Machine-Learning LCA Verification for Source Credibility and Plausibility
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing LCA tools face challenges in maintaining high-quality and reliable LCA databases due to resource limitations, prolonged data validation periods, and insufficient data credibility assessment, particularly with EPDs featuring digitally reproduced signatures, necessitating improved data verification solutions.
Innovation Solution
A server utilizing machine learning models for credibility and plausibility evaluation of LCA data, incorporating natural language processing to identify and verify data quality, and a system architecture for data storage and processing to facilitate efficient data verification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If periodic data reviews and updates are conducted manually, then data quality can be maintained, but time consumption and resource requirements increase
Solution Approach 1:
The system enables self-service through automated data verification where the AI model independently evaluates LCA data sources, checks credibility, and validates data quality without requiring manual intervention. The system automatically monitors data quality metrics and performs verification tasks that would otherwise require human resources, thereby maintaining data quality while reducing time consumption.
Solution Approach 2:
The patent replaces manual mechanical data verification processes with an automated AI-based system. The machine learning model performs credibility assessment, data quality checking, and validation tasks that were previously done manually, substituting human labor with an automated intelligent system that operates continuously without time loss.
2Productivity
If basic rule-based approaches are used for data verification, then processing speed is maintained, but accuracy and reliability of verification deteriorates
Solution Approach 1:
The system changes the verification parameters from simple rule-based checks to multi-dimensional AI-based assessment. The machine learning model evaluates multiple parameters including data source credibility, data quality metrics, plausibility of impact levels, and adherence to international standards, providing accurate verification while maintaining processing speed through automated inference.
Solution Approach 2:
The patent employs a composite verification approach combining multiple verification dimensions: data source credibility assessment, data quality evaluation, plausibility checking, and standard compliance verification. This composite material of verification methods ensures high accuracy while maintaining efficiency through integrated AI processing.
3Reliability
If comprehensive data verification is performed manually, then verification accuracy is improved, but device complexity and operational difficulty increase
Solution Approach 1:
The AI system performs self-service verification automatically, handling complex multi-dimensional assessment without requiring user intervention. The system independently evaluates data sources, checks quality metrics, validates plausibility, and generates verification results, simplifying the operational interface while maintaining high verification accuracy through automated comprehensive checking.
4Productivity
If automated rule-based processing is implemented, then processing efficiency is improved, but adaptability to complex data quality issues deteriorates
Solution Approach 1:
The system transitions from fixed rule-based parameters to dynamic AI-based parameter evaluation. The machine learning model adapts to complex data quality issues by learning from patterns in credible and non-credible data sources, providing versatile handling of various data quality problems while maintaining high processing efficiency through automated inference.
Solution Approach 2:
The verification system becomes dynamic through AI-based adaptive evaluation. The machine learning model continuously learns from new data and updates its verification criteria, enabling it to adapt to evolving data quality issues and complex scenarios while maintaining efficient automated processing speeds.
Data Source
AI summary
Aspects concern a server comprising: a memory configured to store instructions; and a processor configured to execute the stored instructions and configured to: detect life-cycle assessment (LCA) data from an LCA data source; identify information relating to a quality of the LCA data and a quality of the LCA data source using a natural language processing (NLP) technique; evaluate credibility of the LCA data source using a first machine learning model based on the identified information relating to the quality of the LCA data source; evaluate a plausibility of an impact level using a second machine learning model based on the identified information relating to the quality of the LCA data; and verify the LCA data as either valid data or invalid data, based on the evaluated credibility of the LCA data source and the evaluated plausibility of the impact level.