Task Mining Engine for Cross-System RPA Workflow Automation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional operating and software systems lack the ability to provide automation for data and process mining across distinct and separate operating and software systems, necessitating integration of automation into these processes.
Innovation Solution
A task mining engine is implemented, utilizing artificial intelligence to monitor, evaluate, and automate user activity by clustering recorded tasks into steps and extracting sequences to generate automation code that mimics user activity, thereby integrating robotic process automation across computing environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional operating and software systems are used for data and process mining, then data mining and process analysis can be performed within individual systems, but automation cannot be provided across distinct and separate operating and software systems
Solution Approach 1:
The patent implements a universal task mining engine that can operate across multiple distinct operating systems and software applications. The system records, clusters, and extracts tasks from various sources (Windows, macOS, web browsers, desktop applications) using a single unified platform, enabling automated process mining that works universally across different computing environments without requiring system-specific implementations
Solution Approach 2:
The task mining engine serves as an intermediary layer between users and multiple operating systems/software applications. It captures user interactions at the interface level rather than requiring deep integration into each individual system, allowing it to mine tasks across Windows, macOS, and web environments through a common mediation platform that translates diverse system interactions into unified process models
2Productivity
If manual user activity monitoring is performed without automation, then detailed task analysis can be conducted, but the process requires significant human time and effort
Solution Approach 1:
The system implements self-service automation where the task mining engine automatically records user interactions, clusters similar tasks, extracts process sequences, and generates automation-ready outputs without requiring manual intervention. The system serves itself by autonomously capturing screen activities, processing recorded tasks through clustering algorithms, and producing structured process models, eliminating the need for human analysts to manually observe and document each task
Solution Approach 2:
The patent replaces manual mechanical task analysis with automated computational processing. Instead of human analysts manually recording and analyzing tasks, the system uses automated task mining technology that captures user interactions through software agents, processes the data through clustering algorithms, and extracts process sequences computationally, substituting human cognitive and manual labor with automated information processing systems
3Loss of information
If comprehensive task recording is performed across all user activities, then complete process visibility is achieved, but data processing and clustering complexity increases
Solution Approach 1:
The system extracts only the essential and relevant features from comprehensive task recording data. The task mining engine captures complete user activities but then extracts key characteristics such as task sequences, interaction patterns, and process boundaries for clustering analysis. This extraction approach maintains complete data visibility while reducing processing complexity by focusing computational resources on the most significant task attributes rather than processing every raw data point equally
Data Source
AI summary
Disclosed herein is a method implemented by a task mining engine. The task mining engine is stored as processor executable code on a memory. The processor executable code is executed by a processor that is communicatively coupled to the memory. The method includes receiving recorded tasks identifying user activity with respect to a computing environment and clustering the recorded user tasks into steps by processing and scoring each recorded user task. The method also includes extracting step sequences that identify similar combinations or repeated combinations of the steps to mimic the user activity.