Natural Language Database Querying With LLM Prompt Mediation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional tools require extensive training, are tedious to use, and need specialized teams to convert natural language queries into structured language for domain-specific databases, limiting resource availability and efficiency.
Innovation Solution
A system that uses a processor to receive and analyze natural language queries, generate prompts, and transmit them to a large language model (LLM) to create database-specific queries, enabling direct data extraction without additional training or third-party dependencies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conventional tools are used for data retrieval, then specialized teams can process data requests, but the process becomes tedious and time-consuming requiring extensive training
Solution Approach 1:
The system enables users to directly query domain-specific databases using natural language without requiring specialized technical training or intervention. The automated pipeline converts natural language queries into executable database queries, allowing end-users to retrieve data independently and immediately.
Solution Approach 2:
The patent replaces manual mechanical processes (specialized teams manually processing requests) with an automated system that uses natural language processing and database query generation to handle data retrieval requests automatically, eliminating the need for manual intervention.
2Adaptability or versatility
If conventional tools with pre-defined UIs are used, then structured data can be retrieved, but out-of-box requirements cannot be handled
Solution Approach 1:
The system dynamically adapts to different database schemas and query requirements through natural language processing. Instead of fixed pre-defined interfaces, the system interprets user queries in context-specific domain languages and automatically generates appropriate database queries, enabling flexible handling of various out-of-box requirements.
Solution Approach 2:
The patent changes the interface parameter from fixed pre-defined UI options to dynamic natural language input. This allows users to express requirements in their own domain-specific language, and the system adapts the query generation process accordingly, providing versatility without increasing user-side complexity.
3Productivity
If specialized technology teams operate conventional tools, then data can be processed, but resource availability is limited and scalability is constrained
Solution Approach 1:
The system eliminates the dependency on specialized teams by enabling self-service data retrieval. Users can independently execute queries against domain-specific databases without requiring technical expertise or dedicated resources, thereby scaling productivity without proportionally increasing resource requirements.
Solution Approach 2:
The patent introduces an automated intermediary system (natural language processing layer) that translates user queries into database-executable format. This intermediary absorbs the complexity of database interaction, allowing unlimited users to access data through simple natural language queries without consuming specialized team resources.
Data Source
AI summary
A method and a system for querying database data using natural language are provided. The method includes: receiving, via a user interface, a natural language query to extract domain data from a database; analyzing, using a public cloud platform, the natural language query to determine a first database associated with the natural language query; generating, using the public cloud platform and based on a result of the analysis, a prompt for understanding the first database; transmitting the natural language query and the prompt to a second model that is a large language model (LLM); generating, using the second model and based on the transmitted natural language query and the prompt, a database-specific query; transmitting the database-specific query to the first database; generating, using the first database, a response to the natural language query; and transmitting the response to the user interface.