CN106653059A - Automatic identification method and system for infant crying cause - Google Patents
Automatic identification method and system for infant crying cause Download PDFInfo
- Publication number
- CN106653059A CN106653059A CN201611014119.XA CN201611014119A CN106653059A CN 106653059 A CN106653059 A CN 106653059A CN 201611014119 A CN201611014119 A CN 201611014119A CN 106653059 A CN106653059 A CN 106653059A
- Authority
- CN
- China
- Prior art keywords
- crying
- baby
- probability
- time
- reason
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 206010011469 Crying Diseases 0.000 title claims abstract description 278
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000005236 sound signal Effects 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 15
- 230000000474 nursing effect Effects 0.000 claims abstract description 9
- 238000004458 analytical method Methods 0.000 claims description 29
- 230000001575 pathological effect Effects 0.000 claims description 23
- 238000012360 testing method Methods 0.000 claims description 5
- 206010041349 Somnolence Diseases 0.000 claims description 4
- 235000003642 hunger Nutrition 0.000 claims description 4
- 230000037351 starvation Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- BYACHAOCSIPLCM-UHFFFAOYSA-N 2-[2-[bis(2-hydroxyethyl)amino]ethyl-(2-hydroxyethyl)amino]ethanol Chemical compound OCCN(CCO)CCN(CCO)CCO BYACHAOCSIPLCM-UHFFFAOYSA-N 0.000 description 10
- 230000006872 improvement Effects 0.000 description 10
- 230000008859 change Effects 0.000 description 7
- 230000000694 effects Effects 0.000 description 7
- 230000006651 lactation Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 230000035479 physiological effects, processes and functions Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000033764 rhythmic process Effects 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 230000007423 decrease Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 230000011514 reflex Effects 0.000 description 4
- 230000003862 health status Effects 0.000 description 3
- 230000007170 pathology Effects 0.000 description 3
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 239000012141 concentrate Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 210000001015 abdomen Anatomy 0.000 description 1
- 238000013019 agitation Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 206010016766 flatulence Diseases 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/18—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being spectral information of each sub-band
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/66—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for extracting parameters related to health condition
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/72—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for transmitting results of analysis
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Public Health (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Child & Adolescent Psychology (AREA)
- Hospice & Palliative Care (AREA)
- Psychiatry (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention, which relates to the infant nursing field, discloses an automatic identification method and system for an infant crying cause. With the method and system, young parents lack of parenting experience can find out crying causes of infants accurately. The method comprises: a baby crying sound is recorded and a crying audio signal is obtained; a time-frequency characteristic is extracted from the crying audio signal, and probabilities, corresponding to preset different crying causes, of the time-frequency characteristic are obtained according to the time-frequency characteristic and a classified obtained by training in advance; and at least two kinds of crying causes with the highest probabilities and probabilities of the crying causes are displayed at a terminal screen.
Description
Technical field
The present invention relates to Baby Care field, the more particularly to automatic identification technology of baby crying reason.
Background technology
Crying is the first articulation type of baby, is also young infant and the extraneous sole mode linked up.Experienced mother
Mother and doctor can understand the mood of baby, demand and health by vagitus.Due to the decline of modern society's birth rate, very
Many mother's only one of which children, lack correlation experience, be badly in need of technological means come help youth mothers by sob come
The demand of solution baby.
With the development of computer technology and the communication technology, some related technical schemes have been occurred in that.For example, typing
Baby crying, be converted to computer-readable form, by filtered digital signal, estimate base frequency, lubricate data signal,
Exceptional value is eliminated, obtains corresponding acoustic analysis parameter to be identified baby crying reason.
But it was found by the inventors of the present invention that current technology scheme is all can only to provide a crying reason (from multiple
A display is selected in crying reason, or judges whether to belong to certain specific crying reason), and this is crowed when actually used
It is so high that the accuracy of reason of crying often can not show a candle to declare, unfamiliar young mother often attempt solving this reason it
Afterwards baby also is continuing to cry, so as to more flurried.
The content of the invention
It is an object of the invention to provide the automatic identifying method and its system of a kind of baby crying reason, can make to lack
The reason for young father and mother of child-bearing experience relatively accurately know baby crying.
To solve above-mentioned technical problem, embodiments of the present invention disclose a kind of automatic identification side of baby crying reason
Method, comprises the following steps:
Baby crying sound is recorded, sob audio signal is obtained;
Time-frequency characteristics are extracted from the sob audio signal, the grader according to obtained by the time-frequency characteristics and training in advance is obtained
The probability of different crying reasons set in advance is corresponded to the time-frequency characteristics;
The probability of the crying reason of indicating probability highest at least two and these crying reasons on a terminal screen.
In another preference, " on a terminal screen the crying reason of indicating probability highest at least two is crowed with these
In the step of probability of reason of crying ", the crying reason of indicating probability highest at least two and these cryings are former in the way of pie chart
The probability of cause.
In another preference, different crying reasons set in advance include one of following reason or its any combination:
Starvation, sleepy is felt, uncomfortable, wet diaper.
In another preference, " on a terminal screen the crying reason of indicating probability highest at least two is crowed with these
The step of probability of reason of crying ", includes following sub-step:
Filter out crying reason of the probability more than predetermined threshold;
The each crying reason for filtering out is shown on a terminal screen.
In another preference, the first corresponding relation of week old and crying concentrative time interval is preset;
" obtain time-frequency characteristics corresponding to different crying reasons set in advance probability " the step of after also include with
Lower step:
The week old of baby and crying time when acquisition is cryed;
First corresponding relation is searched according to acquired week old, corresponding crying concentrative time interval is obtained;
If the crying time falls in the crying concentrative time interval for searching gained, the probability of causes for pathological is reduced, otherwise increased
Plus the probability of causes for pathological.
In another preference, " obtaining probability of the time-frequency characteristics corresponding to different crying reasons set in advance "
It is further comprising the steps of after step:
The tone of detection sob audio signal;
If testing result is the peak value that tone reaches frequency in the scheduled duration after starting of crying, and the monthly age of baby
Less than predetermined threshold, then increase the probability of pain cause.
It is further comprising the steps of in another preference:
While baby crying sound is recorded, the video of baby face is shot;
Graphical analysis is carried out to the video, the fine folding condition of baby eyes is obtained;
If during baby crying, the baby eyes fine total time in closure state is more than predetermined threshold, then increase
Plus the probability of pain cause.
In another preference, week old is preset and the second corresponding relation of the total time upper limit of crying for 24 hours;
" obtain time-frequency characteristics corresponding to different crying reasons set in advance probability " the step of after also include with
Lower step:
Count the baby it is nearest 24 hours in crying total time;
Second corresponding relation is inquired about according to the week old of the baby, the total time upper limit of crying for 24 hours is obtained;
The total time upper limit if the crying total time cryed more than this 24 hours, increases the probability of causes for pathological.
