US-20260127538-A1 - SYSTEM AND METHODS FOR GOVERNED AGENTIC AI PLATFORM WITH PREDICTION-EVENT LINEAGE AND DIGITAL-TWIN SIMULATION

US20260127538A1US 20260127538 A1US20260127538 A1US 20260127538A1US-20260127538-A1

Abstract

A management system is provided having a digital twin layer, data integration layer, artificial intelligence (AI) and cognitive processing layer, and an extensibility and customization layer, operatively coupled with processing circuitry and memory. The system generates a virtual representation of a network with hubs and endpoints connected electronically, simulates the impact of external factors, and collects and processes real-time data from multiple sources to continuously update simulations. Machine learning algorithms are applied to generate predictive models, enabling users to adjust parameters and test alternative supply chain configurations. The system evaluates the impact of these configurations on performance metrics and provides optimization recommendations, enhancing decision-making and operational efficiency in supply chain networks.

Inventors

David Nason
Kirankumar Balijepalli
Grant Kaley
Jeff Godwin
Aaron Kyle Pickrell

Assignees

David Nason
Kirankumar Balijepalli
Grant Kaley
Jeff Godwin
Aaron Kyle Pickrell

Dates

Publication Date: 20260507
Application Date: 20251107

Claims (20)

1 . A management system comprising: a digital twin layer; a data integration layer; an artificial intelligence (AI) and cognitive processing layer; data integration layer; an extensibility and customization layer; processing circuitry operatively coupled with the digital twin layer, the data integration layer, the AI and cognitive processing layer, the data integration layer, and the extensibility and customization layer; and a memory device including instructions stored thereon, wherein the instructions, which when executed by the processing circuitry, configure the processing circuitry to perform operations that: generates, with the digital twin layer, a virtual representation of a network that includes a hub and endpoints associated with the hub via electronic connections; simulates, with the digital twin layer, an impact of an external factor on the hub, the endpoints, and the electronic connections; uses the data integration layer to: collect real-time data from multiple sources; process the real-time data; and continuously update the simulated impact with the digital twin layer using the real-time data; applies, using the AI and cognitive processing layer, machine learning algorithms to the real-time data and simulated impact to generate predictive models; enables, with the extensibility and customization layer, users to adjust parameters of the virtual representation to test alternative supply chain configurations; evaluates, with the AI and cognitive processing layer, impacts of the alternative configurations on supply chain performance metrics; and provides, with the AI and cognitive processing layer, optimization recommendations based on the evaluation such that bulk data movement is avoided.
2 . The management system of claim 1 , wherein the processing circuitry is further configured to perform operations that generate, using the AI and cognitive processing layer, recommendations for optimizing the network based on the real-time data and the simulated impact.
3 . The management system of claim 1 , wherein the network is a supply chain network and the end points include at least one of suppliers and distribution centers.
4 . The management system of claim 3 , wherein the management system further comprises a natural language interaction interface operatively coupled with the processing circuitry and the processing circuitry is further configured to perform operations that: receives user queries in natural language format regarding supply chain operations associated with the supply chain; processes the natural language queries using a large language model to identify relevant data and analysis requirements, and generates responses to the user queries based on relevant data from the digital twin layer and artificial intelligence analysis engine.
5 . The management system of claim 3 , wherein the electronic connections represent transportation routes between the end points and between the end points and the hub.
6 . The management system of claim 5 , wherein the processing circuitry is further configured to perform operations that identify, with the AI and cognitive processing layer, potential disruptions to supply chain operations associated with the supply chain network.
7 . The management system of claim 1 , wherein the external impact is one of weather conditions at a location associated with one of the hub, the endpoints, and the electronic connections, traffic patterns at the location associated with one of the hub, the endpoints, and the electronic connections, and geopolitical events at the location associated with one of the hub, the endpoints, and the electronic connections.
8 . The management system of claim 1 , wherein the multiple sources includes Internet of Things (IoT) sensors, enterprise resource planning (ERP) systems, warehouse management systems (WMS), and transportation management systems (TMS).
9 . A method of operating a management system comprising a digital twin layer, a data integration layer, an artificial intelligence (AI) and cognitive processing layer, data integration layer, and an extensibility and customization layer, the method comprising: generating, with the digital twin layer, a virtual representation of a network that includes a hub and endpoints associated with the hub via electronic connections; simulating, with the digital twin layer, an impact of an external factor on the hub, the endpoints, and the electronic connections; using the data integration layer to: collect real-time data from multiple sources; process the real-time data; and continuously update the simulated impact with the digital twin layer using the real-time data; applying, using the AI and cognitive processing layer, machine learning algorithms to the real-time data and simulated impact to generate predictive models; enabling, with the extensibility and customization layer, users to adjust parameters of the virtual representation to test alternative supply chain configurations; evaluating, with the AI and cognitive processing layer, impacts of the alternative configurations on supply chain performance metrics; and providing, with the AI and cognitive processing layer, optimization recommendations based on the evaluation such that bulk data movement is avoided.
10 . The method of claim 9 , that the method further comprising generating, using the AI and cognitive processing layer, recommendations for optimizing the network based on the real-time data and the simulated impact.
11 . The method of claim 9 , wherein the network is a supply chain network and the end points include at least one of suppliers and distribution centers.
12 . The method of claim 11 , wherein the management system further comprises a natural language interaction interface and the method further comprises: receiving user queries in natural language format regarding supply chain operations associated with the supply chain; processing the natural language queries using a large language model to identify relevant data and analysis requirements, and generating responses to the user queries based on relevant data from the digital twin layer and artificial intelligence analysis engine.
13 . The method of claim 11 , wherein the electronic connections represent transportation routes between the end points and between the end points and the hub.
14 . The method of claim 13 , wherein the method further comprises identifying, with the AI and cognitive processing layer, potential disruptions to supply chain operations associated with the supply chain network.
15 . The method of claim 9 , wherein the external impact is one of weather conditions at a location associated with one of the hub, the endpoints, and the electronic connections, traffic patterns at the location associated with one of the hub, the endpoints, and the electronic connections, and geopolitical events at the location associated with one of the hub, the endpoints, and the electronic connections.
16 . The method of claim 9 , wherein the multiple sources includes Internet of Things (IoT) sensors, enterprise resource planning (ERP) systems, warehouse management systems (WMS), and transportation management systems (TMS).
17 . A non-transitory, machine-readable medium, comprising instructions, which when performed by a processor of a management system comprising a digital twin layer, a data integration layer, an artificial intelligence (AI) and cognitive processing layer, data integration layer, and an extensibility and customization layer, causes the processor to perform operations to: generate, with the digital twin layer, a virtual representation of a network that includes a hub and endpoints associated with the hub via electronic connections; simulate, with the digital twin layer, an impact of an external factor on the hub, the endpoints, and the electronic connections; use the data integration layer to: collect real-time data from multiple sources; process the real-time data; and continuously update the simulated impact with the digital twin layer using the real-time data; apply, using the AI and cognitive processing layer, machine learning algorithms to the real-time data and simulated impact to generate predictive models; enable, with the extensibility and customization layer, users to adjust parameters of the virtual representation to test alternative supply chain configurations; evaluate, with the AI and cognitive processing layer, impacts of the alternative configurations on supply chain performance metrics; and provide, with the AI and cognitive processing layer, optimization recommendations based on the evaluation such that bulk data movement is avoided.
18 . The non-transitory, machine-readable medium of claim 17 , wherein the instructions further configure the processor to perform operations that generate, using the AI and cognitive processing layer, recommendations for optimizing the network based on the real-time data and the simulated impact.
19 . The non-transitory, machine-readable medium of claim 17 , wherein: the network is a supply chain network and the endpoints include at least one of suppliers and distribution centers; and the management system further comprises a natural language interaction interface and the instructions further configure the processor to perform operations that: receives user queries in natural language format regarding supply chain operations associated with the supply chain; processes the natural language queries using a large language model to identify relevant data and analysis requirements, and generates responses to the user queries based on relevant data from the digital twin layer and artificial intelligence analysis engine.
20 . The non-transitory, machine-readable medium of claim 17 , wherein the electronic connections represent transportation routes between the end points and between the end points and the hub and the instructions further configure the processor to perform operations that identify, with the AI and cognitive processing layer, potential disruptions to supply chain operations associated with the supply chain network.

Description

RELATED APPLICATIONS This application claims priority to and the benefit of U.S. Provisional Patent Application No. 63/717,661, filed Nov. 7, 2024, which is incorporated herein by reference in its entirety. FIELD OF THE INVENTION This disclosure relates to enterprise decision-intelligence platforms, and more particularly to governed, explainable Artificial Intelligence (AI) systems that harmonize multi-source operational data, generate prediction events, simulate system state via digital twins, and orchestrate financial-guardrailed actions across healthcare and supply-chain logistics environments in a governed, closed-loop control plane. BACKGROUND Supply chain systems are typically fragmented across Enterprise Resource Planning (ERP), Electronic Health Records (EHR), Warehouse Management Systems (WMS), Transportation Management Systems (TMS), scheduling, and finance systems, that produce siloed data ans uncoordinated workflows, causing decision latency and blind spots. Existing tools optimize narrow functions but fail to orchestrate the stack end-to-end; legacy architectures accreted from bolt-ons create tangled workflows that resist real-time decisions, simulations, and integrated responses. Supply chains are complex networks involving multiple stakeholders, and are susceptible to disruptions caused by external factors, such as weather, traffic, geopolitical events, supply shortages, and natural disasters. Traditional supply chain management systems often rely on static dashboards and legacy business intelligence (BI) tools that fail to meet the real-time demands of modern data-driven businesses. These tools lack the ability to visualize and simulate potential impacts and provide actionable insights in an intuitive, user-friendly environment, and they often require technical expertise for querying and analyzing data. As a result, they do not provide a comprehensive, integrated environment for strategic planning and decision-making. Over the years, the technology architectures underpinning these systems have evolved haphazardly. AI tools are often introduced ad hoc, without unified governance, explainability, or cost/latency guardrails, resulting in inconsistent outcomes, opaque decision paths, and regulatory risk. Moreover, simulation capabilities—where present—rarely align with real-time data semantics, limiting their value for “what-if” decisioning and change-impact analysis. Rather than starting from a cohesive, future-proof foundation, organizations have added layer upon layer of bolt-on systems and disconnected modules to address immediate needs. Over time, this approach has often created a fragmented patchwork architecture, where different systems, standards, and workflows are tangled together, making it difficult to scale, integrate, or extract real-time insights. This has led to significant operational inefficiencies, limiting businesses' ability to respond swiftly to disruptions and shifts in the market. Healthcare and supply-chain logistics share hard operational constraints, auditability requirements, and strict safety/cost envelopes. Conventional platforms lack: (i) a stable event model that separates facts from predictions; (ii) a governed control plane that applies policy, privacy, provenance, and financial guardrails to model/agent invocations; (iii) a digital-twin layer that can validate AI recommendations against domain constraints; and (iv) a decision-routing layer that executes multi-system actions with traceable justification. SUMMARY Comprising: (a) a data harmonization layer (DHX) that normalizes and feature-engineers multi-source operational data; (b) a governed control plane (DRX) that enforces authentication/authorization, policy, rate/cost/latency/freshness guardrails, privacy protections, and auditability for AI agents and models, with a machine learning model registry, and a retrieval-augmented knowledge layer for low-hallucination enterprise access, and role-bases/policy-based access control (RBAC/PBAC, dual-key authentication, guardrails, and comprehensive audit; (c) a prediction event framework that emits versioned, explainable prediction events; (d) a digital-twin simulation layer (CTD) that validates and stress-tests proposed actions; (e) a financial guardrail layer (CRT) that evaluates budgetary constraints and tradeoffs; and (f) a decision-routing layer (DI) that executes approved actions through APIs, webhooks, or electronic data interchange (EDI) with end-to-end lineage. A digital-twin sandbox (CTD) for scenario planning and policy testing, linked to Decision Routing (DRI) for role-based delivery of actions and recommendations. Financial Guardrails (CRT) integrating treasury and liquidity constraints with operational recommendations for economically grounded decisions and actions that are financially guarded and auditable, elevating mission-control decisions into economic governance. Prediction Events as first-class records containing uncertainty, reason codes, and lin