Supply Chain Data Ingestion With AI Mapping and Live Preview
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing supply chain planning systems rely heavily on manual configuration, which is inefficient and often results in suboptimal setups due to the complexity of global supply chains and the variability of data formats and quality, leading to issues like service failures, over/under-stocking, and high costs.
Innovation Solution
An AI-driven data ingestion process that includes disambiguation, data profiling, and mapping using multiple AI models to standardize and optimize supply chain data, generating a live preview for human validation, and providing recommendations for improvement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual configuration is used for supply chain planning, then human judgment and flexibility are maintained, but the system efficiency and optimization accuracy deteriorate due to the complexity of global supply chains and multitude of variables
Solution Approach 1:
The system enables self-service through automated AI/ML algorithms that independently analyze supply chain data, identify optimal configurations, and generate plans without requiring manual intervention. The algorithms self-correct and improve over time, automatically processing multiple data inputs and making informed choices to resolve the contradiction between efficiency and accuracy.
Solution Approach 2:
The patent replaces the mechanical manual configuration process with an AI/ML-based automated system. The intelligent algorithms substitute human planners' manual work with computational models that can process vast amounts of data and evaluate millions of potential configurations, thereby improving both planning efficiency and configuration accuracy simultaneously.
2Speed
If AI/ML algorithms are used for supply chain optimization, then processing speed and analysis capability improve, but the quality of output deteriorates due to garbage-in-garbage-out phenomena from variable data quality and formats
Solution Approach 1:
The system performs preliminary data profiling and quality assessment before the main AI/ML optimization process. By pre-processing and validating data inputs, the system ensures that high-quality data is fed into the algorithms, preventing the garbage-in-garbage-out phenomenon while maintaining fast processing speeds.
Solution Approach 2:
The patent introduces an intermediary data validation and preprocessing layer between the raw data input and the AI/ML algorithms. This intermediary component cleans, standardizes, and validates data before it reaches the optimization models, ensuring reliable outputs while preserving the speed advantages of automated processing.
3Measurement precision
If sophisticated data ingestion processes are implemented, then data quality and standardization improve, but the time and resource requirements increase significantly requiring expensive subject matter experts
Solution Approach 1:
The system performs automated data profiling, quality assessment, and standardization without requiring expensive subject matter experts. The AI/ML algorithms independently evaluate data quality, identify issues, and apply appropriate corrections, dramatically reducing both time and resource requirements while maintaining high data standardization quality.
Solution Approach 2:
The patent replaces the manual expert-driven data ingestion process with automated intelligent algorithms. The system substitutes expensive human subject matter experts with AI/ML models that can perform data validation, profiling, and standardization faster and more consistently, eliminating the trade-off between quality and time.
Data Source
AI summary
The present invention relates to systems and methods for ingesting of raw client data into a supply chain optimization system. The client enterprise data system (EDS) provides raw data, typically in tabular format across many files, to a data management module of the optimization system. This data is then profiled. and a set of mapping AI models is applied to the profiled data. Each of the plurality of mapping AI models corresponds to a single input feature of the optimization model. As the mapping models are applied, a live preview is generated. This live preview is reviewable by a human operator, and human input can be provided. When there is input, the individual mapping model is updated (without impacting the other mapping models), and a new live preview for that given feature is generated. The resulting standardized feature set may be consumed by the supply chain optimization model.