CN110363143A - Monitoring method, device and system - Google Patents
Monitoring method, device and system Download PDFInfo
- Publication number
- CN110363143A CN110363143A CN201910640156.9A CN201910640156A CN110363143A CN 110363143 A CN110363143 A CN 110363143A CN 201910640156 A CN201910640156 A CN 201910640156A CN 110363143 A CN110363143 A CN 110363143A
- Authority
- CN
- China
- Prior art keywords
- information
- channel state
- target object
- demand information
- state information
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012544 monitoring process Methods 0.000 title claims abstract description 29
- 230000009471 action Effects 0.000 claims abstract description 63
- 238000012806 monitoring device Methods 0.000 claims abstract description 11
- 238000004891 communication Methods 0.000 claims description 56
- 238000004422 calculation algorithm Methods 0.000 claims description 21
- 238000003062 neural network model Methods 0.000 claims description 20
- 239000000284 extract Substances 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 8
- 230000001960 triggered effect Effects 0.000 claims description 5
- 241000208340 Araliaceae Species 0.000 claims description 3
- 241000406668 Loxodonta cyclotis Species 0.000 claims description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 3
- 235000008434 ginseng Nutrition 0.000 claims description 3
- 230000008901 benefit Effects 0.000 claims description 2
- 230000035479 physiological effects, processes and functions Effects 0.000 claims 2
- 238000005516 engineering process Methods 0.000 abstract description 16
- 230000000694 effects Effects 0.000 abstract description 10
- 230000004044 response Effects 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 9
- 238000004378 air conditioning Methods 0.000 description 7
- 238000000513 principal component analysis Methods 0.000 description 6
- 206010011878 Deafness Diseases 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 206010037660 Pyrexia Diseases 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000003862 health status Effects 0.000 description 3
- 230000029058 respiratory gaseous exchange Effects 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- 210000002700 urine Anatomy 0.000 description 3
- 241001465754 Metazoa Species 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 2
- 239000000969 carrier Substances 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000241 respiratory effect Effects 0.000 description 2
- 230000033764 rhythmic process Effects 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 206010011469 Crying Diseases 0.000 description 1
- 210000001015 abdomen Anatomy 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000037081 physical activity Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000036387 respiratory rate Effects 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000000392 somatic effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a monitoring method, a monitoring device and a monitoring system. Wherein, the method comprises the following steps: acquiring activity information of a target object, wherein the activity information comprises: an action and/or physiological parameter of the target subject; extracting channel state information in the activity information; uploading channel state information to a server, wherein the server determines the demand information of a target object according to the channel state information; and receiving the demand information and sending the demand information to the prompting equipment. The invention solves the technical problems that the demand information of the target object cannot be sensed in time and the response efficiency is low due to the fact that the user subjectively experiences and analyzes the activity information of the target object in the related technology.
Description
Technical field
The present invention relates to field of intelligent monitoring, in particular to a kind of monitoring method, device and system.
Background technique
In recent years, as the rapid development of artificial intelligence field and people are to intelligent monitoring, smart home and novel people
The increasingly promotion of machine interaction demand, Human bodys' response (Human Activity Recognition, HAR) technology become mode
One popular research direction in the fields such as identification, computer vision, wireless aware.At present HAR technology be applied to smart home,
In a variety of applications such as intelligent monitoring, somatic sensation television game and medical monitoring.
However, in life, for the specific group of not language competence, due to there is no to efficiently use HAR technology, user
The heart demand that this kind of crowd is often analyzed according to the subjective feeling of oneself causes the real demand of this kind of crowd cannot be timely
Meet.For example, in life less than one full year of life baby, do not loquitur also, to uncomfortable equal passing through needed for itself and
Movement is cryyed to express, and for mother new hand when looking after baby, the sobbing in face of baby is always badly battered, can not be expressly understood that
The real demand or health status of baby.
The reason of for user in the related technology by subjective feeling analysis target object action message, lead to target object
Demand information can not perceive in time, the technical problem that response efficiency is low, currently no effective solution has been proposed.
Summary of the invention
The embodiment of the invention provides a kind of monitoring method, device and system, at least solve in the related technology user with
The reason of analyzing target object action message by means of subjective feeling, causes the demand information of target object that can not perceive, respond in time
The technical issues of low efficiency.
According to an aspect of an embodiment of the present invention, a kind of monitoring method is provided, comprising: obtain the activity of target object
Information, wherein action message includes: the movement and/or physiological parameter of target object；Extract the channel status letter in action message
Breath；Channel state information is uploaded to server, wherein server determines that the demand of target object is believed according to channel state information
Breath；Demand information is received, and demand information is sent to prompt equipment.
Optionally, before the demand information that server determines target object according to channel state information, the above method is also
It include: to obtain channel status sample and demand sample；Channel status sample and demand sample are trained, obtained trained
Neural network model, wherein neural network model obtains demand information for handling channel state information.
Optionally, server determines the demand information of target object according to channel state information, comprising: believes channel status
Breath carries out de-redundancy processing, obtains pretreatment information；Feature extraction is carried out to pretreatment information, obtains characteristic parameter；Based on mind
Through network model identification feature parameter, demand information is obtained.
Optionally, de-redundancy processing is carried out to channel state information, obtains pretreatment information, comprising: pass through low-pass filtering
Device does process of convolution per the data in channel two-by-two in channel state information, obtains denoising data；By dimension-reduction algorithm to going
Data of making an uproar carry out dimension-reduction treatment, obtain pretreatment information.
