【摘要】：近年來(lái),隨著互聯(lián)網(wǎng)的興起,開放計(jì)算系統(tǒng)(Agent系統(tǒng)、P2P網(wǎng)絡(luò)、Ad Hoc網(wǎng)絡(luò)等)和電子商務(wù)(eBay、Amazon等)等應(yīng)用得到了快速發(fā)展。然而,其自身的開放性、匿名性、欺騙性等動(dòng)態(tài)特性使得各種網(wǎng)絡(luò)安全問(wèn)題日益突出,安全性問(wèn)題已成為制約其發(fā)展的關(guān)鍵性因素。而信任評(píng)估機(jī)制為開放式網(wǎng)絡(luò)環(huán)境下的安全提供了一種保障方案,因此如何構(gòu)建合理有效的信任評(píng)估機(jī)制是一項(xiàng)重要任務(wù)。對(duì)于信任評(píng)估結(jié)果的準(zhǔn)確性來(lái)說(shuō),現(xiàn)有的信任評(píng)估機(jī)制還存在一些可以改進(jìn)的地方,如普遍未充分考慮信任的不確定性問(wèn)題,忽略了對(duì)信任的否定及猶豫信息的描述,未考慮到文字評(píng)論和等級(jí)評(píng)價(jià)的不一致問(wèn)題,不能滿足用戶對(duì)評(píng)估準(zhǔn)確性的要求等。因此,本文提出了一種基于情感強(qiáng)度感知的動(dòng)態(tài)信任評(píng)估機(jī)制。該模型將信任管理與情感分析技術(shù)相結(jié)合,對(duì)信任的表達(dá)方式用情感強(qiáng)度向量重新給出了定義,根據(jù)信任屬性數(shù)據(jù)對(duì)實(shí)體間的動(dòng)態(tài)信任關(guān)系進(jìn)行評(píng)估,從而得到對(duì)實(shí)體合理的評(píng)估結(jié)果。首先,收集用戶終端的信任評(píng)論信息,評(píng)論信息是用戶對(duì)信任多維屬性評(píng)價(jià)的組合。利用對(duì)象抽取技術(shù)進(jìn)行信任屬性和對(duì)應(yīng)情感詞的抽取,并根據(jù)中英文情感詞典計(jì)算情感詞在各極性(正面、負(fù)面和中性)的情感強(qiáng)度值,實(shí)現(xiàn)了信任屬性評(píng)價(jià)與情感強(qiáng)度向量的對(duì)應(yīng)關(guān)系。從而更加合理和完備地對(duì)信任進(jìn)行了形式化描述,考慮了信任的不確定性,消除了用戶真實(shí)評(píng)價(jià)與等級(jí)評(píng)價(jià)不一致的問(wèn)題。其次,在量化后的信任評(píng)價(jià)數(shù)據(jù)基礎(chǔ)上,以信任屬性數(shù)據(jù)為計(jì)算單位設(shè)計(jì)信任計(jì)算算法,算法中充分結(jié)合了用戶間的歷史交互數(shù)據(jù)和其他用戶給出的推薦信任數(shù)據(jù),計(jì)算出服務(wù)實(shí)體的信任值�？紤]到信任隨時(shí)間衰減的動(dòng)態(tài)特性,通過(guò)指數(shù)分布法為不同時(shí)期的用戶歷史交易分配時(shí)間權(quán)重,從而使得對(duì)直接信任的評(píng)估更符合服務(wù)實(shí)體的近期表現(xiàn),實(shí)現(xiàn)了對(duì)行為不穩(wěn)定的策略型惡意攻擊的有效遏制。在反饋信任度計(jì)算中,給出了反饋可信度的計(jì)算方法,實(shí)現(xiàn)了對(duì)虛假、欺騙的惡意反饋評(píng)價(jià)的有效鑒別。然后,聯(lián)合得分函數(shù)和精確函數(shù)比較用戶總體信任度,給出了基于情感強(qiáng)度向量的服務(wù)實(shí)體選擇策略。最后,本文基于以上理論,設(shè)計(jì)并實(shí)現(xiàn)了基于情感強(qiáng)度感知的信任評(píng)估機(jī)制,并通過(guò)仿真實(shí)驗(yàn)對(duì)信任評(píng)估機(jī)制的性能進(jìn)行了研究。實(shí)驗(yàn)結(jié)果表明所提模型能夠有效描述實(shí)體間的信任關(guān)系,顯著識(shí)別并消除多種惡意攻擊行為,提高了信任評(píng)估的準(zhǔn)確性。
[Abstract]:In recent years, with the rise of the Internet, the applications of open computing system (Agent system, P2P network, Ad Hoc network, etc.) and electronic commerce (eBay,Amazon etc.) have been developed rapidly. However, its dynamic characteristics, such as openness, anonymity and deceptiveness, make all kinds of network security problems stand out day by day, and security problems have become the key factors restricting its development. The trust evaluation mechanism provides a guarantee scheme for the security in the open network environment, so how to construct a reasonable and effective trust assessment mechanism is an important task. For the accuracy of the results of trust assessment, there are still some improvements in the existing trust assessment mechanism. For example, the uncertainty of trust is not fully considered, and the description of negative and hesitant information about trust is ignored. It does not take into account the inconsistency between text comments and