CN111768863A - Artificial intelligence-based infant development monitoring system and method - Google Patents
Artificial intelligence-based infant development monitoring system and method Download PDFInfo
- Publication number
- CN111768863A CN111768863A CN202010594585.XA CN202010594585A CN111768863A CN 111768863 A CN111768863 A CN 111768863A CN 202010594585 A CN202010594585 A CN 202010594585A CN 111768863 A CN111768863 A CN 111768863A
- Authority
- CN
- China
- Prior art keywords
- infant
- data
- development
- sleep
- motion
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 35
- 230000008131 children development Effects 0.000 title claims abstract description 25
- 230000033001 locomotion Effects 0.000 claims abstract description 61
- 238000011161 development Methods 0.000 claims abstract description 38
- 230000018109 developmental process Effects 0.000 claims abstract description 38
- 235000016709 nutrition Nutrition 0.000 claims abstract description 21
- 230000035764 nutrition Effects 0.000 claims abstract description 21
- 238000001514 detection method Methods 0.000 claims abstract description 14
- 238000011156 evaluation Methods 0.000 claims abstract description 13
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 235000005911 diet Nutrition 0.000 claims description 14
- 230000037213 diet Effects 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 7
- 230000006399 behavior Effects 0.000 claims description 6
- 230000000241 respiratory effect Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 5
- 230000000386 athletic effect Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000007635 classification algorithm Methods 0.000 claims description 4
- 238000010224 classification analysis Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 150000001720 carbohydrates Chemical class 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000003930 cognitive ability Effects 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 claims description 3
- 230000006872 improvement Effects 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 claims description 3
- 102000004169 proteins and genes Human genes 0.000 claims description 3
- 108090000623 proteins and genes Proteins 0.000 claims description 3
- 238000011002 quantification Methods 0.000 claims description 3
- 229940088594 vitamin Drugs 0.000 claims description 3
- 229930003231 vitamin Natural products 0.000 claims description 3
- 235000013343 vitamin Nutrition 0.000 claims description 3
- 239000011782 vitamin Substances 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 2
- 230000003203 everyday effect Effects 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 claims description 2
- 238000013528 artificial neural network Methods 0.000 abstract description 3
- 239000000463 material Substances 0.000 abstract description 2
- 230000000474 nursing effect Effects 0.000 abstract 1
- 238000012706 support-vector machine Methods 0.000 description 7
- 230000036541 health Effects 0.000 description 4
- 206010012559 Developmental delay Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 239000000306 component Substances 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 235000012041 food component Nutrition 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 235000019577 caloric intake Nutrition 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000005428 food component Substances 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000035935 pregnancy Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011165 process development Methods 0.000 description 1
- 230000036578 sleeping time Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/60—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to nutrition control, e.g. diets
Abstract
The invention discloses an infant development monitoring system and method based on artificial intelligence, wherein the system comprises a development evaluation module, an infant limb movement ability identification module, a sleep monitoring module, a nutrition detection module and a doctor's advice tracking module; the infant limb motion capability identification module is used for acquiring a motion picture or video of an infant and capturing and extracting feature points in the motion picture or video by a self-adaptive least square method; forming a motion track of the characteristic points through linear prediction and iterative adjustment, comparing the motion track with the motion track of the characteristic points in the standard motion image, and observing the fitting degree of the two tracks; according to the invention, artificial intelligence is applied to intelligent reminding of image recognition and medical advice tracking in infant motion capture and a neural network analysis method for food nutrition analysis, so that the growth of children is comprehensively monitored and personalized and professional guidance is given, the investment of manpower and material resources is reduced, and the nursing cost is reduced.
Description
Technical Field
The invention relates to the technical field of infant growth monitoring, in particular to an infant development monitoring system and method based on artificial intelligence.
Background
In recent years, along with the progress of artificial intelligence technology, intellectualization has become a development trend of the electronic information industry, and more intelligent products emerge in the living field and enter the home. With the increasing competition of China society, the requirements of parents on the health and education of children are higher and higher, and the fact that children are not allowed to fall off the starting line is a common consensus of parents in China, so that the parents pay attention to the aspects of nutrition, health, development, education and the like of the children from the pregnancy stage.
