基于高校毕业生与招聘企业双选的推荐系统

发布时间：2018-01-27 14:48

本文关键词： 就业毕业生推荐系统协同过滤　出处：《西南科技大学》2017年硕士论文　论文类型：学位论文

【摘要】：推荐系统的出现为解决大数据时代信息过载的问题提供了有力的技术支持,个性化推荐技术也成功应用于电子商务等领域,并取得了丰富的成果。在高校毕业生的就业推荐领域,个性化推荐技术的研究和应用还在进一步的研究和探索中。针对高校毕业生就业推荐问题,本文完成了基于高校毕业生与招聘企业双选的推荐系统的研究与设计。本文首先对个性化推荐技术的研究背景和国内外研究现状进行了总结;其次对推荐系统关键技术进行了介绍,对常用的推荐算法和推荐系统评价指标进行了分析;然后对网络招聘领域推荐系统的特点进行了分析,发现了该领域存在两类对等用户。为解决推荐算法面临的冷启动、数据稀疏性等问题,使用了基于内容过滤的推荐算法和基于双重聚类的协同过滤推荐算法,将两种推荐算法进行融合后的混合推荐技术作为系统的推荐引擎;最后完成就业推荐系统的设计与实现。实验结果表明,本文所采用的混合推荐系统能有效利用两种推荐算法的优势,取得了较好的推荐效果。
[Abstract]:The emergence of recommendation system has provided powerful technical support for solving the problem of information overload in big data era. Personalized recommendation technology has also been successfully applied in e-commerce and other fields. In the field of employment recommendation for college graduates, the research and application of personalized recommendation technology is still in the process of further research and exploration. This paper has completed the research and design of the recommendation system based on the double selection of college graduates and recruitment enterprises. Firstly, this paper summarizes the research background of personalized recommendation technology and the current research situation at home and abroad. Secondly, the key technologies of the recommendation system are introduced, and the commonly used recommendation algorithms and the evaluation index of the recommendation system are analyzed. Then the characteristics of recommendation system in the field of network recruitment are analyzed and two kinds of peer users are found in this field. In order to solve the problems of cold start data sparsity and so on. Using the recommendation algorithm based on content filtering and collaborative filtering recommendation algorithm based on double clustering, the hybrid recommendation technology after the fusion of the two recommendation algorithms is used as the recommendation engine of the system. Finally, the design and implementation of the employment recommendation system are completed. The experimental results show that the hybrid recommendation system can effectively utilize the advantages of the two recommendation algorithms and achieve a good recommendation effect.
【学位授予单位】：西南科技大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TP391.3

【相似文献】