【摘要】：隨著信息技術(shù)的快速發(fā)展,人類(lèi)社會(huì)已經(jīng)由信息貧乏的時(shí)代進(jìn)入了信息過(guò)載時(shí)代。面對(duì)互聯(lián)網(wǎng)上的海量信息,一方面用戶(hù)很難從中找到自己真正感興趣的信息,另一方面,信息的生產(chǎn)者也很難找到對(duì)其真正感興趣的用戶(hù),從而使自己的信息受到關(guān)注。推薦系統(tǒng)通過(guò)分析用戶(hù)行為數(shù)據(jù),提取出用戶(hù)偏好,給用戶(hù)提供個(gè)性化的推薦內(nèi)容,在很多的網(wǎng)絡(luò)應(yīng)用(比如電子商務(wù)網(wǎng)站亞馬遜,淘寶網(wǎng)以及社交網(wǎng)站Linked,Facebook,人人網(wǎng)等)中,已經(jīng)成為了一個(gè)很有前途的處理信息過(guò)載的工具。目前,推薦系統(tǒng)研究領(lǐng)域應(yīng)用較多的推薦算法包括基于用戶(hù)的協(xié)同過(guò)濾推薦算法、基于物品的協(xié)同過(guò)濾推薦算法、基于隱語(yǔ)義模型的推薦算法、基于上下文信息的推薦算法以及基于社交網(wǎng)絡(luò)的推薦算法。其中應(yīng)用最為廣泛的是協(xié)同過(guò)濾(CF)推薦,它通過(guò)挖掘相似用戶(hù)或項(xiàng)目的歷史行為數(shù)據(jù)來(lái)預(yù)測(cè)目標(biāo)用戶(hù)的偏好。盡管協(xié)同過(guò)濾推薦算法已經(jīng)在業(yè)界得到了廣泛應(yīng)用,但傳統(tǒng)的協(xié)同過(guò)濾技術(shù)只利用了“用戶(hù)-項(xiàng)目”二元關(guān)系而未考慮其它信息。當(dāng)信息規(guī)模越來(lái)越大時(shí),它的性能就遇到了很大挑戰(zhàn),比如數(shù)據(jù)的稀疏性(即缺乏足夠數(shù)量的相似用戶(hù)或項(xiàng)目),由數(shù)據(jù)稀疏性及信息源的同質(zhì)化造成的推薦質(zhì)量下降。本文主要研究上下文感知推薦算法,對(duì)上下文的概念,上下文感知推薦系統(tǒng)的研究現(xiàn)狀,社交網(wǎng)絡(luò)數(shù)據(jù)及用戶(hù)行為數(shù)據(jù)進(jìn)行了詳細(xì)介紹。重點(diǎn)研究了上下文信息的提取及對(duì)多種上下文信息的處理,對(duì)社交網(wǎng)絡(luò)數(shù)據(jù)的處理及用戶(hù)相似度的計(jì)算,并提出了基于上下文提取的感知推薦算法以及在此基礎(chǔ)上引入社交網(wǎng)絡(luò)數(shù)據(jù)的基于社交網(wǎng)絡(luò)的上下文感知推薦算法。實(shí)際應(yīng)用中存在著多種類(lèi)型的上下文信息,但并不是每種上下文信息對(duì)于用戶(hù)的偏好都能起到同樣的影響。基于上下文提取的感知推薦算法通過(guò)比較傳統(tǒng)推薦模型在不同上下文片段上的性能來(lái)識(shí)別出那些能影響用戶(hù)偏好的上下文片段,應(yīng)用隨機(jī)決策樹(shù)算法將含有不同類(lèi)型上下文信息的評(píng)分進(jìn)行分割,所產(chǎn)生的子矩陣中的評(píng)分處于相似的上下文中,彼此之間相關(guān)度更高。在樹(shù)的葉子結(jié)點(diǎn)應(yīng)用矩陣分解,通過(guò)求解目標(biāo)函數(shù)來(lái)預(yù)測(cè)目標(biāo)用戶(hù)對(duì)項(xiàng)目的評(píng)分。社交網(wǎng)絡(luò)信息是另一類(lèi)能夠?qū)τ脩?hù)偏好產(chǎn)生重要影響的信息。基于社交網(wǎng)絡(luò)的上下文感知推薦算法引入了一個(gè)社交正則化項(xiàng),通過(guò)學(xué)習(xí)用戶(hù)好友的偏好來(lái)預(yù)測(cè)用戶(hù)的偏好。為了識(shí)別有著相似偏好的好友,提出一種融入上下文信息的皮爾森相關(guān)系數(shù)(pcc)來(lái)度量用戶(hù)相似度。理論分析與實(shí)驗(yàn)結(jié)果表明基于上下文提取的感知推薦算法及基于社交網(wǎng)絡(luò)的上下文感知推薦算法在準(zhǔn)確率上較傳統(tǒng)的推薦算法在性能方面有明顯的提高。
[Abstract]:With the rapid development of information technology, human society has entered the age of information overload from the era of poor information. In the face of the mass of information on the Internet, it is difficult for users to find the information they are interested in. On the other hand, it is difficult for the producers of information to find the users who are interested in it. By analyzing user behavior data, the recommendation system extracts user preferences, provides personalized recommendation content to users, and works in many web applications (e. G. Amazon, Taobao and social networking site Linked,Facebook,) Renren, etc., has become a promising tool for handling information overload. At present, many recommendation algorithms are used in the research field of recommendation system, including user-based collaborative filtering recommendation algorithm, object-based collaborative filtering recommendation algorithm, and recommendation algorithm based on hidden semantic model. Recommendation algorithm based on context information and recommendation algorithm based on social network. The most widely used (CF) recommendation is collaborative filtering, which predicts the preferences of target users by mining historical behavior data of similar users or projects. Although collaborative filtering recommendation algorithm has been widely used in the industry, the traditional collaborative filtering technology only uses the "user-item" binary relationship without considering other information. When the scale of information becomes larger and larger, its performance meets great challenges, such as the sparsity of data (that is, the lack of a sufficient number of similar users or projects), and the deterioration of recommendation quality caused by the sparsity of data and the homogeneity of information sources. This paper mainly studies the context-aware recommendation algorithm, introduces the concept of context, the research status of context-aware recommendation system, social network data and user behavior data in detail. It focuses on the extraction of context information and the processing of various context information, the processing of social network data and the calculation of user similarity. A context-aware recommendation algorithm based on context extraction and a context-aware recommendation algorithm based on social network data are proposed. There are many types of context information in practical applications, but not every context information has the same effect on user preferences. Context-based aware recommendation algorithms identify those contexts that affect user preferences by comparing the performance of traditional recommendation models on different context segments. The random decision tree algorithm is used to segment the score with different types of context information. The score in the generated submatrix is in the same context and the correlation between each other is higher. The matrix decomposition is applied to the leaf node of the tree to predict the target user's score of the item by solving the objective function. Social network information is another type of information that can have an important impact on user preferences. The context-aware recommendation algorithm based on social networks introduces a social regularization item to predict the preferences of users by learning the preferences of their friends. In order to identify friends with similar preferences, a Pearson correlation coefficient (pcc) is proposed to measure user similarity. Theoretical analysis and experimental results show that the performance of context-based perceptive recommendation algorithm and context-aware recommendation algorithm based on social network is significantly higher than that of traditional recommendation algorithm.
【學(xué)位授予單位】：沈陽(yáng)建筑大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類(lèi)號(hào)】：TP391.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前8條

