A Graph Search Approach to Automate Product Concept Translation

Product data translation is essential for the seamless integration of various product-centric activities. Yet, the process to build translators among different software has been left mostly to individual expertise rather than a formal procedure. In this paper, we propose a framework to automatically determine translation rules to enable translation of instances from one system to another. We use a graph search method to obtain the overall translation rule as a combination of multiple basic functions. We apply this method to a subset of non-geometric product knowledge, such as date of creation, color and name of feature used in two commercial systems. We detect the rules using a manually created training data set and evaluate their correctness manually.