With the development of artificial intelligence , the application of recommender systems has been extended to fields such as e-commerce shopping cart analysis or video recommendation system. These systems provide user a recommended resource set based on their habits or behavior patterns to help users saving searching cost. However, these techniques have not been successfully adopted to help users search functions on smart-phones more efficiency. This research is designated to build the context-aware system, which can generate the list of operations predicting which function user might use under certain contexts through continuously learning users operation patterns and related device perceived scenario. The system utilize event-condition-action patterns to describe user frequent behaviors, and the research will focus on developing innovative Action-Condition-Fit algorithm to figure the similarity between action pattern sets and real-time scenario. Proposed system and algorithm will then be built on Google App Engine and Android device to empirically validate its performance through field test.
| Identifer | oai:union.ndltd.org:NSYSU/oai:NSYSU:etd-0821112-143035 |
| Date | 21 August 2012 |
| Creators | Lee, Ko-han |
| Contributors | Bing-Chiang Jeng, Te-Min Chang, Wei-Po Lee, Yuh-Jiuan Tsay |
| Publisher | NSYSU |
| Source Sets | NSYSU Electronic Thesis and Dissertation Archive |
| Language | Cholon |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0821112-143035 |
| Rights | user_define, Copyright information available at source archive |
Page generated in 0.0019 seconds