云環(huán)境下基于社交信息的音樂推薦系統(tǒng)設(shè)計與實現(xiàn)
發(fā)布時間：2018-08-28 13:48
【摘要】：隨著互聯(lián)網(wǎng)的不斷發(fā)展和移動互聯(lián)網(wǎng)的興起,越來越多的人選擇通過互聯(lián)網(wǎng)來隨時隨地享受數(shù)字化音樂帶來的服務(wù)。數(shù)字音樂數(shù)量的激增使得音樂服務(wù)提供商的主要競爭從曲庫的深度和規(guī)模轉(zhuǎn)移到了推薦和發(fā)現(xiàn)音樂方面,推薦系統(tǒng)成為解決該問題的主要技術(shù)手段,而協(xié)同過濾推薦算法作為推薦領(lǐng)域最主流的算法之一,在音樂推薦系統(tǒng)中得到了廣泛應(yīng)用。然而,隨著推薦準(zhǔn)確率的不斷提高,影響協(xié)同過濾推薦算法推薦效果的另一個問題越來越突顯出來:如何發(fā)現(xiàn)相關(guān)度高的新穎推薦項。本文從上述問題出發(fā),提出了融合社交信息的基于圖的協(xié)同過濾改進(jìn)算法,并以該算法為核心技術(shù),設(shè)計開發(fā)了一套完整的音樂推薦系統(tǒng)。主要工作如下:首先,改進(jìn)算法的主要思想是:利用用戶的社交信息,對由項目相似性矩陣構(gòu)建出的用戶偏好圖進(jìn)行擴(kuò)充,以降低通過信息熵計算得出的奇異推薦項的比例,然后將這些項目與通過經(jīng)典協(xié)同過濾算法得到的推薦項合并在一起作為最終的推薦結(jié)果。最后,通過采集自Last.fm上的數(shù)據(jù)對算法的有效性進(jìn)行了驗證。結(jié)果表明,與原始算法相比,該改進(jìn)算法的推薦準(zhǔn)確率平均提高了約2.265%,由此損失的新穎性在相關(guān)指標(biāo)下僅僅約為1.24%。由此說明該算法可以在發(fā)掘出新穎推薦項的同時,提升系統(tǒng)的準(zhǔn)確率,從而達(dá)到更好的推薦效果。其次,基于上述算法,本文設(shè)計并實現(xiàn)了一套音樂推薦系統(tǒng),在進(jìn)行了充分的需求分析和系統(tǒng)架構(gòu)設(shè)計的基礎(chǔ)上,給出了單曲推薦、藝術(shù)家推薦和好友推薦的算法設(shè)計,并提出了歌單推薦的策略;然后通過MapReduce編程范式實現(xiàn)了各個算法并將系統(tǒng)運(yùn)行在Hadoop云平臺上;最后,邀請用戶對系統(tǒng)進(jìn)行了在線測試,當(dāng)推薦數(shù)為25時平均新穎度為4.56,準(zhǔn)確率約為17.6%,證明該音樂推薦系統(tǒng)在兼顧推薦新穎性和準(zhǔn)確率方面具有出色表現(xiàn)。
[Abstract]:With the continuous development of the Internet and the rise of mobile Internet, more and more people choose to enjoy the services brought by digital music anytime and anywhere through the Internet. The surge in the number of digital music has shifted the main competition of music service providers from the depth and scale of music library to the aspect of recommending and discovering music. Recommendation system has become the main technical means to solve this problem. As one of the most popular algorithms in the field of recommendation, collaborative filtering recommendation algorithm has been widely used in music recommendation system. However, with the improvement of recommendation accuracy, another problem that affects the recommendation effect of collaborative filtering is becoming more and more prominent: how to find novel recommendation items with high correlation. Based on the above problems, this paper puts forward an improved algorithm of collaborative filtering based on graph, which integrates social information, and designs a complete music recommendation system based on this algorithm. The main work is as follows: firstly, the main idea of the improved algorithm is to extend the user preference map constructed from the item similarity matrix by using the social information of the user, so as to reduce the proportion of singular recommendation items calculated by the information entropy. Then these items are combined with the recommended items obtained by the classical collaborative filtering algorithm as the final recommendation results. Finally, the validity of the algorithm is verified by collecting data from Last.fm. The results show that compared with the original algorithm, the recommendation accuracy of the improved algorithm is increased by about 2.2655.The resulting novelty is only about 1.24 under the related index. It shows that the algorithm can improve the accuracy of the system and achieve a better recommendation effect. Secondly, based on the above algorithm, this paper designs and implements a set of music recommendation system. On the basis of sufficient requirement analysis and system architecture design, the algorithm design of single song recommendation, artist recommendation and friend recommendation is given. Then we implement each algorithm by MapReduce programming paradigm and run the system on the Hadoop cloud platform. Finally, we invite users to test the system online. When the recommendation number is 25, the average novelty is 4.56 and the accuracy is about 17.6. it is proved that the music recommendation system has excellent performance in both novelty and accuracy.