Currently, artificial intelligence technology is not well applied to infant development monitoring based on artificial intelligence in the field. The existing infant development monitoring device based on artificial intelligence has the defects that under the condition that medical resources are in short supply, a large amount of manpower is still needed to intervene, so that the infant care cost is high, and the whole-process development monitoring and health care suggestion of infants, infants and children cannot be realized.
Therefore, there is a need in the industry to design a device or method that can fully utilize artificial intelligence to monitor the development and growth of infants and provide personalized guidance.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides an infant development monitoring system and method based on artificial intelligence, which can monitor the development and growth of infants and give personalized guidance.
The purpose of the invention is realized by the following technical scheme:
an infant development monitoring system based on artificial intelligence, comprising: the system comprises a development evaluation module, an infant limb movement ability identification module, a sleep monitoring module, a nutrition detection module and a doctor's advice tracking module;
the development evaluation module is used for receiving the child personal information input by the user, performing answer tests aiming at the infant ability indexes of different ages in months according to the child personal information, obtaining ability development scores according to the answer conditions of the user by combining algorithms and mathematical models containing different deep learning structures, and further giving an ability development evaluation report according to the scores;
the infant limb motion capability identification module is used for acquiring a motion picture or video of an infant, identifying the motion picture or video based on an artificial intelligence technology, and capturing and extracting feature points in the motion picture or video by using a self-adaptive least square method; forming a motion track of the characteristic points through linear prediction and iterative adjustment, comparing the motion track with the motion track of the characteristic points in the standard motion image, and observing the fitting degree of the two tracks;
the sleep monitoring module is used for acquiring heart rate data and respiratory data of the infant, fitting the heart rate data and the respiratory data with a sleep condition standard curve of a corresponding age group and judging the sleep state of the infant;
the nutrition detection system module is used for acquiring food images of infants, carrying out convolution processing on the food images based on a food image database established during early-stage image recognition model training and a computer vision model obtained based on convolutional neural network multi-layer training, fitting the convolved results with the food image recognition model obtained through early-stage training again, classifying the obtained features by using a classifier, outputting the classified results to a user, and finally obtaining a food nutrition monitoring result;
the medical advice tracking module is used for acquiring medical advice of a doctor signing a contract in a hospital and giving attention every day.
Preferably, the personal information includes: age, height, weight, medical history; the ability indicators include fine movement, gross movement, social ability, language function, cognitive ability.
Preferably, the infant limb movement capability identification module is further configured to acquire a moving picture or video of an infant, and capture and extract limb actions and behavior behaviors in the moving picture or video by using a self-adaptive least square method; capturing and repairing the motion data of the infant by a method for recovering lost feature points, forming the motion trail of the feature points of the user by a linear prediction and iterative adjustment method, comparing the motion trail with the motion trail of the feature points in a standard motion image, and observing the fitting degree of the two trails; the higher the fitting degree is, the more excellent the child athletic ability is, the guidance for shooting again is given to the data with extremely poor fitting conditions, and corresponding training courses are recommended to the users who still have poor performance after multiple tests.
Preferably, the infant sleep detection pillow detects infant sleep data, and the infrared sleep detector monitors heart rate to acquire heart rate data.
Preferably, the sleep monitoring module is further configured to automatically play the cradle song to help sleep well when the sleep condition of the infant is determined to be unstable; when the multiple times of sleep are not stable, an alarm is given and improvement suggestions are provided for parents, if the two schemes can not solve the problems, the sleep data of the infant are transmitted to a contracting doctor of the cooperative hospital, the doctor gives online guidance according to the data, and the doctor in the hospital can be reserved to carry out offline diagnosis when the problems can not be solved.
Preferably, the nutrition detection system module is further configured to obtain a picture of food for the infant, visually analyze the picture of food, determine the depth of each pixel in the picture by using a pattern recognition technology, connect the picture of specific food with a database, determine the food for the infant, perform nutrition analysis on the food on the basis of recognizing the food, provide food caloric information, and inform a user of the content of protein, fat, carbohydrate, vitamins and other components in the food; and giving personalized diet guidance by combining the past data and the basic situation of the infant.
