Fallback AI System for Redundant Decision-Making During Failover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
AI systems in production computing environments may fail due to various conditions such as fraud or computing attacks, leading to disruptions in decision-making and potential fraud, which existing technologies do not adequately address for seamless redundancy.
Innovation Solution
A fallback AI system is trained using monitored input/output data from a primary AI system, employing machine learning or neural network algorithms to provide redundancy during failover conditions, ensuring continuous AI decision-making with policy layers for risk management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a primary AI system is deployed for automated decision-making in a production computing environment, then productivity and automation are improved, but system reliability deteriorates due to potential failures and timeouts
Solution Approach 1:
The patent implements a fallback AI system that is trained in advance on historical input/output data from the primary AI system. This preliminary training ensures that when the primary system fails, the fallback system can immediately take over without interruption to decision-making operations, thus resolving the contradiction between productivity and reliability.
Solution Approach 2:
The patent establishes a redundant fallback AI system as a protective measure before the primary system fails. This cushioning mechanism absorbs the impact of potential failures by having a pre-trained backup system ready to assume operations, thereby maintaining system availability while the primary system performs automated decision-making.
2Reliability
If a fallback AI system is implemented for redundancy, then system reliability is improved during failover conditions, but device complexity increases
Solution Approach 1:
The patent creates a fallback AI system that copies the decision-making capabilities of the primary system by training on historical input/output data. This copying approach allows the fallback system to replicate essential functions without requiring a complete duplicate architecture, thus improving reliability while limiting the increase in complexity.
Solution Approach 2:
The fallback AI system is designed to perform multiple functions: it serves as a backup during failures, learns from historical data, and can take over decision-making operations seamlessly. This multi-functionality reduces the need for separate specialized components, thereby improving reliability without proportionally increasing system complexity.
3Productivity
If the primary AI system fails or times out, then system reliability deteriorates, but maintaining continuous operation requires additional redundancy mechanisms
Solution Approach 1:
The fallback AI system is trained in advance on historical data so that when the primary system fails, it can immediately provide continuous decision-making operations without requiring complex real-time analysis or additional redundancy mechanisms during the failure event.
Data Source
AI summary
There are provided systems and methods for a fallback artificial intelligence (AI) system for redundancy during system failover. A service provider may provide AI systems for automated decision-making, such as for risk analysis, marketing, and the like. An AI system may operate in a production computing environment in order to provide AI decision-making based on input data, for example, by providing an output decision. In order to provide redundancy to the production AI system, the service provider may train a fallback AI system using the input/output data pairs from the production AI system. This may utilize a deep neural network and a continual learning trainer. Thereafter, when a failover condition is detected for the production AI system, the service provider may switch from the production AI system to the fallback AI system, which may provide decision-making operations during failure of within the production computing environment.