Optionally, characteristic parameter includes fisrt feature parameter and second feature parameter, carries out feature to pretreatment information and mentions
It takes, obtains characteristic parameter, comprising: frequency resolution is carried out to pretreatment information by wavelet transform, obtains spectrogram；It extracts
The wavelet coefficient of each frequency range in spectrogram, as fisrt feature parameter；The upper limit of each sampling instant is cut in estimated spectral figure
Only frequency and centre frequency, as second feature parameter.
Optionally, demand information is received, and demand information is sent to prompt equipment, comprising: passes through Wireless Communication Equipment
Demand information is received, and demand information is sent to target electric appliance, wherein Wireless Communication Equipment is located in target electric appliance；Pass through
Target electric appliance triggering prompt equipment, issues demand information to prompt equipment.
According to another aspect of an embodiment of the present invention, a kind of monitoring method is additionally provided, comprising: obtain Wireless Communication Equipment
The channel state information of upload, wherein channel state information is extracted from the action message of target object by Wireless Communication Equipment,
Action message includes: the movement and/or physiological parameter of target object；The demand letter of target object is determined according to channel state information
Breath；Demand information is sent to prompt equipment.
Optionally, demand information is sent to prompt equipment, comprising: be sent to demand information by Wireless Communication Equipment
Target electric appliance, wherein Wireless Communication Equipment is located in target electric appliance；Prompt equipment is triggered by target electric appliance, to prompt equipment
Issue demand information.
According to another aspect of an embodiment of the present invention, a kind of monitoring device is additionally provided, comprising: first obtains module, uses
In the action message for obtaining target object, wherein action message includes: the movement and/or physiological parameter of target object；Extract mould
Block, for extracting the channel state information in action message；Uploading module, for uploading channel state information to server,
In, server determines the demand information of target object according to channel state information；Receiving module, for receiving demand information, and
Demand information is sent to prompt equipment.
According to another aspect of an embodiment of the present invention, a kind of monitoring device is additionally provided, comprising: third obtains module, uses
In the channel state information for obtaining Wireless Communication Equipment and uploading, wherein channel state information is by Wireless Communication Equipment from target pair
It is extracted in the action message of elephant, action message includes: the movement and/or physiological parameter of target object；Determining module is used for basis
Channel state information determines the demand information of target object；Sending module, for demand information to be sent to prompt equipment.
According to another aspect of an embodiment of the present invention, a kind of storage medium is additionally provided, storage medium includes the journey of storage
Sequence, wherein equipment where control storage medium executes any one of the above monitoring method in program operation.
According to another aspect of an embodiment of the present invention, a kind of processor is additionally provided, processor is used to run program,
In, program executes any one of the above monitoring method when running.
According to another aspect of an embodiment of the present invention, a kind of monitoring system is additionally provided, comprising: Wireless Communication Equipment is used
In the action message for obtaining target object, the channel state information in action message is extracted, and channel state information is uploaded to
Server, wherein action message includes: the movement and/or physiological parameter of target object；Server, for according to channel status
Information determines the demand information of target object；Wireless Communication Equipment is also used to receive demand information, and demand information is sent to
Prompt equipment.
In embodiments of the present invention, the action message of target object is obtained, wherein action message includes: target object
Movement and/or physiological parameter；Extract the channel state information in action message；Channel state information is uploaded to server, wherein
Server determines the demand information of target object according to channel state information；Demand information is received, and demand information is sent to
Prompt equipment.Compared with prior art, above scheme is passed through by extracting the channel state information in target object action message
Man-machine identification technology determines the real demand of target object, informs user using prompt equipment, has reached timely hard objectives pair
The purpose of the demand information of elephant, and then solve user in the related technology and rely on subjective feeling analysis target object action message
Reason causes the demand information of target object not perceive in time, the technical problem that response efficiency is low.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is a kind of flow diagram of according to embodiments of the present invention 1 optional monitoring method；
Fig. 2 is the flow diagram of a kind of according to embodiments of the present invention 1 optional Human bodys' response method；
Fig. 3 is a kind of flow diagram of according to embodiments of the present invention 1 optional server identification behavioural information；
Fig. 4 is a kind of process signal of according to embodiments of the present invention 1 optional air-conditioning system identification baby's sobbing reason
Figure；
Fig. 5 is a kind of flow diagram of according to embodiments of the present invention 2 optional monitoring method；
Fig. 6 is a kind of schematic diagram of according to embodiments of the present invention 3 optional monitoring device；And
Fig. 7 is a kind of schematic diagram of according to embodiments of the present invention 4 optional monitoring device.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
Embodiment 1
According to embodiments of the present invention, a kind of embodiment of monitoring method is provided from the angle of Wireless Communication Equipment, needed
Illustrate, step shown in the flowchart of the accompanying drawings can be in a computer system such as a set of computer executable instructions
It executes, although also, logical order is shown in flow charts, and it in some cases, can be to be different from herein suitable
Sequence executes shown or described step.
Fig. 1 is monitoring method according to an embodiment of the present invention, as shown in Figure 1, this method comprises the following steps:
Step S102 obtains the action message of target object, wherein action message include: target object movement and/or
Physiological parameter.
In a kind of optinal plan, above-mentioned target object can be the human or animal of not language competence, such as less than one week
Baby, pet dog, the deaf-mute etc. in year；Above-mentioned movement can gesticulate movement, pet dog for the sobbing movement of baby, deaf-mute
Bark movement etc.；Above-mentioned physiological parameter can be heartbeat, breathing, pulse etc..
It should be noted that the module for obtaining above-mentioned action message can be Wireless Communication Equipment, the Wireless Communication Equipment
It is set in electric appliance.For example, the WiFi module configured on air-conditioning, the WiFi module etc. that is configured on intelligent sound box.
