CN109840451A - A kind of wearable ring of intelligence payment and its method of payment based on electrocardio identification - Google Patents
A kind of wearable ring of intelligence payment and its method of payment based on electrocardio identification Download PDFInfo
- Publication number
- CN109840451A CN109840451A CN201711214081.5A CN201711214081A CN109840451A CN 109840451 A CN109840451 A CN 109840451A CN 201711214081 A CN201711214081 A CN 201711214081A CN 109840451 A CN109840451 A CN 109840451A
- Authority
- CN
- China
- Prior art keywords
- payment
- electrocardio
- wearable ring
- authentication
- identification
- 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
- 238000012011 method of payment Methods 0.000 title abstract description 10
- 238000004891 communication Methods 0.000 claims abstract description 23
- 238000013144 data compression Methods 0.000 claims abstract description 18
- 238000003860 storage Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000000034 method Methods 0.000 claims description 48
- 230000009466 transformation Effects 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 description 61
- 238000012549 training Methods 0.000 description 47
- 230000010354 integration Effects 0.000 description 20
- 238000010586 diagram Methods 0.000 description 18
- 239000012634 fragment Substances 0.000 description 18
- 230000006870 function Effects 0.000 description 18
- 229910052751 metal Inorganic materials 0.000 description 18
- 239000002184 metal Substances 0.000 description 18
- 238000012360 testing method Methods 0.000 description 15
- 239000013598 vector Substances 0.000 description 14
- 230000008569 process Effects 0.000 description 13
- 238000012986 modification Methods 0.000 description 8
- 230000004048 modification Effects 0.000 description 8
- 238000005070 sampling Methods 0.000 description 8
- 239000004020 conductor Substances 0.000 description 7
- 239000000284 extract Substances 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 7
- 238000001514 detection method Methods 0.000 description 6
- 230000004069 differentiation Effects 0.000 description 6
- 230000009467 reduction Effects 0.000 description 6
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 5
- 239000002390 adhesive tape Substances 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 5
- 229910052710 silicon Inorganic materials 0.000 description 5
- 239000010703 silicon Substances 0.000 description 5
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 4
- 238000013475 authorization Methods 0.000 description 4
- 230000000747 cardiac effect Effects 0.000 description 4
- 238000012937 correction Methods 0.000 description 4
- 230000033001 locomotion Effects 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 239000000741 silica gel Substances 0.000 description 4
- 229910002027 silica gel Inorganic materials 0.000 description 4
- 238000012952 Resampling Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000002994 raw material Substances 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001746 injection moulding Methods 0.000 description 2
- 230000016507 interphase Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000003921 oil Substances 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000002203 pretreatment Methods 0.000 description 2
- 238000000718 qrs complex Methods 0.000 description 2
- 238000011897 real-time detection Methods 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- FNMKZDDKPDBYJM-UHFFFAOYSA-N 3-(1,3-benzodioxol-5-yl)-7-(3-methylbut-2-enoxy)chromen-4-one Chemical compound C1=C2OCOC2=CC(C2=COC=3C(C2=O)=CC=C(C=3)OCC=C(C)C)=C1 FNMKZDDKPDBYJM-UHFFFAOYSA-N 0.000 description 1
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 239000004411 aluminium Substances 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001680 brushing effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 239000007933 dermal patch Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 210000003746 feather Anatomy 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention provides a kind of wearable ring of intelligence payment and its method of payment based on electrocardio identification.It includes wearable ring main body and annulus that the intelligence, which pays wearable ring, and wearable ring main body is mounted on annulus, and the annulus forms the first circuit of conducting after wearer wears;The wearable ring main body includes ECG's data compression unit, payment unit, central controller, storage unit and wireless communication unit;Central controller is connect with each unit in the wearable ring main body;The ECG's data compression unit includes electrode.The method of payment includes: certification or identifies the electrocardio identity of wearer, maintains the authentication or the successful state of identification, processing payment request.Electrocardio authentication is applied in payment by the present invention, also achieves agility while the safety guaranteed payment.
Description
Technical field
The present invention relates to intelligent wearable device field, in particular to a kind of intelligence payment based on electrocardio identification can be worn
Dai Huan and its method of payment.
Background technique
Present study works to have obtained National Natural Science Foundation of China (NSFC) project (NO.61571268), Science and Technology Department, Guangdong Province
Remote human body physiological multi-parameter real time monitoring and analyzing Internet of Things of the major scientific and technological project project-based on smart phone patient monitor is flat
The remote human body physiological multi-parameter of platform and demonstration project and the Committee of Development and Reform, Shenzhen major scientific and technological projects-based on smart phone is real
When monitoring with analysis network platform industrialization subsidy.
With the fast development of mobile Internet, the trend that mobile payment becomes the pith of payment technical field is bright
It is bright.Under the promotion of mobile payment tide, while the quick emergence of mobile payment offers convenience to consumer, phase is also left
The security risk answered, wherein safety of payment undoubtedly becomes everybody one of concern the most.
The wearable ring of intelligence payment in the prior art jumps to payment interface by scanning payment two dimensional code and is paid,
But there is no identification safety authentication units for the wearable ring, not can guarantee the safety of payment.Another kind intelligence in the prior art
For the wearable ring of energy after the electrocardiosignal certification of wearer passes through, which generates a random dynamic password and control
Radio communication mold group processed is sent to mobile terminal, for completing payment.The wearable ring is required in each payment to wearing
The electrocardiosignal of person authenticates, and also to send dynamic password to mobile terminal, be unable to complete authentication-exempt, exempts from password payment,
Need the occasion of quick payment not convenient enough.Intelligence in the prior art pays the safety that wearable ring can not guarantee payment simultaneously
Property and agility.
Summary of the invention
The purpose of the present invention is to solve intelligence in the prior art to pay the peace that wearable ring can not guarantee payment simultaneously
The problem of full property and agility, proposes that a kind of intelligence based on electrocardio identification pays wearable ring.
In order to solve the above technical problems, the invention adopts the following technical scheme:
A kind of wearable ring of intelligence payment based on electrocardio identification, including wearable ring main body and annulus, it is wearable
Ring main body is mounted on annulus, and the annulus forms the first circuit of conducting after wearer wears;The wearable ring main body
Including ECG's data compression unit, payment unit, central controller, storage unit and wireless communication unit;Central controller with
Each unit connection in the wearable ring main body;The ECG's data compression unit includes electrode, and the electrode includes setting
It sets in the wearing of wearable ring and the first electrode of the one side of skin contact and the other faces for dressing Shi Buyu skin contact
Second electrode;The ECG's data compression unit acquires the electrode in the case where the annulus forms the first conducting circuit
To the living body real-time continuous electrocardiosignal of wearer be converted to electrocardio authentication or identification information, and be connected back first
Road maintains the certification or identification information effective during not turning off.
In some preferred embodiments, the first electrode and second electrode of wearable ring can form second by human body
Circuit is connected.
In some preferred embodiments, the payment unit includes near field payment unit and mobile terminal payment application
Software gateway unit;The near field payment unit is for completing near field payment;The mobile terminal payment application software entrance list
Member is that mobile terminal payment application software and wearable ring are attached and provide entrance, for completing remote payment.
On the other hand, the present invention also provides the payers that a kind of intelligence based on electrocardio identification pays wearable ring
Method successively includes:
S100, certification or identify wearer electrocardio identity: wear every time wearable ring and formed first conducting circuit and
When the second conducting circuit, the living body real-time continuous electrocardiosignal of wearable ring acquisition wearer simultaneously carries out authentication or identification,
Authentication records the authentication or the successful state of identification after identifying successfully;
S200, maintain the authentication or the successful state of identification: whether the annulus for detecting wearable ring persistently forms the
One conducting circuit, if so, the authentication or the successful state of identification are maintained, if it is not, then closing the authentication or identification
Successful state;
S300, processing payment request: when authentication or the successful state of identification maintain, if there is payment request, then
Start payment processing program.
In some preferred embodiments, the method for the electrocardio identity of the certification or identification wearer includes such as lower section
One of method: the authentication of auto-correlation transformation electrocardio or recognizer, the authentication of sparse features electrocardio or recognizer, nerve net
The authentication of network electrocardio or recognizer, the authentication of datum mark electrocardio or recognizer.
In some preferred embodiments, it after starting payment processing program, also requires to carry out step S400 payment really
Recognize program, the payment affirmation program is realized in the following way:
S410, it detects whether to form the second conducting circuit, if so, being judged as that payment affirmation program passes through.
In further preferred embodiment, step S420 is executed after completing step S410: judging the second conducting circuit
Turn-on time: if turn-on time is less than preset value, be judged as that confirmation program passes through, if circuit turn-on time be greater than it is default
Value, then it is assumed that wearer goes to step S410 if electrocardio authentication is completed in progress electrocardio authentication.
In some preferred embodiments, described to carry out authentication or be identified by as under type is realized: with
The ecg characteristics template of wearer is compared in electrocardio authentication center.
In some preferred embodiments, included the following steps: before using remote payment function
S510, wearable ring and mobile terminal are bound by application software;
The payment function of mobile terminal payment application software is issued to wearable ring by S520, application software.
In some preferred embodiments, further include step S000 wearer registration: using for the first time, wearable ring is from the heart
Electric authentication center is authorized.
Compared with prior art, the beneficial effects of the present invention are as follows:
Annulus can form the first conducting circuit, and electrode can then form the second conducting circuit, wear wearable ring and shape every time
When at the first conducting circuit and the second conducting circuit, the electrocardiosignal of wearable ring acquisition wearer simultaneously carries out authentication or knowledge
Not and the state is recorded, maintain the authentication in the case where annulus persistently forms the first conducting circuit later or is identified successfully
State.Wearer need to only touch the second electrode of the other faces of wearing Shi Buyu skin contact when paying with finger
Payment can be completed in a short time.The safety of electrocardio authentication or identification for guaranteeing payment, then leads by first
The agility of payment is realized in logical circuit and the second conducting circuit.
