本文選題：推薦系統(tǒng) + 實(shí)時(shí)推薦�。� 參考：《江蘇大學(xué)》2017年碩士論文

【摘要】：現(xiàn)有的職位推薦系統(tǒng)主要通過智能檢索、簡(jiǎn)歷匹配、用戶相似性和定時(shí)推送等方法推薦,然而已有職位推薦方法主要基于用戶的歷史偏好,未考慮用戶行為變化對(duì)求職偏好的影響且無(wú)法根據(jù)該變化及時(shí)響應(yīng)其最新的求職動(dòng)向,導(dǎo)致推薦實(shí)時(shí)性差。另外,現(xiàn)有基于用戶的職位協(xié)同推薦主要采用默認(rèn)值處理職位評(píng)分矩陣的缺失值,未考慮用戶對(duì)職位的偏好差異,降低了相似性計(jì)算質(zhì)量且該方法缺乏考慮用戶的特定需求,如對(duì)薪資或?qū)W歷等屬性的要求,導(dǎo)致推薦的可靠性不高。針對(duì)上述問題,提出了基于用戶動(dòng)態(tài)行為變化的職位實(shí)時(shí)推薦方法。通過監(jiān)聽用戶操作事件,判斷用戶是否發(fā)生添加或更新求職意愿信息和點(diǎn)擊其他職位的行為變化,及時(shí)發(fā)現(xiàn)其最新的求職動(dòng)向并產(chǎn)生推薦,從而解決推薦實(shí)時(shí)性差的問題。此外,提出了基于職位評(píng)分預(yù)測(cè)的協(xié)同推薦算法。在現(xiàn)有UserCF算法基礎(chǔ)上,對(duì)缺失的職位評(píng)分進(jìn)行預(yù)測(cè)填充處理,提升相似性計(jì)算質(zhì)量并對(duì)結(jié)果進(jìn)行過濾,從而提高推薦可靠性。論文主要工作如下:(1)系統(tǒng)需求分析和總體設(shè)計(jì)。為能夠及時(shí)發(fā)現(xiàn)用戶最新求職動(dòng)向并推薦可靠的職位,采用了包括數(shù)據(jù)層、推薦算法層和應(yīng)用層的總體架構(gòu)。為獲取職位資源和用戶偏好信息,數(shù)據(jù)層需采集職位信息和用戶行為數(shù)據(jù)。為向用戶推薦可靠的職位,推薦算法層需利用采集的用戶行為數(shù)據(jù),訓(xùn)練職位推薦算法,以構(gòu)建用戶求職偏好模型。為向用戶展示職位推薦信息,應(yīng)用層需提供前臺(tái)交互頁(yè)面,及時(shí)響應(yīng)用戶操作。因此,系統(tǒng)按照功能劃分為數(shù)據(jù)采集模塊、職位推薦模塊和前臺(tái)頁(yè)面交互模塊。(2)系統(tǒng)詳細(xì)設(shè)計(jì)。針對(duì)數(shù)據(jù)采集模塊,采用職位爬蟲抓取網(wǎng)絡(luò)職位數(shù)據(jù)和利用數(shù)據(jù)庫(kù)或消息隊(duì)列保存用戶行為數(shù)據(jù)。根據(jù)不同的推薦邏輯,將職位推薦模塊分為職位實(shí)時(shí)推薦和職位協(xié)同推薦兩子模塊。針對(duì)職位實(shí)時(shí)推薦,采用消息隊(duì)列保存用戶最新的行為事件消息,當(dāng)用戶發(fā)生添加或更新求職意愿和點(diǎn)擊職位的行為時(shí),通過監(jiān)聽消息隊(duì)列的事件消息變化,分別觸發(fā)在線職位匹配推薦和在線職位關(guān)聯(lián)推薦,以提高推薦的實(shí)時(shí)性。針對(duì)職位協(xié)同推薦,采用預(yù)測(cè)值填充職位評(píng)分矩陣的缺失值,提升相似性質(zhì)量,基于此,計(jì)算協(xié)同推薦結(jié)果并對(duì)其過濾,以提高推薦的可靠性。前臺(tái)頁(yè)面交互模塊基于響應(yīng)式布局的方法設(shè)計(jì)頁(yè)面,以提高推薦響應(yīng)效率。(3)系統(tǒng)實(shí)現(xiàn)與測(cè)試。系統(tǒng)基于J2EE實(shí)現(xiàn)。職位實(shí)時(shí)推薦通過Storm實(shí)現(xiàn)并利用Flume和Kafka收集和緩存事件日志;職位協(xié)同推薦通過Mahout實(shí)現(xiàn)。由測(cè)試結(jié)果可知系統(tǒng)能夠及時(shí)向用戶推薦可靠的職位。此外,在對(duì)職位評(píng)分矩陣的缺失值進(jìn)行預(yù)測(cè)填充后,協(xié)同推薦在準(zhǔn)確率和召回率上平均提升35%和40%。
[Abstract]:The existing job recommendation systems are mainly recommended by intelligent retrieval, resume matching, user similarity and timing push. However, the existing job recommendation methods are mainly based on users' historical preferences. Without considering the influence of user behavior change on job search preference and unable to respond to the latest job search trend according to this change, the recommendation real-time performance is poor. In addition, the default value is mainly used to deal with the missing value of the position score matrix, which does not take into account the difference of the user's preference to the position, which reduces the quality of similarity calculation and does not take into account the specific needs of the users. Such as salary or academic qualifications such as attribute requirements, resulting in recommendation reliability is not high. In order to solve the above problems, a real-time job recommendation method based on user dynamic behavior change is proposed. By monitoring the user's operation events, we can judge whether the user's behavior changes in adding or updating the job seeking intention information and clicking on other positions, and find out the latest job search trend and produce the recommendation in time, so as to solve the problem of poor real-time recommendation. In addition, a collaborative recommendation algorithm based on job score prediction is proposed. Based on the existing UserCF algorithm, the missing job score is predicted and filled, the similarity calculation quality is improved and the results are filtered to improve the reliability of the recommendation. The main work of this paper is as follows: 1) system requirement analysis and overall design. In order to find out the latest job trends of users and recommend reliable positions in time, an overall framework including data layer, recommendation algorithm layer and application layer is adopted. In order to obtain position resource and user preference information, the data layer needs to collect position information and user behavior data. In order to recommend reliable positions to users, the recommendation algorithm layer needs to use the collected user behavior data and train the position recommendation algorithm to build a job preference model. In order to display the position recommendation information to the user, the application layer should provide the front desk interactive page and respond to the user operation in time. Therefore, the system is divided into data acquisition module, position recommendation module and front page interaction module. For the data acquisition module, the position crawler is used to grab the network position data and the database or message queue is used to save the user behavior data. According to the different recommendation logic, the position recommendation module is divided into two sub-modules: real time recommendation and collaborative recommendation. For post recommendation, message queue is used to save the latest behavior event message of user. When the behavior of adding or updating job search will and clicking on position occurs, the event message changes in message queue are monitored. The online position matching recommendation and the online position correlation recommendation are triggered respectively to improve the real-time performance of the recommendation. In order to improve the reliability of the job recommendation, the prediction value is used to fill the missing value of the position score matrix to improve the similarity quality. Based on this, the collaborative recommendation results are calculated and filtered. The front page interaction module designs the page based on the method of response layout to improve the efficiency of recommendation response. The system is implemented based on J2EE. Real time job recommendation is implemented by Storm, event log is collected and cached by Flume and Kafka, and post collaborative recommendation is implemented by Mahout. Test results show that the system can recommend reliable positions to users in time. In addition, after filling in the missing value of the position score matrix, the cooperative recommendation increased the accuracy and recall by an average of 35% and 40%.
【學(xué)位授予單位】：江蘇大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 薛安榮;王丹;黃祖衛(wèi);;基于CSS模板的職位信息并行抽取系統(tǒng)設(shè)計(jì)[J];電子科技;2016年10期