In a kind of optinal plan, above-mentioned WiFi module can be double WiFi modules, and one is used as transmitting terminal, and one is used as and connects
Receiving end.
Step S104 extracts the channel state information in action message.
In above-mentioned steps, since the activity of target object can generate certain interference, nothing to the waveform of Wireless Communication Equipment
The line network equipment extracts channel state information therein by software tool first after getting wireless network signal
(Channel State Information, CSI), i.e. information on extraction WIFI channel sub-carriers waveform.
It is easily noted that, channel state information can measure the phase and amplitude of each subcarrier, by subcarrier information
What is shown is more abundant, shows multi-path resolved ability to a certain extent, especially within the scope of non line of sight, perceives out signal
Small variation, therefore, channel state information have the characteristics that highly sensitive and sensing region is wide.The present invention just allows for
Factor is stated, by extracting the channel state information in wireless network signal, to perceive the real demand of target object.
Step S106 uploads channel state information to server, wherein server determines target according to channel state information
The demand information of object.
In a kind of optinal plan, above-mentioned server can be cloud server, or local server；The demand
Information can be the real demand of target object, including health status, for example, it is thirsty, be hungry, urine pants, fever etc..
The channel state information that server uploads Wireless Communication Equipment pre-processes, for example, filtering, removal abnormal point,
The operation such as characteristic value is extracted, information identifies to treated finally by neural network scheduling algorithm, determines target object
Demand information.
Step S108 receives demand information, and demand information is sent to prompt equipment.
In a kind of optinal plan, above-mentioned prompt equipment can be the mobile terminal of user, or Wireless Communication Equipment
The display panel of the electric appliance at place.
Wireless Communication Equipment is after receiving the demand information that server is determined, the master of the electric appliance where sending it to
Controller is shown by main controller controls display panel, or by the mobile terminal of master controller triggering user, is informed and used
The demand information of family target object.
In an alternative embodiment, Fig. 2 shows a kind of flow diagrams of Human bodys' response method.Such as Fig. 2
It is shown, after Wireless Communication Equipment gets the action message of human body, extract channel state information first, be then sent to
Server.The channel state information that server uploads Wireless Communication Equipment pre-processes, for example, filtering, removal abnormal point,
The operation such as characteristic value is extracted, then information identifies to treated by action recognition module neural network based, really
The demand information of target object is made, the demand information is finally fed back into prompt equipment, to inform user.
In the above embodiments of the present application, the action message of target object is obtained, wherein action message includes: target object
Movement and/or physiological parameter；Extract the channel state information in action message；Channel state information is uploaded to server,
In, server determines the demand information of target object according to channel state information；Demand information is received, and demand information is sent
To prompt equipment.Compared with prior art, above scheme is led to by extracting the channel state information in target object action message
The real demand that man-machine identification technology determines target object is crossed, user is informed using prompt equipment, has reached timely hard objectives
The purpose of the demand information of object, and then solve user in the related technology and subjective feeling is relied on to analyze target object action message
The reason of, cause the demand information of target object not perceive in time, the technical problem that response efficiency is low.
Optionally, before the demand information that server determines target object according to channel state information, the above method is also
It may comprise steps of:
Step S1051 obtains channel status sample and demand sample.
In a kind of optinal plan, above-mentioned channel status sample and demand sample can come from historical activity information and and history
The corresponding demand information of action message.
Step S1052 is trained channel status sample and demand sample, obtains trained neural network model,
Wherein, neural network model obtains demand information for handling channel state information.
Initial neural network model is constantly trained by channel status sample and demand sample, available training
Good neural network model.
In an alternative embodiment, Fig. 3 shows the flow diagram of server identification behavioural information.Such as Fig. 3 institute
Show, server determines the demand information of target object according to channel state information, specifically may be used after getting channel state information
To include:
Step S1061 carries out de-redundancy processing to channel state information, obtains pretreatment information.
Step S1062 carries out feature extraction to pretreatment information, obtains characteristic parameter.
In a kind of optinal plan, features described above parameter can be the characteristic parameter of rhythm of the heart curve, the feature ginseng of respiratory curve
Number, characteristic parameter of sobbing operation curve etc..
Step S1063 is based on neural network model identification feature parameter, obtains demand information.
Optionally, step S1061 carries out de-redundancy processing to channel state information, obtains pretreatment information, specifically can be with
The following steps are included:
Step S10611 is done at convolution in channel state information per the data in channel two-by-two by low-pass filter
Reason obtains denoising data.
In a kind of optinal plan, above-mentioned low-pass filter can be hamming window low-pass filter.
In above-mentioned steps, using hamming window low-pass filter to every antenna two-by-two in a string of channel state information data flows
Between channel link in data do convolution, carry out preliminary denoising.
Step S10612 carries out dimension-reduction treatment to denoising data by dimension-reduction algorithm, obtains pretreatment information.
In a kind of optinal plan, above-mentioned dimension-reduction algorithm can be Principal Component Analysis Algorithm.
Data more for dimension, it is necessary first to which the thing done is exactly that will count under the premise of guaranteeing that data are essential as far as possible
According to dimension reduce.Principal component analysis (Principal Components Analysis, PCA) algorithm is may have correlation
Property the unrelated low-dimensional variable of higher-dimension variable synthesizing linear, new low-dimensional data rally retains the variable of initial data as far as possible.
Dimensionality reduction can be carried out to denoising data by Principal Component Analysis, further achieve the purpose that remove redundant data.
