Skip navigation

DSpace

機構典藏 DSpace 系統致力於保存各式數位資料(如:文字、圖片、PDF)並使其易於取用。

點此認識 DSpace
DSpace logo
English
中文
  • 瀏覽論文
    • 校院系所
    • 出版年
    • 作者
    • 標題
    • 關鍵字
    • 指導教授
  • 搜尋 TDR
  • 授權 Q&A
    • 我的頁面
    • 接受 E-mail 通知
    • 編輯個人資料
  1. NTU Theses and Dissertations Repository
  2. 電機資訊學院
  3. 資訊工程學系
請用此 Handle URI 來引用此文件: http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/98186
完整後設資料紀錄
DC 欄位值語言
dc.contributor.advisor廖世偉zh_TW
dc.contributor.advisorShih-Wei Liaoen
dc.contributor.author高子維zh_TW
dc.contributor.authorTzu-Wei Kaoen
dc.date.accessioned2025-07-30T16:15:31Z-
dc.date.available2025-07-31-
dc.date.copyright2025-07-30-
dc.date.issued2025-
dc.date.submitted2025-07-22-
dc.identifier.citationP. Authors. Paddleocr, awesome multilingual ocr toolkits based on paddlepaddle. https://github.com/PaddlePaddle/PaddleOCR, 2020.
C. Bai and et al. Uibert: Learning generic multimodal representations for ui understanding. arXiv preprint arXiv:2107.13731, 2021.
I.-H. Chang and S.-W. Liao. Video action localization: A comprehensive approach to mobile critical user journey and automated mobile testing dataset generation, 2024.
Z. Chen, L. Mou, Y. Song, H.-T. Zheng, G. Li, L. Fu, and Y. Ning. Actionbert: Leveraging user interface information for action prediction in gui. CoRR, abs/2012.12350, 2020.
R. K. Deka et al. Rico: A mobile app dataset for building data-driven design applications. In Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology, pages 845–854. ACM, 2017.
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova. BERT: Pre-training of deep bidirectional transformers for language understanding. In J. Burstein, C. Doran, and T. Solorio, editors, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota, June 2019. Association for Computational Linguistics.
S. Feng and C. Chen. Gifdroid: Automated replay of visual bug reports for android apps, 2022.
L. Gomez, I. Neamtiu, T. Azim, and T. Millstein. Reran: Timing- and touch-sensitive record and replay for android. In 2013 35th International Conference on Software Engineering (ICSE), pages 72–81, 2013.
H. Guo. A simple algorithm for fitting a gaussian function [dsp tips and tricks]. IEEE Signal Processing Magazine, 28(5):134–137, 2011.
K. Lin et al. Android in the wild: A large-scale dataset for android device control. arXiv preprint arXiv:2307.10088, 2023.
T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár. Focal loss for dense object detection, 2018.
O. Ronneberger, P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015, 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III, pages 234-241. Springer, 2015.
P. Sahoo, A. K. Singh, S. Saha, V. Jain, S. Mondal, and A. Chadha. A systematic survey of prompt engineering in large language models: Techniques and applications, 2025.
G. Team and P. G. et al. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context, 2024.
J. Wei, X. Wang, D. Schuurmans, M. Bosma, B. Ichter, F. Xia, E. Chi, Q. Le, and D. Zhou. Chain-of-thought prompting elicits reasoning in large language models, 2023.
S. Yamanaka, H. Usuba, and J. Sato. Behavioral differences between tap and swipe: Observations on time, error, touch-point distribution, and trajectory for tap-and-swipe enabled targets. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, CHI ’24, New York, NY, USA, 2024. Association for Computing Machinery.
J. Yang, H. Zhang, F. Li, X. Zou, C. Li, and J. Gao. Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v, 2023.
S. Yu, C. Fang, Z. Tuo, Q. Zhang, C. Chen, Z. Chen, and Z. Su. Vision-based mobile app gui testing: A survey, 2024.
J. Zhang, J. Wu, Y. Teng, M. Liao, N. Xu, X. Xiao, Z. Wei, and D. Tang. Android in the zoo: Chain-of-action-thought for gui agents, 2024.
Z. Zhang and A. Zhang. You only look at screens: Multimodal chain-of-action agents, 2024.
Y. Zhao and et al. Vision-language models for vision tasks: A survey. arXiv preprint arXiv:2304.00685, 2023.
Z. Zhong et al. Uied: A hybrid tool for gui element detection. In Proceedings of the 28th ACM International Conference on Multimedia, pages 1759–1767. ACM, 2020.
Özgün Çiçek, A. Abdulkadir, S. S. Lienkamp, T. Brox, and O. Ronneberger. 3du-net: Learning dense volumetric segmentation from sparse annotation, 2016.
-
dc.identifier.urihttp://tdr.lib.ntu.edu.tw/jspui/handle/123456789/98186-
dc.description.abstract本研究提出一個以「行動思維鏈」(Chain-of-Action-Thought, CoAT)為核心的可擴展行動裝置使用者介面資料集自動化生成流程。該流程透過視覺語言模型模擬真實使用者互動,涵蓋畫面描述、行為推理、動作執行與結果驗證,無需人工參與即可產生高品質的互動資料集。資料集包含原始截圖、標註之介面元件、動作動畫以及詳細的語意推理紀錄。
為驗證資料集之有效性,我們提出一個多模態模型,結合 3D U-Net 用於視覺訊號處理,與 BERT 編碼器處理經由 OCR 擷取的文字資訊。我們以 AITW 與本研究資料集進行多組訓練與測試組合實驗。結果顯示,本資料集能提升動作定位準確性,尤其對滑動操作具優勢。本研究為行動裝置使用者介面測試之中的使用者操作定位提供一套完整解方。
zh_TW
