基于TextRank的空管特情案例特征提取技术  

Feature Extraction Technology of Air Traffic Control Case Based on TextRank

作　　者：彭珂 王华伟[1] 倪晓梅 刘伟伟 PENG Ke;WANG Hua-wei;NI Xiao-mei;LIU Wei-wei(Nanjing University of Aeronautics and Astronautics,Nanjing 211000,China;Nanjing Vocational University of Industry Technology,Nanjing 210000,China)

机构地区：[1]南京航空航天大学,江苏南京211000 [2]南京工业职业技术大学,江苏南京210000

出　　处：《航空计算技术》2023年第4期56-60,共5页Aeronautical Computing Technique

基　　金：国家自然科学基金项目资助(72271123)。

摘　　要：针对目前空管特情处置过程中案例记录利用不足的问题,提出了空管特情案例利用框架,并重点研究了其中的案例特征提取方法。基于TextRank算法提出了融合空管特情领域知识与数据分析的特情案例特征提取算法(Special Situation Case TextRank,SSC TextRank)。所提方法利用空管特情领域知识构建领域词典,以提升分词效果,依据风险知识及文本数据分析结果,同时结合层次分析法赋权原理对文本中的特征词进行赋权,以优化各词的初始重要度以及词语重要度权重的计算方法。利用某地区空管局提供的2000年—2019年特情案例验证算法的有效性。结果表明:模型较传统自然语言处理中的关键词提取算法准确率提高了约40%,体现了所提方法在特情案例特征提取方面的有效性和优越性。Aiming at the problem of insufficient use of case records in the process of air traffic control special situation disposal,this paper puts forward the framework of case utilization of air traffic control special situation,and focuses on the method of case feature extraction.Based on TextRank algorithm,this paper puts forward a Special Situation Case TextRank(SSC TextRank)feature extraction algorithm that integrates air traffic control special situation do main knowledge and data analysis.The proposed method firstly utilizes the domain knowledge of air traffic control special situation to build a domain dictionary to improve the effect of word segmentation.Secondly,according to risk knowledge and the results of text data analysis,the feature words in the text are weighted according to the weight principle of analytic hierarchy process,so as to optimize the initial importance of each word and the calculation method of word importance weight.Finally,the validity of the algorithm is verified by using the special case records from 2000 to 2019 provided by a local air traffic administration.The results show that the accuracy of the proposed model is about 40%higher than that of the traditional keyword extraction algorithm in natural language processing,which demonstrates the effectiveness and superiority of the proposed method in feature extraction of special cases.

关 键 词：空管特情案例 案例利用 TextRank算法 特征提取 领域知识 

分 类 号：V35[航空宇航科学与技术—人机与环境工程]