Service recommendation based on description reconstruction in cloud manufacturing

ABSTRACT

Cloud manufacturing has become an important development trend in the manufacturing industry. Manufacturing companies package their resources and capabilities as manufacturing services and publish on cloud manufacturing service system. With the rapid increase of a number of services being published on the service system, information overload becomes an issue. To identify functional requirements accurately and create service compositions in a timely manner, effective manufacturing service recommendation algorithm is urgently needed. Most traditional recommendation methods ignore the evolving characteristics of the cloud manufacturing service system and rely on initial static service descriptions. These descriptions are usually neither comprehensive nor pertinent in describing service application scenarios. To solve such issues, a novel method of Time-aware Targeted Reconstructing Service Descriptions (T-TRSD) is proposed in this paper. T-TRSD aims to reconstruct service descriptions by adding service composition descriptions. The evolving characteristics of services are also taken into consideration by the algorithm. This model complements the potential application scenarios of services, identifies the application scenario of the specific requirement and gives this scenario a higher weight. Based on service descriptions reconstructed by T-TRSD, a new manufacturing service recommendation strategy is offered. Comprehensive experiments show that this method brings a better recommendation performance.

KEYWORDS:

• Cloud manufacturing service system
• manufacturing service recommendation
• service descriptions
• service compositions
• Time-aware
• topic model

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes

1. http://www.programmableweb.com.

Additional information

Funding

This research has been partially supported by the National Natural Science Foundation of China [No.61673230]; High-Tech Ship Research Project of China [17GC26102.01]. Yushun Fan is the Corresponding Author.