Design of a high-dimensional information decision model for smart supply chains using IoT data traceability in the post-public health crisis era

Abstract

Scholars focus on reducing the compression ratio of high-dimensional information decision models and improving model efficiency. Thereby, the data traceability model is optimized. First, the data intelligent supply chain and traceability models in the post-public health crisis era are analyzed. Next, the issues existing in the current information traceability models are discussed. Finally, a new high-dimensional information decision model is designed by optimizing the data traceability model. The feasibility of the optimized model is validated through experiments. The experimental results demonstrate that different frequency factors impact the model’s compression ratio when comparing the optimized model proposed with the traditional model. Furthermore, the optimized model has a lower compression ratio and higher efficiency, as it does not require encoding the entire origin set. To further validate the rationality of the proposed model, experiments are conducted to compare the compression time ratio for data sizes ranging from 100 to 250 Mb. The experimental results show that the optimized model is minimally affected by the file size and has higher efficiency for files of the same size. Therefore, this work provides valuable insights for optimizing information decision models.