A Material Recommendation System for Enterprise Manufacturing Integrated Systems

Aiming at providing effect informations efficiently for appropriate users in the integration systems of enterprise manufacturing who was faced excessive search volume, information overload, time-consuming manual filtering, and no approximate query support problems, a product-user recommendation model was proposed and a recommendation system available for integrating was implemented. This recommendation model combined contents based on filtering and collaborative filtering. In the aspect of items, the specific forms of the recommended items were considered, all the characteristics of the BOM including parts, semi-finished products, products were comprehensively analyzed, and new metric methods were proposed based on content similarity, BOM-based similarity and the integration. Different items selected different methods to define the approximate distances which were the foundation of subject clustering or classification according to the specific circumstances. While in the aspect of users, the user interests were quantified and the user approximation formula were defined according to the characteristics of the production systems. Finally, this paper implemented the recommendation platform in the form of a system suite, considering cold start problem by introducing the latest research results. Experiments show that the system may accurately recommend the items that meet their needs for users and it is an important supplement for current manufacturing systems for obtaining information efficiently. © 2019, China Mechanical Engineering Magazine Office. All right reserved.