1 謝海濤;孟祥武;;適應(yīng)用戶(hù)需求進(jìn)化的個(gè)性化信息服務(wù)模型[J];電子學(xué)報(bào);2011年03期

2 王玉祥;喬秀全;李曉峰;孟洛明;;上下文感知的移動(dòng)社交網(wǎng)絡(luò)服務(wù)選擇機(jī)制研究[J];計(jì)算機(jī)學(xué)報(bào);2010年11期

3 吳湖;王永吉;王哲;王秀利;杜栓柱;;兩階段聯(lián)合聚類(lèi)協(xié)同過(guò)濾算法[J];軟件學(xué)報(bào);2010年05期

4 許海玲;吳瀟;李曉東;閻保平;;互聯(lián)網(wǎng)推薦系統(tǒng)比較研究[J];軟件學(xué)報(bào);2009年02期

5 劉建國(guó);周濤;汪秉宏;;個(gè)性化推薦系統(tǒng)的研究進(jìn)展[J];自然科學(xué)進(jìn)展;2009年01期

6 李蕊;李仁發(fā);;上下文感知計(jì)算及系統(tǒng)框架綜述[J];計(jì)算機(jī)研究與發(fā)展;2007年02期

7 鄧愛(ài)林,朱揚(yáng)勇,施伯樂(lè);基于項(xiàng)目評(píng)分預(yù)測(cè)的協(xié)同過(guò)濾推薦算法[J];軟件學(xué)報(bào);2003年09期

8 趙亮,胡乃靜,張守志;個(gè)性化推薦算法設(shè)計(jì)[J];計(jì)算機(jī)研究與發(fā)展;2002年08期

相關(guān)博士學(xué)位論文 前1條

1 王立才;上下文感知推薦系統(tǒng)若干關(guān)鍵技術(shù)研究[D];北京郵電大學(xué);2012年

，

本文編號(hào)：2337968