CN109598630A - The monitoring and managing method and relevant device of fixed point medical institution based on living things feature recognition - Google Patents
The monitoring and managing method and relevant device of fixed point medical institution based on living things feature recognition Download PDFInfo
- Publication number
- CN109598630A CN109598630A CN201811473507.3A CN201811473507A CN109598630A CN 109598630 A CN109598630 A CN 109598630A CN 201811473507 A CN201811473507 A CN 201811473507A CN 109598630 A CN109598630 A CN 109598630A
- Authority
- CN
- China
- Prior art keywords
- card
- medical insurance
- biological information
- medical
- insurance card
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 80
- 238000012544 monitoring process Methods 0.000 title claims abstract description 37
- 239000003814 drug Substances 0.000 claims abstract description 138
- 230000004044 response Effects 0.000 claims abstract description 7
- 229940079593 drug Drugs 0.000 claims description 110
- 238000012549 training Methods 0.000 claims description 49
- 230000008569 process Effects 0.000 claims description 25
- 239000000284 extract Substances 0.000 claims description 23
- 238000013527 convolutional neural network Methods 0.000 claims description 20
- 230000001815 facial effect Effects 0.000 claims description 16
- 238000012423 maintenance Methods 0.000 claims description 11
- 230000008901 benefit Effects 0.000 claims description 10
- 208000033748 Device issues Diseases 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 claims description 2
- 238000007689 inspection Methods 0.000 claims 1
- 230000001960 triggered effect Effects 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000008520 organization Effects 0.000 description 6
- 238000010276 construction Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000005194 fractionation Methods 0.000 description 4
- 210000004209 hair Anatomy 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000001755 vocal effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 2
- 239000010931 gold Substances 0.000 description 2
- 229910052737 gold Inorganic materials 0.000 description 2
- 230000000977 initiatory effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 244000086443 Craterellus fallax Species 0.000 description 1
- 235000007926 Craterellus fallax Nutrition 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4014—Identity check for transactions
- G06Q20/40145—Biometric identity checks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Security & Cryptography (AREA)
- Technology Law (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Collating Specific Patterns (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The monitoring and managing method and relevant device for the fixed point medical institution that the invention discloses a kind of based on living things feature recognition.This method comprises: the request of swiping the card paid using medical insurance card that fixed point medical institution supervising platform is triggered in response to card swiping device, obtains the identifier of the first biological information and medical insurance card using the user of medical insurance card；According to identifier, the second biological information of the holder of the corresponding medical insurance card of identifier is obtained from social security platform；First biological information is matched with the second biological information；If the first biological information and the second biological information mismatch, the instruction for being forbidden to use the payment of medical insurance card is issued to card swiping device.The present invention is by realizing above scheme based on biometrics identification technology, effective solution in the prior art can not supervise fixed point medical institution, not can avoid fixed point medical institution and swipe the card in violation of rules and regulations using supervision loophole, arbitrarily raise the technical issues of medicine valence.
Description
Technical field
The present invention relates to medical supervision technical field more particularly to a kind of fixed point medical institutions based on living things feature recognition
Monitoring and managing method and relevant device.
Background technique
Social medical insurance is state and society according to certain laws and regulations, is provided for the labourer into scope of insurance coverage
Basic medical demand guarantee when illness and the social security system established.It sees a doctor in order to facilitate insurant, purchase medicine, government doctor
Treatment insurance management relevant department (such as HI center) is stringent from numerous social pharmacies according to certain standard according to national regulation
The qualified social pharmacy of a batch is selected as fixed point pharmacy, that is, hold the insurant of medical insurance card fixed point pharmacy can
To buy the drug for allowing to pay using medical insurance card, to facilitate insurant selection apart from oneself closer fixed point pharmacy
Purchase medicine and medical treatment.Also, it sees a doctor to further facilitate insurant, purchase medicine, need to follow when selecting fixed point pharmacy " two
Determine title examination " also gradually cancel, the audit to fixed point pharmacy is relaxed, so that the quantity of fixed point pharmacy is more and more, it is insured
Personnel can be more convenient medical treatment and purchase medicine.
But due to currently without more complete Regulation Policy, thus with the increase of fixed point pharmacy, problem also follows on sb.'s heels
And arrive.For example, fixed point pharmacy carries out swipe the card in violation of rules and regulations (medical insurance card), arbitrage, generation for number one, using supervision loophole
Brush, random the phenomenon that raising medicine valence, adulterating, emerge one after another.This not only violates medical insurance management relevant regulations, so that medical
Insurance fund is unable to reasonable employment, necessary, reasonable primary care cannot be provided for insured people, while also resulting in industry
Interior harmful competition, seriously affects market order.
So it is urgent to provide one kind to supervise to the fixed point medical institution such as fixed point pharmacy, to prevent fastening point medicine
Mechanism carries out the method swiped the card in violation of rules and regulations, arbitrarily raise medicine valence using supervision loophole.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The monitoring and managing method for the fixed point medical institution that the main purpose of the present invention is to provide a kind of based on living things feature recognition
And relevant device, it is intended to solve in the prior art can not effectively supervise fixed point medical institution, determine to not can avoid
Point medical institution swipe the card in violation of rules and regulations using supervision loophole, arbitrarily raises the technical issues of medicine valence.
To achieve the above object, the monitoring party for pinpointing medical institution based on living things feature recognition that the present invention provides a kind of
Method the described method comprises the following steps:
Medical institution supervising platform is pinpointed in response to the use medical insurance card of card swiping device triggering in fixed point medical institution
The request of swiping the card of payment obtains the first biological information and the medical insurance card of the user using the medical insurance card
Identifier；
According to the identifier, holding for the corresponding medical insurance card of the identifier is obtained from social security platform
The second biological information of person；
First biological information is matched with second biological information；
If first biological information and second biological information mismatch, under the card swiping device
Hair is forbidden to use the instruction of the medical insurance card payment, so that the card swiping device can not be buckled from the medical insurance card
Take.
Preferably, first biological information is to be believed using the first face characteristic of the user of the medical insurance card
Breath, second biological information are the second face characteristic information of the holder of the medical insurance card；
First biological information for obtaining the user using the medical insurance card, comprising:
Receive the user comprising using the medical insurance card that image capture device uploads in the fixed point medical institution
The first facial image real time flow medium file；
According to the Face datection model prestored, people is carried out to each frame stream medium data in the real time flow medium file
Face detection, obtains first facial image, and the Face datection model is based on convolutional neural networks algorithm to face sample number
It is obtained according to convolutional neural networks training is carried out；
Model is extracted according to the face characteristic prestored, face characteristic extraction is carried out to first facial image, obtains institute
The first face characteristic information is stated, the face characteristic extracts model and obtains according to the face characteristic training in the face sample data
?；
It is wherein, described to match first biological information with second biological information, comprising:
First face characteristic information is matched with second face characteristic information.
It is preferably, described to match first face characteristic information with second face characteristic information, comprising:
First face characteristic information is matched one by one with second face characteristic information, determines described first
Cosine similarity between face characteristic information and second face characteristic information；
The cosine similarity is compared with preset similarity threshold；
Wherein, if first biological information and second biological information mismatch, Xiang Suoshu
Card swiping device issues the instruction for being forbidden to use the medical insurance card payment, comprising:
If the cosine similarity is less than the similarity threshold, is issued to the card swiping device and be forbidden to use the doctor
Treat the instruction of insurance card payment.
