在現在的社會裡，手機應用程式已經被人們接受與廣泛地利用，然而目前市面上的手機 App 推薦系統，多以使用者實際使用與回報作為參考，若有惡意行為軟體，在使用者介面後竊取使用者資料，這些推薦系統是難以查知其行為的，因此我們提出了 AppReco，一套可以系統化的推薦 iOS App 的推薦系統，而且不需要使用者去實際操作、執行 App。 整個分析流程包括三個步驟：(1) 透過無監督式學習法的隱含狄利克雷分布(Latent Dirichlet Allocation, LDA)做出主題模型，再使用增長層級式自我組織映射圖(Growing Hierarchical Self-Organizing Map, GHSOM)進行分群。(2)使用靜態分析程式碼，去找出其應用程式所執行的行為。(3)透過我們的評分公式對於這些 App，進行評分。 在分群 App 方面，AppReco 使用這些應用程式的官方敘述來進行分群，讓擁有類似屬性的手機應用程式群聚在一起；在檢視 App 方面，AppReco 透過靜態分析這些 App 的程式碼，來計算其使用行為的多寡；在推薦 App 方面，AppReco 分析類似屬性的 App 與其執行的行為，最後推薦使用者使用較少敏感行為(如使用廣告、使用個人資料、使用社群軟體開發包等)的 App。 而本研究使用在 Apple App Store 上面數千個在各個類別中的前兩百名 App 做為我們的實驗資料集來進行實驗。 / Mobile applications have been widely used in life and become dominant software applications nowadays. However there are lack of systematic recommendation systems that can be leveraged in advance without users’ evaluations. We present AppReco, a systematic recommendation system of iOS mobile applications that can evaluate mobile applications without executions. AppReco evaluates apps that have similar interests with static binary analysis, revealing their behaviors according to the embedded functions in the executable. The analysis consists of three stages: (1) unsupervised learning on app descriptions with Latent Dirichlet Allocation for topic discovery and Growing Hierarchical Self-organizing Maps for hierarchical clustering, (2) static binary analysis on executables to discover embedded system calls and (3) ranking common-topic applications from their matched behavior patterns. To find apps that have similar interests, AppReco discovers (unsupervised) topics in official descriptions and clusters apps that have common topics as similar-interest apps. To evaluate apps, AppReco adopts static binary analysis on their executables to count invoked system calls and reveal embedded functions. To recommend apps, AppReco analyzes similar-interest apps with their behaviors of executables, and recommend apps that have less sensitive behaviors such as commercial advertisements, privacy information access, and internet connections, to users. We report our analysis against thousands of iOS apps in the Apple app store including most of the listed top 200 applications in each category.

近年來，智慧型手機(Smartphone)的銷量超過其他型式手機。智慧型手機具有更先進、更開放的行動作業系統，可允許使用者自行安裝應用程式軟體(Application)來擴充手機功能。目前市面上的應用程式數量非常龐大，在眾多的應用程式和有限的時間下，使用者不太可能將所有的應用程式下載試用，所以對使用者而言，找出自己所想要和需要的應用程式，是個困難的問題。推薦系統可依照使用者的喜好，或是準備推薦項目的相似程度來做推薦，讓使用者能較快得到想要的資訊，目前主要的方式有協同過濾(Collaborative Filtering, CF)、內容過濾(Content-Based Filtering, CBF)，還有結合前述兩種方式的混和式推薦(Hybrid Approach)。 本研究所使用的資料集是由政治大學資訊科學系所開發的實驗平台蒐集而來。資料以側錄的方式，將使用者實際操作手機應用程式的狀況記錄下來，其中包含了25位使用者和1125個應用程式。我們將原始資料集以三種方式整理成三個資料集：一、是否使用應用程式；二、使用應用程式的次數；三、使用應用程式的頻率，其值表示使用者在該應用程式的使用狀況。我們並將資料分成前段與後段時間兩部分，以前段時間的資料當作基準，推薦最多同群使用者使用的應用程式、同群使用者使用次數最多的應用程式，以及同群使用者最常使用的應用程式，然後以後段時間的資料做驗證，計算推薦結果的準確率與召回率加以比較。 我們使用知名的Information Theoretic Co-Clustering Algorithm和兩種基於Minimum Squared Residue Co-Clustering Algorithm的演算法將使用者與應用程式分群，利用分群結果做計算，推薦應用程式給使用者。實驗發現三種演算法在第一個資料集的準確率與召回率表現最好，此資料集以0和1的值，來紀錄使用者在各應用程式的使用狀況。