2 董紅斌;滕旭陽(yáng);楊雪;;一種基于關(guān)聯(lián)信息熵度量的特征選擇方法[J];計(jì)算機(jī)研究與發(fā)展;2016年08期

3 曾安;謝杰民;潘丹;;基于項(xiàng)目候選集的協(xié)同過濾算法[J];計(jì)算機(jī)應(yīng)用研究;2016年12期

4 魯驍;王書鑫;王斌;魯凱;;一種融合地理位置信息的協(xié)同過濾推薦算法[J];中文信息學(xué)報(bào);2016年02期

5 李超;周濤;黃俊銘;程學(xué)旗;沈華偉;;基于用戶相似性傳遞的跨平臺(tái)交叉推薦算法[J];中文信息學(xué)報(bào);2016年02期

6 羅燕;趙書良;李曉超;韓玉輝;丁亞飛;;基于詞頻統(tǒng)計(jì)的文本關(guān)鍵詞提取方法[J];計(jì)算機(jī)應(yīng)用;2016年03期

7 鄭麟;朱福喜;姚杏;;基于屬性提升與局部采樣的推薦評(píng)分預(yù)測(cè)[J];計(jì)算機(jī)學(xué)報(bào);2016年08期

8 黃震華;張佳雯;田春岐;孫圣力;向陽(yáng);;基于排序?qū)W習(xí)的推薦算法研究綜述[J];軟件學(xué)報(bào);2016年03期

9 張玉潔;杜雨露;孟祥武;;組推薦系統(tǒng)及其應(yīng)用研究[J];計(jì)算機(jī)學(xué)報(bào);2016年04期

10 謝海濤;孟祥武;;適應(yīng)用戶需求進(jìn)化的個(gè)性化信息服務(wù)模型[J];電子學(xué)報(bào);2011年03期

相關(guān)碩士學(xué)位論文 前4條

1 路小瑞;基于Hadoop平臺(tái)的職位推薦系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[D];上海交通大學(xué);2015年

2 仵，

本文編號(hào)：1947432