CN110223080A - The determination method and device of the target account of brush face payment platform - Google Patents
The determination method and device of the target account of brush face payment platform Download PDFInfo
- Publication number
- CN110223080A CN110223080A CN201910487967.XA CN201910487967A CN110223080A CN 110223080 A CN110223080 A CN 110223080A CN 201910487967 A CN201910487967 A CN 201910487967A CN 110223080 A CN110223080 A CN 110223080A
- Authority
- CN
- China
- Prior art keywords
- account
- face
- target account
- payment platform
- verification
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/42—Confirmation, e.g. check or permission by the legal debtor of payment
-
- 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)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Security & Cryptography (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
This application discloses a kind of determination method and devices of the target account of brush face payment platform, belong to network technique field, this method comprises: obtaining business datum of the brush face payment platform in first time period;According to the business datum, determine that in second time period, the second time period is the period after the first time period when the brush face payment platform is traded without the number threshold value for carrying out the target account of auxiliary verifying;In registered face account, determine that one or more target account, the number of the target account are less than or equal to the number threshold value.Since the application can be not necessarily to carry out the size of the number threshold value of the target account of auxiliary verifying according to the variation dynamic adjustment of business datum in brush face payment platform, and then target account is adjusted, improves the flexibility of brush face payment.
Description
Technical field
The present invention relates to network technique field, in particular to the determination method of a kind of target account of brush face payment platform and
Device.
Background technique
In brush face payment scene, user first can submit human face data to the background authentication server of brush face payment platform
With terminal data (such as cell-phone number) with registered face account.Later, user is when brush face payment platform is consumed, brush face branch
The human face data of the user of acquisition can be sent to background authentication server by the brush face equipment paid in platform.Background authentication service
Device can carry out payment verification to the human face data that brush face equipment is sent based on the human face data in registered face account.
In the related technology, in order to ensure the safety of brush face payment, for each brush face payment platform, technical staff can be with
Human face data progress payment verification can be based only upon by rule of thumb predefining at most only specified number face account.And it is right
In beyond other face accounts other than the specified number face account, then need to carry out face verification based on human face data,
And need to carry out auxiliary verifying based on terminal data, when face verification and auxiliary verifying pass through, it just can determine that payment verification is logical
It crosses.
But for each brush face payment platform, the face account that can be based only upon human face data progress payment verification is
It is rule of thumb determined from registered face account in advance by technical staff, so that the flexibility of brush face payment is poor.
Summary of the invention
The embodiment of the invention provides a kind of determination method and devices of the target account of brush face payment platform, can solve
The poor problem of the flexibility of brush face payment in the related technology.The technical solution is as follows:
In a first aspect, providing a kind of determination method of the target account of brush face payment platform, which comprises
Obtain business datum of the brush face payment platform in first time period;
According to the business datum, determine auxiliary without carrying out when the brush face payment platform is traded in second time period
The number threshold value of the target account of verifying is helped, the second time period is the period after the first time period;
In registered face account, determine one or more target accounts, the number of the target account be less than or
Equal to the number threshold value.
Optionally, the business datum includes one of following data or a variety of: face verification number, face verification at
Power and air control triggering times;
Wherein, the number threshold value and the face verification number are positively correlated, and are positively correlated with the face verification success rate,
It is negatively correlated with the air control triggering times.
Optionally, described according to the business datum, it determines and trades in second time period in the brush face payment platform
Shi Wuxu carries out the number threshold value of the target account of auxiliary verifying, comprising:
The first weight coefficient is determined according to the business datum;
The product of first weight coefficient and benchmark number is determined as number threshold value;
Wherein, first weight coefficient and the face verification number are positively correlated, just with the face verification success rate
Correlation, it is negatively correlated with the air control triggering times.
It is optionally, described that first weight coefficient is determined according to the business datum, comprising:
Determine the first ratio of the face verification number and benchmark verifying number;
Determine the second ratio of the face verification success rate Yu benchmark success rate;
Determine the third ratio of the air control triggering times Yu benchmark triggering times;
By first ratio, second ratio and the third ratio weighted sum, the first weight coefficient is obtained.
Optionally, described in registered face account, determine one or more target account, comprising:
According to the verifying that the first account is triggered when the brush face payment platform is traded in the registered face account
Request carries out payment verification to first account, and the payment verification includes face verification and auxiliary verifying;
If first account is verified and meets first condition, first account is determined as target account, institute
Stating first condition includes one of following conditions or a variety of;
The first of the human face data carried in the checking request and the human face data registered in first account is similar
Degree is greater than similarity threshold;
Air control triggering times during the payment verification are less than the first frequency threshold value;
The difference that first similarity subtracts the second similarity is greater than difference threshold, and second similarity is described the
The similarity for the human face data registered in the human face data registered in one account, with the fixed target account.
Optionally, after determining one or more target accounts, the method also includes:
The target account is obtained within the third period in the transaction data of the brush face payment platform;
The reliability score value of the target account is determined based on the transaction data;
If the reliability score value is less than point threshold, prompting message, institute are sent to the terminal for logging in the target account
It states prompting message and updates the human face data registered in the target account for prompting;
Wherein, the transaction data includes one of following data or a variety of: the target account passes through face verification
Complete first number of payment verification, the target account passes through face verification and assists second of verifying completion payment verification
Number, when completing payment verification by face verification every time, the human face data that is carried in the checking request that the target account triggers
With the third similarity for the human face data registered in the target account;
The reliability score value is positively correlated with described first time number, negatively correlated with described second time number, with the third phase
Variation degree like degree is negatively correlated.
Optionally, the reliability score value that the target account is determined based on the transaction data, comprising:
Determine that first number subtracts described second time several number difference;
Similarity slope and confidence level are determined according to the first time several third similarities;
Determine the product of the similarity slope, the confidence level and the second weight coefficient;
The sum of the product and the number difference are determined as reliability score value.
