%0 Journal Article %A XIONG Huafeng %A SUN Yinghua %A LI Jianbo %A LIAN Wenjuan %A LIU Xueqing %T Solving of Multi-Attribute Bilateral Matching Problem Under Background of Shared Economy %D 2019 %R 10.3778/j.issn.1002-8331.1809-0017 %J Computer Engineering and Applications %P 222-228 %V 55 %N 24 %X The problem of bilateral matching is modeled by improving the attribute matching degree calculation model so as to obtain the preference order of the two sides. The machine learning idea is introduced to improve the solution of the ant colony algorithm. In view of the early maturity and difficult convergence problem, the nonlinear gradient heuristic information and the state transfer strategy based on historical search information are proposed. In order to reduce the workload of parameters initialing, a self-adjusted method of parameters based on the gradient descent is proposed. The rule considering matching stability and results matching effective guides the pheromone updating of ant colony algorithm. Simulation result shows that evaluation value in the improved ant colony algorithm has a 20% improvement compared with the traditional ant colony algorithm. The matching stability is better than that in the traditional ant colony and the improved RNA calculation. %U http://cea.ceaj.org/EN/10.3778/j.issn.1002-8331.1809-0017