Preferably, before first biological information obtained using the user of the medical insurance card, the side
Method further include:
It constructs the face characteristic and extracts model；
The building face characteristic extracts model, comprising:
Training pattern is constructed according to the face characteristic in the face sample data；
Convolution kernel in the training pattern having a size of 5 × 5 is split as at least two having a size of 3 × 3 convolution kernel；
Based on the convolutional neural networks algorithm, the training pattern is trained, the face characteristic is obtained and extracts
Model.
Preferably, before the face characteristic according in the face sample data constructs training pattern, the method
Further include:
The face sample data is normalized.
Preferably, it is described first biological information is matched with second biological information after,
The method also includes:
If first biological information and second biometric information matches, obtains and protected using the medical treatment
The information of the drug of the user's purchase nearly blocked；
According to the information of the basic medical insurance Drug catalogue and the drug that prestore, judge whether the drug can make
It is bought with the medical insurance card；
If the medical insurance card purchase can be used in the drug, issuing to the card swiping device allows using described
The instruction of medical insurance card payment, so that the card swiping device is deducted fees from the medical insurance card.
Preferably, it if the medical insurance card purchase can be used in the drug, is issued to the card swiping device
Before the instruction for allowing to pay using the medical insurance card, the method also includes:
The corresponding purchase medicine order of drug that the medical insurance card purchase can be used is obtained, is mentioned from the purchase medicine order
Take the price of the drug；
According to the price of the medical insurance drug expense standard and the drug that prestore, judge whether the drug price meets institute
State the regulation of medical insurance drug expense standard；
Wherein, it if the medical insurance card purchase can be used in the drug, is issued to the card swiping device fair
Perhaps the instruction of the medical insurance card is used, comprising:
If the medical insurance card purchase can be used in the drug, and the drug price meets the medical insurance drug expense
With the regulation of standard, then the instruction allowed using the medical insurance card is issued to the card swiping device.
In addition, to achieve the above object, the present invention also proposes a kind of fixed point medical institution based on living things feature recognition
Maintenance device, described device include:
First obtains module, for paying in response to the use medical insurance card of card swiping device triggering in fixed point medical institution
Request of swiping the card, obtain using the medical insurance card user the first biological information and the medical insurance card knowledge
Alias；
Second obtains module, for obtaining the corresponding institute of the identifier from social security platform according to the identifier
State the second biological information of the holder of medical insurance card；
Matching module, for matching first biological information with second biological information；
Sending module is used for when first biological information and second biological information mismatch, to
The card swiping device issues the instruction for being forbidden to use the medical insurance card payment, so that the card swiping device can not be from the doctor
It treats and deducts fees in insurance card.
In addition, to achieve the above object, the present invention also proposes a kind of fixed point medical institution based on living things feature recognition
Monitoring equipment, the equipment include: memory, processor and are stored on the memory and can run on the processor
Based on living things feature recognition fixed point medical institution supervisory process, the fixed point medical institution based on living things feature recognition
Supervisory process be arranged for carrying out it is as described above based on living things feature recognition fixed point medical institution monitoring and managing method step
Suddenly.
In addition, to achieve the above object, the present invention also proposes a kind of storage medium, it is stored with and is based on the storage medium
The supervisory process of the fixed point medical institution of living things feature recognition, the supervision of the fixed point medical institution based on living things feature recognition
The monitoring and managing method of the fixed point medical institution based on living things feature recognition as described above is realized when program is executed by processor
Step.
The supervision scheme of fixed point medical institution provided by the invention based on living things feature recognition, is having user to use medical treatment
When insurance card drug purchase, by the first biological characteristic and the doctor for obtaining the user of currently used medical insurance card drug purchase
The identifier of insurance card is treated, and medical treatment corresponding with current identifier is obtained from social security platform according to the identifier got
Then the second biological information of the real holder of insurance card is believed the first biological information and the second biological characteristic
Breath is matched, could be using the expense of the drug of medical insurance card payment purchase in the two matching, otherwise just Xiang Faqi
Swipe the card request card swiping device issue be forbidden to use the medical insurance card payment instruction so that card swiping device can not be from the medical treatment
It successfully deducts fees in insurance card, so as to effectively avoid medical treatment fixed point medical institution from swipe the card in violation of rules and regulations using supervision loophole.
Detailed description of the invention
Fig. 1 is the fixed point medicine machine based on living things feature recognition for the hardware running environment that the embodiment of the present invention is related to
The structural schematic diagram of the monitoring equipment of structure；
Fig. 2 is that the present invention is based on the processes of the monitoring and managing method first embodiment of the fixed point medical institution of living things feature recognition to show
It is intended to；
Fig. 3 is that the present invention is based on will train in the monitoring and managing method first embodiment of the fixed point medical institution of living things feature recognition
Convolution kernel in model having a size of 5 × 5 be split as two having a size of 3 × 3 convolution kernel schematic diagram；
Fig. 4 is that the present invention is based on will train in the monitoring and managing method first embodiment of the fixed point medical institution of living things feature recognition
Convolution kernel in model having a size of 5 × 5 be split as four having a size of 3 × 3 convolution kernel schematic diagram；
Fig. 5 is that the present invention is based on the processes of the monitoring and managing method second embodiment of the fixed point medical institution of living things feature recognition to show
It is intended to；
Fig. 6 is the structural frames of the maintenance device first embodiment of the fixed point medical institution the present invention is based on living things feature recognition
Figure.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that described herein, specific examples are only used to explain the present invention, is not intended to limit the present invention.
Referring to Fig.1, Fig. 1 is being determined based on living things feature recognition for the hardware running environment that the embodiment of the present invention is related to
The monitoring equipment structural schematic diagram of point medical institution.
As shown in Figure 1, the monitoring equipment for being somebody's turn to do the fixed point medical institution based on living things feature recognition may include: processor
1001, for example, central processing unit (Central Processing Unit, CPU), communication bus 1002, user interface 1003, net
Network interface 1004, memory 1005.Wherein, communication bus 1002 is for realizing the connection communication between these components.User connects
Mouth 1003 may include display screen (Display), input unit such as keyboard (Keyboard), and optional user interface 1003 may be used also
To include standard wireline interface and wireless interface.Network interface 1004 optionally may include the wireline interface of standard, wirelessly connect
Mouth (such as Wireless Fidelity (WIreless-FIdelity, WI-FI) interface).The arbitrary access that memory 1005 can be high speed is deposited
Reservoir (Random Access Memory, RAM) memory, is also possible to stable nonvolatile memory (Non-
Volatile Memory, NVM), such as magnetic disk storage.Memory 1005 optionally can also be independently of aforementioned processor
1001 storage device.
It will be understood by those skilled in the art that structure shown in Fig. 1 is not constituted and is determined based on living things feature recognition
The restriction of the monitoring equipment of point medical institution may include components more more or fewer than diagram, or combine certain components, or
The different component layout of person.
