A method and system for recognizing and prompting infant crying sound

A sound recognition and baby technology, applied in character and pattern recognition, speech analysis, instruments, etc., can solve the problems of not being able to accurately and scientifically obtain the demand status of babies' crying sounds, so as to reduce the nursing workload and improve accuracy and precision , the effect of simple calculation method

Inactive Publication Date: 2020-08-28
NANFANG HOSPITAL OF SOUTHERN MEDICAL UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method also relies on the experience of nurses and other staff, and cannot accurately and scientifically obtain the demand status reflected by the baby's crying.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method and system for recognizing and prompting infant crying sound
  • A method and system for recognizing and prompting infant crying sound

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] refer to figure 1 , the present invention provides a kind of baby cry recognition prompting method, comprises the following steps:

[0046] Obtain the baby's crying signal and action image in real time;

[0047] After preprocessing the baby crying signal, calculate the reverse Mel frequency cepstrum coefficient of the baby crying signal, and discretize the reverse Mel frequency cepstrum coefficient to obtain the reverse Mel frequency cepstrum coefficient discrete value;

[0048] According to the baby crying recognition model established based on the preset Bayesian classification algorithm, the discrete values ​​of the reverse mel-frequency cepstral coefficient are classified and processed, thereby identifying the crying state corresponding to the baby crying signal;

[0049] Based on the preset action behavior database, the baby action image acquired in real time is used to verify the crying state obtained from the baby crying signal recognition;

[0050] Based on t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method and system for recognizing and prompting baby crying, comprising the steps of: acquiring baby crying signals and action images in real time; preprocessing the baby crying signals, calculating and obtaining the reverse Mel of the baby crying signals Frequency cepstral coefficient, and the reverse Mel frequency cepstral coefficient is discretized, and the discrete value of the reverse Mel frequency cepstral coefficient is obtained; the baby cry recognition model established based on the preset Bayesian classification algorithm , classify the discrete values ​​of the inverse Mel frequency cepstrum coefficient, thereby identifying the crying state corresponding to the baby crying signal; use the real-time acquired baby action image to verify the cry obtained from the baby crying signal recognition sound state; send out the corresponding prompt signal. The invention has simple calculation method, high calculation efficiency and high recognition precision, can improve the accuracy and precision of crying state recognition, and can be widely used in the field of baby care.

Description

technical field [0001] The invention relates to the technical field of baby sound analysis, in particular to a method and system for recognizing and prompting baby crying sounds. Background technique [0002] Crying is the only way for babies to express, and it is a special "language". There are several basic expressions of baby crying, including hunger, sleepiness, need to burp, intestinal cramps and discomfort. There is an inherent typical pattern, but adults generally cannot accurately understand the reasons for babies to cry, and cannot understand the needs of babies' crying, which will inevitably lead to inadequate care and care for babies, which is not conducive to the healthy growth of babies. For the current medical service institutions such as neonatology, obstetrics, or confinement centers, during the baby's hospitalization, the monitoring of the baby's crying is to manually check the baby's condition after collecting the baby's crying sound, or to collect the bab...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G10L17/06G10L25/24G10L25/66G06K9/00
CPCG10L17/06G10L25/24G10L25/66G06V40/20
Inventor 周燕莉
Owner NANFANG HOSPITAL OF SOUTHERN MEDICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products