A hypergraph model of product function recombination based on online reviews

Abstract

ABSTRACT Functional module recombination is a common means for manufacturers to upgrade and launch new product quickly. However, this method may bring with significant risks and it requires accurate identification on market trends in the uncertain environments, and cannot be achieved depend on expert experience. Therefore, a data-driven approach is proposed for product function recombination based on online reviews. Firstly, the information collection for e-commerce data is carried out to obtain product functional description, and the incidence matrix (IM) is formed by combining the corresponding relationship between function and product, so as to construct the hypergraph model. After that, for calculating the hyperedge weight and hyperedge degree as well as the hypernode weight and hypernode degree, random walk algorithm is introduced to obtain the transition probability between the function nodes. Moreover, three innovation strategies of product function recombination are proposed, including function expand, function trim and function replace respectively. Meanwhile, through the results of transition probability calculation, quantitative analysis is utilised for the implementation of different strategies. Finally, the headphone is taken as a case to verify the method, which is indicated as an effective functional optimisation tool and can provide a new research basis for product design.