Most scheduling problems are required to follow rigid metrics, such as the maximum completion time, earliest deadline first, etc., ignoring the flexibility of manufacturing services (MSs) and the effects of their historical data hidden in millions of manufacturing activities. The historical data serves as a powerful basis for describing the comprehensiveness or credibility of the MS itself with the help of Industrial IoT enabling all equipment to communicate and take preventive actions. Similar to the bank credit for individuals, MSs should also have their own referential credit values when choosing the most suitable service for a specific manufacturing task. This paper summarizes the MS attributes from six aspects with sufficient sub-attributes. The fuzzy Analytic Network Process combined with the Cross-Entropy method is employed to evaluate the credit of MSs in the complex manufacturing network system. Such service scoring mechanism (SSM) can personify a comprehensive credit evaluation of services, where, a smart service configuration mode based on credit is proposed for carrying out the supply–demand matching with the help of the data-security technology. Subsequently, a credit-based manufacturing mode is derived under SSM. Numerical examples are carried out to demonstrate the validity of the matching mode. The result may assist manufacturers to allocate their manufacturing tasks in real time in a “credit” way and make quicker decisions in exceptional circumstances, while making the chosen service truly competent enough to finish the work, so as to further improve the customer satisfaction.

大多数调度问题都需要遵循严格的度量标准，例如最大完成时间，最早的截止日期优先等，而忽略制造服务（MS）的灵活性以及其历史数据隐藏在数百万个制造活动中的影响。历史数据是通过工业物联网使MS能够全面通信或采取预防措施而描述MS本身的全面性或可信性的有力依据。与个人的银行信用类似，MS在为特定制造任务选择最合适的服务时也应具有自己的参考信用值。本文从六个方面总结了MS属性，并提供了足够的子属性。将模糊分析网络过程与交叉熵方法相结合，对复杂制造网络系统中MS的信用进行评估。这种服务评分机制（SSM）可以代表对服务的全面信用评估，其中，提出了一种基于信用的智能服务配置模式，以借助数据安全技术进行供需匹配。随后，在SSM下导出基于信用的制造模式。数值例子说明了匹配模式的有效性。结果可以帮助制造商以“信用”的方式实时分配制造任务，并在特殊情况下更快地做出决定，同时使选定的服务真正有能力完成工作，