As shown in Figure 1, as may include operating system, data storage mould in a kind of memory 1005 of storage medium
The supervisory process of block, network communication module, Subscriber Interface Module SIM and the fixed point medical institution based on living things feature recognition.
In the monitoring equipment of fixed point medical institution based on living things feature recognition shown in Fig. 1, network interface 1004 is main
The various equipment of medical institution are used for and pinpoint, as card swiping device, image capture device carry out data communication；User interface
1003 are mainly used for carrying out data interaction with user；The present invention is based on the monitoring equipments of the fixed point medical institution of living things feature recognition
In processor 1001, memory 1005 can be set based on living things feature recognition fixed point medical institution monitoring equipment
In, the monitoring equipment of the fixed point medical institution based on living things feature recognition is called in memory 1005 by processor 1001
The supervisory process of the fixed point medical institution based on living things feature recognition of storage, and execute provided in an embodiment of the present invention based on life
The monitoring and managing method of the fixed point medical institution of object feature identification.
The monitoring and managing method for the fixed point medical institution that the embodiment of the invention provides a kind of based on living things feature recognition, referring to figure
2, Fig. 2 be a kind of process signal of the monitoring and managing method first embodiment of the fixed point medical institution based on living things feature recognition of the present invention
Figure.
In the present embodiment, it is described based on living things feature recognition fixed point medical institution monitoring and managing method the following steps are included:
Step S10: fixed point medical institution supervising platform is cured in response to the use of card swiping device triggering in fixed point medical institution
The request of swiping the card of insurance card payment is treated, the first biological information for using the user of the medical insurance card and the doctor are obtained
Treat the identifier of insurance card.
Specifically, in order to guarantee the smooth execution of the monitoring and managing method, the fixed point medical institution supervision provided in this case is flat
Platform needs such as to pinpoint chain pharmacy, fixed point Mono-drugstore, designated medical organization (such as fixed point doctor with each fixed point medical institution in advance
Institute) in various types of card swiping devices, can be the special POS, be also possible to that each of phase account due application program is installed
Kind Intelligent mobile equipment, such as mobile phone, tablet computer and various graph capture devices, place an order for medical staff, issue pharmacy
Terminal device communication connection, so as to carry out the interaction of data and instruction with above equipment.
In addition, fixed point medical institution supervising platform also need with social security platform, i.e., existing management of social insurance center is pre-
First communication connection, what thus be can be convenient knows the information of each insurant.
In addition, above-mentioned the first described biological information, specifically can be face characteristic, fingerprint feature information, iris
Characteristic information, vocal print feature information etc., will not enumerate herein, and any restrictions, those skilled in the art are not also to this
It can according to need the first biological information that setting needs to obtain.
Correspondingly, in the first biological information difference, the equipment of the first biological information of acquisition of selection also can
It is different, for example when the first biological information is face characteristic information, iris feature information, then need to adopt using image
Collect equipment to obtain；When the first biological information is fingerprint feature information, then need to obtain using fingerprint mould group；First
When biological information is vocal print feature information, need to obtain using voice device.
In addition, above-mentioned described medical insurance card, i.e. social medical insurance card, also referred to as medical insurance card.It can be Ji She at present
It protects and medical insurance is in the social security card of one.Correspondingly, above-mentioned identifier is specifically the ID for identifying medical insurance card uniqueness
Or the ID card No. of insured people (Identification) number.
The specific implementation of the first biological information of the user using the medical insurance card is obtained in order to facilitate understanding
Mode is below the first face characteristic information for using the user of the medical insurance card with first biological information,
Second biological information carries out specifically for the second face characteristic information for the holder of the medical insurance card
It is bright.
Specifically, being the first face characteristic using the user of the medical insurance card in first biological information
When information, first biological information for obtaining the user using the medical insurance card, comprising:
(1) use comprising using the medical insurance card that image capture device uploads in the fixed point medical institution is received
The real time flow medium file of first facial image at family.
(2) according to the Face datection model that prestores, to each frame stream medium data in the real time flow medium file into
Row Face datection obtains first facial image.
(3) model is extracted according to the face characteristic prestored, face characteristic extraction is carried out to first facial image, is obtained
First face characteristic information.
It should be noted that in the concrete realization, above-mentioned Face datection model can specifically be calculated based on convolutional neural networks
Method carries out convolutional neural networks training to face sample data and obtains, and face characteristic extracts model then can be according to the face sample
Face characteristic training in notebook data obtains.
About convolutional neural networks, those skilled in the art be could be aware that, in machine learning, before being a kind of depth
Artificial neural network is presented, can accurately identify the information in image.Therefore, by (such as preparatory to face sample data
Downloaded from network, or the facial image of shooting typing) convolutional neural networks training is carried out, so that obtaining one can accurately know
It Chu not Face datection model in image.
In addition, it is noted that in a particular application, the Face datection model of use is specifically to use Caffe (convolution
Neural network framework, Convolutional Architecture for Fast Feature Embedding) it builds, then
It is obtained based on the training of convolutional neural networks algorithm.Since Caffe is a clear, readable high, quick deep learning frame,
Therefore, it is trained based on Caffe and obtains Face datection model, the speed of service can be greatly improved, and instruction can be greatly reduced
Practice the size of resulting Face datection model, so that no matter the resulting Face datection model of training is that real-time target detects mould, i.e.,
Image capture device upload is static images or real time flow medium file, can therefrom be mentioned based on the face detection model
Take out the first facial image of the user using the medical insurance card.
In addition, in order to promote Face datection speed, Face datection model can also be using existing human face data compared with horn of plenty
Face recognition database to real-time quick target detection (YOLO) neural network model carry out convolutional neural networks training obtain.
Further, in order to guarantee that the Face datection model of training acquisition can be more accurate, the liter of YOLO can be used
Grade version YOLOv2 neural network model carries out convolutional neural networks training and obtains.
The training of Face datection model in order to facilitate understanding, is illustrated below:
It writes script and face sample data set is changed into the recognizable format of YOLO, configure three master files of YOLO
Myobj.data (for storing the face sample data for being converted to the recognizable format of YOLO), myobj.name are (every for storing
The corresponding title of a face sample data), myobj.cfg (for storing relevant parameter needed for training process), in YOLO
Then downloading weight file in official website runs order and starts to train, observe the change of avg (average value of each training result) this value
Change, if this value no longer becomes smaller substantially, training can be stopped, and Face datection can be carried out by just obtaining one at this time
Face datection model.
It should be understood that the above is only for example, not constituting restriction to technical solution of the present invention.Actually answering
In, those skilled in the art's computer vision according to known to it, image processing method training obtain the present invention in fact
Neural network model needed for applying mode, herein with no restrictions.
And the building of model is extracted about face characteristic, in this example in order to increase the network depth of training pattern,
The extraction accuracy for enabling the face characteristic trained to extract model greatly improves, and the present embodiment does existing training method
It once improves, specially before being trained, first splits the convolution kernel in training pattern, in order to make it easy to understand,
Operation performed by model construction module is extracted to face characteristic below to be specifically described:
Firstly, constructing training pattern according to the face characteristic in the face sample data.
