共享经济背景下多属性双边匹配问题求解  

Solving of Multi-Attribute Bilateral Matching Problem Under Background of Shared Economy

作　　者：熊化峰 孙英华 李建波 廉文娟[2] 刘雪庆 XIONG Huafeng;SUN Yinghua;LI Jianbo;LIAN Wenjuan;LIU Xueqing(College of Computer Science and Technology,Qingdao University,Qingdao,Shandong 266071,China;College of Information Science and Engineering,Shandong University of Science and Technology,Qingdao,Shandong 266590,China)

机构地区：[1]青岛大学计算机科学技术学院,山东青岛266071 [2]山东科技大学信息科学与工程学院,山东青岛266590

出　　处：《计算机工程与应用》2019年第24期222-228,共7页Computer Engineering and Applications

基　　金：国家自然科学基金（No.61502261）;山东省重点研发计划项目（No.2016GGX101032）;山东省教育厅高校科技计划项目（No.J17KB149）

摘　　要：对双边匹配类问题进行抽象建模,改进属性匹配度计算模型,求出匹配双方的偏好序,引入机器学习的思想改进蚁群算法对之求解。针对蚁群算法前期易早熟、后期难收敛的问题,提出非线性梯度启发信息和基于历史搜索信息的状态转移策略;针对蚁群算法初始参数设置难、调参工作量大的问题,提出基于梯度下降思想的自动调参方法;并制定稳定匹配和当前最优匹配的评价规则,引导蚁群算法的信息素更新。仿真结果表明改进的蚁群算法与传统蚁群算法相比评价值提升约20%。与传统蚁群和基于RNA计算改进的蚁群算法相比求解稳定性更优。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.

关 键 词：共享经济 双边匹配 匹配稳定性 蚁群算法 梯度下降 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]