An infant development monitoring method based on artificial intelligence, comprising:
s1, acquiring body data of the infant; the body data includes: height data, weight data, data relating to sleep conditions, data relating to diet, position data, data relating to intellectual development;
s2, processing the body data;
s3, fitting the body data with a standard curve of an index corresponding to the corresponding age, judging whether the body data is in a preset safety range, and obtaining a monitoring result and a corresponding suggestion; inserting the body data into a standard curve of a corresponding age corresponding index by using a Lagrange interpolation method, and continuously correcting the standard curve to finally obtain a growth curve of the user; comparing the user data with the generated user growth curve, and giving corresponding prediction according to the curve data;
and S4, transmitting the monitoring result, the corresponding suggestion and the corresponding prediction to the user terminal.
Preferably, the standard curve is a curve of different indexes of different ages which is trained and fitted in advance according to a previous data set, and the standard curve forming includes the following steps:
the method comprises the steps of acquiring infant growth and development data in advance, screening frontier medical indexes capable of evaluating the infant growth and development, carrying out combined calculation on the acquired infant growth and development data, carrying out frontier medical index quantification processing, and screening and fitting the data to obtain an age-height development standard curve, an age-weight development standard curve and an age-sleep standard curve.
Preferably, if the physical data is data related to a sleep condition, S3 includes: the server compares the age, the physical state and the data related to the sleep condition of the person under guardianship with the physical state sleep quantity standard curve of the corresponding age to further obtain a training suggestion and a sleep quantity range.
Preferably, step S2 includes: cleaning the body data, deleting blank data and planning partial data; and carrying out classification analysis on the body data by using an SVM classification algorithm.
Compared with the prior art, the invention has the following advantages:
the invention discloses an infant development monitoring system based on artificial intelligence, which comprises: the system comprises a development evaluation module, an infant limb movement ability identification module, a sleep monitoring module, a nutrition detection module and a doctor's advice tracking module; the artificial intelligence is mainly applied to image recognition in infant motion capture, intelligent reminding of medical advice tracking and a neural network analysis method for food nutrition analysis, so that the growth of the infant is comprehensively monitored, personalized and professional guidance is given, the investment of manpower and material resources is reduced, and the infant care cost is reduced.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a schematic flow chart of an infant development monitoring method based on artificial intelligence according to this embodiment.
FIG. 2 is a schematic flowchart illustrating the human motion in the image capturing and extracting based on artificial intelligence according to the embodiment.
Fig. 3 is a schematic flowchart of food image analysis of the deep neural network method based on deep learning according to the present embodiment.
Fig. 4 is a screenshot of the growth test of the present embodiment.
Fig. 5 is a mobile phone screenshot of the height assistant in this embodiment.
Fig. 6 is a mobile phone screenshot of the growing situation question answering according to the embodiment.
Fig. 7 is a mobile phone screenshot of the growth evaluation report according to the embodiment.
Fig. 8 is a screenshot of the nutrition assistant in this embodiment.
Fig. 9 is a mobile phone screenshot of the order tracking according to the embodiment.
Detailed Description
The invention is further illustrated by the following figures and examples.
Referring to fig. 1, an infant development monitoring method based on artificial intelligence includes:
and S1, acquiring the body data of the infant based on the artificial intelligence technology and in combination with related equipment.
Acquiring body data of a child; the body data includes: height data, weight data, data relating to sleep conditions, data relating to diet, position data, data relating to intellectual development;
s2, processing the body data; and (3) performing data understanding, removing irrelevant data, selecting proper data, combining data, discretizing the data and the like by using a deep learning method in the field of artificial intelligence. Specifically, step S2 includes: cleaning the body data, deleting blank data and planning partial data; and carrying out classification analysis on the body data by using an SVM classification algorithm. Further using SVM classification algorithm to perform classification analysis on the data, wherein the specific analysis steps are as follows: randomly scattering the health data and the developmental delay data, classifying the delay data by using an SVM (support vector machine), manually judging the screened delay data, correcting key coefficients in multiple iterations, and improving the accuracy of the model in identifying the developmental delay.