Further, payment unit includes near field payment unit and mobile terminal payment application software gateway unit, is both mentioned
It has supplied near field payment to meet the small amount payment demand in the places such as public transport, supermarket, has also provided mobile terminal payment application software
To meet the needs of remote payment.
Detailed description of the invention
Fig. 1 a, Fig. 1 b are respectively the integrally-built front view and rearview of wearable ring of the invention;
Fig. 2 is the structural schematic diagram of wearable ring main body of the invention;
Fig. 3 builds flow chart for electrocardio authentication center of the invention;
Fig. 4 a is the structural schematic diagram of annulus of the invention, and Fig. 4 b is the front view of wearable ring main body, and Fig. 4 c is that can wear
Wear the rearview of ring main body;
Fig. 5 is the structural schematic diagram of annulus of the invention;
Fig. 6 is the structural schematic diagram of payment unit of the invention;
Fig. 7 is the structural schematic diagram of ECG's data compression unit of the invention;
Fig. 8 is the process signal for the method for payment that the intelligence of the invention based on electrocardio identification pays wearable ring
Figure;
Fig. 9 is the flow diagram of step S400 payment affirmation program of the invention;
Figure 10 is the flow diagram of step S300 payment processing program of the invention;
Figure 11 is flow diagram the step of using before remote payment function in method of payment of the invention;
Figure 12 is the structural schematic diagram of near field payment unit of the invention.
Specific embodiment
It elaborates below to embodiments of the present invention.It is emphasized that following the description is only exemplary,
The range and its application being not intended to be limiting of the invention.
Fig. 1 a be it is of the invention can threading ring integrally-built front view, Fig. 1 b be it is of the invention can threading ring entirety
The rearview of structure.It includes wearable ring main body 10 and annulus 20 that the intelligence based on electrocardio identification, which pays wearable ring,
Wearable ring main body 10 is mounted on annulus 20.
Fig. 2 is the structural schematic diagram of wearable ring main body of the invention.Wearable ring main body 10 includes ECG's data compression
Unit 104, payment unit 102, central controller 100, storage unit 105 and wireless communication unit 103.ECG's data compression mould
104 pieces include be arranged in wearable ring wearing when and skin contact one side first electrode 013 and dress Shi Buyu skin
Patch type electrode can be used in the second electrode 014 of the other faces of contact, electrode, as shown in Figure 1.
Wearable ring main body 10 is the main body of wearable ring, including all multiple-units, wearable ring main body 10 are mounted on annulus
On 20.
Annulus 20 is used to for wearable ring being worn on human body, and annulus 20 forms conducting first after wearer wears
Circuit.
ECG's data compression unit 104 is connect with storage unit 105, the first electrode on ECG's data compression unit 104
013 and second electrode 014 be used to form the second conducting circuit and acquisition signal, which includes voltage signal and electrocardiosignal.
First electrode 013 and 014 collection voltages signal of second electrode can be used for judging whether the circuit between two electrodes is connected, and acquire the heart
Electric signal is then for electrocardio authentication or identification.ECG's data compression unit 104 is by first electrode 013 and second electrode
The electrocardiosignal of 014 collected wearer is converted to electrocardio identity information, stores into storage unit 105.
Payment unit 102 is connect for completing payment with central controller 100.
Central controller 100 is connect with each unit in wearable ring main body 10, for handling information and to each list
Member sends instruction.
Storage unit 105 is connect with central controller 100, wireless communication unit 102, ECG's data compression unit 104, is used
In storage information, including electrocardio identity information and system operation information.
Wireless communication unit 103 is connect with storage unit 105 and central controller 100, wireless communication unit 102 be used for
Exterior terminal is communicated, including sends and receivees information.Received information includes extraneous payment request, wireless communication unit
103 receive payment request communicates the request to central controller 100 later.The information of transmission includes authorization message and electrocardio body
Part authenticates successful information, and authorization message includes the instruction or information for allowing to pay.The form of the exterior terminal can be clothes
Business device, mobile phone, tablet computer, the POS, for example wearable ring of wearable device, wrist-watch, glasses, helmet etc., the present invention is not
As limit.
Wearable ring is worn on one and forms the first conducting circuit afterwards on hand by wearer, and wearer is by an other hand
Finger is put into the second electrode 014 of the other faces of wearing Shi Buyu skin contact, and first electrode 013 is worn in wearable ring
After on hand just and skin contact, it is formed between first electrode 013 and second electrode 014, the second conducting circuit can be worn at this time
Dai Huanhui reminds wearer's progress electrocardio authentication or identification, the form of the prompting to can be the forms such as voice or vibration,
These promptings can be realized by increasing voice unit or vibration unit etc. on wearable ring.Wearer is reminded in wearing ring
After carrying out electrocardio authentication or identification, wearer keeps for the finger of an other hand being put into wearing Shi Buyu skin contact
In the second electrode 014 of other faces, second electrode 014 acquires the electrocardiosignal of wearer at this time, delivers it to electrocardio
Signal processing unit 104 is processed into electrocardio identity information and is stored in storage unit 105, and central controller 100 is by the electrocardio
Unit 103 is compared identity information with the ecg characteristics template of wearer in electrocardio authentication center by wireless communication, if not
Matching, then be not available payment function and warning message be sent to the exterior terminal of binding, if matching, the electrocardio of wearer
Authentication is identified by, and wearable ring records the authentication or the successful state of identification.At this point, central controller 100
Whether first conducting circuit is persistently formed on real-time detection annulus 20, if it is not, such as wearable ring is taken from wearer
Or wearable ring main body 10 is dismantled from annulus 10, then electrocardio authentication or identification failure before determining, wearable ring
It is not available, can prevent wearable ring from being stolen after through electrocardio authentication or identification by other people in this way and is used to pay, if
It is to continue to form the first conducting circuit, then wearable ring is in working condition, is then being received in wireless communication unit 103
Central controller 100 can be communicated the request to when the payment request of outside, central controller 100 starts payment processing program,
At this point, wearer need to only touch the second electrode 014 of the other faces of wearing Shi Buyu skin contact with finger, make first electrode
013 and second electrode 014 formed second conducting circuit, so that it may be completed in a short time payment.Further, it is formed when payment
Second conducting circuit refers to one of following: wearable ring is carrying out electrocardio authentication;Wearable ring is in detection first electrode 013
Whether be connected between second electrode 014.
It builds as follows at electrocardio authentication center:
Fig. 3 builds flow chart for electrocardio authentication center of the invention.
Building for electrocardio authentication center is broadly divided into two stages, registration phase and authentication phase.
Registration phase: the electrocardiosignal of application authentication people is acquired by electrocardiogram acquisition equipment, wherein electrocardiogram acquisition equipment can
Including terminals such as mobile phone, computer, electrocardiograph, intelligent wearable devices, then signal eliminates noise jamming by pretreatment, so
It carries out feature extraction again afterwards to generate ecg characteristics template, electrocardio optimal characteristics template is selected and evaluate later, after selection
Optimal template is stored to electrocardio authentication center;Same step carries out other biological informations except electrocardiosignal
Acquisition, including fingerprint, iris, palmmprint, face, sound, movement and posture, as candidate biometric templates;At the same time, also
It needs to store the second-generation identification card information of application authentication people to electrocardio authentication center, uniquely to indicate application authentication people's
Identity information.
Authentication phase: when there is the request of authenticating device application authentication information of electrocardio authentication central authority, electrocardio
Authentication center sends the ecg characteristics template and identity information of application authentication people on authenticating device, and authenticating device includes
Wearable ring, mobile phone, tablet computer, the POS, POS machine, authenticating device are carried out according to the ecg characteristics template and identity information
Using, but authenticating device does not have the ecg characteristics template at permission change electrocardio authentication center, the only right to use.Authenticating device
It can also apply for candidate biometric templates to electrocardio authentication center, cause certification to be lost when exception occurs in electrocardio authentication
When losing, authenticating device can carry out authentication using candidate biometric templates.
As described above, in the present invention, wearing wearable ring every time and forming the first conducting circuit and the second conducting
When circuit, the electrocardiosignal of wearable ring acquisition wearer simultaneously carries out authentication or identification and records the state, later in ring
Band maintains the authentication or the successful state of identification in the case where persistently forming the first conducting circuit.Wearer is paying
When, the second electrode for the other faces that only wearing Shi Buyu skin contact need to be touched with finger can be completed in a short time payment.
Wherein, if electrocardio authentication or identification do not pass through or wearable ring or wearable ring main body 10 are by from wearer
Disassembly, wearable ring are not all available, and can effectively prevent the stolen brush of wearable ring in this way.Wearable ring passes through electrocardio authentication
Or identification ensure that the safety of payment, and the agility of payment is then realized by the first conducting circuit and the second conducting circuit,
It is convenient to use various payment occasions.
The overall structure of wearable ring is illustrated above, it is also possible to there is the form of some modifications, such as:
After starting payment processing program, central controller 100 can issue prompting, for example be worn by voice or vibrating alert
Finger is touched second electrode 014 by person, then judges the second conducting whether is formed between first electrode 013 and second electrode 014
Circuit is paid if so, central controller 100 controls payment unit 102, passes through voice after completing payment or vibration is informed and worn
Wearer;
The communication pattern of wireless communication unit 103 includes one of Bluetooth communication, WIFI communication, 3G and 4G communication or more
Kind.