Optionally, after determining the target account in registered face account, if the fixed target account
Number number be greater than the number threshold value, the method also includes:
The minimum target account of reliability score value in the fixed target account is determined as non-targeted account.
Optionally, after determining one or more target accounts, the method also includes:
If the second account in one or more target accounts meets second condition, second account is determined as non-mesh
Marking second condition described in account includes one of following conditions or a variety of:
The verifying that the terminal of second account is triggered when the brush face payment platform is traded within the 4th period is asked
The number asked is less than the second frequency threshold value;
It receives and logs in the request for nullifying face account that the terminal of second account is sent;
The air control triggering times of second account are greater than third frequency threshold value.
On the other hand, a kind of determining device of the target account of brush face payment platform is provided, described device includes:
Module is obtained, for obtaining business datum of the brush face payment platform in first time period;
First determining module, it is flat in brush face payment in second time period for determining according to the business datum
Platform trade when without carry out auxiliary verifying target account number threshold value, the second time period be the first time period it
Period afterwards;
Second determining module, in registered face account, determining one or more target account, the target
The number of account is less than or equal to the number threshold value.
Optionally, the business datum includes one of following data or a variety of: face verification number, face verification at
Power and air control triggering times;
Wherein, the number threshold value and the face verification number are positively correlated, and are positively correlated with the face verification success rate,
It is negatively correlated with the air control triggering times.
Optionally, first determining module, comprising:
First determines submodule, for determining the first weight coefficient according to the business datum;
Second determines submodule, for the product of first weight coefficient and benchmark number to be determined as number threshold value;
Wherein, first weight coefficient and the face verification number are positively correlated, just with the face verification success rate
Correlation, it is negatively correlated with the air control triggering times.
Optionally, it described first determines submodule, is used for:
Determine the first ratio of the face verification number and benchmark verifying number;
Determine the second ratio of the face verification success rate Yu benchmark success rate;
Determine the third ratio of the air control triggering times Yu benchmark triggering times;
By first ratio, second ratio and the third ratio weighted sum, the first weight coefficient is obtained.
Optionally, second determining module, is used for:
According to the verifying that the first account is triggered when the brush face payment platform is traded in the registered face account
Request carries out payment verification to first account, and the payment verification includes face verification and auxiliary verifying;
If first account is verified and meets first condition, first account is determined as target account, institute
Stating first condition includes one of following conditions or a variety of;
The first of the human face data carried in the checking request and the human face data registered in first account is similar
Degree is greater than similarity threshold;
Air control triggering times during the payment verification are less than the first frequency threshold value;
The difference that first similarity subtracts the second similarity is greater than difference threshold, and second similarity is described the
The similarity for the human face data registered in the human face data registered in one account, with the fixed target account.
Optionally, the acquisition module is also used to after determining one or more target accounts, obtains the target account
In the transaction data of the brush face payment platform number within the third period;
Described device further include:
Third determining module, for determining the reliability score value of the target account based on the transaction data;
Sending module, if being less than point threshold for the reliability score value, to the terminal hair for logging in the target account
Prompting message is sent, the prompting message is used to prompt to update the human face data registered in the target account;
Wherein, the transaction data includes one of following data or a variety of: the target account passes through face verification
Complete first number of payment verification, the target account passes through face verification and assists second of verifying completion payment verification
Number, when completing payment verification by face verification every time, the human face data that is carried in the checking request that the target account triggers
With the third similarity for the human face data registered in the target account;
The reliability score value is positively correlated with described first time number, negatively correlated with described second time number, with the third phase
Variation degree like degree is negatively correlated.
Optionally, the third determining module, is used for:
Determine that first number subtracts described second time several number difference;
Similarity slope and confidence level are determined according to the first time several third similarities;
Determine the product of the similarity slope, the confidence level and the second weight coefficient;
The sum of the product and the number difference are determined as reliability score value.
Optionally, second determining module, be also used to determine in registered face account the target account it
It afterwards, will be reliable in the fixed target account if the number of the fixed target account is greater than the number threshold value
The minimum target account of degree score value is determined as non-targeted account.
Optionally, second determining module is also used to after determining one or more target accounts, if one or more
The second account in a target account is unsatisfactory for second condition, and second account is determined as Article 2 described in non-targeted account
Part includes one of following conditions or a variety of:
The verifying that the terminal of second account is triggered when the brush face payment platform is traded within the 4th period is asked
The number asked is greater than the second frequency threshold value;
Second account is not nullified;
The air control triggering times of second account are less than third frequency threshold value.
Another aspect provides a kind of target account of brush face payment platform locking equipment really, comprising: memory, processing
Device and the computer program being stored on the memory, the processor realize above-mentioned aspect when executing the computer program
The determination method of the target account of the brush face payment platform.
In another aspect, providing a kind of computer readable storage medium, it is stored in the computer readable storage medium
Instruction, when the computer readable storage medium is run on computers, so that computer is executed as described in terms of above-mentioned
The determination method of the target account of brush face payment platform.
Technical solution bring beneficial effect provided in an embodiment of the present invention includes at least:
The embodiment of the invention provides a kind of determination method and device of the target account of brush face payment platform, the target accounts
Number determination method can according to business datum of the brush face payment platform in first time period, determine in second time period
Without carrying out the number threshold value of the target account of auxiliary verifying when the brush face payment platform is traded, and from registered face account
Middle determining target account.Due to that can be tested according to the variation dynamic adjustment of business datum in brush face payment platform without carrying out auxiliary
The size of the number threshold value of the target account of card, and then target account is adjusted, compared to needing technical staff's root in the related technology
According to empirically determined target account, the method increase the flexibilities of brush face payment.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is real involved in a kind of determination method of the target account of brush face payment platform provided in an embodiment of the present invention
Apply the schematic diagram of environment;
Fig. 2 is a kind of flow chart of the determination method of the target account of brush face payment platform provided in an embodiment of the present invention;
Fig. 3 is the process of the determination method of the target account of another brush face payment platform provided in an embodiment of the present invention
Figure;
Fig. 4 is a kind of flow chart of the method for the first weight coefficient of determination provided in an embodiment of the present invention;
Fig. 5 is the process of the method for the human face data registered in a kind of more fresh target account provided in an embodiment of the present invention
Figure;
Fig. 6 is a kind of flow chart of the method for determining reliability score value provided in an embodiment of the present invention;
Fig. 7 is a kind of block diagram of the determining device of the target account of brush face payment platform provided in an embodiment of the present invention;
Fig. 8 is a kind of block diagram of first determining module provided in an embodiment of the present invention;
Fig. 9 is the block diagram of the determining device of the target account of another brush face payment platform provided in an embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention
Formula is described in further detail.
