摘要
会议是人们日常生活中不可缺少的重要活动,是解决问题、交换信息、共享和创造知识的重要途径,因此智能会议系统是当前学术界和产业界研究的热点之一。但当前的智能会议系统主要集中于物理交互的识别与可视化研究上,对会议中群体语义交互的研究相对较少。群体语义交互是指参会人员针对当前主题所做出的具备语义的交互活动。采用朴素贝叶斯模型,通过对会话中的头部动作、关注度、语气、说话时间长度、交互时机、上次会话角色类型和会话关键词等7个特征属性进行处理,设计并实现了一种会议中群体交互语义的获取方法。实验表明,利用该算法,群体交互语义的识别准确率可以达到80.1%,该算法具有一定的有效性。
Meeting is an important and vital event in our daily life to solve questions,exchange information,share and create knowledge,so smart meeting system is one of the research hotspots in academia and industry.Current smart meeting systems mainly research on recognition and visualization of physical interaction,and less on human semantic interaction in meetings.Human semantic interaction is interaction activities with semantics which is done by participants with regard to current topic.We designed and implemented a method to capture human interaction semantics in meetings with Nave Bayes model via dealing with contributes in session,including head gesture,attention from others,speech tone,speaking time,interaction occasion,type of previous interaction and Key words.Experiments show that the recognition accuracy rate of human interaction semantics can be up to 80.1% using this method,which is effective in some degree.
出处
《计算机科学》
CSCD
北大核心
2011年第10期240-242,258,共4页
Computer Science
基金
国家自然科学基金(60903125)
国家863高技术研究发展计划基金项目(2009AA011903)
教育部"新世纪优秀人才支持计划"(NCET-09-0079)
陕西省自然科学基础研究计划项目(2010JM8033)资助
关键词
会议
朴素贝叶斯
群体交互语义
Meeting
Naive bayes
Human interaction semantics