Aiming at the deficiencies in production, transportation, storage and marketing informatization and the lack of core artificial intelligent applications in Tarim Oilfield, an innovative development idea of oilfield intelligent analysis assisted decision-making sub-system that deeply integrates big data and artificial intelligence technology is proposed, making use of big data technology and comprehensively collects and accurately analyzes a large amount of data generated in the production process of the oilfield by means of data collection, data cleansing, and data transformation. In the production, transportation, storage and marketing balanced module, it is proposed to use Long Short-Term Memory (LSTM) to process and analyze dynamic data, Random Forest (RF)to build a simulation prediction model, and Genetic Algorithm (GA) to optimize the target results. The online diagnosis module of the oilfield intelligent analysis assisted decision-making subsystem uses a threshold-based anomaly detection self-encoder model to monitor the equipment operation status in real time. The online training module for emergency rescue uses a decision tree to construct a decision support model to provide intelligent decision support. The oilfield intelligent analysis assisted decision-making subsystem based on big data and artificial intelligence overcomes the limitations of traditional oilfield production management, improves the overall operational efficiency and resource utilization efficiency, and provides new ideas and methods for the application of artificial intelligence in the development of the entire oilfield industry.