CN109480868B - Intelligent infant monitoring system - Google Patents
Intelligent infant monitoring system Download PDFInfo
- Publication number
- CN109480868B CN109480868B CN201811306109.2A CN201811306109A CN109480868B CN 109480868 B CN109480868 B CN 109480868B CN 201811306109 A CN201811306109 A CN 201811306109A CN 109480868 B CN109480868 B CN 109480868B
- Authority
- CN
- China
- Prior art keywords
- infant
- information
- emotional state
- intelligent terminal
- module
- 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.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4803—Speech analysis specially adapted for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Psychiatry (AREA)
- Artificial Intelligence (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Evolutionary Computation (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
An intelligent infant monitoring system at least comprises a first intelligent terminal, a second intelligent terminal and a cloud server, it is characterized in that the first intelligent terminal is used for automatically collecting physiological information, sound information and/or behavior information of the baby, the second intelligent terminal, the cloud server at least comprises a teaching module and an emotional state analysis module which utilizes an emotional state analysis algorithm to analyze theoretical emotional states based on physiological information, sound information and/or behavior information of the infant, the teaching module completes the teaching process of the theoretical emotional state stored in the preset database based on the actual emotional state information input by the second intelligent terminal, and the emotional state analysis module instructs the second intelligent terminal to send a demand prompt and/or an early warning prompt to the current user based on the demand information corresponding to the actual emotional state of the infant. The invention realizes accurate monitoring of the actual emotional state of the infant based on the individual difference of the infant.
Description
Technical Field
The invention relates to the technical field of infant monitoring, in particular to an intelligent infant monitoring system.
Background
At present, infants in China are mainly fed with formula milk except for breast feeding. The intake of the formula milk directly determines various nutritional factors such as calories, proteins, fats, carbohydrates, minerals, vitamins and the like absorbed by the infant every day. The reserve amount of the nutrient elements in the infant body is relatively small, the adaptability is poorer than that of an adult, and once the intake amount of some nutrient elements is insufficient or the digestion function is disordered, the development process can be obviously influenced in a short time, so that the intake amount and the intake rhythm of the formula milk can directly influence the growth and development of the infant.
Because the requirements of infants of different ages for the intake of formula milk are different, and the influence of different brands of milk powder on the growth and development of the infants is different due to different nutritional ingredients and trace elements, the correct selection of formula milk powder and the measurement of the intake of formula milk powder are also very important works. The parents, the parents of the children, are inexperienced in grasping the daily milk intake and the nursing time point, and require a professional to give certain guidance and help. When the professional person is guided, the professional person often needs to comprehensively know the diet, sleep and growth and development conditions of the child within a certain period of time in the past, so that the individual differences and the current situation of the child can be fully known, and further a proper opinion is given.
When recording the daily formula milk intake of a child, parents usually rely on scales on a feeding bottle to measure the milk intake of the child, but due to the irregular shape of the feeding bottle and the insufficiency of product quality detection, the scales of some feeding bottles are not accurate enough, and have a certain influence on the condition that the parents correctly grasp the formula milk intake of the child. In addition, due to the restriction of various realistic factors of daily life, parents can hardly ensure that the milk intake of children can be recorded timely and accurately each time, so that a complete formula milk intake history record is difficult to provide. Furthermore, parents of newborn babies often forget the milk drinking time of the babies, and the recording is tedious independently, so that sometimes the children cannot be cared for and the recording is inconvenient outside.
Currently, there are some devices on the market for monitoring infant care. Chinese patent (CN 105708468A) discloses a mother-child bracelet, which comprises a child ring and a mother ring, wherein the child ring is used for detecting behavior state information of a child ring wearer, generating abnormal prompt information according to the behavior state information and sending the abnormal prompt information to the mother ring; the mother ring is communicated with the child ring, and the mother ring prompts a mother ring wearer according to the abnormal prompt information. The patent can make guardians know the abnormal condition of the person who is being watched in time, and the person who is being watched is monitored better. However, this patent is only used for monitoring the abnormal state of the infant, and only by advancing the guardian at the end of the mother ring at the time of abnormality, it is impossible to record and analyze the milk drinking time and the bed wetting time of the infant. In particular, the need for an infant cannot be judged based on the sound of the infant crying to facilitate the care of the infant by the guardian.
Therefore, there is a need in the market for an intelligent monitoring system capable of recording the care information of infants and analyzing the needs of infants.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an intelligent infant monitoring system, which at least comprises a first intelligent terminal, a second intelligent terminal and a cloud server, and is characterized in that the first intelligent terminal is used for automatically collecting physiological information, sound information and/or behavior information of an infant, the second intelligent terminal is used for manually inputting life record information and/or actual emotional state information of the infant, the cloud server at least comprises a teaching module and an emotional state analysis module which utilizes an emotional state analysis algorithm to analyze theoretical emotional state based on the physiological information, the sound information and/or the behavior information of the infant, the cloud server also comprises a behavior feature extraction module, the feature extraction module extracts behavior feature parameters of the infant based on the physiological information, the sound information and/or the behavior information of the infant, and selecting a matching physical exercise regimen based on the analysis of the behavior feature parameters.
According to a preferred embodiment, the cloud server further comprises a deep learning training module, the deep learning training module learns and grasps a specific pattern of the limb behaviors of the infant based on the behavior feature parameters of the infant, and the deep learning training module generates an infant training scheme including at least motion training, thinking training and/or emotion training based on the specific pattern.
According to a preferred embodiment, the feature extraction module extracts the behavior feature parameters of the baby based on the specific pattern established by the deep learning module, and matches the corresponding action training unit, thinking training unit and/or emotion training unit based on the behavior feature parameters, and the deep learning training module selects the action training unit, thinking training unit and/or emotion training unit with harmony within a set threshold range based on the specific pattern of the baby to form a baby training scheme.
According to a preferred embodiment, the teaching module completes the teaching process of the theoretical emotional state stored in the preset database based on the actual emotional state information input by the second intelligent terminal, and the emotional state analysis module instructs the second intelligent terminal to send a demand prompt and/or an early warning prompt to the current user based on the demand information corresponding to the actual emotional state of the infant.
According to a preferred embodiment, a teaching module in the cloud server analyzes and completes a teaching process based on the life record information and/or the actual emotional state information input by the second intelligent terminal, wherein the teaching module configures parameters of the state analysis algorithm in advance based on at least two kinds of abnormal emotional state information.
