Data Granularity Gradable Quality Traceability Modeling Method of Traditional Chinese Medicine

Abstract

The data modeling method in the existing Chinese herbal medicine traceability system cannot meet the data granularity requirements of government regulators, the public and the production enterprises at the same time, so we construct a set of data quality and grading method for traceability modeling of Chinese herbal medicines based on the structural pattern recognition theory. Firstly, based on the design and description of the 12 model elements of the transformation process of the Chinese medicine supply chain, the data storage structure and data acquisition algorithm are designed based on relational algebra theory. Then based on the syntax pattern recognition theory and the formal grammar of the traceability data of Chinese herbal medicine products, a recursive-based sentence generation algorithm is constructed and a granularity classification method based on improved push-down automata is established to establish a variable-grained model of Chinese herbal medicine quality traceability data. Finally, taking some Chinese herbal medicine products as an example, the feasibility and effectiveness of the above models and algorithms are verified from the business process analysis to the hierarchical granularity specification.