Controlling Document Workflows for Regulatory Database Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Maintaining relationships between documents and databases is challenging due to varying document formats, requiring significant manual effort, especially in regulatory compliance scenarios where numerous regulations need to be managed and updated.
Innovation Solution
A mix of sequential program logic, off-the-shelf trained ML tools, and fine-tuned ML tools, including large language models, are used to identify requirements, track changes, map regulations to databases, and propose updates, employing a 'human-in-the-loop AI' paradigm.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual methods are used to maintain relationships between documents and databases, then flexibility in handling varying document formats is achieved, but significant manual effort and time are required
Solution Approach 1:
The system enables automated self-service through ML models that independently identify requirements in documents, track changes between versions, map regulations to database entries, and propose updates without requiring manual intervention for each task, thereby reducing manual effort while maintaining adaptability to various document formats
Solution Approach 2:
The patent implements a multi-functional system where a single automated workflow can handle multiple document formats and perform multiple tasks (requirement identification, change tracking, mapping, and update proposal) through integrated ML tools, eliminating the need for separate manual processes for each function
2Productivity
If automated ML tools are used to maintain compliance, then productivity and accuracy are improved, but system complexity increases
Solution Approach 1:
The patent divides the compliance maintenance process into distinct modular tasks (requirement identification, change tracking, mapping, update proposal) that can be independently implemented and managed, reducing overall system complexity while improving productivity through targeted automation of each segment
Solution Approach 2:
The system introduces ML tools as intermediary components between documents and databases, automating the complex mapping and relationship maintenance processes while providing a simplified interface for users, thereby increasing productivity without directly exposing system complexity to end users
3Reliability
If comprehensive change tracking is implemented across multiple document versions, then compliance accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
The system performs preliminary actions by proactively monitoring and tracking changes across document versions before compliance issues arise, using ML tools to identify requirements and map regulations in advance, thereby ensuring compliance accuracy while reducing reactive processing time
Solution Approach 2:
The patent implements feedback mechanisms where the system continuously monitors document changes, compares them against database entries, and automatically proposes updates to maintain compliance, creating a closed-loop process that improves accuracy through iterative refinement while optimizing processing time through automated feedback cycles
Data Source
AI summary
Methods and systems are disclosed for database management with controlling documents. Tasks addressed include: identification of requirements in the documents, tracking changes as documents evolve, mapping documents or requirements to database entries, identifying gaps between documents and the database, and proposing database updates. Disclosed embodiments address these tasks using a combination of sequential program logic, machine-learning tools, and client interaction. Workflows address one or more tasks. Examples pertaining to regulatory documents are presented. Variations are disclosed.