Cognitive AI Layer for RPA Workflow Error Detection and Runtime Repair
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing RPA workflows often contain errors and inefficiencies due to developer mistakes and runtime issues caused by UI changes or system updates, which current technologies fail to adequately address.
Innovation Solution
A cognitive AI layer is integrated into RPA workflows to provide a smart analyzer and smart handler that monitor and suggest improvements or automatically correct errors and inefficiencies during design time and runtime, utilizing generative AI models to understand intent and logical flows.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional RPA workflow development is used without AI assistance, then developers have full control over workflow creation, but errors and inefficiencies are introduced into the workflow logic
Solution Approach 1:
The smart analyzer continuously monitors RPA workflow development and provides real-time feedback to developers about potential errors, inefficiencies, and best practices. This feedback mechanism allows developers to correct issues during the design phase rather than discovering them during runtime, improving both reliability and development efficiency
Solution Approach 2:
The system enables automated self-correction of workflow issues through AI-generated suggestions that can be automatically applied. The cognitive AI layer analyzes the workflow logic and autonomously identifies problems, generating repair suggestions without requiring manual developer intervention for every issue
2Reliability
If RPA automations are deployed without cognitive AI layer, then deployment is simple and quick, but runtime issues occur due to unexpected conditions in UI, changes to applications or operating system
Solution Approach 1:
The cognitive AI layer acts as an intermediary between the RPA automation and the dynamic environment (UI, applications, operating system). It monitors runtime conditions and intervenes when unexpected changes occur, providing adaptive responses that maintain runtime stability without requiring complex reconfiguration of the entire system
Solution Approach 2:
The system transitions from static, rigid RPA workflows to dynamic, adaptive automations that can respond to changing runtime conditions. The smart handler continuously adapts the automation behavior based on real-time monitoring of UI changes, application updates, and system variations, maintaining reliability in dynamic environments
3Productivity
If manual monitoring and correction of RPA workflows is used, then simple system architecture is maintained, but time-consuming and resource-intensive operations occur
Solution Approach 1:
The smart analyzer performs preliminary analysis of RPA workflows during the design phase, identifying potential errors and inefficiencies before the automation is deployed. This preliminary detection and correction prevents issues from reaching runtime, significantly reducing the time required for error detection and correction while improving workflow optimization speed
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A design time smart analyzer and a runtime smart handler for robotic process automation (RPA) are disclosed that use a cognitive artificial intelligence (Al) layer to provide suggestions for an RPA workflow and an RPA automation, respectively. The smart analyzer analyzes an RPA workflow under development to check for errors and inefficiencies. The smart handler attempts to optimize and/or repair RPA automations at runtime.