模糊多目标进化的社会团队形成方法

Social Team Formation Method Based on Fuzzy Multi-objective Evolution

目前,基于社会网络的团队形成问题研究大多采取0-1规则度量专家技能。针对人们通常使用自然语言描述专家技能的情况,提出模糊多目标进化的社会团队形成方法。该方法研究模糊环境下如何从专家社会网络中查询出合适的个体并组成规模一定的团队,实现最小的通信代价和最优的团队绩效。其采用模糊语言变量代替以0-1规则为代表的精确参数来描述专家技能,使用团队绩效的概念衡量团队对任务P的技能表现力。鉴于标准SPEA2算法在进化初期收敛速度慢的缺点,引入档案精英学习策略生成优良个体。另外,考虑到专家技能的模糊性,文中提出了细粒度Dominance判断作为判断个体间支配关系的新准则。仿真实验结果证明,改进算法的收敛速度快,获得的近似Pareto前沿更加逼近真实解集,可有效求解团队形成问题。

The present team formation researches in social network mostly take 0-1 rule to measure expert skills.Aiming at the situation that people often utilize the natural language to describe expert skills,this paper proposed a social team formation method based on fuzzy multi-objective evolution.This method focuses on how to find out the appropriate individuals from the expert social network to form a team with certain size and achieves the optimization between communication cost and team performance under the uncertainty circumstances.In this method,the precise parameters represented by 0-1 rule are replaced by fuzzy language variables to describe expert skill.The concept of team performance is used to measure team capability.Because the standard SPEA2 algorithm has slow convergence at the initial evolutio-nary stage,this paper introduced AEL strategy to generate individuals with good characteristics.Considering the ambi-guity of expert skills,this paper also proposed a fine-grained Dominance judgment as the new rule of judging the dominance relationship of individuals.The simulation results show that the improved algorithm converges fast and obtains good quality approximate PF,which can be successfully applied to solve the team formation problem.