Specifically, sample data described herein can be the face downloaded in advance from each big data platform using network
Image is also possible to shoot the facial image of simultaneously typing in advance, this will not enumerate, and any restrictions are not also done to this.
Then, the convolution kernel in the training pattern having a size of 5 × 5 is split as at least two having a size of 3 × 3 convolution
Core.
Specific fractionation mode can be as shown in Figure 3 and Figure 4.
Specifically, the alphabetical A in Fig. 3 indicates to be the convolution kernel in training pattern having a size of 5 × 5, and alphabetical A1, A2 are
Four after fractionation having a size of 3 × 3 convolution kernel
Letter b in Fig. 4 indicates to be the convolution kernel in training pattern having a size of 5 × 5, and letter b 1, B2, B3 and B4 are to tear open
Point after four having a size of 3 × 3 convolution kernel.
It should be noted that be given above only two kinds specific fractionation modes, not to the technical solution of the application
Any restriction is constituted, those skilled in the art, which can according to need, to be split, herein with no restrictions.
Finally, being based on the convolutional neural networks algorithm, the training pattern is trained, the face characteristic is obtained
Extract model.
It should be noted that extracting model and a kind of convolutional neural networks mould by face characteristic in this present embodiment
Type, i.e. the face Feature Selection Model are mainly made of convolutional layer, pond layer and full articulamentum, wherein convolutional layer and pond layer
Combination can occur repeatedly, the output layer after full articulamentum is located at pond layer, as entire model.
In addition, face characteristic described in the present embodiment, specifically extracts output layer interior joint in model using face characteristic
Output as face characteristic, which, which can be, is made of each characteristic point of face, such as eyes, nose, the corners of the mouth
The profile point of point, eyebrow and face's other component.
In addition, it is necessary to explanation, in practical applications, full articulamentum can there are two, if full articulamentum is two,
Then output layer is the second full articulamentum, and specific those skilled in the art can according to need setting, herein with no restrictions.
In addition, face characteristic extracts the convergence rate of model it is noted that in order to accelerate in subsequent training process,
And generalization ability (adaptation energy of the machine learning algorithm to fresh sample that face characteristic extracts model is promoted to a certain extent
Power), face characteristic used in present embodiment extracts model, carries out according to the face characteristic training in face sample data
Before training, first face sample data can be normalized, so that the face sample number after normalized
According to, can the scale of each feature control in identical range, to greatly reduce every layer of convolutional layer in training process
Middle convolution kernel and as the number of nodes in the full articulamentum of output layer, in simplifying training process while various calculating,
The face characteristic that building can be promoted extracts the accuracy of model.
Step S20: according to the identifier, the corresponding medical insurance of the identifier is obtained from social security platform
The second biological information of the holder of card.
Specifically, the holder of above-mentioned described medical insurance card specifically refers to the corresponding practical ginseng of the medical insurance card
Guarantor.Therefore, according to the identifier, holding for the corresponding medical insurance card of the identifier is obtained from social security platform
The second biological information for the person of having, as insured people is when handling medical insurance card, face characteristic, the fingerprint characteristic letter of typing
Breath, iris feature information, vocal print feature information etc..
Step S30: first biological information is matched with second biological information.
Still with the first biological information for the first face characteristic information, the second biological information is the second face characteristic
It is for information, then in the concrete realization that first face characteristic information and second face characteristic information progress is matched
Concrete operations approximately as:
Firstly, first face characteristic information is matched one by one with second face characteristic information, institute is determined
State the cosine similarity between the first face characteristic information and second face characteristic information.
Then, the cosine similarity is compared with preset similarity threshold.
It should be noted that being given above only a kind of specific manner of comparison, not to technical solution of the present invention
Any restriction is constituted, in the concrete realization, those skilled in the art, which can according to need, chooses suitable manner of comparison, herein
With no restrictions.
Step S40: if first biological information and second biological information mismatch, to the brush
Card apparatus issues the instruction for being forbidden to use the medical insurance card payment, so that the card swiping device can not be from the medical insurance
It deducts fees in card.
Still with the first biological information for the first face characteristic information, the second biological information is the second face characteristic
For information, then after being matched first face characteristic information with second face characteristic information, if described
Cosine similarity is less than the similarity threshold, then issues to the card swiping device and be forbidden to use the medical insurance card payment
Instruction.
Further, the verification settled accounts in order to facilitate supervision department to medical insurance is executing above-mentioned steps S10 to step S40
Before, it is also necessary to storage record first be carried out to the drug purchased in fixed point medical institution.
Specifically, having purchased drug in fixed point medical institution, and when drug is put in storage, need to carry out the information of each
Typing, and the corresponding quantity of typing, purchase bill, relevant departments' fixing the price etc., the content about typing can be as far as possible
In detail, consequently facilitating the supervision and inquiry in later period.
In addition, in order to provide the user with the preferably medical experience of purchase medicine medicine can be bought using medical insurance card in user
When product, first check whether there are also the medicines of user's selection in medical library using terminal device by the medical staff of designated medical organization
Product, if not provided, quantity then make prompting in time already below a certain threshold value, to recommend it according to the case where user
He suitably substitutes drug.If so, executing above-mentioned steps S10 to step S40 by process then in payment process.
Meanwhile after the completion of this transaction, in order to guarantee subsequent normal use, need to timely update and safeguard the bright of drug
Thin table to record the volume residual of each drug, while recording the outbound time of the medical insurance drug, the medical insurance card of buyer
Card number, the expense paid using medical insurance card etc..
Further, in order to avoid appearance " no doctor's evolution, doctor's evolution not on duty " the problem of, standardized drug avoids
Since prescription is unreasonable, user arbitrarily purchases medical insurance fund caused by medicine and settles accounts unreasonable growth.Pinpoint medical institution supervising platform
The information of the healthcare givers of each designated medical organization can also be obtained in advance, and verifies whether healthcare givers has qualification of practising medicine,
Can with prescription, thus avoid designated medical organization do not have can be with the doctor of prescription when, random prescription.
In addition, when determining that each designated medical organization has the doctor to prescribe, it is not on duty to occur doctor in order to prevent,
The supervision to doctor's time on duty can also be arranged in the random evolution of other staff, such as using various anti-equipment of checking card, so that doctor
Shi Bixu parent checks card, and so as to avoid when doctor is not on duty, other people arbitrarily prescribe.
It should be noted that having the above is only for example, the technical solution to the application does not constitute any restriction
During body is realized, those skilled in the art can according to need setting, herein with no restrictions.
By foregoing description it is not difficult to find that the fixed point medical institution based on living things feature recognition provided in the present embodiment
Monitoring and managing method, when there is user using medical insurance card drug purchase, by obtaining currently used medical insurance card drug purchase
User the first biological characteristic and the medical insurance card identifier, and according to the identifier got from social security platform
The second biological information of the real holder of medical insurance card corresponding with current identifier is obtained, it is then raw by first
Object characteristic information is matched with the second biological information, and medical insurance card payment purchase could be utilized in the two matching
Drug expense, otherwise just to initiation swipe the card request card swiping device issue be forbidden to use the medical insurance card pay finger
It enables, so that card swiping device can not successfully deduct fees from the medical insurance card, so as to effectively avoid medical treatment from pinpointing medical machine
Structure swipe the card in violation of rules and regulations using supervision loophole.
