系统科学研究所成立40周年 | 综合集成与知识科学研究小组系列报告 | 2019.11.1
-------------------------------------------------------------------------------------------------------------
15:00-15:30,李振鹏(大理大学)基于Hawkes自激励过程的在线集体注意力动力学过程实证研究
Dynamics of Online Collective Attention as Hawkes Self-exciting Process
Abstract:Understanding the dynamic formation mechanism of online collective attention happened via Internet memes, viral videos, or social media platforms and Web-based business, has been attracted diversified interests and also brought practical applications in the area of marketing and advertising, propagation of information. Bulletin Board System, or BBS can be regarded as an ecosystem of digital resources connected and shaped by collective successive behaviors of users. Clicks and replies of the posts quantify the degree of collective attention. Users' clicks on BBS lead to the up and down of focus on posts, and attention shift between topics. The ratio between clicks and replies measures the heat degree of a post. We analyze the dynamics of collective attention millions of users on the Tianya Zatan Borad of Tianya BBS. By analyzing the dynamics of clicks we uncover a non-trivial Hawkes process self-exciting regularity concerning the impact of novelty exponential decay mechanism. It is able to explain the empirical data of BBS remarkably well, such as popular topics are observed in time frequently cluster, asymptotic normality of clicks. Our findings indicate that collective attention among large populations decays with an exponential decaying law, suggest the existence of a natural time scale over novelty fades.
16:00-16:30,王灿(石家庄铁道大学)铁路工程项目利益相关者关系网络分析
摘要:伴随着“一带一路”倡议得到更多国家响应和中国铁路“走出去”战略的不断推进,国内外铁路工程建设项目日益增多。铁路工程项目环节多,周期长,涉及设计单位、承包商、监理单位、设备供应商以及政府建设部门等诸多利益相关者。分析这些相关者的关系有利于建立合理的治理机制,协调行动、提高工作效率,整合工程资源,降低运行成本,促进他们之间的长期战略合作,实现与国际工程项目管理顺利接轨。本研究对铁路工程建设开工项目中的利益相关者数据进行了分析,探究和描述铁路工程项目不同阶段各参与方关系网络的特性,从关系行为主体、合作强度和拓扑结构等方面分析利益相关者的关系演化规律。
16:30-17:00,许诺(北大方正集团有限公司)事件抽取技术研究
摘要:事件抽取是信息抽取领域一个重要研究方向。事件抽取技术将含有事件信息的非结构化文本以结构化的形式呈现出来,在智能查询、知识图谱构建和自动问答等领域有着广泛应用。本报告首先介绍事件抽取任务的定义;然后,分别从特征构造方式、模型学习方式、语料自动扩展三个方面介绍事件抽取技术的研究现状;最后,介绍基于神经网络模型进行事件抽取研究的探索。
17:00-17:30,贾玉改(中国科学院自动化研究所)大规模计算中相关技术应用
摘要:实际项目均针对真实场景实时计算,因此,首要条件为保证计算系统的稳定高效运行。为此,不同技术方法被引入作为保障机制,例如对计算资源的负载均衡技术、针对数据存储与数据查询的数据库切分技术等。报告将介绍在大规模数据计算中为保障系统的稳定高效运行采用的相关技术。