LLM Cybersecurity Platform Query Translation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
As the number of databases increases, users face difficulties in accurately identifying the appropriate database and API to access the correct data, leading to network congestion, latency, and wastage of computing resources.
Innovation Solution
The use of generative artificial intelligence, specifically large language models (LLMs), to convert natural language queries into database commands, such as Structured Query Language (SQL), for accessing one or more databases, thereby streamlining the data retrieval process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If the number of databases increases to accommodate larger data volumes, then data storage capacity is improved, but user difficulty in identifying appropriate databases and APIs increases
Solution Approach 1:
The patent introduces an LLM-based intermediary system that translates natural language queries into database queries. This mediator layer between users and databases resolves the contradiction by maintaining large data storage capacity while simplifying user interaction through AI-powered query translation, eliminating the need for users to manually identify appropriate databases and APIs.
Solution Approach 2:
The patent replaces the mechanical process of manual database and API selection with an AI-based natural language understanding system. The LLM substitutes the traditional mechanical approach of navigating database schemas with intelligent query translation, enabling users to access data through conversational interfaces rather than technical database navigation.
2Measurement precision
If users manually navigate through multiple databases and APIs to access data, then data retrieval accuracy is improved, but network congestion and latency increase
Solution Approach 1:
The patent applies preliminary action by having the LLM translate and optimize database queries before execution. The system pre-processes natural language queries into optimized database-specific queries, ensuring accurate data retrieval while reducing network latency by eliminating unnecessary intermediate navigation steps and direct queries to appropriate databases.
Solution Approach 2:
The patent implements feedback mechanisms where the LLM learns from query patterns and user interactions to improve query translation accuracy over time. This feedback loop enables the system to maintain high data retrieval accuracy while progressively reducing network latency through optimized query formulation based on observed usage patterns.
3Adaptability or versatility
If users send multiple data requests to various databases, then comprehensive data access is improved, but computing resource wastage increases
Solution Approach 1:
The patent applies universality by implementing a single LLM-based query translation layer that handles diverse data access needs across multiple databases. This universal interface consolidates what would otherwise require multiple separate database connection and query processes, maintaining comprehensive data access while reducing computing resource consumption through unified query optimization.
Solution Approach 2:
The patent changes the parameter of query formulation from raw natural language to optimized database-specific queries generated by LLMs. This parameter transformation enables the system to maintain versatile data access capabilities while optimizing computing resource utilization through intelligent query generation that targets specific databases and APIs only when necessary, avoiding redundant requests.
Data Source
AI summary
A system and method of using generative AI to convert NL queries to database commands for accessing one or more databases. The method includes receiving a natural language (NL) request for information associated with a private network. The method includes providing the NL request to an artificial intelligence (AI) model trained to identify, from a plurality of access objects associated with a plurality of databases and a plurality of event types, a particular access object that provides access to one or more event datasets associated with the NL request. The method includes generating, by a processing device and using the AI model, a database request associated with the particular access object based on the NL request.