【摘要】：隨著電子商務(wù)的發(fā)展,網(wǎng)上購(gòu)買(mǎi)成為了時(shí)下一種主流的購(gòu)物方式,消費(fèi)者在面對(duì)海量信息時(shí),需要付出大量時(shí)間來(lái)找尋自身感興趣的商品。在此情況下,個(gè)性化推薦系統(tǒng)應(yīng)運(yùn)而生,被認(rèn)為是一種有效且符合消費(fèi)者商品需求的營(yíng)銷(xiāo)方法,它能解決電子商務(wù)網(wǎng)站中消費(fèi)者購(gòu)物選擇問(wèn)題,是目前網(wǎng)絡(luò)信息服務(wù)領(lǐng)域的熱點(diǎn)之一。個(gè)性化服務(wù)系統(tǒng)通過(guò)分析使用對(duì)象的行為信息,來(lái)分析消費(fèi)者個(gè)人的興趣差異習(xí)慣,從而提供“一對(duì)一”精準(zhǔn)營(yíng)銷(xiāo)服務(wù)。要實(shí)現(xiàn)個(gè)性化推薦系統(tǒng),必須建立用戶(hù)興趣模型,用戶(hù)建模在個(gè)性化推薦中處于核心地位,建模的質(zhì)量直接影響到推薦系統(tǒng)的質(zhì)量。對(duì)此,通過(guò)捕捉多源用戶(hù)興趣數(shù)據(jù)并進(jìn)行數(shù)據(jù)融合,是提高用戶(hù)興趣建模質(zhì)量的一條重要途徑。本文研究的目的在于針對(duì)B2C網(wǎng)站環(huán)境下,傳統(tǒng)協(xié)同過(guò)濾推薦精度不夠高的問(wèn)題,提出和實(shí)現(xiàn)基于用戶(hù)樹(shù)型網(wǎng)絡(luò)的多源用戶(hù)興趣數(shù)據(jù)融合方法,以改善和優(yōu)化原有方法的推薦質(zhì)量。全文主要研究?jī)?nèi)容如下:首先,本文以建模流程為研究視角,從用戶(hù)信息收集、信息表示、技術(shù)處理、更新方式四個(gè)方面對(duì)個(gè)性化推薦系統(tǒng)中的用戶(hù)興趣模型建立的現(xiàn)有研究成果進(jìn)行比較分析,將信息收集歸納為信息來(lái)源、信息存儲(chǔ)兩個(gè)方面,用以獲取建模的信息來(lái)源;將信息表示歸納為語(yǔ)義表示、量化表示兩類(lèi)方法,用以表征具體的用戶(hù)興趣偏好;將數(shù)據(jù)處理歸納為兩類(lèi)技術(shù),即特征詞權(quán)重、聚類(lèi)技術(shù),用以加工用戶(hù)信息而生成用戶(hù)興趣模型;將數(shù)據(jù)更新歸納為時(shí)間窗口法、遺忘算法、混合模型等三類(lèi)方法,用以體現(xiàn)模型中的用戶(hù)興趣漂移。其次,從用戶(hù)購(gòu)物流程角度出發(fā),總結(jié)出能最大程度反映消費(fèi)者興趣偏好的4個(gè)因子:商品點(diǎn)擊行為、商品收藏行為、放入購(gòu)物車(chē)行為、下單行為。然后具體量化每種指標(biāo)因子的計(jì)算,設(shè)置相應(yīng)規(guī)則實(shí)現(xiàn)靜態(tài)用戶(hù)興趣權(quán)重�？紤]到用戶(hù)興趣變化,設(shè)計(jì)了隨時(shí)間變化的興趣值,彌補(bǔ)了靜態(tài)系統(tǒng)推薦的不足。針對(duì)每個(gè)個(gè)體,進(jìn)一步把興趣區(qū)分為長(zhǎng)期、短期興趣,同時(shí)給出不同的指數(shù)衰減方法。通過(guò)上述處理,實(shí)現(xiàn)了用戶(hù)多源興趣數(shù)據(jù)的有效融合,可以更好地提高推薦精度。最后,實(shí)驗(yàn)基于阿里巴巴集團(tuán)旗下天貓商城提供的真實(shí)用戶(hù)數(shù)據(jù)集,通過(guò)實(shí)施數(shù)據(jù)融合,訓(xùn)練得到每個(gè)用戶(hù)的興趣模型,并計(jì)算出每位用戶(hù)的長(zhǎng)期、短期興趣,以及各自的興趣周期。本文共完成了三組實(shí)驗(yàn),第一組為探討各指標(biāo)屬性因子值;第二組為周期衰減模型與不區(qū)分興趣周期的指數(shù)衰減模型作預(yù)測(cè)精確度對(duì)比實(shí)驗(yàn);第三組為經(jīng)典協(xié)同過(guò)濾算法與本文提出的帶周期衰減過(guò)濾算法對(duì)比實(shí)驗(yàn)。實(shí)驗(yàn)結(jié)果表明,多源用戶(hù)興趣數(shù)據(jù)融合的推薦效果優(yōu)于經(jīng)典的協(xié)同過(guò)濾推薦效果。
[Abstract]:With the development of electronic commerce, online shopping has become a mainstream shopping method. Consumers need to spend a lot of time to find the goods they are interested in the face of a great deal of information. In this case, personalized recommendation system emerges as the times require, which is considered to be an effective and suitable marketing method to meet the needs of consumers. It can solve the problem of consumer shopping choice in e-commerce websites. It is one of the hot spots in the field of network information service. By analyzing the behavior information of the users, the individualized service system can analyze the consumers' different habits of interest, thus providing the "one to one" precision marketing service. In order to realize personalized recommendation system, user interest model must be established. User modeling is the core of personalized recommendation, and the quality of modeling directly affects the quality of recommendation system. Therefore, it is an important way to improve the quality of user interest modeling by capturing multi-source user interest data and data fusion. The purpose of this paper is to propose and implement a multi-source user interest data fusion method based on user tree network to solve the problem that the recommendation accuracy of traditional collaborative filtering is not high enough in B2C website