rating evaluation, and can not meet the requirements of users for the accuracy of evaluation and so on. Therefore, this paper proposes a dynamic trust evaluation mechanism based on emotion intensity perception. This model combines trust management with emotion analysis technology, and redefines the expression of trust with emotion intensity vector, and evaluates the dynamic trust relationship between entities according to the trust attribute data. Thus, the reasonable evaluation results of the entity are obtained. Firstly, the trust comment information of user terminal is collected, which is a combination of users' evaluation of multi-dimensional attributes of trust. The object extraction technique is used to extract the trust attribute and the corresponding affective words, and the emotional intensity of the affective words in all polarity (positive, negative and neutral) is calculated according to the Chinese and English emotional Dictionary. The relationship between the evaluation of trust attribute and the emotion intensity vector is realized. Therefore, the formal description of trust is more reasonable and complete, the uncertainty of trust is considered, and the problem of inconsistency between user's real evaluation and grade evaluation is eliminated. Secondly, on the basis of quantized trust evaluation data, trust computing algorithm is designed with trust attribute data as the unit of calculation. The algorithm fully combines the historical interactive data between users and the recommended trust data given by other users. Calculates the trust value of the service entity. Taking into account the dynamic characteristics of trust decay over time, the exponential distribution method is used to assign time weights to users' historical transactions over different periods, thus making the assessment of direct trust more consistent with the recent performance of service entities. An effective containment of strategic malicious attacks with unstable behavior is achieved. In the calculation of feedback trust, the calculation method of feedback credibility is given, and the effective identification of false and deceptive malicious feedback evaluation is realized. Then, the total trust degree of the user is compared with the precision function, and the service entity selection strategy based on the emotion intensity vector is given. Finally, based on the above theory, a trust evaluation mechanism based on emotion intensity perception is designed and implemented, and the performance of trust evaluation mechanism is studied through simulation experiments. The experimental results show that the proposed model can effectively describe the trust relationship between entities, identify and eliminate many malicious attacks, and improve the accuracy of trust evaluation.
【學(xué)位授予單位】：南京郵電大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP393.08