In another preference, " obtaining probability of the time-frequency characteristics corresponding to different crying reasons set in advance "
It is further comprising the steps of after step:
Obtain time interval of the crying time of origin away from last time time of nursing;
If the time interval is more than predetermined threshold, increase the probability of hungry reason.
Embodiments of the present invention also disclose a kind of automatic recognition system of baby crying reason, and recording elements are used for
Baby crying sound is recorded, sob audio signal is obtained;
Analytic unit, for extracting time-frequency characteristics from the sob audio signal, according to the time-frequency characteristics and training in advance institute
The grader for obtaining, obtains probability of the time-frequency characteristics corresponding to different crying reasons set in advance;
Display unit, for the crying reason of indicating probability highest at least two on a terminal screen and these crying reasons
Probability.
In another preference, display unit in the way of pie chart the crying reason of indicating probability highest at least two and
The probability of these crying reasons.
In another preference, also include:
First memory cell, for storing the first corresponding relation of week old set in advance and crying concentrative time interval;
First information acquiring unit, the week old of baby and crying time when crying for obtaining;
First query unit, for searching the first corresponding relation according to acquired week old, obtains corresponding crying and concentrates
Period;
First adjustment unit, for judging whether the crying time falls in the crying concentrative time interval for searching gained, if
The probability of causes for pathological is then reduced, otherwise increases the probability of causes for pathological.
In another preference, also include:
Tone detection unit, for detecting the tone of sob audio signal;
Second adjustment unit, for judging whether testing result is that tone reaches frequency in the scheduled duration after starting of crying
The peak value of rate, and the monthly age of baby is less than predetermined threshold, if it is increases the probability of pain cause.
In another preference, video capture unit, for while baby crying sound is recorded, shooting baby's face
The video in portion;
Eye analytic unit, for carrying out graphical analysis to the video, obtains the fine folding condition of baby eyes;
3rd adjustment unit, for judge during baby crying whether baby eyes it is fine in closure state it is total when
Between be more than predetermined threshold, if it is increase pain cause probability.
In another preference, also include:
Second memory cell, the second correspondence for storing week old set in advance and 24 hours crying total time upper limits is closed
System;
Crying time statistic unit, for count the baby it is nearest 24 hours in crying total time;
Second query unit, when crying total for according to the week old of the baby the second corresponding relation of inquiry, obtaining 24 hours
Between the upper limit;
4th adjustment unit, for judging the total time upper limit of whether crying more than this 24 hours crying total time, if
It is the probability for then increasing causes for pathological.
In another preference, also include:
Lactation information acquisition unit, for obtaining time interval of the crying time of origin away from last time time of nursing;
5th adjustment unit, for judging that the time interval, whether more than predetermined threshold, if it is increases hungry reason
Probability.
Embodiment of the present invention compared with prior art, at least with following difference and effect:
By the grader obtained by the time-frequency characteristics input training in advance of baby crying sound, the general of different crying reasons is obtained
Rate, and show various crying reasons and its probability, can make that the father and mother for lacking child-bearing experience relatively accurately know crying can
Energy reason, so as to start to exclude the inducement for causing crying one by one from maximum likelihood, makes to obtain with the baby of language performance
In time and effectively look after.Under some adverse environments (environment as noise is larger), the accuracy of automatic decision has necessarily
Decline because showing various crying reasons on a terminal screen, there is preferable fault-tolerance, will not be because of terminal occasionally
Erroneous judgement and make the father and mother for lacking child-bearing experience lose direction.
Further, the period for being occurred according to week old and baby crying is modified to the probability of physiology, causes for pathological, can
Further to improve the accuracy of the baby crying analysis of causes.
Further, with reference to the monthly age, the probability of pain and other reasons is carried out according to the situation of change of tone and rhythm
Amendment, can further improve the accuracy to the baby crying analysis of causes.
Further, the probability of pain cause is modified according to the closure situation of baby's eyes, can be further carried
The high accuracy to the baby crying analysis of causes.
Further, the total crying time in counting one day, with reference to week old, the probability of physiology, causes for pathological is carried out
Amendment, can further improve the accuracy to the baby crying analysis of causes.
Further, with reference to the time apart from last time lactation adjusting the probability of hungry reason, can further improve right
The accuracy of the baby crying analysis of causes.
Description of the drawings
Fig. 1 is a kind of schematic flow sheet of the automatic identifying method of baby crying reason in first embodiment of the invention.
Fig. 2 is baby crying reason display interface schematic diagram in first embodiment of the invention.
Fig. 3 is a kind of schematic flow sheet of the automatic identifying method of baby crying reason in four embodiment of the invention.
Fig. 4 is a kind of structural representation of the automatic recognition system of baby crying reason in seventh embodiment of the invention.
Specific embodiment
In the following description, in order that reader more fully understands the application and proposes many ins and outs.But, this
Even if the those of ordinary skill in field is appreciated that many variations without these ins and outs and based on following embodiment
And modification, it is also possible to realize each claim of the application technical scheme required for protection.
Relational language:
Time-frequency characteristics:Audio signal after time frequency analysis (Time-frequency analysis), in time-frequency plane
The various forms and parameter of (time-frequency plane).Time frequency analysis can be calculated in various analyses including Fourier transformation etc.
Method.
Especially it is noted that the alleged various crying reasons of the present invention cry former all referring to possibility, especially " pathology "
Because being not necessarily referring to confirm as illness, less refer to and be defined as, with a certain disease, simply illustrating that the possibility of illness is larger, it is proposed that
To examination in hospital, in case because the baby head of a family does not give birth to children experience and delay the state of an illness.
Although it was found by the inventors of the present invention that there is the technologies of many identification baby crying reasons in prior art,
What the recognition accuracy that it is declared often was obtained in laboratory conditions for certain specific crying reason, once recording
When have a more noise, or the mode of recording is not professional, then the accuracy rate for judging can decline a lot, the crying reason meeting for being given
It is inaccurate, or even unfamiliar young mother can be misled.
In addition often for a specific reasons training in prior art, for example, it is known that this baby is bitterly
(for example making baby's pain with instrument), corresponding crying sound is used to train under record.Such training result is both for single
Reason.And in actual application, the crying of possible baby has behind several reasons to promote simultaneously, for example, a baby starves
, while crying, no one processes in time again tired, now, which reason no matter is shown, even accurately (being such as hungry or being stranded
), baby still may proceed to cry after unfamiliar young mother is processed according to this reason, and young mother will feel
This software is forbidden, without use.
