Major formula analysis and discovery method

Abstract

The invention discloses a major formula analysis and discovery method, relates to the technical field of traditional Chinese medicine special departments and diseases, doctors and literature major formula big data correlation research, and solves the problems that a correlation rule-based analysis method is relatively fuzzy for definition of correlation among medicines and a clustering-based major formula correlation research method has relatively large difference in eigenvalue extraction and similarity measurement methods in the prior art. According to the major formula analysis and discovery method, each knowledge unit is endowed with coordinate mapping by utilizing a deep learning technology based on a knowledge graph; distance information is fully utilized to reflect correlation among major formulae; the advantages of correlation rules, sample clustering and complex network community discovery can be integrated; and the advantages, namely, multi-dimensional knowledge graph presentation and knowledge reasoning, inexistent in the conventional method are achieved. A user can freely set a community quantity; and the method has remarkable superiority in common medicine pair semantic retrieval, visual traditional Chinese medicine community discovery, single medicine and basic formula correlation research.

Description

technical field [0001] The invention relates to the technical field of big data correlation research on TCM special diseases, physicians, and core prescriptions of literature, and in particular relates to an analysis and discovery method of core prescriptions. Background technique [0002] In the field of traditional Chinese medicine, there is a high level of support in the drug pair compatibility law, that is, the drug combination with a higher frequency is the core prescription. In the construction of the Chinese medicine knowledge map, it is necessary to mine the core prescriptions of Chinese medicine to discover the correlation between them. The knowledge map integrates all disciplines, and links knowledge units of different sources, types, and structures into a graph. Based on the metadata of each discipline, it provides users with a wider and deeper knowledge system and continues to expand. In essence, it systematizes and relationalizes domain knowledge data, and visu...

AI Technical Summary

Problems solved by technology

[0003] Existing technologies mainly use association rules and complex networks to mine the core prescriptions of traditional Chinese medicine. The above methods mostly use frequency analysis as the basis for statistical inference. Although they are widely used, there are still limitations, such as inconsistent parameter setting levels and inconsistent result evaluation standards. Often come to redundant conclusions or conclusions that cannot be explained by traditional compatibility theory, etc.

The analysis method based on association rules has a vague definition of "association" between drugs; there are large differences in feature value extraction and similarity measurement methods among various studies found by the core method based on clustering; complex network analysis methods are divided into applications The core party found that it is still at the stage of node degree analysis, lacking a deep combination of theory and analysis

Images