College student behavior abnormity early warning method and system based on multi-source data fusion

By using a multi-source data fusion method, visual, audio, and semantic features are collected and processed in real time. Anomaly coefficients are calculated by combining multi-source data, which solves the problems of environmental interference and low recognition accuracy in traditional monitoring, and realizes efficient identification and real-time early warning of abnormal behavior in universities.

CN122332841APending Publication Date: 2026-07-03ZHEJIANG GUGEL INTELLIGENT TECHNOLOGY CO LTD
1 Cites 1 Cited by

Patent Information

Application Number
CN202610800635.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-06-04
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

Traditional surveillance videos are easily affected by external environmental factors in abnormal behavior identification, the model recognition is not robust, and image, voice and semantic features are difficult to extract stably, resulting in low accuracy and efficiency in personnel identification.

Method used

A multi-source data fusion-based approach is adopted to collect video streams of the target area in real time, extract visual tensors, audio feature sequences and semantic vectors, calculate anomaly coefficients for anomaly warning through multimodal feature alignment and fusion, and combine multi-source data such as access control, classroom attendance, campus consumption and library borrowing data for anomaly determination.

Benefits of technology

It improves the robustness of recognition and the real-time performance of early warning in complex monitoring scenarios, reduces detection latency and computational redundancy, avoids the limitations of audio noise interference and single visual modality, and achieves preliminary screening and efficient identification of potential risks.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a college student behavior abnormity early warning method and system based on multi-source data fusion, and relates to the technical field of image processing. The method comprises the following steps: acquiring video streams of people in a target area in real time, performing classification feature extraction on the video streams to obtain behavior features, obtaining a determined list according to the behavior features, acquiring multi-source data, calculating according to the multi-source data to obtain an abnormal coefficient, and if the abnormal coefficient is greater than a threshold value, judging that the target people are abnormal behavior people. Performing abnormity early warning according to the behavior characteristics corresponding to the abnormal behavior personnel; an abnormal coefficient is calculated through multi-source data fusion to realize hidden risk preposed preliminary screening, detection delay and calculation redundancy brought by traditional monitoring whole-process analysis are reduced, video stream real-time acquisition and cloud behavior feature extraction are started for high-risk personnel, audio noise interference and limitation of a single visual mode are avoided, and the real-time monitoring of the high-risk personnel is realized. And the recognition robustness and the early warning real-time performance in a complex monitoring scene are improved.
Need to check novelty before this filing date? Find Prior Art