Inpatient medical records which contain clinical narrative information generated from medical procedures have rich content and unlimited expression capabilities. In this paper, we proposed a novel method to assist health practitioners to write narrative clinical texts through a more efficient and safer manner. The core technologies supporting this work are named entity recognition (NER) and similarity computation: the CRF-based NER in this work has a good performance whose F-score has reached 89.23%, and the LDA model and similarity test has reached a precision of 71.28%. After these fundamental work, we designed and developed an intelligent writing assistant module: at sentence level, we used a conditional random field (CRF) method to train a NER model. When doctors type in an entity, several input candidates will pop up for selection; at paragraph level, we used a Gibbs-LDA++ tool and named entities to characterize the topics and key entities of existing records. When doctors create a new clinical text, the patient’s structured data will be used as input to match similar paragraphs. As doctors keep typing in, the matching paragraphs also might change dynamically according to the input content.