Optionally, characteristic parameter includes fisrt feature parameter and second feature parameter, carries out feature to pretreatment information and mentions
It takes, obtains characteristic parameter, can specifically include:
Step S10621 carries out frequency resolution to pretreatment information by wavelet transform, obtains multiple frequency ranges.
Step S10622 extracts the wavelet coefficient of each frequency range in spectrogram, as fisrt feature parameter.
In above-mentioned steps, frequency resolution is carried out to the pretreatment information in a period of time by wavelet transform, is obtained
Then multiple frequency ranges extract the wavelet coefficient of each frequency range, as fisrt feature parameter.
Step S10623, the upper cut-off frequency and centre frequency of each sampling instant in estimated spectral figure, as second
Characteristic parameter.
In a kind of optinal plan, above-mentioned upper cut-off frequency and centre frequency can be estimated using percentage algorithm.
Percentage (Percentiles) algorithm can carry out operation to the spectrogram of movement, estimate each sampling instant
The upper limit (upper) cutoff frequency and center (center) frequency.
Optionally, step S108 receives demand information, and demand information is sent to prompt equipment, can specifically include:
Step S1081 receives demand information by Wireless Communication Equipment, and demand information is sent to target electric appliance,
In, Wireless Communication Equipment is located in target electric appliance.
In a kind of optinal plan, above-mentioned target electric appliance can be include the household electrical appliance of Wireless Communication Equipment, such as air-conditioning,
Intelligent sound box etc..
Step S1082, triggers prompt equipment by target electric appliance, issues demand information to prompt equipment.
As previously mentioned, above-mentioned prompt equipment can be the mobile terminal of user, or where Wireless Communication Equipment
The display panel of target electric appliance.
Target electric appliance of the Wireless Communication Equipment after receiving the demand information that server is determined, where sending it to
Master controller, by main controller controls display panel show demand information, or by master controller triggering user mobile end
The demand information of ownership goal object is informed at end.
By taking baby crys as an example, Fig. 4 shows the flow diagram that baby's sobbing reason is identified by air-conditioning system.Such as figure
Double WiFi equipments are configured shown in 4, on air-conditioning, one is used as transmitting terminal, and one is used as receiving end, obtains crying for baby in receiving end
Tears action message, such as heartbeat, breathing, pulse, the movement of sobbing etc., then statistics extracts channel state information, is sent to
To cloud server.Cloud server analyzes the true cause of baby's sobbing using intelligent algorithm, is fed back to sky
The master controller of tune.Demand information is sent to the APP of customer mobile terminal by WiFi equipment by master controller, informs user baby
The true cause of vagitus tears, such as belly is hungry, urine pants etc..Be easily noted that, by baby's respiratory rate for detecting and
Palmic rate can also analyze the health status of baby, such as catch a cold, have a fever, suffering from cold or other symptoms.Above scheme passes through people
Body Activity recognition technology identifies that auxiliary mother new hand more easily control looks after baby to the action message of baby, is expressly understood that
The real demand of baby, enables baby's blossom out.
In embodiments of the present invention, the action message of target object is obtained, wherein action message includes: target object
Movement and/or physiological parameter；Extract the channel state information in action message；Channel state information is uploaded to server, wherein
Server determines the demand information of target object according to channel state information；Demand information is received, and demand information is sent to
Prompt equipment.Compared with prior art, above scheme is passed through by extracting the channel state information in target object action message
Man-machine identification technology determines the real demand of target object, informs user using prompt equipment, protects the privacy of user, reach
The purpose of the demand information of timely hard objectives object, so that monitoring technology is more humanized, and then solves in the related technology
The reason of user is by subjective feeling analysis target object action message, causes the demand information of target object not feel in time
Know, the technical problem that response efficiency is low.
Embodiment 2
According to embodiments of the present invention, a kind of embodiment of monitoring method is provided from the angle of server, Fig. 5 is according to this
The monitoring method of inventive embodiments, as shown in figure 5, this method comprises the following steps:
Step S502 obtains the channel state information that Wireless Communication Equipment uploads, wherein channel state information is by wireless network
Network equipment is extracted from the action message of target object, and action message includes: the movement and/or physiological parameter of target object.
In a kind of optinal plan, cloud server can be passed through or local server obtains above-mentioned channel state information；On
It states Wireless Communication Equipment to be set in electric appliance, such as the WiFi module configured on air-conditioning, the WiFi module configured on intelligent sound box
Deng；Above-mentioned WiFi module can be double WiFi modules, and one is used as transmitting terminal, and one is used as receiving end.
Since the activity of target object can generate certain interference to the waveform of Wireless Communication Equipment, Wireless Communication Equipment exists
After getting wireless network signal, channel state information therein (Channel State is extracted by software tool first
Information, CSI), that is, extract the information on WiFi channel sub-carriers waveform.
It is easily noted that, channel state information can measure the phase and amplitude of each subcarrier, by subcarrier information
What is shown is more abundant, shows multi-path resolved ability to a certain extent, especially within the scope of non line of sight, perceives out signal
Small variation, therefore, channel state information have the characteristics that highly sensitive and sensing region is wide.The present invention just allows for
Factor is stated, by extracting the channel state information in wireless network signal, to perceive the real demand of target object.
In a kind of optinal plan, above-mentioned target object can be the human or animal of not language competence, such as less than one week
Baby, pet dog, the deaf-mute etc. in year；Above-mentioned movement can gesticulate movement, pet dog for the sobbing movement of baby, deaf-mute
Bark movement etc.；Above-mentioned physiological parameter can be heartbeat, breathing, pulse etc..
