Abstract: A method is provided for data processing based on a multi-layer perceptrons (MLP) architecture. The method comprises determining a plurality of tokens for a piece of data, generating an amplitude and a phase for each of the plurality of tokens, optimizing the plurality of tokens by mixing the plurality of tokens based on the amplitudes and the phases, and determining one or more features included in the piece of data based on the plurality of optimized tokens. Each token includes information associated with a segment of the piece of data.

Abstract: 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.