一种针对对抗性行为的同轨迹团伙识别方法及装置

By reconstructing trajectory sequences, calculating trajectory confidence and adversarial index, adjusting edge weights, generating weighted time series graphs, and identifying groups with the same trajectory, the problem of misjudgment and missed detection caused by adversarial behavior in existing technologies is solved, and the recognition effect and robustness are improved.

CN121692068BActive Publication Date: 2026-07-17FUJIAN FUNO MOBILE COMM TECH CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
FUJIAN FUNO MOBILE COMM TECH CO LTD
Filing Date
2025-11-18
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

When existing technologies take countermeasures against targets, methods based on trajectory similarity or call detail record (CDR) community detection are prone to misjudgment or missed detection, making it difficult to effectively identify groups with the same trajectory.

Method used

By reconstructing trajectory sequences, calculating trajectory confidence and adversarial index, adjusting edge weights, generating a weighted time series graph, identifying the overall confidence of gangs, outputting a list of suspected gangs, and combining multiple adversarial behavior detections, generating a clear adversarial evidence summary.

Benefits of technology

It improves the identification of gangs with the same trajectory in adversarial behavior scenarios, reduces the negative impact of base station sparsity or signaling noise, improves the robustness of identification, and generates evidence summaries that are easy to verify.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121692068B_ABST
    Figure CN121692068B_ABST
Patent Text Reader

Abstract

本发明提供的一种针对对抗性行为的同轨迹团伙识别方法及装置，其方法包括：根据涉案号码的通信数据重建轨迹序列，并计算得到轨迹置信度；根据通信数据和轨迹序列对多种对抗性行为进行识别，生成对抗性指数；根据轨迹置信度得到初始权重，根据对抗性指数进行边权调整，得到加权时序图；基于加权时序图得到计算每一个涉案号码的团伙综合置信度，输出疑似团伙名单。本发明通过通信数据和轨迹序列对多种对抗性行为进行识别，生成对抗性指数，并根据对抗性指数进行边权调整，从而基于调整边权后的加权时序图来识别团伙，从而在对抗性行为场景下提升同轨迹团伙的识别效果。
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • User attribute and social network detection system based on space-time locus

    CN106600052A

  • Operator trajectory data-based accompanying mode matching method

    CN110991525A

  • Advertisement recommendation method and system fused with user dynamic behavior modeling

    CN120198179A

  • Method for detecting illegal behaviors after examination based on cross-mirror tracking and identity authentication

    CN120877378A