S3, fitting the body data with a standard curve of an index corresponding to the corresponding age in an earlier stage, and judging whether the body data is in a preset safety range to obtain a monitoring result and a corresponding suggestion; inserting the body data into a standard curve of a corresponding age corresponding index by using a Lagrange interpolation method in the middle period, and continuously correcting the standard curve to finally obtain a growth curve of the user; comparing the user data with the generated user growth curve, and giving corresponding prediction according to the curve data;
as shown in fig. 5, the standard curve is a curve of different ages and different indicators trained and fitted in advance according to a previous data set, and the standard curve forming includes the following steps: the method comprises the steps of acquiring infant growth and development data in advance, screening frontier medical indexes capable of evaluating the infant growth and development, carrying out combined calculation on the acquired infant growth and development data, carrying out frontier medical index quantification processing, and screening and fitting the data to obtain an age-height development standard curve, an age-weight development standard curve and an age-sleep standard curve.
For example, if the body data is data related to a sleep condition, S3 includes: the server compares the age, the physical state and the data related to the sleep condition of the person under guardianship with the physical state sleep quantity standard curve of the corresponding age to further obtain a training suggestion and a sleep quantity range.
And S4, transmitting the monitoring result, the corresponding suggestion and the corresponding prediction to the user terminal. And step S3, the server judges, and transmits the monitoring result and the corresponding suggestion to a user terminal provided with a monitoring evaluation APP after the server finishes the judgment, wherein the user terminal is one of a smart phone, a tablet personal computer, a PC (personal computer) or a notebook computer. The guardian (user) can also access the server to inquire the monitoring data through the user terminal, as shown in fig. 4, 7 and 8.
An infant development monitoring system based on artificial intelligence based on the above infant development monitoring method based on artificial intelligence, comprising: the system comprises a development evaluation module, an infant limb movement ability identification module, a sleep monitoring module, a nutrition detection module and a doctor's advice tracking module;
as shown in fig. 6, the development evaluation module is configured to receive child personal information (age, height, weight, medical history) input by a user, perform a question answering test for infant ability indexes (fine movement, coarse movement, social ability, language function, cognitive ability) of different ages in different months according to the child personal information, combine an algorithm and a mathematical model (for example: 1. training is performed by using a support vector machine (s vi M) algorithm, and output dependent variables can determine whether a patient is slow to develop or not) including learning structures of different depths according to the question answering condition of the user;
referring to fig. 2, the infant limb movement ability identification module is configured to obtain a moving picture or video of an infant, and capture and extract feature points in the moving picture or video by using an adaptive least square method; forming a motion track of the characteristic points through linear prediction and iterative adjustment, comparing the motion track with the motion track of the characteristic points in the standard motion image, and observing the fitting degree of the two tracks; the method can iteratively extract more complex and higher-level features from the low-level features by utilizing the advantage that a deep convolutional neural network (CNN network) can automatically learn, thereby better establishing a computer vision model.
Specifically, the infant limb movement ability identification module is further configured to acquire a moving picture or video of an infant, and capture and extract limb actions and behavior behaviors in the moving picture or video through a self-adaptive least square method; capturing and repairing the motion data of the infant by a method for recovering lost feature points, forming the motion trail of the feature points of the user by a linear prediction and iterative adjustment method, comparing the motion trail with the motion trail of the feature points in a standard motion image, and observing the fitting degree of the two trails; the higher the fitting degree is, the more excellent the child athletic ability is, the guidance for shooting again is given to the data with extremely poor fitting conditions, and corresponding training courses are recommended to the users who still have poor performance after multiple tests.
The sleep monitoring module is used for acquiring heart rate data and respiratory data of the infant, fitting the heart rate data and the respiratory data with a sleep condition standard curve of a corresponding age group and judging the sleep state of the infant;
in this embodiment, detect infant's sleep data through infant's sleep detection pillow, carry out heart rate monitoring through infrared ray sleep detector, acquire heart rate data. The sleep monitoring module is also used for automatically playing cradle music to help sleep safely when the sleeping condition of the infant is judged to be unstable; when the multiple times of sleep are not stable, an alarm is given and improvement suggestions are provided for parents, if the two schemes can not solve the problems, the sleep data of the infant are transmitted to a contracting doctor of the cooperative hospital, the doctor gives online guidance according to the data, and the doctor in the hospital can be reserved to carry out offline diagnosis when the problems can not be solved.
