Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method and device for predicting crying causes of baby

A baby and cause technology, which is applied in the field of prediction method and device for the reason of baby crying, can solve problems such as inaccurate results, immature technology for predicting the reason of baby crying, unable to respond to baby needs in time, etc., and achieve the effect of accurate prediction

Inactive Publication Date: 2019-03-22
IFLYTEK CO LTD
View PDF9 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the crying information is difficult to interpret, which not only causes parents to be in a hurry, but also fails to respond to the baby's needs in a timely manner, or even meet the baby's needs in a targeted manner. Therefore, how to know the reason for the baby's crying is an urgent problem to be solved
[0003] The existing techniques for predicting the cause of infant crying are immature, and most of them draw on more mature solutions in the field of voice to predict, but based on the difference between the audio of infant crying and the voice of normal people, it leads to the use of existing technologies to predict the cause of infant crying. The results of the reason for crying are not accurate enough

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
  • Method and device for predicting crying causes of baby
  • Method and device for predicting crying causes of baby
  • Method and device for predicting crying causes of baby

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0084] see figure 1 , a schematic flow chart of a method for predicting the cause of a baby’s cry provided in this embodiment, the method includes the following steps:

[0085] S101: Obtain the original audio data and original video data of the target infant during the crying period by synchronously recording the audio and video of the target infant, as the target audio data and target video data respectively, wherein the original video data includes the face of the target infant Close-up video data and / or action video data.

[0086] In this embodiment, any baby whose crying cause is predicted by using this embodiment is defined as a target baby. In order to realize the prediction of the crying reason of the target baby, the audio and video of the target baby can be recorded synchronously. When recording the audio data of the target baby, recording equipment such as a microphone can be utilized to record the sound of the target baby, so that the audio data of the target baby...

no. 2 example

[0121] This embodiment will introduce the specific process of how to use the pre-built crying reason prediction model to "predict the crying reason of the target baby according to the target audio data and target video data".

[0122] Among them, the crying cause prediction model is mainly composed of an input layer, an encoding layer, a fusion layer, a decoding layer, and an output layer, such as figure 2 shown. Wherein, the input layer input is the original audio data and original video data of the target baby, and the input layer outputs the target audio data and target video data of the target baby; The video data is encoded; the function of the fusion layer is to fuse the coding features output by the coding layer; the function of the decoding layer is to decode the fusion features output by the fusion layer; the function of the output layer is to predict the target baby according to the decoding features output by the decoding layer reason for crying.

[0123] Next, t...

no. 3 example

[0176] This embodiment will introduce the construction process of the crying cause prediction model mentioned in the above embodiments. Specifically, the following steps D1-D3 may be included:

[0177] Step D1: A large amount of training sample data is collected.

[0178] In this embodiment, in order to construct a crying cause prediction model, it is necessary to pre-collect sample audio data and sample video data of the same sample baby in the same crying period, thereby collecting multiple sets of such data, and using each set of data as a training sample. It should be noted that each set of training sample data can be acquired in the manner described in S101 in the first embodiment.

[0179] After collecting a large amount of training sample data, each training sample data can be sorted, classified and labeled manually according to the actual situation, that is, the crying sample baby is manually processed, and according to the response result of the sample baby, Mark 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 device for predicting crying causes of a baby. The method includes the steps that firstly, original audio data and original video data of the target baby in a crying period are obtained and serve as target audio data and target video data by synchronously recording an audio and video of the target baby, wherein the original video data includes facial close-up video data and / or behavioral act video data of the target baby; secondly, the crying causes of the target baby can be predicted according to the obtained target audio data and the target video data. Itcan be seen that when the crying causes of the target baby are predicted, the audio data and the video data of the target baby in the crying period are combined so that the crying causes of the target baby can be more accurately predicted out.

Description

technical field [0001] The present application relates to the technical field of information processing, and in particular to a method and device for predicting the cause of a baby's crying. Background technique [0002] Language and writing are the main ways and methods of human communication. Newborn babies cannot communicate with language, and crying has become the most important way of expressing emotions. The research results of infant experts show that crying is not only the main way of communicating with the outside world, but also an important source of information reflecting its physiological and psychological needs, physical and mental health status, and even the level of intellectual development. However, the crying information is difficult to interpret, which not only causes parents to be in a hurry, but also fails to respond to the baby's needs in a timely manner, and even cannot meet the baby's needs in a targeted manner. Therefore, how to know the reason for t...

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
IPC IPC(8): G10L25/18G10L25/21G10L25/72G06K9/00
CPCG10L25/18G10L25/21G10L25/72G06V40/20
Inventor 鲍晓
Owner IFLYTEK CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com