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with enforcement of the accompanying drawing to the present invention
Mode is described in further detail.
First embodiment of the invention is related to a kind of automatic identifying method of baby crying reason.Fig. 1 is the baby crying
The schematic flow sheet of the automatic identifying method of reason.
In a step 101, baby crying sound is recorded, obtains sob audio signal.
In a preference, the recording of crying sound and display are carried out with mobile terminal (such as smart mobile phone, panel computer).
In other embodiments, it is also possible to use miscellaneous equipment, such as PC, special-purpose terminal to be recorded and shown.
Then into step 102, time-frequency characteristics are extracted from the sob audio signal, according to the time-frequency characteristics and training in advance
The grader of gained, obtains probability of the time-frequency characteristics corresponding to different crying reasons set in advance.
In a preference, different crying reasons set in advance include one of following reason or its any combination:
Starvation, sleepy is felt, uncomfortable, wet diaper.
In another preference, different crying reasons set in advance include following reason in it is any two or more
Kind:
Pathology, hungry, sleepy is felt, uncomfortable, belly flatulence, wants to beat every pain is feared, irritated, wet diaper, etc..
Then into step 103, on a terminal screen the crying reason of indicating probability highest at least two and these cryings
The probability of reason.In a preference, as shown in Fig. 2 indicating probability highest at least two is cryed original in the way of pie chart
The probability of cause and these crying reasons.In other embodiments, can with other graphics context modes be show crying reason and
Its probability, for example, shown in histogrammic mode, shown with mode word etc..
By the grader obtained by the time-frequency characteristics input training in advance of baby crying sound, the general of different crying reasons is obtained
Rate, and show various crying reasons and its probability, can make that the father and mother for lacking child-bearing experience relatively accurately know crying can
Energy reason, so as to start to exclude the inducement for causing crying one by one from maximum likelihood, makes to obtain with the baby of language performance
In time and effectively look after.Under some adverse environments (environment as noise is larger), the accuracy of automatic decision has necessarily
Decline, but because present embodiment shows on a terminal screen various crying reasons, have preferable fault-tolerance, no
Because of terminal erroneous judgement occasionally the father and mother for lacking child-bearing experience can be made to lose direction.
It is appreciated that above-mentioned technical proposal there can be the change in various ways and details when implementing, one is named
The example of a little changes.
In one embodiment, above technical scheme can be realized by smart mobile phone APP.The training of grader
Beyond the clouds server is realized.The used data of training collect cloud server by smart mobile phone.
In one embodiment, the analysis of crying reason is carried out on mobile terminals.
In one embodiment, by audio signal is sent to into high in the clouds after mobile terminal recording, by cloud server point
Analysis is obtained being sent to mobile terminal after reason and shown.
In one embodiment, recorded by mobile terminal and propose time-frequency characteristics from sob audio signal, time-frequency is special
Levy and send cloud server to carry out the analysis of causes, cloud server will be sent to into mobile terminal the reason for analyzing gained and shown.
In one embodiment, the classification to be distinguished of grader is that (N is more than 2 to pre-set N number of classification
Integer), can be using the induced factor of the time-frequency characteristics of crying audio frequency prerecorded and the known crying audio frequency as data
Source is trained.After training terminates, the time-frequency characteristics of a crying audio frequency are input into housebroken grader, the grader can be with
Export the N number of probability corresponding to N number of classification (crying reason).
In one embodiment, grader can be trained with Jing data and obtain N number of model (corresponding to the crying of N number of classification
Reason), in the time-frequency characteristics to housebroken grader one crying audio frequency of input, grader can be calculated in N number of model
Time-frequency characteristics with input time-frequency characteristics similarity, according to Similarity Measure corresponding to N number of classification N number of probability.
In one embodiment, grader is realized based on deep neural network.
In one embodiment, grader is realized based on one group of Weak Classifier organized with tree.
In one embodiment, grader is realized based on BP artificial neural networks.
In one embodiment, crying reason of an indicating probability more than predetermined threshold.I.e. step 103 includes following two
Sub-steps:
Filter out crying reason of the probability more than predetermined threshold.
The each crying reason for filtering out is shown on a terminal screen.
In one embodiment, indicating probability highest M crying reason and its probability, wherein M on a terminal screen
For integer set in advance.
In one embodiment, all crying reasons and its probability are shown on a terminal screen.
Second embodiment of the invention is related to a kind of automatic identifying method of baby crying reason.
Second embodiment is improved on the basis of first embodiment, is mainly theed improvement is that:According to week
The period that age and baby crying occur is modified to the probability of physiology, causes for pathological, can further improve baby crying former
Because of the accuracy analyzed.Specifically:
Preset the first corresponding relation of week old and crying concentrative time interval.In one embodiment, week set in advance
The corresponding relation of age and crying concentrative time interval includes:The corresponding crying concentrative time interval of 3 week old has at three sections, respectively 18~23 points
4~7 points and 9~11 points.The corresponding crying concentrative time interval of 6 week old is 15 points to 24 points and 0 point to 5 points.10 weeks corresponding
Crying concentrative time interval is 17 points to 23 points, etc..
The probability of the different crying reasons of gained is adjusted after step 102, it is specific as follows:
The week old of baby and crying time when acquisition is cryed.In one embodiment, week old can be by defeated in advance
The date of birth of the baby for entering is calculated.
First corresponding relation is searched according to acquired week old, corresponding crying concentrative time interval is obtained.
If the crying time falls in the crying concentrative time interval for searching gained, the probability of causes for pathological is reduced, otherwise increased
Plus the probability of causes for pathological.
In each embodiment of the application, increase the relative scale that the probability of certain reason refers to a variety of causes probability
Relation is made adjustment, and increases the relative scale of specific reasons, relative scale the reason for reduce other.For example, in an enforcement
In example, it is a total of 5 kinds it is default the reason for, the probability sum of 5 kinds of reasons is 100%, if being to increase the probability of causes for pathological,
On the one hand ratio of the causes for pathological in 100% total probability is increased, on the other hand, correspondingly (such as in the way of equal proportion)
The ratio of other 4 kinds of default reasons is reduced, the probability sum for making 5 kinds of reasons was all 100% before and after probability adjustment.
Hereafter execution step 103.
It is appreciated that above-mentioned technical proposal there can be the change in various ways and details when implementing, one is named
The example of a little changes.
In one embodiment, the corresponding relation of week old and crying concentrative time interval is according to the setting of the empirical value of expert.
In one embodiment, the corresponding relation of week old and crying concentrative time interval is obtained according to historical data statistics.
Historical data can be the data that user uploads, and have the cry time for occurring and the crying reason for confirming afterwards in these data.