Referring to fig. 3, the nutrition detection system module is configured to obtain a food image of an infant, perform convolution processing on the food image based on a food image database established during early-stage image recognition model training and a computer vision model obtained through multi-layer training based on a convolutional neural network, fit the convolved result with the food image recognition model obtained through early-stage training again, perform classification processing on obtained features (such as food type, heat, nutritional components, and the like) by using a classifier, output the classification result to a user, and finally obtain a food nutrition monitoring result; the convolutional neural network (CNN network) is mainly improved continuously through multi-layer training of an input layer, a hidden layer and an output layer, and the recognition hit rate is improved. The input layer is mainly responsible for cutting, scaling and segmenting an original image input by a user and preprocessing the original image. Specifically, the nutrition detection system module is further configured to obtain a food picture of the infant, judge the depth of each pixel in the picture by performing visual analysis on the food picture and adopting a pattern recognition technology, connect a picture of specific food with a database, judge the food of the infant, perform nutrition analysis on the food on the basis of recognizing the food, provide food caloric information, and inform a user of the content of protein, fat, carbohydrate, vitamins and other components in the food; and giving personalized diet guidance by combining the past data and the basic situation of the infant.
As shown in fig. 9, the order tracking module is configured to obtain orders and daily notes for doctors in a contract hospital.
In this embodiment, the infant development monitoring system based on artificial intelligence further includes a diet module, where the diet module is configured to form a training set by collecting food picture data provided by a user, extract feature vectors (such as food quantity and food components) in the picture by using an SVM algorithm, calculate data provided by the user to a terminal according to the feature vectors, and divide diet structures of the user into two types according to a calculation result, where one type is a diet structure beneficial to healthy development of infants, and the other type is a diet structure unhealthy and not beneficial to healthy development of infants, and a scheme suitable for age groups of infants and growth and development conditions is customized for the user on caloric intake and diet advice.
In the above infant development monitoring system based on artificial intelligence, body data necessary for realizing the growth monitoring function is distinguished, and the data is divided into data that can be directly acquired by a monitoring terminal and data that cannot be directly acquired. Data (such as age, height, weight and the like) which can be directly acquired is selected to be directly collected when information is collected for a user, and in the case of data (such as athletic ability, social ability and the like) which cannot be directly acquired, an intelligent data acquisition algorithm is developed by learning the conventional medical common indexes, for example, the data acquisition is realized by performing algorithms such as motion capture, voice analysis and the like on infants, and advanced thesis algorithms in the fields of image recognition, voice recognition and the like are fully realized in the process.
In this embodiment, the optimization and verification of each module are also performed: and finishing the deep learning when the model tends to be stable, and testing and checking the final algorithm given by the server. Inputting latest complete data (age, height, weight, sleeping quantity, diet structure and the like) of a batch of hospitals, substituting the latest complete data into a final fitting curve to be calculated by a server, outputting evaluation data of physical signs, exercise capacity and the like of a user, and giving reference suggestions to the sleeping time and the diet structure of the user. Comparing the algorithm test result with the doctor judgment result, checking whether the algorithm test result is matched with the doctor judgment result, and improving the learning algorithm to learn again if the algorithm test result is not matched with the doctor judgment result; and if the algorithm is matched with the preset application, embedding the obtained algorithm into the app to carry out internal testing on part of users.
In this embodiment, the development of the WeChat applet and the application is also performed: the android application is developed by taking APK as a center in the early stage, the android application is used by jdk as an environment, android sdk and adt are tools, eclipse is developed by an editor, the UI of the APK is beautified and improved in the middle stage, and the android is used as a reference to establish a WeChat public number and develop on an IOS platform in the later stage.
The above-mentioned embodiments are preferred embodiments of the present invention, and the present invention is not limited thereto, and any other modifications or equivalent substitutions that do not depart from the technical spirit of the present invention are included in the scope of the present invention.
