With the development of Internet technology, the phenomenon of text information overload occurs frequently, and automatic text summarization technology has become a research hotspot. However, in real situations, there is no enough data accumulation in many fields, and lack of high-quality labeled summarization data. Therefore, the paper realizes the generation of Chinese text summarization based on LSTM and attention mechanism, by utilizing LSTM to capture semantic features and combining the attention mechanism based on contextual semantics. Experiments show that the text summarization generation model we constructed has an obvious improvement in F1 value compared with other models. It can complete the task of text summarization generation and solve the problem of low-quality text summarization in some fields.