基于Agent联盟的协作学习系统研究

为了在协作学习系统中实现学习者Agent之间的有效合作,通过引入一种新的合作机制--同学关系网模型(Schoolmate Relation Web Model),来构建学习系统中学习者Agent之间的同学联盟,并且基于学习者Agent之间的同学联盟来实现多个学习者Agent之间的协作学习.在每个同学联盟中,任意两个Agent之间都具有同学关系,并且联盟中的所有Agent相互协作,共同完成学习任务.另外,联盟中的学习者Agent之间的通信不是直接进行的,而是通过一个黑板来进行,这可以显著地提高Agent之间的通信效率.由于同学关系网模型可以避免Agent联盟形成的盲目性,并且可以提高学习者Agent之间的交互效率,从而使得我们基于Agent同学联盟的协作学习系统可以实现学习者Agent之间的有效合作,弥补了现有协作学习系统的不足.     

Agent技术及其在网络协作学习中的应用研究

应用Agent的智能特征,把Agent思想嵌入到网络协作学习系统中;分析了网上协作学习环境、协作学习区、学习环境的运作方式以及其特点。引入智能Agent的网络协作学习环境,实现了个性化教学,能充分调动学习者的主动性。     

基于多Agent的分布式资源检索系统的设计

Agent是具有适应环境的软件实体,其能够通过感知自身和环境中的信息,自主采取行动实现一系列预先设定的目标或任务.多A-genl系统是由多个自主的Agent组成,每个Agent都有自己的职责,并与其它Agent通信获取信息,互相协作完成整个问题求解.     

基于多代理的个性化推荐学习系统

针对现有学习系统存在信息过载、缺乏个性化服务能力、不能提供检索服务的问题,提出基于多代理构建个性化推荐学习系统。该系统利用JADE设计学习者Agent与推荐Agent,采用Lucene设计带有个性化能力的搜索引擎支持推荐,并融合3种推荐方法发挥多Agent间协商与协作的优势。实验结果表明,相比单一推荐方法,该系统具有较好的推荐效果和效率。     

基于知识空间的多级感知空间处理技术研究

在网络协同化学习环境中,由于学习环境比较复杂,解决学习者在学习过程中的"孤独感"问题以提高网络环境的社会性,对于学习者顺利完成学习任务来说显得非常重要.在CSCW的感知处理技术的基础上,基于知识空间理论和知识域间关系模型,利用学习者的兴趣模型和能力模型,提出了多学习内容、多学习目标、多学习等级的动态多级感知空间模型,在学习者的学习过程中,通过灵活的感知处理技术和感知敏感度调节,为学习者感知到其他学习者的信息和行为,为寻求或是提供其他学习者的交流和指导,共同完成学习任务提供了有效的途径.     

基于Agent的智能决策支持系统开发与应用

针对传统决策支持系统的局限性,该文提出了一个基于Agent的智能决策支持系统开发方案。利用界面Agent、信息Agent、移动Agent、协作Agent来实现系统的智能部件,多Agent通过协作Agent信息路由器进行协作和交互,共同完成决策支持任务。并将该模型应用于草业信息管理决策支持系统中,系统运行结果证明了模型的有效性和科学性。     

Multi-agent系统中认知协作研究

将问题分解形成的子问题间的关联性作为Multi-agent系统中Agent协作关系的特征性描述,并在此基础上依据粗糙集理论、马尔可夫决策过程和信息认知理论,分析Multi agent系统中的协作关系,以及Agent的认知协作过程。     

基于改进合同网协议的多Agent协作模型

合同网是用于分布式问题求解环境下各Agent进行通信和协作的一种协议,各个Agent内部的知识、能力和策略在问题求解过程中总是动态变化的。为了能够得到实用性强且易于实现的协作模型,分析了传统经典合同网的缺点并进行了改进,利用熟人模型对投标者进行了合理的筛选。采用Agent的主动感知特性,改进了任务Agent接受任务的被动性。在投标过程中引人信任度、感知系数和活跃度等智能参数,防止了投标者在投标过程中的自私性,平衡了各个合同承担者的负载。通过实验证明,改进的合同网降低了网络通信量,提高了多Agent系统协作的效率。     

