CN116304596A - Indoor child safety monitoring method and device, electronic equipment and storage medium - Google Patents
Indoor child safety monitoring method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116304596A CN116304596A CN202310603321.XA CN202310603321A CN116304596A CN 116304596 A CN116304596 A CN 116304596A CN 202310603321 A CN202310603321 A CN 202310603321A CN 116304596 A CN116304596 A CN 116304596A
- Authority
- CN
- China
- Prior art keywords
- data
- safety monitoring
- characteristic data
- child safety
- risk
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 360
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000007781 pre-processing Methods 0.000 claims abstract description 36
- 238000012806 monitoring device Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims description 52
- 230000033001 locomotion Effects 0.000 claims description 26
- 238000001914 filtration Methods 0.000 claims description 18
- 238000004140 cleaning Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 15
- 238000012706 support-vector machine Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 11
- 230000001133 acceleration Effects 0.000 claims description 9
- 230000036772 blood pressure Effects 0.000 claims description 9
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 8
- 239000008280 blood Substances 0.000 claims description 8
- 210000004369 blood Anatomy 0.000 claims description 8
- 229910052760 oxygen Inorganic materials 0.000 claims description 8
- 239000001301 oxygen Substances 0.000 claims description 8
- 238000013473 artificial intelligence Methods 0.000 abstract description 6
- 238000004590 computer program Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000006399 behavior Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000009499 grossing Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000033764 rhythmic process Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 210000000707 wrist Anatomy 0.000 description 2
- 241000699670 Mus sp. Species 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Alarm Systems (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The application discloses an indoor child safety monitoring method, an indoor child safety monitoring device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, wherein the indoor child safety monitoring method comprises the following steps: collecting original characteristic data in a monitoring environment, wherein the original characteristic data at least comprises image data, sound data, temperature data, humidity data and air quality data; preprocessing the original characteristic data to obtain target characteristic data; inputting the target characteristic data into a preset target child safety monitoring model to obtain a safety monitoring result; judging whether a child in the monitoring environment has safety risk or not according to the original characteristic data and the safety monitoring result; if the original characteristic data and the preset risk prompt are transmitted to the guardian account. The technical problem that indoor children safety monitoring degree of accuracy is low has been solved to this application.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to an indoor child safety monitoring method, an indoor child safety monitoring device, electronic equipment and a storage medium.
Background
As the modern society is rapidly developed and the life rhythm of people is accelerated, the time that children independently move in home is more and more, and the indoor child safety problem is also gradually gaining importance. Traditional safety measures, such as door and window locks, safety protection nets and the like, can reduce the probability of accidents to a certain extent, but still have certain potential safety hazards. In addition, there are some safety monitoring methods based on artificial intelligence technology, but these methods mainly perform feature recognition on the behavior action of the child to determine whether the current behavior action of the child is dangerous action, wherein the feature dimension for performing the risk determination is only image information, so that the accuracy of safety monitoring of the child indoors is lower to a certain extent due to comparison on one side.
Disclosure of Invention
The main purpose of the application is to provide an indoor child safety monitoring method, an indoor child safety monitoring device, electronic equipment and a storage medium, and aims to solve the technical problem of low indoor child safety monitoring accuracy.
To achieve the above object, the present application provides an indoor child safety monitoring method, including:
collecting original characteristic data in a monitoring environment, wherein the original characteristic data at least comprises image data, sound data, temperature data, humidity data and air quality data;
Preprocessing the original characteristic data to obtain target characteristic data, wherein the preprocessing at least comprises cleaning, filtering and normalizing;
inputting the target characteristic data into a preset target child safety monitoring model to obtain a safety monitoring result, wherein the target child safety monitoring model is obtained by training according to a plurality of groups of historical characteristic data;
judging whether a child in the monitoring environment has safety risk or not according to the original characteristic data and the safety monitoring result;
if the original characteristic data and the preset risk prompt are transmitted to the guardian account.
Optionally, before the step of preprocessing the raw feature data to obtain target feature data, the method further includes:
collecting motion data and physiological data of a target child in the monitoring environment, wherein the motion data at least comprise acceleration data, and the physiological data at least comprise heart rate data, blood pressure data and blood oxygen saturation data;
the motion data and the physiological data are added to the raw feature data.
Optionally, before the step of preprocessing the raw feature data to obtain target feature data, the method further includes:
Carrying out three-dimensional modeling on the monitoring environment according to the image data to obtain a three-dimensional space coordinate system corresponding to the monitoring environment;
identifying a target child in the monitoring environment according to the image data, and obtaining a first coordinate of the target child in the three-dimensional space coordinate system;
determining a risk distance according to a second coordinate and the first coordinate of a preset risk position in the three-dimensional space coordinate system, wherein the preset risk position at least comprises one of a balcony and a window;
the risk distance is added to the raw feature data.
Optionally, before the step of inputting the target feature data into a preset target child safety monitoring model to obtain a safety monitoring result, the method further includes:
acquiring and preprocessing historical characteristic data in a plurality of groups of indoor environments to obtain target historical characteristic data, wherein the historical characteristic data at least comprise a plurality of groups of image data, sound data, temperature data, humidity data, air quality data, motion data, physiological data and risk distances in various scenes of the indoor environments;
Based on a preset support vector machine algorithm, an initial child safety monitoring model is constructed;
training the initial child safety monitoring model according to the target historical characteristic data and risk labels corresponding to the target historical characteristic data to obtain a target child safety monitoring model, wherein the risk labels at least comprise risks and no risks.
Optionally, the training the initial child safety monitoring model according to the target historical feature data and the risk tag corresponding to the target historical feature data, and the step of obtaining the target child safety monitoring model includes:
dividing the target historical characteristic data into a training set and a testing set;
the characteristic data in the training set is input into the initial child safety monitoring model to obtain a corresponding first safety monitoring result;
determining a first prediction precision of the initial child safety monitoring model according to a risk tag corresponding to the feature data in the training set and a corresponding first safety monitoring result;
iteratively optimizing model parameters of the initial child safety monitoring model based on the first prediction precision of the initial child safety monitoring model to obtain a child safety monitoring model to be detected;
The feature data in the training set are input into the child safety monitoring model to be tested, so that a corresponding second safety monitoring result is obtained;
determining a second prediction precision of the child safety monitoring model to be detected according to the risk tag corresponding to the characteristic data in the training set and a corresponding second safety monitoring result;
and if the second prediction precision accords with a preset precision threshold, setting the child safety monitoring model to be detected as a target child safety monitoring model.
Optionally, the step of preprocessing the raw feature data to obtain target feature data includes:
cleaning the original characteristic data to remove abnormal data in the original characteristic data, and obtaining first characteristic data;
filtering the first characteristic data to obtain second characteristic data;
and inputting the second characteristic data into a preset normalization function to obtain target characteristic data.
