基於環境與互動情境之手機程式使用預測

Mobile Apps Prediction by Environmental and Interactional Contexts

10.6342/NTU.2014.01514

胡雅婷

智慧型手機 ； 手機程式 ； 情境感知 ； smartphone ； mobile apps ； context-aware

國立臺灣大學電機工程學系學位論文

2014年

碩士

陳銘憲

繁體中文

隨著智慧型手機的普及，手機應用程式的數量急速的增加，並在使 用者的日常生活中扮演不可或缺的角色。我們提出了APEIC 以預測在 不同的使用情境下，使用者會優先使用哪一個程式。預測手機程式使 用的好處包括將需要的程式預先載入記憶體以降低啟動所需的時間， 以及將不需要的程式關掉以避免程式在背景持續消耗手機電力。在這 篇論文裡，情境的描述包含了環境情境和互動情境兩種不同的類型， 前者指的是裝置周遭的環境資訊，比方說時間、空間、使用者的運動 狀態等，而互動情境則是指程式使用的先後順序。我們收集了實際的 手機程式使用資料，進而分析程式的使用情境，將觀察的結果作為設 計預測模型的參考。利用使用者過去的使用紀錄，預測模型學習如何 從當下的環境情境以及互動情境評估每個程式被開啟的機率，以及如 何從已經開啟的程式來推測接下來將會被使用的程式。根據使用者目 前的使用情況，預測模型會自動調整預測的結果以符合當下的使用模 式。我們除了利用收集到的實際資料進行實驗，也根據收集的資料設 計了一個手機使用資料產生器，利用產生器製造的合成資料進行完整 的參數分析。實驗的結果顯示出我們提出的預測不但準確而且適用於 不同的使用模式。結合其他研究夥伴先前提出的應用，我們可以實作 出一個實用的手機應用。程式會在手機螢幕上會顯示一個常駐的啟動 器，列出預測模型依據當前情境，推測使用者目前最有可能使用的手 機程式，並且根據使用者現在的活動以推薦合適的應用程式。

With the growing prevalence of smartphones, there is an increasing number of mobile applications which play important roles in daily life. In this thesis, we propose a framework of APEIC (standing for App Prediction by Environmental and Interactional Contexts) to predict apps that are most likely to be used according to the current context. The context consists of environmental context (EC), which is characterized by features extracted from built-in sensors, and interactional context (IC), which is defined as the app launch sequence. The benefits of such prediction include fast app launching by pre-loading the right apps into memory, and also efficient power management by terminating apps which are not to be used in the near future. We collected real app usage traces and made some observations that provide insights into the design of our prediction model. First, from past traces, we adopt features representing EC to build a naive Bayes classifier and evaluate the launch contributions between apps from IC respectively. Second, from the current condition, Poisson distribution is used to model the re-access pattern of certain apps. Finally, we can rank the apps by the sum of their launch intensities. We conduct experiments on both real data and synthetic data. The results demonstrate the capability and the robustness of our prediction framework. Furthermore, in combination with our companions’ work, we design a smart launcher which helps users have rapid access to the apps they need and recommends other useful apps according to the context at that time.

