A chatting robot system based on a fuzzy neural network comprises a speech acquisition terminal, a characteristic extracting module, a matching searching module, a fuzzy neural network analysis module, a speech postprocessing module and a speech broadcasting module, wherein the characteristic extracting module is connected with the speech acquisition terminal, the matching searching module is provided with a sound model data base and connected with the characteristic extracting module, the fuzzy neural network analysis module is connected with the matching searching module, the speech broadcasting module is connected with the matching searching module, the speech broadcasting module is connected with the speech postprocessing module, and the fuzzy neural network analysis module is provided with a fuzzy neural network training data base and a knowledge data base. According to the chatting robot system based on the fuzzy neural network and a chatting method, the technologies of fuzzy recognition, pattern matching searching, a artificial neural network and the like are utilized, the fuzzy reasoning process of thinking and speeches of the human brain is simulated, a reply can be made according to contexts and emotion characteristics, and the system has the self-learning ability in different scenarios.