An approach to improve the efficiency of configurators

Configurators have been generally accepted as important tools to bridge the gap between customers' needs and company offerings in the form of specific instances of product platform. To date, improving the efficiency of configurators is a big challenge for both the academic research and the current practice in the competitive global marketplace. In this paper, a new configurator design approach is presented to tackle the configuration task in an efficient manner by providing adaptive and customized configuring sequence for individual customers to best match his preference towards the products. To represent and manipulate the probabilistic nature of customers' preferences, Bayesian network is deployed to reflect the product physical structure and the likelihood of the customers' potential preferences among components. The configuring process is modeled as an uncertainty elimination process and an information theory based algorithm is applied to obtain customers' targeted configuration. The idea is to sequentially select the component with most relevant information for a customer to configure from the remaining components pool based on his previous steps' specification. A case study is reported to demonstrate the feasibility and potential of the proposed method.