Optionally, the step of judging whether the child in the monitoring environment has a safety risk according to the original characteristic data and the safety monitoring result includes:
if the original characteristic data have the characteristic data exceeding a preset data threshold value or the safety monitoring result is that the risk exists, judging that the safety risk exists for the children in the monitoring environment;
And if the original characteristic data does not have the characteristic data exceeding the preset data threshold value and the safety monitoring result is that the safety monitoring result is risk-free, judging that the safety risk of the children in the monitoring environment does not exist.
The application also provides an indoor child safety monitoring device, indoor child safety monitoring device is applied to indoor child safety monitoring equipment, indoor child safety monitoring device includes:
the device comprises a characteristic acquisition module, a monitoring module and a control module, wherein the characteristic acquisition module is used for acquiring original characteristic data in a monitoring environment, and the original characteristic data at least comprises image data, sound data, temperature data, humidity data and air quality data;
the preprocessing module is used for preprocessing the original characteristic data to obtain target characteristic data, wherein the preprocessing at least comprises cleaning, filtering and normalization processing;
the safety monitoring module is used for inputting the target characteristic data into a preset target child safety monitoring model to obtain a safety monitoring result, wherein the target child safety monitoring model is obtained by training according to a plurality of groups of historical characteristic data;
the risk judging module is used for judging whether the child in the monitoring environment has safety risk or not according to the original characteristic data and the safety monitoring result;
And the risk prompt module is used for pushing the original characteristic data and the preset risk prompt to the guardian account if the original characteristic data and the preset risk prompt exist.
The application also provides an electronic device, which is an entity device, and includes: the indoor child safety monitoring system comprises a memory, a processor and a program of the indoor child safety monitoring method, wherein the program is stored in the memory and can run on the processor, and the program of the indoor child safety monitoring method can realize the steps of the indoor child safety monitoring method when being executed by the processor.
The present application also provides a computer readable storage medium having stored thereon a program for implementing an indoor child safety monitoring method, which when executed by a processor implements the steps of the indoor child safety monitoring method as described above.
The present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of an indoor child safety monitoring method as described above.
The application provides an indoor child safety monitoring method, device, electronic equipment and storage medium, firstly, original characteristic data in a monitoring environment are collected, wherein the original characteristic data at least comprise image data, sound data, temperature data, humidity data and air quality data, then the original characteristic data are preprocessed to obtain target characteristic data, the preprocessing at least comprises cleaning, filtering and normalization processing to filter noise in the characteristic data and enable the characteristic data to be more standardized, then the target characteristic data are input into a preset target child safety monitoring model to obtain a safety monitoring result, the target child safety monitoring model is obtained through training according to a plurality of groups of historical characteristic data, whether the child in the monitoring environment has safety risks or not is judged according to the original characteristic data and the safety monitoring result, if so, the original characteristic data and the preset risk prompt are pushed to a person, the indoor child safety monitoring is carried out by combining the original characteristic data of each characteristic dimension in the environment, various characteristic dimensions in the indoor environment are more comprehensively considered, and the defect that the safety monitoring situation of the child in the indoor environment is not monitored by combining the original characteristic data in the monitoring environment is overcome through the comprehensive characteristic recognition method, and the safety prompt is overcome, and the technical error of the safety monitoring situation is not timely judged.
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 that are required to be used in the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
FIG. 1 is a flow chart of a first embodiment of an indoor child safety monitoring method of the present application;
fig. 2 is a schematic diagram of a visual risk prompt at a mobile phone end in an embodiment of the present application;
FIG. 3 is a flow chart of a second embodiment of the indoor child safety monitoring method of the present application;
FIG. 4 is a schematic view of the structure of an indoor child safety monitoring device according to an embodiment of the present application;
fig. 5 is a schematic device structure diagram of a hardware operating environment related to an indoor child safety monitoring method in an embodiment of the present application.
The implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments.
Detailed Description
In order to make the above objects, features and advantages of the present application more comprehensible, the following description will make the technical solutions of the embodiments of the present application clear and complete with reference to the accompanying drawings of the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, based on the embodiments herein, which are within the scope of the protection of the present application, will be within the purview of one of ordinary skill in the art without the exercise of inventive faculty.
Example 1
At present, along with the rapid development of society, the life rhythm of people is accelerated, and the time that children independently move in home is more and more, so that the indoor child safety problem also draws more attention. Traditional safety measures, such as door and window locks, safety protection nets and the like, can reduce the probability of accidents to a certain extent, but still have certain potential safety hazards. There are some artificial intelligence technologies for these problems, but these methods mainly perform feature recognition on child behavior to determine whether the current child behavior is dangerous, where feature dimensions for performing danger determination only have image information, so comparing one-sided results in lower accuracy of safety monitoring for indoor children to some extent. Aiming at the technical problems, the embodiment of the application provides an indoor child safety monitoring scheme based on artificial intelligence, which mainly realizes intelligent monitoring on child behaviors by utilizing original characteristic data of each dimension in a monitoring environment and a target child safety monitoring model trained by an artificial intelligence technology, thereby achieving more comprehensive and accurate safety guarantee.
An embodiment of the present application provides an indoor child safety monitoring method, in a first embodiment of the indoor child safety monitoring method of the present application, referring to fig. 1, the indoor child safety monitoring method includes:
step S10, collecting original characteristic data in a monitoring environment, wherein the original characteristic data at least comprise image data, sound data, temperature data, humidity data and air quality data;
step S20, preprocessing the original characteristic data to obtain target characteristic data, wherein the preprocessing at least comprises cleaning, filtering and normalizing;
step S30, inputting the target characteristic data into a preset target child safety monitoring model to obtain a safety monitoring result, wherein the target child safety monitoring model is obtained by training according to a plurality of groups of historical characteristic data;
step S40, judging whether the child in the monitoring environment has safety risk or not according to the original characteristic data and the safety monitoring result;
and step S50, if the original characteristic data and the preset risk prompt are pushed to the guardian account.
In the embodiment of the present application, it should be noted that the monitored environment is an indoor environment, and the target child in the monitored environment may be one or more. The original characteristic data are mainly obtained through various sensors installed indoors, specifically, the image data can be obtained through a camera, and the image data at least comprise indoor environment image data and child image data which are collected through the camera; the sound data may be obtained by a microphone, the sound data may include decibel values, the temperature data may be obtained by a thermometer, the humidity data may be obtained by a hygrometer, and the air quality data may be obtained by a PM2.5 sensor. The above-mentioned various feature data are all numerical feature data, and there is no type of feature data. In addition, the preprocessing process of the original characteristic data is to remove abnormal values and missing values in the original characteristic data, and the original characteristic data of each dimension is normalized to a similar data scale, so that the original characteristic data is conveniently processed through a target child safety monitoring model, and the accuracy of a safety monitoring result is improved. In addition, when judging whether the child in the monitoring environment has a safety risk, it is required to judge whether the original feature data in the monitoring environment is abnormal and whether the safety monitoring result is risk-free, so as to avoid erroneous judgment caused by an error of the target child safety monitoring model, for example, when the temperature data in the environment is abnormally high, but the safety monitoring result output by the target child safety monitoring model is risk-free, and if there is a possibility of fire occurrence in this case, it is possible to determine that the child in the monitoring environment has a safety risk. When the original characteristic data and the preset risk prompt are pushed to the guardian account, the network can be connected with a sensor for collecting the monitoring environment, and the specific value of the original characteristic data is sent to an intelligent terminal connected with the network by the network, so that the user can know the risk existing in the monitoring environment in time, and safety measures can be conveniently taken in time.
