Multi-dimensional quantitative analysis method and system for tracing origins of traditional medicine disease terms in ancient books and documents

Abstract

The present invention provides a multi-dimensional quantitative analysis method and system for tracing origins of traditional Chinese medicine (TCM) disease terms in ancient books and documents, the method specifically includes the steps of: S1, construction of an ancient book and document corpus: collecting TCM ancient books and documents from successive dynasties, performing digital processing and standardized annotation of the documents, and constructing an ancient book and document corpus including document age, document type, academic school, text content and structured annotation information; and S2, preprocessing of terms to be traced: acquiring TCM disease terms to be traced, performing synonym merging, variant character standardization and vague term definition on the terms, and generating term semantic feature vectors. The present invention can comprehensively excavate the inheritance and evolution information of TCM disease terms in ancient books, and improve the comprehensiveness and depth of traceability analysis.