GPTVoiceTasker: Advancing Multi-step Mobile Task Efficiency Through Dynamic Interface Exploration and Learning

要旨

Virtual assistants have the potential to play an important role in helping users achieve different tasks. However, these systems face challenges in their real-world usability, characterized by inefficiency and struggles in grasping user intentions. Leveraging recent advances in Large Language Models (LLMs), we introduce GPTVoiceTasker, a virtual assistant poised to enhance user experiences and task efficiency on mobile devices. GPTVoiceTasker excels at intelligently deciphering user commands and executing relevant device interactions to streamline task completion. For unprecedented tasks, GPTVoiceTasker utilises the contextual information and on-screen content to continuously explore and execute the tasks. In addition, the system continually learns from historical user commands to automate subsequent task invocations, further enhancing execution efficiency. From our experiments, GPTVoiceTasker achieved 84.5% accuracy in parsing human commands into executable actions and 85.7% accuracy in automating multi-step tasks. In our user study, GPTVoiceTasker boosted task efficiency in real-world scenarios by 34.85%, accompanied by positive participant feedback. We made GPTVoiceTasker open-source, inviting further research into LLMs utilization for diverse tasks through prompt engineering and leveraging user usage data to improve efficiency.

著者
Minh Duc Vu
CSIRO's Data61, Clayton, Victoria, Australia
Han Wang
Monash University, Melbourne, VIC, Australia
Jieshan Chen
CSIRO's Data61, Sydney, New South Wales, Australia
Zhuang Li
Monash University, Melbourne, Australia
Shengdong Zhao
City University of Hong Kong, Hong Kong, China
Zhenchang Xing
CSIRO's Data61 & Australian National University, ACTON, ACT, Australia
Chunyang Chen
Technical University of Munich, Heilbronn, Germany
論文URL

https://doi.org/10.1145/3654777.3676356

動画

会議: UIST 2024

ACM Symposium on User Interface Software and Technology

セッション: 3. Machine Learning for User Interfaces

Westin: Allegheny 3
5 件の発表
2024-10-15 18:00:00
2024-10-15 19:15:00