Interaction Dynamics in AEC Global Teamwork

Architecture, engineering, and construction (AEC) global project teamwork is communication intensive and relies heavily on synchronous and asynchronous information and collaboration technologies (ICT). We explore in this paper how an asynchronous ICT, called ThinkTank, reshaped the work practice of design-construction global teams, and how the interaction with this ICT reshaped the purpose and benefits of its use. ThinkTank is a web-based asynchronous collaboration and discussion forum. We introduce the influence diffusion model (IDM) that formalizes the process of identifying the influence of people, messages, and terms mathematically. Discovering who the influence leaders in project teams are can be beneficial and critical from a corporate management perspective, since they can guide or motivate the team towards successful actions and outcomes. We present the ThinkTank-IDM integrated system and its validation with a testbed of 53 AEC global team project archived in ThinkTank over 8 years.     

基于多Agent的协同工作环境的实现

为了支持跨平台、异构环境下的协同工作,提出了一个基于多Agent的网上协同工作环境(multi-agent based cooperative work, MACW),构造了MACW系统的三层逻辑模型以及多Agent和浏览器/服务器相结合的系统结构,并结合多Agent技术、JMF等关键技术给出了系统的具体实现。MACW较好的解决了现有的协同工作环境存在的灵活性差、扩展能力不足、对意外情况不能及时处理等问题。     

Learning attention-based strategies to cooperate for multi-agent path finding

Multi-agent path finding (MAPF) is a challenging multi-agent systems problem where all agents are required to effectively reach their goals concurrently with not colliding with each other and avoiding obstacles. In MAPF, it is a challenge to effectively express the observation of agents, utilize historical information, and effectively communicate with neighbor agents. To tackle these issues, in this work, we proposed a well-designed model that utilizes the local states of nearby agents and outputs an optimal action for each agent to execute. We build the local observation encoder by using residual attention CNN to extract local observations and use the Transformer architecture to build an interaction layer to combine local observations of agents. With the purpose of overcoming the deficiency of success rate, we also designed a new evaluation index, namely extra time rate (ETR). The experimental results show that our model is superior to most previous models in terms of success rate and ETR. In addition, we also completed the ablation study on the model, and the effectiveness of each component of the model was proved.     

分布式多媒体协同工作系统DMCS的模型与实现

分布多媒体协同工作系统ＤＭＣＳ是基于ＣＳＣＷ协作机制设计的ＣＳＣＷ原型系统。     

基于多分片贝叶斯网络的多Agent系统模型表示

多Agent系统模型表示是系统实现推理、学习、自组织和Agent间通信的基础。由于多Agent系统结点较多的特性, 一般用单个贝叶斯网络作为模型表示是不现实的。本文提出用多分片的贝叶斯网络作为多Agent系统的表示语言,并详细讨论了将多分片贝叶斯网络转化为具有良好推理计算特性的联合树扩展形式的连接联合森林的具体过程。     

基于多Agent的监控调度系统软件模型

针对传统监控系统软件的缺陷,本文在介绍Agent概念的基础上,对Agent技术在监控系统中的应用进行研究,提出了基于多Agent的监控调度系统软件模型,并在实际中进行了应用.     

基于MAS的分布式智能控制初探

论述了工业控制技术的发展历程,从初期的开环控制到智能控制、分布式控制;重点讨论了基于MAS的分布式智能控制的思想、研究内容和重点,并综述了国内外一些研究组织、学者的研究成果;提出了基于MAS理论的联盟方法研究分布式智能控制系统中各子系统间协调控制问题的思路以及研究进展。     

浅谈高校办公自动化系统建设

办公自动化系统建设是高校工作现代化建设的一项重要内容，是提高高校在高技术教育条件下整体工作能力的有效途径。对高校在高技术条件下如何搞好办公自动化系统建设提出了几点建议。     

Web搜索引擎系统的设计与实现

对基于HTTP协议自动检索Web信息和自动管理信息检索范围的方法进行了分析，并验证了协同信息发现的可操作性及效率。     

基于消息中间件的网络协同编辑环境框架

给出了利用消息中间件和事件抽象技术来实现文本协同编辑环境的实现框架 ,并在此框架的基础上实现了基于MBus中间件的共享WPS协同编辑系统 .基于此框架可以在网络多媒体会议系统中实现各种可编辑文档的共享和协同编辑 .此框架通过实现的协同文本编辑环境验证了实现网络会议系统中各种可编辑文档协同共享编辑的可能性和可靠性 ,并且能够进一步完善视频会议的功能并增加会议的真实感和沉浸感