Fig. 1 is real involved in a kind of determination method of the target account of brush face payment platform provided in an embodiment of the present invention
Apply the schematic diagram of environment.As shown in Figure 1, the implementation environment may include: server 110 and one or more terminals 120.The clothes
Business device 110 can be a server, or the server cluster consisted of several servers or a cloud computing clothes
Business center.The terminal 120 can be provided with the brush face equipment of camera for PC, laptop, tablet computer etc..It should
Connection can be established by cable network or wireless network between server 110 and the one or more terminal 120.
In embodiments of the present invention, which can be the background authentication clothes of one or more brush face payment platforms
Business device.The embodiment of the present invention is illustrated so that the server 110 is the background authentication server of multiple brush face payment platforms as an example.
Each brush face payment platform can be solid door shop or network shops (being referred to as on-line shop).If the brush face
Payment platform is entity shops, and one or more terminals 120 can be set in the entity shops.It can be in each terminal 120
It is provided with camera, and the human face data of user can be acquired by the camera, later by the human face data of the user of acquisition
It is sent to server 110, so that server 110 sent terminal 120 based on the human face data in registered face account
Human face data carries out payment verification.Wherein, which can be the facial image of the user of camera shooting.
If the brush face payment platform is network shops, terminal 120 can be terminal used by a user, the terminal 120
On be provided with camera.For user when being paid by terminal 120, terminal 120 can acquire user's by the camera
Human face data, and the human face data of the user of acquisition is sent to server 110, so that server 110 is based on registered people
Human face data in face account carries out payment verification to the human face data that terminal 120 is sent.
Fig. 2 is a kind of flow chart of the determination method of the target account of brush face payment platform provided in an embodiment of the present invention.
This method can be applied in server 110 shown in FIG. 1.As shown in Fig. 2, this method may include:
Step 201 obtains business datum of the brush face payment platform in first time period.
In embodiments of the present invention, server can obtain brush face payment platform first after receiving detection instruction
Business datum in period.Alternatively, server can obtain brush face payment platform at the first time every a detection cycle
Business datum in section.The first time period can be current time before the first specified duration period, alternatively, this
What one period was also possible to be indicated by the detection instruction.Wherein, which, which can be in server, presets
Fixation duration, such as can be 24 hours.Alternatively, the first specified duration can also be indicated by the detection instruction.
The business datum of the brush face payment platform can be to carry out payment verification in the server of the brush face payment platform
When the related data that generates.Exemplary, which may include one of following data or a variety of: face verification time
Number, face verification success rate and air control triggering times.
Step 202, according to business datum, determine auxiliary without carrying out when brush face payment platform is traded in second time period
Help the number threshold value of the target account of verifying.
Wherein, which is the period after first time period.The first time period and the second time period
Duration may be the same or different, it is not limited in the embodiment of the present invention.Optionally, which, which verifies, may include
One of fingerprint authentication, password authentification and terminal authentication are a variety of.Wherein, the terminal authentication may include cell-phone number verifying or
Person's identifying code verifying etc..
Step 203, in registered face account, determine one or more target accounts, the number of the target account
Less than or equal to number threshold value.
In embodiments of the present invention, it can be previously stored with multiple registered face accounts in server, determining nothing
After the number threshold value that need to carry out the target account of auxiliary verifying, server can determine one in registered face account
A or multiple target accounts.The subsequent one or more target account, can only base when the brush face payment platform is traded
Payment verification is carried out in human face data, without carrying out auxiliary verifying.
In conclusion the embodiment of the invention provides a kind of determination method of the target account of brush face payment platform, the mesh
The determination method for marking account can be determined according to business datum of the brush face payment platform in first time period in second time period
Without carrying out the number threshold value of the target account of auxiliary verifying when inherent brush face payment platform transaction, and from registered face
Target account is determined in account.It is auxiliary due to that can be not necessarily to carry out according to the variation dynamic adjustment of business datum in brush face payment platform
It helps the size of the number threshold value of the target account of verifying, and then adjusts target account, compared to needing technology people in the related technology
The empirically determined target account of member, the method increase the flexibilities of brush face payment.
Fig. 3 is the process of the determination method of the target account of another brush face payment platform provided in an embodiment of the present invention
Figure.This method can be applied in server 110 shown in FIG. 1.As shown in figure 3, this method may include:
Step 301 obtains business datum of the brush face payment platform in first time period.
In embodiments of the present invention, server can obtain brush face payment platform first after receiving detection instruction
Business datum in period.Alternatively, server can obtain brush face payment platform at the first time every a detection cycle
Business datum in section.The first time period can be current time before the first specified duration period, alternatively, this
What one period was also possible to be indicated by the detection instruction.Wherein, which, which can be in server, presets
Fixation duration, such as can be 24 hours.Alternatively, the first specified duration can also be indicated by the detection instruction.
In the present invention is implemented, when brush face payment platform is traded, the terminal of brush face payment platform collects user
After the human face data of user, the checking request for carrying human face data can be sent, to server to carry out payment verification.
