FLOWER: Flow-Oriented Entity-Relationship Tool

TL;DR

FLOWER is an innovative end-to-end tool that automatically constructs and visualizes entity-relationship models from large data sources, enhancing data understanding and insights with improved accuracy and efficiency.

Contribution

This paper introduces FLOWER, the first tool to automatically detect constraints and build entity-relationship models dynamically for SQL and natural language, reducing manual effort.

Findings

Outperforms reservoir sampling by 2.4x in distribution representation

Achieves 2.6x better constraint learning and 2.15x faster processing

Improves data storytelling accuracy by 1.19x with less context

Abstract

Exploring relationships across data sources is a crucial optimization for entities recognition. Since databases can store big amount of information with synthetic and organic data, serving all quantity of objects correctly is an important task to deal with. However, the decision of how to construct entity relationship model is associated with human factor. In this paper, we present flow-oriented entity-relationship tool. This is first and unique end-to-end solution that eliminates routine and resource-intensive problems of processing, creating and visualizing both of explicit and implicit dependencies for prominent SQL dialects on-the-fly. Once launched, FLOWER automatically detects built-in constraints and starting to create own correct and necessary one using dynamic sampling and robust data analysis techniques. This approach applies to improve entity-relationship model and data storytelling to better understand the foundation of data and get unseen insights from DB sources using SQL or natural language. Evaluated on state-of-the-art STATS benchmark, experiments show that FLOWER is superior to reservoir sampling by 2.4x for distribution representation and 2.6x for constraint learning with 2.15x acceleration. For data storytelling, our tool archives 1.19x for accuracy enhance with 1.86x context decrease compare to LLM. Presented tool is also support 23 languages and compatible with both of CPU and GPU. Those results show that FLOWER can manage with real-world data a way better to ensure with quality, scalability and applicability for different use-cases.