Abstract: Aiming at the huge number of task and personnel in the product development,a task assignment method of product development based on clustering analysis and two-sided matching was proposed to improve the overall satisfaction between task and personnel.By considering the index information of personnel attributes,the personnel were clustered by K-mediods clustering algorithm,which had the similar attribute characteristics.The evaluation and decision of optimal task set corresponded to each personnel clustering were realized by combining personnel preference information with dominance analysis based tasks sorting method,and then the exact match of task and personnel was realized in each clustering group based on two-sided matching theory.The feasibility and effectiveness of the proposed method were demonstrated by a case study.

Key words: product development, K-mediods clustering, two-sided matching, task assignment

摘要： 针对产品开发中人员和任务数量庞大的情形,为提高任务和人员的综合满意度,提出了一种基于聚类分析和双边匹配的产品开发任务分配方法。在分析人员属性指标信息的基础上,通过改进的K-mediods聚类算法完成属性特征相似人员的聚类,并结合人员偏好信息和优势数分析的任务评价排序方法,实现各人员聚类所对应的最优任务集的评价决策;运用双边匹配理论完成每个聚类群内任务与人员之间的精确匹配。通过实例验证了所提出的方法的有效性和可行性。

关键词: 产品开发, K-mediods聚类, 双边匹配, 任务分配