Step S504 determines the demand information of target object according to channel state information.
In a kind of optinal plan, the demand information can be the real demand of target object, strong including target object
Health situation, for example, it is thirsty, be hungry, urine pants, fever etc..
The channel state information that server uploads Wireless Communication Equipment pre-processes, for example, filtering, removal abnormal point,
The operation such as characteristic value is extracted, information identifies to treated finally by neural network scheduling algorithm, determines target object
Demand information.
Demand information is sent to prompt equipment by step S506.
In a kind of optinal plan, above-mentioned prompt equipment can be the mobile terminal of user, or Wireless Communication Equipment
The display panel of the electric appliance at place.
In an alternative embodiment, after server determines demand information, Wireless Communication Equipment institute is sent it to
Electric appliance master controller, shown by main controller controls display panel, or by master controller triggering user shifting
Dynamic terminal, informs the demand information of ownership goal object.
In another alternative embodiment, after server determines demand information, the movement of user can directly be triggered
Terminal informs the demand information of ownership goal object.
Optionally, before the demand information that step S504 determines target object according to channel state information, the above method
Can with the following steps are included:
Step S5031 obtains channel status sample and demand sample.
In a kind of optinal plan, above-mentioned channel status sample and demand sample can come from historical activity information and and history
The corresponding demand information of action message.
Step S5032 is trained channel status sample and demand sample, obtains trained neural network model,
Wherein, neural network model obtains demand information for handling channel state information.
Initial neural network model is constantly trained by channel status sample and demand sample, available training
Good neural network model.
Still by taking Fig. 3 as an example, step S504 determines the demand information of target object according to channel state information, specifically can wrap
Include following steps:
Step S5041 carries out de-redundancy processing to channel state information, obtains pretreatment information.
Step S5042 carries out feature extraction to pretreatment information, obtains characteristic parameter.
In a kind of optinal plan, features described above parameter can be the characteristic parameter of rhythm of the heart curve, the feature ginseng of respiratory curve
Number, characteristic parameter of sobbing operation curve etc..
Step S5043 is based on neural network model identification feature parameter, obtains demand information.
Optionally, step S5041 carries out de-redundancy processing to channel state information, obtains pretreatment information, specifically can be with
The following steps are included:
Step S50411 is done at convolution in channel state information per the data in channel two-by-two by low-pass filter
Reason obtains denoising data.
In a kind of optinal plan, above-mentioned low-pass filter can be hamming window low-pass filter.
In above-mentioned steps, using hamming window low-pass filter to every antenna two-by-two in a string of channel state information data flows
Between channel link in data do convolution, carry out preliminary denoising.
Step S50412 carries out dimension-reduction treatment to denoising data by dimension-reduction algorithm, obtains pretreatment information.
In a kind of optinal plan, above-mentioned dimension-reduction algorithm can be Principal Component Analysis Algorithm.
Data more for dimension, it is necessary first to which the thing done is exactly that will count under the premise of guaranteeing that data are essential as far as possible
According to dimension reduce.Principal component analysis (Principal Components Analysis, PCA) algorithm is may have correlation
Property the unrelated low-dimensional variable of higher-dimension variable synthesizing linear, new low-dimensional data rally retains the variable of initial data as far as possible.
Dimensionality reduction can be carried out to denoising data by Principal Component Analysis, further achieve the purpose that remove redundant data.
Optionally, characteristic parameter includes fisrt feature parameter and second feature parameter, carries out feature to pretreatment information and mentions
It takes, obtains characteristic parameter, can specifically include:
Step S50421 carries out frequency resolution to pretreatment information by wavelet transform, obtains multiple frequency ranges.
Step S50422 extracts the wavelet coefficient of each frequency range in spectrogram, as fisrt feature parameter.
In above-mentioned steps, frequency resolution is carried out to the pretreatment information in a period of time by wavelet transform, is obtained
Then multiple frequency ranges extract the wavelet coefficient of each frequency range, as fisrt feature parameter.
Step S50423, the upper cut-off frequency and centre frequency of each sampling instant in estimated spectral figure, as second
Characteristic parameter.
In a kind of optinal plan, above-mentioned upper cut-off frequency and centre frequency can be estimated using percentage algorithm.
Percentage (Percentiles) algorithm can carry out operation to the spectrogram of movement, estimate each sampling instant
The upper limit (upper) cutoff frequency and center (center) frequency.
Optionally, step S506 demand information is sent to prompt equipment, can specifically include:
Demand information is sent to target electric appliance by Wireless Communication Equipment, wherein Wireless Communication Equipment by step S5061
In target electric appliance.
In a kind of optinal plan, above-mentioned target electric appliance can be include the household electrical appliance of Wireless Communication Equipment, such as air-conditioning,
Intelligent sound box etc..
Step S5062, triggers prompt equipment by target electric appliance, issues demand information to prompt equipment.
As previously mentioned, above-mentioned prompt equipment can be the mobile terminal of user, or where Wireless Communication Equipment
The display panel of target electric appliance.
Target electric appliance of the Wireless Communication Equipment after receiving the demand information that server is determined, where sending it to
Master controller, by main controller controls display panel show demand information, or by master controller triggering user mobile end
The demand information of ownership goal object is informed at end.
It should be noted that being related to the scheme that preferred embodiment and embodiment 1 provide in the above embodiments of the present application 2
And application scenarios implementation process is identical, but not limited to the examples scheme provided by 1.
