ML Word Pockets for Analytics Dashboard Data Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Self-service analytics solutions often fail to operate correctly due to mismatches in terminology between pre-built dashboards and user environments, requiring manual mapping and increasing implementation and maintenance costs.
Innovation Solution
The use of trained machine learning models that employ word pockets to map data elements between pre-built analytics dashboards and user landscapes, associating data elements with standard terminology and synonyms, allowing for automatic data element mapping and reducing manual intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If standard terminology is used in pre-built analytics dashboards, then the dashboards can be universally applied, but they may not match user environment terminology causing operational failures
Solution Approach 1:
The patent introduces terminology mapping as an intermediary layer between standard dashboard terminology and user environment terminology. The mapping process translates standard terms (e.g., 'Revenue') to user-specific terms (e.g., 'Sales Amount') using machine learning models, allowing the dashboard to operate correctly without changing its universal structure.
2Reliability
If manual terminology mapping is performed, then dashboard operation correctness is improved, but implementation and maintenance costs increase
Solution Approach 1:
The patent implements self-service terminology mapping using machine learning models that automatically perform the mapping without human intervention. The system extracts terminology relationships from data sources and autonomously creates and updates mappings, eliminating the need for manual configuration while maintaining high accuracy.
Solution Approach 2:
The patent replaces the mechanical manual mapping process with an automated machine learning-based system. Instead of manual review and configuration of terminology mappings, the system uses trained models to automatically translate between standard and user terminology, significantly reducing implementation and maintenance effort.
3Reliability
If manual terminology mapping is performed, then dashboard operation correctness is improved, but time consumption increases
Solution Approach 1:
The patent performs preliminary terminology mapping by pre-training machine learning models on terminology relationships before deployment. The system extracts and stores mapping relationships in advance, so that during actual dashboard operation, the mapping occurs automatically without time-consuming manual intervention.
4Extent of automation
If automatic machine learning mapping is used, then manual intervention is reduced, but the complexity of the system increases
Solution Approach 1:
The patent segments the terminology mapping system into distinct components: machine learning model training, mapping execution, and model updating. Each component handles specific tasks independently, making the overall complex system manageable through modular design and clear separation of concerns.
Data Source
AI summary
Technologies are described for mapping data elements for pre-built analytics dashboards. For example, a list of data elements that are present in a target landscape can be obtained and compared to data elements that are used by a pre-built analytics dashboard to determine a first category of data elements that are present in the target landscape but not in the pre-built analytics dashboard and a second category of data elements that are present in the pre-built analytics dashboard but not in the target landscape. The data elements that are present in the pre-built analytics dashboard but not in the target landscape can then be mapped to the data elements in the target landscape using a trained machine learning model. The trained machine learning model uses word pockets to separately associate data elements with standard terminology and synonyms.