A peak recognition method and device based on a deep learning model and a medium

By using a peak identification method based on a deep learning model, the problems of noise misjudgment and low signal-to-noise ratio in spectral peak identification are solved, achieving high accuracy and high efficiency in peak identification, which is applicable to data processing such as gas chromatography, liquid chromatography, and mass spectrometry.

CN122241241APending Publication Date: 2026-06-19ANHUI WAYEE SCI & TECH CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
ANHUI WAYEE SCI & TECH CO LTD
Filing Date
2026-05-21
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

Existing technologies suffer from noise misjudgment, low processing timeliness and accuracy in spectral peak identification, making it difficult to meet the high real-time and high accuracy requirements of modern analysis, especially when faced with low signal-to-noise ratio and complex waveforms.

Method used

A peak identification method based on a deep learning model is adopted. By acquiring and labeling a one-dimensional dataset, a one-dimensional convolutional deep learning model is constructed. Combining training samples and the verification process, the start and end points of peaks are identified, and negative peaks are flipped and raised to enhance the model's noise resistance.

Benefits of technology

It improves the accuracy and noise resistance of spectral peak identification, can identify complex situations such as peak clusters, has strong applicability, reduces computing power overhead, and improves the robustness and stability of computation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122241241A_ABST
    Figure CN122241241A_ABST
Patent Text Reader

Abstract

This invention discloses a peak identification method, apparatus, and medium based on a deep learning model. The method includes: acquiring raw data, which is a one-dimensional dataset of data point indices and response values; labeling the peak types and peak start-end indices of the raw data; removing invalid regions based on the labeling content and data source to obtain training samples or data to be processed; constructing a one-dimensional convolutional deep learning model based on the training samples and training the model; obtaining the basic start-end points and the maximum length of the peak indices of the data to be processed based on the training model; and selecting the minimum values ​​corresponding to the minimum values ​​that meet the verification requirements based on the basic start-end points and the maximum length of the peak indices as the correction start-end points. The peak identification method proposed in this application is a data-driven algorithm. By training the model, it can identify the basic start-end points of peaks, and combined with correction processing, it can obtain accurate peak positions.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Waveform analysis device

    CN111373256B

  • A chromatographic peak recognition method based on convolutional neural network

    CN111767790B

  • Data generation method and device, and recognizer generation method and device

    CN115997219B

  • Negative peak detection method and device and readable storage medium

    CN119959437A