基于大数据的人才信息流向分析系统  

Talent Information Flow Analysis System Based on Big Data

作　　者：睢治 曹杰 王立文[1] 

机构地区：[1]徐州工程学院信息工程学院,江苏 徐州

出　　处：《数据挖掘》2020年第3期176-182,共7页Hans Journal of Data Mining

摘　　要：基于大数据的人才信息流向分析系统对地区的基本人才信息进行系统的收集、整理后,流动人口的经济特征包括就业身份、职业属性、单位性质、就业收入与住房支出等变量[1],将这些影响的主要因素提取,提取共有属性,可以根据人才流动时的地区特点、经济影响、时间、性别等因素进行分类,简单划分成稳定型人才、流动型人才、回归型人才等作为人才信息流动的训练样本集,基于k-近邻算法对新导入的人才信息进行分析,将人才划分到不同种类中,为决策者提供数据支持。基于大数据的人才信息流向分析系统为决策者们提供一个可视化方便、效率高的分析系统,系统设计使用UML用例图进行软件需求分析,使用包图进行软件体系设计。The talent information flow analysis system based on big data systematically collects the basic tal-ent information of the region. After sorting, the economic characteristics of the floating population include variables such as employment status, occupational attributes, unit nature, employment in-come and housing expenditure [1]. The main factors of these influences are extracted, and the common attributes are extracted. They can be classified according to the regional characteristics, economic impact, time, gender and other factors during the flow of talents. They can be simply di-vided into stable talents, mobile talents, and regression talents as the flow of talent information. The training sample set based on k-nearest neighbor algorithm analyzes the newly imported talent information, divides the talents into different categories, provides data support for decision makers, and the talent information flow analysis system based on big data provides decision makers with a visual, convenient and efficient analysis system. The system design uses UML use case diagrams for software requirements analysis, and the software system design uses package diagrams for soft-ware system design.

关 键 词：人才信息流向 K-近邻算法 数据支持 UML 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]