CN114710555A - Infant monitoring method and device - Google Patents
Infant monitoring method and device Download PDFInfo
- Publication number
- CN114710555A CN114710555A CN202210627666.4A CN202210627666A CN114710555A CN 114710555 A CN114710555 A CN 114710555A CN 202210627666 A CN202210627666 A CN 202210627666A CN 114710555 A CN114710555 A CN 114710555A
- Authority
- CN
- China
- Prior art keywords
- feature
- monitoring
- abnormal
- target
- state detection
- 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.)
- Pending
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
- A61B5/02—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
- A61B5/02055—Simultaneously evaluating both cardiovascular condition and temperature
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/66—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for extracting parameters related to health condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/04—Babies, e.g. for SIDS detection
-
- 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
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/14542—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring blood gases
Abstract
The application discloses a baby monitoring method and a device, wherein the baby monitoring method comprises the following steps: acquiring visual monitoring data, corresponding audio monitoring data and corresponding physical sign monitoring data corresponding to a target baby; according to the visual monitoring data, the audio monitoring data, the physical sign monitoring data and a preset abnormal state detection model, performing abnormal state detection on the target infant to obtain an abnormal state detection result; if the abnormal state detection result is abnormal, determining a target visual monitoring feature, a corresponding target audio monitoring feature and a corresponding target sign monitoring feature corresponding to the abnormal state detection result by performing model interpretation on the abnormal state detection result; according to the target visual monitoring feature, the target audio monitoring feature and the target sign monitoring feature, positioning the abnormal reason of which the abnormal state detection result is abnormal: and pushing the reason for the abnormality to the guardian of the target baby. The application solves the technical problem of low infant monitoring accuracy.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a baby monitoring method and device.
Background
With the continuous development of artificial intelligence, the application of artificial intelligence is more and more extensive, and at present, when a baby is monitored, whether the baby cries or not is detected, if so, a guardian of the baby is informed to process the crying, but when the baby is in a crying state, the guardian usually has difficulty in accurately judging the reason why the baby cries or cries, namely, the reason why the baby is in an abnormal state, so that the accuracy of monitoring the baby by the guardian is influenced.
Disclosure of Invention
The present application mainly aims to provide a method and a device for infant monitoring, which aim to solve the technical problem of low accuracy of infant monitoring in the prior art.
In order to achieve the above object, the present application provides an infant monitoring method, which includes:
acquiring visual monitoring data, corresponding audio monitoring data and corresponding physical sign monitoring data corresponding to a target baby;
according to the visual monitoring data, the audio monitoring data, the sign monitoring data and a preset abnormal state detection model, performing abnormal state detection on the target infant to obtain an abnormal state detection result;
if the abnormal state detection result is abnormal, determining a target visual monitoring feature, a corresponding target audio monitoring feature and a corresponding target sign monitoring feature corresponding to the abnormal state detection result by performing model interpretation on the abnormal state detection result;
according to the target visual monitoring feature, the target audio monitoring feature and the target sign monitoring feature, positioning an abnormal reason of which the abnormal state detection result is abnormal;
and pushing the abnormal reason to the guardian of the target infant.
The present application further provides a baby monitoring device, the device is a virtual device, the baby monitoring device includes:
the acquisition module is used for acquiring visual monitoring data, corresponding audio monitoring data and corresponding physical sign monitoring data corresponding to a target baby;
the abnormal state detection module is used for detecting the abnormal state of the target infant according to the visual monitoring data, the audio monitoring data, the sign monitoring data and a preset abnormal state detection model to obtain an abnormal state detection result;
the model interpretation module is used for determining a target visual monitoring feature, a corresponding target audio monitoring feature and a corresponding target sign monitoring feature corresponding to the abnormal state detection result by performing model interpretation on the abnormal state detection result if the abnormal state detection result is abnormal;
an abnormal reason positioning module, configured to position an abnormal reason of which the abnormal state detection result is abnormal according to the target visual monitoring feature, the target audio monitoring feature, and the target sign monitoring feature;
and the abnormal reason pushing module is used for pushing the abnormal reason to the guardian of the target infant.
The present application further provides an electronic device, the electronic device including: a memory, a processor and a program of the infant monitoring method stored on the memory and executable on the processor, the program of the infant monitoring method when executed by the processor implementing the steps of the infant monitoring method as described above.
The present application also provides a computer readable storage medium having a program for implementing a method for infant monitoring stored thereon, which program, when being executed by a processor, implements the steps of the method for infant monitoring as described above.
The present application also provides a computer program product comprising a computer program which, when being executed by a processor, performs the steps of the infant monitoring method as described above.
Compared with the technical means of monitoring the baby by detecting whether the baby cries or not in the prior art, the baby monitoring method and the baby monitoring device firstly acquire visual monitoring data, corresponding audio monitoring data and corresponding physical sign monitoring data corresponding to the target baby; according to the visual monitoring data, the audio monitoring data, the sign monitoring data and a preset abnormal state detection model, abnormal state detection is carried out on the target baby to obtain an abnormal state detection result, the purpose that whether the baby is in an abnormal state or not is detected through multiple dimensions of the visual data, the auditory data and the sign data is achieved, and therefore the accuracy of baby abnormal state detection can be improved; if the abnormal state detection result is abnormal, determining a target visual monitoring feature, a corresponding target audio monitoring feature and a corresponding target sign monitoring feature corresponding to the abnormal state detection result by performing model interpretation on the abnormal state detection result; according to the target visual monitoring feature, the target audio monitoring feature and the target physical sign monitoring feature, the abnormal state detection result is positioned to be an abnormal reason, the reason that the baby is in the abnormal state is positioned in a model interpretation mode, the abnormal reason is pushed to the guardian of the target baby, the guardian can correspondingly care the baby according to the abnormal reason, the technical defect that the accuracy of infant monitoring of the guardian is affected due to the fact that the reason that the baby is in the abnormal state is difficult to accurately judge is overcome, and the accuracy of infant monitoring is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and, together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a schematic flow chart of a first embodiment of an infant monitoring method according to the present application;
FIG. 2 is a schematic flow chart of a second embodiment of the infant monitoring method of the present application;
fig. 3 is a schematic structural diagram of a hardware operating environment related to an infant monitoring method according to an embodiment of the present application.