Fig. 4 a is the structural schematic diagram of annulus of the invention, and Fig. 4 b is the front view of wearable ring main body, and Fig. 4 c is that can wear
Wear the rearview of ring main body.Annulus 20 includes strip conductor (not shown) and retainer plate 220, the setting of 220 both ends of retainer plate
There are two metal connector 221 and 222, strip conductor connect to form access with metal connector 221 and 222.Wearable ring master
Body 10 is mounted in retainer plate 220, the contact 110 and 120 at wearable 10 both ends of ring main body respectively with metal connector 221 and
222 contacts, form the first circuit between wearable ring main body 10 and annulus 20.Returning between wearable ring main body 10 and annulus 20
When road is not turned on, for example annulus 20 is destroyed, wearable ring main body 10 is disassembled, wearable ring is removed, and wearable ring can not
It uses.
As described above, in the present invention, strip conductor is connect with metal connector 221 and 222, ring main body 10 is dressed
The contact 110 and 120 at both ends is contacted with metal connector 221 and 222.In this way, strip conductor is just connect with wearing ring main body 10,
An anti-dismounting structure is formed, once some component is disassembled, payment function is not available, to avoid wearable ring stolen
Brush.
The structure of annulus is illustrated above, it is also possible to there is the form of some modifications, such as:
Strip conductor is conductive silicon adhesive tape.Electric silica gel raw material and retainer plate are put into silica gel mould, solid oil is passed through
It presses technique to complete the production of conductive silicon adhesive tape, and connect conductive silicon adhesive tape closely with the metal connector at retainer plate both ends, reach
It is acted on to conducting;
Conductive silicon adhesive tape is put into mold and is fixed, it is 30-60 degree soft silica gel that hardness is laid flat in corresponding conductive silicon adhesive tape
Raw material completes the encapsulated molding of surface soft silica gel of annulus by solid-state oil pressure technique;
Metal connector is metal spring needle;
By plastic cement products injection molding process, TPU or TPE raw material, metal connector are passed through into mold injection molding
Technique forms retainer plate 220, and the shape of retainer plate 220 can be to be oval, round, rectangular, and invention is not limited thereto.
Fig. 5 is the structural schematic diagram of annulus of the invention.One end of annulus 20 is equipped with metal press-stud 230, and the other end is equipped with
Through-hole 240, metal press-stud 230 are connect with strip conductor (not shown), and annulus is made to form the first conducting circuit.Wearer will
After one end of annulus 20 penetrates the other end, then metal press-stud 230 buckled into the through-hole 240 of other end annulus, forms annulus
First conducting circuit.When 230 snap-fastener of metal press-stud disengages, it is disassembly status, electrocardio authentication that wearable ring, which is formed and disconnected,
Or identification failure.
As described above, in the present invention, the metal press-stud 230 of 20 one end of annulus and the through-hole 240 of the other end fasten
Afterwards, annulus 20 forms conducting circuit.Only when annulus 20 forms conducting circuit, the open state of payment unit 102 just can quilt
It maintains, once annulus 20 does not form the first conducting circuit, electrocardio authentication or identification failure, avoids other people for wearable ring
Brush is stolen after taking from the body of wearer.
The structure of annulus is illustrated above, it is also possible to there is the form of some modifications, such as:
The material of metal press-stud 230 includes stainless steel, copper or aluminium;
Metal press-stud 230 is buckled on annulus 20 and is fixed, allows metal press-stud and strip conductor to form access, can be completed
The installation of metal press-stud 230, it is such simple to operate;
The shape of through-hole 240 includes round, oval, rectangular.
Fig. 6 is the structural schematic diagram of payment unit of the invention.Payment unit 102 includes near field payment unit 112 and moves
Dynamic terminal pays application software gateway unit 122.Near field payment unit 112 is for completing near field payment.Mobile terminal payment is answered
It is that mobile terminal payment application software and wearable ring are attached and provide entrance with software gateway unit 122, it is remote for completing
Cheng Zhifu.
In payment, central controller 100 judges that external payment request is that near field payment request or remote payment are asked
It asks, correspondingly controls near field payment unit 112 or mobile terminal payment application software gateway unit 122 completes payment.
As described above, in the present invention, payment unit 102 includes near field payment unit 112 and mobile terminal payment
Application software gateway unit 122 had provided near field payment both to meet the small amount payment demand in the places such as public transport, supermarket, had also mentioned
For Third-party payment to meet the needs of remote payment.
The structure of payment unit is illustrated above, it is also possible to there is the form of some modifications, such as:
Mobile terminal payment application software includes Alipay payment and wechat payment;
Such as Figure 12, near field payment unit 112 includes NFC (Near Field Communication, near-field communication) function
Chip 132 and intelligent encryption chip 142.Wherein, NFC function chip is for the communication function in payment process, intelligent encryption core
Piece 142 is further ensured that safety of payment for encrypting to the information of transaction.
Fig. 7 is the structural schematic diagram of ECG's data compression unit of the invention.ECG's data compression unit 104 further includes putting
Big device unit 301, AD conversion unit 302 and microcontroller 200.Amplifier unit 301 and electrode 013,014 and digital-to-analogue conversion
Unit 302 connects, and amplifier unit 301 amplifies the electrocardiosignal of electrode 013,014 collected wearer.Modulus turns
It changes unit 302 to connect with amplifier unit 301 and microcontroller 200, AD conversion unit 302 amplifies amplifier unit 301
Signal later is converted to the accessible digital signal of microcontroller 200, and the digital signal is transmitted to microcontroller 200.
Microcontroller 200 is connect with AD conversion unit 301 and storage unit 105, and microcontroller 200 passes AD conversion unit 302
The digital signal come pre-process and generates electrocardio identity information by electrocardio recognizer, is saved in storage unit 105
For electrocardio authentication.
As described above, in the present invention, using dual processor framework, electrocardiosignal is independent by microcontroller 200
Electrocardio identity information is managed into, electrocardio authentication is then completed by central controller 100, can be reduced the power consumption of system and be controlled to center
The loss of device 100 processed, so that the service life and single charge that effectively extend wearable ring are using the time.
The method of payment that the above-mentioned intelligence based on electrocardio identification pays wearable ring is described below:
Fig. 8 is the flow diagram for the method for payment that the intelligence based on electrocardio identification pays wearable ring.The payment
Method includes:
S100, certification or identify wearer electrocardio identity: wear every time wearable ring and formed first conducting circuit and
When the second conducting circuit, the second electrode 014 of wearable ring acquires the living body real-time continuous electrocardiosignal of wearer, by the signal
ECG's data compression unit 104 is sent to be processed into electrocardio identity information and be stored in storage unit 105, central controller
The electrocardio identity information is passed through the ecg characteristics mould of wearer in wireless communication unit 103 and electrocardio authentication center by 100
Plate is compared, if mismatching, is not available payment function and warning message is sent to the exterior terminal of binding, if
Match, then the electrocardio authentication of wearer or be identified by, wearable ring enter to working condition and record the authentication or
Identify successful state;Further, authentication or be identified by as under type realize: wireless communication unit 103 to
Electrocardio authentication center issues the request of authentication information, and electrocardio authentication center sends the ecg characteristics template of wearer
Onto the wireless communication unit 103 of wearable ring, central controller 100 will be stored in the heart of the wearer in storage unit 105
Electric identity information is compared with ecg characteristics template.
S200, the authentication or the successful state of identification are maintained: after the electrocardio authentication success of wearer, center
Whether first conducting circuit is persistently formed on 100 real-time detection annulus 20 of controller, if it is not, such as wearable ring is by from wearer
It takes with it or wearable ring main body 10 is dismantled from annulus 10, then electrocardio authentication or identification failure before determining,
Wearable ring is not available, and can be prevented wearable ring from being stolen after through electrocardio authentication by other people in this way and is used to pay,
If circuit is connected, wearable ring is in working condition;
S300, processing payment request: when authentication or the successful state of identification maintain, if there is payment request, then
Start payment processing program.If receiving external payment request, central controller 100 starts payment processing program: control paying bill
Member 102 completes transaction, and after completing payment, wearable ring notifies wearer by way of voice or vibration.
The method of payment of wearable ring is illustrated above, it is also possible to there is the form of some modifications, for example is authenticated
Or the method for the electrocardio identity of identification wearer is one of with the following method:
The authentication of auto-correlation transformation electrocardio or recognizer:
Step 301, into electrocardio authentication state;
Step 302, it acquires the electrocardiosignal of wearer and pre-processes, detect R wave position, intercept the step of QT wave band
Suddenly;
Step 303, the QT wave band of interception is subjected to feature extraction using auto-correlation transformation algorithm, obtains electrocardio auto-correlation sequence
The step of column;
Step 304, the electrocardio autocorrelation sequence that will acquire is returned by way of fitting and carries out dimensionality reduction, and feature is generated
The step of template;
Step 305, the feature templates of generation and electrocardio optimal characteristics template are subjected to aspect ratio pair, it is complete according to optimal threshold
The step of at certification.
In this embodiment, the formula of auto-correlation transformation algorithm described in step 303 is
Wherein, x [i] indicates electrocardio sequence, and N indicates the length of electrocardio sequence, and x [i+m] indicates to translate m sequence to electrocardio sequence
Electrocardio sequence afterwards, m=0,1,2 ..., M-1, M < < N, Rxx[m] indicates electrocardiosignal autocorrelation sequence, Rxx[0] electrocardio is indicated
The energy of sequence.
It should be noted that autocorrelation sequence R between Different Individualxx[m] has apparent otherness, can be used as a body-centered
The inherent feature of electric signal.Since QRS complex is that electrocardiosignal changes minimum most stable of composition under test wrapper border not of the same race,
So length of the value of m close to QRS wave, autocorrelation sequence R of the electrocardio sequence x [i] after auto-correlation processingxx[m] is still
High dimensional signal needs to carry out dimension-reduction treatment.