According to a preferred embodiment, the emotional state analysis module stores the life recording information and/or the actual emotional state information of the infant, which is inputted by the user to the second intelligent terminal in a text, voice, video and/or graphic manner, and the external condition, physiological information, sound information and/or behavior information automatically collected by the first intelligent terminal to a preset database in an associated manner, or the first intelligent terminal records the external conditions inducing the actual emotional state of the infant and stores or provides the external conditions to the preset database in a form of being associated with the corresponding actual emotional state, the emotional state analysis module analyzes based on a correlation between a particular emotional state of the infant and the external condition, and indicating the second intelligent terminal to give an early warning based on the correlation to the specific emotional state.
According to a preferred embodiment, the cloud server further comprises a correction module, the correction module corrects theoretical emotional state information determined based on analysis of the external conditions, the physiological information, the sound information and/or the behavior information collected by the first intelligent terminal based on the actual emotional state information of the infant, and a preset database which is formed by the corrected theoretical emotional state information and can be searched according to life record information, the physiological information and/or the external conditions of the infant is formed.
According to a preferred embodiment, the cloud server is provided with a nursing suggestion module which is associated with medical information of a third-party medical institution, the nursing suggestion module retrieves corresponding medical nursing information based on the actual emotional state of the infant and sends prompt information through the second intelligent terminal, and/or the nursing suggestion module prompts infant disease warning information of a nearby area and/or a specific time period issued by the third-party medical institution through the second intelligent terminal based on the geographical position determined by the second intelligent terminal, and prompts the infant prevalence rate estimated based on the infant physiological information acquired by the first intelligent terminal through the second intelligent terminal.
According to a preferred embodiment, the nursing advice module issues infant nursing advice through the second intelligent terminal based on the infant disease warning information of the nearby area and/or the specific time period provided by the third-party medical institution.
According to a preferred embodiment, the cloud server further comprises a baby profile matched with the baby personality, the baby profile creates and adaptively adjusts initial configuration information based on life record information and actual emotional state change trend information of the baby to form baby emotional parameters, and the baby profile selects a corresponding baby nursing scheme based on analysis of the baby emotional parameters and sends the baby nursing scheme to the second intelligent terminal; wherein the initial configuration information comprises at least a birth date, a blood type and/or a gender of the infant.
The invention has the beneficial technical effects that:
(1) according to the invention, by monitoring physiological information, sound and behavior information of the baby, emotion expression and requirements of the baby can be accurately analyzed, and the baby monitoring system is beneficial for a guardian to take care of the baby in time;
(2) different infants have different emotion specific expression modes, and the method can form an analysis process which accords with the individuality of the infants through a teaching process aiming at different infants, so that the specific emotion of each infant is more accurately analyzed;
(3) the invention takes the external conditions as the analysis elements, and can accurately determine the influence of the external changes on the infant, thereby enabling the guardian to improve the living conditions of the infant in time aiming at the changes of the external conditions and avoiding the infant from crying due to the external conditions;
(4) according to the invention, a reasonable nursing suggestion is sent to the guardian according to the medical information of the baby in the nearby area, so that the guardian is prevented from carrying the baby to move in the region with high morbidity, and the health of the baby is ensured.
Drawings
FIG. 1 is a schematic diagram of the logic modules of the present invention; and
fig. 2 is a schematic diagram of the method steps of the emotional state analysis module of the present invention.
List of reference numerals
10: the first smart peer 20: second intelligent terminal
30: the cloud server 31: database with a plurality of databases
32: the teach module 33: emotional state analysis module
34: the correction module 331: sound analysis module
332: emotion analysis module
Detailed Description
The following detailed description is made with reference to the accompanying drawings.
The invention provides an intelligent infant monitoring system which at least comprises a first intelligent terminal 10, a second intelligent terminal 20 and a cloud server 30. As shown in fig. 1, the first smart client 10 and the second smart client 20 are respectively connected to the cloud server 30 in a wired or wireless manner. The first intelligent terminal 10 and the second intelligent terminal 20 are connected in a wired or wireless manner.
The first smart terminal 10 is disposed on the body of the infant. The first intelligent terminal is wearable equipment, such as a smart ring, a smart garment and a smart sticker. The first intelligent terminal is used for automatically acquiring physiological information, sound information and/or behavior information of the baby. The physiological information of the baby includes body temperature, pulse, heartbeat, sweat humidity and other information. Sweat moisture refers to the degree to which an infant sweats. The sound information comprises the rhythm, frequency, brightness and/or loudness of the sound emitted by the infant, in particular the rhythm, frequency, brightness and/or loudness of laughter, the rhythm, frequency, brightness and/or loudness of crying. The behavior information of the baby at least comprises the behavior information such as arm swinging frequency and swinging amplitude, body twisting, leg swinging frequency and swinging amplitude and the like.
Preferably, the first smart terminal 10 further collects the external condition information of the environment where the infant is located. The external condition information at least comprises information such as external temperature, humidity, noise, oxygen content, light brightness, weather cloudy and sunny and the like.
And the second intelligent terminal 20 is used for manually inputting the life record information and/or the actual emotional state information of the baby. The life record information at least comprises the time of each milk feeding of the infant, the milk drinking amount, the time of diaper changing, the defecation time, the waking time and/or the sleeping time.
The actual emotional state information is an actual emotional state of the infant. Because of differences in the individuality of infants, even if the behavior and crying rhythm are the same, the emotions expressed by the infants are different and different. Therefore, in the initial stage of the system of the present invention, it is necessary to correct the error between the theoretical emotional state and the actual emotional state in the system through a teaching process. The guardian is the most direct observer of the actual emotional state of the baby, which may reflect the reality by manually entering the actual emotional state of the baby. Or the guardian determines the actual emotional state expressed by the baby crying by the baby's reaction to the actions of nursing, changing diapers, etc. Through multiple teaching processes, parameters of an emotional state analysis algorithm in the system can be corrected, and a monitoring system which is matched with the personality of the baby and accurate in analysis is formed. Therefore, the actual emotional state information of the infant requires manual input.
Preferably, the actual emotional state information of the infant is different from the actual emotional state information of the adult. The actual emotional state information of the infant is simple, and includes not only real emotional information, such as happy feeling, uneasy feeling, dysphoria, drowsiness, fear, tension, etc., but also demanding emotions, such as hunger, thirst, pain, dysuria, satiety, defecation, clasping, etc. Therefore, the emotion state of the baby is analyzed, so that a guardian can take corresponding measures to take care of the baby, the requirements of the baby can be met, and the fatigue caused by guessing the requirements of the baby by the guardian can be avoided.