dc.description.abstractThis work presents a fully automated pipeline for scalable mobile UI dataset generation, driven by a Chain-of-Action-Thought (CoAT) framework. The pipeline simulates realistic user interactions using a vision-language model to describe screen content, reason through actions, execute commands, and validate outcomes—without human intervention. The resulting dataset includes raw screenshots, annotated UI elements, action animations,and detailed semantic reasoning traces.
To demonstrate the effectiveness of the generated dataset, we introduce a multimodal model that combines 3D U-Net for visual understanding and a BERT encoder for processing textual information extracted via OCR. We evaluate this model across different training and testing configurations, using both AITW and our dataset. Results show that our dataset improves action localization performance, particularly for swipe-based interactions. This work contributes a robust solution for user action localization in mobile GUI testing.
en
dc.description.provenanceSubmitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-07-30T16:15:31Z
No. of bitstreams: 0
en
dc.description.provenanceMade available in DSpace on 2025-07-30T16:15:31Z (GMT). No. of bitstreams: 0en
dc.description.tableofcontentsVerification Letter from the Oral Examination Committee i
Acknowledgements ii
摘要 iii
Abstract iv
Contents vi
List of Figures viii
List of Tables ix
Chapter 1 Introduction 1
Chapter 2 Related Work 4
2.1 Mobile UI Dataset Collection . . . . . . . . . . . . . . . . . . . . . 4
2.2 Performance-Enhanced Techniques of Large Language Model Agents 6
2.3 UI Element Detection and Screen Text Understanding . . . . . . . . 7
2.4 Mobile GUI Testing with Vision-Language Models . . . . . . . . . . 8
Chapter 3 Methodology 11
3.1 Automated Mobile Phone UI Dataset Generation Pipeline . . . . . . 11
3.1.1 Environment Setup . . . . . . . . . . . . . . . . . . . . . . . . . . 12
3.1.2 Pipeline Structure . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
3.1.3 Pipeline Parameter Setup . . . . . . . . . . . . . . . . . . . . . . . 14
3.2 Vision Language Model For Action Localization . . . . . . . . . . . 15
3.2.1 Swipe Action Detection . . . . . . . . . . . . . . . . . . . . . . . . 15
3.2.2 Model Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . 16
Chapter 4 Evaluation 20
4.1 Mobile Phone UI Dataset Evaluation . . . . . . . . . . . . . . . . . 20
4.2 Automated Dataset Generation Pipeline CoAT Ablation Study . . . . 22
4.3 Model Evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
Chapter 5 Conclusion 28
References 32
Appendix A — Justification for Swipe Action Design 35
Appendix B — Examples of Our Dataset 37
Appendix C — Prompts to LLM Agents 38
C.1 System Instruction for Execution Agent . . . . . . . . . . . . . . . . 38
C.2 Screen Description Prompts . . . . . . . . . . . . . . . . . . . . . . 40
C.3 Action Think Prompts . . . . . . . . . . . . . . . . . . . . . . . . . 41
C.4 Action Execution Prompts . . . . . . . . . . . . . . . . . . . . . . . 42
C.5 System Instructions for Validation Agent . . . . . . . . . . . . . . . 43
C.6 Results Validation Prompts . . . . . . . . . . . . . . . . . . . . . . . 44
-
dc.language.isoen-
dc.subject行動裝置圖像使用者介面測試zh_TW
dc.subject行動裝置使用者介面資料集zh_TW
dc.subject使用者操作定位zh_TW
dc.subject行動思維鏈zh_TW
dc.subject視覺語言模型zh_TW
dc.subjectUser Action localizationen
dc.subjectMobile GUI testingen
dc.subjectVision-Language Modelen
dc.subjectChain-of-Action-Thoughten
dc.subjectMobile UI Dataseten
dc.title運用行動思維鏈及多模態模型進行可擴展自動化行動裝置使用者介面資料集生成及使用者操作定位zh_TW
dc.titleScalable Automated Mobile UI Dataset Generation Using Chain-of-Action-Thought Framework and Multimodal Models for User Action Localizationen
dc.typeThesis-
dc.date.schoolyear113-2-
dc.description.degree碩士-
dc.contributor.oralexamcommittee傅楸善;黃上恩;葉春超;吳昆達zh_TW
dc.contributor.oralexamcommitteeChiou-Shann Fuh;Shang-En Huang;Chun-Chao Yeh;Kun-Da Wuen
dc.subject.keyword行動裝置圖像使用者介面測試,行動裝置使用者介面資料集,使用者操作定位,行動思維鏈,視覺語言模型,zh_TW
dc.subject.keywordMobile GUI testing,Mobile UI Dataset,User Action localization,Chain-of-Action-Thought,Vision-Language Model,en
dc.relation.page44-
dc.identifier.doi10.6342/NTU202502184-
dc.rights.note未授權-
dc.date.accepted2025-07-23-
dc.contributor.author-college電機資訊學院-
dc.contributor.author-dept資訊工程學系-
dc.date.embargo-liftN/A-
顯示於系所單位:資訊工程學系

文件中的檔案:
檔案 大小格式 
ntu-113-2.pdf
  未授權公開取用
1.94 MBAdobe PDF
顯示文件簡單紀錄


系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。

社群連結
聯絡資訊
10617臺北市大安區羅斯福路四段1號
No.1 Sec.4, Roosevelt Rd., Taipei, Taiwan, R.O.C. 106
Tel: (02)33662353
Email: ntuetds@ntu.edu.tw
意見箱
相關連結
館藏目錄
國內圖書館整合查詢 MetaCat
臺大學術典藏 NTU Scholars
臺大圖書館數位典藏館
本站聲明
© NTU Library All Rights Reserved