| 引用本文: | 郭茂祖,陈加栋,张彬,等.融合空间偏好和语义的个体活动识别方法.[J].国防科技大学学报,2022,44(3):57-66.[点击复制] |
| GUO Maozu,CHEN Jiadong,ZHANG Bin,et al.Method for individual activities recognition incorporating spatial preference and semantics[J].Journal of National University of Defense Technology,2022,44(3):57-66[点击复制] |
|
| |
|
|
| 本文已被：浏览 5032次 下载 3993次 |
| 融合空间偏好和语义的个体活动识别方法 |
| 郭茂祖1,陈加栋1,张彬1,赵玲玲2,李阳1 |
|
(1. 北京建筑大学 电气与信息工程学院, 北京 100044;2. 哈尔滨工业大学 计算机科学与技术学院, 黑龙江 哈尔滨 150001)
|
| 摘要: |
| 个体活动识别对用户画像、个性化推荐、异常行为检测、群体行为分析和基于活动的资源配置优化具有重要价值。提出了一种基于稀疏的社交媒体签到数据的个体活动语义识别方法,从签到数据中提取活动行为的时间周期性和趋势性特征,并采用空间偏好量化算法,从个体与群体活动的空间关联中提取群体和个体的空间访问偏好,使用自然语言嵌入工具BERT模型提取访问兴趣点的语义。时间特征、空间偏好特征和访问兴趣点名称语义特征共同构成表征群体、个体偏好的时空联合特征,通过极限梯度提升分类器对其进行分类,得到活动语义识别结果。在Foursquare数据集上的对比实验和消融实验中验证了所提活动语义识别模型可以有效提升活动语义识别的准确性。 |
| 关键词: 活动语义识别 空间偏好 兴趣点语义 极限梯度提升树 BERT |
| DOI：10.11887/j.cn.202203008 |
| 投稿日期：2021-06-15 |
| 基金项目:国家自然科学基金面上资助项目(61871020,62101022)；北京市属高校高水平创新团队建设计划资助项目(IDHT20190506)；国家重点研发计划子课题资助项目(2020YFF0305501)；北京市教委科技计划重点资助项目(KZ201810016019) |
|
| Method for individual activities recognition incorporating spatial preference and semantics |
| GUO Maozu1, CHEN Jiadong1, ZHANG Bin1, ZHAO Lingling2, LI Yang1 |
|
(1. School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, China;2. School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China)
|
| Abstract: |
| The recognition of individual activities helps in the realisation of functions such as user profiling, personalized recommendations, abnormal behaviour detection, city-wide group behaviour analysis and resource allocation optimisation. A recognition method for the semantics of individual activities based on sparse social media check-in data was proposed. The temporal periodicity and tendency features of activity behaviors were extracted from the check-in data, and a spatial preference quantification algorithm was utilized to extract the preferences of groups and individuals from the spatial relevance between individual and group activities. The natural language embedding model BERT was used to extract the semantics of POIs (point of interest). The temporal features, spatial preference features and text features of POI′s names constituted the joint spatio-temporal features characterizing group and individual preferences, and the joint features were classified by the extreme gradient boosting classifier to obtain the activity semantic recognition results. With the results of comparison experiments and ablation experiments on the Foursquare dataset, it was validated that the model proposed can effectively improve the accuracy of activity semantics recognition. |
| Keywords: semantic recognition of activities spatial preference semantics of point of interest extreme gradient boosting tree BERT |
|
|
|
|
|
