This article proposes an intelligent data directory construction scheme aimed at supporting the design of ultra-high voltage converter stations. The scheme utilizes visual techniques such as knowledge graphs to analyze large-scale data in the power industry and establish a data classification and grading standard. Specifically, the scheme selectively identifies key or core data for association analysis to reduce data processing scale and improve the speed of the directory system. After determining the results of data classification and grading, the scheme employs machine learning algorithms to perform semantic analysis and reasoning on important/core data, providing recommended associated information. Additionally, the scheme selectively performs association analysis on data based on its sensitivity and importance level to reduce the impact of data analysis on system performance and ensure efficient operation. The intelligent data directory also automatically retrieves relevant data based on factors such as association, timeliness, and source, and provides recommended information resources to workers, thereby improving data availability and effectively reducing work pressure.