實驗比較三個演算法的結果，在大部分的情況之下，一個基於Minimum Squared Residue Co-Clustering Algorithm的演算法，給出的結果較好。 此外，我們也發現應用程式開發者將應用程式上架提供下載時，以個人主觀想法對該應用程式定義其分類，與我們利用雙分群方法，以使用者實際操作的情況將應用程式分類的結果有些差異，或許在Google Play的分類上可做調整。 本研究提出推薦系統的框架具有彈性，未來可以使用不同的雙分群演算法做分群，也能套用其他的推薦方式。 / With the rapid evolution of smartphone devices, tens of thousands applications have been supplied on online stores such as App Store (operated by Apple Inc.) and Google Play (operated by Google Inc.). Since there are many applications, recommending applications to users becomes an important topic. In this thesis, we present a framework for using a co-clustering algorithm to recommend applications to users. Recommendations are a part of everyday life. People usually rely on some external knowledge to make informed decisions about a particular artifact or action. Using recommender systems is one of general approaches that help people make decisions. There are three common types of recommender systems, namely collaborative filtering, content-based filtering, and hybrid recommender systems. In this thesis, we use the dataset that was collected by a tool developed by the Department of Computer Science at the National Chengchi University. It recorded the users’ behavior when they were using their smartphones. We transform the original dataset into three types of datasets: 1) indicating whether a user used an application; 2) indicating the number of uses made by a user for an application; 3) indicating the frequency of uses made by a user for an application. Furthermore, we divide each dataset into two parts: The first part containing data for the early time period is used as the recommending base, and the second part containing data for the late time period is used for verifying the results. We utilize three famous co-clustering algorithms, which are the Information Theoretic Co-Clustering Algorithm and two algorithms based on the Minimum Squared Residue Co-Clustering Algorithm, in the proposed framework. According to the clusters given by a co-clustering algorithm, we recommend top five applications to each user by referring to the maximum number of users, the maximum number of uses, and the most frequently used applications that are in the same cluster. We calculate the precision and recall values to compare the results. From the experimental results, we find that the best result corresponds to the first type of dataset and also that one of the algorithms based on the Minimum Squared Residue Co-Clustering Algorithm is better than the other two algorithms in terms of the precision and recall values. From the clusters of applications, we obtain some interesting insights into the categories of applications. The categories of applications are set by their developers, but the users may not totally agree with the settings. There might be space for improvement for the categories of applications on the online store. In the future, we can utilize different co-clustering algorithms and other recommended methods in the proposed framework.