In above-mentioned business datum, face verification number can refer to that server receives terminal transmission in first time period
Multiple checking requests in effective checking request number.In embodiments of the present invention, if server is calculated based on recognition of face
Method determines that the corresponding facial image of the human face data carried in checking request is clear and has portrait, then can determine the checking request
For effective checking request.If server determines the corresponding face of the human face data carried in checking request based on face recognition algorithms
There are multiple people in fogging image or the facial image, then the checking request can be determined for invalid authentication request.
The face is proved to be successful the ratio that rate refers to recognition of face number of success Yu face verification number, the recognition of face
Number of success refers to: server is received in first time period in effective checking request, the number that face verification passes through.
Optionally, multiple registered human face datas are previously stored in server, server is receiving terminal transmission
The checking request for carrying human face data after, the human face data and multiple registered human face datas can be carried out respectively
Match, if being greater than first threshold with the collected human face data similarity of terminal there are one in multiple registered human face datas
Human face data can then determine that face verification passes through.Exemplary, which can be 80%.
The air control triggering times can refer to the terminal of the brush face payment platform in the first time period internal trigger server
Carry out the number of risk control (such as preventing transaction).In embodiments of the present invention, server is receiving testing for terminal transmission
After card request, the corresponding face account of the human face data carried in the available checking request, and then obtain the face account
In the transaction data of any brush face payment platform.If server judges that the face account is full according to the human face data and transaction data
Foot states one of condition or a variety of, then can trigger risk control: face account single in brush face payment platform is handed over
Easy number is greater than limit;The face account is greater than maximum number of times in the number of the checking request of scheduled duration internal trigger, i.e., should
There is the behavior that repeatedly brush is single in face account;In registered human face data, it is greater than first with the similarity of the human face data
The number of threshold value is greater than the number upper limit.
It is exemplary, it is assumed that the number upper limit be 3, if server by the corresponding human face data of face account with it is registered
Human face data matching after, it is corresponding with the face account there are four registered human face data in registered human face data
The similarity of human face data be greater than first threshold, then can determine the safety of the corresponding human face data of face account compared with
Low, server can send the prompting message of air control authentication failed to terminal.
It should be noted that server can be counted in the brush face payment platform in first time period based on air control algorithm
Air control triggering times and each air control trigger the reason of.
Step 302 determines the first weight coefficient according to business datum.
Server can determine the first weight coefficient after obtaining business datum according to the business datum, if the business
Data include face verification number, face verification success rate and air control triggering times, as shown in figure 4, the step 302 can wrap
It includes:
Step 3021, the first ratio for determining face verification number and benchmark verifying number.
The benchmark, which verifies number, to be pre-stored fixed value in server.For example, benchmark verifying number can be with
For the average value for the face verification number that multiple brush face payment platforms actually trigger in reference period.The reference period can
Think any time period before first time period.
Exemplary, server can determine that a secondary standard verifies number every other month, and benchmark verifying number can be
Average value of multiple brush face payment platforms in the interior face verification number actually triggered in the month before.
Step 3022, the second ratio for determining face verification success rate Yu benchmark success rate.
The face, which is proved to be successful rate, to be the face verification success of multiple brush face payment platform in reference period
The mean value of rate.
Step 3023, the third ratio for determining air control triggering times Yu benchmark triggering times.
The benchmark triggering times can be the equal of air control triggering times of multiple brush face payment platforms in reference period
Value.
Step 3024, by the first ratio, the second ratio and third ratio weighted sum, obtain the first weight coefficient.
The corresponding first weight w1 of the first ratio, corresponding second weight of the second ratio can be previously stored in server
The w2 and corresponding third weight w3 of third ratio.Server, can after determining the first ratio, the second ratio and third ratio
To be based on first weight w1, the second weight w2 and third weight w3 to first ratio, second ratio and the third
Ratio weighted sum, and then obtain the first weight coefficient.First weight coefficient V can satisfy:
Wherein, x2 is face verification number, verifies number on the basis of x1;Y2 is that face is proved to be successful rate, on the basis of y1 at
Power;Z2 is air control triggering times, and z1 is benchmark triggering times.With reference to above-mentioned formula as can be seen that first weight coefficient with
Face verification number is positively correlated, and is positively correlated with face verification success rate, negatively correlated with air control triggering times.
Optionally, the initial ratio of first weight w1, the second weight w2 and third weight w3 can satisfy w1:w2:w3
=1:2:7.With the demand of the business development of the upgrading and brush face payment platform of face recognition algorithms, server can also be real-time
Update the ratio of first weight w1, the second weight w2 and third weight w3.For example, server can be based on brush face payment platform
The turnover of daily face verification number and the payment of brush face determines the weight letter for being used to measure out a weight quality
Number k=f (w1, w2, w3), so according to weighting function k be the first weight w1, the second weight w2 and third weight w3 determine compared with
Excellent weight ratio.
For example, if to brush face payment safety it is more demanding, specific gravity shared by third weight w3 can be improved.If
Specific gravity shared by the first weight w1 then can be improved in the portfolio that the brush face payment platform need to be improved.In addition, server can also be with
Constantly update benchmark verifying number, benchmark success rate and benchmark triggering times.
The product of first weight coefficient and benchmark number is determined as number threshold value by step 303.
The number threshold value can in second time period after the first period of time in the transaction of brush face payment platform without
It need to carry out the threshold value of the target account of auxiliary verifying.The first time period can be identical with the duration of the second time period, can also
With difference, it is not limited in the embodiment of the present invention.
Optionally, benchmark number N can be previously stored in server, after determining the first weight coefficient V, server
The product of the first weight coefficient V He benchmark number N can be calculated, and the product is determined as number threshold value.The number threshold
Value can satisfy: N × V.Wherein, which it is rule of thumb preset to can be technical staff.It is exemplary, the benchmark
Number can be 500.