With reference to Fig. 5, Fig. 5 is that a kind of monitoring and managing method second of the fixed point medical institution based on living things feature recognition of the present invention is real
Apply the flow diagram of example.
Based on above-mentioned first embodiment, the monitoring and managing method of fixed point medical institution of the present embodiment based on living things feature recognition exists
After the step S30, further includes:
Step S50: determine that the medical insurance card purchase can be used in the drug, Xiang Suoshu card swiping device issues permission
The instruction paid using the medical insurance card, so that the card swiping device is deducted fees from the medical insurance card.
The realization process of above-mentioned steps S50 in order to facilitate understanding, is specifically described below:
Specifically, if determining first biological information and second biological characteristic by executing step S30
Information matches obtain the information for the drug bought using the user of the medical insurance card first.
It should be noted that the information of drug described herein, can specifically include the title, number, factory of drug
Family, drug classification, project specifications (such as every box how many bag, every bag how many grams etc.) etc., will not enumerate herein, also do not do to this
Any restrictions, those skilled in the art can according to need the content that setting needs to obtain.
Then, according to the information of the basic medical insurance Drug catalogue and the drug that prestore, whether judge the drug
The medical insurance card purchase can be used, if the medical insurance card purchase can be used in the drug, swipe the card to described
Equipment issues the instruction for allowing to pay using the medical insurance card, so that the card swiping device is buckled from the medical insurance card
Take.
It should be understood that above-mentioned described basic medical insurance Drug catalogue specifically directly can select Government Medical to protect
" the national basic medical insurance Drug catalogue " that danger management relevant department formulates, that is, make no modifications, being also adapted to property
Increase the drug of part commercial medical insurance expenditure reimbursement.
Also, it inquires, above-mentioned basic medical insurance Drug catalogue can be stored in the form of table 1 for convenience.
The storage table of 1 basic medical insurance Drug catalogue of table
It should be noted that having the above is only for example, not constituting any restriction to technical solution of the present invention
During body is realized, those skilled in the art can according to need the storage table of building basic medical insurance Drug catalogue, herein not
It is limited.
By foregoing description it is not difficult to find that the fixed point medical institution based on living things feature recognition provided in the present embodiment
Monitoring and managing method, by matching first biological information with second biological information, and described
When one biological information and second biometric information matches, the user's purchase for using the medical insurance card is obtained
The information of drug, and according to the information of the basic medical insurance Drug catalogue and the drug that prestore, to judge that the drug is
It is no that medical insurance card purchase can be used, when determining that medical insurance card purchase can be used in the drug, just to
The card swiping device issues the instruction for allowing to pay using the medical insurance card, so as to further avoid fixed point therapeutic machine
Structure replaces medical insurance drug using non-medical insurance drug, gains medical insurance gold by cheating, not only brings loss to insured people, also result in medical treatment
The unreasonable use of insurance fund.
In addition, it is noted that in the concrete realization, in order to prevent to pinpoint medical institution further for itself benefit
Benefit, the generation for phenomena such as arbitrarily raising medicine valence using supervision loophole, adulterate, is determining that the doctor can be used in the drug
Treating insurance card purchase can also be into before Xiang Suoshu card swiping device issues the instruction for allowing to pay using the medical insurance card
One step obtains the corresponding purchase medicine order of drug that the medical insurance card purchase can be used, and extracts from the purchase medicine order
The price of the drug judges the drug valence then according to the price of the medical insurance drug expense standard and the drug prestored
Whether lattice meet the regulation of the medical insurance drug expense standard, if the medical insurance card purchase can be used in the drug, and
The drug price meets the regulation of the medical insurance drug expense standard, then issuing to the card swiping device allows using the doctor
Treat the instruction of insurance card.In this way, effective supervision to fixed point medical institution may be implemented, so that Medical Benefits Fund
Market order can be ensured, and then preferably ensured insurant interests by reasonable employment.
In addition, the embodiment of the present invention also proposes a kind of storage medium, it is stored on the storage medium based on biological characteristic
The supervisory process of the fixed point medical institution of identification, the supervisory process of the fixed point medical institution based on living things feature recognition are located
The step of managing the monitoring and managing method that the fixed point medical institution based on living things feature recognition as described above is realized when device executes.
It is the maintenance device first embodiment of the fixed point medical institution the present invention is based on living things feature recognition referring to Fig. 6, Fig. 6
Structural block diagram.
As shown in fig. 6, the maintenance device for the fixed point medical institution based on living things feature recognition that the embodiment of the present invention proposes
It include: that the first acquisition module 6001, second obtains module 6002, matching module 6003 and sending module 6004.
Wherein, first module 6001 is obtained, uses medical treatment for what is triggered in response to card swiping device in fixed point medical institution
The request of swiping the card of insurance card payment, obtains the first biological information for using the user of the medical insurance card and the medical treatment
The identifier of insurance card.
Second obtains module 6002, for it is corresponding to obtain the identifier from social security platform according to the identifier
The medical insurance card holder the second biological information.
Matching module 6003 is used for first biological information and second biological information progress
Match.
Sending module 6004, for being mismatched in first biological information and second biological information
When, Xiang Suoshu card swiping device issues the instruction for being forbidden to use medical insurance card payment, so that the card swiping device can not be from
It deducts fees in the medical insurance card.
In addition, it is noted that the first biological characteristic letter that the first acquisition module 6001 is got in the concrete realization
Breath is specifically as follows the first face characteristic information of the user using the medical insurance card, and the second acquisition module 6002 is got
The second biological information be specifically as follows the medical insurance card holder the second face characteristic information.It is thus above-mentioned
It is special that first acquisition module 6001 can specifically be refined as real time flow medium file reception submodule, Face datection submodule and face
Reference ceases extracting sub-module.
Correspondingly, when first biological information is the first face characteristic information, the first acquisition module 6001 is obtained
Take the operation of the first biological information of the user using the medical insurance card specific as follows:
Firstly, receiving what image capture device in the fixed point medical institution uploaded by files in stream media receiving submodule
Real time flow medium file comprising using the first facial image of the user of the medical insurance card；Then, by Face datection
Module carries out face to each frame stream medium data in the real time flow medium file according to the Face datection model prestored
Detection, obtains first facial image；Finally, extracting mould according to the face characteristic prestored by face characteristic extracting sub-module
Type carries out face characteristic extraction to first facial image, obtains first face characteristic information.
Correspondingly, when first biological information is the first face characteristic information, matching module 6003 will be described
First biological information and second biological information carry out matched operation, specifically: first face is special
Reference breath is matched with second face characteristic information.
It should be noted that in the concrete realization, above-mentioned Face datection model can specifically be calculated based on convolutional neural networks
Method carries out convolutional neural networks training to face sample data and obtains, and face characteristic extracts model then can be according to the face sample
Face characteristic training in notebook data obtains.
Further, it is given birth to guarantee that the first acquisition module 6001 obtains the first of the user of the use medical insurance card
The operation of object characteristic information can be gone on smoothly, and need to construct the above-mentioned Face datection model used in advance and face characteristic extracts
Model.It therefore, can also include Face datection model in the maintenance device of the fixed point medical institution based on living things feature recognition
It constructs module and face characteristic extracts model construction module.
