Automated Compliance Mapping Using Supervised Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Companies face challenges in efficiently and accurately mapping control policies to regulatory documents to ensure compliance, as regulatory documents are extensive and complex, requiring automated and detailed electronic mapping that considers the meaning and context of obligations.
Innovation Solution
A computer-implemented method and system using supervised machine learning techniques to map control policies to regulatory documents, involving the extraction of features from both policy and regulatory documents, and utilizing a control framework to determine compliance, incorporating domain and global corpora for context and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated mapping is implemented, then productivity is improved, but measurement precision deteriorates
Solution Approach 1:
The patent introduces control frameworks as intermediary structures that bridge regulatory documents and policy documents. The control framework contains standardized control elements that serve as mediators, enabling automated mapping while maintaining precision through the structured intermediary layer that captures the semantic meaning of obligations.
Solution Approach 2:
The patent applies preliminary action by pre-defining control frameworks with standardized control elements before the mapping process. Regulatory documents are mapped to these pre-established control frameworks, which then serve as templates for mapping policy documents. This preliminary structuring enables accurate automated mapping without requiring complex real-time analysis.
2Measurement precision
If manual mapping is used, then measurement precision is improved, but productivity deteriorates
Solution Approach 1:
The system enables self-service by allowing the automated mapping process to perform the work that previously required manual human analysis. The machine learning models and control frameworks work together to automatically map control policies to regulatory obligations without human intervention, achieving both high productivity and maintained precision through the structured control framework approach.
3Ease of operation
If simple mapping is applied, then ease of operation is improved, but measurement precision deteriorates
Solution Approach 1:
The patent segments the complex mapping problem into distinct components: regulatory documents are broken down into control frameworks with standardized control elements, and policy documents are mapped to these segmented control elements. This segmentation simplifies the operation by providing a structured approach while maintaining precision through the detailed control element definitions that capture contextual meaning.
Solution Approach 2:
The system changes parameters by transforming unstructured text into structured control framework mappings. The control framework defines specific parameters and attributes for each control element, enabling the system to capture and process contextual information systematically. This parameter transformation maintains precision while simplifying operation through standardized data structures.
Data Source
AI summary
Techniques for mapping policy documents to regulatory documents to check for compliance between the policies and documents are provided. In one example, a computer-implemented method determining, by a system operatively coupled to a processor, an information input, a control framework, and a document from a first group consisting of a regulatory document and a policy document, wherein the information input is a corpora from a second group consisting of a domain corpora and a global corpora. The computer-implemented method can also comprise mapping, by the system, the received regulatory document or the received policy document to the control framework using a supervised machine learning technique.