In this embodiment, it is returned described in step 304 by way of fitting and carries out dimensionality reduction, generated
Feature templates are by indicating electrocardio autocorrelation sequence with polynomial approximation, and obtaining indicates the electrocardio auto-correlation with feature templates
Sequence.
Specifically, the multinomial is a0+a1f1(xi)+a2f2(xi)+...+akfk(xi)=ATFi≈Rxx[i].Wherein A table
Show feature templates, and in above-mentioned multinomial, A=(a0,a1,a2,...,ak)T,Fi=(1, f1(xi),f2(xi),...,fk(xi)
)T, i=0,1,2,3 ..., M-1, wherein 1, f1(xi),f2(xi),...,fk(xi) it is respectively for 0 time, 1 time, 2 times ..., k of x
Secondary orthogonal polynomial, wherein
I.e.F is the sample frequency of electrocardiosignal.
The calculation formula of feature templates are as follows:
Wherein, λ, α ∈ (0,1), λ, α
For regularization coefficient,For the vector A and F after solutioni, obtained feature templates are A=(a0,
a1,a2,...,ak)T, k < < M takes n feature templates A of n template generation1,A2,...,An, 10≤n≤20.
In this embodiment, interception QT wave band described in step 302 is on the left of the R wave 90 milliseconds
Minimum point is Q wave point, and maximum of points is T crest value point within 300 milliseconds of the R wave right side, on the right side of the T crest value point
First-order difference is for the first time the T waveform cut off by bearing positive position, then generates the described of regular length by wave shape correcting
QT wave band.
In this embodiment, pretreatment described in step 302 includes: to be filtered to electrocardiosignal, is adopted
The electrocardiosignal for collecting user's certain time length, filters out Hz noise, baseline drift and myoelectricity interference etc. using suitable filter and makes an uproar
Sound.Preferably, trap is carried out to the Frequency point of power frequency 50Hz, removes 50Hz Hz noise in waveform;Use cutoff frequency 40Hz
Butterworth LPF filter out myoelectricity interference;Baseline drift is eliminated using the high-pass filter greater than 1Hz.
In some embodiments, the feature extraction further includes using the differentiation word for rarefaction representation in step 303
Allusion quotation learning algorithm obtains, specifically,
Wherein, J(D,C)Dictionary D and sparse features C, Verif (X after being to solve fori,Xj,D,Ci,Cj) it is feature differentiation attribute, λ is sparse
Degree coefficient, α are regularization coefficient, λ and α value range is all between 0 to 1.
XiWith XjRespectively indicate i-th and j-th of QT wave, CiAnd CjIt respectively indicates and XiAnd XjCorresponding sparse features.
Wherein, i ≠ j.
Wherein,
Dm is the minimum range between the inhomogeneity of setting, label (Xi) indicate XiClass number.
s.t.||dj| |=1,1≤j≤l
Wherein, X=(X1,X2,...,Xn) indicate n QT wave;D=(d1,d2,...,dl) indicate dictionary dimension, l is big
In 1 any number;Indicate sparse features.
In further embodiments, in step 303 the feature extraction the following steps are included:
C1: determine that the length of window that an ecg information is included at least on interception electrocardiosignal, length of window are greater than one
The heart claps length, it is ensured that each window contains at least one the complete information of heart bat.The heartbeat of normal person at 60-100 beats/min,
Special population is generally also at 40 beats/min or more, therefore length of window selects 1-2 seconds or more, that is, can ensure that in window and at least wrap
Containing the complete information that a heart is clapped, the complete information that a heart is clapped here is not limited to the same heart and claps, also claps comprising two hearts
Different piece can be combined into a heart bat complete information.Length of window is no longer after window d is fixed, when training and test
Variation.
C2: according to the length of window determined, sliding window intercepts the heart of corresponding length from any position of electrocardiosignal
Electric window intercepts in electrocardio window procedure, does not have any restrictions to the initial point position of window, especially heavy in the real-time testing stage
It wants.
The electrocardio window: being divided into multiple fixed length segments by C3, obtains multiple characteristic fragments, each electrocardio window
Mouth is divided into any fixed length segments of n, and wherein n is greater than or equal to 1, it is assumed that and it by the electrocardio window that window d is intercepted is x, it is any fixed
Length is divided into n characteristic fragment { x1, x2,...,xn, any fixed length segment refers to that fragment length is less than electrocardio length of window and consolidates
It is fixed.
Characteristic fragment includes two stages by full-automatic feature extraction layer: convolutional layer and maximum pond layer;Wherein: including with
Lower step:
A21: parallel-convolution is carried out to the characteristic fragment by multiple convolutional layers, obtains multiple vector values, herein
For multiple 1 × m dimensional vector values.Wherein convolutional layer number is n, and each convolutional layer number of plies is greater than 1, and convolution kernel K is one-dimensional convolution kernel;
N characteristic fragment { x1, x2,...,xnBy generating n vector { c after convolutional layer1, c2,...,cn, in which:
Wherein i value range is [1, n], and l is the convolution number of plies, and b is biasing, and initial value can zero setting.
N vector { c1, c2,...,cnDirectly generate matrix A=[c1, c2,...,cn]m×n。
A22: multiple vector values generate depth integration feature by the maximum pond layer.Maximum pond core having a size of 1 ×
N, maximum pond core generate depth integration feature DeepFusionFeature=[f after acting on matrix A1,f2,...fm]T.It is maximum
Pond core acts on matrix A:
fi=max (ci1, ci2,...,cin);
A23: the depth integration feature is trained classification, output category judging result, root by the full articulamentum
The full-automatic feature extraction layer is extracted as the feature extractor according to classification judging result.
In certain embodiments, the method for feature extraction is different, comprising: first in detection electrocardiosignal each datum mark with
The heartbeat of quasi periodic is extracted as original electrocardiographicdigital feature.Electrocardiosignal is a kind of quasi-periodic signal, but is not entire
Ingredient in cardiac cycle all has specificity, wherein the P wave, QRS complex and T wave in each cardiac cycle contain major part
Electrocardio specificity information.The embodiment of the present invention is from the wave band for cutting in continuous electrocardiosignal in each cardiac cycle as former
The ecg characteristics of beginning.For this purpose, to orient the datum mark of heartbeat.In addition, in subsequent wave shape correcting link, it is also necessary to further
P wave and T wave are handled.Therefore, it is necessary to orient the key position of these waveforms, these points are referred to as datum mark.This
Inventive embodiments include: P wave starting point (Ps) and P wave terminal (Pe), R wave crest (R), J wave for the datum mark of each heartbeat detection
Starting point (J), T wave crest (Tp) and T wave terminal (Te) amount to 6 class datum marks.
Wherein, electrocardiosignal totally relatively mitigates, and R wave is most sharp part.R wave is located at the minimum of signal second differnce
It is worth position, and first-order difference is 0.The minimum of the second differnce signal of original signal of the embodiment of the present invention determines the thick of R wave
Slightly position.After the rough position for orienting R wave, it is in this feature of maximum position further according to R-wave amplitude, first derivative is
0, in the discrete case, i.e., first-order difference signal closest to zero that, the R crest location of registration accordingly.
Further, in 160-180 millisecond ranges on the left of each R wave one preferably as at 170 milliseconds for P wave starting point Ps;
With in 80-100 millisecond ranges on the left of each R wave one preferably as at 90 milliseconds for P wave terminal Pe;With 80-100 on the right side of each R wave crest
Preferably if 90 milliseconds of places are J wave starting point (J) at one in millisecond range;It is with the maximum value in one section of region on the right side of each R wave crest (R)
T wave crest (Tp), this section of region is since J wave starting point at 2/3 current RR interphase (duration i.e. two neighboring R wave crest)
Cut-off;With first-order difference signal on the right side of T wave crest (Tp) for the first time by bearing positive position as T wave terminal (Te).
Due to the variation of heart rate, the heartbeat in each paracycle is not identical, therefore the embodiment of the present invention proposes one kind
The method of segmented waveform correction eliminates the influence of heart rate variability, and the basic skills of correction is that segmentation weight is carried out to former heartbeat signal
Sampling extends pattern-band duration specifically, up-sample to pattern-band after up-sampling, is unified for 460-500 milliseconds, excellent
Such as 480 milliseconds of choosing;QRS wave section is remained unchanged, such as 180 milliseconds long;For T wave band, respectively to wherein J-Tp sections and Tp-
Tp sections of progress down-samplings, so that each duration of two segments is unified for 10-20 milliseconds after resampling, preferably such as 15 milliseconds.Finally, it corrects
Heartbeat overall length afterwards is almost the same, and for example, 690 milliseconds.Since heart rate is different to people in different time and after different motion
Sample, and the difference of this heart rate should not become the standard for measuring people's identity characteristic.The present invention is generated on the basis of QRS wave section
A kind of signal facilitating detection, cardiac cycle length is consistent, to eliminate heart rate variability bring difference.
Finally, using PCA dimensionality reduction and extraction coefficient feature is as final ecg characteristics;PCA principal component analysis can will be believed
Number energy focuses on direct current and low frequency part, and the present invention carries out feature extraction and feature to by the smoothed out heartbeat of PCA whereby
Dimensionality reduction.Preferably, it extracts and keeps each shafting number of the contribution rate more than given threshold as coefficient characteristics, given threshold is preferably
99%.Experiment test discovery, the coefficient vector registration of heartbeat is higher, shows that inter- object distance is small between them;Energy mainly divides
Cloth is in preceding 80 dimension.
