World Intellectual Property Organization Releases Shanghai Maritime University Patent Application for Raman Spectrum Classification Method, Species Blood and Semen Classification Method, and Species Classification Method

Publication Name: Medical Patent NewsPatent Application Number: WO2024CN82557 20240320Patent Publication Number: WO2025050613 (A1)International Patent Classification Codes: G06F18/2413Cooperative Patent Classification Codes: G01N21/65 (EP, CN, US), G01N33/49 (US), G06F18/10 (CN), G06F18/213 (CN), G06F18/214 (CN), G06F18/2413 (CN), G06F18/253 (CN), G06N3/045 (CN), G06N3/0464 (CN), G06N3/084 (CN), G01N2201/126 (US), G01N2201/1296 (EP, CN)Patent Status: Application

Geneva, March 18 -- World Intellectual Property Organization has released Shanghai Maritime University patent application for raman spectrum classification method, species blood and semen classification method, and species classification method. This invention was developed by Zhou Rigui, Ren Pengju and Zhou Hanxuan.

The patent application number is WO2024CN82557 20240320. The patent publication number is WO2025050613 (A1). International Patent Classification code is G06F18/2413. Cooperative Patent Classification codes are G01N21/65 (EP, CN, US), G01N33/49 (US), G06F18/10 (CN), G06F18/213 (CN), G06F18/214 (CN), G06F18/2413 (CN), G06F18/253 (CN), G06N3/045 (CN), G06N3/0464 (CN), G06N3/084 (CN), G01N2201/126 (US), G01N2201/1296 (EP and CN).

According to the abstract released by the World Intellectual Property Organization: "Disclosed in the present invention are a Raman spectrum classification method, a species blood and semen classification method, and a species classification method. The Raman spectrum classification method comprises: first, acquiring a plurality of pieces of Raman spectrum data, and taking same as a training set and a test set; second, on the basis of existing spectral quality, performing a series of preprocessing on the Raman spectrum data, so as to acquire Raman spectrum data having obvious peak information; then, inputting the Raman spectrum data having obvious peak information into a neural network model in which one-dimensional convolution and a multi-head self-attention mechanism are combined, and training a classification model; and finally, inputting Raman spectrum test set data into the trained classification model, so as to obtain a final classification result. Local peak feature information can be obtained by means of performing convolution computation on a spectrum, global peak correlation information can be obtained by means of performing multi-head self-attention computation on the spectrum, and a multi-scale feature fusion effect is achieved; and local feature peaks of a Raman spectrum can be effectively combined with global peak correlations, so that a more accurate classification representation is achieved, thereby improving the classification accuracy."

Copyright© 2025, Globalipnews.com