The objectives, features, and advantages of the present application will be further described with reference to the accompanying drawings.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, embodiments accompanying figures are described in detail below. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Example one
In a first embodiment of the infant monitoring method of the present application, referring to fig. 1, the infant monitoring method includes:
step S10, acquiring visual monitoring data, corresponding audio monitoring data and corresponding physical sign monitoring data corresponding to a target baby;
step S20, according to the visual monitoring data, the audio monitoring data, the physical sign monitoring data and a preset abnormal state detection model, performing abnormal state detection on the target infant to obtain an abnormal state detection result;
step S30, if the abnormal state detection result is abnormal, determining a target visual monitoring feature, a corresponding target audio monitoring feature and a corresponding target sign monitoring feature corresponding to the abnormal state detection result by performing model interpretation on the abnormal state detection result;
step S40, according to the target visual monitoring feature, the target audio monitoring feature and the target sign monitoring feature, positioning the abnormal condition detection result as an abnormal reason;
step S50, pushing the abnormality reason to the guardian of the target infant.
In this embodiment, it should be noted that image acquisition device, audio acquisition device and sign data acquisition device are installed near target baby, wherein, image acquisition device can be the camera for gather baby's image as visual monitoring data, audio acquisition device can be the microphone, is used for gathering baby's audio frequency as audio monitoring data, sign data acquisition device can be wearable smart machine, for example smart watch or smart bracelet etc. and the sign monitoring data of gathering can be one or more in the sign eigenvalue such as heartbeat, body temperature and blood oxygen content.
As one example, steps S10 to S50 include: acquiring a baby image corresponding to a target baby, a corresponding baby audio and corresponding physical sign monitoring data, wherein the physical sign monitoring data consists of at least one physical sign monitoring feature; carrying out feature extraction on the infant image to obtain each visual monitoring feature, and carrying out feature extraction on the infant audio to obtain each audio monitoring feature; inputting an input sample composed of each visual monitoring feature, each audio monitoring feature and each physical sign monitoring feature into the preset abnormal state detection model, judging whether the target infant is in abnormal state detection or not, and obtaining an abnormal state detection result; if the abnormal state detection result is abnormal, respectively calculating the feature contribution degree of each visual monitoring feature, each audio monitoring feature and each physical sign monitoring feature to the abnormal state detection result by performing model interpretation on the abnormal state detection result; according to each feature contribution degree, determining a target visual monitoring feature, a corresponding target audio monitoring feature and a corresponding target sign monitoring feature corresponding to the abnormal state detection result; taking the target visual monitoring feature, the target audio monitoring feature and the target sign monitoring feature as indexes, and positioning the abnormal reason of which the abnormal state detection result is abnormal; and pushing the abnormal reason to the guardian of the target infant.
Wherein the visual monitoring data comprises an infant image corresponding to the target infant, the audio monitoring data comprises infant audio emitted by the infant, the physical sign monitoring data comprises at least one physical sign monitoring feature,
the step of detecting the abnormal state of the target infant according to the visual monitoring data, the audio monitoring data, the physical sign monitoring data and a preset abnormal state detection model to obtain an abnormal state detection result comprises the following steps:
step S21, respectively extracting visual features of the infant image according to visual feature extraction models corresponding to different visual features to obtain each visual monitoring feature;
step S22, respectively carrying out audio feature extraction on the infant audio according to audio feature extraction models corresponding to different audio features to obtain each audio monitoring feature;
step S23, splicing each visual monitoring feature, each audio monitoring feature and each physical sign monitoring feature to obtain an infant state feature;
and step S24, carrying out abnormal state detection on the target infant according to the infant state characteristics and the preset abnormal state detection model to obtain an abnormal state detection result.
In this embodiment, it should be noted that the visual monitoring feature may be an oral-nasal visual monitoring feature representing an oral-nasal shielding degree, or an arm visual monitoring feature representing an arm swing amplitude, and accordingly, the visual feature extraction model may be a feature extraction model extracting the oral-nasal visual monitoring feature from the infant image, or a feature extraction model extracting the arm visual monitoring feature from the infant image. The audio monitoring features can be crying audio monitoring features representing crying degree, and can also be breathing audio monitoring features representing breathing smoothness, and correspondingly, the audio feature extraction model can be a feature extraction model for extracting the crying audio monitoring features from the infant audio, and can also be a feature extraction model for extracting the breathing audio monitoring features from the infant audio. The feature extraction model may be a deep machine learning model, such as a convolutional neural network model or the like.