Preferably, the cloud server 30 includes at least a teaching module 32 and an emotional state analysis module 33 performing theoretical emotional state analysis using an emotional state analysis algorithm based on physiological information, voice information, and/or behavior information of the infant. The teaching module completes the teaching process of the theoretical emotional state stored in the preset database 31 based on the actual emotional state information input by the second intelligent terminal.
The teaching process in the invention is to correct parameters in the emotional state analysis algorithm based on the deviation between the actual emotional state and the theoretical emotional state obtained by calculation and analysis, so that the theoretical emotional state obtained by calculation and analysis is consistent with the actual emotional state of the infant.
Preferably, the emotional state analysis module 33 instructs the second smart peer to send a demand prompt and/or an early warning prompt to the current user based on the demand information corresponding to the actual emotional state of the infant.
After obtaining the actual emotional state of the infant, the emotional state analysis module 33 sends the infant's needs or corresponding measures to the second smart peer of the guardian. And the second intelligent terminal sends a demand prompt or an early warning prompt to the current user.
Preferably, the emotional state analysis module analyzes the change trend of the baby based on the actual emotional state change of the baby, and instructs the second intelligent terminal to send an early warning prompt to the guardian when the change trend of the actual emotional state change exceeds a critical value at a predictable time point.
Preferably, a teaching module in the cloud server analyzes and completes a teaching process based on the life record information and/or the actual emotional state information input by the second intelligent terminal. The teachings herein refer to exemplary artificial intelligence programming. The teaching module is used for configuring parameters of the emotional state analysis algorithm in advance based on at least two kinds of abnormal emotional state information. Preferably, the emotional state analysis algorithm comprises a Bayesian classification algorithm, a neural network, a support vector machine, a decision tree, case inference based learning, association rule learning and other machine learning algorithms.
Preferably, the emotional state analysis module includes at least a sound analysis module 331 and an emotion analysis module 332. The sound module performs a first emotional state analysis based on the tempo, frequency, brightness, and/or loudness of the sound of the infant. The emotion analysis module analyzes based on the physiological information, the behavior information, the life record information and/or the first analysis information and obtains second emotion state analysis information.
For example, the emotional state analysis algorithm includes an emotional state analysis of baby crying. One of the emotional state analysis algorithms pre-stored in the preset database and the teaching process thereof are as follows.
S1: acquiring a plurality of sections of training data of the crying audio of the baby, wherein each training data corresponds to two known crying reasons;
s2: extracting the characteristics of each section of training data to obtain a characteristic parameter vector of each section of training data; preferably, after the feature extraction, the noise reduction is carried out on the crying signals in the training data, and data segments with noise larger than a preset threshold are detected and picked out;
s3: performing principal component analysis on the characteristic parameter vectors of the multiple sections of training data to obtain a plurality of principal components;
s4: calculating the mean and variance of the projection scores of the training data corresponding to each crying reason on each main component, and selecting P main components from the main components according to the variance, wherein P is an integer greater than 1;
s5: acquiring data to be identified of the baby crying audio, and calculating projection values of the data to be identified on the P main components;
s6: calculating the probability of the data to be distinguished corresponding to each theoretical emotional state according to the projection score, the mean value and the variance of the data to be distinguished;
s7: and correcting the projection scores based on the actual emotional state of the baby fed back by the second intelligent terminal. And if the actual emotional state fed back by the second intelligent terminal is the same as one of the theoretical emotional states, the probability of the theoretical emotional state is further increased by correcting the orthographic projection score. Through repeated teaching processes, the theoretical emotional state is more consistent with the actual emotional state.
Preferably, the multi-segment training data includes N samples of the crying signals, K characteristic parameters are extracted from the N samples of the crying signals, where the K characteristic parameters extracted from the nth sample of the crying signal are recorded as a characteristic parameter vector Sn ═ Snl，Sn2,…,snk]T. And calculating covariance matrixes corresponding to the K characteristic parameters of the N samples of the crying signals, and marking the covariance matrixes as C. Where C is a matrix of K times K. Decomposing eigenvalues of the covariance matrix to obtain K eigenvalues and eigenvalues corresponding to the K eigenvaluesAmount of the compound (A).
Decomposing the eigenvalue of the covariance matrix C, and arranging the eigenvalues from large to small to obtain { lambda1，λ2，…，λkIn the time of the design, Q characteristic values with the largest characteristic values and corresponding characteristic vectors are taken from the characteristic values to form two Q-dimensional characteristic subspaces, wherein the value of Q is taken
G is any preset value between 0.9 and 0.99. Of the Q principal components, the k-th principal component is taken, and the eigenvalue of the principal component is recorded as lambdak，λkThe corresponding feature vector is denoted ukCalculating the characteristic parameter vector S of the nth crying signalnThe projection score on the k-th feature vector. Finding out the crying signal belonging to the j-th crying reason from the N crying signals, and marking as NjThen the K feature parameter vectors project the mean of the scores on the K feature vector
Sum variance σjkThen calculate
Wherein the content of the first and second substances,
in each of the above formulae, J represents the total number of types of causes of crying, and XkThe separation of the projection scores of the characteristic parameter vectors representing the crying signal at the kth principal component. Y iskThe concentration of the feature parameter vector representing the crying signal in the projection score of the kth principal component. L iskRepresenting the ability of the respective principal components to discriminate between the causes of crying. L is a radical of an alcoholkLarger means stronger discrimination ability thereof.
Arranging the Q main components in sequence, and selecting LkThe P main components with the maximum values are used for subsequent crying reason identification, wherein the P takes the smaller value of Q and M.
h is a preset value with the value between 2% and 0.5%.
Probability of j-th cause in emotional state analysis algorithm
According to the obtained P main components, for each training data in the set of training data, steps S5 and S6 are respectively executed to obtain the probability that the training data corresponds to each reason, the probability maximum reason corresponding to the training data is calculated, and the probability maximum reason is compared with the known crying reason corresponding to the training data. And removing the training data with the maximum probability reason different from the known crying reason from the two groups of selected training data, taking the rest training data as a newly selected group of training data, and executing the steps again until a preset exit condition is met.
