Aiming at the problem of Influence Maximization （IM） in heterogeneous information networks， an Influence Maximization algorithm （DAGIM） based on Directed Acyclic Graph （DAG） was proposed. Firstly， the influence of nodes was measured based on the DAG structure， and then the marginal gain strategy was used to select the nodes with the most influence. The DAG structure has strong expressive power， which not only describes the explicit relationship between different types of nodes， but also depicts the implicit relationship between nodes， and more completely retains the heterogeneous information of the network. Experimental results on three real datasets verify that the performance of the proposed DAGIM algorithm is better than those of Degree， PageRank， Local Directed Acyclic Graph （LDAG） and Meta-Path-based Information Entropy （MPIE） algorithms.

Hyperlink prediction aims to utilize inherent properties of observed network to reproduce the missing links in the network. Existing hyperlink prediction algorithms often make predictions based on entire network， and some link types with insufficient training samples data may be missed， resulting in imcomplete link types to be detected. To address this problem， a clustering-based hyperlink prediction algorithm named C-CMM was proposed. Firstly， the dataset was divided into clusters， and then the model was constructed for each cluster to perform hyperlink prediction. The proposed algorithm can make full use of the information contained in the observation samples of each cluster， and widen the coverage range of the prediction results. Experimental results on three real-world datasets show that the proposed algorithm outperforms a great number of state-of-the-art link prediction algorithms in prediction accuracy and efficiency， and has the prediction coverage more comprehensive.