Saved in:
Bibliographic Details
Main Authors: Huang, Forrest, Li, Gang, Li, Tao, Li, Yang
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.07023
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910411545116672
author Huang, Forrest
Li, Gang
Li, Tao
Li, Yang
author_facet Huang, Forrest
Li, Gang
Li, Tao
Li, Yang
contents Macros are building block tasks of our everyday smartphone activity (e.g., "login", or "booking a flight"). Effectively extracting macros is important for understanding mobile interaction and enabling task automation. These macros are however difficult to extract at scale as they can be comprised of multiple steps yet hidden within programmatic components of mobile apps. In this paper, we introduce a novel approach based on Large Language Models (LLMs) to automatically extract semantically meaningful macros from both random and user-curated mobile interaction traces. The macros produced by our approach are automatically tagged with natural language descriptions and are fully executable. We conduct multiple studies to validate the quality of extracted macros, including user evaluation, comparative analysis against human-curated tasks, and automatic execution of these macros. These experiments and analyses show the effectiveness of our approach and the usefulness of extracted macros in various downstream applications.
format Preprint
id arxiv_https___arxiv_org_abs_2310_07023
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Automatic Macro Mining from Interaction Traces at Scale
Huang, Forrest
Li, Gang
Li, Tao
Li, Yang
Human-Computer Interaction
Computation and Language
Machine Learning
Macros are building block tasks of our everyday smartphone activity (e.g., "login", or "booking a flight"). Effectively extracting macros is important for understanding mobile interaction and enabling task automation. These macros are however difficult to extract at scale as they can be comprised of multiple steps yet hidden within programmatic components of mobile apps. In this paper, we introduce a novel approach based on Large Language Models (LLMs) to automatically extract semantically meaningful macros from both random and user-curated mobile interaction traces. The macros produced by our approach are automatically tagged with natural language descriptions and are fully executable. We conduct multiple studies to validate the quality of extracted macros, including user evaluation, comparative analysis against human-curated tasks, and automatic execution of these macros. These experiments and analyses show the effectiveness of our approach and the usefulness of extracted macros in various downstream applications.
title Automatic Macro Mining from Interaction Traces at Scale
topic Human-Computer Interaction
Computation and Language
Machine Learning
url https://arxiv.org/abs/2310.07023