In Opportunistic Network based mobile data diversion algorithms, the need for multi-hop transmission makes the selection of the next hop node critical. The traditional Prophet algorithm calculates the encounter delivery probability of a node based on historical encounter information as a forwarding condition. However, algorithms for data diversion are more concerned with the issue of nodes’ propagation influence in the network. Therefore, in this paper, we propose a metric to measure the dynamic influence of a node (sir) and use the CNN-BiLSTM-Attention model to predict the sir value of a node during the current time period in the route. After that, a data diversion algorithm based on deep learning prediction of node influence is proposed in combination with encounter delivery probability. The experimental results show that the NS-Prophet algorithm performs well in terms of performance metrics in opportunistic networks, and the triage efficiency in cellular networks is also improved.