About convolutional neural networks, those skilled in the art be could be aware that, in machine learning, before being a kind of depth
Artificial neural network is presented, can accurately identify the information in image.Therefore, by (such as preparatory to face sample data
Downloaded from network, or the facial image of shooting typing) convolutional neural networks training is carried out, so that obtaining one can accurately know
It Chu not Face datection model in image.About its specific training process, those skilled in the art can be by searching for phase
Pass data realizes that details are not described herein again.
The building of model is extracted about face characteristic, the present embodiment has done existing training method and once improved, specifically
First to split the convolution kernel in training pattern before being trained, in order to make it easy to understand, being mentioned below to face characteristic
Operation performed by model construction module is taken to be specifically described:
Firstly, constructing training pattern according to the face characteristic in the face sample data.
Then, the convolution kernel in the training pattern having a size of 5 × 5 is split as at least two having a size of 3 × 3 convolution
Core.
Finally, being based on the convolutional neural networks algorithm, the training pattern is trained, the face characteristic is obtained
Extract model.
It should be noted that be given above only two kinds specific fractionation modes, not to the technical solution of the application
Any restriction is constituted, those skilled in the art, which can according to need, to be split, herein with no restrictions.
In addition, it is certain comparative in order to allow the feature between different dimensions numerically to have, to greatly improve subsequent
The face characteristic that training obtains extracts the accuracy of model, the fixed point medicine machine based on living things feature recognition provided in this example
The maintenance device of structure can also include normalized module, so as to extract model construction module according to institute in face characteristic
Before stating the face characteristic building training pattern in face sample data, by normalized module first to the face sample number
According to being normalized, so that the face sample data after normalized, can control the scale of each feature
In identical range, and then the face characteristic for promoting building extracts the accuracy of model.
By foregoing description it is not difficult to find that in the present embodiment, when there is user using medical insurance card drug purchase, pass through
Obtain the first biological characteristic of the user of currently used medical insurance card drug purchase and the identifier of the medical insurance card, and root
The real holder of medical insurance card corresponding with current identifier is obtained from social security platform according to the identifier got
The second biological information, then the first biological information is matched with the second biological information, in the two
Otherwise timing just could be swiped the card to initiation under the card swiping device of request using the expense of the drug of medical insurance card payment purchase
Hair is forbidden to use the instruction of medical insurance card payment, so that card swiping device can not successfully deduct fees from the medical insurance card, from
And medical treatment fixed point medical institution can effectively be avoided swipe the card in violation of rules and regulations using supervision loophole.
It should be noted that workflow described above is only schematical, not to protection model of the invention
Enclose composition limit, in practical applications, those skilled in the art can select according to the actual needs part therein or
It all achieves the purpose of the solution of this embodiment, herein with no restrictions.
In addition, the not technical detail of detailed description in the present embodiment, reference can be made to provided by any embodiment of the invention
The monitoring and managing method of fixed point medical institution based on living things feature recognition, details are not described herein again.
The first embodiment of maintenance device based on the above-mentioned fixed point medical institution based on living things feature recognition, proposes this hair
The maintenance device second embodiment of the bright fixed point medical institution based on living things feature recognition.
In the present embodiment, the maintenance device of the fixed point medical institution based on living things feature recognition further includes drug letter
Breath obtains module, medical insurance drug judgment module and the second sending module.
Wherein, the medicine information obtains module, for special in first biological information and second biology
When levying information matches, the information for the drug bought using the user of the medical insurance card is obtained.
The medical insurance drug judgment module, for the letter according to the basic medical insurance Drug catalogue and the drug prestored
Breath, judges whether the drug can be used the medical insurance card purchase.
Second sending module, for the drug can be used the medical insurance card purchase when, to the brush
Card apparatus issues the instruction for allowing to pay using the medical insurance card, so that the card swiping device is from the medical insurance card
It deducts fees.
By foregoing description it is not difficult to find that in the present embodiment, by by first biological information and described second
Biological information is matched, and in first biological information and second biometric information matches, is obtained
Take the information for the drug bought using the user of the medical insurance card, and according to the basic medical insurance Drug catalogue that prestores and
The information of the drug is determining that the drug can to judge whether the drug can be used the medical insurance card purchase
When using the medical insurance card to buy, the finger for allowing to pay using the medical insurance card is just issued to the card swiping device
It enables, replaces medical insurance drug so as to further avoid designated medical organization using non-medical insurance drug, gain medical insurance gold by cheating, no
Loss only is brought to insured people, also results in the unreasonable use of Medical Benefits Fund.
In addition, it is noted that in the concrete realization, in order to prevent to pinpoint medical institution further for itself benefit
Benefit, the generation for phenomena such as arbitrarily raising medicine valence using supervision loophole, adulterate, the order medical institution provided in the present embodiment
Maintenance device can also include: medical insurance drug reasonable price judgment module, so as to true in medical insurance drug judgment module
The medical insurance card purchase can be used in the fixed drug, and Xiang Suoshu card swiping device, which issues, to be allowed using the medical insurance card
Before the instruction of payment, is obtained by medical insurance drug reasonable price judgment module and the medical insurance card purchase can be used
The corresponding purchase medicine order of drug, and the price of the drug is extracted from the purchase medicine order, then according to the medical insurance medicine prestored
The price of product expense standard and the drug, judges whether the drug price meets the rule of the medical insurance drug expense standard
It is fixed, the second sending module for allowing the instruction using the medical insurance card is issued to the card swiping device so as to control,
The medical insurance card purchase can be used in the drug, and the drug price meets the medical insurance drug expense standard
When regulation, the instruction allowed using the medical insurance card is just issued to the card swiping device.In this way, it may be implemented
Effective supervision to fixed point medical institution, enables Medical Benefits Fund by reasonable employment, has ensured market order, Jin Ergeng
Good has ensured insurant interests.
It should be noted that workflow described above is only schematical, not to protection model of the invention
Enclose composition limit, in practical applications, those skilled in the art can select according to the actual needs part therein or
It all achieves the purpose of the solution of this embodiment, herein with no restrictions.
In addition, the not technical detail of detailed description in the present embodiment, reference can be made to provided by any embodiment of the invention
The monitoring and managing method of fixed point medical institution based on living things feature recognition, details are not described herein again.
In addition, it should be noted that, herein, the terms "include", "comprise" or its any other variant are intended to contain
Lid non-exclusive inclusion, so that process, method, article or system including a series of elements are not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or system
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or system including the element.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as read-only memory (Read Only Memory, ROM)/RAM, magnetic disk, CD), including some instructions are used so that one
Terminal device (can be mobile phone, computer, server or the network equipment etc.) executes side described in each embodiment of the present invention
Method.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of monitoring and managing method of the fixed point medical institution based on living things feature recognition, which is characterized in that the described method includes:
Fixed point medical institution supervising platform is paid in response to the use medical insurance card of card swiping device triggering in fixed point medical institution
Request of swiping the card, obtain using the medical insurance card user the first biological information and the medical insurance card knowledge
Alias；
According to the identifier, obtain the holder's of the corresponding medical insurance card of the identifier from social security platform
Second biological information；
First biological information is matched with second biological information；
If first biological information and second biological information mismatch, taboo is issued to the card swiping device
The instruction only paid using the medical insurance card, so that the card swiping device can not deduct fees from the medical insurance card.
