Snore monitoring method and system based on deep learning algorithm and corresponding electric bed control method and system

Abstract

The invention discloses a snore monitoring method based on a deep learning algorithm. The snore monitoring method is based on deep learning and voice recognition technologies and comprises the steps of: acquiring an audio signal and slicing according to preset sample duration; judge whether a slice contains sound by using a silence detection algorithm; extracting acoustic spectrum features from the audio slice containing sound; inputting the generated spectrum features into a deep neural network to extract deep learning features; classifying the extracted deep learning features by using a fully connected layer; and carrying out snore event judgment and intervention according to preset duration. The invention also discloses a related system. Compared with a traditional method, the snore recognition method and system based on the deep learning algorithm, which are provided by the invention, have the advantages that the snore and non-snore judgment accuracy is greatly improved, and better user experience (Fig. 1) is brought.

Description

technical field [0001] The present invention relates to speech-related technology and deep learning technology, in particular to a method and device for snoring monitoring and electric bed control based on deep learning algorithm. Background technique [0002] According to incomplete statistics, nearly 20% of the population in my country snores, and those who snore severely may even cause obstructive apnea, which seriously affects their health. [0003] At present, related snoring detection technologies mostly adopt the following methods: use contact wearable devices for detection, this method can achieve the highest detection rate and is not easy to be falsely triggered, but it will affect sleep; use sound sensors to detect decibels or vibration sensors to detect airway Vibration method, but the accuracy of this method is low, and false detection is prone to occur. Therefore, there is a need for a snoring detection and intervention system that can accurately detect snoring...

AI Technical Summary

Problems solved by technology

[0003] At present, related snoring detection technologies mostly adopt the following methods: use contact wearable devices for detection, this method can achieve the highest detection rate and is not easy to be falsely triggered, but it will affect sleep; use sound sensors to detect decibels or vibration sensors to detect airway Vibration method, but the accuracy of this method is low, and it is easy to cause false detection

Images