Rule-Based Decision Support for Supply Chain Deviations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Supply chain planners face challenges in quickly addressing deviations from planned parameters due to the high volume of tasks and intense time pressure, often resulting in suboptimal solutions in supply chain management scenarios.
Innovation Solution
A computer-implemented method and system that utilizes a rule-based decision support system to analyze plan deviations, simulate remediation solutions, and generate a ranked list of candidate solutions based on resource simulations, enabling efficient and informed decision-making.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If planners manually analyze data from various sources to resolve supply chain deviations, then they can address unexpected problems, but the high volume of tasks and intense time pressure result in suboptimal solutions and planner overwhelm
Solution Approach 1:
The patent introduces an intelligent decision support system that acts as an intermediary between supply chain planners and the complex data analysis task. The system includes a natural language processing module that translates planner queries into executable analysis, a simulation engine that evaluates multiple remediation solutions, and an automated reporting mechanism. This intermediary handles the time-consuming data analysis and solution evaluation, allowing planners to focus on decision-making without being overwhelmed by manual analysis tasks
Solution Approach 2:
The patent replaces the mechanical manual analysis process with an automated computational system. Instead of planners manually collecting, analyzing, and evaluating supply chain data, the system uses natural language processing, automated data querying, simulation engines, and algorithmic optimization to perform these tasks. This substitution eliminates the time pressure and human error associated with manual analysis while maintaining or improving solution quality
2Reliability
If planners spend more time analyzing multiple remediation solutions, then solution quality improves, but the time pressure and task volume prevent thorough evaluation
Solution Approach 1:
The patent implements preliminary action by pre-configuring the system with supply chain models, constraints, and evaluation criteria before deviations occur. When a deviation is detected, the system immediately queries pre-established data sources and runs simulations using pre-defined methodologies. The system also pre-generates multiple remediation solutions based on historical data and established best practices, allowing planners to review optimized options without time pressure rather than analyzing options from scratch
Solution Approach 2:
The patent uses copying by creating virtual replicas of the supply chain system through simulation models. Instead of analyzing real-world scenarios in real-time, the system creates copies of the supply chain state and tests multiple remediation solutions in these virtual environments. This allows thorough evaluation of numerous solutions without impacting actual operations or consuming excessive real-time resources, as simulations can run in parallel and be completed quickly
3Reliability
If the system evaluates multiple remediation solutions with resource simulations, then the likelihood of suboptimal outcomes decreases, but the complexity of the decision support system increases
Solution Approach 1:
The patent segments the complex decision support system into distinct modular components: a natural language processing module for query interpretation, a data querying module for information retrieval, a simulation engine for evaluating remediation solutions, and a reporting module for presenting results. Each module handles a specific aspect of the analysis independently, making the overall complex system manageable, maintainable, and scalable. This segmentation allows the system to evaluate multiple solutions thoroughly without becoming an unmanageable monolith
Data Source
AI summary
A computer-implemented method can receive a new plan deviation alert having a deviation level that quantifies a mismatch between expected supply chain parameters specified by a supply chain plan and observed supply chain parameters. Responsive to the new plan deviation alert, the method can perform a rule-based search to find a plurality of potential remediation solutions to correct the mismatch. The method can simulate implementation of the potential remediation solutions and evaluate expended resources associated with them. Based on the evaluated expended resources, the method can generate a ranked list of candidate remediation solutions and display the ranked list of candidate remediation solutions in a user interface. The method can receive a selected remediation solution from the ranked list of candidate remediation solutions for initiation. Machine learning can be used on an expert user's selection to adapt to the expert's preferences and provide more relevant remediation solutions.