As one example, steps S21 to S23 include: respectively inputting the infant image into visual feature extraction models corresponding to different visual features, and respectively extracting different visual monitoring features in the infant image; respectively inputting the infant audio into audio feature extraction models corresponding to different audio features, and respectively extracting different audio monitoring features in the infant audio; splicing the visual monitoring features, the audio monitoring features and the physical sign monitoring features to obtain infant state features, wherein the visual monitoring features, the audio monitoring features and the physical sign monitoring features can be vectors or matrixes with preset dimensions; the infant state features are input into the preset abnormal state detection model, the infant state features are mapped to corresponding infant state classification labels, whether the target infant is in an abnormal state or not is judged according to the infant state classification labels, and an abnormal state detection result is obtained, wherein the abnormal state detection result can represent whether the target infant is in a binary classification label of the abnormal state or not.
The step of detecting the abnormal state of the target infant according to the infant state characteristics and the preset abnormal state detection model to obtain an abnormal state detection result comprises the following steps:
step S241, constructing a matrix of the baby state characteristics changing along with time in a preset time period to obtain baby state characteristic time sequence data;
step S242, predicting the state of the target infant at the next time step by inputting the infant state feature time series data into the preset abnormal state detection model, and performing abnormal state detection on the target infant to obtain an abnormal state detection result.
In the present embodiment, it should be noted that, in many situations, when the infant is in an abnormal state, for example, when the infant is in a state of breathing difficulty covered by the mouth and nose or when the infant tries to jump over the rail of the crib, the infant is already in a dangerous state, and therefore, in order to ensure that the infant is not in the dangerous state, it is necessary to monitor the state of the infant by predicting the state of the infant on the time line in advance. Accordingly, the preset abnormal state detection model may be a recurrent neural network model, and may be used to predict the state of the infant at the next time step in advance.
As one example, steps S241 to S242 include: acquiring infant state characteristics of a target infant in a preset time period; constructing a matrix of the infant state characteristics changing along with time in a preset time period to obtain infant state characteristic time sequence data; predicting the state of the target infant at the next time step by inputting the infant state feature time series data into the preset abnormal state detection model to obtain an infant state label; and judging whether the target infant is in an abnormal state or not according to the infant state label to obtain an abnormal state detection result.
Wherein the visual monitoring data at least comprises a visual monitoring feature, the audio monitoring data at least comprises an audio monitoring feature, the physical sign monitoring data at least comprises a physical sign monitoring feature,
the step of determining the target visual monitoring feature, the corresponding target audio monitoring feature and the corresponding target physical sign monitoring feature corresponding to the abnormal state detection result by performing model interpretation on the abnormal state detection result comprises:
step S31, respectively calculating a first feature contribution degree of each of the visual monitoring features to the abnormal state detection result, a second feature contribution degree of each of the audio monitoring features to the abnormal state detection result, and a third feature contribution degree of each of the vital sign monitoring features to the abnormal state detection result;
step S32, selecting a target visual monitoring feature from the visual monitoring features according to the first feature contribution degrees;
step S33, selecting a target audio monitoring feature from the audio monitoring features according to the second feature contribution degrees;
step S34, selecting a target physical sign monitoring feature from the physical sign monitoring features according to the third feature contribution degrees.
In this embodiment, it should be noted that the first feature contribution degree is a degree of influence of the visual monitoring feature on the abnormal state detection result, the second feature contribution degree is a degree of influence of the audio monitoring feature on the abnormal state detection result, and the third feature contribution degree is a degree of influence of the physical sign monitoring feature on the abnormal state detection result. The feature contribution degree includes a positive feature contribution degree and a negative feature contribution degree, where the positive feature contribution degree indicates that the abnormal state detection result has a positive influence, that is, the abnormal state detection result is supported to be abnormal, and the positive influence is exerted on the probability increase that the abnormal state detection result is abnormal, and the negative feature contribution degree indicates that the abnormal state detection result has a negative influence, that is, the abnormal state detection result is not supported to be abnormal, and the negative influence is exerted on the probability increase that the abnormal state detection result is abnormal.
As one example, steps S31 to S34 include: based on the preset abnormal state detection Model, respectively calculating a first feature contribution degree of each visual monitoring feature to the abnormal state detection result, a second feature contribution degree of each audio monitoring feature to the abnormal state detection result, and a third feature contribution degree of each physical monitoring feature to the abnormal state detection result through a preset feature contribution degree calculation mode, wherein the preset feature contribution degree calculation mode comprises SHAP (SHAPLY Additive ExPlations) and LIME (Local Interactive Model-Additive Explosition) and the like; selecting the feature with the largest first feature contribution degree from all the visual monitoring features as a target visual monitoring feature; selecting the feature with the largest second feature contribution degree from all the audio monitoring features as a target audio monitoring feature; and selecting a target physical sign monitoring characteristic with the maximum third characteristic contribution degree from all the physical sign monitoring characteristics. The specific calculation process for calculating the feature contribution degree by using the SHAP or LIME is the prior art, and is not described herein again.
Wherein, the step of locating the abnormal reason for which the abnormal state detection result is abnormal according to the target visual monitoring feature, the target audio monitoring feature and the target sign monitoring feature comprises:
step S41, acquiring a visual feature label corresponding to the target visual monitoring feature, an audio feature label corresponding to the target audio monitoring feature and a physical sign feature label corresponding to the target physical sign monitoring feature;
step S42, splicing the visual feature label, the audio feature label and the physical sign feature label to obtain an index label;
step S43, according to the index tag, finding the abnormal reason that the abnormal state detection result is abnormal.