As an example, steps S10 to S50 include: collecting original characteristic data in a monitoring environment through each sensor installed in the monitoring environment, wherein the original characteristic data at least comprise image data, sound data, temperature data, humidity data and air quality data; cleaning and filtering the original characteristic data to remove noise in the original characteristic data; normalizing the original characteristic data according to a preset normalization function to obtain target characteristic data; inputting the target characteristic data into a target child safety monitoring model trained in advance, and predicting the risk condition of the child in the monitoring environment through the target child safety monitoring model to obtain a safety monitoring result, wherein the safety monitoring result is risk or risk-free; judging whether the original characteristic data of each dimension of the original characteristic data has the characteristic data exceeding a preset threshold range or not, and if the characteristic data exceeding the preset threshold range exists, judging that the children in the monitoring environment have safety risks; if the characteristic data exceeding the preset threshold range does not exist, and the safety monitoring result is that the risk exists, judging that the safety risk exists for the children in the monitoring environment; if the characteristic data exceeding the preset threshold range does not exist, and the safety monitoring result is that the risk is not found, judging that the safety risk of the children in the monitoring environment does not exist. If the safety risk exists in the children in the monitoring environment, the original characteristic data and the preset risk prompt are sent to a monitoring account of the user through a network, and the original characteristic data and the preset risk prompt can be displayed on an intelligent terminal (such as a mobile phone).
Wherein, before the step of preprocessing the original feature data to obtain target feature data, the method further comprises:
step S11, acquiring motion data and physiological data of a target child in the monitoring environment, wherein the motion data at least comprise acceleration data, and the physiological data at least comprise heart rate data, blood pressure data and blood oxygen saturation data;
step S12, adding the motion data and the physiological data to the raw feature data.
In the embodiment of the application, it should be noted that the technical solution of the embodiment of the application adds the motion data and the physiological data of the target child as a part of the original characteristic data, and the motion data and the physiological data are acquired through an intelligent bracelet worn on the wrist of the target child. In the technical scheme of the embodiment of the application, whether the target child is in a state with a violent change in motion state or not can be analyzed through acceleration data, for example, falling and the like can lead to rapid acceleration increase, and heart rate data, blood pressure data and blood oxygen saturation data in physiological data can directly represent the body health state of the target child.
As an example, steps S11 to S12 include: acquiring movement data and physiological data of a target child through a smart bracelet worn on the wrist of the target child, wherein the movement data comprise acceleration data, and the physiological data comprise heart rate data, blood pressure data and blood oxygen saturation data; the motion data and the physiological data are added to the raw feature data.
In a possible embodiment, when physiological data of a target child in a monitoring environment is abnormal, it can be determined that the target child has a safety risk, and corresponding image data, sound data, humidity data, air quality data, heart rate data, blood pressure data, blood oxygen saturation data and risk monitoring results are sent to a mobile phone end of a user through a camera, a microphone, a thermometer, a hygrometer, a PM2.5 sensor and a smart bracelet worn by the target child, which are connected with the Internet, wherein the content displayed on the mobile phone end specifically comprises a video image with humidity of 90%, temperature of 20 ℃ and PM2.5 ug/m, heart rate of 125bpm, blood pressure of 140mmHg, blood oxygen of 98% and indoor audio frequency, the heart rate and the blood pressure are all significantly higher than a normal range, and the user is prompted to take safety measures in time.
As another example, in the case where the target child does not wear the smart band, an image corresponding to the target child is obtained by performing person recognition on the image data, and acceleration data of the target child is calculated according to the change of the recognized image of the target child in each frame, and the acceleration is added to the original data.
In addition, before the step of preprocessing the raw feature data to obtain target feature data, the method further includes:
step S13, carrying out three-dimensional modeling on the monitoring environment according to the image data to obtain a three-dimensional space coordinate system corresponding to the monitoring environment;
step S14, identifying a target child in the monitoring environment according to the image data, and obtaining a first coordinate of the target child in the three-dimensional space coordinate system;
step S15, determining a risk distance according to a second coordinate and the first coordinate of a preset risk position in the three-dimensional space coordinate system, wherein the preset risk position at least comprises one of a balcony and a window;
and step S16, adding the risk distance to the original characteristic data.
In the embodiment of the application, it should be noted that, by further processing the image data, the technical scheme of the embodiment of the application obtains the risk distance between the target child and the preset risk position in the indoor environment, and adds the risk distance to the original feature data, and compared with the collected original image data, the risk distance can more clearly represent the risk degree of the position of the target child, and the risk distance can be added to the original feature data to perform safety monitoring through the target child safety monitoring model, so that the accuracy of predicting the target child safety monitoring model is further improved, meanwhile, the dimension of the original feature data is enriched, when judging whether the child in the monitoring environment has safety risk or not, a referenceable index is increased, and missing report and false report of a risk prompt are avoided.
As an example, step S13 to step S16 include: selecting a panoramic image frame from image data acquired by a camera, wherein the panoramic image frame comprises a preset risk position in the indoor environment; selecting a point from the panoramic image frame as an origin of a three-dimensional space coordinate system, and carrying out three-dimensional modeling on a monitoring environment in the panoramic image frame based on the origin to obtain the three-dimensional space coordinate system of the monitoring environment; acquiring a preset risk position in the monitoring environment, and determining a second coordinate of the preset risk position in the monitoring environment, wherein the preset risk position can be obtained through manual annotation or intelligent identification; identifying a target child in the image data through a preset character recognition model, and determining a first coordinate of the target child, wherein the character recognition model can use existing character recognition models mature in various technologies, such as a Haar cascade classifier or a convolutional neural network model; calculating the risk distance between the target child and the preset risk positions according to the first coordinate and the second coordinate, wherein if more than one preset risk positions exist, the risk distances between the target child and each preset risk position are calculated respectively; the risk distance is added to the raw feature data.
