本文關(guān)鍵詞： 聚類算法 神經(jīng)網(wǎng)絡(luò)算法 Holt-Winters 文本分類 數(shù)據(jù)分類　出處：《河北農(nóng)業(yè)大學(xué)》2015年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著移動互聯(lián)網(wǎng)的出現(xiàn),手機(jī)游戲、手機(jī)視頻、手機(jī)超市、無線音樂、手機(jī)閱讀、手機(jī)動漫等業(yè)務(wù)也隨之呈現(xiàn)。同時,中國移動的數(shù)據(jù)業(yè)務(wù)迅猛發(fā)展,使得日常業(yè)務(wù)管理的難度、復(fù)雜性越來越大。因錯單、惡意消費等問題給公司造成損失也使得客戶的滿意度降低,因此需要一些強(qiáng)有力的手段來監(jiān)控數(shù)據(jù)業(yè)務(wù)以便及時發(fā)現(xiàn)問題。目前實際運行的業(yè)務(wù)監(jiān)控系統(tǒng)主要針對用戶惡意消費、錯單量大、SP平臺利用系統(tǒng)漏洞非法獲利等現(xiàn)象造成的數(shù)據(jù)量急劇增大現(xiàn)象進(jìn)行監(jiān)控分析,但對某些業(yè)務(wù)存在誤報及漏報的情況。例如手機(jī)游戲、手機(jī)超市、手機(jī)閱讀等包月業(yè)務(wù)大多在月初進(jìn)行訂購,會導(dǎo)致訂購量大幅波動,屬于正�，F(xiàn)象,由于現(xiàn)有系統(tǒng)中算法的缺陷,未區(qū)分此類現(xiàn)象,產(chǎn)生大量錯誤的告警。本文針對現(xiàn)有業(yè)務(wù)監(jiān)控系統(tǒng)中存在的誤報漏報問題進(jìn)行研究,引入新的算法解決誤報漏報的問題,并通過機(jī)器學(xué)習(xí)算法訓(xùn)練智能告警過濾器,通過告警回復(fù)信息指導(dǎo)告警的過濾,以減輕工作人員的工作量。本文主要工作如下:(1)針對數(shù)據(jù)業(yè)務(wù)量波動較大的業(yè)務(wù)引入DBSCAN聚類算法,解決少量突發(fā)數(shù)據(jù)對算法結(jié)果的影響并且減少對波動很大但屬于正�，F(xiàn)象的數(shù)據(jù)的錯誤告警。同時,本文對該算法進(jìn)行改進(jìn),提高了該算法的效率,使得該算法可以應(yīng)用到時間粒度較精確的大數(shù)據(jù)業(yè)務(wù)。(2)針對周期性數(shù)據(jù)業(yè)務(wù),本文提出應(yīng)用神經(jīng)網(wǎng)絡(luò)算法與Holt-Winters組合模型進(jìn)行監(jiān)控的方法解決周期性業(yè)務(wù)異常數(shù)據(jù)漏報的問題。對于特殊業(yè)務(wù)進(jìn)行特殊監(jiān)控,提高了業(yè)務(wù)監(jiān)控系統(tǒng)產(chǎn)生告警的準(zhǔn)確率以及查全率。(3)業(yè)務(wù)監(jiān)控系統(tǒng)自動產(chǎn)生的告警信息仍需交由工作人員進(jìn)行處理,為減少人工工作量同時提高業(yè)務(wù)監(jiān)控系統(tǒng)產(chǎn)生告警的準(zhǔn)確度,本文提出利用告警回復(fù)信息,通過數(shù)據(jù)分類技術(shù)訓(xùn)練告警過濾器,指導(dǎo)告警的過濾。實驗表明,利用告警過濾器可分離出無效的告警信息,減少人工工作量。本文對原有業(yè)務(wù)監(jiān)控系統(tǒng)進(jìn)行的算法改進(jìn)可較好解決誤報漏報問題,并通過加入告警過濾器分離無效告警,實現(xiàn)減少人工工作量的目的。下一步將對告警過濾系統(tǒng)進(jìn)行深入研究,通過實現(xiàn)系統(tǒng)的自我學(xué)習(xí)、自我更新提高告警過濾效果。
[Abstract]:With the emergence of the mobile Internet, mobile phone games, mobile video, mobile supermarket, wireless music, mobile phone reading, mobile animation and other services are also emerging. At the same time, China Mobile's data business is developing rapidly. It makes the daily business management more and more difficult and complex. Because of the wrong order, malicious consumption and other problems to the company, it also makes the customer satisfaction decrease. Therefore, some powerful means are needed to monitor data services in order to detect problems in a timely manner. At present, the operational business monitoring system is mainly aimed at malicious consumption by users. The large amount of errors in SP platform makes use of system vulnerabilities and other phenomena such as illegal profit to monitor and analyze the phenomenon of a sharp increase in data, but some businesses exist false alarm and underreporting situation, such as mobile phone games, mobile supermarket, Most of the monthly services, such as mobile phone reading, order at the beginning of the month, which results in large fluctuations in the order volume, which is a normal phenomenon. Due to the defects of the existing system algorithms, there is no distinction between such phenomena. In this paper, a new algorithm is introduced to solve the problem of false false alarm, and the intelligent alarm filter is trained by machine learning algorithm. In order to reduce the workload of staff, the main work of this paper is as follows: 1) to introduce DBSCAN clustering algorithm for services with volatile data traffic. To solve the influence of a small amount of burst data on the result of the algorithm and to reduce the error alarm of the highly volatile but normal data. At the same time, this paper improves the algorithm to improve the efficiency of the algorithm. This algorithm can be applied to big data service with more accurate time granularity. In this paper, the neural network algorithm and Holt-Winters combined model are used to solve the problem of missing abnormal data of periodic services. It improves the accuracy of alarm generated by the service monitoring system and the recall rate. 3) the alarm information generated automatically by the business monitoring system still needs to be handled by the staff. In order to reduce the manual workload and improve the accuracy of alarm generated by the service monitoring system, this paper proposes to use the alarm response information and train the alarm filter through the data classification technology to guide the alarm filtering. The invalid alarm information can be separated by using the alarm filter, and the manual workload can be reduced. The algorithm improvement of the original service monitoring system can better solve the problem of false false alarm and separate the invalid alarm by adding the alarm filter. In the next step, the alarm filtering system will be deeply studied, and the alarm filtering effect will be improved through self-learning and self-updating.
【學(xué)位授予單位】：河北農(nóng)業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2015
【分類號】：TP181;TP277

