计算机科学与探索

• 学术研究 •    下一篇

面向12345政务热线事件分拨的深度行为语义网络

陈顺,易修文,张钧波,李天瑞,郑宇   

  1. 1.西南交通大学 计算机与人工智能学院,成都 611756
    2.北京京东智能城市大数据研究院,北京 100176
    3.京东城市(北京)数字科技有限公司,北京 100176

Deep Behavior and Semantic Network for 12345 Hotline Event Dispatch

CHEN Shun, YI Xiuwen, ZHANG Junbo, LI Tianrui, ZHENG Yu   

  1. 1.School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756, China
    2.JD Intelligent Cities Research, BDA, Beijing 100176, China
    3.JD Intelligent Cities Technology Co., Ltd, Beijing 100176, China

摘要: 市民在遇到困难时,会通过12345政务服务热线寻求帮助。在收到市民请求之后,热线工作人员将对市民的需求进行分析,并将事件分拨给对应的政府部门进行处理。目前通过人工完成的分拨过程占用了大量的人力资源,同时许多事件被分拨到错误的部门。为了提高分拨过程的效率和正确率,提出了一种数据驱动的高效自动化事件分拨方法。基于历史分拨记录,事件文本和部门职责,设计了一个用于事件分拨的深度行为语义网络(Deep Behavior and Semantic Network,DBSN)。它包含了三个部分,分别是历史行为编码,事件语义学习和多维特征匹配网络。历史行为编码模块构建了一个在事件类别和分拨部门之间的多级二分图,通过图编码学习行为特征。事件语义学习模块使用卷积神经网络(convolutional neural network,CNN)网络和注意力机制来学习事件诉求和部门权责的语义特征。多维特征匹配模块从行为,语义两个维度上将事件与部门的特征做匹配。在实验中,使用了两年的南通12345政务热线数据,实验结果证明了提出的方法与基线方法相比具有优势。

关键词: 12345政务热线, 事件分拨, 层次二分图, 文本分类, 城市计算

Abstract: In China, citizens can seek help from the 12345 hotlines when they suffer from problems in daily life. After receiving requests from citizens, the hotline officer analyzes the demand of citizens and dispatches events to the corresponding government departments. Currently, the whole process mainly relies on manual work, which takes up a lot of human resources and leads to many incorrect dispatches. To improve the efficiency and accuracy of dispatching, in this paper, an efficient automatic data-driven event dispatch approach is proposed. Considering the historical dispatch records, event text and department responsibility, a Deep Behavior and Semantic Network (DBSN) for event dispatch is proposed. The network mainly consists of a history behavior encoding module, an event semantic learning module and a multi-dimension feature matching module. The history behavior encoding module builds a hierarchical bipartite graph network between different categories of events and departments, learning dispatch patterns through graph node embedding. The event semantic learning module uses the CNN and attention mechanism to learn the semantic information of event demand and department responsibility. The multi-dimension feature matching module matches events and departments from three dimensions including behavior, semantic and fusion features. Based on the Nantong 12345 Hotline data, experimental results demonstrate the advantages of the proposed approach compared with baselines.

Key words: 12345 Hotline, Event Dispatch, Hierarchical Bipartite Graph, Text Classification, Urban Computing