The step of preprocessing the original characteristic data to obtain target characteristic data comprises the following steps:
step S21, cleaning the original characteristic data to remove abnormal data in the original characteristic data, and obtaining first characteristic data;
step S22, filtering the first characteristic data to obtain second characteristic data;
step S23, inputting the second characteristic data into a preset normalization function to obtain target characteristic data.
In the embodiment of the present application, it should be noted that, in the embodiment of the present application, the original feature data is preprocessed to filter noise in the original feature data, reject abnormal values and missing values, and obtain normalized target feature data so as to facilitate processing according to a target child safety monitoring model, so as to obtain a more accurate safety monitoring result. The process of cleaning the original characteristic data includes deleting a missing value and an abnormal value, wherein the missing value may be a blank characteristic value caused by that the corresponding characteristic data is not collected due to abnormal sensor, for example, at a certain moment, an intelligent bracelet for collecting physiological data of a target child fails, so that the collected heart rate is 0, but the heart rate is recovered to be normal after a short time, and the characteristic data with the heart rate of 0 needs to be removed from the original characteristic data so as not to influence a safety monitoring result; the anomaly may be a characteristic value that is abnormally high or low in the collected characteristic data due to sensor anomalies, such as a thermometer malfunction, resulting in a collected temperature value that is significantly below room temperature. The filtering process may be performed by various filters, such as a low-pass filter, a high-pass filter, a band-pass filter, or a smoothing filter, and is mainly used for filtering noise existing in the original characteristic data, such as noise interference in the collected sound data.
As an example, steps S21 to S23 include: deleting the missing value and the abnormal value in the original characteristic data to obtain first characteristic data; inputting the first characteristic data into a preset smoothing filter, and filtering the first characteristic data through the smoothing filter to obtain denoised second characteristic data; and inputting the second characteristic data into a preset normalization function to obtain target characteristic data after normalization processing.
As an example, the expression of the preset normalization function is:
wherein,,for +.>Normalized target feature data, ++>Is the +.>The>Characteristic data of individual dimensions->And->Respectively the +.>Maximum and minimum values in feature data of each dimension.
In addition, the step of judging whether the child in the monitoring environment has safety risk according to the original characteristic data and the safety monitoring result comprises the following steps:
step S41, if feature data exceeding a preset data threshold exists in the original feature data or the safety monitoring result is that the risk exists, judging that the safety risk exists for the children in the monitoring environment;
And step S42, if the original characteristic data does not have the characteristic data exceeding the preset data threshold value and the safety monitoring result is that the safety monitoring result is risk-free, judging that the safety risk of the children in the monitoring environment does not exist.
In the embodiment of the application, it should be noted that, the technical scheme of the embodiment of the application combines the preset data threshold value preset by the user, the original characteristic data and the safety monitoring result output by the target child safety monitoring model to judge whether the child in the monitoring environment has safety risks or not, comprehensively considers the data of each dimension, and improves the comprehensiveness and accuracy of indoor child safety monitoring. Each item of characteristic data in the original characteristic data can be independently used for judging whether safety risks exist, if one item exceeds a standard, for example, sound is larger than 70 db, heart rate is larger than 120, and the like, the safety risks of children in the monitoring environment can be determined, the safety monitoring result output by the target child safety monitoring model can also be independently used for judging whether the safety risks exist, and the safety risks of children in the monitoring environment can be confirmed only when the preset data threshold value is not exceeded in the original characteristic data and the safety monitoring result is no risk, so that safety risk missing report caused by errors is avoided, and the safety of indoor children is better ensured.
As an example, step S41 to step S42 include: judging whether feature data exceeding a preset data threshold exists in the original feature data; if the original characteristic data have the characteristic data exceeding the preset data threshold value, judging that the safety risk exists for the children in the monitoring environment; if the original characteristic data does not have the characteristic data exceeding the preset data threshold value, judging whether the safety monitoring result is at risk or not; if the safety monitoring result is that the risk exists, judging that the safety risk exists for the children in the monitoring environment, and if the safety monitoring result is that the risk does not exist, judging that the safety risk does not exist for the children in the monitoring environment.
The embodiment of the application provides an indoor child safety monitoring method, firstly, original characteristic data in a monitoring environment are collected, wherein the original characteristic data at least comprise image data, sound data, temperature data, humidity data and air quality data, the original characteristic data are preprocessed to obtain target characteristic data, the preprocessing at least comprises cleaning, filtering and normalization processing to filter noise in the characteristic data and enable the characteristic data to be more standardized, then the target characteristic data are input into a preset target child safety monitoring model to obtain a safety monitoring result, the target child safety monitoring model is obtained according to training of multiple groups of historical characteristic data, whether safety risks of children in the monitoring environment exist or not is judged according to the original characteristic data and the safety monitoring result, if so, the original characteristic data and the preset risk cues are pushed to a guardian account number, the technical scheme of the embodiment of the application comprehensively considers various characteristic dimensions in an indoor environment by combining the original characteristic data of each characteristic dimension in the environment, and the situation that the safety monitoring of the children in the indoor environment does not exist is completely overcome through the fact that the safety monitoring is carried out by combining the original characteristic data in the indoor environment, and the safety monitoring performance of the safety monitoring model is not comprehensively judged, and the technical error of the safety monitoring is prevented from being judged.
Example two
Further, in another embodiment of the present application, the same or similar content as the first embodiment may be referred to the above description, and will not be repeated. On this basis, before the step of inputting the target feature data into a preset target child safety monitoring model to obtain a safety monitoring result, referring to fig. 3, the method further includes:
step A10, acquiring and preprocessing historical characteristic data in a plurality of groups of indoor environments to obtain target historical characteristic data, wherein the historical characteristic data at least comprise a plurality of groups of image data, sound data, temperature data, humidity data, air quality data, motion data, physiological data and risk distances in various scenes of the indoor environments;
step A20, constructing an initial child safety monitoring model based on a preset support vector machine algorithm;
and step A30, training the initial child safety monitoring model according to the target historical characteristic data and risk labels corresponding to the target historical characteristic data to obtain a target child safety monitoring model, wherein the risk labels at least comprise risks and no risks.
In the embodiment of the present application, it should be noted that, the embodiment of the present application provides a method for training a target child safety monitoring model, in which multi-dimensional historical feature data including image data, sound data, temperature data, humidity data, air quality data, motion data, physiological data, and risk distance is specifically adopted as sample data for training, so that feature dimensions of the model are improved, comprehensiveness of safety monitoring is increased, and performance of the target child safety monitoring model is improved. The historical characteristic data under the multi-group indoor environment comprises the historical characteristic data corresponding to different indoor environments respectively, the multi-group image data, the sound data, the temperature data, the humidity data, the air quality data, the motion data, the physiological data and the risk distance under various scenes refer to the historical characteristic data corresponding to different activity scenes of the child activity in a certain indoor environment, the activity scenes can comprise playing, learning, dining, resting and the like, the historical characteristic data of various scenes in daily life are summarized, and the generalization capability of the target child safety monitoring model is effectively enhanced.
