本文選題：個(gè)性化推薦 + 用戶(hù)行為　； 參考：《哈爾濱商業(yè)大學(xué)》2017年碩士論文

【摘要】：隨著電子商務(wù)和互聯(lián)網(wǎng)的發(fā)展普及,使得面向用戶(hù)的個(gè)性化推薦越來(lái)越被重視,準(zhǔn)確的推薦不僅僅能幫助用戶(hù)節(jié)省大量時(shí)間而且可以幫助電子商務(wù)網(wǎng)站贏得用戶(hù)的關(guān)注,進(jìn)而提高電子商務(wù)網(wǎng)站的銷(xiāo)量。然而不同用戶(hù)的背景不同,對(duì)推薦結(jié)果的期望也不同,因此需要從多個(gè)角度挖掘用戶(hù)隱藏的信息,更好的為用戶(hù)給出個(gè)性化的推薦。本文研究基于用戶(hù)的潛在行為以及社交關(guān)系發(fā)掘用戶(hù)的偏好,從以下方面優(yōu)化用戶(hù)個(gè)性化推薦:研究用戶(hù)行為時(shí)效特征以及用戶(hù)行為和偏好的關(guān)系,并提升預(yù)測(cè)用戶(hù)偏好的效率;研究網(wǎng)頁(yè)拓?fù)渑c網(wǎng)頁(yè)權(quán)重的關(guān)系,進(jìn)而優(yōu)化網(wǎng)頁(yè)排序,為用戶(hù)給出準(zhǔn)確的推薦;研究基于負(fù)向社交關(guān)系以及主題被推薦給用戶(hù)的概率特征為歷史信息非常稀少的非活躍用戶(hù)給出推薦,優(yōu)化基于負(fù)向社交關(guān)系和推薦主題概率特征的融合,為非活躍用戶(hù)給出準(zhǔn)確的推薦。提出以下方法優(yōu)化用戶(hù)的個(gè)性化推薦:(1)提出一種優(yōu)化基于行為感知的用戶(hù)個(gè)性化推薦方法,通過(guò)分析用戶(hù)的歷史訪(fǎng)問(wèn)行為,建立映射用戶(hù)行為和偏好關(guān)系的隱馬爾可夫模型,并通過(guò)聚類(lèi)減少優(yōu)化用戶(hù)參數(shù)的時(shí)間,得到一種平衡準(zhǔn)確度和時(shí)間復(fù)雜度的個(gè)性化推薦方法。(2)提出基于網(wǎng)頁(yè)拓?fù)渥R(shí)別網(wǎng)頁(yè)異常排名的用戶(hù)推薦優(yōu)化方法,基于網(wǎng)頁(yè)拓?fù)渥R(shí)別異常提升網(wǎng)頁(yè)排名的行為,研究網(wǎng)頁(yè)拓?fù)鋵?duì)網(wǎng)頁(yè)權(quán)重值的提升效果,并通過(guò)網(wǎng)頁(yè)的鏈入權(quán)重值和鏈入網(wǎng)頁(yè)數(shù)量的關(guān)系識(shí)別網(wǎng)頁(yè)異常排名現(xiàn)象,為個(gè)性化推薦創(chuàng)造公正的網(wǎng)頁(yè)排名環(huán)境,進(jìn)而提高對(duì)用戶(hù)的個(gè)性化推薦質(zhì)量。(3)提出基于負(fù)向社交關(guān)系和泊松過(guò)程融合的非活躍用戶(hù)推薦優(yōu)化方法,由用戶(hù)間的初始負(fù)向社交關(guān)系和衰減傳遞系數(shù)矩陣擴(kuò)展用戶(hù)間的負(fù)向社交關(guān)系,基于負(fù)向社交關(guān)系約束為非活躍用戶(hù)給出推薦主題的期望,然后基于泊松過(guò)程預(yù)測(cè)用戶(hù)對(duì)推薦主題滿(mǎn)意的概率,將概率高的推薦主題作為最終的推薦發(fā)送給用戶(hù),為非活躍用戶(hù)給出準(zhǔn)確的推薦。
[Abstract]:With the development of electronic commerce and Internet, more and more attention has been paid to personalized recommendation for users. Accurate recommendation can not only help users save a lot of time, but also help e-commerce websites win the attention of users.And then improve the sales of e-commerce websites.However, different users have different backgrounds and different expectations for the recommended results. Therefore, it is necessary to mine hidden information from multiple angles to provide personalized recommendations for users.In this paper, we study the potential behaviors and social relationships of users to explore their preferences, and optimize their personalized recommendations from the following aspects: the characteristics of user behavior and the relationship between user behaviors and preferences.It also improves the efficiency of predicting user preferences, studies the relationship between web topology and web page weights, and then optimizes the ranking of web pages to give users accurate recommendations.The probabilistic features based on negative social relationships and topics recommended to users are proposed for inactive users with very little historical information, and the fusion of probability features based on negative social relationships and recommended themes is optimized.Give accurate recommendations for inactive users.This paper proposes the following methods to optimize the personalized recommendation of users: 1) A user personalized recommendation method based on behavioral awareness is proposed. By analyzing the historical access behavior of users, a hidden Markov model is established to map the relationship between user behavior and preference.Through clustering to reduce the time of optimizing user parameters, a personalized recommendation method, which balances accuracy and time complexity, is obtained.) based on the abnormal ranking of web page topology, a user recommendation optimization method is proposed.Based on the behavior of page topology recognition anomaly to enhance the ranking of web pages, this paper studies the effect of web topology on the weight of web pages, and identifies the abnormal ranking phenomenon of web pages by the relationship between the value of link weight and the number of web pages.In order to create a fair website ranking environment for personalized recommendation, and then improve the quality of personalized recommendation to users, this paper proposes an optimization method of inactive user recommendation based on negative social relationship and Poisson process fusion.The initial negative social relationship between users and the attenuation transfer coefficient matrix are used to expand the negative social relationship among users. Based on the constraint of negative social relationship, the expectation of recommending topics for inactive users is obtained.Then, based on the Poisson process, the probability of users' satisfaction with the recommendation topic is forecasted, and the recommendation topic with high probability is sent to the user as the final recommendation to give the accurate recommendation for inactive users.
【學(xué)位授予單位】：哈爾濱商業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.3;F713.55

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 朱永習(xí);嚴(yán)廣樂(lè);;有向在線(xiàn)社交網(wǎng)絡(luò)的拓?fù)浣Y(jié)構(gòu)分析[J];信息技術(shù);2016年09期

2 葛桂麗;袁凌云;王興超;;基于情境感知的用戶(hù)個(gè)性化興趣建模[J];計(jì)算機(jī)應(yīng)用研究;2017年04期

3 彭慧麗;張嘯劍;;基于差分隱私的空間分割研究綜述[J];燕山大學(xué)學(xué)報(bào);2016年03期

4 張亞楠;曲明成;劉宇鵬;;基于社交關(guān)系拓?fù)浣Y(jié)構(gòu)的冷啟動(dòng)推薦方法[J];浙江大學(xué)學(xué)報(bào)(工學(xué)版);2016年05期

5 劉啟華;;基于興趣社區(qū)和信任鄰居的混合推薦研究[J];情報(bào)科學(xué);2016年02期

6 李競(jìng)飛;商振國(guó);張鵬;宋大為;;融合用戶(hù)實(shí)時(shí)搜索狀態(tài)的自適應(yīng)查詢(xún)推薦模型[J];計(jì)算機(jī)科學(xué)與探索;2016年09期

7 李楓林;陳德鑫;梁少星;;基于語(yǔ)義關(guān)聯(lián)和情景感知的個(gè)性化推薦方法研究[J];情報(bào)雜志;2015年10期

8 徐雅斌;孫曉晨;;位置社交網(wǎng)絡(luò)的個(gè)性化位置推薦[J];北京郵電大學(xué)學(xué)報(bào);2015年05期

9 張琳;邢歡;王汝傳;吳超杰;;復(fù)雜網(wǎng)絡(luò)環(huán)境下基于推薦鏈分類(lèi)的動(dòng)態(tài)信任模型[J];通信學(xué)報(bào);2015年09期

10 童國(guó)平;孫建軍;;基于搜索日志的用戶(hù)行為分析[J];現(xiàn)代圖書(shū)情報(bào)技術(shù);2015年Z1期

相關(guān)碩士學(xué)位論文 前1條

1 余善紅;基于社會(huì)網(wǎng)絡(luò)的個(gè)性化推薦系統(tǒng)關(guān)鍵技術(shù)研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2011年

，

本文編號(hào)：1762009