【參考文獻(xiàn)】

相關(guān)期刊論文 前6條

1 周水庚,周傲英,曹晶,胡運發(fā);一種基于密度的快速聚類算法[J];計算機(jī)研究與發(fā)展;2000年11期

2 劉衛(wèi)寧;曾嬋娟;孫棣華;;基于DBSCAN算法的營運車輛超速點聚類分析[J];計算機(jī)工程;2009年05期

3 魯松,李曉黎,白碩,王實;文檔中詞語權(quán)重計算方法的改進(jìn)[J];中文信息學(xué)報;2000年06期

4 萬潔;;ARIMA模型與Holt-Winters模型在鐵路旅客周轉(zhuǎn)量預(yù)測中的比較[J];鐵道運輸與經(jīng)濟(jì);2010年02期

5 樊重俊,韓崇昭,胡保生;時間序列神經(jīng)網(wǎng)絡(luò)預(yù)測模型[J];統(tǒng)計與信息論壇;1996年03期

6 侯福均,吳祈宗;BP神經(jīng)網(wǎng)絡(luò)在鐵路客運市場時間序列預(yù)測中的應(yīng)用[J];運籌與管理;2003年04期

相關(guān)博士學(xué)位論文 前1條

1 孫越恒;基于統(tǒng)計的NLP技術(shù)在中文信息檢索中的應(yīng)用研究[D];天津大學(xué);2005年

相關(guān)碩士學(xué)位論文 前1條

1 張詠;中國移動業(yè)務(wù)監(jiān)控項目溝通管理研究[D];北京郵電大學(xué);2009年

，

本文編號：1534616