In addition, the target child safety monitoring model is constructed based on a support vector machine algorithm (Support Vector Machine, SVM), the support vector machine algorithm is a classification model, the input characteristic data can be subjected to classification processing to obtain a positive value output result or a negative value output result, in the embodiment of the application, the positive value output result can be a safety monitoring result with risk, namely, the classification result after classifying the input characteristic data through the classification model corresponding to the support vector machine is a positive value, then the safety monitoring result for predicting and outputting the child safety according to the input characteristic data is judged to be risk, and similarly, the negative value output result is a safety monitoring result with risk. Training the initial child safety monitoring model is supervised model training, historical characteristic data and risk labels corresponding to the historical characteristic data are required to be applied, the risk labels comprise risk labels or risk-free labels, the historical characteristic data are distinguished and marked manually, and the risk labels are used for representing whether safety risks exist for target children under the condition of each group of characteristic data in the historical characteristic data.
As an example, in the process of constructing the initial child safety monitoring model based on a preset support vector machine algorithm, the decision function expression of the applied initial child safety monitoring model is:
wherein,,for the output safety monitoring result, < >>As a sign function +.>For characteristic data set sequence number,/->For the total number of groups of feature data, +.>Is->Weights of group feature data ∈>Scalar (s)/(s)>∈+1,−1,/>When = +1, it means +.>Belongs to the positive category (i.e. positive output result), +.>-1 represents +.>Belongs to the negative category (i.e. negative output result), +.>Transposed row vector of column vector corresponding to feature data,/->Is->Column vectors corresponding to group feature data, +.>Is the bias value.
As an example, steps a10 to a30 include: acquiring historical characteristic data of a plurality of groups of indoor environments through sensors installed in various indoor environments, wherein the historical characteristic data at least comprises a plurality of groups of image data, sound data, temperature data, humidity data, air quality data, motion data, physiological data and risk distances of the indoor environments in various scenes; preprocessing the historical characteristic data to obtain target historical characteristic data, wherein the preprocessing at least comprises cleaning, filtering and normalizing; constructing a two-class model based on a Support Vector Machine (SVM) algorithm to obtain an initial child safety monitoring model; acquiring risk labels corresponding to each group of feature data in the target historical feature data, wherein the risk labels are manually input; dividing the target historical characteristic data into a training set and a testing set, training the initial child safety monitoring model through the training set so as to iteratively optimize model parameters of the initial child safety monitoring model, wherein the model parameters at least comprise: learning rate (learning rate), iteration number (iteration), depth (depth), loss function (loss function), and regularization parameter (regularization); testing whether the initial child safety monitoring model meets preset conditions or not through the test set, wherein the preset conditions at least comprise prediction accuracy; and if the initial child safety monitoring model meets the preset conditions, stopping training, and setting the trained initial child safety monitoring model as a target child safety monitoring model.
The step of training the initial child safety monitoring model according to the target historical feature data and the risk tag corresponding to the target historical feature data to obtain a target child safety monitoring model comprises the following steps:
step A31, dividing the target historical characteristic data into a training set and a testing set;
a32, obtaining a corresponding first safety monitoring result by inputting the characteristic data in the training set into the initial child safety monitoring model;
step A33, determining a first prediction precision of the initial child safety monitoring model according to a risk tag corresponding to the feature data in the training set and a corresponding first safety monitoring result;
step A34, iteratively optimizing model parameters of the initial child safety monitoring model based on the first prediction precision of the initial child safety monitoring model to obtain a child safety monitoring model to be detected;
step A35, obtaining a corresponding second safety monitoring result by inputting the characteristic data in the training set into the child safety monitoring model to be tested;
step A36, determining a second prediction precision of the child safety monitoring model to be detected according to a risk tag corresponding to the feature data in the training set and a corresponding second safety monitoring result;
And step A37, setting the child safety monitoring model to be tested as a target child safety monitoring model if the second prediction precision accords with a preset precision threshold.
In the embodiment of the present application, it should be noted that, the embodiment of the present application provides a method for training a target child safety monitoring model through target historical feature data, specifically, optimizing model parameters of an initial child safety monitoring model through a training set, and then testing whether the child safety monitoring model to be tested meets preset conditions through a testing set, so as to obtain a target child safety monitoring model meeting a preset precision threshold requirement, which is used for monitoring child safety conditions in an indoor environment, so that indoor child safety monitoring accuracy is improved, where the preset precision threshold is a percentage, for example, 98%.
As an example, steps a31 to a37 include: dividing the target historical characteristic data into a training set and a testing set based on a preset proportion, wherein the preset proportion can be 9:1, namely the ratio of the characteristic data group number in the training set to the characteristic data group number in the testing set is 9:1; inputting the characteristic data in the training set into the initial child safety monitoring model, and predicting the child safety condition corresponding to the input characteristic data through the initial child safety monitoring model to obtain a corresponding first safety monitoring result; calculating the ratio of the number of risk labels matched with the input characteristic data in the first safety monitoring results to the total number of the first safety monitoring results, and obtaining the first prediction accuracy of the initial child safety monitoring model; model parameters of the initial child safety monitoring model are adjusted, initial child safety monitoring models corresponding to each group of model parameters are obtained, and the execution steps are returned: inputting the characteristic data in the training set into the initial child safety monitoring model, and predicting the child safety condition corresponding to the input characteristic data through the initial child safety monitoring model to obtain a corresponding first safety monitoring result until the first prediction precision of the initial child safety monitoring model corresponding to each group of model parameters is obtained; selecting the group of model parameters corresponding to the initial child safety monitoring model with the highest prediction precision as optimized model parameters, and setting the initial child safety monitoring model corresponding to the optimized model parameters as a child safety monitoring model to be detected; inputting the characteristic data in the test set into the to-be-tested child safety monitoring model, and predicting the child safety condition corresponding to the input characteristic data through the to-be-tested child safety monitoring model to obtain a corresponding second safety monitoring result; calculating the ratio of the number of risk labels matched with the input characteristic data in the second safety monitoring results to the total number of the second safety monitoring results, and obtaining second prediction accuracy of the child safety monitoring model to be detected; judging whether the second prediction precision is higher than a preset precision threshold value or not; if the second prediction precision is not higher than the preset precision threshold, setting the child safety monitoring model to be detected as an initial child safety monitoring model and returning to execute the steps A32 to A36; and if the second prediction precision is higher than the preset precision threshold, stopping training, and setting the to-be-detected child safety monitoring model as a target child safety monitoring model.
