With the rapid development of the Internet and artificial intelligence technology, massive text data is growing exponentially, and the news industry is generating massive text data every moment. Most of the existing knowledge graphs focus on tourism, healthcare, finance and other fields, while there are relatively few in the news field, which is not well constructed. Aiming at the above problems, this paper firstly devotes to the construction of ontology library in news domain, and precisely defines 8 types of entities and 9 types of relations, which lays a solid foundation for the construction of news knowledge graph. Subsequently, with the help of web crawler technology, we extensively collected news text and image data, and carried out rigorous knowledge cleaning, extraction and fusion processing on these data to ensure the accuracy and completeness of the data. Finally, with the help of Neo4j graph database, the effective storage of news knowledge is realised, and the news domain knowledge graph is successfully constructed. It provides new ideas and means for information mining and utilisation in the news industry, and also provides rich, high-quality data support for downstream applications, which is expected to promote the intelligent development of the news field.