US 12,405,964 B2
Data processing system and data processing method
Xu Jin, Shanghai (CN); and Guoxin Sun, Shanghai (CN)
Assigned to DIGIWIN CO., LTD., Shanghai (CN); and DATA SYSTEMS CO., LTD., New Taipei (TW)
Filed by DIGIWIN CO., LTD., Shanghai (CN); and DATA SYSTEMS CO., LTD., New Taipei (TW)
Filed on Oct. 12, 2023, as Appl. No. 18/486,139.
Claims priority of application No. 202310917778.8 (CN), filed on Jul. 24, 2023.
Prior Publication US 2025/0036647 A1, Jan. 30, 2025
Int. Cl. G06F 16/25 (2019.01); G06F 16/28 (2019.01); G06N 5/02 (2023.01)
CPC G06F 16/254 (2019.01) [G06F 16/285 (2019.01); G06N 5/02 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A data processing system, comprising:
a storage device, configured to store a data processing module, a feature processing module, and a classification conversion module; and
a processor, electrically connected to the storage device, and configured to execute the data processing module, the feature processing module, and the classification conversion module,
wherein the data processing module generates summary data according to an association relationship between a plurality of form data, the data processing module performs feature index calculation on the summary data to generate feature index data, wherein the feature index calculation is an ETL (extract, transform, load) engineering calculation, and the data processing module preprocesses the feature index data to generate a sample label data set,
wherein the feature processing module generates a training data set according to the sample label data set,
wherein the classification conversion module builds a classification model according to the training data set, and builds a structured semantic knowledge base according to the classification model,
wherein when the classification conversion module builds the structured semantic knowledge base, the classification conversion module reads a plurality of classification rules from the classification model to generate a plurality of triplet data, and the classification conversion module determines whether a factor data and category labels in a first triplet data are same as those of the second triplet data,
wherein when the classification conversion module determines the factor data and category labels in the first triplet data are same as those of the second triplet data, the classification conversion module combines the first triplet data and the second triplet data to generate fused triplet data in the structured semantic knowledge base, wherein an amount of data of the fused triplet data is less than a total amount of data of the first triplet data and the second triplet data.