Abstract: Named entity recognition refers to the task of extracting proper nouns or specific named entities from text. As a key step of information extraction to transform unstructured data into structured data, it has been widely applied in machine translation, emotion analysis, information retrieval and other fields, which has been a hot issue in natural language processing. This paper makes a detailed analysis of the existing named entity recognition technology methods, focuses on the deep learning based on named entity recognition method and its implementation process. Furthermore, it analyzes the advantages and disadvantages of the representative typical algorithms, meanwhile, discussing the application prospect of named entity recognition in power system.