Abstract: In order to improve the intelligent regulation performance of agricultural parks, a retrieval method of regulation strategy of energy supply and consumption system in agricultural parks based on knowledge graph is proposed. Firstly, a structured data feature extraction system for the energy supply and consumption system of agricultural parks is constructed, and a data feature label library is formed through interval processing. Secondly, the deep learning technology is used to realize the recognition of named entities and their relationships, and the knowledge graph is constructed with the help of Neo4 j graph database. Then, an optimization strategy retrieval method of energy supply and consumption system in agricultural parks based on knowledge graph is proposed, so as to retrieve the corresponding control strategy layer by layer according to the data characteristics of the operation scene to be optimized. The simulation results show that this method can effectively improve the efficiency of strategy generation compared with the traditional modeling and optimization algorithm, and visualize the multi-dimensional characteristics of the operation scene and its strategy matching path, so as to provide support for the intelligent decision-making of the energy supply and consumption system of agricultural parks.