Abstract: The traditional data integration method of power information system operation and maintenance takes a long time, and the data coverage rate is low in the integration process. Therefore, a data integration method of power information system operation and maintenance based on artificial intelligence is designed. A unified data integration standard and data classification principle for operation and maintenance of power information system are given, different data types according to the relationship between data is defined, the operation and maintenance data of power information system is classified and processed, and the inconsistent and repeated data after classification is eliminated to reduce the interference of invalid data and improve the efficiency of data integration. Then a unified coding standard is established, the classified data is checked and coded, whether the classified data set matches the actual data is determined. Based on the offline data, deep learning algorithm is used to integrate the operation and maintenance data of power information system to reduce the occupancy of resources in the system and improve the coverage of effective data. Experiments show that the data integration method of this design takes less time than the traditional method, and the data coverage is high, which proves that the design method is feasible and has practical application significance.