It can be seen that the number threshold value finally determined and face verification in conjunction with the formula of above-mentioned first weight coefficient V
Number is positively correlated, and is positively correlated with face verification success rate, negatively correlated with air control triggering times.
In embodiments of the present invention, which can be identical with the duration of the second time period.For example, server
It can be passed through every the duration of first time period according to business datum of the brush face payment platform in a upper first time period
Above-mentioned steps 301 and step 303 are executed, determines the number threshold value in next first time period (i.e. second time period).
Exemplary, the duration of the first time period and second time period all can be 24 hours.Then server can be every
0 point of business datum based on the previous day of its morning calculates the same day in the transaction of brush face payment platform without carrying out auxiliary verifying
The number threshold value of target account.
In embodiments of the present invention, server can be according to the difference of business datum, using above-mentioned step in server
Rapid 301 and step 303 dynamically adjust the size of number threshold value, and then improve the flexibility that number threshold value determines, while improving brush
The safety and stability of face payment, it is ensured that the effective development of business in brush face payment platform.Since target account is in brush face branch
Without carrying out auxiliary verifying during paying, and then the operation of user is simplified, improves payment efficiency.
Server can determine after through the above steps 301 to 303 determine number threshold value in registered face account
The number threshold value target account.Method with continued reference to Fig. 3, the determination target account may include:
Step 304, the verifying triggered according to the first account in registered face account when brush face payment platform is traded
Request carries out payment verification to the first account.
Wherein, which can be the checking request that first account triggers for the first time in the brush face payment platform.It is right
In the checking request of the triggering, server needs both to carry out face verification when carrying out payment verification to first account, also into
Row auxiliary verifying.When face verification and auxiliary verifying pass through, it just can determine that payment verification passes through.The auxiliary is verified
One of fingerprint authentication, password authentification and terminal authentication are a variety of.Wherein, the terminal authentication may include cell-phone number verifying or
Person's identifying code verifying etc..
In brush face payment scene, each user first can submit human face data and terminal data (such as hand to server
Machine number) with registered face account, which is used for the human face data and terminal data of unique identification user.Server can be with
According to the face account, the human face data of submission and terminal data of each user's registration, the face of each registration is stored in advance
Corresponding relationship between account human face data corresponding with the face account of each registration and terminal data.
Terminal in brush face payment platform can send verifying to server and ask after collecting the human face data of user
It asks, the human face data of the collected user of terminal is carried in the checking request.Server is in the verifying for receiving terminal transmission
After request, the human face data which acquires can be matched with multiple registered human face datas, and by it is multiple
The registered human face data for being greater than first threshold with the human face data similarity of terminal acquisition in the human face data of registration is true
It is set to target human face data, if the number of the target human face data is one, can determines that face verification passes through.Basis later
The target human face data, from the face account of the pre-stored registration and corresponding human face data of the face account of registration and terminal
The corresponding face account of the target human face data is determined in corresponding relationship between data, and the face account is determined as first
Account.
Later, server can send the reminder message that face is verified to terminal.Terminal disappears receiving the prompting
After breath, display terminal data input screen.The terminal data that the user received inputs is sent to server later.Service
Device verifies the terminal data received based on the terminal data registered in first account, if registered in the first account
Terminal data is identical as the terminal data received, then confirms that auxiliary is verified.It is possible thereby to determine face verification and auxiliary
Verifying passes through, then server, which can determine, passes through the first account payment verification.
If step 305, the first account are verified and meet first condition, the first account is determined as target account.
Wherein, which may include one of following conditions or a variety of:
(1) the first similarity of the human face data carried in the checking request and the human face data registered in the first account is big
In similarity threshold.For example, the similarity threshold can be 70%.
If the first similarity of the human face data carried in checking request and the human face data registered in the first account is greater than
Similarity threshold then shows that the human face data reliability carried in the checking request is higher.
(2) the air control triggering times during payment verification are less than the first frequency threshold value.The air control triggering times refer to touching
Send out the number that server carries out risk control.If the air control triggering times less than the first frequency threshold value, show first account
The number that trigger the server carries out risk control is less, and the safety of first account is higher.
The difference that (3) first similarities subtract the second similarity is greater than difference threshold, which can be first
The similarity for the human face data registered in the human face data registered in account, with fixed target account.The difference threshold can
Think 30%.
If the difference that first similarity subtracts the second similarity is greater than difference threshold, show to register in first account
Human face data, it is lower with the similarity of registered human face data in fixed target account, i.e., in first account
The accuracy of the human face data of registration is higher.
If the number of fixed target account is one, the face number that server can will be registered in first account
According to being determined as the second similarity with the similarity for the human face data registered in this fixed target account.If having determined that
Target account number be it is multiple, then server can calculate the human face data registered in first account, with it is each really
The similarity for the human face data registered in fixed target account obtains multiple similarities, and most by numerical value in multiple similarity
High similarity is determined as the second similarity.
Exemplary, if fixed target account has 3, server can calculate the face number registered in the first account
According to the similarity with the human face data registered in this 3 fixed target accounts, 3 similarities are obtained, later by 3 phases
It is determined as the second similarity like the highest similarity of numerical value in degree.
In embodiments of the present invention, which may include all conditions in above three condition, that is to say, clothes
Business device is detecting the first account satisfaction: (when sim1 > s1) && (sim1-sim2) > s2&&f1 < f2, it can be by first account
It is determined as target account.Wherein, sim1 is the first similarity, and s1 is similarity threshold, and sim2 is the second similarity, and s2 is difference
Threshold value.F1 is air control triggering times, and f2 is the first frequency threshold value.
It should be noted that for different brush face payment platforms, which be may be the same or different.
And the difference threshold may be the same or different.It is not limited in the embodiment of the present invention.
For each for the first time in the first account of brush face payment platform transaction, server is both needed to carry out face verification to it
It is verified with auxiliary, after determining that the first account meets above-mentioned first condition, which is determined as target account, with this
Analogize, until determining number threshold value target account.
