Knowledge Graph Recommendations for Circular Product Lifecycle Decisions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems lack an integrated and semantic approach to manage heterogeneous data across the lifecycle of products, limiting accurate prediction of life expectancy and effective decision-making for circular economy frameworks, and fail to provide scalable insights for sustainable product management.
Innovation Solution
A vertical-agnostic knowledge graph-driven system that semantically contextualizes product data, generating insights for circular economy frameworks by determining features and recommending actions across the lifecycle phases, including material selection, supplier choice, and anomaly prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traditional non-semantic methods are used to manage product data, then data management is simple, but the system cannot provide integrated 360-degree view of product aspects and circular economy insights
Solution Approach 1:
The patent introduces a knowledge graph as an intermediary layer between raw product data and users/analysts. This knowledge graph semantically contextualizes heterogeneous data from multiple lifecycle phases, enabling integrated 360-degree views without requiring direct complex queries to source systems. The knowledge graph acts as a mediator that transforms unstructured data into meaningful, queryable relationships.
Solution Approach 2:
The system builds a universal knowledge graph framework that can handle multiple types of product data (physical properties, chemical properties, biological properties, compliance information) from various lifecycle phases through a single unified structure. This multi-functional approach allows the same system to serve diverse analytical needs across different industries and product types.
2Loss of information
If data from multiple lifecycle phases handled by different vendors is collected, then comprehensive product information is obtained, but data authenticity and accuracy become difficult to ensure
Solution Approach 1:
The system implements feedback mechanisms where the knowledge graph continuously validates and updates product information as new data becomes available from different lifecycle phases. The semantic relationships in the knowledge graph enable cross-validation of data from multiple sources, improving reliability through iterative refinement and consistency checks across the product lifecycle.
Solution Approach 2:
The patent merges data from multiple independent vendors and lifecycle phases into a unified knowledge graph structure. By combining heterogeneous data sources through standardized semantic relationships, the system achieves comprehensive coverage while maintaining data integrity through the unifying framework of the knowledge graph.
3Ease of operation
If heterogeneous data about products, materials, and compliance across geographic regions is managed, then circular economy decision-making is improved, but data processing complexity increases
Solution Approach 1:
The system transforms heterogeneous data with different formats, units, and structures into a standardized parameter framework within the knowledge graph. By changing the parameters of diverse data sources into a common semantic language, the system enables easy querying and analysis for circular economy decisions without exposing users to the underlying complexity of data heterogeneity.
Solution Approach 2:
The patent replaces traditional mechanical data processing methods (manual data consolidation, spreadsheet management) with semantic web technologies and knowledge graph algorithms. This substitution automates the complex task of integrating heterogeneous data from multiple sources, making circular economy decision-making accessible without requiring manual data processing expertise.
4Reliability
If accurate prediction of life expectancy is required, then product reliability is improved, but data exchange among lifecycle phases must be comprehensive
Solution Approach 1:
The system performs preliminary actions by continuously collecting and storing data from all lifecycle phases in the knowledge graph before life expectancy prediction is needed. This advance preparation ensures that comprehensive data is already organized and validated when prediction algorithms are applied, eliminating the need for last-minute data gathering and ensuring accurate predictions.
Data Source
AI summary
A system, apparatus, and method is provided for recommending actions to enable circular economy framework across lifecycle of product including components in industrial environment. The method including determining, by processing unit, features for a given phase of lifecycle of product based on information associated with unique identifier of product. The information is stored in knowledge graph including semantic information pertaining to product, components of product, properties of components of the product and behavior of components of the product at each lifecycle phase of product. The method includes determining performance indicators pertaining to circular economy framework in industrial environment based on features from knowledge graph for given phase of lifecycle of product. The method includes recommending actions for given lifecycle phase of product such that determined one or more performance indicators are within predefined range enabling circular economy framework in industrial environment.