2. the method as described in claim 1, which is characterized in that first biological information is to use the medical insurance
The first face characteristic information of the user of card, second biological information are the second of the holder of the medical insurance card
Face characteristic information；
First biological information for obtaining the user using the medical insurance card, comprising:
Receive the comprising the user using the medical insurance card that image capture device uploads in the fixed point medical institution
The real time flow medium file of one facial image；
According to the Face datection model prestored, face inspection is carried out to each frame stream medium data in the real time flow medium file
Survey, obtain first facial image, the Face datection model be based on convolutional neural networks algorithm to face sample data into
The training of row convolutional neural networks obtains；
Model is extracted according to the face characteristic that prestores, face characteristic extraction is carried out to first facial image, obtains described the
One face characteristic information, the face characteristic extract model and are obtained according to the face characteristic training in the face sample data；
It is wherein, described to match first biological information with second biological information, comprising:
First face characteristic information is matched with second face characteristic information.
3. method according to claim 2, which is characterized in that described by first face characteristic information and second people
Face characteristic information is matched, comprising:
First face characteristic information is matched one by one with second face characteristic information, determines first face
Cosine similarity between characteristic information and second face characteristic information；
The cosine similarity is compared with preset similarity threshold；
Wherein, it if first biological information and second biological information mismatch, swipes the card to described
Equipment issues the instruction for being forbidden to use the medical insurance card payment, comprising:
If the cosine similarity is less than the similarity threshold, is issued to the card swiping device and be forbidden to use the medical treatment guarantor
The instruction of danger card payment.
4. method as claimed in claim 2 or claim 3, which is characterized in that described to obtain the user's for using the medical insurance card
Before first biological information, the method also includes:
It constructs the face characteristic and extracts model；
The building face characteristic extracts model, comprising:
Training pattern is constructed according to the face characteristic in the face sample data；
Convolution kernel in the training pattern having a size of 5 × 5 is split as at least two having a size of 3 × 3 convolution kernel；
Based on the convolutional neural networks algorithm, the training pattern is trained, the face characteristic is obtained and extracts model.
5. method as claimed in claim 4, which is characterized in that the face characteristic structure according in the face sample data
It builds before training pattern, the method also includes:
The face sample data is normalized.
6. the method as described in claim 1, which is characterized in that described that first biological information is raw with described second
After object characteristic information is matched, the method also includes:
If first biological information and second biometric information matches obtain and use the medical insurance card
User purchase drug information；
According to the information of the basic medical insurance Drug catalogue and the drug that prestore, judge whether the drug can be used institute
State the purchase of medical insurance card；
If the medical insurance card purchase can be used in the drug, issuing to the card swiping device allows using the medical treatment
The instruction of insurance card payment, so that the card swiping device is deducted fees from the medical insurance card.
7. method as claimed in claim 6, which is characterized in that if the medical insurance card purchase can be used in the drug
It buys, then before issuing the instruction for allowing to pay using the medical insurance card to the card swiping device, the method also includes:
The corresponding purchase medicine order of drug that the medical insurance card purchase can be used is obtained, extracts institute from the purchase medicine order
State the price of drug；
According to the price of the medical insurance drug expense standard and the drug that prestore, judge whether the drug price meets the doctor
Protect the regulation of drug expenditure standard；
Wherein, if the medical insurance card purchase can be used in the drug, issuing to the card swiping device allows to make
With the instruction of the medical insurance card, comprising:
If the medical insurance card purchase can be used in the drug, and the drug price meets the medical insurance drug expenditure mark
Quasi- regulation, then issue the instruction allowed using the medical insurance card to the card swiping device.
8. a kind of maintenance device of the fixed point medical institution based on living things feature recognition, which is characterized in that described device includes:
First obtains module, for the brush paid using medical insurance card in response to card swiping device triggering in fixed point medical institution
Card request, obtains the identification of the first biological information and the medical insurance card of the user using the medical insurance card
Number；
Second obtains module, for obtaining the corresponding doctor of the identifier from social security platform according to the identifier
Treat the second biological information of the holder of insurance card；
Matching module, for matching first biological information with second biological information；
Sending module is used for when first biological information and second biological information mismatch, Xiang Suoshu
Card swiping device issues the instruction for being forbidden to use the medical insurance card payment, so that the card swiping device can not be protected from the medical treatment
It deducts fees in the card of danger.
9. a kind of monitoring equipment of the fixed point medical institution based on living things feature recognition, which is characterized in that the equipment includes: to deposit
Reservoir, processor and it is stored in the fixed point based on living things feature recognition that can be run on the memory and on the processor
The supervisory process of medical institution, the supervisory process of the fixed point medical institution based on living things feature recognition are arranged for carrying out such as power
Benefit require any one of 1 to 7 described in based on living things feature recognition fixed point medical institution monitoring and managing method the step of.