Embodiment 3
According to embodiments of the present invention, a kind of monitoring device is provided, Fig. 6 is shown according to the monitoring device of the embodiment of the present application
It is intended to.As shown in fig. 6, the device 600 includes the first acquisition module 602, extraction module 604, uploading module 606 and receiving module
608。
Wherein, first module 602 is obtained, for obtaining the action message of target object, wherein action message includes: mesh
Mark the movement and/or physiological parameter of object；Extraction module 604, for extracting the channel state information in action message；Upload mould
Block 606, for uploading channel state information to server, wherein server determines target object according to channel state information
Demand information；Receiving module 608 is sent to prompt equipment for receiving demand information, and by demand information.
Optionally, above-mentioned apparatus can also include: the second acquisition module, for true according to channel state information in server
It sets the goal before the demand information of object, obtains channel status sample and demand sample；Training module, for channel status sample
This and demand sample are trained, and obtain trained neural network model, wherein neural network model is for handling channel shape
State information, obtains demand information.
Optionally, uploading module can specifically include: preprocessing module, for carrying out at de-redundancy to channel state information
Reason obtains pretreatment information；Parameter extraction module obtains characteristic parameter for carrying out feature extraction to pretreatment information；Identification
Module obtains demand information for being based on neural network model identification feature parameter.
Optionally, preprocessing module can specifically include: convolution module, for being believed by low-pass filter channel status
Process of convolution is done per the data in channel two-by-two in breath, obtains denoising data；Dimensionality reduction module, for passing through dimension-reduction algorithm to denoising
Data carry out dimension-reduction treatment, obtain pretreatment information.
Optionally, characteristic parameter includes fisrt feature parameter and second feature parameter, and parameter extraction module specifically can wrap
Include: parsing module obtains multiple frequency ranges for carrying out frequency resolution to pretreatment information by wavelet transform；First mentions
Submodule is taken, for extracting the wavelet coefficient of each frequency range, as fisrt feature parameter；Second extracting sub-module, for passing through
Preset algorithm estimates the upper cut-off frequency and centre frequency of each sampling instant in spectrogram, as second feature parameter.
Optionally, receiving module can specifically include: receiving submodule, for receiving demand letter by Wireless Communication Equipment
Breath, and demand information is sent to target electric appliance, wherein Wireless Communication Equipment is located in target electric appliance；Trigger module, for leading to
Target electric appliance triggering prompt equipment is crossed, issues demand information to prompt equipment.
It should be noted that above-mentioned first obtains module 602, extraction module 604, uploading module 606 and receiving module 608
The example and application realized corresponding to the step S102 to step S108 in embodiment 1, four modules with corresponding step
Scene is identical, but is not limited to the above embodiments 1 disclosure of that.
Embodiment 4
According to embodiments of the present invention, a kind of monitoring device is provided, Fig. 7 is shown according to the monitoring device of the embodiment of the present application
It is intended to.As shown in fig. 7, the device 700 includes that third obtains module 702, determining module 704 and sending module 706.
Wherein, third obtains module 702, for obtaining the channel state information of Wireless Communication Equipment upload, wherein channel
Status information is extracted from the action message of target object by Wireless Communication Equipment, and action message includes: the movement of target object
And/or physiological parameter；Determining module 704, for determining the demand information of target object according to channel state information；Sending module
706, for demand information to be sent to prompt equipment
Optionally, above-mentioned apparatus can also include: the 4th acquisition module, for determining target according to channel state information
Before the demand information of object, channel status sample and demand sample are obtained；Training module is used for channel status sample and needs
It asks sample to be trained, obtains trained neural network model, wherein neural network model is for handling channel status letter
Breath, obtains demand information.
Optionally it is determined that module can specifically include: preprocessing module, for being carried out at de-redundancy to channel state information
Reason obtains pretreatment information；Parameter extraction module obtains characteristic parameter for carrying out feature extraction to pretreatment information；Identification
Module obtains demand information for being based on neural network model identification feature parameter.
Optionally, preprocessing module can specifically include: convolution module, for being believed by low-pass filter channel status
Process of convolution is done per the data in channel two-by-two in breath, obtains denoising data；Dimensionality reduction module, for passing through dimension-reduction algorithm to denoising
Data carry out dimension-reduction treatment, obtain pretreatment information.
Optionally, characteristic parameter includes fisrt feature parameter and second feature parameter, and parameter extraction module specifically can wrap
Include: parsing module obtains multiple frequency ranges for carrying out frequency resolution to pretreatment information by wavelet transform；First mentions
Submodule is taken, for extracting the wavelet coefficient of each frequency range, as fisrt feature parameter；Second extracting sub-module, for passing through
Preset algorithm estimates the upper cut-off frequency and centre frequency of each sampling instant in spectrogram, as second feature parameter.
Optionally, sending module can specifically include: sending submodule, for demand information to be passed through Wireless Communication Equipment
It is sent to target electric appliance, wherein Wireless Communication Equipment is located in target electric appliance；Trigger module, for being triggered by target electric appliance
Equipment is prompted, issues demand information to prompt equipment.
It should be noted that above-mentioned third, which obtains module 702, determining module 704 and sending module 706, corresponds to embodiment
Step S502 to step S506 in 2, three modules are identical as example and application scenarios that corresponding step is realized, but not
It is limited to 2 disclosure of that of above-described embodiment.
Embodiment 5
According to embodiments of the present invention, a kind of storage medium is provided, storage medium includes the program of storage, wherein in journey
Equipment executes the monitoring method in embodiment 1 or 2 where controlling storage medium when sort run.
Embodiment 6
According to embodiments of the present invention, a kind of processor is provided, processor is for running program, wherein run in program
Monitoring method in Shi Zhihang embodiment 1 or 2.