The embodiment of the application provides a method for training a target child safety monitoring model before the step of inputting target characteristic data into a preset target child safety monitoring model to obtain a safety monitoring result, wherein the method specifically adopts multi-dimensional historical characteristic data including image data, sound data, temperature data, humidity data, air quality data, motion data, physiological data and risk distance as sample data to train an initial child safety monitoring model constructed based on a support vector machine, improves the characteristic dimension of the trained target child safety monitoring model, increases the comprehensiveness of safety monitoring, and improves the performance of the target child safety monitoring model.
Example III
The embodiment of the application also provides an indoor child safety monitoring device, indoor child safety monitoring device is applied to indoor child safety monitoring equipment, referring to fig. 4, indoor child safety monitoring device includes:
the feature collection module 101 is configured to collect raw feature data in a monitored environment, where the raw feature data at least includes image data, sound data, temperature data, humidity data, and air quality data;
The preprocessing module 102 is configured to preprocess the raw feature data to obtain target feature data, where the preprocessing at least includes cleaning, filtering, and normalizing;
the safety monitoring module 103 is configured to input the target feature data into a preset target child safety monitoring model to obtain a safety monitoring result, where the target child safety monitoring model is obtained by training according to multiple sets of historical feature data;
the risk judging module 104 is configured to judge whether a child in the monitoring environment has a safety risk according to the original feature data and the safety monitoring result;
and the risk prompt module 105 is configured to push the original feature data and a preset risk prompt to the guardian account if the original feature data and the preset risk prompt exist.
Optionally, the feature collection module 101 is further configured to:
collecting motion data and physiological data of a target child in the monitoring environment, wherein the motion data at least comprise acceleration data, and the physiological data at least comprise heart rate data, blood pressure data and blood oxygen saturation data;
the motion data and the physiological data are added to the raw feature data.
Optionally, the feature collection module 101 is further configured to:
carrying out three-dimensional modeling on the monitoring environment according to the image data to obtain a three-dimensional space coordinate system corresponding to the monitoring environment;
identifying a target child in the monitoring environment according to the image data, and obtaining a first coordinate of the target child in the three-dimensional space coordinate system;
determining a risk distance according to a second coordinate and the first coordinate of a preset risk position in the three-dimensional space coordinate system, wherein the preset risk position at least comprises one of a balcony and a window;
the risk distance is added to the raw feature data.
Optionally, the safety monitoring module 103 is further configured to:
acquiring and preprocessing historical characteristic data in a plurality of groups of indoor environments to obtain target historical characteristic data, wherein the historical characteristic data at least comprise a plurality of groups of image data, sound data, temperature data, humidity data, air quality data, motion data, physiological data and risk distances in various scenes of the indoor environments;
based on a preset support vector machine algorithm, an initial child safety monitoring model is constructed;
Training the initial child safety monitoring model according to the target historical characteristic data and risk labels corresponding to the target historical characteristic data to obtain a target child safety monitoring model, wherein the risk labels at least comprise risks and no risks.
Optionally, the safety monitoring module 103 is further configured to:
dividing the target historical characteristic data into a training set and a testing set;
the characteristic data in the training set is input into the initial child safety monitoring model to obtain a corresponding first safety monitoring result;
determining a first prediction precision of the initial child safety monitoring model according to a risk tag corresponding to the feature data in the training set and a corresponding first safety monitoring result;
iteratively optimizing model parameters of the initial child safety monitoring model based on the first prediction precision of the initial child safety monitoring model to obtain a child safety monitoring model to be detected;
the feature data in the training set are input into the child safety monitoring model to be tested, so that a corresponding second safety monitoring result is obtained;
determining a second prediction precision of the child safety monitoring model to be detected according to the risk tag corresponding to the characteristic data in the training set and a corresponding second safety monitoring result;
And if the second prediction precision accords with a preset precision threshold, setting the child safety monitoring model to be detected as a target child safety monitoring model.
Optionally, the preprocessing module 102 is further configured to:
cleaning the original characteristic data to remove abnormal data in the original characteristic data, and obtaining first characteristic data;
filtering the first characteristic data to obtain second characteristic data;
and inputting the second characteristic data into a preset normalization function to obtain target characteristic data.
Optionally, the risk judging module 104 is further configured to:
if the original characteristic data have the characteristic data exceeding a preset data threshold value or the safety monitoring result is that the risk exists, judging that the safety risk exists for the children in the monitoring environment;
and if the original characteristic data does not have the characteristic data exceeding the preset data threshold value and the safety monitoring result is that the safety monitoring result is risk-free, judging that the safety risk of the children in the monitoring environment does not exist.
The indoor child safety monitoring device provided by the application adopts the indoor child safety monitoring method in the embodiment, so that the technical problem of low indoor child safety monitoring accuracy is solved. Compared with the prior art, the indoor child safety monitoring device provided by the embodiment of the application has the same beneficial effects as the indoor child safety monitoring method provided by the embodiment, and other technical features in the indoor child safety monitoring device are the same as the features disclosed by the method of the previous embodiment, and are not repeated herein.
Example IV
The embodiment of the application provides electronic equipment, the electronic equipment includes: at least one processor; and a memory communicatively linked to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the indoor child safety monitoring method of the first embodiment.
Referring now to fig. 5, a schematic diagram of an electronic device suitable for use in implementing embodiments of the present disclosure is shown. 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 assistant, personal digital assistants), PADs (tablet computers), PMPs (Portable Media Player, portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 5 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.
As shown in fig. 5, the electronic device may include a processing means (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 means into a random access memory (RAM, random access memory). In the RAM, various programs and data required for the operation of the electronic device are also stored. The processing device, ROM and RAM are connected to each other via a bus. Input/output (I/O) interfaces are also linked to the bus.
In general, the following systems may be linked to I/O interfaces: input devices including, for example, touch screens, touch pads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices including, for example, liquid crystal displays (LCDs, liquid crystal display), speakers, vibrators, etc.; storage devices including, for example, magnetic tape, hard disk, etc.; a communication device. The communication means may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. While electronic devices having various systems are shown in the figures, it should be understood that not all of the illustrated systems are required to be implemented or provided. More or fewer systems may alternatively be implemented or provided.
In particular, according to embodiments of the present disclosure, the processes described above with reference to 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 shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from ROM. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by a processing device.
The electronic equipment provided by the application adopts the indoor child safety monitoring method in the embodiment, so that the technical problem of low indoor child safety monitoring accuracy is solved. Compared with the prior art, the electronic device provided in the embodiment of the present application has the same beneficial effects as the indoor child safety monitoring method provided in the first embodiment, and other technical features in the electronic device are the same as the features disclosed in the method in the previous embodiment, which is not described in detail herein.
It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the description of the above embodiments, particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing is merely 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 think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to 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 indoor child safety monitoring of the first embodiment described above.
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 foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical link 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, erasable Programmable Read-Only Memory, 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 this 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, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
The above-described computer-readable storage medium may be contained in an electronic device; or may exist alone without being assembled into an electronic device.
