关键词: 云制造, 服务推荐, 服务组合, 场景聚类, 主题模型

Abstract: To better mine and organize the service composition scenario information in the cloud manufacturing service system,and establish an efficient service recommendation algorithm to assist users to create service compositions,a cloud manufacturing service recommendation model based on scenario recognition was proposed.The model first reconstructed the initial service composition description by supplementing function information.Then the model clustered the service compositions by application scenario based on the obtained comprehensive scenario descriptions,and established a weighted service library for each scenario.The service recommendation was completed by identifying the scenario categories of user requirements and utilizing the weighted service library of each scenario.Experiments on the real-world data set showed that the proposed method brought a better performance in recommendation effect.

Key words: cloud manufacturing, service recommendation, service composition, scenario clustering, topic model