Claims (10)
1. An infant development monitoring system based on artificial intelligence, comprising: the system comprises a development evaluation module, an infant limb movement ability identification module, a sleep monitoring module, a nutrition detection module and a doctor's advice tracking module;
the development evaluation module is used for receiving the child personal information input by the user, performing answer tests aiming at the infant ability indexes of different ages in months according to the child personal information, obtaining ability development scores according to the answer conditions of the user by combining algorithms and mathematical models containing different deep learning structures, and further giving an ability development evaluation report according to the scores;
the infant limb motion capability identification module is used for acquiring a motion picture or video of an infant, identifying the motion picture or video based on an artificial intelligence technology, and capturing and extracting feature points in the motion picture or video by using a self-adaptive least square method; forming a motion track of the characteristic points through linear prediction and iterative adjustment, comparing the motion track with the motion track of the characteristic points in the standard motion image, and observing the fitting degree of the two tracks;
the sleep monitoring module is used for acquiring heart rate data and respiratory data of the infant, fitting the heart rate data and the respiratory data with a sleep condition standard curve of a corresponding age group and judging the sleep state of the infant;
the nutrition detection system module is used for acquiring food images of infants, carrying out convolution processing on the food images based on a food image database established during early-stage image recognition model training and a computer vision model obtained based on convolutional neural network multi-layer training, fitting the convolved results with the food image recognition model obtained through early-stage training again, classifying the obtained features by using a classifier, outputting the classified results to a user, and finally obtaining a food nutrition monitoring result;
the medical advice tracking module is used for acquiring medical advice of a doctor signing a contract in a hospital and giving attention every day.
2. The system and method of claim 1, wherein the personal information includes: age, height, weight, medical history; the ability indicators include fine movement, gross movement, social ability, language function, cognitive ability.
3. The system and method for monitoring infant development based on artificial intelligence according to claim 1, wherein the infant limb movement ability recognition module is further configured to obtain a moving picture or video of an infant, and extract limb actions and behavior behaviors in the moving picture or video by adaptive least square method; capturing and repairing the motion data of the infant by a method for recovering lost feature points, forming the motion trail of the feature points of the user by a linear prediction and iterative adjustment method, comparing the motion trail with the motion trail of the feature points in a standard motion image, and observing the fitting degree of the two trails; the higher the fitting degree is, the more excellent the child athletic ability is, the guidance for shooting again is given to the data with extremely poor fitting conditions, and corresponding training courses are recommended to the users who still have poor performance after multiple tests.
4. The artificial intelligence based infant development monitoring system of claim 1, wherein infant sleep data is detected by an infant sleep detection pillow, and heart rate data is acquired by performing heart rate monitoring by an infrared sleep detector.
5. The artificial intelligence based infant development monitoring system of claim 1, wherein the sleep monitoring module is further configured to automatically play cradle song to help sleep when the infant sleep condition is determined to be unstable; when the multiple times of sleep are not stable, an alarm is given and improvement suggestions are provided for parents, if the two schemes can not solve the problems, the sleep data of the infant are transmitted to a contracting doctor of the cooperative hospital, the doctor gives online guidance according to the data, and the doctor in the hospital can be reserved to carry out offline diagnosis when the problems can not be solved.
6. The artificial intelligence based infant development monitoring system of claim 1, wherein the nutrition detection system module is further configured to obtain a picture of food for the infant, determine the depth of each pixel in the picture by performing visual analysis on the picture of food, connect the picture of a specific food to a database, determine the food for the infant, perform nutrition analysis on the food based on the food being identified, provide food caloric information, and inform a user of the content of protein, fat, carbohydrate, vitamins and other components in the food; and giving personalized diet guidance by combining the past data and the basic situation of the infant.
7. An infant development monitoring method based on artificial intelligence is characterized by comprising the following steps:
s1, acquiring body data of the infant; the body data includes: height data, weight data, data relating to sleep conditions, data relating to diet, position data, data relating to intellectual development;
s2, processing the body data;
s3, fitting the body data with a standard curve of an index corresponding to the corresponding age, judging whether the body data is in a preset safety range, and obtaining a monitoring result and a corresponding suggestion; inserting the body data into a standard curve of a corresponding age corresponding index by using a Lagrange interpolation method, and continuously correcting the standard curve to finally obtain a growth curve of the user; comparing the user data with the generated user growth curve, and giving corresponding prediction according to the curve data;
and S4, transmitting the monitoring result, the corresponding suggestion and the corresponding prediction to the user terminal.
