城市轨道交通服务质量评价是行业监管部门为监督和评估轨道交通运营服务水平，定期开展的考核工作。传统的城市轨道交通服务质量评价采用比较各线路总体得分的形式，对乘客的主体感知和真实需求的探讨较少。为提高城市轨道交通服务质量，基于乘客的感知及需求构建城市轨道交通服务质量评价指标体系，建立基于结构方程模型(structural equation modeling，SEM)及贝叶斯网络的综合评价模型。通过SEM评估模型中变量之间的关系，利用贝叶斯推理与诊断对其进行辅助决策，以更准确地揭示各变量对服务质量的影响程度，有针对性地优化服务方案，多维度地满足乘客需求。最后以昆明市轨道交通为例，对其服务质量进行评价。研究结果表明：设施可靠、人工服务与出行安全对服务质量的影响幅度较大；通过对模型未知参数的拟合优度进行评价，得到偏差信息准则DIC=29>10，验证了本文所提模型的可行性与适用性。

The evaluation of urban rail transit service quality is regularly carried out by the industry supervisory department to monitor and evaluate the operation service level of rail transit. The traditional evaluation of urban rail transit service quality involves comparing the overall scores of each line with less exploration of the main perceptions and real needs of passengers. To improve the service quality of urban rail transit, an evaluation index system of urban rail transit service quality was constructed based on passengers’ perceptions and demands, and a comprehensive evaluation model based on SEM and a Bayesian network were developed. The relationship between variables in the model is evaluated by SEM, and the auxiliary decision is made by Bayesian inference and diagnosis, to more accurately reveal the influence degree of each variable on the quality of service, optimize the service plan targeted, and meet the demands of passengers in multiple dimensions. Finally, take Kunming rail transit as an example to evaluate its service quality. The results show that the reliability of facilities, manual service, and travel safety has a great influence on service quality. By evaluating the goodness of fit of the unknown parameters of the model, the Deviance Information Criterion DIC=29>10 was obtained, which verified the feasibility and applicability of the model proposed in this paper.

U231