「餐桌變化多端，輕鬆管理菜籃。」是Chef Mommy帶給使用者的主要價值。 Chef Mommy為了解決有烹飪需求者在菜色變化與食材選購上的問題，透過網站與手機應用程式，應用雲端科技提供食譜搜尋引擎、食材庫存管理、食譜比對推薦、一週菜單規劃與採購清單管理等服務，為使用者提供方便省時，又可兼顧菜色變化與食材管理的料理解決方案。使用者藉由Chef Mommy的服務，能夠以家中庫存食材為基礎，得到原本沒想到的菜色建議，進而在備餐時搭配出更多菜色變化，為家人、朋友準備出豐盛而美好的一餐。 以台灣為例，行政院主計處2010年的家庭收支調查顯示，國內家庭花費在飲食相關採購上的支出，高達8,400億元，在這當中，國內整體食材供應市場規模粗估超過2,000億元。Chef Mommy除了在第一、二階段，針對網站與手機應用程式開發服務功能外，第三、第四階段更將規劃與食材供應業者或連鎖超市業者進行合作，將食譜推薦服務與食材購買進行連結，切入使用者的購買流程，並據此獲利。 藉著滿足使用者輕鬆管理食材與希望菜色天天有變化的需求，Chef Mommy將投入資源，培養使用者常用的習慣，以深入使用者的飲食體驗。透過使用者長期使用的歷程記錄，可了解使用者習慣購買的食材與偏好的食譜、料理方式等資訊，據此拓展出更大的飲食市場商機。 / In order to solve users’ problems of dish variety and ingredients purchase, Chef Mommy will provide services such as recipe search engine, ingredient inventory management, recommended recipes, weekly menu planning and shopping list management via its website and mobile app. As for these convenient services, Chef Mommy wants to provide a total cooking solution that can help users saving their time and giving consideration to dish variety and ingredients purchase at the same time. Based on ingredient inventory in home, Chef Mommy will recommend recipes that users may not expect or remember originally, and then with more dish variety, they can prepare a bountiful meal for family and friends. In Taiwan, 2010 Family Income and Expenditure Survey by the DGBAS shows that domestic household expenditures spent on diet-related purchase, up to NTD$ 840 billion, in which the overall food supply market size were roughly over NTD$ 200 billion. Chef Mommy will focus on developing services functions in the 1st and 2nd stages, and cut into the users’ buying process by recipes recommend service in the 3rd and 4th stages. By linking users’ recipe choice and ingredient purchase, Chef Mommy will cooperate with food supply companies or supermarket chains and gain profit from it. Chef Mommy will invest resources to training users’ habits of using Chef Mommy’s services. Via users’ long-term usage history, Chef Mommy will know users’ accustomed to buy ingredients, preferred recipes, cooking methods and other cooking information. According to this, Chef Mommy will be able to expand to a greater diet market.

本研究首先從文獻回顧及實際調查中深入探討影響參觀者使用博物館行動導覽系統的七大影響因素，接著據此設計並實作出在智慧型手機平台上使用之一套博物館行動導覽系統，以期有效解決現有參觀者遇到的導覽問題。研究中使用設計科學之研究方法，提出解決方案，並且依據實際環境、背景以及文獻基礎，設計整體的系統架構。接著以故宮為例，建構出本研究之博物館行動導覽系統手機應用程式。系統開發完成後，以實驗法進行設計之驗證，評估結果顯示：本研究所提出之行動導覽系統相較於傳統之紙本導覽，可提升參觀者使用博物館行動導覽系統的意願、感知價值及滿意度。本研究之博物館行動導覽系統建置過程、以及系統成效的驗證，可作為手機應用程式（APP）廠商建置行動導覽系統或使用設計科學法開發其他類別的APP之指引；亦或作為博物館策劃展覽活動與導入行動導覽系統之依據；此外本研究亦指出使用者預期實際使用系統之感知與預期系統需求之落差，以供未來相關研究參考。 / In this research, according to literature review and field observations, we first identify and discuss seven design factors affecting visitors’ usability in museum mobile navigation systems. We then design and construct a museum mobile navigation system on the basis of the seven factors. The purpose is to meet the visitors’ needs and increase the visitors’ intention and satisfaction toward using the museum mobile navigation system. Design science research method is used in this research to propose solution plans. According to actual environment, context, and literature, the complete system architecture is designed. We then build a mobile navigation application on Android for the National Palace Museum and evaluate the design to ensure this system can effectively solve the problems that the visitors encountered during navigation process. In this research, the building process of the mobile museum navigation system and the evaluation of the system performance could provide guidance to APP vendors; or a basis for museums to plan an exhibition and to implement a mobile navigation system. Moreover, the gap between users’ perception of using the real system and their expected system requirements can be identified; this could serve as the reference point of future related research.