基于EDM的大学生职业发展方向预测方法研究

发布时间：2018-05-07 19:10

本文选题：数据挖掘 + 灰色预测算法　；参考：《东北师范大学》2017年硕士论文

【摘要】：随着国家对高等教育投入的不断加大,各地高校的招生规模也随之扩大,在校学生的人数越来越多,大多数普通高校都面临着学生就业难的问题。诚然,毕业生的职业发展受到包括个体素质、家庭背景、就业政策等多种因素影响,但在高校中教育引导的影响仍处主要地位。在《教育部关于做好2016届全国普通高等学校毕业生就业创业工作的通知》中第三条指出:大力提高就业指导服务能力,建立精准推送就业服务机制,各地高校要充分利用“互联网+”技术,实现智能化供需匹配,实现就业服务信息化、个性化。在这种大形势下,如何提升大学生的综合素质,提高高校人才培养质量,成为各高校亟待解决的重中之重。因此,在高校教育中,教育工作者如何为学生合理、有效、及时地开展职业发展方向指导工作是一项重要的工作任务。但是在这种教育信息化快速发展的大环境下,在高校教育工作者的工作有很大诉求的情况下,教学过程中积累的海量数据却只是以各种不同形式的表格存储在不同的计算机上,并没有被更深层次的挖掘使用,这造成了这些数据被大量的闲置。面对以上现状,笔者在研究中发现在进行高校学生职业发展方向指导工作中,对大学生的未来职业发展方向进行预测是必要的,有效的预测方法可以为教育工作者提供客观、简便的数据支撑及理论依据,助其顺利实施教育指导工作。因此,本文就此开展了一系列的研究工作。笔者首先分析了高校职业生涯教育工作过程中存在的问题,进而进行了教育数据挖掘相关理论与常用方法分析和大学生职业发展方向影响因子维度分析,从而确定了本文的研究维度,然后进行了预测模型的建模、算法实现及预测方法的实例检验等相关研究。根据以上的研究,笔者得出了以下结论:灰色预测算法在中小规模数据预测上性能更优越;基于综合素质测评数据进行预测,得到的预测结论(预测学生的未来职业发展方向)更加客观、精准。但本研究中的算法设计仍存在不足,可以在未来的研究中尝试通过更大量的数据和更多的实验验证去调整相关参数,从而进一步优化算法。
[Abstract]:With the increasing of the national investment in higher education, the enrollment scale of colleges and universities has also expanded, and the number of students is increasing. Most ordinary colleges and universities are facing the problem of difficult employment of students. It is true that the professional development of graduates is influenced by many factors, such as individual quality, family background, employment policy and so on, but the influence of educational guidance is still in the main position in colleges and universities. The third article of the notice of the Ministry of Education on doing a good Job in the Employment and Entrepreneurship of the 2016 National ordinary College graduates points out: vigorously improve the ability of employment guidance services, and establish a mechanism for precise employment promotion service. Colleges and universities all over the world should make full use of "Internet" technology, realize intelligent supply and demand matching, and realize the informationization and individuation of employment service. In this situation, how to improve the comprehensive quality of college students and improve the quality of talent training has become the most important task to be solved. Therefore, in college education, it is an important task for educators to guide their career development in a reasonable, effective and timely manner. However, under the circumstances of the rapid development of educational informatization and the great demands of the educators in colleges and universities, the massive data accumulated in the teaching process is only stored on different computers in various forms. It is not used in deeper mining, which results in a large amount of idle data. In the face of the above situation, the author finds that it is necessary to predict the future career development direction of college students in the process of guiding the career development direction of college students, and the effective prediction method can provide objective for the educators. Simple data support and theoretical basis for its smooth implementation of education guidance. Therefore, this paper carried out a series of research work. The author first analyzes the problems existing in the process of career education in colleges and universities, and then analyzes the relevant theories and methods of educational data mining and the dimension analysis of the influencing factors of college students' career development direction. The dimension of this paper is determined, and then the modeling of the prediction model, the algorithm realization and the example test of the prediction method are studied. Based on the above research, the author draws the following conclusions: the grey prediction algorithm has better performance in the prediction of small and medium scale data, and based on the comprehensive quality evaluation data to predict, The predicted conclusions are more objective and accurate. However, the algorithm design in this study is still insufficient, we can try to adjust the relevant parameters through more data and more experimental verification in the future research, so as to further optimize the algorithm.
【学位授予单位】：东北师范大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：G647.38;TP311.13

【参考文献】