LLM-Based Data Configuration Management for Changing Compliance Requirements
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Managing large scale computing systems to comply with diverse and changing digital data requirements across different locations and jurisdictions is challenging due to the complexity and rigidity of existing systems, leading to compliance gaps and potential security breaches.
Innovation Solution
A data configuration management system utilizing a large language model to generate tasks for modifying digital data assets and processing operations based on detected changes in system requirements frameworks, leveraging a knowledge graph to map relationships and determine compliance gaps, and implementing control actions through a graphical user interface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual monitoring and updating of data assets is used to ensure compliance with digital data requirements, then compliance accuracy can be maintained, but the system complexity and time consumption increase significantly
Solution Approach 1:
The patent introduces an intermediary system comprising a knowledge graph and large language model that acts as a mediator between compliance requirements and data assets. The knowledge graph stores structured compliance rules and relationships, while the LLM processes natural language queries and generates compliance assessments, thereby reducing the complexity of direct manual monitoring while maintaining high compliance accuracy through intelligent automation.
Solution Approach 2:
The patent replaces manual mechanical monitoring processes with an automated intelligent system. Instead of human operators manually checking compliance, the system uses the LLM to automatically analyze data assets against compliance requirements stored in the knowledge graph, substituting human labor with automated AI-based mechanisms that reduce time consumption and operational complexity.
2Stability of the object's composition
If existing rigid systems are used to manage digital data requirements, then system stability is maintained, but adaptability to changing requirements deteriorates
Solution Approach 1:
The patent implements a dynamic system where the knowledge graph can be updated with new compliance requirements and the LLM can adapt to changing data assets and regulations. The system continuously learns from new inputs and adjusts its compliance assessments, transforming the rigid static monitoring approach into a dynamic adaptive framework that maintains stability through controlled evolution of its knowledge base and processing capabilities.
3Reliability
If comprehensive monitoring of all data assets is implemented to ensure compliance, then compliance coverage is improved, but computational load increases
Solution Approach 1:
The patent segments the compliance monitoring task by organizing data assets and compliance requirements into structured modules within the knowledge graph. The LLM processes compliance checks in a systematic segmented manner, analyzing different data assets against relevant compliance rules separately, which improves comprehensive coverage while managing computational load through organized modular processing rather than monolithic analysis.
Solution Approach 2:
The patent performs preliminary organization of compliance requirements and data asset relationships in the knowledge graph before actual compliance assessment. This preliminary structuring of information allows the LLM to efficiently query and analyze only relevant compliance rules for each data asset, reducing unnecessary computational overhead while maintaining comprehensive monitoring coverage across all assets.
Data Source
AI summary
Methods, systems, and non-transitory computer readable storage media are disclosed for managing computing systems to comply with system requirements frameworks that indicate specific requirements on how the computing systems should handle certain data types. In response to detecting a change to one or more digital data requirements of a system requirements framework, the disclosed systems access a configuration profile of an entity and utilize a large language model to determine if data assets or data processing operations comply with the changes to the digital data requirements. In response to determining a configuration gap of the configuration profile based on detected changes to the digital data requirements, the disclosed systems utilize a large language model to generate tasks for correcting the configuration gap. The disclosed systems generate one or more tasks by modifying data assets, data processing operations, or other digital data associated with the entity.