1. launching for mobile devices using predictive user context. In Proceedings of the
   連結：
2. 113–126. ACM, 2012.
   連結：
3. by exploiting energy and launch delay trade-off of mobile multimedia applications.
   連結：
4. [3] Kristijan Mihalic and Manfred Tscheligi. Interactional context for mobile applications.
   連結：
5. In Proceeding of the 20th International Symposium on Human Factors in
   連結：
6. Telecommunication HFT, pages 20–23, 2006.
   連結：
7. On the feature discovery for app usage prediction in smartphones. In Data Mining
   連結：
8. application usage using contextual information. In Proceedings of the 2012 ACM
   連結：
9. Conference on Ubiquitous Computing, pages 1059–1065. ACM, 2012.
   連結：
10. [6] Ye Xu, Mu Lin, Hong Lu, Giuseppe Cardone, Nicholas Lane, Zhenyu Chen, Andrew
    連結：
11. computers, pages 69–76. ACM, 2013.
    連結：
12. of mobile application usage for smart phones. In Proceedings of the 2012 ACM
    連結：
13. Conference on Ubiquitous Computing, pages 173–182. ACM, 2012.
    連結：
14. dynamic shortcuts to facilitate application launching on mobile devices. Procedia
    連結：
15. prediction using rank-score characteristics. In Cognitive Informatics & Cognitive
    連結：
16. 217. IEEE, 2013.
    連結：
17. [10] Xun Zou, Wangsheng Zhang, Shijian Li, and Gang Pan. Prophet: what app you wish
    連結：
18. Marlin. Practical prediction and prefetch for faster access to applications on mobile
    連結：
19. intelligent launcher for mobile apps based on individual usage patterns. In Proceedings
    連結：
20. ACM, 2013.
    連結：
21. [14] Zhung-Xun Liao, Yi-Chin Pan, Wen-Chih Peng, and Po-Ruey Lei. On mining mobile
    連結：
22. apps usage behavior for predicting apps usage in smartphones. In Proceedings of the 22nd ACM international conference on Conference on information & knowledge
    連結：
23. [15] Donghee Lee, Jongmoo Choi, Jong-Hun Kim, Sam H Noh, Sang Lyul Min, Yookun
    連結：
24. [16] Martin Ester, Hans-Peter Kriegel, Jorg Sander, and Xiaowei Xu. A density-based
    連結：
25. algorithm for discovering clusters in large spatial databases with noise. In Kdd,
    連結：
26. [17] Antti Oulasvirta, Tye Rattenbury, Lingyi Ma, and Eeva Raita. Habits make smartphone
    連結：
27. use more pervasive. Personal and Ubiquitous Computing, 16(1):105–114,
    連結：
28. mining algorithms for market basket databases. Knowledge Discovery in Databases:
    連結：
29. [1] Tingxin Yan, David Chu, Deepak Ganesan, Aman Kansal, and Jie Liu. Fast app
30. 10th international conference on Mobile systems, applications, and services, pages
31. [2] Yi-Fan Chung, Yin-Tsung Lo, and Chung-Ta King. Enhancing user experiences
32. ACM Transactions on Embedded Computing Systems (TECS), 12(1s):37, 2013.
33. [4] Zhung-Xun Liao, Shou-Chung Li, Wen-Chih Peng, Philip S Yu, and Te-Chuan Liu.
34. (ICDM), 2013 IEEE 13th International Conference on, pages 1127–1132. IEEE,
35. 2013.
36. [5] Ke Huang, Chunhui Zhang, Xiaoxiao Ma, and Guanling Chen. Predicting mobile
37. Campbell, and Tanzeem Choudhury. Preference, context and communities: A multifaceted
38. approach to predicting smartphone app usage patterns. In Proceedings of the 17th annual international symposium on International symposium on wearable
39. [7] Choonsung Shin, Jin-Hyuk Hong, and Anind K Dey. Understanding and prediction
40. [8] Chen Sun, Jun Zheng, Huiping Yao, Yang Wang, and D Frank Hsu. Apprush: Using
41. Computer Science, 19:445–452, 2013.
42. [9] Chen Sun, Yang Wang, Jun Zheng, and D Frank Hsu. Feature fusion for mobile usage
43. Computing (ICCI* CC), 2013 12th IEEE International Conference on, pages 212–
44. to use next. In Proceedings of the 2013 ACM conference on Pervasive and ubiquitous
45. computing adjunct publication, pages 167–170. ACM, 2013.
46. [11] Shu-Bo Chao. Context-aware daily activity summarization with mobile devices.
47. Master’s thesis, National Taiwan University, Jan 2013.
48. [12] Abhinav Parate, Matthias Bohmer, David Chu, Deepak Ganesan, and Benjamin M
49. phones. In Proceedings of the 2013 ACM international joint conference on Pervasive
50. and ubiquitous computing, pages 275–284. ACM, 2013.
51. [13] Li-Yu Tang, Pi-Cheng Hsiu, Jiun-Long Huang, and Ming-Syan Chen. ilauncher: an
52. of the 28th Annual ACM Symposium on Applied Computing, pages 505–512.
53. management, pages 609–618. ACM, 2013.
54. Cho, and Chong Sang Kim. On the existence of a spectrum of policies that subsumes
55. the least recently used (lru) and least frequently used (lfu) policies. ACM
56. SIGMETRICS Performance Evaluation Review, 27(1):134–143, 1999.
57. volume 96, pages 226–231, 1996.
58. 2012.
59. [18] Colin Cooper and Michele Zito. Realistic synthetic data for testing association rule
60. PKDD 2007, pages 398–405, 2007.