Autonomous GRC Program Generation via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current GRC systems require manual user input for generating computer programs to set field values, which can neglect relationships between objects and require prior knowledge of proprietary syntax and programming, limiting efficiency and accuracy.
Innovation Solution
A method and system that uses machine learning to detect changes in GRC objects, generate snapshots, train models to identify relationships, and autonomously generate computer programs to set field values, eliminating the need for manual coding and prior knowledge of object correlations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual user input is used to generate computer programs for setting field values, then users can control the program generation process, but the process requires prior knowledge of proprietary syntax and programming, increasing the difficulty of operation
Solution Approach 1:
The system performs program generation automatically without requiring user input of syntax or programming knowledge. The machine learning model autonomously analyzes object relationships and generates executable programs, allowing the system to serve itself in the program generation task rather than relying on user expertise.
Solution Approach 2:
The patent replaces the mechanical process of manual programming with an automated machine learning system. Instead of users manually writing code according to proprietary syntax, the system uses trained models to automatically generate programs based on detected object relationships, substituting human cognitive effort with automated intelligence.
2Measurement precision
If manual user input is used to generate computer programs, then users can specify field values, but the process neglects relationships between objects, reducing the accuracy of program generation
Solution Approach 1:
The system uses feedback from detecting changes among objects to continuously improve program generation. The machine learning model analyzes the relationships between objects and uses this feedback to automatically adjust and generate appropriate field value settings, ensuring that object relationships are properly considered without manual intervention.
Solution Approach 2:
The system performs preliminary analysis of object relationships and change detection before generating the final program. By pre-processing the data to identify relationships among objects and detect changes, the system prepares the necessary information in advance, enabling accurate and efficient program generation without requiring users to manually specify all parameters.
3Extent of automation
If manual coding is required for GRC program generation, then users can customize programs, but the process requires prior knowledge of programming, increasing the time required for program creation
Solution Approach 1:
The system autonomously generates executable programs without requiring user coding or customization input. The machine learning model self-services the program generation task by automatically analyzing object relationships and producing ready-to-execute code, eliminating the time users would spend on manual programming while maintaining full customization based on detected relationships.
Solution Approach 2:
The patent replaces the time-consuming mechanical process of manual coding with automated machine learning. The system substitutes human programming activities with automated model inference, generating customized programs instantaneously based on detected object relationships and changes, thereby dramatically reducing the time required for program creation.
4Ease of operation
If users manually specify all field values and relationships, then complete control is achieved, but the process requires knowledge of all object correlations, increasing the complexity of operation
Solution Approach 1:
The system automatically detects and learns object correlations through change detection and machine learning. By continuously monitoring relationships among objects and using this feedback to generate appropriate field values, the system captures and utilizes object correlation information without requiring users to manually know or specify these relationships, thereby preserving information while simplifying operation.
Solution Approach 2:
The patent replaces the need for users to manually specify object correlations with automated machine learning detection. The system substitutes human knowledge of object relationships with automated inference capabilities, allowing the model to discover and utilize correlations among objects without user intervention, thus eliminating the requirement for specialized knowledge while maintaining complete field value control.
Data Source
AI summary
Methods and systems for generating a computer program for a governance, risk, compliance (GRC) system are described. In an example, a processor may detect a change among a plurality of objects in the GRC system. The processor may generate a snapshot of the plurality of objects in response to the detected change. The snapshot may include the detected change among the plurality of objects. The processor may train a machine learning model using the snapshot. The trained machine learning model may indicate relationships among a set of related objects, where the related objects may be among the plurality of objects. The processor may generate a computer program based on the trained machine learning model. The computer program may include a set of instructions for setting a field value of an object among the set of related objects.