The present disclosure relates to an incremental backup method and system for a CAD engineering data file, and the method includes: chunking historical CAD engineering data based on a sliding window approach, to determine a first data block group; calculating a first hash fingerprint value separately for each data block in the first data block group; chunking, based on the sliding window approach, CAD engineering data to be backed up, to determine a second data block group; calculating a second hash fingerprint value separately for each data block in the second data block group; and determining a backup status of the data block in the second data block group based on the first hash fingerprint value and the second hash fingerprint value. The present disclosure resolves a problem that a long time is occupied when a large-scale engineering CAD data file is saved by applying a full backup.