Autonomous Supply Chain Data Hub for Error-Corrected Standardization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern supply chains face challenges in transforming and standardizing vast quantities of data from multiple entities without introducing errors, leading to incorrect interpretations and dilution of data usefulness.
Innovation Solution
An autonomous data hub system utilizing machine learning models and a permissioned blockchain to autonomously standardize and correct errors in supply chain data by continuously training and updating models to recognize data errors and changes, using semantic metadata and permissioned blockchains to track errors across entities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If data is transformed and standardized into a single format, then data accessibility and common vocabulary are improved, but systemic errors and data usefulness are degraded
Solution Approach 1:
The patent introduces an intermediary system that includes error detection models and correction mechanisms positioned between the heterogeneous data sources and the standardized data output. This intermediary layer transforms data while simultaneously detecting and correcting errors, preventing error propagation during standardization. The system uses multiple models including error detection models trained on historical error data and correction models that apply fixes based on detected error patterns.
Solution Approach 2:
The system implements feedback loops where detected errors and corrections are fed back into the model training process. The error detection models continuously learn from new error patterns discovered in the supply chain data, and correction models are updated with feedback on their correction accuracy. This feedback mechanism allows the system to improve its error detection and correction capabilities over time while maintaining data standardization.
2Reliability
If data standardization is performed manually, then error control is improved, but processing time and operational complexity are degraded
Solution Approach 1:
The patent replaces manual mechanical review processes with automated machine learning models. Error detection models automatically scan standardized data for errors using patterns learned from historical data, and correction models automatically apply fixes without human intervention. This substitution of automated intelligent systems for manual processes maintains high error control while dramatically reducing processing time and operational complexity.
Solution Approach 2:
The system implements self-service capabilities where the error detection and correction models autonomously identify and fix errors in standardized data without requiring manual review. The models self-correct common error patterns such as formatting inconsistencies, data type mismatches, and validation failures, freeing human operators to focus on more complex issues while maintaining high data quality standards.
Data Source
AI summary
A system and method of autonomous data hub processing that uses semantic metadata, machine learning models, and a permissioned blockchain to autonomously standardize, identify and correct errors in supply chain data is disclosed. Embodiments input supply chain data stored in a supply chain database, train with the machine learning model trainer, one or more machine learning models to identify one or more data errors in the supply chain data, clean the one or more identified data errors from the supply chain data, and store cleaned supply chain data. Embodiments also update one or more machine learning models to identify one or more data errors in cleaned supply chain data, and join and aggregate one or more sets of cleaned supply chain data.