Vehicle Data Asset Recognition Based on Pattern Matching

Existing data asset identification schemes predomi-nantly rely on manual categorization methods, which are often associated with high costs and low accuracy. Consequently, there is an urgent need for more intelligent and automated solutions to enhance the efficiency and precision of data asset identification. To address this challenge, this paper proposes a pattern-matching-based vehicle data asset identification scheme, which leverages a pre-trained model to automatically generate asset labels for data fields, thereby enabling more efficient classification and identification of vehicle data assets. This model scheme generates corresponding classification prediction results based on the sequence of each input data item in the tabular data and assigns appropriate asset labels to each column of data. The experimental results show that, compared to other schemes, the scheme proposed in this paper demonstrates certain advantages in both recognition efficiency and accuracy.