As one example, steps S41 to S43 include: acquiring a visual feature tag corresponding to the target visual monitoring feature, an audio feature tag corresponding to the target audio monitoring feature and a physical sign feature tag corresponding to the target physical sign monitoring feature; splicing the visual feature labels, the audio feature labels and the physical sign feature labels to obtain index labels; respectively calculating the label similarity between the index label and each preset abnormal reason label; selecting a preset abnormal reason corresponding to a label with the label similarity larger than a preset similarity threshold value from all preset abnormal reason labels as a target abnormal reason label; and taking the target abnormal reason label as the abnormal reason of which the abnormal state detection result is abnormal. The index tag and the preset abnormal reason tag can be vectors, and the tag similarity can be the distance between the vectors.
Compared with the technical means of monitoring the baby by detecting whether the baby has crying or not in the prior art, the embodiment of the application firstly acquires visual monitoring data, corresponding audio monitoring data and corresponding physical sign monitoring data corresponding to the target baby; according to the visual monitoring data, the audio monitoring data, the sign monitoring data and a preset abnormal state detection model, abnormal state detection is carried out on the target infant to obtain an abnormal state detection result, so that the purpose of detecting whether the infant is in an abnormal state or not through multiple dimensions of the visual data, the auditory data and the sign data is achieved, and therefore the accuracy of infant abnormal state detection can be improved; if the abnormal state detection result is abnormal, determining a target visual monitoring feature, a corresponding target audio monitoring feature and a corresponding target sign monitoring feature corresponding to the abnormal state detection result by performing model interpretation on the abnormal state detection result; according to the target visual monitoring feature, the target audio monitoring feature and the target physical sign monitoring feature, the abnormal state detection result is positioned to be an abnormal reason, the reason that the baby is in the abnormal state is positioned in a model interpretation mode, the abnormal reason is pushed to the guardian of the target baby, the guardian can correspondingly care the baby according to the abnormal reason, the technical defect that the accuracy of infant monitoring of the guardian is affected due to the fact that the reason that the baby is in the abnormal state is difficult to accurately judge is overcome, and the accuracy of infant monitoring is improved.
Example two
Further, referring to fig. 2, based on the first embodiment, in another embodiment of the infant monitoring method of the present application, the step of locating the abnormal cause of the abnormal state detection result as the abnormal cause according to the target visual monitoring feature, the target audio monitoring feature and the target physical sign monitoring feature includes:
step A10, splicing the target vision monitoring feature, the target audio monitoring feature and the target sign monitoring feature to obtain an abnormal factor feature;
step A20, predicting the abnormal state detection result as the abnormal reason according to the abnormal factor characteristics and a preset abnormal reason positioning model.
As an example, the steps a10 to a20 include: splicing the target visual monitoring feature, the target audio monitoring feature and the target sign monitoring feature to obtain a spliced feature, and taking the spliced feature as an abnormal factor feature; inputting the abnormal factor characteristics into a preset abnormal reason positioning model, and mapping the abnormal factor characteristics into a target abnormal reason label; and taking a preset abnormal reason corresponding to the target abnormal reason label as an abnormal reason of which the abnormal state detection result is abnormal.
Wherein the preset abnormal state detection model comprises an abnormal factor characteristic classification model,
the step of predicting the abnormal reason of which the abnormal state detection result is abnormal according to the abnormal factor characteristics and a preset abnormal reason positioning model comprises the following steps:
step A21, inputting the abnormal factor features into the abnormal factor feature classification model, classifying the abnormal factor features to obtain feature classification labels;
step a22, according to the feature classification label, finding the abnormal state detection result as an abnormal reason.
As an example, the steps a21 to a22 include: inputting the abnormal factor features into the abnormal factor feature classification model for classification, and mapping the abnormal factor features into corresponding feature classification labels, wherein the feature classification labels can be vectors; and calculating the label similarity between the feature classification label and each preset abnormal reason label, and taking the abnormal reason corresponding to the preset abnormal reason label with the highest label similarity as the abnormal reason of which the abnormal state detection result is abnormal.
The embodiment of the application provides an abnormal cause positioning method, which comprises the steps of screening target visual monitoring features in each visual monitoring feature, screening target audio monitoring in each audio monitoring feature and screening target sign monitoring features in each sign monitoring feature in a model interpretation mode, achieving the purpose of removing information which is irrelevant to the abnormal state of a current infant or has low relevance from all monitoring information of the infant, splicing the target visual monitoring features, the target audio monitoring features and the target sign monitoring features according to the target visual monitoring features, obtaining abnormal factor features with high relevance information causing the abnormal state of the target infant, and predicting the abnormal cause of an abnormal state detection result to be abnormal according to the abnormal factor features and a preset abnormal cause positioning model, the purpose of positioning the abnormal reason according to the abnormal factor characteristics of the highly-associated information which causes the target infant to be in the abnormal state is achieved, and the accuracy of positioning the abnormal reason when the infant is in the abnormal state is improved.
EXAMPLE III
An embodiment of the present application further provides an infant monitoring device, which includes:
the acquisition module is used for acquiring visual monitoring data, corresponding audio monitoring data and corresponding physical sign monitoring data corresponding to a target infant;
the abnormal state detection module is used for detecting the abnormal state of the target infant according to the visual monitoring data, the audio monitoring data, the sign monitoring data and a preset abnormal state detection model to obtain an abnormal state detection result;
the model interpretation module is used for performing model interpretation on the abnormal state detection result to determine a target visual monitoring feature, a corresponding target audio monitoring feature and a corresponding target sign monitoring feature corresponding to the abnormal state detection result if the abnormal state detection result is abnormal;
an abnormal reason positioning module, configured to position an abnormal reason of which the abnormal state detection result is abnormal according to the target visual monitoring feature, the target audio monitoring feature, and the target sign monitoring feature;
and the abnormal reason pushing module is used for pushing the abnormal reason to the guardian of the target infant.