Fig. 5 is the method flow diagram for the human face data registered in a kind of more fresh target account provided in an embodiment of the present invention.
As shown in figure 5, after above-mentioned steps 305, this method can also include:
Step 306 obtains target account within the third period in the transaction data of brush face payment platform.
Server after determining one or more target accounts, available either objective account within the third period
The transaction data of brush face payment platform, the transaction data may include one of following data or a variety of:
(1) the target account completes first number of payment verification by face verification.I.e. the target account is in third
Between only pass through the number that face verification completes payment verification in brush face payment platform in section.
In embodiments of the present invention, the third period is when second after determining one or more target accounts is specified
The long period.Wherein, which can be preset fixed duration in server, such as this is second specified
Duration can be 1 month.
(2) the target account completes second number of payment verification by face verification and auxiliary verifying.That is the target account
Complete the number of payment verification number within the third period by face verification and auxiliary verifying in brush face payment platform.
(3) when by face verification completing payment verification every time, the people that carries in the checking request which triggers
The third similarity for the human face data registered in face data and the target account.In brush face payment platform i.e. within the third period
Every time only by face verification complete payment verification when, server can determine the target account trigger checking request in carry
Human face data and target account in the third similarity of human face data registered, and then it is similar to obtain several thirds for the first time
Degree.
It is exemplary, if the target account only completes payment by face verification in brush face payment platform within the third period
First number of verifying can be 10 times, then 10 third similarities can be calculated in server.
Step 307, the reliability score value that target account is determined based on transaction data.
In embodiments of the present invention, if the transaction data includes first time number, second number and first time several thirds
Similarity, then the reliability score value and first number are positively correlated, negatively correlated with second number, the variation degree with third similarity
It is negatively correlated.Optionally, as shown in fig. 6, the step 307 may include:
Step 3071 determines that first number subtracts second several number difference.
The number difference can be n1-n2, wherein n1 is first number, and n2 is second number.
Step 3072 determines similarity slope and confidence level according to several third similarities for the first time.
Server can determine fitting a straight line according to the first time several third similarities by the way of linear fit,
And then obtain similarity slope and confidence level.
Wherein, which, which reflects, carries in the checking request that within the third period target account triggers
Human face data, compared to the variation degree for the human face data registered in the target account.The numerical value of the similarity slope is smaller, table
The variation for the human face data registered in the human face data and the target account carried in the checking request of bright target account triggering
It is smaller.The confidence level reflects the reliability of the similarity slope, which shows this is calculated similar closer to 1
The reliability for spending slope is higher.
Wherein, confidence level r meets:Wherein, n refers to the third got
The number of similarity, yiRefer to i-th of third similarity, xiRefer to getting the time point of i-th of third similarity,I.e.Refer to the mean value at n time point,Refer to the mean value of n third similarity.
Step 3073, the product for determining similarity slope, confidence level and the second weight coefficient.
Server can be previously stored with the second weight coefficient, which can be the weight factor greater than 0.
The sum of product and number difference are determined as reliability score value by step 3074.
The reliability score value sc meets: (n1-n2)+w4 × sl × r, wherein and n1 is first number, and n2 is second number,
Sl is similarity slope, and r is confidence level, and w4 is the second weight coefficient.Under normal conditions, which is negative value.Root
It can be seen that the reliability score value according to the formula of above-mentioned reliability score value and first number be positively correlated, it is negatively correlated with second number,
It is negatively correlated with the variation degree of third similarity.
If step 308, reliability score value are less than point threshold, the terminal of Xiang Denglu target account sends prompting message.
It can be previously stored with point threshold in server, after determining reliability score value, can detecte the reliability
Whether score value is less than point threshold, if the reliability score value of the target account is less than point threshold, illustrates in the target account
The reliability of the human face data of registration is lower, therefore server can send prompting message to the terminal for logging in the target account,
The prompting message is used to prompt to update the human face data registered in the target account.
It should be noted that server is obtaining target account within the third period in the number of deals of brush face payment platform
According to later, the reliability score value of the target account can be calculated by executing above-mentioned steps 307.Alternatively, server can also be with
Reliability score value is determined according to the human face data detection model constructed in advance.
Optionally, server can obtain people based on the training of a large amount of first sample data by the way of machine learning
Face Data Detection model.Therefore, server is getting target account within the third period in the transaction of brush face payment platform
After data, which can be directly inputted in human face data detection model, and by the face Data Detection model
The result of output is determined as reliability score value.
Wherein, which may include that first sample number, the second sample number, similarity sample are oblique
Rate, sample confidence level and the 4th weight.In embodiments of the present invention, reliability point is determined by human face data detection model
Value, the transaction data that need to only will acquire input the face Data Detection model, reliability score value can be obtained, improve determination
The efficiency of reliability score value.
In embodiments of the present invention, after server determines one or more target account in registered face account,
Fixed target account will can be updated, update mode at least may include following two kinds:
As a kind of optional implementation, after one or more target account is determined in registered face account,
If the number of fixed target account is greater than number threshold value, server can be by reliability in fixed target account point
It is worth minimum target account and is determined as non-targeted account, i.e., deletes the target account from fixed target account.
It is exemplary, if number threshold value is 10, after executing the step 305, if server defines 11 target accounts
Number, then the minimum target account of reliability score value in fixed 11 target accounts can be determined as non-targeted by server
Account.That is to say, server can the target account deleted from fixed 11 target accounts, and then only retain 10 mesh
Mark account.
As another optional implementation, if the second account in the one or more target account is unsatisfactory for second
Condition, then second account can be determined as non-targeted account by server, i.e., by second account from determining one or
It is deleted in multiple target accounts.The second condition may include one of following conditions or a variety of:
(1) checking request that the terminal of second account is triggered when brush face payment platform is traded within the 4th period
Number is greater than the second frequency threshold value.