Preferably, in the emotional state analysis algorithm, the extracted features include any two or more of the following features. Such as: average cry duration, cry duration variance, average cry energy, cry energy variance, pitch frequency, average of pitch frequency, maximum of pitch frequency, minimum of pitch frequency, dynamic range of pitch frequency, average rate of change of pitch frequency, second formant frequency, average rate of change of second formant frequency, average of first formant frequency, maximum of first formant frequency, minimum of first formant frequency, dynamic range of first formant frequency, second formant frequency, average rate of change of second formant frequency, average of second formant frequency, maximum of second formant frequency, minimum of second formant frequency, dynamic range of second formant frequency, Mel-frequency cepstral parameter, inverted Mel-frequency cepstral parameter.
Preferably, the emotional state analysis module determines that the crying of the infant is due to hunger based on the last breastfeeding time of the infant, the swing frequency of the infant's limbs, and the acoustic characteristics of the infant.
Preferably, the emotional state analysis module analyzes the variation trend of the actual emotional state based on the physiological information, the sound information and the behavior information of the infant, and judges the imminent crying probability representing hunger of the infant. And when the probability of crying caused by hunger exceeds a preset critical value, the second intelligent end of the knowledge sends out milk feeding prompt information.
Preferably, the emotional state analysis module stores the life recording information and/or the actual emotional state information of the infant, which is input to the second intelligent terminal by the user in a text, voice, video and/or graphic manner, and the external condition, physiological information, sound information and/or behavior information automatically collected by the first intelligent terminal to a preset database in an associated manner.
Preferably, the step of the second smart terminal inputting the life recording information or the actual emotional state information by the user includes: the user selects the life recording information, emotion type and level of the current baby in a click mode, and/or the user inputs the life recording information and/or actual emotional state of the baby in a text, voice, video or graphic mode.
Specifically, the second intelligent terminal inputs life recording information and/or actual emotional state information of the baby in a text, voice, video and/or graphic mode. For example, the second smart terminal is provided with a selection key that displays text and/or graphics. The guardian can manually input corresponding information only by triggering the selection key. Or the second intelligent end is provided with a microphone and a camera which are connected with the voice recognition module. The guardian records the life information of the baby through voice input or a mode of shooting and inputting videos.
For example, the second smart terminal is provided with a touch screen, and the touch screen displays modules with various functions. The guardian selects the life recording information, emotion type and level of the current infant in a click mode. The guardian can also record the baby's life information and his own feelings by editing text information, entering a voice recording, taking pictures or entering video.
The first intelligent terminal and the second intelligent terminal respectively send the collected information to the cloud server. Preferably, the first intelligent terminal and the second intelligent terminal are respectively provided with a flash memory. Under the condition of being connected with the cloud server, the first intelligent end and the second intelligent end send acquired data information to a preset database of the cloud server in real time. Under the condition that the connection with the cloud server is obstructed, the first intelligent terminal and the second intelligent terminal store the acquired data information in a flash memory mode. And under the condition of good subsequent connection with the cloud server, the first intelligent terminal and the second intelligent terminal send the data information of the flash memory to a preset database of the cloud server. By the arrangement, the data of the system can be guaranteed not to be lost due to signal transmission obstacles, and the authenticity and the validity of the data are guaranteed.
Preferably, the first smart terminal records the external conditions inducing the actual emotional state of the infant and stores or provides the external conditions to a preset database in association with the corresponding actual emotional state. The emotional state analysis module analyzes based on a correlation between a specific emotional state of the infant and an external condition, and instructs the second smart terminal to perform early warning based on the correlation for the triggering of the specific emotional state.
For example, sensitive infants encounter unpleasant external conditions and cry or act against them, causing actual emotional information such as crying. Therefore, the external condition information is associated with the actual emotional state information, so that the guardian can effectively change bad external conditions or leave the baby from the bad external conditions, and the baby stops crying and obtains comfortable experience. When the correlation between a particular emotional state of the infant and an external condition, such as the intensity of the noise, is high, the intensity value of the noise is listed as alerting the external condition. The emotional state analysis module prompts the second intelligent terminal to change the noise environment where the baby is located or to bring the baby away from the noise environment when the first intelligent terminal collects the noise intensity value within the warning external condition range.
Preferably, the second smart terminal is configured to retrieve, by the user, the actual emotional state information stored in the preset database and/or the second smart terminal in a manner related to the life recording information of the infant and/or the external condition.
For example, the second intelligent terminal is provided with a retrieval function. The method is used for the guardian to retrieve the actual emotional state information stored in the preset database and/or the second intelligent terminal according to the mode related to the life record information and/or the external conditions of the baby. The guardian can call up the life record of the baby on the day by inputting the date of the life record information of the day or taking care of the behavior. Alternatively, the guardian may adjust all the actual emotional state information of the baby at the temperature by inputting the external condition information, such as the external temperature. The setting of retrieval function is convenient for the guardian to transfer and show medical personnel or third party mechanism with the life record information of baby and the actual mood change information of a certain period of time, is favorable to studying the state of an illness of baby, also is favorable to the guardian to further know baby's habits and customs, avoids the baby to produce bad events such as hypersensitivity in the external world.
Preferably, the cloud server further comprises a correction module 34. The correction module can be one or more of a data analysis module, a data verification module and a server.
The correction module corrects theoretical emotional state information determined based on analysis of the external conditions, the physiological information, the sound information and/or the behavior information collected by the first intelligent terminal based on the actual emotional state information of the infant. And the preset database is formed by the corrected theoretical emotional state information and can be searched according to the life record information, the physiological information and/or the external conditions of the baby.
Although the teaching module is arranged, the theoretical emotional state information and the actual emotional state information tend to be matched. However, the guardian may make an erroneous determination on the actual emotional state information of the infant due to insufficient experience in taking care of the infant, and thus the second intelligent terminal inputs the erroneous actual emotional state information, thereby further making parameter adjustment of the emotional state analysis algorithm erroneous. Therefore, the arrangement of the correction module is also crucial. Or the baby behavior information acquired by the first intelligent terminal has errors, so that the recording error of the behavior information is large.