The crying time of origin of non-causes for pathological can be counted, be found out the period concentrated of crying.
In one embodiment, the corresponding relation of week old and crying concentrative time interval is first to be built according to a kind of above-mentioned mode
It is vertical, then constantly changed according to the data that user newly uploads, there is the time and thing for occurring of crying in the data that user newly uploads
The crying reason for confirming afterwards.
Third embodiment of the invention is related to a kind of automatic identifying method of baby crying reason.
3rd embodiment is improved on the basis of first embodiment, is mainly theed improvement is that:With reference to the moon
In age, the probability of pain and other reasons is modified according to the situation of change of tone and rhythm, can further be improved to baby
Children cry is cried the accuracy of the analysis of causes.Specifically:
The probability of the different crying reasons of gained is adjusted between step 102 and step 103, it is specific as follows:
The tone of detection sob audio signal.
If testing result is the peak value that tone reaches frequency in the scheduled duration after starting of crying, and the monthly age of baby
Less than predetermined threshold, then increase the probability of pain cause.
Inventor find, the baby crying that pain causes on tone and rhythm at the beginning (as within first second) if it is fast
Speed has reached the peak value of frequency, and the baby crying that other reasonses such as starvation etc. cause generally just reaches peak in the stage casing cryed
Value is subsequently rapid to fall after rise.And simultaneously because after the increase at baby's monthly age, particularly 6 months, the rhythm side that baby entirely crys
Formula can all the more be equal to the crying that pain causes, and peak value is being reached at the very start.The crying sound cycle that crying stage casing refers to
The middle time point of (baby crying is repeated cyclically), for example, if the crying sound cycle is 10 seconds, the frequency after generation of crying
Rate gradually strengthens, subsequently the time in or so the 4-6 seconds reach peak value.
Four embodiment of the invention is related to a kind of automatic identifying method of baby crying reason.
4th embodiment is improved on the basis of first embodiment, is mainly theed improvement is that:According to baby
The closure situation of youngster's eyes is modified to the probability of pain cause, can further improve the standard to the baby crying analysis of causes
True property.
The flow process of the 4th embodiment is as shown in Figure 3.
In step 301, baby crying sound is recorded, while shooting the video of baby face.
Then into step 302, time-frequency characteristics are extracted from the sob audio signal, according to the time-frequency characteristics and training in advance
The grader of gained, obtains probability of the time-frequency characteristics corresponding to different crying reasons set in advance.
Then into step 303, graphical analysis is carried out to captured video, obtain the fine folding condition of baby eyes.
Then into step 304, judge during baby crying, the baby eyes fine total time in closure state is
It is no more than predetermined thresholdIf yes then enter step 305, otherwise into step 306.
In step 305, on the basis of the probability distribution of the different crying reasons of step 302 gained, pain is increased former
The probability of cause.
Within step 306, the crying reason of indicating probability highest at least two and these crying reasons on a terminal screen
Probability.
Inventor has found that, for crying caused by pain cause, baby's eyes in whole process almost remain tight
Close, wherein only at little gap, eyes are parted a little, while whole ocular high-pressure, brows are tightly knitted.And its
His reason such as feared during the baby crying caused with agitation, eyes then the overwhelming majority when keep open configuration or half
Open half.
Fifth embodiment of the invention is related to a kind of automatic identifying method of baby crying reason.
5th embodiment is improved on the basis of first embodiment, is mainly theed improvement is that:Statistics one
The crying time total in it, with reference to week old, the probability of physiology, causes for pathological is modified, can further be improved to baby
The accuracy of the crying analysis of causes.Specifically:
Preset week old and the second corresponding relation of the total time upper limit of crying for 24 hours.
It is further comprising the steps of between step 102 and step 103:
Count the baby it is nearest 24 hours in crying total time.
Second corresponding relation is inquired about according to the week old of the baby, the total time upper limit of crying for 24 hours is obtained.
The total time upper limit if the crying total time cryed more than this 24 hours, increases the probability of causes for pathological.
It is appreciated that above-mentioned technical proposal there can be the change in various ways and details when implementing, one is named
The example of a little changes.
In one embodiment, the crying by a sound pick-up outfit to a baby carries out the monitoring of 24 hours.The recording
Equipment can be smart mobile phone, have sound-recording function bracelet, pin ring, recording terminal of customization etc..If the sound pick-up outfit inspection
The sound with baby crying feature is measured, then records the beginning and ending time of crying, be uploaded to the shifting such as cloud server or mobile phone
Dynamic terminal, so as to mobile terminal count the baby it is nearest 24 hours in crying total time when can use these information.
In one embodiment, for the baby of the second week old, 24 hours cry total time the upper limit be 105 minutes, the 3rd
Week old, the total time upper limit of crying of 4th week age, 24 hours of the 5th week old gradually increase, and the 6th week old is 165 minutes, the 6th week
24 hours crying total time upper limits after age are gradually reduced.
In one embodiment, the total time upper limit of crying for 24 hours sets based on experience value.
In one embodiment, 24 hours cry total time the upper limit be according to the crying in 24 hours of more baby it is total when
Between and its historical data statistics of health status obtain.
In one embodiment, 24 hours crying total time upper limits can be according to the crying total time before a baby
And its health status carries out personalized adjustment.For example, 24 hour cry total time flat of the specific baby in the second week old
Average confirms to be in health status far below the corresponding 24 hours crying total time upper limits of the second week old, and the baby, then may be used
The corresponding 24 hours crying total time upper limits of each week old after to reduce the baby.Similarly, if the 24 of a specific baby
Hour crys total time higher than 24 hours of the corresponding week old total time upper limits of crying, then can suitably increase each after the baby
The corresponding 24 hours crying total time upper limits of week old.
Sixth embodiment of the invention is related to a kind of automatic identifying method of baby crying reason.
6th embodiment is improved on the basis of first embodiment, is mainly theed improvement is that:With reference to away from
The probability of hungry reason is adjusted from the time of last time lactation, can further be improved to the accurate of the baby crying analysis of causes
Property.Specifically:
It is further comprising the steps of between step 102 and step 103:
Obtain time interval of the crying time of origin away from last time time of nursing.
If the time interval is more than predetermined threshold, increase the probability of hungry reason.
It is appreciated that above-mentioned technical proposal there can be the change in various ways and details when implementing, one is named
The example of a little changes.
In one embodiment, on mobile terminals by pop-up dialogue box requirement user's output last time time of nursing.
In one embodiment, it is intended that after each lactation of baby, user can on mobile terminals record time of nursing, upload
To cloud server.When needing to obtain last time time of nursing, can obtain from cloud server.