The authentication of sparse features electrocardio or recognizer:
The step of acquiring electrocardiosignal;
The electrocardiosignal of acquisition is pre-processed with interception QT wave module in pretreatment, R wave position is detected, intercepts QT
The step of wave;With processing unit to acquisition come electrocardiosignal pre-process, detect R wave position, interception m QT waveform, it is excellent
Selection of land, the number of QT wave are 16.
It should be noted that preferably, the interception of QT waveform passes through sampling number partitioning.Specifically, sampling frequency is obtained
Rate fHz, QT wavelength t takes 0.32-0.44 seconds;QRS wave a length of 0.1 second.QT number of samples num=[f*t], wherein [] is to be rounded
Function.QRS number of samples num_QRS=[f*0.1].The point centered on each R wave takes forward [(num_QRS-1)/2] a point,
(num-1- [(num_QRS-1)/2]) a point, including R wave central point is taken to constitute QT wave backward.
Sample frequency f depends on the frequency of used electrocardiogram acquisition equipment itself, it is preferable that f=125Hz, num=
[125*0.4]=50, num_QRS=[125*0.1]=12.
The QT wave of interception is used for the differentiation of rarefaction representation in the extraction of multiple ecg characteristics and data processing module
Dictionary learning algorithm generates the step of sparse features;
Wherein, include: for the differentiation dictionary learning algorithm of rarefaction representation
Wherein, J(D,C)Dictionary D and sparse features C, Verif (X after being to solve fori,Xj,D,Ci,Cj) it is that characteristic area is adhered to separately
Property, λ is sparse degree coefficient, and α is regularization coefficient, λ and α value range is all between 0 to 1.
XiWith XjRespectively indicate i-th and j-th of QT wave, CiAnd CjIt respectively indicates and XiAnd XjCorresponding sparse features.
Wherein, i ≠ j.
Wherein,
Dm is the minimum range between the inhomogeneity of setting, label (Xi) indicate XiClass number.
s.t.||dj| |=1,1≤j≤l
Wherein, X=(X1,X2,...,Xn) indicate n QT wave;D=(d1,d2,...,dl) indicate dictionary dimension, l is big
In 1 any number;Indicate sparse features.
The sparse features of generation are based on optimal threshold and carry out fuzzy matching in template matching module, complete preliminary certification,
The step of being voted later based on highest entropy, completing certification.
Preferably, the search process of optimal threshold is scanned for using Euclidean distance, and specifically, search process includes:
The selected subset S arbitrarily from optimal characteristics module F, residue character module are FcS;
Using S as training set, FcS and protrdata are test set searching threshold thd1;
Using FcS as training set, S and protrdata are test set searching threshold thd2;
Calculate the maximin maxthd, minthd of Euclidean distance two-by-two in training set.Searching times are set
Iternum then traverses threshold valueI value is from 1 to iternum herein, to obtain FRR
={ frr1,frr2,...,frriternumAnd FAR={ far1,far2,...,fariternum}.It is available by FRR and FAR |
FAR-FRR |=| far1-frr1|, | far2-frr2| ..., | fariternum-frriternum|, take frr and far difference absolute
I-th threshold corresponding to value minimum is the most suitable threshold value searched, i.e. thd1 and thd2.
Optimal threshold Best_thd is obtained based on thd1 and thd2:
Wherein, Num (x) indicates the number of x.
In this embodiment, step 104 is ballot certification benchmark using frequency as the highest entropy, whenWhen meeting, i.e., the individual authentication passes through.Otherwise, authentification failure.
Wherein, FiIndicate i-th of optimal sparse features module;C2jIndicate j-th of sample to be certified;I value is 1 to nl.j
Value is 1 to m.f(Fi,C2j) it is feature FiWith the distance computation of feature C2j;It indicates to work as feature FiWith feature
C2jSpacing be less than optimal threshold Best_thd when take 1, otherwise take 0.
The authentication of neural network electrocardio or recognizer:
The electrocardio identity process of certification wearer is broadly divided into two stages of model training stage and real-time testing stage,
Model training stage includes the Nonlinear Classification in pretreatment and snippet extraction, the training of full-automatic feature extraction layer and parallel sorting
Device training, real-time testing stage include pretreatment and the Nonlinear Classifier in snippet extraction, Concurrent Feature extraction, parallel sorting
Parallel sorting and the ballot of highest entropy.
Model training stage the following steps are included:
A1, pretreatment and snippet extraction: will be used for the acquisition of trained and electrocardiosignal to be identified progress any position, and
To the ECG signal processing of acquisition, snippet extraction is carried out to pretreated electrocardiosignal and obtains multiple characteristic fragments;
A2, the training of full-automatic feature extraction layer: according to full-automatic feature extraction network to multiple feature pieces of acquisition
Section by automatically extracting the full-automatic feature extraction layer of training module and full articulamentum is trained, after extracting training it is complete certainly
Feature extraction layer is moved as feature extractor;
The real-time testing stage the following steps are included:
B1, pretreatment and snippet extraction: it will be used for the acquisition of electrocardiosignal progress to be identified any position, and to acquisition
ECG signal processing, to pretreated electrocardiosignal carry out snippet extraction obtain multiple characteristic fragments;
B2, feature identification: according to the trained multiple feature extractors of model training stage to electrocardiosignal to be identified
Concurrent Feature extraction is carried out, parallel sorting is carried out to the feature extracted, exports identification result.
Specifically specifically include that pretreatment and snippet extraction;Full-automatic feature extraction layer training;Concurrent Feature is extracted;Parallel
Classification;The ballot of highest entropy.
Wherein in step A1 the following steps are included:
C1: being filtered electrocardiosignal, the electrocardiosignal of user's certain time length is acquired, using suitable filter
Filter out the noises such as Hz noise, baseline drift and myoelectricity interference.Trap is carried out to the Frequency point of power frequency 50Hz, is removed in waveform
50Hz Hz noise;Myoelectricity interference is filtered out using the Butterworth LPF of cutoff frequency 40Hz;Use the height for being greater than 1Hz
Bandpass filter eliminates baseline drift.
C2: determine that the length of window that an ecg information is included at least on interception electrocardiosignal, length of window are greater than one
The heart claps length, it is ensured that each window contains at least one the complete information of heart bat.The heartbeat of normal person at 60-100 beats/min,
Special population is generally also at 40 beats/min or more, therefore length of window selects 1-2 seconds or more, that is, can ensure that in window and at least wrap
Containing the complete information that a heart is clapped, the complete information that a heart is clapped here is not limited to the same heart and claps, also claps comprising two hearts
Different piece can be combined into a heart bat complete information.Length of window is no longer after window d is fixed, when training and test
Variation.
C3: according to the length of window determined, sliding window intercepts the heart of corresponding length from any position of electrocardiosignal
Electric window intercepts in electrocardio window procedure, does not have any restrictions to the initial point position of window, especially heavy in the real-time testing stage
It wants.
The electrocardio window: being divided into multiple fixed length segments by C4, obtains multiple characteristic fragments, each electrocardio window
Mouth is divided into any fixed length segments of n, and wherein n is greater than or equal to 1, it is assumed that and it by the electrocardio window that window d is intercepted is x, it is any fixed
Length is divided into n characteristic fragment { x1, x2,...,xn, any fixed length segment refers to that fragment length is less than electrocardio length of window and consolidates
It is fixed.
In step A2, the full-automatic feature extraction layer includes multiple convolutional layers and maximum pond layer, uses full-automatic feature
It extracts network and carries out full-automatic feature extraction, needing clear convolution kernel is one-dimensional convolution kernel, and down-sampled process is also one-dimensional operation,
Maximum pond operation is also one-dimensional operation.
Using full-automatic feature extraction network training, the full-automatic extraction module of the full-automatic feature extraction network includes complete
Automatic Feature Extraction layer and full articulamentum, the full-automatic feature extraction layer include multiple convolutional layers and maximum pond layer, this implementation
Full-automatic feature extraction network used in example, including convolution layer model and full connection layer model are made based on identification target
Structural adjustment, these structural adjustments include: the increase and decrease of the convolution number of plies, the increase and decrease of the full connection number of plies, maximum pond layer the number of plies with
Number adjustment, the one-dimensional change in size of convolution kernel, down-sampled one-dimensional change in size, convolutional layer are connect entirely with the input of other Fusion Features
The parallel training process of layer.
Characteristic fragment includes two stages by full-automatic feature extraction layer: convolutional layer and maximum pond layer;Wherein: including with
Lower step:
A21: parallel-convolution is carried out to the characteristic fragment by multiple convolutional layers, obtains multiple vector values, herein
For multiple 1 × m dimensional vector values.Wherein convolutional layer number is n, and each convolutional layer number of plies is greater than 1, and convolution kernel K is one-dimensional convolution kernel;
N characteristic fragment { x1, x2,...,xnBy generating n vector { c after convolutional layer1, c2,...,cn, in which:
Wherein i value range is [1, n], and l is the convolution number of plies, and b is biasing, and initial value can zero setting.
N vector { c1, c2,...,cnDirectly generate matrix A=[c1, c2,...,cn]m×n。
A22: multiple vector values generate depth integration feature by the maximum pond layer.Maximum pond core having a size of 1 ×
N, maximum pond core generate depth integration feature DeepFusionFeature=[f after acting on matrix A1,f2,...fm]T.It is maximum
Pond core acts on matrix A:
fi=max (ci1, ci2,...,cin);
A23: the depth integration feature is trained classification, output category judging result, root by the full articulamentum
The full-automatic feature extraction layer is extracted as the feature extractor according to classification judging result.
Classification is trained using typical losses function, in the step A23: when training discrimination is greater than threshold value, then
Deconditioning extracts depth integration feature, extracts using the full-automatic feature extraction layer that the depth integration feature forms as feature
Otherwise extractor continues to train.Wherein, typical losses function is Euclidean distance:
Wherein, when N is the training of full-automatic feature extraction layer, pass through the number of samples of full-automatic feature extraction layer every time.