10. a kind of storage medium, which is characterized in that be stored with the fixed point medicine based on living things feature recognition on the storage medium
The realization when supervisory process of the supervisory process of mechanism, the fixed point medical institution based on living things feature recognition is executed by processor
The step of monitoring and managing method of fixed point medical institution as described in any one of claim 1 to 7 based on living things feature recognition.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811473507.3A CN109598630A (en) | 2018-12-04 | 2018-12-04 | The monitoring and managing method and relevant device of fixed point medical institution based on living things feature recognition |
| PCT/CN2019/118818 WO2020114221A1 (en) | 2018-12-04 | 2019-11-15 | Biometric recognition-based designated medical institution supervision method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811473507.3A CN109598630A (en) | 2018-12-04 | 2018-12-04 | The monitoring and managing method and relevant device of fixed point medical institution based on living things feature recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109598630A true CN109598630A (en) | 2019-04-09 |
Family
ID=65960944
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811473507.3A Pending CN109598630A (en) | 2018-12-04 | 2018-12-04 | The monitoring and managing method and relevant device of fixed point medical institution based on living things feature recognition |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109598630A (en) |
| WO (1) | WO2020114221A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020114221A1 (en) * | 2018-12-04 | 2020-06-11 | 平安医疗健康管理股份有限公司 | Biometric recognition-based designated medical institution supervision method and related device |
| CN111539833A (en) * | 2020-04-10 | 2020-08-14 | 支付宝(杭州)信息技术有限公司 | Medical expense payment method, device and system |
| CN113159973A (en) * | 2021-02-25 | 2021-07-23 | 华夏方圆信用评估有限公司 | Intelligent medical insurance fund dynamic supervision method and system |
| CN113283894A (en) * | 2021-06-07 | 2021-08-20 | 支付宝(杭州)信息技术有限公司 | Method, device and computer readable medium for payment based on medical insurance electronic certificate |
| CN114037540A (en) * | 2021-11-05 | 2022-02-11 | 湖南创研科技股份有限公司 | Medical insurance fund supervision system and monitoring method thereof |
| CN114037541A (en) * | 2021-11-05 | 2022-02-11 | 湖南创研科技股份有限公司 | Fixed-point medicine institution supervision method based on biological feature recognition and related equipment |
| CN116525060A (en) * | 2023-06-25 | 2023-08-01 | 中南大学 | Intelligent area monitoring method and system based on medical product supervision model |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112925819B (en) * | 2020-12-21 | 2023-05-19 | 上海药慧信息技术有限公司 | Method and device for mining bid-winning information of medicine |
| CN113688784B (en) * | 2021-09-10 | 2024-05-14 | 平安医疗健康管理股份有限公司 | Face recognition-based medical insurance card embezzlement risk recognition method and related equipment thereof |
| CN118333533B (en) * | 2024-06-17 | 2024-08-23 | 南京市医疗保障局 | Recruitment settlement system combined with index rate |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105868977A (en) * | 2016-04-01 | 2016-08-17 | 深圳市至高通信技术发展有限公司 | Drug sale supervision method, system and apparatus |
| CN107920070A (en) * | 2017-11-15 | 2018-04-17 | 中移在线服务有限公司 | Identity identifying method, server and system |
| CN208077174U (en) * | 2017-11-15 | 2018-11-09 | 中移在线服务有限公司 | Identification device for authentication |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108596814A (en) * | 2018-04-20 | 2018-09-28 | 聊城农村商业银行股份有限公司 | Social security Verification System based on recognition of face |
| CN108665559A (en) * | 2018-05-21 | 2018-10-16 | 中兴智能视觉大数据技术（湖北）有限公司 | A kind of testimony of a witness ticket verification management system and method |
| CN108876297A (en) * | 2018-06-14 | 2018-11-23 | 平安健康保险股份有限公司 | For the automatic auditing method of business medical insurance, device, equipment and storage medium |
| CN109598630A (en) * | 2018-12-04 | 2019-04-09 | 平安医疗健康管理股份有限公司 | The monitoring and managing method and relevant device of fixed point medical institution based on living things feature recognition |
-
2018
- 2018-12-04 CN CN201811473507.3A patent/CN109598630A/en active Pending
-
2019
- 2019-11-15 WO PCT/CN2019/118818 patent/WO2020114221A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105868977A (en) * | 2016-04-01 | 2016-08-17 | 深圳市至高通信技术发展有限公司 | Drug sale supervision method, system and apparatus |
| CN107920070A (en) * | 2017-11-15 | 2018-04-17 | 中移在线服务有限公司 | Identity identifying method, server and system |
| CN208077174U (en) * | 2017-11-15 | 2018-11-09 | 中移在线服务有限公司 | Identification device for authentication |
Non-Patent Citations (1)
| Title |
|---|
| 王立峰: ""基于人脸识别的医保监管系统设计与实现"", 《万方数据知识服务平台》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020114221A1 (en) * | 2018-12-04 | 2020-06-11 | 平安医疗健康管理股份有限公司 | Biometric recognition-based designated medical institution supervision method and related device |
| CN111539833A (en) * | 2020-04-10 | 2020-08-14 | 支付宝(杭州)信息技术有限公司 | Medical expense payment method, device and system |
| CN111539833B (en) * | 2020-04-10 | 2023-01-10 | 支付宝(杭州)信息技术有限公司 | Medical expense payment method, device and system |
| CN113159973A (en) * | 2021-02-25 | 2021-07-23 | 华夏方圆信用评估有限公司 | Intelligent medical insurance fund dynamic supervision method and system |
| CN113283894A (en) * | 2021-06-07 | 2021-08-20 | 支付宝(杭州)信息技术有限公司 | Method, device and computer readable medium for payment based on medical insurance electronic certificate |
| CN114037540A (en) * | 2021-11-05 | 2022-02-11 | 湖南创研科技股份有限公司 | Medical insurance fund supervision system and monitoring method thereof |
| CN114037541A (en) * | 2021-11-05 | 2022-02-11 | 湖南创研科技股份有限公司 | Fixed-point medicine institution supervision method based on biological feature recognition and related equipment |
| CN116525060A (en) * | 2023-06-25 | 2023-08-01 | 中南大学 | Intelligent area monitoring method and system based on medical product supervision model |
| CN116525060B (en) * | 2023-06-25 | 2023-10-03 | 中南大学 | Intelligent area monitoring method and system based on medical product supervision model |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020114221A1 (en) | 2020-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109598630A (en) | The monitoring and managing method and relevant device of fixed point medical institution based on living things feature recognition | |
| CN103729764B (en) | Data transferring method and system based on biological characteristic | |
| CN107369011A (en) | The electronic equipment and its operating method of e-payment are provided | |
| CN107657525A (en) | One kind loan measures and procedures for the examination and approval and server | |
| CN109637616A (en) | Medicine distribution method, apparatus, equipment and the storage medium of shared prescription | |
| US20130151267A1 (en) | System to allow for a pharmacist to store a filled prescription in an electronic lockbox for subsequent retrieval by a customer after identity verification | |
| CN108305178A (en) | A kind of insurance kind sale intelligent recommendation method, equipment and storage medium | |
| CN109616176A (en) | Method, apparatus, equipment and the storage medium that auxiliary doctor prescribes | |
| CN112199575A (en) | Virtual bank account opening method, device, equipment and computer storage medium | |
| US20140074638A1 (en) | Consumer self-authorization for electronic records | |
| EP3642776A1 (en) | Facial biometrics card emulation for in-store payment authorization | |
| CN109543444A (en) | A kind of file signature method, apparatus, storage medium and server | |
| CN106104572A (en) | For identifying the system and method that document process and Business Works are integrated | |
| Alzamel et al. | Point of Sale (POS) Network with Embedded Fingerprint Biometric Authentication | |
| CN109426963A (en) | Authenticate the biometric system of biometrics request | |
| CN109615547A (en) | Recognition methods, device, terminal and the computer readable storage medium of abnormal purchase medicine | |
| CN108898438A (en) | Endowment transaction methods, device and computer readable storage medium | |
| US20230107711A1 (en) | Systems and methods for identifying a secondary card user | |
| CN109934723A (en) | A kind of medical insurance fraud recognition methods, device and equipment | |
| CN109255718A (en) | Insurance benefits method and apparatus, computer equipment and readable storage medium storing program for executing | |
| CN107392614A (en) | The implementation method and device of off-line transaction | |
| CN111028909B (en) | Method, device, equipment and storage medium for processing outpatient chronic disease information | |
| CN109523395A (en) | Medical supervision method, apparatus, terminal and medium based on abnormal operation identification | |
| CN108961523A (en) | Hospital register method, device and medical terminal | |
| US20230169473A1 (en) | Medication return platform for extracting value from unused medications |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220526 Address after: 518000 China Aviation Center 2901, No. 1018, Huafu Road, Huahang community, Huaqiang North Street, Futian District, Shenzhen, Guangdong Province Applicant after: Shenzhen Ping An medical and Health Technology Service Co.,Ltd. Address before: Room 12G, Block H, 666 Beijing East Road, Huangpu District, Shanghai 200000 Applicant before: PING AN MEDICAL AND HEALTHCARE MANAGEMENT Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190409 |
|
| RJ01 | Rejection of invention patent application after publication |