基于云計算的知識服務推薦系統(tǒng)研究
[Abstract]:According to the user information and behavior, such as gender, age, hobbies and user selection records, the recommendation system can select the content of its possible interest from a large amount of knowledge to the user. The recommendation system satisfies the personalized service characteristics of knowledge service. With the continuous collection of user information and behavior data, the recommendation quality is also improved, and the recommendation system is close to accurate recommendation. Recommendation system is of great significance in social network, e-commerce, search engine and internet advertising marketing. Today, our learning system is closely related to social networks and search engines, so it is of great significance to study the recommendation system to promote our learning. Cloud computing platform provides the natural advantage for recommendation system. First of all, data storage in the cloud is clustered and storage management is virtualized, which theoretically provides the recommendation system with unlimited data storage capacity and efficient data throughput, so the recommendation system can be quickly acquired. Massive training data to provide quality recommendations; Secondly, the distributed computing power of cloud and virtualization of physical resources provide high response ability for recommendation system, which is helpful to provide personalized recommendation for a large number of users. Through the elaboration of knowledge service, recommendation system, cloud computing related technology, the personalized recommendation system model is constructed, the knowledge base under cloud environment is constructed, and the user model is constructed. The recommendation algorithm based on collaborative filtering is improved on the basis of MapReduce, so that the recommendation system can meet the requirements of computing in the age of mass data. In theory, it has certain exploration significance to knowledge service in cloud computing environment, and has reference value to recommend personalized knowledge service to learners in practice.
【學位授予單位】:河南師范大學
【學位級別】:碩士
【學位授予年份】:2013
【分類號】:TP391.3
【參考文獻】
相關期刊論文 前10條
1 倪光南;;新技術發(fā)展環(huán)境下的電子政務建設[J];電子政務;2010年11期
2 王彥;;圖書館基于知識管理的知識服務[J];圖書館學刊;2011年05期
3 吳真明;試析網絡環(huán)境下的個性化信息服務[J];圖書情報知識;2003年06期
4 陳梅;;圖書館知識服務新模式——個性化推薦系統(tǒng)問題和算法實現(xiàn)研究[J];圖書情報工作網刊;2012年05期
5 楊金星;高月紅;張欣;常永宇;;一種基于普通用戶終端的測試信息收集方法[J];現(xiàn)代電信科技;2011年08期
6 呂紅梅;;圖書館知識服務的特點、內容和實施原則[J];現(xiàn)代情報;2005年12期
7 馬宏偉;張光衛(wèi);李鵬;;協(xié)同過濾推薦算法綜述[J];小型微型計算機系統(tǒng);2009年07期
8 張曉林;走向知識服務:尋找新世紀圖書情報工作的生長點[J];中國圖書館學報;2000年05期
9 劉建國;周濤;汪秉宏;;個性化推薦系統(tǒng)的研究進展[J];自然科學進展;2009年01期
10 袁心;崔秀美;;基于Google云服務的個人學習環(huán)境(PLE)的構建[J];棗莊學院學報;2010年02期
相關博士學位論文 前1條
1 任磊;推薦系統(tǒng)關鍵技術研究[D];華東師范大學;2012年
相關碩士學位論文 前2條
1 朱曄;我國知識服務現(xiàn)狀分析和體系架構研究[D];南京理工大學;2007年
2 孫丹;基于用戶信息行為的個性化知識服務研究[D];華中師范大學;2012年
本文編號:2362232
本文鏈接:http://sikaile.net/kejilunwen/sousuoyinqinglunwen/2362232.html