基于改进合同网协议的多Agent协作模型

合同网是用于分布式问题求解环境下各Agent进行通信和协作的一种协议,各个Agent内部的知识、能力和策略在问题求解过程中总是动态变化的。为了能够得到实用性强且易于实现的协作模型,分析了传统经典合同网的缺点并进行了改进,利用熟人模型对投标者进行了合理的筛选。采用Agent的主动感知特性,改进了任务Agent接受任务的被动性。在投标过程中引人信任度、感知系数和活跃度等智能参数,防止了投标者在投标过程中的自私性,平衡了各个合同承担者的负载。通过实验证明,改进的合同网降低了网络通信量,提高了多Agent系统协作的效率。     

基于多代理的网络协作学习模型研究

多Agent技术在远程教育中的应用成为目前人工智能领域的研究热点。CSCL系统普遍存在智能化不足,交互性差的问题,据此结合Web技术和多Agent技术提出了一个新的基于多Agent的网络协作学习模型,给出了模型的体系结构,并对模型中几个主要的Agent的内部功能结构和同步协作过程进行了描述。     

Enhancing non-task sociability of asynchronous CSCL environments

While from a technological perspective Computer Supported Collaborative Learning (CSCL) systems have been improved considerably, previous studies have shown that the social aspect of the CSCL is often neglected or assumed to happen automatically by simply creating such virtual learning environments. By distinguishing between students’ non-task social interactions from on-task interactions, and through a content analysis, this paper demonstrates that non-task interactions do occur frequently in CSCL environments. Furthermore, by conducting a self-reported survey, the present study operationalizes non-task sociability of CSCL environments and determines factors that affect them. The findings from the survey revealed that the sense of cohesion and awareness about others significantly impact the non-task sociability of CSCL. Furthermore, the study demonstrates that the perception of self-representation and perception of compatibility affect the sense of cohesion and awareness about others and indirectly contribute to the perceived non-pedagogical sociability of the environment. The findings of this paper can be used in future research for investigating the relationship between the non-task sociability of CSCL and other CSCL factors. The study also provides the CSCL lecturers and facilitators with a conceptual model by which sociability can be explicitly addressed in their course planning and delivery processes. And finally, this study develops and validates an instrument that guides required changes in current CSCL systems to improve the non-task social functionality of the environment.     

解析CSCL在教学中的应用

通过对计算机支持的协同学习（CSCL）相关的理论与计算机应用结合在CSCL系统/平台的设计中进行了分析,提出了基于网络的计算机支持的协同学习系统中应该提高计算机的应用,以及在CSCL系统/平台设计中的一些建议。     

Group awareness in CSCL environments

Group awareness is an emerging topic in research on computer-supported collaborative learning (CSCL). It covers the knowledge and perception of behavioral, cognitive, and social context information on a group or its members. A central aim of CSCL-related research on group awareness is the development of tools that implicitly guide learners’ behavior, communication, and reflection by the presentation of information on a learning partner or a group. This special issue comprises six empirical contributions and a concluding discussion that present a broad spectrum of current research on this topic including behavioral, cognitive and social group awareness. An introductory outline of how group awareness is formed, processed and translated in action along the contributions is intended to integrate the diverse research activities on group awareness in CSCL environments.     

Knowledge awareness in CSCL: A psychological perspective

In this paper, a specific group awareness approach for CSCL settings, namely knowledge awareness, is presented. We classify knowledge awareness in relation to already well-established concepts like shared mental models, common ground, and transactive memory system in order to provide a comprehensive definition of this approach. The functionality of knowledge awareness tools aiming at fostering knowledge awareness is conceptualized in a cyclical model. Three application scenarios are presented to illustrate how knowledge awareness tools work in three different tasks. All these knowledge awareness tools have been found to be effective, that is all tools could foster knowledge awareness and led to increased learning performance.     

