Traditional Chinese medicine syndrome type identification method and system

Abstract

The invention relates to a traditional Chinese medicine syndrome type identification method and system, and the method comprises the steps: carrying out the processing of a to-be-identified text through a pre-established syndrome type word segmentation model, obtaining a to-be-identified syndrome type abbreviation, searching a corresponding initial syndrome type name in a composition model table, obtaining a corresponding syndrome type vector V from a pre-established element vector matrix according to the preliminary syndrome type name, traversing each vector record in the pre-established syndrome type vector matrix, and when a syndrome type vector R of which the cosine similarity with the syndrome type vector V meets a preset similarity threshold is found, determining that the syndrome type vector V meets the preset similarity threshold; and if yes, taking the syndrome type name corresponding to the syndrome type vector R as the final target syndrome type name of the syndrome type vector V. According to the method, the traditional Chinese medicine syndrome types can be effectively segmented, and the professional requirements of the traditional Chinese medicine industry are met.

Description

technical field [0001] The invention belongs to the technical field of text recognition, and in particular relates to a method and system for recognizing syndrome types of traditional Chinese medicine. Background technique [0002] With the electronicization of TCM medical records, ancient TCM books and modern TCM literature, the research on TCM technology has been further developed. In order to realize in-depth data mining and analysis on the basis of TCM electronic data, the structuring of medical texts is particularly important. Among them, the identification of TCM texts is an effective way to study and structure medical texts and obtain more accurate syndrome types. And grasp the effective method of syndrome type corresponding treatment. [0003] Common text recognition methods include maximum entropy model, conditional random field model, attention mechanism model, deep neural network, etc. Due to the different requirements for text recognition in different professio...

AI Technical Summary

Problems solved by technology

[0004] The present invention intends to provide a method and system for identifying TCM syndrome types to solve the problem that existing text recognition methods for segmenting TCM syndrome types cannot meet the professional needs of the TCM industry. The technical problem to be solved by the present invention is through The following technical solutions are implemented:

Images