Based on context-aware theory, this paper proposes an online anomaly detection and warning method for multi-angle transmission grid construction business processes. The business process model for transmission grid construction is constructed using a Petri net, and the data is preprocessed. The context in the business event log is initially refined, and the data in the model training is labeled using the supervised learning method. The sliding window Euclidean distance model is applied to build an anomaly detection model for the transmission grid construction business process, and the data is filtered by mean value aggregation to obtain the threshold value for anomaly monitoring and to realize anomaly detection and warning. This paper’s anomaly detection and early warning model is applied to carry out transmission grid construction business flow optimization practice in the G Power Supply Bureau of Yunnan Province, China. Since the optimization in June, the timeliness and accuracy of material matching of G Power Supply Bureau have been stable at more than 90%, and the execution rate of the operation plan and on-time completion rate of billing have also been maintained at a high level of about 95%. The number of cancellations and adjustments to transmission network construction operations has decreased from 20% to 30% to less than 7%, and the overall satisfaction score of transmission network construction business processes has reached 4.15.