基于改进的TextRank算法的计算机辅助定密研究

RESEARCH ON COMPUTER-AIDED SECRET-LEVEL CLASSIFICATION BASED ON IMPROVED TEXTRANK ALGORITHM

针对传统定密方式定密不严谨、定密尺度难以把握、经验难以积累等问题,提出基于改进的TextRank算法的计算机辅助定密方法,该方法通过定密规则的词性特点,将句向量分解为名词向量和非名词向量,构造基于词性的句向量,利用改进的TextRank算法对文档语句排序,获取在定密细则影响下的关键语句权重,计算文档密级分数,判断文档密级。实验结果表明,该方法比目前传统定密方式准确率有所提高。

Aimed at the problems that the traditional document secret-level classification is not rigorous,its classification scale is difficult to grasp,and the experience is difficult to accumulate,an algorithm of computer-aided secret-level classification based on improved TextRank algorithm is proposed.According to the part-of-speech characteristics of the classification,this method decomposed the sentence vectors into noun vectors and non-noun vectors,and constructed the part-of-speech based sentence vectors.The improved TextRank algorithm was used to sort the document sentences,obtain the key sentence weights under the influence of this secret rules,calculate the document secret score,and judge the document secret-level.Experimental results show that the accuracy of this algorithm is higher than the current traditional secret-level classification method.