For example, the correction module corrects theoretical emotional state information corresponding to physiological information, sound information, and behavior information of the infant based on the actual emotional state. When the error between the theoretical emotional state analyzed by the emotional state analysis module and the actual emotional state is gradually increased, the fact that the expression of the infant changes due to learning and growth is meant, and the change of the behavior information is the most remarkable. For example, early infants wanted to cradle primarily crying, which does not have a distinct regularity in the behavior of their arms or legs. The baby can express the emotion of holding through more swing arms in five months. If the guardian finds the theoretical emotional state information received by the second intelligent terminal and the actual emotional state of the infant, the system can correct the emotional state information by triggering the correction module and the actual emotional state information for multiple times. At this time, the correction module corrects theoretical emotional state information corresponding to the behavior information based on the actual emotional state. Since the life of the infant is simple and repeated emotional states occur many times a day, analysis deviations due to growth can be corrected again by correcting for many times.
Preferably, the cloud server is provided with a nursing suggestion module which is associated with medical information of a third-party medical institution. The nursing suggestion module retrieves corresponding medical care information based on the actual emotional state of the infant and sends prompt information through the second intelligent terminal.
And/or the nursing suggestion module prompts the infant disease warning information of the nearby area and/or the specific time period issued by the third-party medical institution through the second intelligent terminal based on the geographic position determined by the second intelligent terminal, and prompts the infant prevalence rate estimated based on the infant physiological information acquired by the first intelligent terminal through the second intelligent terminal.
For example, the emotional state analysis module is uncomfortable in analyzing the actual emotion of the infant, and the body temperature is abnormal. The emotional state analysis module sends the actual emotional state information to the care advice module. The nursing suggestion module retrieves corresponding medical care information based on the actual emotional state of the baby and sends prompt information through the second intelligent terminal to prompt a guardian to take care of the baby in a scientific mode, and therefore the guardian is prevented from carrying out wrong nursing behaviors due to confusion or no professional knowledge.
For example, haze weather worsens in spring and the incidence of pneumonia in the community where the infant is located increases. The first intelligent terminal or the second intelligent terminal has a function of collecting geographical position information. The nursing suggestion module retrieves the prevalence rate of infants in the nearby area and/or for a specific time period released by a third-party medical institution based on the geographical location determined by the first intelligent terminal and/or the second intelligent terminal, and finds that the incidence rate of pneumonia is increased. The nursing suggestion module prompts infant disease warning information such as pneumonia incidence through the second intelligent terminal. Meanwhile, the nursing suggestion module can autonomously evaluate the physiological information of the infant in the near term for the sick pneumonia, or send the physiological information of the infant in the near term to a third-party medical institution, and professional medical personnel can evaluate the sick. The infant prevalence rate of the nursing suggestion module is prompted through the second intelligent terminal to remind a guardian to pay attention to recent life nursing of the infant, and the infant is prevented from suffering from pneumonia. In particular, for infant diseases with infectious nature, the nursing advice module is particularly important to inform the guardian of the attention to protect the infant from the infectious disease area or to isolate the infectious condition in the first time of the infection risk period.
Preferably, the nursing suggestion module issues the baby nursing suggestion through the second intelligent terminal based on the baby disease warning information of the nearby area and/or the specific time period provided by the third-party medical institution.
For example, when the nursing suggestion module sends infant nursing suggestions to the second intelligent terminal based on infectious diseases of the community area where the infant is located, wherein the infectious diseases are provided by a third-party medical institution, such as suggestions of frequently changing clothes, reducing the frequency of going out, increasing the water feeding frequency and the like, the guardian scientifically improves the immunity of the infant. The panic emotion of the guardian caused by disease infection is avoided, useless nursing behaviors of the guardian caused by lack of professional knowledge are also avoided, and the discomfort of the baby is increased. The infant nursing suggestion enables a guardian to systematically and scientifically care infants, protects the infants and reduces the probability of infection.
Preferably, the cloud server further comprises a baby profile. The character of the infant is difficult to be accurately confirmed in the early stage. The guardian cannot confirm the character of the infant by observation, and thus cannot assist the intellectual development of the infant by using an appropriate nurturing method. The earlier the character of the infant is confirmed, the more the infant is raised in a proper way, which contributes to the intellectual development of the infant.
The infant profile of the present invention is set individually for each infant. The infant profile, when created, includes initial configuration information for the birth date, blood type and gender of the infant. Preferably, the initial configuration information further comprises initial infant emotional parameters based on the birth date, blood type and gender analysis. When the monitoring system operates, the infant configuration file extracts infant life record information, actual emotion state information and variation trend thereof from a pre-stored database to adaptively adjust initial infant emotion parameters in the infant configuration file to form infant emotion parameters. The infant profile selects a regimen that is more appropriate for the infant based on an analysis of the emotional parameters of the infant.
For example, if a baby develops faster than a peer child, learns louder, babble, and can make different sounds for relatives and have different emotional states, first in the second month, the baby profile sends the corresponding baby care plan to the second smart terminal to facilitate different guardian-baby interactions. For example, infant profiles analyze the emotional parameters of infants, with a higher frequency of anger, and infants who are irritable but have a significant response to music. The infant profile sends a milder infant care plan to the second intelligent terminal, including listening to songs with a relaxed mood, to relieve the mood of the infant, reduce the behavior of the infant crying intentionally due to anger, and reduce the fatigue level of the guardian.
Preferably, the first intelligent terminal at least comprises one or more of a physiological information sensor, a sound collector, an acceleration sensor, a balance sensor and a flash memory storage device. For example, the first smart terminal is a smart band.
The second intelligent terminal at least comprises one or more of an information input device, a display device, a flash memory storage device and an analysis module. The second intelligent terminal can be an intelligent bracelet and also can be intelligent equipment, for example, one or more of a smart phone, an intelligent bracelet, intelligent glasses, a notebook and a computer.
Preferably, the system of the present invention may further include a first intelligent terminal, a second intelligent terminal, and a third intelligent terminal. The first intelligent end and the second intelligent end are both convenient to move and are light portable intelligent bracelets, and the third intelligent end is a smart phone or a computer. The second intelligent terminal is used for receiving, displaying and inputting life recording information of the baby. The third intelligent terminal can retrieve all information records about the baby while executing all functions of the second intelligent terminal, wherein the information records comprise the actual emotional state information of the baby and the change trend, the illness probability and the nursing advice of the baby, and even the third intelligent terminal is directly connected with a third-party medical institution to obtain the most direct and effective medical advice.
Example 2
This embodiment is a further improvement of embodiment 1, and repeated contents are not described again.
The intelligent infant monitoring system at least comprises a first intelligent terminal 10, a second intelligent terminal 20 and a cloud server 30. The cloud server also comprises a behavior feature extraction module.