【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：TP391.3
本文編號：2209578
[Abstract]:With the continuous development of the Internet and the rise of mobile Internet, more and more people choose to enjoy the services brought by digital music anytime and anywhere through the Internet. The surge in the number of digital music has shifted the main competition of music service providers from the depth and scale of music library to the aspect of recommending and discovering music. Recommendation system has become the main technical means to solve this problem. As one of the most popular algorithms in the field of recommendation, collaborative filtering recommendation algorithm has been widely used in music recommendation system. However, with the improvement of recommendation accuracy, another problem that affects the recommendation effect of collaborative filtering is becoming more and more prominent: how to find novel recommendation items with high correlation. Based on the above problems, this paper puts forward an improved algorithm of collaborative filtering based on graph, which integrates social information, and designs a complete music recommendation system based on this algorithm. The main work is as follows: firstly, the main idea of the improved algorithm is to extend the user preference map constructed from the item similarity matrix by using the social information of the user, so as to reduce the proportion of singular recommendation items calculated by the information entropy. Then these items are combined with the recommended items obtained by the classical collaborative filtering algorithm as the final recommendation results. Finally, the validity of the algorithm is verified by collecting data from Last.fm. The results show that compared with the original algorithm, the recommendation accuracy of the improved algorithm is increased by about 2.2655.The resulting novelty is only about 1.24 under the related index. It shows that the algorithm can improve the accuracy of the system and achieve a better recommendation effect. Secondly, based on the above algorithm, this paper designs and implements a set of music recommendation system. On the basis of sufficient requirement analysis and system architecture design, the algorithm design of single song recommendation, artist recommendation and friend recommendation is given. Then we implement each algorithm by MapReduce programming paradigm and run the system on the Hadoop cloud platform. Finally, we invite users to test the system online. When the recommendation number is 25, the average novelty is 4.56 and the accuracy is about 17.6. it is proved that the music recommendation system has excellent performance in both novelty and accuracy.
【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：TP391.3
【參考文獻(xiàn)】
相關(guān)期刊論文 前4條
1 馮智明;蘇一丹;覃華;鄧海;;基于遺傳算法的聚類與協(xié)同過濾組合推薦算法[J];計算機(jī)技術(shù)與發(fā)展;2014年01期
2 冷亞軍;梁昌勇;陸青;陸文星;;基于近鄰評分填補(bǔ)的協(xié)同過濾推薦算法[J];計算機(jī)工程;2012年21期
3 朱郁筱;呂琳媛;;推薦系統(tǒng)評價指標(biāo)綜述[J];電子科技大學(xué)學(xué)報;2012年02期
4 于洪;李轉(zhuǎn)運(yùn);;基于遺忘曲線的協(xié)同過濾推薦算法[J];南京大學(xué)學(xué)報(自然科學(xué)版);2010年05期
相關(guān)博士學(xué)位論文 前1條
1 陰紅志;社會化媒體中若干時空相關(guān)的推薦問題研究[D];北京大學(xué);2014年
相關(guān)碩士學(xué)位論文 前1條
1 金玉;基于MUSICXML的音樂個性化推薦系統(tǒng)[D];吉林大學(xué);2015年
，本文編號：2209578
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2209578.html
最近更新
教材專著
