AI Listener Logging for Accurate RPA Workflow Discovery

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current robotic process automation (RPA) techniques are inefficient in identifying and automating repetitive tasks, as they rely on costly and time-consuming manual logging and review of user actions, often resulting in inaccurate process identification and suboptimal automation workflows.

Innovation Solution

An AI-based system that deploys listener applications on user computing systems to generate logs of user interactions, which are then analyzed by AI layers to identify potential RPA processes, automatically generating workflows and robots to automate these processes without user intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual logging and review of user actions is used to identify automation opportunities, then process identification can be performed, but it is costly and time-consuming

Engineering Contradiction:

Improveprocess identification accuracyVSAvoidtime to identify automation opportunities

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the mechanical manual review process with an AI-based automated analysis system. The AI system processes logs of user actions automatically to identify repetitive tasks and automation opportunities, eliminating the need for human reviewers to manually examine logs while maintaining or improving identification accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service automation opportunity identification by having the AI system autonomously analyze user action logs and generate automation recommendations without requiring manual intervention. The system serves itself by automatically processing the data and producing actionable insights.

Inventive Principle:

Principle #25Self-service

2Measurement precision

If manual logging and review of user actions is used to identify automation opportunities, then process identification can be performed, but it is costly

Engineering Contradiction:

Improveprocess identification accuracyVSAvoidcost to identify automation opportunities

Core Design Contradiction:

Measurement precisionVSLoss of energy

Solution Approach 1:

The patent replaces expensive manual review processes with automated AI analysis. The AI system processes logs of user actions to identify automation opportunities without requiring human reviewers, thereby reducing the cost associated with manual labor while maintaining identification accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system uses disposable, low-cost computational resources to process logs automatically rather than relying on expensive human expertise. The AI system can process large volumes of log data at minimal cost compared to paying reviewers to manually analyze the same data.

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

3Loss of information

If a human reviewer analyzes video recordings to generate logs of user actions, then process documentation can be created, but it is too expensive and time consuming to be practical

Engineering Contradiction:

Improveaccuracy of user action captureVSAvoidefficiency of automation identification

Core Design Contradiction:

Loss of informationVSProductivity

Solution Approach 1:

Instead of having humans watch video recordings to create logs, the system inverts the approach by using AI to automatically generate logs directly from structured log data. This eliminates the need for video review while capturing the same or better information about user actions.

Inventive Principle:

Principle #13The other way round (Inversion)

Solution Approach 2:

The patent replaces the manual video review mechanism with automated log analysis using AI. The system processes structured logs that capture user actions programmatically, eliminating the need for human reviewers to watch and interpret video recordings, thereby dramatically improving efficiency.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Loss of information

If manual review of video recordings is used to capture user actions, then process documentation can be created, but the reviewer's account may not be accurate

Engineering Contradiction:

Improveaccuracy of user action captureVSAvoidtime for manual review

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The patent replaces subjective human interpretation of video recordings with objective AI-based log analysis. The system processes structured logs that automatically capture user actions, eliminating human error and subjectivity while maintaining accuracy and reducing review time.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11541548B2Artificial intelligence-based process identification, extraction, and automation for robotic process automation

Publication Date: 2023.01.03 UIPATH INC

AI summary

Artificial intelligence (AI)-based process identification, extraction, and automation for robotic process automation (RPA) is disclosed. Listeners may be deployed to user computing systems to collect data pertaining to user actions. The data collected by the listeners may then be sent to one or more servers and be stored in a database. This data may be analyzed by AI layers to recognize patterns of user behavioral processes therein. These recognized processes may then be distilled into respective RPA workflows and deployed to automate the processes.