In embodiments of the present invention, which can be pre-stored fixed numbers in server.This
Four periods can specify the period in duration for the third after determining one or more target accounts.The third is specified
Duration can be preset fixed duration in server, such as it can be 1 month or 3 months that the third, which specifies duration, should
Second frequency threshold value can be 0 or 1.
If the checking request that the terminal of second account is triggered when brush face payment platform is traded within the 4th period
Number is not more than the second frequency threshold value, then shows that second account is lower in the trading frequency of brush face payment platform.
(2) second accounts are not nullified.
In embodiments of the present invention, the terminal for logging in the second account can be user terminal.It can be installed in user terminal
The application program for having brush face to pay, the interface of the application program are provided with the button for nullifying face account, and user terminal is receiving
After being directed to the triggering command of the button of the cancellation face account to user, is sent to server and nullify face account request.If clothes
Business device does not receive user terminal and sends cancellation face account request, then can determine that the second account is not nullified.If server connects
It receives user terminal and sends cancellation face account request, then can determine that the second account is nullified.
(3) the air control triggering times of second account are less than third frequency threshold value.I.e. second account is in any one brush face
The number that air control triggers in payment platform is less than third frequency threshold value.The third frequency threshold value can be pre-stored for server
Fixed numbers, exemplary, which can be 4.
If the air control triggering times of the second account be less than third frequency threshold value, show the second account trigger the server into
The number of row risk control is less, and the safety of second account is higher.
In embodiments of the present invention, which may include all conditions in above three condition, that is to say, clothes
Business device is detecting that the second account is unsatisfactory for: (t1 > t2) && (when fla) && (r1 < r2), the second account can be determined as non-
Target account.Wherein, t1 tests for what the terminal of second account within the 4th period was triggered when brush face payment platform is traded
The number of request is demonstrate,proved, t2 is the second frequency threshold value.When fla is true (true), indicate not receive the user for logging in the second account
The request for the cancellation face account that terminal is sent.R1 is the air control triggering times of the second account, and r2 is third frequency threshold value.
Second account can be determined as non-targeted by server when determining that the second account is unsatisfactory for above-mentioned second condition
Account deletes second account from fixed one or more target accounts.
In embodiments of the present invention, server gets business datum of the brush face payment platform in first time period every time
Later, number threshold value can be determined by executing above-mentioned steps 301 and step 303.Alternatively, server can also be according to preparatory
The number threshold value of building determines model to be determined as number threshold value.
Exemplary, server can be obtained a by the way of machine learning based on the training of a large amount of second sample data
Number threshold value determines model.Therefore, server, can after getting business datum of the brush face payment platform in first time period
It is determined in model so that the business datum is inputted the number threshold value, and the number threshold value is determined that the output result of model is determined as
Number threshold value.
Wherein, each second sample data may include face verification time numerical example, face verification success rate sample and wind
Control triggering times sample.
In embodiments of the present invention, server can refer to during training number threshold value determines model every second
Section of fixing time collects the business datum of multiple brush face payment platforms, and the business datum being collected into is stored to sample database.
Server can be based on the sample data training pattern in the sample database.For example, server can collect multiple brushes daily
Second sample data of face payment platform, and daily 23: 50 based on the second sample data training mould in sample database
Type.When the second sample data that server is collected into reaches specified quantity, server can carry out sample using big data frame
The acquisition and analysis of notebook data, so that obtaining number threshold value determines model.
It should be noted that the determination method and step of the target account for the brush face payment platform that the embodiment of the present disclosure provides
Sequencing can carry out appropriate adjustment, for example, step 306 to step 308 can executing the step 301 to after step 305
To execute, can not also execute.Anyone skilled in the art, can be light in the technical scope that the disclosure discloses
The method for being readily conceivable that variation should all cover within the protection scope of the disclosure, therefore repeat no more.
In conclusion the embodiment of the invention provides a kind of determination method of the target account of brush face payment platform, the mesh
The determination method for marking account can be determined according to business datum of the brush face payment platform in first time period in second time period
Without carrying out the number threshold value of the target account of auxiliary verifying when inherent brush face payment platform transaction, and from registered face
Target account is determined in account.It is auxiliary due to that can be not necessarily to carry out according to the variation dynamic adjustment of business datum in brush face payment platform
It helps the size of the number threshold value of the target account of verifying, and then adjusts target account, compared to needing technology people in the related technology
The empirically determined target account of member, the method increase the flexibilities of brush face payment.
Fig. 7 is a kind of block diagram of the determining device 70 of the target account of brush face payment platform provided in an embodiment of the present invention.
As shown in fig. 7, the apparatus may include: obtain module 701, the first determining module 702 and the second determining module 703.
Module 701 is obtained, for obtaining business datum of the brush face payment platform in first time period.
First determining module 702 is traded in second time period in brush face payment platform for determining according to business datum
Shi Wuxu carries out the number threshold value of the target account of auxiliary verifying, and second time period is the period after first time period.
Second determining module 703, in registered face account, determining one or more target account, target
The number of account is less than or equal to number threshold value.
In conclusion the embodiment of the invention provides a kind of determining device of the target account of brush face payment platform, first
Obtaining module can determine according to business datum of the brush face payment platform of module acquisition in first time period is obtained second
In brush face payment platform transaction without carrying out the number threshold value of the target account of auxiliary verifying in period, second really later
Cover half block determines target account from registered face account.Due to can be according to the change of business datum in brush face payment platform
Change the size of the number threshold value of target account of the dynamic adjustment without carrying out auxiliary verifying, and then adjusts target account, compared to
The empirically determined target account of technical staff is needed in the related technology, and the method increase the flexibilities of brush face payment.
Optionally, business datum includes one of following data or a variety of: face verification number, face verification success rate
And air control triggering times;
Wherein, number threshold value and face verification number are positively correlated, and are positively correlated with face verification success rate, with air control triggering time
Number is negatively correlated.
