Table Metadata Inference Using Knowledge Graph Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing tabular data analysis programs struggle to accurately infer the real-world referents of data, leading to incorrect data visualization and insight generation, such as misclassification of variables and inappropriate aggregation functions, which hinder relevant analytics.
Innovation Solution
A computing system utilizing a metadata inference machine learning model that generates inferred table metadata based on entries in a table and semantic data from a knowledge graph, including row and column type classifications, and outputs a metadata display interface for improved data visualization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional data analysis programs are used to infer table metadata, then the system complexity remains low, but the measurement precision of variable classification deteriorates
Solution Approach 1:
A knowledge graph serves as an intermediary between the table data and the metadata inference process. The knowledge graph stores semantic information about real-world entities and their relationships, which the machine learning model uses to improve classification accuracy without significantly increasing system complexity
Solution Approach 2:
Traditional rule-based metadata inference mechanisms are replaced with a machine learning model that leverages semantic information from knowledge graphs. This substitution enables more accurate variable classification by learning from semantic patterns rather than relying on predefined rules
2Reliability
If simple metadata inference methods are used, then the ease of operation is maintained, but the reliability of data visualization deteriorates
Solution Approach 1:
The system performs self-service by automatically inferring metadata and generating visualizations without requiring manual user intervention. The machine learning model autonomously classifies variables and selects appropriate aggregation functions, maintaining ease of operation while improving reliability
3Measurement precision
If manual metadata specification is required, then the measurement precision improves, but the productivity deteriorates
Solution Approach 1:
Manual metadata specification is replaced with automated machine learning-based inference. The system processes table data and knowledge graph information to generate accurate metadata automatically, eliminating the need for manual intervention while maintaining high accuracy through semantic understanding
Data Source
AI summary
A computing system including memory storing a table including a plurality of entries arranged in a plurality of rows and a plurality of columns. The memory may further store a knowledge graph in which semantic data is stored. The computing system may further include a processor configured to, at a metadata inference machine learning model, generate inferred table metadata based at least in part on the entries included in the table and the semantic data included in the knowledge graph. The inferred table metadata may include one or more row type classifications of one or more respective rows or one or more column type classifications of one or more respective columns. The processor may be further configured to generate a metadata display interface element that visually represents the inferred table metadata and output the metadata display interface element for display at a graphical user interface (GUI).