The carbon footprint management system and traceability methods face the practical needs of effectively integrating heterogeneous data from multiple sources, the important task of accurately identifying key emission links, and the objective situation of further improving cross enterprise collaboration and sharing mechanisms. In view of this, this article creatively introduces association rule algorithms in the field of big data, aiming to build an innovative model specifically for cross industry products that integrates efficient sharing of carbon footprint data and full process traceability functions. The model first performs standardized preprocessing operations on various types of data generated during the carbon footprint certification process to ensure consistency and availability of data formats, and then uses the FP-Growth algorithm to deeply explore potential carbon emission association rules between different supply chain nodes. The experimental results objectively demonstrate that compared with traditional carbon footprint data processing methods, the association rule mining method based on FP-Growth algorithm exhibits higher operational efficiency and stronger stability in the processing of cross industry carbon footprint data. Specifically, under the same minimum support condition, the average running time of the Apriori algorithm was significantly reduced from 18.6 seconds to 7.9 seconds, and the two key indicators of rule confidence and improvement were significantly improved.
Lai et al. (Thu,) studied this question.