In one embodiment, while baby crying sound is recorded, the video of baby face is shot, and to baby's face
The video in portion carries out graphical analysis, if Jing graphical analyses find that baby presents the reflex activity of search, increases hungry former
The probability of cause.
In one embodiment, propose that user observes and be input into the reflection whether baby presents search on mobile terminals
The information of activity, and the video of typical baby's search activity is played on the mobile terminal, to help unfamiliar use
Family understanding is the reflex activity what baby searches.If user input baby presents the information of the reflex activity of search,
Increase the probability of hungry reason.
In one embodiment, the reflex activity of search and the time apart from last time lactation can be used in combination with, to enter
One step increases the accuracy for judging.
Above-mentioned second to the 6th embodiment is all on the basis of the probability distribution of step 102 gained, according to extra
Information carries out the adjustment of certain mode to probability distribution.The mode of these adjustment can be used alone, it is also possible to combine
(will be in the technical scheme of the second to the 6th embodiment various combine) be used, so that the accuracy for judging enters one
Step is lifted.
Seventh embodiment of the invention is related to a kind of automatic recognition system of baby crying reason.Fig. 4 is the baby crying
The structural representation of the automatic recognition system of reason.The automatic recognition system of the baby crying reason includes:
Recording elements, for recording baby crying sound, obtain sob audio signal.
Analytic unit, for extracting time-frequency characteristics from the sob audio signal, according to the time-frequency characteristics and training in advance institute
The grader for obtaining, obtains probability of the time-frequency characteristics corresponding to different crying reasons set in advance.
Display unit, for the crying reason of indicating probability highest at least two on a terminal screen and these crying reasons
Probability.In a preference, display unit in the way of pie chart the crying reason of indicating probability highest at least two and this
The probability of a little crying reasons.
First embodiment is the method embodiment corresponding with present embodiment, and present embodiment can be implemented with first
Mode is worked in coordination enforcement.The relevant technical details mentioned in first embodiment are still effective in the present embodiment, in order to
Reduce and repeat, repeat no more here.Correspondingly, the relevant technical details mentioned in present embodiment are also applicable in the first enforcement
In mode.
Eighth embodiment of the invention is related to a kind of automatic recognition system of baby crying reason.
8th embodiment is improved on the basis of the 7th embodiment, is mainly theed improvement is that according to week old
The period occurred with baby crying is modified to the probability of physiology, causes for pathological, can further improve baby crying reason
The accuracy of analysis.Specifically, increased with lower unit relative to the 7th embodiment:
First memory cell, for storing the first corresponding relation of week old set in advance and crying concentrative time interval.
First information acquiring unit, the week old of baby and crying time when crying for obtaining.
First query unit, for searching the first corresponding relation according to acquired week old, obtains corresponding crying and concentrates
Period.
First adjustment unit, for judging whether the crying time falls in the crying concentrative time interval for searching gained, if it is,
Then on the Probability Basis of the different crying reasons of analytic unit output, the probability of causes for pathological is reduced, otherwise increase pathology former
The probability of cause.
Second embodiment is the method embodiment corresponding with present embodiment, and present embodiment can be implemented with second
Mode is worked in coordination enforcement.The relevant technical details mentioned in second embodiment are still effective in the present embodiment, in order to
Reduce and repeat, repeat no more here.Correspondingly, the relevant technical details mentioned in present embodiment are also applicable in the second enforcement
In mode.
Ninth embodiment of the invention is related to a kind of automatic recognition system of baby crying reason.
9th embodiment is improved on the basis of the 7th embodiment, is mainly theed improvement is that and is combined the moon
In age, the probability of pain and other reasons is modified according to the situation of change of tone and rhythm, can further be improved to baby
Children cry is cried the accuracy of the analysis of causes.Specifically, increased with lower unit on the basis of the 7th embodiment:
Tone detection unit, for detecting the tone of sob audio signal.
Second adjustment unit, for judging whether testing result is that tone reaches frequency in the scheduled duration after starting of crying
The peak value of rate, and the monthly age of baby is less than predetermined threshold, if it is, the probability of the different crying reasons in analytic unit output
On the basis of increase pain cause probability.
3rd embodiment is the method embodiment corresponding with present embodiment, and present embodiment can be implemented with the 3rd
Mode is worked in coordination enforcement.The relevant technical details mentioned in 3rd embodiment are still effective in the present embodiment, in order to
Reduce and repeat, repeat no more here.Correspondingly, the relevant technical details mentioned in present embodiment are also applicable in the 3rd enforcement
In mode.
Tenth embodiment of the invention is related to a kind of automatic recognition system of baby crying reason.
Tenth embodiment is improved on the basis of the 7th embodiment, is mainly theed improvement is that:According to baby
The closure situation of youngster's eyes is modified to the probability of pain cause, can further improve the standard to the baby crying analysis of causes
True property.Specifically, increased with lower unit relative to the 7th embodiment:
Video capture unit, for while baby crying sound is recorded, shooting the video of baby face.
Eye analytic unit, for carrying out graphical analysis to the video, obtains the fine folding condition of baby eyes.
3rd adjustment unit, for judge during baby crying whether baby eyes it is fine in closure state it is total when
Between be more than predetermined threshold, if it is, analytic unit output different crying reasons Probability Basis on increase pain cause
Probability.
4th embodiment is the method embodiment corresponding with present embodiment, and present embodiment can be implemented with the 4th
Mode is worked in coordination enforcement.The relevant technical details mentioned in 4th embodiment are still effective in the present embodiment, in order to
Reduce and repeat, repeat no more here.Correspondingly, the relevant technical details mentioned in present embodiment are also applicable in the 4th enforcement
In mode.
Eleventh embodiment of the invention is related to a kind of automatic recognition system of baby crying reason.
11st embodiment is improved on the basis of the 7th embodiment, is mainly theed improvement is that:Statistics
The crying time total in one day, with reference to week old, the probability of physiology, causes for pathological is modified, can further be improved to baby
Children cry is cried the accuracy of the analysis of causes.Specifically, relative to the 7th embodiment, also add with lower unit:
Second memory cell, the second correspondence for storing week old set in advance and 24 hours crying total time upper limits is closed
System.
Crying time statistic unit, for count the baby it is nearest 24 hours in crying total time.
Second query unit, when crying total for according to the week old of the baby the second corresponding relation of inquiry, obtaining 24 hours
Between the upper limit.
4th adjustment unit, for judging the total time upper limit of whether crying more than this 24 hours crying total time, if
It is then to increase the probability of causes for pathological on the Probability Basis of the different crying reasons of analytic unit output.
