一种基于飞行任务上下文感知的异常行为检测方法及系统
By parsing the UAV mission protocol to generate dynamic tags, and combining normalized mutual information and random forest models, the adaptability and computational efficiency issues of UAV abnormal behavior detection are solved, achieving high-precision abnormal behavior recognition and camouflage attack detection.
CN121980408BActive Publication Date: 2026-07-17WEBRAY TECH BEIJING CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- WEBRAY TECH BEIJING CO LTD
- Filing Date
- 2026-01-26
- Publication Date
- 2026-07-17
Smart Images
Figure CN121980408B_ABST
Abstract
本发明提供了一种基于飞行任务上下文感知的异常行为检测方法及系统，应用于数据处理技术领域。本申请对无人机飞行动态数据、任务协议数据进行处理，通过解析任务协议中的MASSION_ITEM字段获取任务类型，生成动态标签；将GPS定位数据结合归一化互信息与随机森林重要性评分筛选任务敏感特征，生成任务相关特征子集；基于随机森林模型对任务相关特征子集进行处理，为每个任务类型训练专属分类模型，生成各类任务专属分类模型；基于各类任务专属分类模型对无人机实时飞行状态数据进行预测，得到各任务类型的概率分布，根据设定阈值进行判断，生成无人机异常行为判定结果。
Need to check novelty before this filing date? Find Prior Art