Embodiment 7
According to embodiments of the present invention, a kind of monitoring system is provided, comprising:
Wireless Communication Equipment extracts the channel state information in action message for obtaining the action message of target object,
And channel state information is uploaded to server, wherein action message includes: the movement and/or physiological parameter of target object.
Server, for determining the demand information of target object according to channel state information.
Wireless Communication Equipment is also used to receive demand information, and demand information is sent to prompt equipment
Further, the instruction of other steps in embodiment 1 or 2 can also be performed in Wireless Communication Equipment or server, this
Place repeats no more.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
In the above embodiment of the invention, it all emphasizes particularly on different fields to the description of each embodiment, does not have in some embodiment
The part of detailed description, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, such as the division of the unit, Ke Yiwei
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of unit or module
It connects, can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
On unit.It can some or all of the units may be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can for personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned includes: that USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic or disk etc. be various to can store program code
Medium.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (13)
1. a kind of monitoring method characterized by comprising
Obtain the action message of target object, wherein the action message includes: movement and/or the physiology of the target object
Parameter；
Extract the channel state information in the action message；
The channel state information is uploaded to server, wherein the server is according to channel state information determination
The demand information of target object；
The demand information is received, and the demand information is sent to prompt equipment.
2. the method according to claim 1, wherein being determined in the server according to the channel state information
Before the demand information of the target object, the method also includes:
Obtain channel status sample and demand sample；
The channel status sample and demand sample are trained, trained neural network model is obtained, wherein the mind
Through network model for handling the channel state information, the demand information is obtained.
3. according to the method described in claim 2, it is characterized in that, the server determines institute according to the channel state information
State the demand information of target object, comprising:
De-redundancy processing is carried out to the channel state information, obtains pretreatment information；
Feature extraction is carried out to the pretreatment information, obtains characteristic parameter；
The characteristic parameter is identified based on the neural network model, obtains the demand information.
4. according to the method described in claim 3, it is characterized in that, being obtained to channel state information progress de-redundancy processing
To pretreatment information, comprising:
Process of convolution is done per the data in channel two-by-two in the channel state information by low-pass filter, obtains denoising number
According to；
Dimension-reduction treatment is carried out to the denoising data by dimension-reduction algorithm, obtains pretreatment information.
5. according to the method described in claim 3, it is characterized in that, the characteristic parameter includes that fisrt feature parameter and second are special
Parameter is levied, feature extraction is carried out to the pretreatment information, obtains characteristic parameter, comprising:
Frequency resolution is carried out to the pretreatment information by wavelet transform, obtains spectrogram；
The wavelet coefficient for extracting each frequency range in the spectrogram, as the fisrt feature parameter；
The upper cut-off frequency and centre frequency for estimating each sampling instant in the spectrogram are joined as the second feature
Number.
6. the method according to claim 1, wherein receiving the demand information, and the demand information is sent out
It send to prompt equipment, comprising:
The demand information is received by Wireless Communication Equipment, and the demand information is sent to target electric appliance, wherein is described
Wireless Communication Equipment is located in the target electric appliance；
The prompt equipment is triggered by the target electric appliance, issues the demand information to the prompt equipment.
7. a kind of monitoring method characterized by comprising
Obtain the channel state information that Wireless Communication Equipment uploads, wherein the channel state information is set by the wireless network
Standby to extract from the action message of target object, the action message includes: the movement and/or physiology ginseng of the target object
Number；
The demand information of the target object is determined according to the channel state information；
The demand information is sent to prompt equipment.
8. the method according to the description of claim 7 is characterized in that the demand information is sent to prompt equipment, comprising:
The demand information is sent to target electric appliance by Wireless Communication Equipment, wherein the Wireless Communication Equipment is located at institute
It states in target electric appliance；
The prompt equipment is triggered by the target electric appliance, issues the demand information to the prompt equipment.
9. a kind of monitoring device characterized by comprising
First obtains module, for obtaining the action message of target object, wherein the action message includes: the target pair
The movement and/or physiological parameter of elephant；
Extraction module, for extracting the channel state information in the action message；
Uploading module, for uploading the channel state information to server, wherein the server is according to the channel status
Information determines the demand information of the target object；
Receiving module is sent to prompt equipment for receiving the demand information, and by the demand information.
10. a kind of monitoring device characterized by comprising
Third obtains module, for obtaining the channel state information of Wireless Communication Equipment upload, wherein the channel state information
It is extracted from the action message of target object by the Wireless Communication Equipment, the action message includes: the target object
Movement and/or physiological parameter；
Determining module, for determining the demand information of the target object according to the channel state information；
Sending module, for the demand information to be sent to prompt equipment.
11. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein run in described program
When control the storage medium where equipment perform claim require 1 or 7 described in monitoring method.
12. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Benefit require 1 or 7 described in monitoring method.
