为促进检验检测业服务质量提升，以检验检测（IT）服务质量评级和用户服务需求为切入点，采用基于长短期记忆网络（LSTM）的深度学习方法，设计由有形性、可靠性、响应性、安全性和移情性5个维度构成的评价体系，通过检验检测-服务质量-长短期记忆网络-情感分析模型（IT-QoS-LSTM-SA）对检验检测服务机构服务质量（QoS）进行评价与反馈，并利用7万多条相关文本数据进行实证。结果显示：LSTM模型在检验检测用户评论分类中的准确率达到了85.24%；根据情感分析（SA）计算得出检验检测服务质量的总评分为0.491 6，处于满意和非常满意程度之间。由此可以直观地看出检验检测服务质量在各项评价指标上的优劣程度。

In order to promote the service quality of the inspection and testing (IT) industry, the IT service quality rating and user service demand are used as the entry point, and a deep learning method based on long and short-term memory network (LSTM) is adopted, an evaluation system including five dimensions: tangibility, reliability, responsiveness, security and empathy is designed, and the inspection and testing - service quality - long and short-term memory network - sentiment analysis model (IT -QoS-LSTM-SA) to evaluate and provide feedback on the quality of service (QoS) of IT service organizations, and more than 70,000 relevant text data are applied for empirical evidence. The results show that LSTM model achieves an accuracy rate of 85.24% in the classification of IT user reviews; the overall rating of IT service quality is 0.491 6 according to sentiment analysis (SA)., which is between satisfactory and very satisfactory . This can visually see the quality of IT services in the degree of merit of each evaluation index.

F224；G301

国家重点研发项目“面向中小微企业的综合质量服务技术研发与应用”(项目编号：2019YFB1405300)；北京市属高等学校优秀青年人才培育计划项目“中小微企业综合质量智能服务与优化技术研究”（BPHR202203233）