The goal of smart tourism construction is to improve tourism service and tourist experience by using the latest information technologies. To enable tourists to dialog with the electronic explanation system of scenic spots by natural voice, an intelligent tourism explanation system based on natural language processing and ontology knowledge retrieval was proposed in this study. Firstly, the physical view and logical view of the system architecture was designed. Secondly, the key technologies of text vector, named entity recognition, dialogue policy management and tourism knowledge retrieval were analyzed. Finally, a prototype was developed, verifying the feasibility of the system.