Optionally, the visual monitoring data at least includes a visual monitoring feature, the audio monitoring data at least includes an audio monitoring feature, the vital signs monitoring data at least includes a vital signs monitoring feature, and the model interpretation module is further configured to:
respectively calculating a first feature contribution degree of each visual monitoring feature to the abnormal state detection result, a second feature contribution degree of each audio monitoring feature to the abnormal state detection result and a third feature contribution degree of each physical monitoring feature to the abnormal state detection result;
selecting a target visual monitoring feature from the visual monitoring features according to the first feature contribution degrees;
selecting a target audio monitoring feature from the audio monitoring features according to the second feature contribution degrees;
and selecting a target sign monitoring feature from the sign monitoring features according to the contribution degree of each third feature.
Optionally, the abnormality cause positioning module is further configured to:
acquiring a visual feature tag corresponding to the target visual monitoring feature, an audio feature tag corresponding to the target audio monitoring feature and a physical sign feature tag corresponding to the target physical sign monitoring feature;
splicing the visual feature label, the audio feature label and the physical sign feature label to obtain an index label;
and searching the abnormal reason of which the abnormal state detection result is abnormal according to the index tag.
Optionally, the abnormality cause positioning module is further configured to:
splicing the target visual monitoring feature, the target audio monitoring feature and the target sign monitoring feature to obtain an abnormal factor feature;
and predicting the abnormal reason of which the abnormal state detection result is abnormal according to the abnormal factor characteristics and a preset abnormal reason positioning model.
Optionally, the preset abnormal state detection model includes an abnormal factor feature classification model, and the abnormal cause positioning module is further configured to:
classifying the abnormal factor features by inputting the abnormal factor features into the abnormal factor feature classification model to obtain feature classification labels;
and searching the abnormal reason of which the abnormal state detection result is abnormal according to the characteristic classification label.
Optionally, the visual monitoring data includes an infant image corresponding to the target infant, the audio monitoring data includes an infant audio emitted by the infant, the sign monitoring data includes at least one sign monitoring feature, and the abnormal state detection module is further configured to:
respectively extracting visual features of the infant image according to visual feature extraction models corresponding to different visual features to obtain each visual monitoring feature;
respectively extracting audio features of the infant audio according to audio feature extraction models corresponding to different audio features to obtain each audio monitoring feature;
splicing each visual monitoring feature, each audio monitoring feature and each physical sign monitoring feature to obtain an infant state feature;
and detecting the abnormal state of the target infant according to the infant state characteristics and the preset abnormal state detection model to obtain an abnormal state detection result.
Optionally, the abnormal state detection module is further configured to:
constructing a matrix of the baby state characteristics changing along with time in a preset time period to obtain baby state characteristic time sequence data;
and predicting the state of the target infant at the next time step by inputting the infant state feature time series data into the preset abnormal state detection model, and detecting the abnormal state of the target infant to obtain an abnormal state detection result.
By adopting the infant monitoring method in the embodiment, the infant monitoring device provided by the application solves the technical problem of low infant monitoring accuracy. Compared with the prior art, the beneficial effects of the infant monitoring device provided by the embodiment of the present application are the same as the beneficial effects of the infant monitoring method provided by the above embodiment, and other technical features of the infant monitoring device are the same as those disclosed in the above embodiment method, which are not described herein again.
Example four
An embodiment of the present application provides an electronic device, and the electronic device includes: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the infant monitoring method according to the first embodiment.
Referring now to FIG. 3, shown is a schematic diagram of an electronic device suitable for use in implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 3, the electronic device may include a processing apparatus (e.g., a central processing unit, a graphic processor, etc.) that may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) or a program loaded from a storage apparatus into a Random Access Memory (RAM). In the RAM, various programs and data necessary for the operation of the electronic apparatus are also stored. The processing device, ROM and RAM are trained with each other over the bus. An input/output (I/O) interface is also connected to the bus.
Generally, the following systems may be connected to the I/O interface: input devices including, for example, touch screens, touch pads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, and the like; output devices including, for example, Liquid Crystal Displays (LCDs), speakers, vibrators, and the like; storage devices including, for example, magnetic tape, hard disk, etc.; and a communication device. The communication means may allow the electronic device to communicate wirelessly or by wire with other devices to exchange data. While the figures illustrate an electronic device with various systems, it is to be understood that not all illustrated systems are required to be implemented or provided. More or fewer systems may alternatively be implemented or provided.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means, or installed from a storage means, or installed from a ROM. The computer program, when executed by a processing device, performs the above-described functions defined in the methods of the embodiments of the present disclosure.
By adopting the infant monitoring method in the embodiment, the electronic device provided by the application solves the technical problem of low infant monitoring accuracy. Compared with the prior art, the beneficial effects of the electronic device provided by the embodiment of the present application are the same as the beneficial effects of the infant monitoring method provided by the above embodiment, and other technical features of the electronic device are the same as those disclosed in the above embodiment method, which are not described herein again.
It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the foregoing description of embodiments, the particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
EXAMPLE five
The present embodiment provides a computer-readable storage medium having computer-readable program instructions stored thereon for performing the method of infant monitoring in the first embodiment.
The computer readable storage medium provided by the embodiments of the present application may be, for example, a usb disk, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or a combination of any of the above. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present embodiment, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device. Program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer-readable storage medium may be embodied in an electronic device; or may be present alone without being incorporated into the electronic device.