Preferably, the behavior feature extraction module extracts the physiological information, the sound information and/or the behavior feature parameters of the infant according to a preset behavior model. For example, the frequency of arm swing when the baby laughs loud, the frequency of leg swing, the acceleration of kicking the legs, heartbeat parameters, and body temperature parameters.
Preferably, the behavior feature extraction module comprises a matching identification module. And the behavior feature extraction module sends the behavior feature parameters to the matching identification module. And the matching identification module analyzes the behavior characteristic parameters. Preferably, the matching identification module compares the behavior characteristic parameters with the behavior models in the database by using cosine similarity and outputs a group of similar values. And sorting the similarity values from large to small, and outputting the physical exercise scheme corresponding to the maximum similarity in the database.
Preferably, since there are hundreds of individual individualities of infants, the preset behavior model may not be able to completely match and extract the behavior characteristics of the infant. Therefore, a behavior model that can be built by deep learning from the behavior of the infant is particularly important. Preferably, the cloud server further comprises a deep learning training module. And the deep learning training module adopts a CNN algorithm to train to obtain a CNN model. The CNN model comprises an input layer, a convolution layer, a full connection layer and an output layer; and a hidden layer is arranged between the input layer and the convolution layer. A hidden layer is arranged between the convolution layer and the full connection layer. The deep learning training module transmits the trained CNN model to the feature extraction module.
The feature extraction module extracts the physiological information, the sound information and/or the behavior information of the infant by adopting a CNN model to obtain a feature vector or a behavior model. The feature extraction module transfers the feature vectors to the matching identification module. The feature extraction module transfers the behavior model to a library of behavior models in a database.
Preferably, the CNN model extracts and processes the feature vector or the behavior model as follows:
A. inputting physiological information, the sound information and/or the behavior information of the baby into a cloud server through a first intelligent terminal and storing the physiological information, the sound information and/or the behavior information in an input layer of a CNN model;
B. performing convolution on the physiological information, the sound information and/or the behavior information on a volume base layer to extract a feature vector; the formula of the calculation on the base layer of the volume is: conv ═ σ (imgMat ° W + b).
Wherein conv represents convolution layer input parameters, σ represents an activation function ReLU, imgMat represents a gray image matrix, W represents a convolution kernel, represents a convolution operation, and b represents an offset value.
C. The input layer is propagated forward to the convolutional layer, and the process of forward propagation is expressed as:
a2＝σ(z2)＝σ(a1*W2+b2)。
wherein, a2The convolution layer input parameters, subscripts for layer number, asterisks for convolution, b for bias, and σ for the activation function ReLU.
D. The hidden layer is propagated forward to the convolutional layer, and the forward propagation process is expressed as:
a1＝σ(z1)＝σ(a1-1*W1+b1)
wherein, alThe convolutional layer input parameters are denoted by subscript, convolution by asterisk, bias by b, and activation function ReLU by σ.
E. The hidden layer is propagated to the full connection layer in a forward direction, and the forward propagation process comprises the following steps:
A1＝σ(z1)＝σ(W1a1-1+b1)。
wherein, AlThe parameters are input for the fully connected layers, subscripts denote the number of layers, asterisks denote convolution, b denotes bias, and σ is the activation function ReLU.
Preferably, the deep learning training module learns and grasps the specific pattern of the limb behaviors of the infant based on the behavior feature parameters of the infant. The specific patterns include at least different emotional patterns. The expressive emotions of each infant were not the same for similar frequencies of crying, arm swing and leg swing. Some expressed emotions are hunger, some expressed emotions are uncomfortable, and some expressed emotions are wanted to embrace. Therefore, the deep learning training module learns and grasps the specific mode of the limb behaviors of the infant based on the behavior characteristic parameters of the infant, and can know the specific emotion expression mode of the infant more individually. The deep learning training module generates an infant training regimen based on a particular pattern including at least motion training, thought training, and/or emotion training.
Preferably, the feature extraction module extracts the behavior feature parameters of the infant based on the behavior model established by the deep learning module corresponding to the specific mode, and matches the corresponding action training unit, the thinking training unit and the emotion training unit based on the behavior feature parameters. The deep learning training module selects the action training unit, the thinking training unit and the emotion training unit with harmony within a set threshold range based on a specific mode of the infant to form an infant training scheme.
For example, the feature extraction module extracts the behavioral feature parameters based on the CNN model. And at least one of the behavioral characteristic parameters corresponds to a particular mode of the infant. The feature extraction module matches the behavior feature parameters with the behavior model by adopting cosine similarity, and takes at least one action training unit, at least one thinking training unit and/or at least one emotion training unit corresponding to the maximum similarity value as the training scheme constituent elements. Although the motion training unit, the thinking training unit and/or the emotion training unit are extracted based on the behavior feature parameters, it is important to conform to the coordination of the human science of the infant. If the action training unit and the thinking training unit are contradictory, the baby can feel uncomfortable, and the opposite effect is achieved. Preferably, the coordination value between each action training unit, between the thought training units and/or between the emotion training units is calculated.
For example, the physiological parameters corresponding to the action training unit are matched with the physiological parameters corresponding to the thought training unit. If the matching degree is between 60% and 80%, the action training unit and the thinking training unit are coordinated. If the matching degree is less than 60%, the action training unit and the thinking training unit are uncoordinated. For example, the action training unit slows the heart rate and the breathing rate, and the thinking training unit needs a large amount of oxygen and increases the breathing rate. If the matching degree is less than 60%, the body of the infant is difficult to feel, and the effect of thinking training cannot be achieved. If the matching degree is greater than 80%, the body of the infant may be damaged due to the fast heartbeat speed.
Similarly, the physiological parameters corresponding to the action training unit are matched with the physiological parameters corresponding to the emotion training unit, and the physiological parameters corresponding to the thinking training unit and the physiological parameters corresponding to the emotion training unit are matched within the range of the preset threshold value. Preferably, the preset threshold range is not limited to 60% to 80%, and may be preset according to specific actions, emotions and thinking training.
Namely, the deep learning training module and the behavior feature extraction module of the cloud server further help the baby to carry out personalized monitoring and training, help the baby to grow healthily, form good thinking habits and characters, and can effectively control emotion.
