一种多维感知系统的多源数据采集方法及系统

By calculating the consistency and similarity of environmental feature vectors in a multidimensional perception system, dividing the scene into time periods and iteratively updating the weights, the problem of inaccurate identification of abnormal data in the multidimensional perception system is solved, thus improving the accuracy and reliability of the data.

CN121723196BActive Publication Date: 2026-07-17SHAANXI ZHONGKE LIXING INTELLIGENT TECHNOLOGY CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHAANXI ZHONGKE LIXING INTELLIGENT TECHNOLOGY CO LTD
Filing Date
2025-12-23
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing technologies in multidimensional sensing systems neglect the correlation between multiple sensing dimensions, leading to inaccurate identification of abnormal data and the accidental deletion of valid data, which affects data integrity and the system's understanding capabilities.

Method used

By calculating the single-environment consistency and perceptual similarity of the environmental feature vector, combining the initial weights to divide the scene time period, and performing clustering by iteratively updating the target sensing weights, the system finally detects and removes abnormal data based on the reference scene time period.

Benefits of technology

It improves the accuracy and reliability of data in multidimensional perception systems, ensures that key information is not lost, and enhances the system's ability to understand complex environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121723196B_ABST
    Figure CN121723196B_ABST
Patent Text Reader

Abstract

本发明涉及数据处理技术领域,具体涉及一种多维感知系统的多源数据采集方法及系统,方法包括:基于来自多维感知系统的至少两种传感数据提取对应的环境特征向量得到环境感知相似度;基于环境感知相似度划分场景时段,并对场景时段进行初次聚类;计算两组场景时段对之间的环境匹配相似度,进而获取目标感应权重并迭代更新环境感知相似度,重新划分场景时段并再次聚类,直至场景时段以及聚类结果稳定,将与当前时段同属一类的场景时段确定为参考场景时段;以参考场景时段数据为基准,通过预设异常检测算法分析当前时段数据,完成异常数据的检测与去除。本发明将筛选出的参考场景时段作为基准,清洗当前时段异常数据,从而显著提升数据可靠性。
Need to check novelty before this filing date? Find Prior Art