摘要
为了高效、快速、准确地处理工程论坛问答中未经规范描述的知识应用情境,面向工程论坛中的中文问答记录,提出一种人工干涉少、用户需求敏感性高、情境匹配准确性高的知识应用情境获取方法,进而从自然语言描述的文本中快速获取与用户当前任务关联的知识应用情境并推送相应答案。以CAD技术论坛中的问答为实验素材,对工程师可能产生的知识需求做出预测。实验表明,该方法比现有方法能够更有效地利用中文工程论坛问答这种普遍存在但开发不足的知识资源,快速准确地获取其中匹配用户知识需求的知识应用情境和答案,有助于低成本地建立一套主动式知识推荐系统并提高其工作性能。
To conduct the un-annotated informal Knowledge Application Context （KAC） in forum Question and An- swer （Q＆A） efficiently, rapidly and precisely, a KAC elieitation method which had higher sensitivity and precision in matching KAC with less human intervention was proposed from natural-language-describing forum Q^A texts and recommend corresponding answers related to users＇ current missions. KAC retrieving experiment was carried out in CAD technical forum, and the correct prediction of engineer＇s knowledge needs was conducted. The result in- dicated that the proposed method significantly outperformed than the currents methods in utilizing the Q^As in Chi- nese engineering forum, which was helpful to build active knowledge recommend systems and improve their per- formance.
出处
《计算机集成制造系统》
EI
CSCD
北大核心
2016年第5期1187-1196,共10页
Computer Integrated Manufacturing Systems
基金
国家自然科学基金资助项目(70971085
71271133)
上海市教委科研创新重点资助项目(13ZZ012)~~
关键词
知识应用情境
论坛问答
文本挖掘
知识推荐
knowledge application context
{orum question and answer
text mining
knowledge recommendation
