US 12,147,926 B2
Orchestrated intelligent supply chain optimizer
David Michael Evans, Welwyn Garden City (GB); and Robert Derward Rogers, Oakland, CA (US)
Assigned to Oii, Inc., Oakland, CA (US)
Filed by Oii, Inc., Oakland, CA (US)
Filed on Apr. 12, 2022, as Appl. No. 17/719,195.
Application 17/719,195 is a continuation of application No. 17/102,103, filed on Nov. 23, 2020.
Claims priority of provisional application 63/174,948, filed on Apr. 14, 2021.
Claims priority of provisional application 63/089,542, filed on Oct. 8, 2020.
Claims priority of provisional application 62/940,014, filed on Nov. 25, 2019.
Prior Publication US 2022/0309436 A1, Sep. 29, 2022
Int. Cl. G06Q 10/06 (2023.01); G06Q 10/0631 (2023.01); G06Q 10/0637 (2023.01); G06Q 10/0639 (2023.01)
CPC G06Q 10/06375 (2013.01) [G06Q 10/06315 (2013.01); G06Q 10/0639 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An orchestrated intelligent supply chain optimizer comprising:
a data management interface for configuring connections to data from a customer enterprise data system (EDS), wherein the customer data is received in at least one of a asynchronous process and a synchronous process;
a parameter and model archive database for storing the customer data;
an optimization server for training an AI model based upon an input feature vector and a set of supply chain network attributes from the customer data to predict future performance, and for generating a series of heatmaps for each node of a supply chain, wherein each heatmap compares reorder frequency charted against safety stock levels for a key metric subject to constraints overlay, wherein supply chain optimization results are calculated as the intersection of the safety stock levels and the reorder frequency that results in an optimization of the key metric while adhering to the constraints overlay, wherein the optimization includes millions of solution options for a given organization by simulating an ensemble of future behaviors using the trained AI model in view of item specific information and compute estimates with confidence levels of future outcomes based upon the ensembles using the trained AI model, and presenting the supply chain optimization results to at least one planner, wherein machine learning or AI models are used to recommend contents and display parameters of the supply chain optimization results based on the customer data retrieved from the data management module and the parameter and model archive;
a data importer including a) an item parameter data collector for collecting in real-time the item specific information from a plurality of monitors, including current safety stock levels, delivery frequency and order multiples, and b) a transmitter for transmitting the collected item parameter data to the optimization server; and
a user feedback interface for receiving the supply chain optimization results from the optimization module to and for conditioning the results for optimal usefulness and impact.