The computer readable storage medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring visual monitoring data, corresponding audio monitoring data and corresponding physical sign monitoring data corresponding to a target baby; according to the visual monitoring data, the audio monitoring data, the physical sign monitoring data and a preset abnormal state detection model, abnormal state detection is carried out on the target infant, and an abnormal state detection result is obtained; if the abnormal state detection result is abnormal, determining a target visual monitoring feature, a corresponding target audio monitoring feature and a corresponding target sign monitoring feature corresponding to the abnormal state detection result by performing model interpretation on the abnormal state detection result; according to the target visual monitoring feature, the target audio monitoring feature and the target sign monitoring feature, positioning an abnormal reason of which the abnormal state detection result is abnormal; and pushing the abnormal reason to the guardian of the target infant.
Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented by software or hardware. Wherein the names of the modules do not in some cases constitute a limitation of the unit itself.
The computer-readable storage medium provided by the application stores computer-readable program instructions for executing the infant monitoring method, and solves the technical problem of low infant monitoring accuracy. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the embodiment of the present application are the same as those of the infant monitoring method provided by the above embodiment, and are not described herein again.
Example six
The present application also provides a computer program product comprising a computer program which, when being executed by a processor, performs the steps of the infant monitoring method as described above.
The computer program product provided by the application solves the technical problem of low infant monitoring accuracy. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present application are the same as those of the infant monitoring method provided by the above embodiment, and are not described herein again.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.
Claims (10)
1. An infant monitoring method, comprising:
acquiring visual monitoring data, corresponding audio monitoring data and corresponding physical sign monitoring data corresponding to a target baby;
according to the visual monitoring data, the audio monitoring data, the sign monitoring data and a preset abnormal state detection model, performing abnormal state detection on the target infant to obtain an abnormal state detection result;
if the abnormal state detection result is abnormal, determining a target visual monitoring feature, a corresponding target audio monitoring feature and a corresponding target sign monitoring feature corresponding to the abnormal state detection result by performing model interpretation on the abnormal state detection result;
according to the target visual monitoring feature, the target audio monitoring feature and the target sign monitoring feature, positioning an abnormal reason of which the abnormal state detection result is abnormal;
and pushing the abnormal reason to the guardian of the target infant.
2. The method of claim 1, wherein the visual monitoring data includes at least one visual monitoring characteristic, the audio monitoring data includes at least one audio monitoring characteristic, the vital signs monitoring data includes at least one vital signs monitoring characteristic,
the step of determining the target visual monitoring feature, the corresponding target audio monitoring feature and the corresponding target physical sign monitoring feature corresponding to the abnormal state detection result by performing model interpretation on the abnormal state detection result comprises:
respectively calculating a first feature contribution degree of each visual monitoring feature to the abnormal state detection result, a second feature contribution degree of each audio monitoring feature to the abnormal state detection result and a third feature contribution degree of each physical monitoring feature to the abnormal state detection result;
selecting a target visual monitoring feature from the visual monitoring features according to the contribution degree of each first feature;
selecting a target audio monitoring feature from the audio monitoring features according to the second feature contribution degrees;
and selecting a target physical sign monitoring characteristic from the physical sign monitoring characteristics according to the third characteristic contribution degrees.
3. The infant monitoring method of claim 1, wherein the step of locating the abnormal condition detection result as an abnormal cause of the abnormality according to the target visual monitoring feature, the target audio monitoring feature and the target physical sign monitoring feature comprises:
acquiring a visual feature tag corresponding to the target visual monitoring feature, an audio feature tag corresponding to the target audio monitoring feature and a physical sign feature tag corresponding to the target physical sign monitoring feature;
splicing the visual feature label, the audio feature label and the physical sign feature label to obtain an index label;
and searching the abnormal reason of which the abnormal state detection result is abnormal according to the index tag.
4. The infant monitoring method of claim 1, wherein the step of locating the abnormal condition detection result as an abnormal cause of the abnormality according to the target visual monitoring feature, the target audio monitoring feature and the target physical sign monitoring feature comprises:
splicing the target visual monitoring feature, the target audio monitoring feature and the target physical sign monitoring feature to obtain an abnormal factor feature;
and predicting the abnormal reason of which the abnormal state detection result is abnormal according to the abnormal factor characteristics and a preset abnormal reason positioning model.
5. The infant monitoring method of claim 4, wherein the predetermined abnormal state detection model comprises an abnormal factor feature classification model,
the step of predicting the abnormal reason of which the abnormal state detection result is abnormal according to the abnormal factor characteristics and a preset abnormal reason positioning model comprises the following steps:
classifying the abnormal factor features by inputting the abnormal factor features into the abnormal factor feature classification model to obtain feature classification labels;
and searching the abnormal reason of which the abnormal state detection result is abnormal according to the characteristic classification label.
6. The method of claim 1, wherein the visual monitoring data includes images of a baby corresponding to the target baby, the audio monitoring data includes audio of the baby emitted by the baby, the vital signs monitoring data includes at least one vital signs monitoring feature,
the step of detecting the abnormal state of the target infant according to the visual monitoring data, the audio monitoring data, the physical sign monitoring data and a preset abnormal state detection model to obtain an abnormal state detection result comprises the following steps:
respectively extracting visual features of the infant image according to visual feature extraction models corresponding to different visual features to obtain each visual monitoring feature;
respectively extracting audio features of the infant audio according to audio feature extraction models corresponding to different audio features to obtain each audio monitoring feature;
splicing each visual monitoring feature, each audio monitoring feature and each physical sign monitoring feature to obtain an infant state feature;
and detecting the abnormal state of the target infant according to the infant state characteristics and the preset abnormal state detection model to obtain an abnormal state detection result.
