Snoring sound detection method and apparatus

By acquiring human sensory signals and audio signals, and combining sound intensity and phase characteristics, a snoring detection model is used to determine the attribution of snoring sounds. This solves the problem of unclear attribution of snoring sounds in multi-person cohabitation environments and achieves personalized and accurate sleep monitoring.

CN122153606APending Publication Date: 2026-06-05AIMENG SMART HOME (ZHUHAI) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
AIMENG SMART HOME (ZHUHAI) CO LTD
Filing Date
2026-05-08
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

In smart home and smart sleep monitoring scenarios where multiple people live together, existing snoring detection cannot clearly identify the source of snoring, resulting in sleep monitoring data containing snoring information from different users. This makes it impossible to achieve accurate health tracking of individuals and the detection accuracy is insufficient.

Method used

By acquiring human body sensing signals and audio signals, the device's usage status and audio characteristics are determined. A snoring detection model is adopted, combining dual feature fusion of sound intensity and sound phase characteristics. The sound intensity coefficient reference table and sound phase coefficient reference table are used for fitting analysis, along with a complete coefficient calibration and effectiveness evaluation mechanism. The snoring is attributed by weighted summation combined with the device's usage status.

Benefits of technology

It improves the accuracy of snoring detection and attribution, avoids health misjudgments caused by mixed snoring data, and achieves a leap from generalized environmental monitoring to precise individual monitoring.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122153606A_ABST
    Figure CN122153606A_ABST
Patent Text Reader

Abstract

The application discloses a snoring sound detection method and device, the method comprising: acquiring a human body sensing signal and an audio signal; determining a device usage state and an audio feature based on the human body sensing signal and the audio signal; selecting a corresponding feature combination based on the human body sensing signal, the device usage state and the audio feature, and inputting the corresponding feature combination into a preset snoring sound detection model for snoring sound detection to determine a current snoring sound state; if the current snoring sound state is determined, determining an initial snoring sound attribution probability based on a preset sound intensity coefficient reference table, a sound phase coefficient reference table and the audio feature, and performing weighted summation on the initial snoring sound attribution probability and the device usage state to determine a final snoring sound attribution result. The application effectively solves the technical defects that snoring sound attribution cannot be determined, detection accuracy is insufficient, and there is a lack of scientific benchmark reference system and probability calculation logic in the process of snoring sound detection in a multi-person cohabitation scene, and effectively improves detection and attribution judgment accuracy.
Need to check novelty before this filing date? Find Prior Art