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 井世忠;董才林;喻瑩;李佳偉;;基于模糊理論的網(wǎng)構(gòu)軟件信任評(píng)估方法[J];計(jì)算機(jī)工程;2012年05期

2 耿延軍;張紅旗;周靖;;基于模糊理論的行為信任評(píng)估研究[J];計(jì)算機(jī)工程與設(shè)計(jì);2007年24期

3 龍毅宏;潘丹;張海松;唐志紅;;基于模糊Petri網(wǎng)的信任評(píng)估[J];信息安全與通信保密;2008年03期

4 路峰;吳慧中;;網(wǎng)格環(huán)境下的信任評(píng)估模型研究[J];計(jì)算機(jī)應(yīng)用研究;2008年04期

5 彭冰;付才;韓蘭勝;崔永泉;;無(wú)線自組網(wǎng)中基于匿名電子投票的信任評(píng)估[J];計(jì)算機(jī)仿真;2009年02期

6 郎波;雷凱;江川;張靜輝;;基于信任訪問(wèn)控制中信任評(píng)估與追溯方法研究[J];計(jì)算機(jī)應(yīng)用;2009年06期

7 邱洪君;黃佳進(jìn);;分布式信任評(píng)估研究[J];計(jì)算機(jī)工程與應(yīng)用;2009年25期

8 劉大成;張宏銘;黃引;;網(wǎng)絡(luò)空間下一種新型信任評(píng)估機(jī)制[J];四川兵工學(xué)報(bào);2009年09期

9 吳靜;劉衍珩;王健;李偉平;;車載自組網(wǎng)的可信認(rèn)證與信任評(píng)估框架[J];通信學(xué)報(bào);2009年S1期

10 楊成云;張明清;唐俊;;基于信任評(píng)估的安全路由方案設(shè)計(jì)[J];計(jì)算機(jī)工程;2010年07期

相關(guān)會(huì)議論文 前3條

1 劉彬;張仁津;;一種基于Web服務(wù)的信任評(píng)估模型[A];2010年全國(guó)開放式分布與并行計(jì)算機(jī)學(xué)術(shù)會(huì)議論文集[C];2010年

2 張曉琴;陳蜀宇;常光輝;盧華瑋;;可信網(wǎng)絡(luò)中的信任評(píng)估模型[A];第十四屆全國(guó)容錯(cuò)計(jì)算學(xué)術(shù)會(huì)議(CFTC'2011)論文集[C];2011年

3 王斌;房燦新;劉慶峰;;基于Ad-Hoc網(wǎng)絡(luò)構(gòu)建離散式信任評(píng)估機(jī)制的研究[A];2008年中國(guó)高校通信類院系學(xué)術(shù)研討會(huì)論文集（下冊(cè)）[C];2009年

相關(guān)博士學(xué)位論文 前5條

1 牛景春;供應(yīng)鏈企業(yè)信任評(píng)估與可信服務(wù)組合方法研究[D];燕山大學(xué);2016年

2 路峰;信任評(píng)估模型及其方法研究[D];南京理工大學(xué);2009年

3 許小豐;無(wú)線傳感器網(wǎng)絡(luò)路由信任評(píng)估與數(shù)據(jù)傳輸控制關(guān)鍵技術(shù)研究[D];北京郵電大學(xué);2010年

4 范存群;車聯(lián)網(wǎng)環(huán)境下基于可靠接入的高效數(shù)據(jù)傳輸機(jī)制研究[D];北京郵電大學(xué);2014年

5 李俊;服務(wù)網(wǎng)絡(luò)中服務(wù)協(xié)同的可信機(jī)制與算法研究[D];浙江大學(xué);2012年

相關(guān)碩士學(xué)位論文 前10條

1 王瑞超;基于反饋信任的用戶行為動(dòng)態(tài)信任評(píng)估模型研究[D];天津理工大學(xué);2015年

2 顧峗;數(shù)據(jù)驅(qū)動(dòng)的量化信任評(píng)估模型及其在農(nóng)業(yè)物聯(lián)網(wǎng)中的應(yīng)用[D];復(fù)旦大學(xué);2014年

3 劉元兵;基于屬性和信任評(píng)估的訪問(wèn)控制機(jī)制研究[D];西南交通大學(xué);2016年

4 汪礦;基于情感強(qiáng)度感知的動(dòng)態(tài)信任評(píng)估機(jī)制研究[D];南京郵電大學(xué);2016年

5 高云璐;云計(jì)算下信任評(píng)估技術(shù)的研究[D];上海交通大學(xué);2012年

6 井世忠;一種網(wǎng)構(gòu)軟件動(dòng)態(tài)信任評(píng)估模型研究[D];華中師范大學(xué);2012年

7 吳守才;云環(huán)境中基于信任評(píng)估的數(shù)據(jù)自銷毀研究[D];遼寧大學(xué);2015年

8 徐培;信任評(píng)估理論在商品評(píng)價(jià)信息可信度判定中的應(yīng)用[D];合肥工業(yè)大學(xué);2015年

9 鄒璐;基于普適環(huán)境的動(dòng)態(tài)協(xié)同的信任評(píng)估模型的研究[D];遼寧工程技術(shù)大學(xué);2011年

10 楊莎;基于云理論的信任評(píng)估模型及應(yīng)用研究[D];華北電力大學(xué);2011年

，

本文編號(hào)：2205221