ML Rule Extraction for Automated Process Workflows
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current process management systems lack efficient automation capabilities, relying heavily on manual intervention and requiring complex rules for decision-making, which hampers productivity and accuracy in processes like approval workflows.
Innovation Solution
The implementation of a machine learning model that extracts and evaluates rules from historical data to determine a set of optimized rules for automated process execution, using decision trees to predict outcomes and reduce manual interaction by integrating these rules into process workflows.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual intervention is used for process execution, then flexibility and judgment can be applied, but productivity and efficiency are reduced
Solution Approach 1:
The system enables processes to execute themselves by automatically extracting rules from historical data through machine learning models. The process management system autonomously analyzes past process executions, identifies patterns, and generates executable rules without requiring continuous manual intervention, thereby achieving self-service automation while maintaining productivity.
Solution Approach 2:
The patent replaces manual mechanical decision-making with an automated machine learning-based rule extraction system. The system uses computational algorithms to analyze historical data and generate execution rules, substituting the mechanical process of manual review and decision-making with an automated electronic system that operates continuously without human intervention.
2Measurement precision
If complex rules are used for decision-making, then accuracy can be improved, but device complexity and ease of operation are reduced
Solution Approach 1:
The system extracts only the essential rules from complex historical process data using machine learning algorithms. By taking out and isolating the critical decision-making patterns from the overwhelming amount of historical data, the system achieves high accuracy without requiring complex manual rule definitions. The extracted rules are simplified and directly executable, reducing operational complexity while maintaining precision.
Solution Approach 2:
The patent transforms complex decision-making parameters into simplified executable rules through machine learning analysis. The system changes the representation of complex decisions into a standardized rule format that is easier to process and execute, converting complex manual judgment parameters into automated computational parameters that maintain accuracy while reducing operational complexity.
3Extent of automation
If rules are extracted from historical data, then automation capability is improved, but loss of information may occur during data processing
Solution Approach 1:
The system implements feedback mechanisms where extracted rules are validated against historical data to ensure accuracy. The machine learning model continuously refines rule extraction by comparing predicted outcomes with actual historical results, providing feedback that prevents information loss and ensures the extracted rules accurately represent the underlying process logic while maintaining automation capability.
Data Source
AI summary
The present disclosure relates to computer-implemented methods, software, and systems for utilizing tools and techniques for identifying process rules for automated execution of instances of a process workflow. One example method includes extracting rules from a machine learning model for prediction of execution results of process workflow instances. Metrics defining coverage and accuracy of the rules are calculated. The rules are evaluated according to the metrics and are reduced to a first set of rules that are provided for further evaluation. A rule from the first set of rules is determined to be incorporated into process rules defined for the process workflow at a process execution engine. The process rules associated with execution of the process workflow are updated to include the first rule and to generate a process result automatically according to the first rule when the instance complies with prerequisites defined at the first rule.