5th embodiment is the method embodiment corresponding with present embodiment, and present embodiment can be implemented with the 5th
Mode is worked in coordination enforcement.The relevant technical details mentioned in 5th embodiment are still effective in the present embodiment, in order to
Reduce and repeat, repeat no more here.Correspondingly, the relevant technical details mentioned in present embodiment are also applicable in the 5th enforcement
In mode.
Twelveth embodiment of the invention is related to a kind of automatic recognition system of baby crying reason.
12nd embodiment is improved on the basis of the 7th embodiment, is mainly theed improvement is that:With reference to
The probability of hungry reason is adjusted apart from the time of last time lactation, can further be improved to the accurate of the baby crying analysis of causes
Property.Specifically, relative to the 7th embodiment, also add with lower unit:
Lactation information acquisition unit, for obtaining time interval of the crying time of origin away from last time time of nursing.
5th adjustment unit, for whether judging the time interval more than predetermined threshold, if it is, defeated in analytic unit
Increase the probability of hungry reason on the Probability Basis of the different crying reasons for going out.
6th embodiment is the method embodiment corresponding with present embodiment, and present embodiment can be implemented with the 6th
Mode is worked in coordination enforcement.The relevant technical details mentioned in 6th embodiment are still effective in the present embodiment, in order to
Reduce and repeat, repeat no more here.Correspondingly, the relevant technical details mentioned in present embodiment are also applicable in the 6th enforcement
In mode.
Above-mentioned 8th to the 12nd embodiment is all the probability distribution obtained by the analytic unit in the 7th embodiment
On the basis of, the adjustment of certain mode is carried out to probability distribution according to extra information.The mode of these adjustment can individually make
With, it is also possible to the use that combines (will be in the technical scheme of the 8th to the 12nd embodiment various combine), from
And the accuracy of judgement is further lifted.
It should be noted that each method embodiment of the present invention can be realized in modes such as software, hardware, firmwares.
No matter the present invention is to realize that instruction code may be stored in any kind of computer with software, hardware or firmware mode
In addressable memory (such as it is permanent or revisable, it is volatibility or non-volatile, it is solid-state or non-solid
State, fixed or removable medium etc.).Equally, memory may, for example, be programmable logic array
(Programmable Array Logic, referred to as " PAL "), random access memory (Random Access Memory, referred to as
" RAM "), programmable read only memory (Programmable Read Only Memory, referred to as " PROM "), read-only storage
(Read-Only Memory, referred to as " ROM "), Electrically Erasable Read Only Memory (Electrically Erasable
Programmable ROM, referred to as " EEPROM "), disk, CD, digital versatile disc (Digital Versatile Disc,
Referred to as " DVD ") etc..
It should be noted that each unit mentioned in each equipment embodiment of the invention is all logical block, physically,
One logical block can be a part for a physical location, or a physical location, can be with multiple physics
The combination of unit realizes, these logical blocks Physical realizations of itself is not most important, and these logical blocks institutes are real
The combination of existing function is only the key of the technical problem for solving proposed by the invention.Additionally, the innovation in order to project the present invention
Part, the above-mentioned each equipment embodiment of the present invention is not less close by the technical problem relation proposed by the invention with solution
Unit introduce, this is not intended that the said equipment embodiment does not have other units.
It should be noted that in claims and specification of this patent, such as first and second or the like pass
It is that term is used merely to make a distinction an entity or operation and another entity or operate, and not necessarily requires or secretly
Show and there is any this actual relation or order between these entities or operation.And, term " including ", "comprising" or
Its any other variant is intended to including for nonexcludability so that process, method, article including a series of key elements or
Person's equipment not only includes those key elements, but also including other key elements being not expressly set out, or also include for this mistake
The intrinsic key element of journey, method, article or equipment.In the absence of more restrictions, limited by sentence " including "
Key element, it is not excluded that also there is other identical element in including the process of the key element, method, article or equipment.
In claims and specification of this patent, if it is mentioned that perform certain behavior according to certain key element, then referring to will according at least to this
Element performs the meaning of the behavior, which includes two kinds of situations:According only to the key element perform behavior and according to the key element and its
Its key element performs the behavior.
Although by referring to some of the preferred embodiment of the invention, being shown and described to the present invention,
It will be understood by those skilled in the art that can in the form and details to it, various changes can be made, without departing from this
Bright spirit and scope.
Claims (10)
1. a kind of automatic identifying method of baby crying reason, it is characterised in that comprise the following steps:
Baby crying sound is recorded, sob audio signal is obtained;
Time-frequency characteristics are extracted from the sob audio signal, the grader according to obtained by the time-frequency characteristics and training in advance is somebody's turn to do
Probability of the time-frequency characteristics corresponding to different crying reasons set in advance;
The probability of the crying reason of indicating probability highest at least two and these crying reasons on a terminal screen.
2. the automatic identifying method of baby crying reason according to claim 1, it is characterised in that described " in end panel
In the step of probability of the crying reason of indicating probability highest at least two and these crying reasons on curtain ", in the way of pie chart
The probability of the crying reason of indicating probability highest at least two and these crying reasons.
3. the automatic identifying method of baby crying reason according to claim 1, it is characterised in that described set in advance
Different crying reasons include one of following reason or its any combination:
Starvation, sleepy is felt, uncomfortable, wet diaper.
4. the automatic identifying method of baby crying reason according to claim 1, it is characterised in that described " in end panel
The step of probability of the crying reason of indicating probability highest at least two and these crying reasons on curtain ", includes following sub-step:
Filter out crying reason of the probability more than predetermined threshold;
The each crying reason for filtering out is shown on a terminal screen.
5. the automatic identifying method of baby crying reason according to claim 3, it is characterised in that preset week old and
First corresponding relation of crying concentrative time interval;
Also wrap after the step of described " obtaining probability of the time-frequency characteristics corresponding to different crying reasons set in advance "
Include following steps:
The week old of baby and crying time when acquisition is cryed;
First corresponding relation is searched according to acquired week old, corresponding crying concentrative time interval is obtained;
If the crying time falls in the crying concentrative time interval for searching gained, the probability of causes for pathological is reduced, otherwise increased
Plus the probability of causes for pathological.
6. the automatic identifying method of baby crying reason according to claim 3, it is characterised in that " obtain institute described
State time-frequency characteristics corresponding to different crying reasons set in advance probability " the step of after it is further comprising the steps of:
Detect the tone of the sob audio signal;
If testing result is the peak value that tone reaches frequency in the scheduled duration after starting of crying, and the monthly age of baby is less than
Predetermined threshold, then increase the probability of pain cause.
7. the automatic identifying method of baby crying reason according to claim 3, it is characterised in that also including following step
Suddenly:
While baby crying sound is recorded, the video of baby face is shot;
Graphical analysis is carried out to the video, the fine folding condition of baby eyes is obtained;
If during baby crying, the baby eyes fine total time in closure state is more than predetermined threshold, then increase pain
The probability of pain reason.
