考虑可执行度的地铁服务质量提升策略研究

On quality improvement schemes of metro service considering feasibility

基于地铁运营服务质量评价结果制定合理的策略以提升服务质量,是地铁运营管理的重要工作。为了使一定时期内地铁运营服务质量提升策略具有更好的可执行性,融合考量基于乘客视角的服务质量指标的得分、权重和一定时期内受限于运营技术条件、资源的改进可执行度,将决策树引入重要性战略矩阵(IPA),构建用于决策服务质量指标改进优先级和改进幅度的决策树-重要性战略矩阵模型(DT-IPA)。DT-IPA模型运用分类回归树(CART)算法构建决策树,计算服务质量指标权重并生成分类规则,然后运用层次分析法计算指标改进可执行度。基于所获取的指标权重构建IPA,运用分类规则和指标改进可执行度优化调整由IPA确定的指标初始改进优先级,并量化被调整指标的改进幅度,使调整后的总体服务质量达到预期目标。以2020年11月长沙地铁2号线运营服务质量调查数据开展实证分析。案例结果表明:“车厢拥挤度”指标落在IPA决策的优先改进区,但由于其改进可执行度不足,DT-IPA模型把该指标的改进优先级调整为最低,并选择适当提升“购票与充值服务”和“生命与财产安全”指标服务水平,使得总体服务质量仍有94.3%的概率获得非常满意的评价。实证分析验证了DT-IPA模型的有效性,该方法可用作地铁运营单位提升服务质量的决策工具。

It is an important management task of metro agencies to formulate reasonable improvement schemes based on the surveyresults of service quality.In order to make quality promotion strategy of metro service more implementable in a certain period,by considering scores and weights of passenger perceived service quality attributes as well as their improvement feasibility limited by operational technical conditions and resources,the Decision Tree(DT)was integrated into theImportance-Performance Analysis(IPA)to build a DT-IPA model,which was used to determine the improvement priority of attributes,and to quantify the degree of improvement.The DT-IPA model begins with using the Classification and Regression Tree(CART)algorithm to construct an optimal decision tree to derive the weights of attributes and to generate if-then rules.Then,the analytic hierarchy process was applied to compute the degree of improvement feasibility of attributes.The weights of attributes were applied to construct IPA;the if-then rules and the degree of improvement feasibility were used to optimize the initial improvement priority of attributes determined by IPA and to quantify the degree of improvement of the adjusted attributes.After the adjustment,the overall service quality can reach a high score,realizing the operation goal.An empirical study was conducted based on the survey of Changsha Metro Line 2 in November 2020.The result shows that train crowdedness was assigned to the“concentrate here”quadrant of IPA.However,due to the insufficient improvement feasibility of this attribute,the DT-IPA model adjusted its improvement priority to the lowest level,and chose to appropriately improve the service level of“ticket purchase and top-up service”and“safety and security”,which enabled the overall service quality to the rank of“very satisfying”with a possibility of 94.3%.The proposed method can be a decision-making tool for metro agency managers to improve the quality of metro service.