7. The infant monitoring method of claim 6, wherein the step of detecting abnormal conditions of the target infant according to the infant status characteristics and the predetermined abnormal condition detection model to obtain abnormal condition detection results comprises:
constructing a matrix of the baby state characteristics changing along with time in a preset time period to obtain baby state characteristic time sequence data;
and predicting the state of the target infant at the next time step by inputting the infant state feature time series data into the preset abnormal state detection model, and detecting the abnormal state of the target infant to obtain an abnormal state detection result.
8. An infant monitoring device, characterized in that the infant monitoring device:
the acquisition module is used for acquiring visual monitoring data, corresponding audio monitoring data and corresponding physical sign monitoring data corresponding to a target infant;
the abnormal state detection module is used for detecting the abnormal state of the target infant according to the visual monitoring data, the audio monitoring data, the sign monitoring data and a preset abnormal state detection model to obtain an abnormal state detection result;
the model interpretation module is used for determining a target visual monitoring feature, a corresponding target audio monitoring feature and a corresponding target sign monitoring feature corresponding to the abnormal state detection result by performing model interpretation on the abnormal state detection result if the abnormal state detection result is abnormal;
an abnormal reason positioning module, configured to position an abnormal reason of which the abnormal state detection result is abnormal according to the target visual monitoring feature, the target audio monitoring feature, and the target sign monitoring feature;
and the abnormal reason pushing module is used for pushing the abnormal reason to the guardian of the target infant.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method of infant monitoring of any one of claims 1-7.
10. A computer-readable storage medium, in which a program for implementing a method for infant monitoring is stored, and which is executed by a processor for implementing the steps of the method for infant monitoring as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210627666.4A CN114710555A (en) | 2022-06-06 | 2022-06-06 | Infant monitoring method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210627666.4A CN114710555A (en) | 2022-06-06 | 2022-06-06 | Infant monitoring method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114710555A true CN114710555A (en) | 2022-07-05 |
Family
ID=82177680
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210627666.4A Pending CN114710555A (en) | 2022-06-06 | 2022-06-06 | Infant monitoring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114710555A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115482836A (en) * | 2022-08-05 | 2022-12-16 | 深圳市景创科技电子股份有限公司 | Infant AI monitoring method and device |
| CN116304596A (en) * | 2023-05-26 | 2023-06-23 | 深圳市明源云科技有限公司 | Indoor child safety monitoring method and device, electronic equipment and storage medium |
| CN116386671A (en) * | 2023-03-16 | 2023-07-04 | 宁波星巡智能科技有限公司 | Infant crying type identification method, device, equipment and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107742116A (en) * | 2017-11-13 | 2018-02-27 | 湖南超能机器人技术有限公司 | A kind of infant emotion change detection and knowledge method for distinguishing |
| CN108615333A (en) * | 2018-05-25 | 2018-10-02 | 朱利 | Infant asphyxia early warning system based on artificial intelligence and method |
| CN108992079A (en) * | 2018-06-12 | 2018-12-14 | 珠海格力电器股份有限公司 | A kind of Infant behavior monitoring method based on emotion recognition and Application on Voiceprint Recognition |
| CN109509484A (en) * | 2018-12-25 | 2019-03-22 | 科大讯飞股份有限公司 | A kind of prediction technique and device of baby crying reason |
| US20190130720A1 (en) * | 2017-10-27 | 2019-05-02 | Benjamin Lui | Systems and methods for a machine learning baby monitor |
| US20190226943A1 (en) * | 2018-01-23 | 2019-07-25 | Mitsubishi Heavy Industries, Ltd. | Facility condition monitoring device and facility condition monitoring method |
| CN110706449A (en) * | 2019-09-04 | 2020-01-17 | 中移（杭州）信息技术有限公司 | Infant monitoring method and device, camera equipment and storage medium |
| CN111281358A (en) * | 2020-02-24 | 2020-06-16 | 湘潭大学 | Real-time monitoring system of baby robot |
| CN112069949A (en) * | 2020-08-25 | 2020-12-11 | 开放智能机器（上海）有限公司 | Artificial intelligence-based infant sleep monitoring system and monitoring method |
| CN112650608A (en) * | 2020-12-28 | 2021-04-13 | 广州虎牙科技有限公司 | Abnormal root cause positioning method and related device and equipment |
| CN113496586A (en) * | 2020-04-08 | 2021-10-12 | 北京沃东天骏信息技术有限公司 | Infant monitoring method, infant monitoring device, infant monitoring equipment and storage medium |
| CN113989893A (en) * | 2021-11-02 | 2022-01-28 | 安徽兰臣信息科技有限公司 | Expression and voice bimodal-based children emotion recognition algorithm |
| CN114187660A (en) * | 2021-12-08 | 2022-03-15 | 云知声（上海）智能科技有限公司 | Infant care device and method based on artificial intelligence and infant behavior model |
| CN114463937A (en) * | 2022-03-07 | 2022-05-10 | 云知声智能科技股份有限公司 | Infant monitoring method and device, electronic equipment and storage medium |
-
2022
- 2022-06-06 CN CN202210627666.4A patent/CN114710555A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190130720A1 (en) * | 2017-10-27 | 2019-05-02 | Benjamin Lui | Systems and methods for a machine learning baby monitor |
