Multi-label multi-mode holographic pulse condition recognition method based on graph convolution network

Abstract

The invention discloses a multi-label multi-mode holographic pulse condition recognition method based on a graph convolution network. A relation matrix is constructed by adopting a data driving mode;a graph neural network is adopted to mine co-occurrence modes of pulse condition tags and tags and tags and data in a data set to define correlations between the tags and between the tags and the data; then, the features of pulse condition video are extracted by adopting space-time separable 3D convolution; the whole model structure adopts 2D convolution operation at the front; the space-time separable 3D convolution operation is carried out at the back, and finally data fusion is carried out in a weighted point multiplication mode according to the pulse condition video feature vector and thepulse condition relationship feature vector extracted by the space-time separable 3D convolution and graph neural network, so that the pulse diagnosis process of the machine becomes more efficient andaccurate.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a multi-label multi-modal holographic pulse recognition method based on graph convolutional networks. Background technique [0002] TCM diagnosis is realized by looking, smelling and asking. Wang, refers to observing complexion; Wen, refers to listening to sound; Ask, refers to inquiring about symptoms; Cut, refers to feeling the pulse. Among them, the pulse is the most complicated. For example, physicians of all dynasties have different views on the length of each part of cun, guan, and chi. However, the view of "taking three cun for the pulse, and one inch for each of the three parts" has been recognized by most doctors. At present, there are various instruments and analysis methods for collecting patients' pulse conditions, but the detected signals are mostly electrical signals and pressure signals, and the signal dimensions are small, which cannot represent v...

AI Technical Summary

Problems solved by technology

This type of method has two deficiencies. First, the dependence between the pulse conditions is ignored, and multiple classification models are output as a result. When inferring, multiple models need to be loaded, which affects the efficiency; second, the electrical signal and Pressure signal, signal dimension is small, unable to represent various information such as lumen volume, blood flow velocity, three-dimensional movement of vessels, etc., which affects the accuracy of the model

Images