Trained stop condition is that trained discrimination acc_tr is greater than threshold value acc_pre, and threshold value acc_pre is according to practical need
It asks and is ok between 0.5-1.0,For the prediction classification number of j-th of training sample,For j-th training sample
Concrete class number.
When training discrimination acc_tr is greater than threshold value acc_pre, model training stops, and extracts full-automatic feature extraction layer
As feature extractor, depth integration feature is extracted, in the step A2, according to the acquisition feelings of electrocardiosignal described in step A1
Condition further trains full-automatic feature extraction layer if can continue to acquire electrocardiosignal, will be original when reaching bigger threshold value
Feature extractor replacement.
It further include the training to the Nonlinear Classifier, comprising: by step B21 in the model training stage
The classification number in the depth integration feature extracted is using Nonlinear Classifier training module to scheduled Nonlinear Classification
Device is trained, specifically:
Training stage, collected electrocardiosignal have category label, and the characteristic fragment of these electrocardiosignals is by training
Full-automatic feature extraction layer afterwards extracts depth integration feature.
Common Nonlinear Classifier, such as kernel support vectors machine and neural network are selected, using with category label
Depth integration feature trains Nonlinear Classifier parameter.
In step B2, comprising the following steps:
B21, feature extraction carry out Concurrent Feature extraction to electrocardiosignal to be identified according to multiple feature extractors,
Obtain the depth integration feature of the electrocardiosignal to be identified;
B22, tagsort, to the depth integration feature of the electrocardiosignal to be identified, according to electrocardiosignal to be identified
Classification number by training after multiple Nonlinear Classifier parallel sortings, complete identification.
Real-time perfoming is filtered in real-time testing stage, pretreatment and snippet extraction, the window based on any initial position
Mouth interception, therefore when collected electrocardiosignal reaches window d length, identification process can be started.
As acquisition signal increases, constantly there is characteristic fragment to need to carry out feature extraction.Feature extractor is trained complete
Finish, depth integration is extracted to characteristic fragment parallel using the full-automatic feature extraction layer (feature extractor) after multiple training here
Feature.The parallel number of convolutional layer is determined with experimental facilities performance according to actual needs after training, and parallel number is got over multiple features and mentioned
Take speed faster.
After characteristic fragment is by the full-automatic feature extraction layer (feature extractor) after training, one-dimensional is extracted
Depth integration feature.
Parallel sorting is carried out using Nonlinear Classifier, and then it is quick to make up feature extractor (full-automatic feature extraction layer)
But insufficient training process.Nonlinear Classifier has completed the training to Nonlinear Classifier parameter in the training stage.
Parallel sorting is carried out to depth integration feature using the Nonlinear Classifier after multiple training, wherein non-after training
The number of linear classifier is identical as the convolutional layer number after training in Concurrent Feature extraction module.
Each Nonlinear Classifier can identify a prediction classification to the depth integration feature of input, as us
Preliminary classification classification.
The present embodiment, in the step B2, carrying out identification by multiple Nonlinear Classifiers is preliminary identification,
Further include the steps that voting by feature and carry out final identification procedure: being voted using highest entropy, count preliminary identity
Entropy of all categories in identification, according to the entropy counted, using the corresponding classification number of maximum entropy as final recognition result.
By highest entropy vote module carry out highest entropy ballot when, frequently with entropy such as frequency.It counts in preliminary classification
The number of the appearance of each classification calculates the frequency of each classification in preliminary classification.
According to the entropy counted, maximum entropy, such as highest frequency are searched.The corresponding classification number of maximum entropy is system
Final recognition result.
100 people are arbitrarily selected to survey in the ecg database PTB Diagnostic ECG Database of internal authority
Examination, everyone selects the full-automatic feature extraction layer of 200 window training and Nonlinear Classifier module, then from everyone the residue heart
It intercepts 100 windows in electric signal to be tested, accuracy rate reaches 99.9% or more, tests quantity and test result is in a leading position
Status is all satisfied actual demand.
This method provides foreseeable effect for large-scale crowd application.Convolutional neural networks are mentioned in image classification and feature
Aspect is taken to have been achieved with good effect, an important feature is that have distortion invariance and shift invariant.Change network
Structure is applied to one-dimensional electrocardiosignal.Any window cuts electrocardiosignal, each although window initial position is different
Window at least guarantees the complete information that a heart is clapped, while all window sizes are identical, and each window segment is divided into arbitrarily
Fixed length segment, by the characteristic of convolutional neural networks, by the feature selecting feature in maximum pond, completely automatic extraction electrocardio letter
Number feature.After the completion of full-automatic feature extraction network training, the depth integration feature extracted using full-automatic feature extraction layer,
Design Nonlinear Classifier further classifies and is voted by highest entropy, can take into account training speed, depth integration feature can divide
Property, identification speed and performance, so that it is real-time based on electrocardiosignal in practical application to can satisfy the method for the present embodiment
Identification.The advantage of deep learning is also exactly that learning sample is more, and network performance is better, and recognition effect is more preferably.
The authentication of datum mark electrocardio or recognizer:
The method for authenticating the electrocardio identity of wearer includes pre-treatment step, characteristic extraction step and authenticating step, wherein
Pre-treatment step includes being filtered to the electrocardiosignal of acquisition to eliminate interference, and characteristic extraction step includes detection electrocardio
Heartbeat signal of each datum mark to extract quasi periodic in signal carries out segmentation wave to heartbeat as original electrocardiographicdigital feature
After shape correction, recycles PCA dimensionality reduction and extraction coefficient feature is as final ecg characteristics, authenticating step includes using to be based on template
Matched method carrys out discriminating test sample, and whether authentication is successful.Preferably, each datum mark includes that the P wave of heartbeat rises
Point (Ps), P wave terminal (Pe), R wave crest (R), J wave starting point (J), T wave crest (Tp) and T wave terminal (Te).
In a preferred embodiment, in the characteristic extraction step, Trigger jitter detection and waveform are carried out in the following manner
Segmentation:
Electrocardiosignal determines the position of the R wave of heartbeat by wavelet transformation mode, or is believed with the second differnce of electrocardiosignal
Number minimum determine heartbeat R wave rough position, then determine that first-order difference signal at the rough position of R wave is closest
In zero that point, the position of R wave crest (R) is positioned accordingly;
With at one in 160-180 millisecond ranges on the left of each R wave crest (R) for P wave starting point (Ps);Apart from each R wave
On the left of peak (R) in 80-100 millisecond ranges one at for P wave terminal (Pe);With the 80-100 milliseconds of ranges on the right side of each R wave crest
It is J wave starting point (J) at interior one;With, for T wave crest (Tp), this section of region is from J at the maximum value in one section of region on the right side of each R wave crest
Wave starting point (J) starts at 2/3 current RR interphase cut-off;With first-order difference signal on the right side of T wave crest (Tp) for the first time by bearing just
Position at be T wave terminal (Te).
In a preferred embodiment, in the characteristic extraction step, segmented waveform correction is carried out in the following manner:
Segmentation resampling is carried out to heartbeat signal, wherein up-sampling to each pattern-band, extends P wave after up-sampling
Duan Shichang makes each pattern-band duration be unified for 460-500 milliseconds;Each QRS wave section duration is remained unchanged;For each T wave band,
Respectively to J~Tp sections and Tp~Tp sections progress down-samplings, so that respectively duration is unified for two segments after each T wave band resampling
10-20 milliseconds.
In a preferred embodiment, it in the characteristic extraction step, extracts and keeps contribution rate each more than given threshold
For shafting number as coefficient characteristics, given threshold is preferably 99%.
As described above, a kind of intelligence based on electrocardio identification of embodiment of the present invention pays wearable ring
The electrocardio identity of method of payment, S100 certification or identification wearer are used to authenticate the identity of wearer, and electrocardio authentication belongs to
Biometrics identification technology, compared to traditional biological feather recognition method such as fingerprint, palmmprint, face, iris etc., electrocardiosignal
With living body real-time continuous biological characteristic, it is difficult to forge, acquisition is convenient, has convenience more higher than other biological feature and peace
Congruent grade.S200 maintain the authentication or the successful state of identification from another point of view ensure that wearable ring is by wearing
Person uses, and prevents wearable ring from stealing brush by other people.On the basis of in front the step of, S300 handles payment request short
Payment can be completed in time.Due to only needing just to need to carry out when wearing wearable ring the electrocardio authentication of wearer,
During payment, wearer need to only use finger to touch second electrode 014, thus when waiting when reducing payment
Between, the Product Experience of wearer is improved, also both ensure that safety, also achieves agility.
After starting payment processing program, also require to carry out step S400 payment affirmation program, Fig. 9 is step of the invention
The flow diagram of S400 payment affirmation program, payment affirmation program are realized in the following way:
S410, it detects whether to form the second conducting circuit, if so, being judged as that payment affirmation program passes through;That is center control
Whether the finger that device 100 processed detects wearer touches second electrode 014, if so, between first electrode 013 and second electrode 014
It will form the second conducting circuit.
S420, the turn-on time for judging the second conducting circuit: if the turn-on time in the circuit between electrode is less than preset value,
Then it is judged as that confirmation program passes through, if circuit turn-on time is greater than preset value, then it is assumed that wearer is carrying out electrocardio authentication
Or identification returns to step S410 if electrocardio authentication or identification is completed.The preset value of turn-on time can be wearable
It is configured on ring.
