【摘要】：由于國(guó)家對(duì)精品課程建設(shè)的大力推廣,作為精品課程核心內(nèi)容之一的精品課程網(wǎng)絡(luò)教學(xué)平臺(tái)也已經(jīng)得到普及。然而現(xiàn)在的精品課程網(wǎng)絡(luò)教學(xué)平臺(tái)普遍存在個(gè)性化學(xué)習(xí)推薦功能較弱、互動(dòng)性較差等情況,所以用戶利用網(wǎng)絡(luò)教學(xué)平臺(tái)進(jìn)行學(xué)習(xí)的體驗(yàn)并不優(yōu)秀,這也成為了導(dǎo)致網(wǎng)絡(luò)教學(xué)平臺(tái)利用率不高的因素之一。本文基于關(guān)聯(lián)規(guī)則挖掘技術(shù)和AJAX技術(shù),以軟件工程技術(shù)為指導(dǎo),設(shè)計(jì)并實(shí)現(xiàn)了具有個(gè)性化學(xué)習(xí)內(nèi)容推薦功能和較強(qiáng)互動(dòng)功能的精品課程網(wǎng)絡(luò)教學(xué)平臺(tái)。個(gè)性化學(xué)習(xí)內(nèi)容推薦功能包含兩個(gè)核心子模塊：一是實(shí)現(xiàn)關(guān)聯(lián)規(guī)則挖掘子模塊,二是利用關(guān)聯(lián)規(guī)則實(shí)現(xiàn)學(xué)習(xí)內(nèi)容推薦子模塊。在關(guān)聯(lián)規(guī)則挖掘模塊中采用了Apriori算法對(duì)用戶的訪問日志進(jìn)行關(guān)聯(lián)規(guī)則挖掘,實(shí)現(xiàn)用戶訪問系統(tǒng)時(shí)的學(xué)習(xí)內(nèi)容推薦；同時(shí),基于用戶訪問的內(nèi)容數(shù)據(jù)具有層次性的特點(diǎn),本文也研究了利用ML-SH挖掘算法對(duì)同層數(shù)據(jù)進(jìn)行關(guān)聯(lián)規(guī)則挖掘,從而實(shí)現(xiàn)了板塊之間的訪問推薦效果。在平臺(tái)實(shí)現(xiàn)的基礎(chǔ)上,本文對(duì)平臺(tái)的關(guān)聯(lián)規(guī)則模塊進(jìn)行了測(cè)試,并對(duì)測(cè)試過程中關(guān)聯(lián)規(guī)則模塊可能存在的問題進(jìn)行了分析。同時(shí),為了獲知用戶對(duì)平臺(tái)推薦的學(xué)習(xí)內(nèi)容的滿意程度,即系統(tǒng)推薦的效果,本文提出了利用統(tǒng)計(jì)用戶訪問系統(tǒng)推薦的內(nèi)容數(shù)量占其當(dāng)次訪問的內(nèi)容數(shù)量的比值,作為評(píng)判用戶滿意度的方式,并以該方式對(duì)系統(tǒng)的推薦效果進(jìn)行了實(shí)驗(yàn)測(cè)試,實(shí)驗(yàn)結(jié)果證明用戶對(duì)推薦的內(nèi)容是感到滿意的。
[Abstract]:Due to the national promotion of the construction of high-quality courses, as one of the core contents of high-quality courses, the network teaching platform of high-quality courses has also been popularized. However, the current excellent course network teaching platform generally has the situation that the personalized learning recommendation function is weak, the interaction is poor and so on, so the user's experience of using the network teaching platform to carry on the study is not excellent. This has also become one of the factors that lead to the low utilization rate of network teaching platform. Based on association rule mining technology and AJAX technology, this paper designs and implements a network teaching platform for excellent courses with personalized learning content recommendation function and strong interaction function under the guidance of software engineering technology. The personalized learning content recommendation function consists of two core sub-modules: one is to realize the association rule mining sub-module, the other is to use the association rules to realize the learning content recommendation sub-module. In the association rule mining module, Apriori algorithm is used to mine the user's access log, and the learning content recommendation is realized when the user accesses the system. At the same time, based on the hierarchical characteristics of the content data accessed by users, this paper also studies the use of ML-SH mining algorithm to mine association rules for the same layer of data, so as to achieve the effect of access recommendation between plates. On the basis of the implementation of the platform, this paper tests the association rules module of the platform, and analyzes the possible problems of the association rules module in the testing process. At the same time, in order to know the satisfaction of users with the learning content recommended by the platform, that is, the effect of system recommendation, this paper proposes to use the ratio of the number of recommended content to the number of content that users visit the system. As a way to judge user satisfaction, the recommendation effect of the system is tested in this way. The experimental results show that the user is satisfied with the recommended content.
【學(xué)位授予單位】：廣西大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP311.13;TP393.092

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 陳以海;;高校精品課程網(wǎng)站建設(shè)探索[J];中國(guó)教育信息化;2008年01期

，

本文編號(hào)：2483689