Automated Data Annotation via Knowledge Graph Replication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large industrial conglomerates face challenges in consistently translating IT data to business data across multiple companies due to the IT/OT divide, often requiring dedicated data stewards that are difficult to hire and integrate, especially in newly set-up geographical regions.
Innovation Solution
An automated method using machine learning to replicate data catalogues across companies by creating templatized business terms, logics, and data profiles from a reference factory, stored in a knowledge graph, allowing for automated translation without the need for dedicated data stewards, utilizing an automated business logic configurator and data configurator.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If dedicated data stewards are hired to translate IT data to business data across multiple companies, then data translation quality and consistency are improved, but hiring and integration difficulties especially in new geographical regions worsen
Solution Approach 1:
The system creates a reference data catalogue from a source company that captures the mapping between IT data models and business data models. This reference catalogue is then replicated and adapted to target companies, eliminating the need to hire dedicated data stewards at each location while maintaining consistent translation quality across the conglomerate.
Solution Approach 2:
The automated system enables target companies to perform their own data translation by leveraging the pre-configured reference data catalogue. The system automatically adapts the reference catalogue to local IT data models without requiring specialized human expertise at each location, making the organizations self-sufficient in data translation tasks.
2Measurement precision
If data catalogues are manually configured at each company, then data translation accuracy is improved, but time consumption and operational complexity worsen
Solution Approach 1:
The reference data catalogue is pre-configured with accurate mappings between IT data models and business data models at a source company. This preliminary configuration captures the translation logic that can then be rapidly replicated to multiple target companies, eliminating the need for time-consuming manual configuration at each location while preserving translation accuracy.
Solution Approach 2:
The reference data catalogue serves as a universal template that can be applied across multiple companies within the conglomerate. Despite differences in IT software selections and data models at various locations, the same reference catalogue structure and translation logic can be adapted to all target companies, reducing operational complexity and time consumption.
3Productivity
If automated methods are used to replicate data catalogues across companies, then time consumption and operational complexity are reduced, but the ability to handle diverse IT data models across different companies worsens
Solution Approach 1:
The system dynamically adapts the reference data catalogue to match the specific IT data models of each target company. Rather than using a static, one-size-fits-all approach, the system flexibly adjusts the replicated catalogue to accommodate different IT software selections and data model variations across the conglomerate, maintaining both efficiency and adaptability.
Data Source
AI summary
Systems and methods for automating process setting to a target factory, which can involve creating templatized business terms, templatized business data configurator logics, and a templatized data profile by machine learning from training data from at least one reference factory; storing the templatized business terms, the templatized business data configurator logics, and the templatized data profile into a knowledge graph; querying the knowledge graph with a data profile of the target factory to obtain corresponding templated business terms; and applying the corresponding templated business terms and corresponding templated business data configurator logics to a data catalogue of the target factory.