8. The artificial intelligence based infant development monitoring method according to claim 7, wherein the standard curve is a curve of different ages and different indicators trained and fitted in advance according to previous data sets, and the standard curve forming comprises the following steps:
the method comprises the steps of acquiring infant growth and development data in advance, screening frontier medical indexes capable of evaluating the infant growth and development, carrying out combined calculation on the acquired infant growth and development data, carrying out frontier medical index quantification processing, and screening and fitting the data to obtain an age-height development standard curve, an age-weight development standard curve and an age-sleep standard curve.
9. The method for monitoring infant development based on artificial intelligence of claim 8, wherein if the physical data is data related to sleep status, S3 includes: the server compares the age, the physical state and the data related to the sleep condition of the person under guardianship with the physical state sleep quantity standard curve of the corresponding age to further obtain a training suggestion and a sleep quantity range.
10. The artificial intelligence based infant development monitoring method of claim 7, wherein step S2 includes:
cleaning the body data, deleting blank data and planning partial data; and carrying out classification analysis on the body data by using an SVM classification algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010594585.XA CN111768863B (en) | 2020-06-28 | 2020-06-28 | Infant development monitoring system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010594585.XA CN111768863B (en) | 2020-06-28 | 2020-06-28 | Infant development monitoring system and method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111768863A true CN111768863A (en) | 2020-10-13 |
| CN111768863B CN111768863B (en) | 2024-02-02 |
Family
ID=72721914
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010594585.XA Active CN111768863B (en) | 2020-06-28 | 2020-06-28 | Infant development monitoring system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111768863B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112700843A (en) * | 2021-01-14 | 2021-04-23 | 徐磊 | Comprehensive infant nutrition monitoring system |
| CN114098654A (en) * | 2022-01-24 | 2022-03-01 | 南京信息工程大学 | Human body sleep state detection method and device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809472A (en) * | 2015-05-04 | 2015-07-29 | 哈尔滨理工大学 | SVM-based food classifying and recognizing method |
| CN106023244A (en) * | 2016-04-13 | 2016-10-12 | 南京邮电大学 | Pedestrian tracking method based on least square locus prediction and intelligent obstacle avoidance model |
| CN106295158A (en) * | 2016-08-04 | 2017-01-04 | 青岛歌尔声学科技有限公司 | A kind of automatic aided management system of infant, management method and equipment |
| CN106709525A (en) * | 2017-01-05 | 2017-05-24 | 北京大学 | Method for measuring food nutritional component by means of camera |
| CN107358034A (en) * | 2017-06-26 | 2017-11-17 | 怡璟科技（北京）有限公司 | The comprehensive monitoring and controlling method and system of a kind of children's health |
| CN107595248A (en) * | 2017-08-31 | 2018-01-19 | 郭淳 | A kind of method and system for detecting and evaluating upgrowth and development of children situation |
| CN109447140A (en) * | 2018-10-19 | 2019-03-08 | 广州四十五度科技有限公司 | A method of the image recognition based on neural network deep learning simultaneously recommends cognition |
| CN109636694A (en) * | 2018-12-21 | 2019-04-16 | 广州智而康网络科技有限公司 | A kind of method and system of child's health data management |
| CN110060777A (en) * | 2019-03-29 | 2019-07-26 | 井红 | System and method is instructed in a kind of evaluation of children's torso and nutrition early education |
| CN110741404A (en) * | 2017-06-30 | 2020-01-31 | 尤妮佳股份有限公司 | Program and child care support method |
-
2020
- 2020-06-28 CN CN202010594585.XA patent/CN111768863B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809472A (en) * | 2015-05-04 | 2015-07-29 | 哈尔滨理工大学 | SVM-based food classifying and recognizing method |
| CN106023244A (en) * | 2016-04-13 | 2016-10-12 | 南京邮电大学 | Pedestrian tracking method based on least square locus prediction and intelligent obstacle avoidance model |
| CN106295158A (en) * | 2016-08-04 | 2017-01-04 | 青岛歌尔声学科技有限公司 | A kind of automatic aided management system of infant, management method and equipment |