As described above, in the present invention, step S400 payment affirmation program, which passes through, judges leading for the second conducting circuit
The logical time, can intelligent recognition wearer be to be led carrying out electrocardio authentication or identification or preparing to pay to circuit
Logical judgement is also heavy wearer's authentication, ensure that the reliability of payment, also achieves quick payment.When due to payment
It needs to be formed the second conducting circuit by step S400 and judges turn-on time, can prevent wearer from accidentally touching and leading to unexpected branch
It pays.
Step S400 payment affirmation program is illustrated above, it is also possible to there is the form of some modifications, for example is walked
Rapid S420 judges that the turn-on time in the second conducting circuit becomes: the electrocardiosignal for acquiring wearer carries out electrocardio authentication, if
Electrocardio authentication passes through, then is judged as that confirmation program passes through, if not passing through, refuses to pay.
Figure 10 is the flow diagram of step S300 payment processing program of the invention.S300 payment processing program includes
The near field S310 payment processing program and S320 remote payment processing routine.
S310, near field payment processing program successively include:
S311, control near field payment unit are paid, and Transaction Information is recorded, user is reminded after the completion of payment;
S312, the waiting of wearable ring use next time;
S320, remote payment processing routine successively include:
S321, the electrocardio authentication for sending wearer or the information that has passed through of identification are to mobile terminal;The mobile terminal includes
Mobile phone, tablet computer, POS machine, wearable device etc..
S322, mobile terminal automatically enter the preset payment cipher of wearer, remind user after the completion of payment;
S323, the waiting of wearable ring use next time.
As described above, in the present invention, S312 and S323 are after the completion of payment for step, it can all enter and wait next time
The state used, it is complete because wearer needs to be touched second electrode 014 with hand and payment unit 102 can just be made to enter use state
After payment, the use state of payment unit 102 is closed, and can not be paid again, can be effectively prevented accidentally brush, again in this way
The phenomenon that brushing again guarantees the interests of wearer.
With reference to Figure 11, included the following steps: before using remote payment function
S510, wearable ring and mobile terminal are bound by application software;Wearer needs wearable ring and moves
Dynamic terminal is bound, so that wearable ring is communicated with mobile terminal.One is equipped on mobile terminal for wearable
The application software of ring, after wearable ring and mobile terminal binding, wearer also need by wearable ring and the application software into
Row binding.
The payment function of mobile terminal payment application software is issued to wearable ring by S520, application software.Application software
In mobile terminal payment application software include wechat payment software, Alipay payment software, mobile terminal payment application software
Gateway unit 122 provides the entrance that mobile terminal payment application software accesses wearable ring, and wearer can be in application software
The payment function of mobile terminal payment application software is issued to wearable ring, when payment, wearable ring be can be realized
Corresponding Third-party payment function.
As described above, in the present invention, wearable ring is bound with mobile terminal, it can be in time by Transaction Information
Or system notification information is sent to wearer, to remind wearer.The application software for borrowing mobile terminal, can be by various thirds
Square payment function is issued to wearable ring, has flexibility.
Figure 12 is the flow diagram that step S000 wearer of the invention registers.The method of payment of wearable ring further includes
S000 wearer registration:
It uses for the first time, wearable ring is authorized from electrocardio authentication center.Wearable ring unit by wireless communication
103 send authorization requests to electrocardio authentication center, and the electrocardio authentication center processing request Concurrency goes out to authorize, wearable
It, can be to electrocardio authentication center application authentication information when using backward after ring obtains the authorization at electrocardio authentication center
Request.
Step S000 wearer registration is illustrated above, it is also possible to there is the form of some modifications, for example is used
One of following method:
Autocorrelation sequence electrocardio register method:
The QT wave band of interception is subjected to feature extraction using auto-correlation transformation algorithm, obtains the step of electrocardio autocorrelation sequence
Suddenly;
The electrocardio autocorrelation sequence that will acquire is returned by way of fitting and carries out dimensionality reduction, and the step of feature templates is generated
Suddenly;
The step of selecting and evaluate electrocardio optimal characteristics template from the feature templates of generation;
The step of optimal threshold is obtained from electrocardio optimal characteristics template;
Specifically, taking the minimum range of feature templates vector between any two is (thd_down), maximum distance is (thd_
Up), then the value range of threshold value is (thd_down, thd_up), the number of iterations iternum, then the step-length changed isThe value of threshold value isWherein i=1,
2,...,iternum。
False acceptance rate (FAR) and false rejection rate (FRR) are the functions of threshold value, in systems, mistake occur and receives
It is different with the cost of wrong rejection, it is assumed that it is cost that the cost that mistake receives, which occurs,1, the cost that False Rejects occur is
cost2(cost1>cost2), ROC curve is made according to FAR and FRR first, makes cost curve further according to ROC curve, is selected
So that threshold value corresponding to overall cost minimum is optimal threshold best_thd.
Sparse features electrocardio register method:
A, negative sample is prestored in the negative sample pre-collecting and preprocessing module the step of;It should be noted that negative sample
Prodata is made of the QT waveform of h user, and each user includes n QT waveform;It is mainly used for pre-training dictionary D and best
Threshold search, h value range theoretical value are more than or equal to 1, value is bigger, and pre-training dictionary D performance is better and optimal threshold is searched
Suo Yue is accurate, it is preferable that h takes 100.For each user, n QT wave of interception is more, and training performance is better, but is consumed
Time also accordingly promoted, it is preferable that the number n of the QT wave takes 16.It is generated after the completion of pre-training dictionary D training and prestores negative sample
This sparse features protrdata.
B, the electrocardiosignal as negative sample of acquisition is pre-processed with interception QT wave module in pretreatment, is detected
The step of R wave position, interception QT wave;Judge to register user whether as new user, if not new user, i.e., in the negative sample prestored
Included user in this does not need to update dictionary, newest dictionary D '=D at this time.If it is new user, then need by
Line learning algorithm updates dictionary D, and then obtains newest dictionary D '.The on-line learning algorithm is existed by Mairal et al.
The rarefaction representation word that " Online learning for matrix factorization and sparse coding " is proposed
Allusion quotation on-line learning algorithm updates dictionary D, specifically, according to pre-training dictionary D, solves corresponding sparse features C, is counted by D and C
Reconstructed error is calculated, newest dictionary D '=D is quickly updated.Wherein, refer to new user QT waveform.
C, the QT wave of interception is used for the differentiation dictionary of rarefaction representation in preliminary ecg characteristics template extraction module
Learning algorithm generates the step of sparse features template:
Wherein, J(D,C)Dictionary D and sparse features C, Verif (X after being to solve fori,Xj,D,Ci,Cj) it is feature differentiation attribute, λ is sparse
Degree coefficient, α are regularization coefficient, λ and α value range is all between 0 to 1.
XiWith XjRespectively indicate i-th and j-th of QT wave, CiAnd CjIt respectively indicates and XiAnd XjCorresponding sparse features.
Wherein, i ≠ j.
Wherein,
Dm is the minimum range between the inhomogeneity of setting, label (Xi) indicate XiClass number.
s.t.||dj| |=1,1≤j≤l
Wherein, X=(X1,X2,...,Xn) indicate n QT wave;D=(d1,d2,...,dl) indicate dictionary dimension, l is big
In 1 any number;Indicate sparse features.
D, the step of optimal sparse features template is evaluated in best ecg characteristics evaluation module based on sparse features template
Suddenly;
Specifically, using leaving-one method, differentiated one by one by threshold value, thus excluding outlier.
Wherein, C1=(C11,C12,...,C1n);f(C1i,C1j) it is feature C1iWith feature C1jDistance computation;It indicates to work as feature C1iWith feature C1jSpacing be less than preset threshold prothd when take 1, otherwise take 0.Prothd
Value often take the average value mean (f (C1 of n sparse featuresi,C1j)).I value is 1 to n.J value is 1 to n, and i ≠ j.
When above formula condition meets, i-th of sample is chosen as high-quality sparse features;When being unsatisfactory for, i-th of sample is as different
Constant value is suggested.Finally select optimal sparse features template F=(F1,F2,...,Fnl), wherein nl≤n.
E, the step of optimal threshold being searched out in optimal threshold search module based on optimal sparse features template.
As described above, in the present invention, electrocardiosignal in collection process vulnerable to many random noises and around ring
The influence of border interference is caused collection point that can generate with skin and is contacted due to tested individual respiratory movement or body movement
Variation, and then different types of noise jamming can be caused.Electrocardiosignal can be filtered by pretreatment to remove noise
Interference, guarantee the accuracy of electrocardiosignal, to improve the reliability of electrocardio authentication.
Wearable ring of the invention includes bracelet and finger ring, and technical solution of the present invention passes through the change or substitution of adaptability
It also can be applied to other electronic equipments such as mobile phone, tablet computer, the POS, POS machine etc. later.
The above content is combine it is specific/further detailed description of the invention for preferred embodiment, cannot recognize
Fixed specific implementation of the invention is only limited to these instructions.For those of ordinary skill in the art to which the present invention belongs,
Without departing from the inventive concept of the premise, some replacements or modifications can also be made to the embodiment that these have been described,
And these substitutions or variant all shall be regarded as belonging to protection scope of the present invention.
Claims (10)
1. a kind of intelligence based on electrocardio identification pays wearable ring, it is characterised in that including wearable ring main body and ring
Band, wearable ring main body are mounted on annulus, and the annulus forms the first circuit of conducting after wearer wears;It is described can
Dressing ring main body includes ECG's data compression unit, payment unit, central controller, storage unit and wireless communication unit;In
Centre controller is connect with each unit in the wearable ring main body;The ECG's data compression unit includes electrode, described
Electrode include when the wearing of wearable ring is set and the first electrode of the one side of skin contact and wearing Shi Buyu skin contact
Other faces second electrode;The ECG's data compression unit is in the case where the annulus forms the first conducting circuit by institute
The living body real-time continuous electrocardiosignal for stating the collected wearer of electrode is converted to electrocardio authentication or identification information, and
First conducting circuit maintains the certification or identification information effective during not turning off.
