RBF神经网络的旅游管理系统安全风险评价
2020-08-07张文正
张文正



摘 要: 针对传统旅游管理系统安全风险评价方法存在的评价误差大的缺点,提出一种RBF神经网络的旅游管理系统安全风险评价方法。在RBF神經网络的基础上,建立安全风险评价指标体系,并采用灰色关联度分析法确定各评价指标的权重,再计算安全风险评价指标值,通过专家评价法确定安全风险评价等级后,训练样本数据,采用模糊评价法对旅游管理系统安全风险做出评价,至此完成RBF神经网络的旅游管理系统安全风险评价方法的设计与实现。实验结果表明,与传统的安全风险评价方法相比,文中提出的评价方法能够更精确地评价旅游管理系统的安全风险,具有更高的有效性。
关键词: 旅游管理; 安全风险评价; RBF神经网络; 评价指标建立; 样本数据训练; 评价方法设计
中图分类号: TN915.08?34; TP183 文献标识码: A 文章编号: 1004?373X(2020)13?0065?04
Method of tourism management system safety risk assessment
based on RBF neural network
ZHANG Wenzheng
(Shangqiu Institute of Technology, Shangqiu 476000, China)
Abstract: A tourism management system security risk assessment method based on RBF neural network is proposed to cope with the defect of big error of the security risk assessment methods for the traditional tourism management system. On the basis of the RBF neural network, a security risk evaluation index system is built, the grey relational analysis (GRA) method is used to determine the weight of each evaluation index, and then the security risk evaluation index value is calculated. The security risk evaluation grade is determined with the expert evaluation method for the training of the sample data. The security risk of tourism management system is evaluated with the fuzzy evaluation method. The design and implementation of the tourism management system safety risk assessment method based on the RBF neural network are completed by the above means. The experimental results show that, in comparison with the traditional security risk assessment method, the proposed evaluation method can evaluate the security risks of the tourism management systems more accurately and has higher effectiveness.
Keywords: tourism management; security risk assessment; RBF neural network; evaluation index establishment; sample data training; evaluation method design
0 引 言
随着人们生活水平的提高,旅游成为一种受到人们广泛欢迎的休闲方式,旅游业得到了长足的发展。随着互联网技术的不断发展,旅游从业者改变了原始的管理方式,通过旅游管理系统对旅游相关的信息进行管理[1?4]。然而,网络在给用户带来便利的同时,也会给旅游管理系统的安全性带来一定的风险。为保证网络信息的安全性,对其做出评价是十分必要的[5]。因此,采用某种方法对旅游管理系统安全风险的评价具有非常重要的意义。RBF神经网络是一种三层前向神经网络,具有结构简单、局部逼近能力强的特点,被广泛应用在各种非线性控制和评价中[6?10]。……