基于SIP协议的CSCL系统的设计与实现

介绍了会话呼叫信令控制协议SIP.针对当前CSCL系统在提供"个性化"服务与支持移动性等方面灵活度不够的问题,综合运用CSCL的原理、SIP协议、数据库技术及协同处理技术,设计并实现了一种基于SIP协议的CSCL系统,着重讨论了该系统的体系结构、SIP服务器、SIP终端及CSCL系统协同服务的实现方案,并给出了CSCL学习者间的会话连接实例,最后从CSCL系统在农村推广应用的角度提出的下一步改进的方向.     

Group awareness and regulation in computer-supported collaborative learning

Group awareness is of critical relevance for collaborative learning and interaction and is thus often referred to in CSCL research. However, the concept is only vaguely defined as some kind of understanding or perception of characteristics of learning partners or the collaborating group. Most CSCL research activities concerned with group awareness aim at modifying learners' awareness using so-called group awareness tools. However, there are much less attempts to measure group awareness and to conceptualize its formation. Thus, building on existing group awareness research, this article derives a conceptualization with six defining aspects of group awareness: (1) group awareness is cognitive, (2) group awareness is conscious, (3) group awareness is current, (4) group awareness is individual, (5) group awareness is social, and (6) group awareness is perceived as valid. Additionally, while it is often assumed that group awareness builds on self-regulatory skills, its role in regulating behavior and cognition within a social context is seldom explored. Thus, this article aims at defining and analyzing the concept of group awareness, specifying its relation to regulatory processes, and sketching possible research paths whilst building on, complementing, and informing tool-driven research.

     

一个虚拟教室的协同感知技术

协同感知技术近来成为CSCW和CSCL的一个新的研究领域，它足一个先进的人机接口技术。该文介绍了一个在虚拟教室中实现的协同感知代理的框架结构以及这个协同感知代理的工作过程，在该协同感知过程中实现了对感知信息的灵活过滤，提高了协同感知的效率。     

Supporting controversial CSCL discussions with augmented group awareness tools

This paper describes the development of augmented group awareness tools that take mutual user ratings of their online discussion contributions as input, aggregate these data, and visually feed these data back to the members in real time, thereby informing participants about how the group as a whole perceives their contributions. A specific group awareness tool was experimentally tested in a CSCL scenario using online controversies about a physics domain. The learning material was distributed across group members to create a situation where an individual minority member with a scientifically correct viewpoint faces a majority favoring a plausible, but incorrect viewpoint. It was hypothesized that in unsupported CSCL groups an incorrect majority would dominate a correct minority, whereas in groups that were supported by an augmented group awareness tool minority influence could be strengthened by making minority contributions salient. The paper reports results in support of this hypothesis, and discusses the mechanisms leading to the benefits of group awareness tools for collaborative learning.     

Design patterns for monitoring and evaluating CSCL processes

Both quantitative and qualitative methods are being increasingly used to investigate the learning dynamics that take place within CSCL environments. Since such practices are a crucial aspect of the CSCL field, Design Patterns (DPs) can be used for capitalizing on experience and sharing know-how among practitioners. This paper describes three DP instances that have been developed and fine tuned by a community of practice consisting of researchers, instructional designers and tutors with the aim of supporting monitoring and evaluation of CSCL interactions. The DP solutions are based on a set of indicators, some of quantitative and some of qualitative nature, as well as on the methods to gauge these indicators, starting from data tracked by the e-learning system. The process of development of these DPs is described and examples of use are reported and discussed in order to advance the instructional design field and inform the development of CSCL systems. The proposed DPs belong to a Language, aimed at describing tracking problems in different types of e-learning systems and at capturing in their solutions the know-how developed by communities of experts in the different fields.