人物相关会议信息抽取系统设计及实现  

Design and Implementation of Person Related Conference Information Extraction System

作　　者：熊蕊 吴晨生[1] 赵桂芬[1] Xiong Rui;Wu Chensheng;Zhao Guifen(Beijing Institute of Science and Technology Information,Beijing 100044)

机构地区：[1]北京市科学技术情报研究所,北京100044

出　　处：《情报杂志》2020年第7期142-150,共9页Journal of Intelligence

基　　金：北京市财政项目“支撑北科智库的应用人工智能和大数据技术的信息快速处理能力建设”(编号:PXM2019_178214_000004)研究成果之一。

摘　　要：[目的/意义]智能化信息抽取工具是情报3.0工作流程中的技术基础。构建一个信息抽取系统智能化地进行情报采集和情报处理,生成研究对象人物相关的会议活动情报信息,从而揭示某些(比如研究热点、政策评价、人物意图等)特征、变化及规律,以满足情报人员的快速情报判读需求,发挥决策支持的功能。[方法/过程]设计并实现了一个人物相关会议信息抽取系统,面向互联网信息智能化抽取特定人物对象相关的会议信息,包括会议名称、会议时间、会议主题和人物观点,最后生成事件列表以及经过可视化处理的事件时间演化图提供给用户。[结果/结论]该文设计实现的信息抽取系统能够快速准确地抽取有价值的情报信息,解决了情报3.0时代信息过载的难题,实现了以智能化工具支撑情报判读与决策。[Purpose/Significance]The intelligent information extraction tool is the technical basis in the intelligence 3.0 workflow.The research aims to construct an information extraction system to intelligently collect intelligence and process intelligence and generate conference activity intelligence information related to the people acting as the research object,so as to reveal certain feature characteristics(such as research hotspots,policy evaluations,character intentions,etc.),changes,and rules.The system can satisfy the needs of intelligence personnel for rapid intelligence interpretation with decision support.[Method/Process]A character-related conference information extraction system is developed.Person-related conference information,including conference name,conference time,conference theme and person’s opinion,can be extracted intelligently from the Internet.Finally,event list and the visualized event time evolution map are provided as the results to the user.[Result/Conclusion]The information extraction system proposed in this paper can extract valuable information quickly and accurately.It solves the problem of information overload in the information age of 3.0,and realizes the intelligence interpretation and decision making with intelligent tools.

关 键 词：情报3.0工作流程 情报判读 会议信息抽取 系统设计及实现 

分 类 号：G350[文化科学—情报学]