2. the intelligence according to claim 1 based on electrocardio identification pays wearable ring, it is characterised in that wearable
The first electrode and second electrode of ring can form the second conducting circuit by human body.
3. the intelligence according to claim 1 or 2 based on electrocardio identification pays wearable ring, it is characterised in that described
Payment unit includes near field payment unit and mobile terminal payment application software gateway unit;The near field payment unit has been used for
It is paid near field;The mobile terminal payment application software gateway unit be mobile terminal payment application software and wearable ring into
Row connection provides entrance, for completing remote payment.
4. the method for payment that a kind of intelligence based on electrocardio identification pays wearable ring, it is characterised in that successively include:
S100, certification or the electrocardio identity for identifying wearer: wearing wearable ring every time and forms the first conducting circuit and second
When circuit is connected, the living body real-time continuous electrocardiosignal of wearable ring acquisition wearer simultaneously carries out authentication or identification, identity
Authenticate or record after identifying successfully the authentication or the successful state of identification;
S200, maintain the authentication or the successful state of identification: whether the annulus for detecting wearable ring, which persistently forms first, is led
Logical circuit, if so, the authentication or the successful state of identification are maintained, if it is not, then closing the authentication or identifying successfully
State;
S300, processing payment request: when authentication or the successful state of identification maintain, if there is payment request, then start
Payment processing program.
5. the intelligence according to claim 4 based on electrocardio identification pays the method for payment of wearable ring, feature
The method for being the certification or the electrocardio identity of identification wearer includes one of following method: auto-correlation transformation electrocardio identity is recognized
Card or recognizer, the authentication of sparse features electrocardio or recognizer, the authentication of neural network electrocardio or recognizer, base
Electrocardio authentication on schedule or recognizer.
6. the intelligence according to claim 4 based on electrocardio identification pays the method for payment of wearable ring, feature
It is, after starting payment processing program, also requires to carry out step S400 payment affirmation program, the payment affirmation program is logical
It crosses as under type is realized:
S410, it detects whether to form the second conducting circuit, if so, being judged as that payment affirmation program passes through.
7. the intelligence according to claim 6 based on electrocardio identification pays the method for payment of wearable ring, feature
It is, executes step S420 after completing step S410: judges the turn-on time in the second conducting circuit: being preset if turn-on time is less than
Value is then judged as that confirmation program passes through, if circuit turn-on time is greater than preset value, then it is assumed that wearer recognizes in progress electrocardio identity
Card, if electrocardio authentication is completed, goes to step S410.
8. the intelligence according to claim 4 based on electrocardio identification pays the method for payment of wearable ring, feature
It is, it is described to carry out authentication or be identified by as under type is realized: with wearer in electrocardio authentication center
Ecg characteristics template is compared.
9. the intelligence according to claim 4 based on electrocardio identification pays the method for payment of wearable ring, feature
It is, is included the following steps: before using remote payment function
S510, wearable ring and mobile terminal are bound by application software;
The payment function of mobile terminal payment application software is issued to wearable ring by S520, application software.
10. paying the payer of wearable ring according to the described in any item intelligence based on electrocardio identification of claim 4-9
Method, which is characterized in that further include step S000 wearer registration: using for the first time, wearable ring is obtained from electrocardio authentication center
It must authorize.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711214081.5A CN109840451A (en) | 2017-11-28 | 2017-11-28 | A kind of wearable ring of intelligence payment and its method of payment based on electrocardio identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711214081.5A CN109840451A (en) | 2017-11-28 | 2017-11-28 | A kind of wearable ring of intelligence payment and its method of payment based on electrocardio identification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109840451A true CN109840451A (en) | 2019-06-04 |
Family
ID=66880819
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711214081.5A Pending CN109840451A (en) | 2017-11-28 | 2017-11-28 | A kind of wearable ring of intelligence payment and its method of payment based on electrocardio identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109840451A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110403599A (en) * | 2019-08-19 | 2019-11-05 | 深圳旭宏医疗科技有限公司 | Cardioelectric monitor method, apparatus, computer equipment and storage medium |
CN110750775A (en) * | 2019-10-22 | 2020-02-04 | 广东乐芯智能科技有限公司 | Heart rate identity recognition method |
CN110786850A (en) * | 2019-11-11 | 2020-02-14 | 菏泽学院 | Electrocardiosignal identity recognition method and system based on multi-feature sparse representation |
CN112364327A (en) * | 2020-11-27 | 2021-02-12 | 风林科技(深圳)有限公司 | Intelligent wearable device identity authentication method and intelligent wearable device |
CN112818315A (en) * | 2021-02-26 | 2021-05-18 | 山东大学 | Electrocardiosignal identity recognition method and system fusing multi-feature information |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104102915A (en) * | 2014-07-01 | 2014-10-15 | 清华大学深圳研究生院 | Multiple-template matching identity recognition method based on ECG (Electrocardiogram) under electrocardiogram abnormality state |
CN105740679A (en) * | 2014-12-24 | 2016-07-06 | 三星电子株式会社 | Electronic device having user identifying function and user authentication method |
CN106326705A (en) * | 2015-06-30 | 2017-01-11 | 宇龙计算机通信科技(深圳)有限公司 | Authorization authentication method and device and relevant equipment |
CN107111703A (en) * | 2015-01-05 | 2017-08-29 | 三星电子株式会社 | Use the method and apparatus of the user authentication of biological characteristic |
-
2017
- 2017-11-28 CN CN201711214081.5A patent/CN109840451A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104102915A (en) * | 2014-07-01 | 2014-10-15 | 清华大学深圳研究生院 | Multiple-template matching identity recognition method based on ECG (Electrocardiogram) under electrocardiogram abnormality state |
CN105740679A (en) * | 2014-12-24 | 2016-07-06 | 三星电子株式会社 | Electronic device having user identifying function and user authentication method |
CN107111703A (en) * | 2015-01-05 | 2017-08-29 | 三星电子株式会社 | Use the method and apparatus of the user authentication of biological characteristic |
CN106326705A (en) * | 2015-06-30 | 2017-01-11 | 宇龙计算机通信科技(深圳)有限公司 | Authorization authentication method and device and relevant equipment |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110403599A (en) * | 2019-08-19 | 2019-11-05 | 深圳旭宏医疗科技有限公司 | Cardioelectric monitor method, apparatus, computer equipment and storage medium |
CN110750775A (en) * | 2019-10-22 | 2020-02-04 | 广东乐芯智能科技有限公司 | Heart rate identity recognition method |
CN110750775B (en) * | 2019-10-22 | 2021-12-03 | 西安云晖猎豹智能科技有限公司 | Heart rate identity recognition method |
CN110786850A (en) * | 2019-11-11 | 2020-02-14 | 菏泽学院 | Electrocardiosignal identity recognition method and system based on multi-feature sparse representation |
CN112364327A (en) * | 2020-11-27 | 2021-02-12 | 风林科技(深圳)有限公司 | Intelligent wearable device identity authentication method and intelligent wearable device |
CN112818315A (en) * | 2021-02-26 | 2021-05-18 | 山东大学 | Electrocardiosignal identity recognition method and system fusing multi-feature information |
CN112818315B (en) * | 2021-02-26 | 2022-03-15 | 山东大学 | Electrocardiosignal identity recognition method and system fusing multi-feature information |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109840451A (en) | A kind of wearable ring of intelligence payment and its method of payment based on electrocardio identification | |
CN108776788B (en) | Brain wave-based identification method | |
Abo-Zahhad et al. | Biometric authentication based on PCG and ECG signals: present status and future directions | |
Regouid et al. | Multimodal biometric system for ECG, ear and iris recognition based on local descriptors | |
CN108460318B (en) | Identity authentication/identification method and equipment based on electrocardiosignals | |
AU2003256693B2 (en) | Method and apparatus for electro-biometric identiy recognition | |
CA2586772C (en) | Method and apparatus for electro-biometric identity recognition | |
WO2018152711A1 (en) | Electrocardiographic authentication-based door control system and authentication method therefor | |
Chauhan et al. | A survey of emerging biometric modalities | |
CN101499134A (en) | Iris recognition method and system based on field programmable gate array | |
EP3449409B1 (en) | Biometric method and device for identifying a person through an electrocardiogram (ecg) waveform | |
CN110287918A (en) | Vivo identification method and Related product | |
JP5642210B2 (en) | Method and apparatus for electronic biometric identification recognition | |
CN101819629B (en) | Supervising tensor manifold learning-based palmprint identification system and method | |
KR101578167B1 (en) | self-organized real-time authentication method using ECG signal | |
CN109255219A (en) | A kind of temperature sense unlocking method and system based on bio-identification terminal | |
CN111062021B (en) | Method and device for identity authentication based on wearable equipment | |
Guelta et al. | An Improved Behavioral Biometric System based on Gait and ECG signals. | |
CN107888552B (en) | A kind of identity identifying method and system based on electrocardiosignal | |
Liwen et al. | A dual-biometric-modality identification system based on fingerprint and EEG | |
CN111444489B (en) | Double-factor authentication method based on photoplethysmography sensor | |
Rabie et al. | Nfc-based person-specific assisting system in home environment | |
Al-Rahawe et al. | An analysis on biometric traits recognition | |
Shrikhande et al. | Personal identification using different biometrics: A review | |
Rabie et al. | Nfc-based person-specific medical assistant for elderly and disabled people |
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: 20190604 |
|
RJ01 | Rejection of invention patent application after publication |