13. a kind of monitoring system characterized by comprising
Wireless Communication Equipment extracts the channel state information in the action message for obtaining the action message of target object,
And the channel state information is uploaded to server, wherein the action message include: the target object movement and/
Or physiological parameter；
The server, for determining the demand information of the target object according to the channel state information；
The Wireless Communication Equipment is also used to receive the demand information, and the demand information is sent to prompt equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910640156.9A CN110363143A (en) | 2019-07-16 | 2019-07-16 | Monitoring method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910640156.9A CN110363143A (en) | 2019-07-16 | 2019-07-16 | Monitoring method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110363143A true CN110363143A (en) | 2019-10-22 |
Family
ID=68219554
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910640156.9A Pending CN110363143A (en) | 2019-07-16 | 2019-07-16 | Monitoring method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110363143A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111306715A (en) * | 2020-03-03 | 2020-06-19 | 青岛海尔空调器有限总公司 | Air conditioner and control method thereof |
| CN111652122A (en) * | 2020-06-01 | 2020-09-11 | 珠海格力智能装备有限公司 | Configuration method and device of vision system |
| CN113432252A (en) * | 2021-06-08 | 2021-09-24 | Tcl空调器(中山)有限公司 | Control method and device of air conditioner, cloud server, air conditioner and storage medium |
| CN113918012A (en) * | 2021-09-26 | 2022-01-11 | 珠海格力电器股份有限公司 | Control interface switching processing method and device, intelligent equipment and terminal |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105232022A (en) * | 2015-09-17 | 2016-01-13 | 太原理工大学 | Non-invasive breath and heartbeat detection implementation method based on CSI (channel state information) signal strength in WiFi |
| CN106407905A (en) * | 2016-08-31 | 2017-02-15 | 电子科技大学 | Machine learning-based wireless sensing motion identification method |
| CN107331136A (en) * | 2017-05-11 | 2017-11-07 | 深圳市斑点猫信息技术有限公司 | Indoor human body activity detection approach and system based on WiFi |
| CN108875584A (en) * | 2018-05-23 | 2018-11-23 | 西北工业大学 | A kind of highly reliable user behavior recognition method based on wireless aware |
| US20190020425A1 (en) * | 2017-07-17 | 2019-01-17 | Peking University | Method for determining a doppler frequency shift of a wireless signal directly reflected by a moving object |
| CN109316192A (en) * | 2018-09-13 | 2019-02-12 | 清华大学 | Sitting posture detecting method and device based on mobile network's channel state information |
-
2019
- 2019-07-16 CN CN201910640156.9A patent/CN110363143A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105232022A (en) * | 2015-09-17 | 2016-01-13 | 太原理工大学 | Non-invasive breath and heartbeat detection implementation method based on CSI (channel state information) signal strength in WiFi |
| CN106407905A (en) * | 2016-08-31 | 2017-02-15 | 电子科技大学 | Machine learning-based wireless sensing motion identification method |
| CN107331136A (en) * | 2017-05-11 | 2017-11-07 | 深圳市斑点猫信息技术有限公司 | Indoor human body activity detection approach and system based on WiFi |
| US20190020425A1 (en) * | 2017-07-17 | 2019-01-17 | Peking University | Method for determining a doppler frequency shift of a wireless signal directly reflected by a moving object |
| CN108875584A (en) * | 2018-05-23 | 2018-11-23 | 西北工业大学 | A kind of highly reliable user behavior recognition method based on wireless aware |
| CN109316192A (en) * | 2018-09-13 | 2019-02-12 | 清华大学 | Sitting posture detecting method and device based on mobile network's channel state information |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111306715A (en) * | 2020-03-03 | 2020-06-19 | 青岛海尔空调器有限总公司 | Air conditioner and control method thereof |
| CN111652122A (en) * | 2020-06-01 | 2020-09-11 | 珠海格力智能装备有限公司 | Configuration method and device of vision system |
| CN113432252A (en) * | 2021-06-08 | 2021-09-24 | Tcl空调器(中山)有限公司 | Control method and device of air conditioner, cloud server, air conditioner and storage medium |
| CN113918012A (en) * | 2021-09-26 | 2022-01-11 | 珠海格力电器股份有限公司 | Control interface switching processing method and device, intelligent equipment and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110363143A (en) | Monitoring method, device and system | |
| CN105902257B (en) | Sleep state analysis method and device, intelligent wearable device | |
| Bentlemsan et al. | Random forest and filter bank common spatial patterns for EEG-based motor imagery classification | |
| CN109363659B (en) | Heart rate monitoring method and device based on deep learning and storage medium | |
| WO2018152712A1 (en) | Vehicle-mounted health and safety driving assistance device | |
| CN105662356A (en) | Physiological physical sign monitoring method and device | |
| CN110737201B (en) | Monitoring method and device, storage medium and air conditioner | |
| CN109086789A (en) | A kind of image-recognizing method and system | |
| CN109009017A (en) | A kind of intelligent health monitoring system and its data processing method | |
| CN106936526A (en) | A kind of contactless sleep stage device and method based on channel condition information | |
| CN110353649A (en) | A kind of heart rate detection method | |
| CN109124620A (en) | A kind of atrial fibrillation detection method, device and equipment | |
| EP2884889A2 (en) | Real-time physiological characteristic detection based on reflected components of light | |
| CN106109164A (en) | Rehabilitation system and the control method of rehabilitation system | |
| CN106510686A (en) | Heart disease diagnosis system based on cloud service | |
| CN107049308A (en) | A kind of idea control system based on deep neural network | |
| US10617356B2 (en) | Garment and cardiac data processing | |
| CN114999643A (en) | WiFi-based intelligent monitoring method for old people | |
| CN105249958B (en) | Human body information monitoring method, apparatus and system | |
| WO2016104498A1 (en) | Drowsiness estimation device and drowsiness estimation program | |
| CN109492779B (en) | Household appliance health management method and device and household appliance | |
| CN109674474A (en) | Sleep apnea recognition methods, equipment and computer-readable medium | |
| WO2014108109A2 (en) | It-shirt | |
| JP6914597B2 (en) | Pet / person friendship measuring device and pet / person friendship measuring program | |
| CN108056772A (en) | A kind of long-range fetal heart monitoring automatic analysis system and its method |
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: 20191022 |
|
| RJ01 | Rejection of invention patent application after publication |