摘要：[Objective]Real-time monitoring of co. ruminant behavior is of paramount importance for promptly obtaining relevant information about co. health and predicting co. ***,various strategies have been proposed for monitoring co. ruminant behavior,including video surveillance,sound reco.nition,and sensor monitoring ***‐ever,the application of edge device gives rise to the issue of inadequate real-time *** reduce the volume of data transmission and cloud co.puting workload while achieving real-time monitoring of dairy co. rumination behavior,a real-time monitoring method was proposed for co. ruminant behavior based on edge co.puting.[Methods]Autono‐mously designed edge devices were utilized to co.lect and process six-axis acceleration signals from co.s in *** on these six-axis data,two distinct strategies,federated edge intelligence and split edge intelligence,were investigat‐ed for the real-time reco.nition of co. ruminant *** on the real-time reco.nition method for co. ruminant behavior leveraging federated edge intelligence,the CA-MobileNet v3 network was proposed by enhancing the MobileNet v3 network with a co.laborative attention ***,a federated edge intelligence model was designed uti‐lizing the CA-MobileNet v3 network and the FedAvg federated aggregation *** the study on split edge intelli‐gence,a split edge intelligence model named MobileNet-LSTM was designed by integrating the MobileNet v3 network with a fusion co.laborative attention mechanism and the Bi-LSTM network.[Results and Discussions]Through co.para‐tive experiments with MobileNet v3 and MobileNet-LSTM,the federated edge intelligence model based on CA-Mo‐bileNet v3 achieved an average Precision rate,Recall rate,F1-Sco.e,Specificity,and Accuracy of 97.1%,97.9%,97.5%,98.3%,and 98.2%,respectively,yielding the best reco.nition performance.[co.clusions]It is provided a real-time and effective method for monitoring co. rumin