8. the automatic identifying method of baby crying reason according to claim 3, it is characterised in that preset week old and
Second corresponding relation of the total time upper limit of crying for 24 hours;
Also wrap after the step of described " obtaining probability of the time-frequency characteristics corresponding to different crying reasons set in advance "
Include following steps:
Count the baby it is nearest 24 hours in crying total time;
Second corresponding relation is inquired about according to the week old of the baby, the total time upper limit of crying for 24 hours is obtained;
The total time upper limit if the crying total time cryed more than this 24 hours, increases the probability of causes for pathological.
9. the automatic identifying method of baby crying reason according to claim 3, it is characterised in that " obtain institute described
State time-frequency characteristics corresponding to different crying reasons set in advance probability " the step of after it is further comprising the steps of:
Obtain time interval of the crying time of origin away from last time time of nursing;
If the time interval is more than predetermined threshold, increase the probability of hungry reason.
10. a kind of automatic recognition system of baby crying reason, it is characterised in that include:
Recording elements, for recording baby crying sound, obtain sob audio signal;
Analytic unit, for extracting time-frequency characteristics from the sob audio signal, according to obtained by the time-frequency characteristics and training in advance
Grader, obtains probability of the time-frequency characteristics corresponding to different crying reasons set in advance;
Display unit, it is general with these crying reasons for the crying reason of indicating probability highest at least two on a terminal screen
Rate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611014119.XA CN106653059B (en) | 2016-11-17 | 2016-11-17 | Automatic identification method and system for infant crying reason |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611014119.XA CN106653059B (en) | 2016-11-17 | 2016-11-17 | Automatic identification method and system for infant crying reason |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106653059A true CN106653059A (en) | 2017-05-10 |
CN106653059B CN106653059B (en) | 2020-06-30 |
Family
ID=58808536
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611014119.XA Active CN106653059B (en) | 2016-11-17 | 2016-11-17 | Automatic identification method and system for infant crying reason |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106653059B (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107393556A (en) * | 2017-07-17 | 2017-11-24 | 京东方科技集团股份有限公司 | A kind of method and device for realizing audio frequency process |
CN107564541A (en) * | 2017-09-04 | 2018-01-09 | 南方医科大学南方医院 | A kind of Portable baby crying sound identifier and its recognition methods |
CN107657965A (en) * | 2017-09-22 | 2018-02-02 | 许灿丽 | Vagitus identifier and knowledge method for distinguishing |
CN107705786A (en) * | 2017-09-27 | 2018-02-16 | 努比亚技术有限公司 | A kind of method of speech processing, device and computer-readable recording medium |
CN107767874A (en) * | 2017-09-04 | 2018-03-06 | 南方医科大学南方医院 | A kind of baby crying sound identification reminding method and system |
CN108536996A (en) * | 2018-03-01 | 2018-09-14 | 北京小米移动软件有限公司 | Method, apparatus, storage medium and intelligent baby bed are slept in automatic roars of laughter |
CN108806723A (en) * | 2018-05-21 | 2018-11-13 | 深圳市沃特沃德股份有限公司 | Baby's audio recognition method and device |
CN109509484A (en) * | 2018-12-25 | 2019-03-22 | 科大讯飞股份有限公司 | A kind of prediction technique and device of baby crying reason |
CN111276159A (en) * | 2018-12-05 | 2020-06-12 | 阿里健康信息技术有限公司 | Infant pronunciation analysis method and server |
CN111951830A (en) * | 2020-06-30 | 2020-11-17 | 苏州航天***工程有限公司 | Method, server, mobile phone, external equipment and system for identifying baby cry |
CN112750467A (en) * | 2021-01-19 | 2021-05-04 | 珠海格力电器股份有限公司 | Infant cry analysis method, model training method, device and electronic equipment |
CN113035229A (en) * | 2021-04-23 | 2021-06-25 | 西安马克医疗科技有限公司 | Infant watching method based on infant body characteristics |
CN113270115A (en) * | 2020-02-17 | 2021-08-17 | 广东美的制冷设备有限公司 | Infant monitoring device, infant monitoring method thereof, control device and storage medium |
EP3940698A1 (en) | 2020-07-13 | 2022-01-19 | Zoundream AG | A computer-implemented method of providing data for an automated baby cry assessment |
TWI766673B (en) * | 2021-05-05 | 2022-06-01 | 量子音樂股份有限公司 | Analysis method and analysis device of infant crying |
WO2022262281A1 (en) * | 2021-06-15 | 2022-12-22 | 青岛海尔空调器有限总公司 | Control method and apparatus for air conditioner, and air conditioner |
TWI815019B (en) * | 2019-10-04 | 2023-09-11 | 仁寶電腦工業股份有限公司 | System, method and storage medium for providing information |
CN111951830B (en) * | 2020-06-30 | 2024-06-07 | 苏州航天***工程有限公司 | Identification method, server, mobile phone, external equipment and system for baby crying |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20070087296A (en) * | 2006-02-23 | 2007-08-28 | 조동욱 | Crying analysis technique for diagnosis of colic |
CN101807396A (en) * | 2010-04-02 | 2010-08-18 | 陕西师范大学 | Device and method for automatically recording crying of babies |
JP2011154130A (en) * | 2010-01-26 | 2011-08-11 | Kanazawa Univ | Voice identification device and voice identification system using the same |
CN103280220A (en) * | 2013-04-25 | 2013-09-04 | 北京大学深圳研究生院 | Real-time recognition method for baby cry |
CN105719663A (en) * | 2014-12-23 | 2016-06-29 | 郑载孝 | Baby cry analyzing method |
-
2016
- 2016-11-17 CN CN201611014119.XA patent/CN106653059B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20070087296A (en) * | 2006-02-23 | 2007-08-28 | 조동욱 | Crying analysis technique for diagnosis of colic |
JP2011154130A (en) * | 2010-01-26 | 2011-08-11 | Kanazawa Univ | Voice identification device and voice identification system using the same |
CN101807396A (en) * | 2010-04-02 | 2010-08-18 | 陕西师范大学 | Device and method for automatically recording crying of babies |
CN103280220A (en) * | 2013-04-25 | 2013-09-04 | 北京大学深圳研究生院 | Real-time recognition method for baby cry |
CN105719663A (en) * | 2014-12-23 | 2016-06-29 | 郑载孝 | Baby cry analyzing method |
Non-Patent Citations (2)
Title |
---|
