US 12,306,848 B2
Data fusion system and data fusion 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 Dec. 20, 2023, as Appl. No. 18/389,829.
Claims priority of application No. 202311008879.X (CN), filed on Aug. 10, 2023.
Prior Publication US 2025/0053569 A1, Feb. 13, 2025
Int. Cl. G06F 16/25 (2019.01); G06F 16/23 (2019.01); G06F 18/25 (2023.01)
CPC G06F 16/254 (2019.01) [G06F 16/2365 (2019.01); G06F 18/253 (2023.01)] 18 Claims
OG exemplary drawing
 
1. A data fusion method, comprising:
executing, by a processor, a feature extraction module to extract a plurality of feature data from a plurality of form data;
executing, by the processor, a model building module to perform a preprocessing operation on the plurality of feature data and build a prediction model;
executing, by the processor, a model disassembly module to disassemble the prediction model into a plurality of triples data; and
executing, by the processor, a data fusion module to fuse the plurality of triples data into knowledge graph data,
wherein extracting the plurality of feature data from the plurality of form data comprises:
performing table association processing on the plurality of form data to generate summary table data; and
performing an ETL (Extract, Transform, Load) engineering calculation on the summary table data to generate the plurality of feature data.