Online review driven route planning of green cold chain logistics: Considering service attribute preference

For the long-distance cold chain transportation, this study focuses on green route planning in the cold chain multimodal transport network, considering the customers' preferences on transport service attributes. To extract customers' preferences from online reviews, we build the bidirectional gated recurrent units (BiGRU) and Logit framework. The coefficients representing the preferences for transport service attributes are calculated and integrated into the route planning model. To enhance the reliability of the routes, we utilize fuzzy set theories to describe travel time, transport cost coefficient, and capacity as trapezoidal fuzzy numbers. Then, we develop a fuzzy route planning model aims to minimize transportation cost, damage cost, refrigeration cost, carbon emission cost, and reliability cost. The numerical experiments are conducted on the new land and sea corridor in southwest China. The proposed method can plan the route which meet the customers’ preferences on transportation cost, travel time, reliability and carbon emission. Moreover, logistics companies can strike a balance between cost and reliability by setting confidence coefficients for travel time and capacity. Furthermore, carbon trading policy implements the significant effect on carbon emission reduction in cold chain logistics, when the trading price is 2 RMB per unit.