The analysis process of the classical Dendritic Cell Algorithm (DCA) is performed offline, which has constrained its application in the area of anomaly detection. In order to continuously detect abnormal behaviors as soon as they occur, a real-time analysis algorithm is proposed, when an antigen has been presented by sufficient dendritic cells, it will be immediately output and assessed, thus the purpose of real-time or near-to real-time analysis can be achieved. Sufficient assessments will reduce the influence of the errors, and the antigen and signal pool of temporal correlation will eliminate the mutual interference of the antigens and signals, which are far apart. The results of the experiments show that the realtime analysis algorithm proposed has the considerable detection accuracy.