胡祖斌等: "《儿童启蒙丛书 0-1岁宝宝养育大全》", 30 September 2012, 湖北科学技术出版社 * |
葛晓利: "应用啼哭信号分析方法评估婴儿术后疼痛的研究_葛晓利", 《万方学位论文》 * |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107393556A (en) * | 2017-07-17 | 2017-11-24 | 京东方科技集团股份有限公司 | A kind of method and device for realizing audio frequency process |
CN107767874A (en) * | 2017-09-04 | 2018-03-06 | 南方医科大学南方医院 | A kind of baby crying sound identification reminding method and system |
CN107564541A (en) * | 2017-09-04 | 2018-01-09 | 南方医科大学南方医院 | A kind of Portable baby crying sound identifier and its recognition methods |
CN107767874B (en) * | 2017-09-04 | 2020-08-28 | 南方医科大学南方医院 | Infant crying recognition prompting method and system |
CN107564541B (en) * | 2017-09-04 | 2018-11-02 | 南方医科大学南方医院 | A kind of Portable baby crying sound identifier and its recognition methods |
CN107657965A (en) * | 2017-09-22 | 2018-02-02 | 许灿丽 | Vagitus identifier and knowledge method for distinguishing |
CN107705786A (en) * | 2017-09-27 | 2018-02-16 | 努比亚技术有限公司 | A kind of method of speech processing, device and computer-readable recording medium |
CN108536996A (en) * | 2018-03-01 | 2018-09-14 | 北京小米移动软件有限公司 | Method, apparatus, storage medium and intelligent baby bed are slept in automatic roars of laughter |
CN108536996B (en) * | 2018-03-01 | 2020-07-03 | 北京小米移动软件有限公司 | Automatic sleep-soothing method, device, storage medium and intelligent baby crib |
CN108806723A (en) * | 2018-05-21 | 2018-11-13 | 深圳市沃特沃德股份有限公司 | Baby's audio recognition method and device |
CN108806723B (en) * | 2018-05-21 | 2021-08-17 | 深圳市沃特沃德股份有限公司 | Baby voice recognition method and device |
CN111276159A (en) * | 2018-12-05 | 2020-06-12 | 阿里健康信息技术有限公司 | Infant pronunciation analysis method and server |
CN109509484A (en) * | 2018-12-25 | 2019-03-22 | 科大讯飞股份有限公司 | A kind of prediction technique and device of baby crying reason |
TWI815019B (en) * | 2019-10-04 | 2023-09-11 | 仁寶電腦工業股份有限公司 | System, method and storage medium for providing information |
CN113270115A (en) * | 2020-02-17 | 2021-08-17 | 广东美的制冷设备有限公司 | Infant monitoring device, infant monitoring method thereof, control device and storage medium |
CN113270115B (en) * | 2020-02-17 | 2023-04-11 | 广东美的制冷设备有限公司 | Infant monitoring device, infant monitoring method thereof, control device and storage medium |
CN111951830A (en) * | 2020-06-30 | 2020-11-17 | 苏州航天***工程有限公司 | Method, server, mobile phone, external equipment and system for identifying baby cry |
CN111951830B (en) * | 2020-06-30 | 2024-06-07 | 苏州航天***工程有限公司 | Identification method, server, mobile phone, external equipment and system for baby crying |
EP3940698A1 (en) | 2020-07-13 | 2022-01-19 | Zoundream AG | A computer-implemented method of providing data for an automated baby cry assessment |
WO2022012777A1 (en) | 2020-07-13 | 2022-01-20 | Zoundream Ag | A computer-implemented method of providing data for an automated baby cry assessment |
CN112750467A (en) * | 2021-01-19 | 2021-05-04 | 珠海格力电器股份有限公司 | Infant cry analysis method, model training method, device and electronic equipment |
CN113035229A (en) * | 2021-04-23 | 2021-06-25 | 西安马克医疗科技有限公司 | Infant watching method based on infant body characteristics |
TWI766673B (en) * | 2021-05-05 | 2022-06-01 | 量子音樂股份有限公司 | Analysis method and analysis device of infant crying |
WO2022262281A1 (en) * | 2021-06-15 | 2022-12-22 | 青岛海尔空调器有限总公司 | Control method and apparatus for air conditioner, and air conditioner |
Also Published As
Publication number | Publication date |
---|---|
CN106653059B (en) | 2020-06-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106653059A (en) | Automatic identification method and system for infant crying cause | |
CN104065928B (en) | A kind of behavior pattern statistic device and method | |
CN106653001A (en) | Baby crying identifying method and system | |
CN107133629B (en) | Picture classification method and device and mobile terminal | |
CN105030199A (en) | Sleep monitoring method and device | |
CN107767874B (en) | Infant crying recognition prompting method and system | |
TW201642126A (en) | Method for evaluating user's use of a portable mobile device | |
CN110111815A (en) | Animal anomaly sound monitoring method and device, storage medium, electronic equipment | |
CN116386277A (en) | Fatigue driving detection method and device, electronic equipment and medium | |
JP2011154130A (en) | Voice identification device and voice identification system using the same | |
CN112674771A (en) | Depression crowd identification method and device based on image fixation difference | |
CN110807117A (en) | User relationship prediction method and device and computer readable storage medium | |
CN102473409A (en) | Anchor model adaptation device, integrated circuit, AV (audio video) device, online self-adaptation method, and program therefor | |
CN114708964A (en) | Vertigo auxiliary analysis statistical method and system based on intelligent feature classification | |
CN114238033A (en) | Board card running state early warning method, device, equipment and readable storage medium | |
JPWO2020152953A1 (en) | Discriminator, cell mass discrimination method, and computer program | |
CN115223232A (en) | Eye health comprehensive management system | |
CN111785300B (en) | Crying detection method and system based on deep neural network | |
CN114463671A (en) | User personality identification method based on video data | |
CN115590477B (en) | Sleep staging method and device based on self-supervision, electronic equipment and storage medium | |
CN117297540B (en) | Visual fatigue monitoring method and system based on intelligent glasses | |
CN110021147A (en) | A kind of method for detecting fatigue driving demarcated based on machine learning and numerical value | |
CN117523213B (en) | Noise tag identification method based on meta denoising and negative learning | |
CN108447565A (en) | A kind of small for gestational age infant disease forecasting method based on improvement noise reduction autocoder | |
US20230200697A1 (en) | Automatic evolution method for brainwave database and automatic evolving system for detecting brainwave |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210125 Address after: 200092 Shanghai city Yangpu District Kongjiang Road No. 1665 Patentee after: Xinhua Hospital Affiliated to Shanghai Jiaotong University School of Medicine Address before: Room 1202, building 33, 800 Jinxiu Road, Pudong New Area, Shanghai 200135 Patentee before: Shen Xiaoming |
|
TR01 | Transfer of patent right |