Human-in-the-Loop RPA Training for User-Specific Workflow Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robotic process automation (RPA) technologies struggle to adapt to the specific needs of individual users, leading to inefficiencies and suboptimal performance.
Innovation Solution
A human-in-the-loop robot training system that utilizes a listener to monitor user interactions with RPA robots, log data, and transmit it to a server for analysis. The server determines if modifications are needed to the RPA workflow and inserts activities or sequences of activities to personalize the robot's functionality for the user.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If RPA robots are deployed based on anticipated general functionality needs, then the robots can perform standard tasks, but they cannot adapt to the specific needs of individual users
Solution Approach 1:
The system implements feedback by monitoring user interactions with the RPA robot through a listener component that captures exceptions and usage patterns. This feedback loop enables the server to analyze logged data and automatically modify workflows to better suit individual user needs, transforming a static general-purpose robot into an adaptive user-specific assistant without requiring complex manual reconfiguration
Solution Approach 2:
The RPA robot system performs self-service by automatically learning from user interactions and modifying its own workflows. The server analyzes logged exception data and autonomously inserts corrective activities or sequence modifications into the workflow, enabling the robot to self-improve and adapt to user preferences without external intervention or complex programming
2Reliability
If the RPA workflow is modified to address user-specific exceptions, then the robot performance improves, but the workflow complexity increases
Solution Approach 1:
The system segments the workflow modification process by isolating exception handling into distinct, insertable activity blocks. When the server identifies a recurring exception pattern, it creates modular corrective activities that can be inserted at specific points in the workflow without redesigning the entire process. This segmentation maintains workflow readability and manageability while improving reliability
Solution Approach 2:
The system applies preliminary action by proactively inserting corrective activities into the workflow based on predicted exception patterns. The server analyzes logged data to identify potential failure points and pre-empts issues by adding preventive activities or alternative paths before exceptions occur, thereby improving reliability without requiring complex reactive error handling
Data Source
AI summary
Human-in-the-loop robot training using artificial intelligence (AI) for robotic process automation (RPA) is disclosed. This may be accomplished by a listener robot watching interactions of a user or another robot with a computing system. Based on the interactions by the user or robot with the computing system, the robot may be improved and/or personalized for the user or a group of users.