基于个性化自适应学习的海量资源安全威胁信息定向识别模型

Directional Identification Model of Massive Resource Security Threat Information Based on Personalized Adaptive Learning

随着互联网资源总量的增长,其传输渠道也在不断拓宽。在此过程中,受到渠道组织多元化的影响,海量资源安全的威胁信息识别准确性与全面性均会出现一定程度的下降,威胁海量资源安全性与应用效果。为解决上述问题,设计基于个性化自适应学习的海量资源安全威胁信息定向识别模型。根据识别序列生成标准,测定威胁信息的个性化学习风格,再通过选择近似学习者的处理方法,完成基于个性化自适应学习的海量资源传输路径分析,分析关键的资源信息,并从中提取必要的文件参量,按照敏感序列标注原则,完善现有的定向分级策略,实现海量资源安全威胁信息定向识别模型的顺利应用。实验结果表明,该模型可将召回率指标控制在既定数值标准之下,能够适当提升威胁信息的识别准确性与全面性,避免了海量资源传输过程信息安全问题的干扰。

With the growth of the total amount of the Internet resources,its transmission channels are also expanding.In this process,affected by the diversification of channel organizations,the accuracy and comprehensiveness of threat information identification affecting the security of massive resources will decline to a certain extent,threatening the security and application effect of massive resources.In order to solve the above problems,a directional identification model of massive resource security threat information based on personalized adaptive learning is designed.According to the identification sequence generation standard,we determine the personalized learning style of threat information,and then complete the mass resource transmission path analysis based on personalized adaptive learning by selecting the processing method similar to learners,analyze the key resource information,extract the necessary document parameters,and improve the existing directional classification strategy according to the principle of sensitive sequence labeling,realize the smooth application of the directional identification model of massive resource security threat information.The experimental results show that the model can control the recall index under the established numerical standard,appropriately improve the accuracy and comprehensiveness of threat information identification,and avoid the interference of information security in the process of massive resource transmission.