It should be noted that the above-mentioned embodiments are exemplary, and that those skilled in the art, having benefit of the present disclosure, may devise various arrangements that are within the scope of the present disclosure and that fall within the scope of the invention. It should be understood by those skilled in the art that the present specification and figures are illustrative only and are not limiting upon the claims. The scope of the invention is defined by the claims and their equivalents.
Claims (9)
1. An intelligent infant monitoring system at least comprises a first intelligent terminal, a second intelligent terminal and a cloud server, and is characterized in that,
the first intelligent terminal is used for automatically collecting physiological information, sound information and/or behavior information of the baby,
the second intelligent terminal is used for manually inputting life record information and/or actual emotional state information of the baby,
the cloud server at least comprises a teaching module and an emotional state analysis module which utilizes an emotional state analysis algorithm to analyze theoretical emotional states based on the physiological information, the sound information and/or the behavior information of the infant, wherein,
the cloud server further comprises a behavior feature extraction module that extracts behavior feature parameters of the infant based on the physiological information, the sound information, and/or the behavior information of the infant and selects a matching physical exercise regimen based on an analysis of the behavior feature parameters,
the characteristic extraction module extracts the behavior characteristic parameters of the baby based on the specific mode established by the deep learning module and matches the corresponding action training unit, thinking training unit and emotion training unit based on the behavior characteristic parameters,
the deep learning training module selects the action training units, the thinking training units and the emotion training units with harmony within a set threshold range to form a baby training scheme based on a specific mode of a baby.
2. The intelligent infant monitoring system of claim 1, wherein the cloud server further comprises a deep learning training module that learns and masters specific patterns of infant limb behavior based on behavior feature parameters of an infant, and
the deep learning training module generates an infant training regimen including at least motion training, thinking training, and/or emotion training based on the particular pattern.
3. The intelligent infant monitoring system of claim 2, wherein the teaching module performs a teaching process of theoretical emotional states stored in a preset database based on the actual emotional state information inputted by the second intelligent terminal,
and the emotional state analysis module instructs the second intelligent terminal to send a demand prompt and/or an early warning prompt to the current user based on the demand information corresponding to the actual emotional state of the infant.
4. The intelligent infant monitoring system of claim 3, wherein the teach module in the cloud server analyzes and completes the teach process based on the life recording information and/or the actual emotional state information inputted by the second intelligent terminal, wherein,
the teach module pre-configures parameters of the state analysis algorithm based on at least two types of abnormal emotional state information.
5. The intelligent infant monitoring system of claim 4, wherein the emotional state analysis module stores the life recording information and/or the actual emotional state information of the infant, which is inputted by the user to the second intelligent terminal in a text, voice, video and/or graphic manner, and the external condition, physiological information, sound information and/or behavior information automatically collected by the first intelligent terminal in a preset database in an associated manner,
or the first intelligent terminal records the external conditions inducing the actual emotional state of the infant and stores or provides the external conditions to the preset database in a form of being associated with the corresponding actual emotional state,
the emotional state analysis module analyzes based on a correlation between a specific emotional state of the infant and the external condition, and instructs the second smart terminal to warn based on the correlation of the specific emotional state.
6. The intelligent infant monitoring system of claim 5, wherein the cloud server further comprises a correction module,
the correction module corrects theoretical emotional state information determined by analyzing the external conditions, the physiological information, the sound information and/or the behavior information collected by the first intelligent terminal based on the actual emotional state information of the infant, and a preset database which can be searched according to life record information, the physiological information and/or the external conditions of the infant is formed by the corrected theoretical emotional state information.
7. The intelligent infant monitoring system of claim 6 wherein the cloud server is provided with a care advice module for medical information association with a third party medical institution,
the nursing suggestion module retrieves corresponding medical nursing information based on the actual emotional state of the infant and sends prompt information through the second intelligent terminal, and/or
The nursing suggestion module prompts the infant disease warning information of the nearby area and/or the specific time period issued by the third-party medical institution through the second intelligent terminal based on the geographic position determined by the second intelligent terminal, and prompts the infant prevalence rate estimated based on the infant physiological information acquired by the first intelligent terminal through the second intelligent terminal.
8. The intelligent infant monitoring system of claim 7 wherein the nursing advice module issues infant nursing advice via the second intelligent terminal based on infant disease alert information provided by a third party medical institution for a vicinity and/or for a specific period of time.
9. The intelligent infant monitoring system of claim 8 wherein the cloud server further comprises an infant profile matching an infant personality,
the infant profile creates and adaptively adjusts initial configuration information based on the infant's life recording information and actual emotional state change trend information to form infant emotional parameters,
the infant configuration file selects a corresponding infant care scheme based on the analysis of the emotional parameters of the infant and sends the infant care scheme to a second intelligent terminal; wherein the content of the first and second substances,
the initial configuration information comprises at least the birth date, blood type and/or sex of the infant.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811306109.2A CN109480868B (en) | 2018-11-02 | 2018-11-02 | Intelligent infant monitoring system |
| CN202210218118.6A CN114569131A (en) | 2018-11-02 | 2018-11-02 | Intelligent analysis system for infant demand |
| CN202210218119.0A CN114569132A (en) | 2018-11-02 | 2018-11-02 | Infant training system based on teaching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811306109.2A CN109480868B (en) | 2018-11-02 | 2018-11-02 | Intelligent infant monitoring system |