| CN106709525A (en) * | 2017-01-05 | 2017-05-24 | 北京大学 | Method for measuring food nutritional component by means of camera |
| CN107358034A (en) * | 2017-06-26 | 2017-11-17 | 怡璟科技（北京）有限公司 | The comprehensive monitoring and controlling method and system of a kind of children's health |
| CN110741404A (en) * | 2017-06-30 | 2020-01-31 | 尤妮佳股份有限公司 | Program and child care support method |
| CN107595248A (en) * | 2017-08-31 | 2018-01-19 | 郭淳 | A kind of method and system for detecting and evaluating upgrowth and development of children situation |
| CN109447140A (en) * | 2018-10-19 | 2019-03-08 | 广州四十五度科技有限公司 | A method of the image recognition based on neural network deep learning simultaneously recommends cognition |
| CN109636694A (en) * | 2018-12-21 | 2019-04-16 | 广州智而康网络科技有限公司 | A kind of method and system of child's health data management |
| CN110060777A (en) * | 2019-03-29 | 2019-07-26 | 井红 | System and method is instructed in a kind of evaluation of children's torso and nutrition early education |
Non-Patent Citations (1)
| Title |
|---|
| 叶亚等: "某社区1岁儿童营养过剩与睡眠时间的关系研究", 《中国医药指南》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112700843A (en) * | 2021-01-14 | 2021-04-23 | 徐磊 | Comprehensive infant nutrition monitoring system |
| CN114098654A (en) * | 2022-01-24 | 2022-03-01 | 南京信息工程大学 | Human body sleep state detection method and device |
| CN114098654B (en) * | 2022-01-24 | 2022-04-08 | 南京信息工程大学 | Human body sleep state detection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111768863B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chambers et al. | Computer vision to automatically assess infant neuromotor risk | |
| JP3224675U (en) | Interactive and adaptive learning using pupil response, face tracking, and emotion detection, neurocognitive disorder diagnosis, and non-following detection system | |
| CN108428202A (en) | A kind of method and system for delivering and managing study training program | |
| KR20200005986A (en) | System and method for diagnosing cognitive impairment using face recognization | |
| CN110135242B (en) | Emotion recognition device and method based on low-resolution infrared thermal imaging depth perception | |
| CN105873515A (en) | Methods for assessing infant and child development via eye tracking | |
| WO2020010668A1 (en) | Human body health assessment method and system based on sleep big data | |
| CN112334989A (en) | Method and system for characterizing stool patterns of infants | |
| CN110584601A (en) | Method for monitoring and evaluating cognitive function of old people | |
| CN111768863A (en) | Artificial intelligence-based infant development monitoring system and method | |
| CN114999646B (en) | Newborn exercise development assessment system, method, device and storage medium | |
| JP3954295B2 (en) | IDENTIFICATION / RESPONSE MEASUREMENT METHOD, COMPUTER-READABLE RECORDING MEDIUM CONTAINING IDENTIFICATION / REACTION MEASUREMENT PROGRAM | |
| CN114096194A (en) | Systems and methods for cognitive training and monitoring | |
| Roffo et al. | Automating the administration and analysis of psychiatric tests: The case of attachment in school age children | |
| CN113658697B (en) | Psychological assessment system based on video fixation difference | |
| CN112135568A (en) | Information processing apparatus, information processing method, and program | |
| Bethell et al. | A deep transfer learning model for head pose estimation in rhesus macaques during cognitive tasks: Towards a nonrestraint noninvasive 3Rs approach | |
| CN117133409A (en) | Auxiliary child autism spectrum disorder rehabilitation system based on VR interaction technology | |
| Tolu et al. | Perspective on investigation of neurodegenerative diseases with neurorobotics approaches | |
| Wedyan | Augmented reality and novel virtual sample generation algorithm based autism diagnosis system | |
| KR101878359B1 (en) | System and method for detecting mutiple-intelligence using information technology | |
| Hua et al. | Distinguishing medication ON and OFF for Parkinson’s disease through repetitive foot motion recognition and analysis | |
| Guo et al. | Upper limb motion recognition for unsupervised stroke rehabilitation based on Support Vector Machine | |
| Shabbeer et al. | Detection of Parkinson's Disease and Its Severity Using Deep Learning | |
| Maharaj et al. | Automated measurement of repetitive behavior using the Microsoft Kinect: a proof of concept |
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 |