Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
MODEL TRAINING METHOD, SIGNAL RECOGNITION METHOD AND APPARATUS, COMPUTING PROCESSING DEVICE, COMPUTER PROGRAM, AND COMPUTER-READABLE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2023/004572
Kind Code:
A1
Abstract:
A model training method, a signal recognition method and apparatus, a computing processing device, a computer program, and a computer-readable medium. The model training method comprises: obtaining a training sample set, the training sample set comprising sample electrocardiogram signals and anomaly labels of the sample electrocardiogram signals, and the anomaly labels comprising a target anomaly label and at least one related anomaly label; inputting the sample electrocardiogram signals into a multitask model, and training the multitask model on the basis of a multitask learning mechanism according to an output of the multitask model and the anomaly label, the multitask model comprising a target task model and at least one related task model, a target output of the target task model being a target anomaly label of the inputted sample electrocardiogram signals, and an target output of the related task model being a related anomaly label of the inputted sample electrocardiogram signals; and determining that a trained target task model is a target anomaly recognition model, the target anomaly recognition model being used for identifying a target anomaly in electrocardiogram signals inputted into the target anomaly recognition model.

Inventors:
ZHANG CHUNHUI (CN)
ZHANG ZHENZHONG (CN)
Application Number:
PCT/CN2021/108605
Publication Date:
February 02, 2023
Filing Date:
July 27, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
BOE TECHNOLOGY GROUP CO LTD (CN)
International Classes:
A61B5/00; G06N3/08
Foreign References:
CN111134662A2020-05-12
CN111401558A2020-07-10
CN111110224A2020-05-08
CN112800222A2021-05-14
US20190130247A12019-05-02
Attorney, Agent or Firm:
BEIJING RUN ZEHENG INTELLECTUAL PROPERTY LAW FIRM (CN)
Download PDF: