Help, It Looks Confusing: GUI Task Automation Through Demonstration and Follow-up Questions

TL;DR

This paper introduces HILC, a user-in-the-loop system that enables non-programmers to create automation scripts through demonstration and follow-up questions, effectively handling complex GUI tasks.

Contribution

The paper presents a novel demonstration-based framework with follow-up queries that improves script generation for GUI automation by non-programmers.

Findings

HILC outperforms Sikuli Slides in user study tasks.

Users can efficiently teach HILC to perform complex GUI tasks.

HILC requires less training time compared to baseline systems.

Abstract

Non-programming users should be able to create their own customized scripts to perform computer-based tasks for them, just by demonstrating to the machine how it's done. To that end, we develop a system prototype which learns-by-demonstration called HILC (Help, It Looks Confusing). Users train HILC to synthesize a task script by demonstrating the task, which produces the needed screenshots and their corresponding mouse-keyboard signals. After the demonstration, the user answers follow-up questions. We propose a user-in-the-loop framework that learns to generate scripts of actions performed on visible elements of graphical applications. While pure programming-by-demonstration is still unrealistic, we use quantitative and qualitative experiments to show that non-programming users are willing and effective at answering follow-up queries posed by our system. Our models of events and appearance are surprisingly simple, but are combined effectively to cope with varying amounts of supervision. The best available baseline, Sikuli Slides, struggled with the majority of the tests in our user study experiments. The prototype with our proposed approach successfully helped users accomplish simple linear tasks, complicated tasks (monitoring, looping, and mixed), and tasks that span across multiple executables. Even when both systems could ultimately perform a task, ours was trained and refined by the user in less time.