188宝金博页面版

第 23 卷第 3 期 复 杂 系 统 与 复 杂 性 科 学 Vol.23 No.32026 年 6 月 COMPLEX SYSTEMS AND COMPLEXITY SCIENCE Jun. 2026文章编号:1672 3813 ( 2026 ) 03 0152 09 ; DOI : 10.13306 / j.1672-3813.2026.03.018考虑多时间尺度特征的 GRU-Transformer 酒店入住率预测付 丽 1 ,王西琼 2(1. 太原师范学院经济与管理学院,山西 晋中 030619 ; 2. 泸州职业技术学院文旅学院,四川 泸州 646600 )摘要: 针对当前酒店入住率预测问题中数据难获取,预测具有滞后性,挖掘数据周期性与连续性特征不充分的现状,提出一种考虑多时间尺度特征的 GRU-Transformer 混合深度学习方法。首先对年、月、日周期时间片段入住率数据特征矩阵进行建模,构建模型输入数据;然后构建 Attention-GRU 和 Conv-Transformer 模块相结合的并行计算结构,对数据周期性与连续性特征进行挖掘,融合特征后输出预测值;最后对 2 家酒店历史入住率数据进行参数调优以及消融与对比实验。实验表明:所提算法在预测精度上提升较大,同时能够充分满足时效性的时间要求,可用于酒店入住率数据实时预测,帮助酒店管理者及时调整经营战略,提升酒店竞争力。关键词: 酒店;入住率预测;深度学习; GRU ; Transformer 模型中图分类号: TP183 ; F59 文献标识码: A收稿日期: 2024 07 09 ; 修回时间: 2024 11 26基金项目: 山西省哲学社会科学规划课题( 2022YY131 );山西省回国留学人员科研资助项目(2021 147 )第一作者: 付 丽( 1988 ),女,山西大同人,博士,讲师,主要研究方向为消费者行为分析等。The Hotel Occupancy Rate Forecasting Based on GRU-transformer Considering Multi-time Scale FeaturesFU Li1 , WANG Xiqiong2(1.School of Economics and Management , Taiyuan Normal University , Jinzhong 030619 , China ; 2. College of Culture and Tourism , Luzhou Vocational and Technical College , Luzhou 646000 , China )Abstract : In view of the current situation of difficult data acquisition , lagging forecasting and in-sufficient periodicity and continuity of data mining in hotel occupancy prediction , a hybrid deep learning method of GRU-Transformer considering multi-time scale features is proposed. First , model the occupancy rate data feature matrix of year , month and day cycle time segments , and construct the input data of the model. Then , a parallel computing structure combining Attention-GRU and Conv-Transformer modules is constructed to excavate the periodic and continuity char-acteristics of the data and output the predicted value after integrating the characteristics. Finally , the historical occupancy data of two hotels are optimized and the ablation and comparison experi-ments are carried out. Experiments show that the algorithm proposed in this paper can greatly improve the prediction accuracy , and can fully meet the time requirement of timeliness. It can be used for real-time prediction of hotel occupancy data , help hotel managers timely adjust business strategy and improve hotel competitiveness.Keywords : hotel ; occupancy rate forecast ; deep learning ; GRU ; transformer model0 引言近年来,随着大数据与网络技术的发展,酒店系统积累了大量蕴含客流变化规律与趋势的数据,基于人工智能的酒店数据挖掘技术已经成为合理配置酒店资源、规避风险、提升酒店服务水平的有力支撑 [1 2 ] 。针对当前酒