environment. To improve and optimize the recommended quality of the original method. The main contents of this paper are as follows: firstly, from the perspective of modeling process, this paper focuses on user information collection, information representation, and technology processing. This paper compares and analyzes the existing research results of user interest model in personalized recommendation system from four aspects of updating mode, and summarizes the information collection into two aspects: information source and information storage, in order to obtain the information source of modeling. The information representation is classified into semantic representation and quantitative representation to represent specific user preferences, and the data processing is classified into two kinds of techniques, namely, the weight of feature words, the clustering technique. The user interest model is generated by processing user information, and the data update is summarized into three kinds of methods, such as time window method, forgetting algorithm and hybrid model, to reflect the drift of user interest in the model. Secondly, from the point of view of the user's shopping flow, four factors which can reflect the consumer's interest and preference to the greatest extent are summarized: commodity click behavior, commodity collection behavior, shopping cart behavior, order behavior. Then the calculation of each index factor is quantified and the corresponding rules are set to realize the static user interest weight. Considering the change of user's interest, the interest value changed with time is designed, which makes up for the deficiency of static system recommendation. For each individual, interest is further divided into long term and short term interest, and different exponential decay methods are given. Through the above processing, the effective fusion of user's multi-source interest data can be realized, and the recommendation accuracy can be improved better. Finally, the experiment is based on the real user data set provided by Tmall Mall, which is owned by Alibaba Group. Through the implementation of data fusion, the interest model of each user is trained, and the long-term and short-term interest of each user is calculated. And their respective interest cycles. In this paper, three groups of experiments have been completed, the first group is to discuss the attribute factor value of each index, the second group is to compare the prediction accuracy between the periodic attenuation model and the exponential attenuation model which does not distinguish the period of interest. The third group is a comparative experiment between the classical collaborative filtering algorithm and the periodic attenuation filtering algorithm proposed in this paper. The experimental results show that the recommendation effect of multi-source user interest data fusion is better than that of classical collaborative filtering.
【學(xué)位授予單位】：四川師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類(lèi)號(hào)】：F724.6

【參考文獻(xiàn)】

相關(guān)期刊論文 前4條

1 宋江春;沈鈞毅;;一種新的Web用戶(hù)群體和URL聚類(lèi)算法的研究[J];控制與決策;2007年03期

2 汪中;劉貴全;陳恩紅;;一種優(yōu)化初始中心點(diǎn)的K-means算法[J];模式識(shí)別與人工智能;2009年02期

3 王有為;許博;衛(wèi)學(xué)啟;凌鴻;;基于用戶(hù)訪問(wèn)序列聚類(lèi)的網(wǎng)站導(dǎo)航系統(tǒng)[J];系統(tǒng)工程理論與實(shí)踐;2010年07期

4 業(yè)寧,李威,梁作鵬,董逸生;一種Web用戶(hù)行為聚類(lèi)算法[J];小型微型計(jì)算機(jī)系統(tǒng);2004年07期

，

本文編號(hào)：2191240