AI Model Rule Engine Update Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Updating rule engines using artificial intelligence models is hindered by the need for specific training data, complexity in interpreting rule engine intricacies, and the lack of explainability in unsupervised models.
Innovation Solution
The system detects when a rule engine should be updated and generates code to improve its performance without requiring specific training data. This is achieved by using artificial intelligence models to modify inputs and compare outputs, determining when modifications are needed based on differences in output characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If artificial intelligence models are trained to directly create or update rule engines, then the ability to automate complex decision-making processes is improved, but the time and resources required for training data generation and model training increase significantly
Solution Approach 1:
The system performs preliminary actions by using the artificial intelligence model to generate modified rule engine scripts before actual deployment. The model analyzes historical data and generates potential updates in advance, allowing the system to evaluate multiple scenarios without requiring extensive training data generation time during production updates.
Solution Approach 2:
The system creates a copy of the rule engine script and uses the artificial intelligence model to generate modifications on this copy. The modified script is then compared with the original to determine if updates are needed, avoiding the need to train the model on every specific rule engine configuration and reducing training data requirements.
2Measurement precision
If artificial intelligence models are trained with high specificity to learn effectively, then the accuracy of rule engine updates is improved, but the labor intensity of training data labeling increases
Solution Approach 1:
The system employs self-service mechanisms where the artificial intelligence model automatically analyzes historical data and generates modified rule engine scripts without requiring manual labeling of training data. The model independently determines updates by comparing its generated modifications against the original script and evaluation criteria, eliminating labor-intensive data labeling while maintaining update accuracy.
3Adaptability or versatility
If unsupervised artificial intelligence models are used to update rule engines, then the flexibility and adaptability of the system is improved, but the explainability of the update decisions deteriorates
Solution Approach 1:
The system implements feedback mechanisms where the artificial intelligence model's generated modifications are evaluated against predefined criteria and compared with the original rule engine script. This feedback loop provides explainability by showing what changes were made and why, while the unsupervised nature of the model maintains its adaptability to different rule engine configurations and historical data patterns.
Data Source
AI summary
The systems and methods provide a model deployment criterion. The model deployment criterion indicates a difference in a value against which the proxy model may be measured to determine when, if ever, the proxy model should be deployed to replace the existing rule engine. The model deployment criterion may be keyed to the proxy model (e.g., based on a difference in its size, throughput speed, number of changes, etc.), the existing rule engine (e.g., based on a difference in its age, update occurrences to its rule base, etc.), and/or comparisons between models (e.g., based on differences in results, throughput speed, efficiency, etc.).