The discovery of new drugs is a systematic project with long cycle and low success rate. The traditional drug discovery is to find effective targets related to diseases, and then to screen and design effective small molecules (or large molecules) using various technologies. Artificial intelligence technology has made significant progress in the medical field. In the field of new drug discovery, artificial intelligence technology can integrate a large number of high-dimensional phenotype data, including high-throughput omics data, network pharmacology data and images, so as to effectively screen therapeutic targets and design drugs, saving the costs of drug discovery and shortening the time required for drug discovery. In this article, we explored the drug discovery process driven by new generation of artificial intelligence technology, hoping to provide a reference for the development of new drugs.