The computer-readable storage medium carries one or more programs that, when executed by an electronic device, cause the electronic device to: collecting original characteristic data in a monitoring environment, wherein the original characteristic data at least comprises image data, sound data, temperature data, humidity data and air quality data; preprocessing the original characteristic data to obtain target characteristic data, wherein the preprocessing at least comprises cleaning, filtering and normalizing; inputting the target characteristic data into a preset target child safety monitoring model to obtain a safety monitoring result, wherein the target child safety monitoring model is obtained by training according to a plurality of groups of historical characteristic data; judging whether a child in the monitoring environment has safety risk or not according to the original characteristic data and the safety monitoring result; if the original characteristic data and the preset risk prompt are transmitted to the guardian account.
Computer program code for carrying out operations of the present disclosure may be written in 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 linked to the user's computer through any kind of network, including a local area network (LAN, local area network) or a wide area network (WAN, wide Area Network), or it may be linked to an external computer (e.g., through the internet using an internet service provider).
The flowcharts 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 in software or hardware. Wherein the name of the module does not constitute a limitation of the unit itself in some cases.
The computer readable storage medium is stored with computer readable program instructions for executing the indoor child safety monitoring method, and solves the technical problem of low indoor child safety 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 indoor child safety monitoring method provided by the above embodiment, and are not described in detail herein.
Example six
The present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of an indoor child safety monitoring method as described above.
The application provides a computer program product which solves the technical problem of low accuracy of indoor child safety monitoring. 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 indoor child safety monitoring method provided by the above embodiment, and are not described in detail herein.
The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims.
Claims (10)
1. An indoor child safety monitoring method, characterized in that the indoor child safety monitoring method comprises:
collecting original characteristic data in a monitoring environment, wherein the original characteristic data at least comprises image data, sound data, temperature data, humidity data and air quality data;
preprocessing the original characteristic data to obtain target characteristic data, wherein the preprocessing at least comprises cleaning, filtering and normalizing;
inputting the target characteristic data into a preset target child safety monitoring model to obtain a safety monitoring result, wherein the target child safety monitoring model is obtained by training according to a plurality of groups of historical characteristic data;
judging whether a child in the monitoring environment has safety risk or not according to the original characteristic data and the safety monitoring result;
if the original characteristic data and the preset risk prompt are transmitted to the guardian account.
2. The indoor child safety monitoring method of claim 1, wherein prior to the step of preprocessing the raw characteristic data to obtain target characteristic data, the method further comprises:
Collecting motion data and physiological data of a target child in the monitoring environment, wherein the motion data at least comprise acceleration data, and the physiological data at least comprise heart rate data, blood pressure data and blood oxygen saturation data;
the motion data and the physiological data are added to the raw feature data.
3. An indoor child safety monitoring method according to claim 2, wherein prior to the step of preprocessing the raw characteristic data to obtain target characteristic data, the method further comprises:
carrying out three-dimensional modeling on the monitoring environment according to the image data to obtain a three-dimensional space coordinate system corresponding to the monitoring environment;
identifying a target child in the monitoring environment according to the image data, and obtaining a first coordinate of the target child in the three-dimensional space coordinate system;
determining a risk distance according to a second coordinate and the first coordinate of a preset risk position in the three-dimensional space coordinate system, wherein the preset risk position at least comprises one of a balcony and a window;
the risk distance is added to the raw feature data.
4. An indoor child safety monitoring method according to claim 3, wherein before the step of inputting the target characteristic data into a preset target child safety monitoring model to obtain a safety monitoring result, the method further comprises:
Acquiring and preprocessing historical characteristic data in a plurality of groups of indoor environments to obtain target historical characteristic data, wherein the historical characteristic data at least comprise a plurality of groups of image data, sound data, temperature data, humidity data, air quality data, motion data, physiological data and risk distances in various scenes of the indoor environments;
based on a preset support vector machine algorithm, an initial child safety monitoring model is constructed;
training the initial child safety monitoring model according to the target historical characteristic data and risk labels corresponding to the target historical characteristic data to obtain a target child safety monitoring model, wherein the risk labels at least comprise risks and no risks.
5. The method of indoor child safety monitoring according to claim 4, wherein the step of training the initial child safety monitoring model according to the target historical feature data and the risk tag corresponding to the target historical feature data to obtain a target child safety monitoring model comprises:
dividing the target historical characteristic data into a training set and a testing set;
the characteristic data in the training set is input into the initial child safety monitoring model to obtain a corresponding first safety monitoring result;
Determining a first prediction precision of the initial child safety monitoring model according to a risk tag corresponding to the feature data in the training set and a corresponding first safety monitoring result;
iteratively optimizing model parameters of the initial child safety monitoring model based on the first prediction precision of the initial child safety monitoring model to obtain a child safety monitoring model to be detected;
the feature data in the training set are input into the child safety monitoring model to be tested, so that a corresponding second safety monitoring result is obtained;
determining a second prediction precision of the child safety monitoring model to be detected according to the risk tag corresponding to the characteristic data in the training set and a corresponding second safety monitoring result;
and if the second prediction precision accords with a preset precision threshold, setting the child safety monitoring model to be detected as a target child safety monitoring model.
6. The method of indoor child safety monitoring according to claim 1, wherein the step of preprocessing the raw characteristic data to obtain target characteristic data comprises:
cleaning the original characteristic data to remove abnormal data in the original characteristic data, and obtaining first characteristic data;
Filtering the first characteristic data to obtain second characteristic data;
and inputting the second characteristic data into a preset normalization function to obtain target characteristic data.
7. The method of indoor child safety monitoring according to claim 1, wherein the step of determining whether a child in the monitored environment is at risk for safety based on the raw characteristic data and the safety monitoring results comprises:
if the original characteristic data have the characteristic data exceeding a preset data threshold value or the safety monitoring result is that the risk exists, judging that the safety risk exists for the children in the monitoring environment;
and if the original characteristic data does not have the characteristic data exceeding the preset data threshold value and the safety monitoring result is that the safety monitoring result is risk-free, judging that the safety risk of the children in the monitoring environment does not exist.
8. An indoor child safety monitoring device, the indoor child safety monitoring device comprising:
the device comprises a characteristic acquisition module, a monitoring module and a control module, wherein the characteristic acquisition module is used for acquiring original characteristic data in a monitoring environment, and the original characteristic data at least comprises image data, sound data, temperature data, humidity data and air quality data;
The preprocessing module is used for preprocessing the original characteristic data to obtain target characteristic data, wherein the preprocessing at least comprises cleaning, filtering and normalization processing;
the safety monitoring module is used for inputting the target characteristic data into a preset target child safety monitoring model to obtain a safety monitoring result, wherein the target child safety monitoring model is obtained by training according to a plurality of groups of historical characteristic data;
the risk judging module is used for judging whether the child in the monitoring environment has safety risk or not according to the original characteristic data and the safety monitoring result;
and the risk prompt module is used for pushing the original characteristic data and the preset risk prompt to the guardian account if the original characteristic data and the preset risk prompt exist.