Related Child Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210218119.0A Division CN114569132A (en) | 2018-11-02 | 2018-11-02 | Infant training system based on teaching |
| CN202210218118.6A Division CN114569131A (en) | 2018-11-02 | 2018-11-02 | Intelligent analysis system for infant demand |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109480868A CN109480868A (en) | 2019-03-19 |
| CN109480868B true CN109480868B (en) | 2022-07-22 |
Family
ID=65693841
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210218118.6A Pending CN114569131A (en) | 2018-11-02 | 2018-11-02 | Intelligent analysis system for infant demand |
| CN202210218119.0A Pending CN114569132A (en) | 2018-11-02 | 2018-11-02 | Infant training system based on teaching |
| CN201811306109.2A Active CN109480868B (en) | 2018-11-02 | 2018-11-02 | Intelligent infant monitoring system |
Family Applications Before (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210218118.6A Pending CN114569131A (en) | 2018-11-02 | 2018-11-02 | Intelligent analysis system for infant demand |
| CN202210218119.0A Pending CN114569132A (en) | 2018-11-02 | 2018-11-02 | Infant training system based on teaching |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN114569131A (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110400639B (en) * | 2019-07-12 | 2023-09-15 | 上海启倍生健康科技有限公司 | Multimode infant language life management vehicle based on artificial intelligence technology |
| CN110808071A (en) * | 2019-10-29 | 2020-02-18 | 浙江萌宠日记信息科技股份有限公司 | Mother and infant information transfer method and system based on information fusion |
| CN110930643A (en) * | 2019-12-11 | 2020-03-27 | 南京邮电大学 | Intelligent safety system and method for preventing infants from being left in car |
| 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 |
| CN111420214A (en) * | 2020-03-24 | 2020-07-17 | 西安文理学院 | Voice appeasing system capable of autonomously identifying emotion of baby |
| CN116134463A (en) * | 2020-06-30 | 2023-05-16 | 五代健康有限公司 | Intelligent system and method for event tracking |
| CN111951830B (en) * | 2020-06-30 | 2024-06-07 | 苏州航天系统工程有限公司 | Identification method, server, mobile phone, external equipment and system for baby crying |
| CN113892829A (en) * | 2021-09-09 | 2022-01-07 | 旭宝乐科技(深圳)有限公司 | Remote control milk brewing method and device based on behavior monitoring and storage medium |
| CN114073504B (en) * | 2021-11-26 | 2024-06-25 | 四川护理职业学院 | Infant vital sign monitoring system and monitoring method |
| CN114469072B (en) * | 2021-12-08 | 2023-08-08 | 四川大学华西第二医院 | Method for automatically predicting psychological development of infants by using camera |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105518683A (en) * | 2014-05-23 | 2016-04-20 | 施京 | System and method for child characteristics identification and potential development and assessment |
| CN107025371A (en) * | 2017-03-09 | 2017-08-08 | 安徽创易心理科技有限公司 | A kind of mood is dynamically monitored and management method and system |
| CN108074633A (en) * | 2017-12-27 | 2018-05-25 | 广东小天才科技有限公司 | Exercise coordination monitoring method based on daily activities and wearable device |
| CN108308947A (en) * | 2015-10-28 | 2018-07-24 | 曾迪 | Multi-mode controls acoustooptic interaction children logic, sense system training game pad |
| CN108492829A (en) * | 2018-03-13 | 2018-09-04 | 广州势必可赢网络科技有限公司 | Method, device and system for reminding crying of baby |
| CN108806765A (en) * | 2018-05-23 | 2018-11-13 | 刘博韬 | A kind of intelligence baby monitoring system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9882675B2 (en) * | 2013-08-16 | 2018-01-30 | Origin Wireless, Inc. | Time-reversal wireless systems having asymmetric architecture |
| US20160292983A1 (en) * | 2015-04-05 | 2016-10-06 | Smilables Inc. | Wearable infant monitoring device |
-
2018
- 2018-11-02 CN CN202210218118.6A patent/CN114569131A/en active Pending
- 2018-11-02 CN CN202210218119.0A patent/CN114569132A/en active Pending
- 2018-11-02 CN CN201811306109.2A patent/CN109480868B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105518683A (en) * | 2014-05-23 | 2016-04-20 | 施京 | System and method for child characteristics identification and potential development and assessment |
| CN108308947A (en) * | 2015-10-28 | 2018-07-24 | 曾迪 | Multi-mode controls acoustooptic interaction children logic, sense system training game pad |
| CN107025371A (en) * | 2017-03-09 | 2017-08-08 | 安徽创易心理科技有限公司 | A kind of mood is dynamically monitored and management method and system |
| CN108074633A (en) * | 2017-12-27 | 2018-05-25 | 广东小天才科技有限公司 | Exercise coordination monitoring method based on daily activities and wearable device |
| CN108492829A (en) * | 2018-03-13 | 2018-09-04 | 广州势必可赢网络科技有限公司 | Method, device and system for reminding crying of baby |
| CN108806765A (en) * | 2018-05-23 | 2018-11-13 | 刘博韬 | A kind of intelligence baby monitoring system |
Non-Patent Citations (1)
| Title |
|---|
| 一种仿婴儿欠自由度四足爬行机器人;张秀丽;《机器人》;20160731;第38卷(第4期);第458-466页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109480868A (en) | 2019-03-19 |
| CN114569131A (en) | 2022-06-03 |
| CN114569132A (en) | 2022-06-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109480868B (en) | Intelligent infant monitoring system | |
| CN108310587B (en) | Sleep control device and method | |
| Schuller et al. | The interspeech 2017 computational paralinguistics challenge: Addressee, cold & snoring | |
| US10528121B2 (en) | Smart wearable devices and methods for automatically configuring capabilities with biology and environment capture sensors | |
| Kalantarian et al. | A survey of diet monitoring technology | |
| CN107427716B (en) | Method and system for optimizing and training human performance | |
| Bi et al. | AutoDietary: A wearable acoustic sensor system for food intake recognition in daily life | |
| CN108806765A (en) | A kind of intelligence baby monitoring system | |
| WO2019058284A1 (en) | Lactation coaching system and method | |
| CN110584601B (en) | Old man cognitive function monitoring and evaluation system | |
| CN110099601A (en) | Detection respiration parameter simultaneously provides the system and method for biofeedback | |
| WO2019019491A1 (en) | Method and system for detecting blood oxygen saturation | |
| CN115120236A (en) | Emotion recognition method and device, wearable device and storage medium | |
| Franchak et al. | Long-form recording of infant body position in the home using wearable inertial sensors | |
| US20230363668A1 (en) | Device for detecting challenging behaviors in people with autism | |
| CN113288145A (en) | Teaching device and method for training emotion control capability | |
| CN112674760A (en) | Wearable sensor-based Parkinson upper limb movement detection method | |
| KR102196779B1 (en) | Artificial intelligence based necklace type wearable device | |
| CN108461125B (en) | Memory training device for the elderly | |
| US20190254532A1 (en) | Baby language translation system and method of using the same | |
| US11776373B2 (en) | System and method for detecting child distress and generating suggestion for relieving child distress | |
| Patyk | Detecting eating episodes from daily patterns of wrist motion using recurrent neural networks | |
| JP7435965B2 (en) | Information processing device, information processing method, learning model generation method, and program | |
| Pradeep et al. | Infant Monitoring System Using Convolutional Neural Network | |
| Jahangir et al. | Development of a Smart Infant Monitoring System for Working Mothers |
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 |