverse logistics processes, demand prediction processes, demand management processes, demand aggregation processes, machines, ships, barges, maritime ports, airports, airways, waterways, roadways, railways, bridges, tunnels, online retailers, ecommerce sites, demand factors, supply factors, delivery systems, floating assets, points of origin, points of destination, points of storage, points of use, networks, information technology systems, software platforms, containers, container handling facilities, customs, export control, border control, drones, robots, robotic handling systems, 3D printers, vehicles, autonomous vehicles, or waterways.

10. The computer-implemented method of claim 1 ,
wherein the training data set includes a set of objects or events that is labeled according to a classification taxonomy, and
wherein the classification taxonomy includes at least one of: an operating state, a fault condition, an operating flow, or a behavior of at least one value chain network entity of the set of value chain network entities.

11. The computer-implemented method of claim 1 , wherein the procurement action is executed by a value chain network digital twin.

12. The computer-implemented method of claim 1 , further comprising:
automatically notifying, by the computing device, a customer about a potential for a delay of the product and a backordering option for the product.

13. The computer-implemented method of claim 1 , wherein the first set of data types includes at least one of temperature sensor data, wear sensor data, light sensor data, vibration sensor data, or humidity sensor data.

14. A computing system comprising one or more processors and one or more memories configured to perform operations including:
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 pr

Assignees

• Strong Force Vcn Portfolio 2019 Llc

Inventors

• Cella Charles H
• Cardno Andrew
• Parenti Jenna
• Locke Andrew S
• Kell Brad
• El-Tahry Teymour S
• Fortin Jr Leon
• Bunin Andrew
• Sharma Kunal
• Charon Taylor
• Malchev Hristo
• Vetter Eric P
• Stein David
• Goodman Benjamin D

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06Q2220/00

  Business processing using cryptography · CPC title

• G06Q50/04

  Manufacturing · CPC title

• G06Q30/0202

  Market predictions or forecasting for commercial activities · CPC title