Natural Language Data Warehouse Extension Without Schema Expertise
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data augmentation processes in data analytics require users to have a detailed understanding of their system's configuration and manually define each data attribute, making them non-user-friendly.
Innovation Solution
A system that receives natural language inputs to automate data warehouse creation and extension, understanding user instructions in plain language and performing corresponding actions without requiring detailed knowledge of the data warehouse or its schemas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual data attribute definition is used, then data augmentation capability is achieved, but user operation complexity increases
Solution Approach 1:
The system performs self-service by automatically discovering data attributes, relationships, and schemas without requiring manual user definition. The system autonomously navigates data sources, identifies relevant columns and relationships, and generates data warehouse structures based on its own analysis of the source data.
Solution Approach 2:
The manual mechanical process of defining data attributes is replaced with an automated intelligent system that uses natural language processing and machine learning to discover and define data structures. The system substitutes human manual configuration with automated algorithmic analysis of data sources.
2Manufacturing precision
If detailed system knowledge is required, then data augmentation precision is improved, but learning time increases
Solution Approach 1:
The system acts as an intermediary between the user's natural language request and the complex data warehouse system. It translates simple user intent into precise technical data warehouse configurations, eliminating the need for users to learn complex system details while maintaining high precision in data augmentation.
Solution Approach 2:
The system performs preliminary analysis and discovery of data sources, relationships, and schemas before the user needs to define anything. It pre-processes the data landscape, identifies relevant structures, and prepares the groundwork for precise data augmentation without requiring user investment in learning time.
3Ease of operation
If automated natural language processing is used, then ease of operation is improved, but system complexity increases
Solution Approach 1:
The system uses natural language processing as an intermediary layer between the simple user interface and the complex data warehouse operations. It translates user-friendly natural language requests into complex technical operations, shielding users from system complexity while enabling automated processing.
Data Source
AI summary
In accordance with an embodiment, described herein is a system and method for automated data warehouse creation and extension from user natural language requests. A data augmentation system, operating on one or more computers, can receive a natural language input from a user, including an instruction to augment a set of data, for example to create a fact/dimension, or to extend an existing data entity by bringing additional columns from a source data and publishing the combined data to a target data warehouse instance. The system determines an understanding associated with the user instruction in plain-language terms (for example, “extend sales order transactions with approval status”), and determines and performs a corresponding course of actions to create, extend, or otherwise augment the set of data, without requirement for the user to have a detailed knowledge of the data warehouse, its schemas, or other data dependencies.