9. An electronic device, the electronic device comprising:
at least one processor; the method comprises the steps of,
a memory communicatively linked to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the indoor child safety monitoring method of any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a program for realizing the indoor child safety monitoring method, the program for realizing the indoor child safety monitoring method being executed by a processor to realize the steps of the indoor child safety monitoring method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310603321.XA CN116304596A (en) | 2023-05-26 | 2023-05-26 | Indoor child safety monitoring method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310603321.XA CN116304596A (en) | 2023-05-26 | 2023-05-26 | Indoor child safety monitoring method and device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116304596A true CN116304596A (en) | 2023-06-23 |
Family
ID=86783751
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310603321.XA Pending CN116304596A (en) | 2023-05-26 | 2023-05-26 | Indoor child safety monitoring method and device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116304596A (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108683724A (en) * | 2018-05-11 | 2018-10-19 | 江苏舜天全圣特科技有限公司 | A kind of intelligence children's safety and gait health monitoring system |
CN108812407A (en) * | 2018-05-23 | 2018-11-16 | 平安科技(深圳)有限公司 | Animal health status monitoring method, equipment and storage medium |
CN109269556A (en) * | 2018-09-06 | 2019-01-25 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of equipment Risk method for early warning, device, terminal device and storage medium |
CN109842682A (en) * | 2019-01-31 | 2019-06-04 | 内蒙古工业大学 | A kind of study of distributed environment safety and method for early warning based on Internet of Things |
CN111063162A (en) * | 2019-12-05 | 2020-04-24 | 恒大新能源汽车科技(广东)有限公司 | Silent alarm method and device, computer equipment and storage medium |
CN113473074A (en) * | 2020-04-27 | 2021-10-01 | 海信集团有限公司 | Detection method, electronic equipment, detection equipment and storage medium |
CN114710555A (en) * | 2022-06-06 | 2022-07-05 | 深圳市景创科技电子股份有限公司 | Infant monitoring method and device |
CN114821674A (en) * | 2022-06-28 | 2022-07-29 | 合肥的卢深视科技有限公司 | Sleep state monitoring method, electronic device and storage medium |
CN114885133A (en) * | 2022-07-04 | 2022-08-09 | 中科航迈数控软件(深圳)有限公司 | Depth image-based equipment safety real-time monitoring method and system and related equipment |
CN115984967A (en) * | 2023-01-05 | 2023-04-18 | 北京轩宇空间科技有限公司 | Human body falling detection method, device and system based on deep learning |
-
2023
- 2023-05-26 CN CN202310603321.XA patent/CN116304596A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108683724A (en) * | 2018-05-11 | 2018-10-19 | 江苏舜天全圣特科技有限公司 | A kind of intelligence children's safety and gait health monitoring system |
CN108812407A (en) * | 2018-05-23 | 2018-11-16 | 平安科技(深圳)有限公司 | Animal health status monitoring method, equipment and storage medium |
CN109269556A (en) * | 2018-09-06 | 2019-01-25 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of equipment Risk method for early warning, device, terminal device and storage medium |
CN109842682A (en) * | 2019-01-31 | 2019-06-04 | 内蒙古工业大学 | A kind of study of distributed environment safety and method for early warning based on Internet of Things |
CN111063162A (en) * | 2019-12-05 | 2020-04-24 | 恒大新能源汽车科技(广东)有限公司 | Silent alarm method and device, computer equipment and storage medium |
CN113473074A (en) * | 2020-04-27 | 2021-10-01 | 海信集团有限公司 | Detection method, electronic equipment, detection equipment and storage medium |
CN114710555A (en) * | 2022-06-06 | 2022-07-05 | 深圳市景创科技电子股份有限公司 | Infant monitoring method and device |
CN114821674A (en) * | 2022-06-28 | 2022-07-29 | 合肥的卢深视科技有限公司 | Sleep state monitoring method, electronic device and storage medium |
CN114885133A (en) * | 2022-07-04 | 2022-08-09 | 中科航迈数控软件(深圳)有限公司 | Depth image-based equipment safety real-time monitoring method and system and related equipment |
CN115984967A (en) * | 2023-01-05 | 2023-04-18 | 北京轩宇空间科技有限公司 | Human body falling detection method, device and system based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110503081B (en) | Violent behavior detection method, system, equipment and medium based on interframe difference | |
Zhang et al. | Multivariate time series missing data imputation using recurrent denoising autoencoder | |
Cai et al. | GBDT‐Based Fall Detection with Comprehensive Data from Posture Sensor and Human Skeleton Extraction | |
CN114710555A (en) | Infant monitoring method and device | |
CN112149615A (en) | Face living body detection method, device, medium and electronic equipment | |
US11741986B2 (en) | System and method for passive subject specific monitoring | |
CN112967733A (en) | Method and device for intelligently identifying crying category of baby | |
CN112270246A (en) | Video behavior identification method and device, storage medium and electronic equipment | |
CN113988487B (en) | High-temperature disaster prevention index detection method, device, equipment, storage medium and product | |
CN114547252A (en) | Text recognition method and device, electronic equipment and medium | |
CN116304596A (en) | Indoor child safety monitoring method and device, electronic equipment and storage medium | |
CN117726162A (en) | Community risk level assessment method and system based on multi-mode data fusion | |
CN117671440A (en) | Abnormal portrait file detection method and system | |
CN113746780A (en) | Abnormal host detection method, device, medium and equipment based on host image | |
CN116840835B (en) | Fall detection method, system and equipment based on millimeter wave radar | |
CN115406626A (en) | AR (augmented reality) glasses-based fault detection method and device, AR glasses and medium | |
CN110458743B (en) | Community management method, device, equipment and storage medium based on big data analysis | |
CN113920720A (en) | Highway tunnel equipment fault processing method and device and electronic equipment | |
CN112560700A (en) | Information association method and device based on motion analysis and electronic equipment | |
CN113449627B (en) | Personnel tracking method based on AI video analysis and related device | |
CN115238805B (en) | Training method of abnormal data recognition model and related equipment | |
CN117671355A (en) | Object defect detection optimization method and device, electronic equipment and readable storage medium | |
CN116343343B (en) | Intelligent evaluation method for crane lifting command action based on cloud end architecture | |
CN118396309A (en) | Intelligent building office space operation and maintenance management system and method | |
CN118038619A (en) | Multi-mode federal learning method and system for intelligent fire monitoring and early warning |
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 |
Application publication date: 20230623 |
|
RJ01 | Rejection of invention patent application after publication |