基于知识相似度的产品开发任务分配方法  

Task assignment method of product development based on knowledge similarity

作　　者：陈友玲[1] 左丽丹 牛禹霏 王龙 CHEN Youling;ZUO Lidan;NIU Yufei;WANG Long(College of Mechanical Engineering,Chongqing University,Chongqing 400044,China)

机构地区：[1]重庆大学机械工程学院,重庆400044

出　　处：《计算机应用》2019年第2期323-329,共7页journal of Computer Applications

基　　金：国家自然科学基金资助项目(71271224)~~

摘　　要：针对产品开发的任务分配中知识不对等问题,提出一种基于任务与人员双边匹配的产品开发任务分配方法。首先,从知识量化的角度把任务与人员的匹配转化为任务与人员之间的知识相似度,建立序值矩阵,转换成任务对人员匹配的满意度矩阵;其次,根据人员在不同任务属性下对任务的偏好程度,获得人员对任务满意度的序值矩阵;然后,以双方之间的满意度最大为原则,构建基于双边匹配的任务分配多目标优化模型,采用基于隶属度函数的加权和方法转化为线性规划,并通过Matlab编程求解该模型;最后以某企业生产曲轴连杆机构为例,求解4项任务与7名人员双方满意度最大的匹配结果,确定最终的分配方案,与基于聚类分析和双边匹配的产品开发任务分配方法相比,结果显示人员3和人员7之间的知识相似度、人员偏好存在明显差值,表明所提方案能更高效地分配任务。Focusing on the issue that knowledge is not equal in task assignment of product development,a task assignment model of product development based on bilateral matching of task and designer was proposed.Firstly,the matching between task and designer was transformed into the similarity of knowledge between task and designer from the perspective of knowledge quantification,then the order value matrix was established and transformed into the satisfaction degree matrix of task to designer matching.Secondly,according to the degree of preference of the designer to the task under different task attributes,the order value matrix of designer satisfaction to task was obtained.Thirdly,based on the principle of maximum satisfaction between the two parties,a multi-objective optimization model based on knowledge similarity and designer preference was constructured.The method of weighted sums based on membership function was used to change the multi-objective optimization model into linear programming model,then the obtained model would be solved by Matlab programming.Finally,taking a crankshaft linkage mechanism produced by one enterprise as an example,the matching result between four tasks and seven designer was obtained to determine the final assignment plan.By comparing with task assignment methods of product development based on clustering analysis and bilateral matching,the apparent difference between the knowledge similarity and the designer preference between the designer 3 and 7 indicated that the proposed method can assign tasks more efficiently.

关 键 词：产品开发 任务分配 知识相似度 人员偏好 双边匹配 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TP391.9[自动化与计算机技术—控制科学与工程]