| CN107742116A (en) * | 2017-11-13 | 2018-02-27 | 湖南超能机器人技术有限公司 | A kind of infant emotion change detection and knowledge method for distinguishing |
| US20190226943A1 (en) * | 2018-01-23 | 2019-07-25 | Mitsubishi Heavy Industries, Ltd. | Facility condition monitoring device and facility condition monitoring method |
| CN108615333A (en) * | 2018-05-25 | 2018-10-02 | 朱利 | Infant asphyxia early warning system based on artificial intelligence and method |
| CN108992079A (en) * | 2018-06-12 | 2018-12-14 | 珠海格力电器股份有限公司 | A kind of Infant behavior monitoring method based on emotion recognition and Application on Voiceprint Recognition |
| CN109509484A (en) * | 2018-12-25 | 2019-03-22 | 科大讯飞股份有限公司 | A kind of prediction technique and device of baby crying reason |
| CN110706449A (en) * | 2019-09-04 | 2020-01-17 | 中移（杭州）信息技术有限公司 | Infant monitoring method and device, camera equipment and storage medium |
| CN111281358A (en) * | 2020-02-24 | 2020-06-16 | 湘潭大学 | Real-time monitoring system of baby robot |
| CN113496586A (en) * | 2020-04-08 | 2021-10-12 | 北京沃东天骏信息技术有限公司 | Infant monitoring method, infant monitoring device, infant monitoring equipment and storage medium |
| CN112069949A (en) * | 2020-08-25 | 2020-12-11 | 开放智能机器（上海）有限公司 | Artificial intelligence-based infant sleep monitoring system and monitoring method |
| CN112650608A (en) * | 2020-12-28 | 2021-04-13 | 广州虎牙科技有限公司 | Abnormal root cause positioning method and related device and equipment |
| CN113989893A (en) * | 2021-11-02 | 2022-01-28 | 安徽兰臣信息科技有限公司 | Expression and voice bimodal-based children emotion recognition algorithm |
| CN114187660A (en) * | 2021-12-08 | 2022-03-15 | 云知声（上海）智能科技有限公司 | Infant care device and method based on artificial intelligence and infant behavior model |
| CN114463937A (en) * | 2022-03-07 | 2022-05-10 | 云知声智能科技股份有限公司 | Infant monitoring method and device, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| OKEKE STEPHEN ET AL.: ""Real-Time Infant-at-Risk Detection and Tracking using Faster RCNN-Based Convolution Neural Network"", 《2019 INTERNATIONAL CONFERENCE ON COMPUTING, POWER AND COMMUNICATION TECHNOLOGIES (GUCON)》 * |
| 魏丽娜: ""婴儿情绪信息的模式识别技术研究与实现"", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115482836A (en) * | 2022-08-05 | 2022-12-16 | 深圳市景创科技电子股份有限公司 | Infant AI monitoring method and device |
| CN116386671A (en) * | 2023-03-16 | 2023-07-04 | 宁波星巡智能科技有限公司 | Infant crying type identification method, device, equipment and storage medium |
| CN116304596A (en) * | 2023-05-26 | 2023-06-23 | 深圳市明源云科技有限公司 | Indoor child safety monitoring method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114710555A (en) | Infant monitoring method and device | |
| CN115357470B (en) | Information generation method and device, electronic equipment and computer readable medium | |
| CN110287810B (en) | Vehicle door motion detection method, device and computer readable storage medium | |
| CN110070076B (en) | Method and device for selecting training samples | |
| CN110287817B (en) | Target recognition and target recognition model training method and device and electronic equipment | |
| CN116277040A (en) | Mechanical arm vibration suppression method, device, equipment and medium based on deep learning | |
| US9648481B2 (en) | Calling a response provider based on detection of an emergency situation | |
| CN116563007A (en) | Credit risk prediction method, electronic equipment and readable storage medium | |
| CN114116431B (en) | System operation health detection method and device, electronic equipment and readable storage medium | |
| CN115460353A (en) | Teaching tracking camera equipment configuration method and device, electronic equipment and medium | |
| CN112560690A (en) | Multi-modal characteristic character attribute labeling method, device, equipment and medium | |
| CN114063964A (en) | Volume compensation optimization method and device, electronic equipment and readable storage medium | |
| CN116109932B (en) | House security detection method, house security detection device, electronic equipment and readable storage medium | |
| CN114863650B (en) | Obstacle early warning method and device, electronic equipment and readable storage medium | |
| CN115205982B (en) | Standing tracking detection method, electronic device, and medium | |
| US20180130365A1 (en) | Handwritten homework monitoring using wearable device | |
| CN115470292B (en) | Block chain consensus method, device, electronic equipment and readable storage medium | |
| CN116737051B (en) | Visual touch combination interaction method, device and equipment based on touch screen and readable medium | |
| CN114584607B (en) | Communication connection establishing method and device, electronic equipment and readable storage medium | |
| CN115840016B (en) | Backup reduction method, device, equipment and computer medium of chromatographic analysis system | |
| CN114781567B (en) | Detection equipment installation method and device, electronic equipment and readable storage medium | |
| CN114647721B (en) | Educational intelligent robot control method, device and medium | |
| CN114742754A (en) | Pulmonary nodule detection method, electronic device and computer-readable storage medium | |
| CN109697470B (en) | Recognition model training method and device, electronic equipment and storage medium | |
| CN115910321A (en) | Abnormal behavior detection system, method, electronic device and readable storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220705 |