基于游览行为和逆向强化学习的游客偏好学习  

Tourist preference learning method based on travel behavior and inverse reinforcement learning

作　　者：宣闻 常亮[1] XUAN Wen;CHANG Liang(Guangxi Key Laboratory of Trusted Software,Guilin University of Electronic Technology,Guilin 541004,China)

机构地区：[1]桂林电子科技大学广西可信软件重点实验室,广西桂林541004

出　　处：《桂林电子科技大学学报》2023年第3期173-180,共8页Journal of Guilin University of Electronic Technology

基　　金：国家自然科学基金(U1811264,U1711263,61966009,61862016);广西自然科学基金(2018GXNSFDA281045,2017GXNSFAA198283);广西高校中青年教师科研基础能力提升项目(2019KY0226)。

摘　　要：为了获取游客在景区内的游览行为数据从而学习出游客的细粒度偏好,提出一种基于游览行为和逆向强化学习的游客偏好学习方法。该方法通过物联网和移动传感器技术,采集游客在特定景点内的各个游览点的拍照次数、游玩时间等游览行为数据。针对采集到的行为数据设计逆向强化学习算法,基于获取到的真实数据进行细粒度偏好学习。基于真实场景的实验结果表明,该方法能够在少量游客游览行为数据的情况下,有效学习出游客的细粒度偏好。In order to obtain tourists'behavior data in scenic and learn the tourists'fine-grained preferences,tourist preference learning method based on travel behavior and inverse reinforcement learning is proposed.First of all,through the Internet of things and mobile sensor technology to collect tourists'behavior data such as the number of taking photos,the time of visiting in the point of scenic spots.Then,the inverse reinforcement learning algorithm is designed for the collected behavior data to perform fine-grained preference learning based on the obtained real data.The experimental results show that the method can effectively learn fine-grained preferences with a small amount of tourist behavior data based on real scenarios.

关 键 词：游客偏好 游览行为 逆向强化学习 移动传感器技术 细粒度偏好 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]