Optionally, as shown in figure 8, the first determining module 702, comprising:
First determines submodule 7021, for determining the first weight coefficient according to business datum;
Second determines submodule 7022, for the product of the first weight coefficient and benchmark number to be determined as number threshold value;
Wherein, the first weight coefficient and face verification number are positively correlated, and are positively correlated with face verification success rate, are touched with air control
It is negatively correlated to send out number.
Optionally, it first determines submodule 7021, is used for:
Determine the first ratio of face verification number and benchmark verifying number;
Determine the second ratio of face verification success rate Yu benchmark success rate;
Determine the third ratio of air control triggering times Yu benchmark triggering times;
By the first ratio, the second ratio and third ratio weighted sum, the first weight coefficient is obtained.
Optionally, the second determining module 703, is used for:
According to the first account in registered face account when brush face payment platform is traded the checking request that triggers, to the
One account carries out payment verification, and payment verification includes face verification and auxiliary verifying;
If the first account is verified and meets first condition, the first account is determined as target account, first condition packet
Include one of following conditions or a variety of;
First similarity of the human face data carried in checking request and the human face data registered in the first account is greater than phase
Like degree threshold value;
Air control triggering times during payment verification are less than the first frequency threshold value;
The difference that first similarity subtracts the second similarity is greater than difference threshold, and the second similarity is to register in the first account
Human face data, the similarity with the human face data registered in fixed target account.
Optionally, module is obtained, is also used to after determining one or more target accounts, obtains target account in third
In the transaction data of brush face payment platform in period;
As shown in figure 9, the device further include:
Third determining module 704, for determining the reliability score value of target account based on transaction data;
Sending module 705, if being less than point threshold for reliability score value, the terminal of Xiang Denglu target account sends prompt
Message, prompting message are used for the human face data for prompting to register in more fresh target account;
Wherein, transaction data includes one of following data or a variety of: target account is completed to pay by face verification
First number of verifying, target account are verified by face verification and auxiliary to be completed second number of payment verification, passes through every time
When face verification completes payment verification, registered in the human face data and target account that carry in the checking request of target account triggering
Human face data third similarity;
Reliability score value and first number are positively correlated, negatively correlated with second number, negative with the variation degree of third similarity
It is related.
Optionally, third determining module 704, is used for:
Determine that first number subtracts second several number difference;
Similarity slope and confidence level are determined according to several third similarities for the first time;
Determine the product of similarity slope, confidence level and the second weight coefficient;
The sum of product and number difference are determined as reliability score value.
Optionally, the second determining module 703, after being also used to determine target account in registered face account, if
The number of fixed target account is greater than number threshold value, by the target account that reliability score value in fixed target account is minimum
Number it is determined as non-targeted account.
Optionally, the second determining module 703 is also used to after determining one or more target accounts, if one or more
The second account in a target account is unsatisfactory for second condition, and the second account is determined as under non-targeted account second condition includes
State one of condition or a variety of:
The number for the checking request that the terminal of the second account is triggered when brush face payment platform is traded within the 4th period
Greater than the second frequency threshold value;
Second account is not nullified;
The air control triggering times of second account are less than third frequency threshold value.
In conclusion the embodiment of the invention provides a kind of determining device of the target account of brush face payment platform, first
Obtaining module can determine according to business datum of the brush face payment platform of module acquisition in first time period is obtained second
In brush face payment platform transaction without carrying out the number threshold value of the target account of auxiliary verifying in period, second really later
Cover half block determines target account from registered face account.Due to can be according to the change of business datum in brush face payment platform
Change the size of the number threshold value of target account of the dynamic adjustment without carrying out auxiliary verifying, and then adjusts target account, compared to
The empirically determined target account of technical staff is needed in the related technology, and the method increase the flexibilities of brush face payment.
The embodiment of the invention provides a kind of target account of brush face payment platform locking equipments really, comprising: memory, place
The computer program of device and storage on a memory is managed, processor realizes Fig. 2 or brush face shown in Fig. 3 when executing computer program
The determination method of the target account of payment platform.Wherein, locking equipment can be clothes to the target account of the brush face payment platform really
Business device.
The embodiment of the invention provides a kind of computer readable storage medium, it is stored in the computer readable storage medium
Instruction, when computer readable storage medium is run on computers, so that computer executes brush face as shown in Figure 2 or Figure 3
The determination method of the target account of payment platform.
The foregoing is merely alternative embodiments of the invention, are not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (12)
1. a kind of determination method of the target account of brush face payment platform, which is characterized in that the described method includes:
Obtain business datum of the brush face payment platform in first time period;
According to the business datum, determines and tested when the brush face payment platform is traded without carrying out auxiliary in second time period
The number threshold value of the target account of card, the second time period are the period after the first time period;
In registered face account, determine that one or more target account, the number of the target account are less than or equal to
The number threshold value.
2. the method according to claim 1, wherein the business datum includes one of following data or more
Kind: face verification number, face verification success rate and air control triggering times;
Wherein, the number threshold value and the face verification number are positively correlated, and are positively correlated with the face verification success rate, with institute
It is negatively correlated to state air control triggering times.
3. according to the method described in claim 2, determination is in the second time it is characterized in that, described according to the business datum
Section in the brush face payment platform transaction when without carry out auxiliary verifying target account number threshold value, comprising:
The first weight coefficient is determined according to the business datum;
The product of first weight coefficient and benchmark number is determined as number threshold value;
Wherein, first weight coefficient and the face verification number are positively correlated, and are positively correlated with the face verification success rate,
It is negatively correlated with the air control triggering times.
4. according to the method described in claim 3, it is characterized in that, described determine the first weight system according to the business datum
Number, comprising:
Determine the first ratio of the face verification number and benchmark verifying number;
Determine the second ratio of the face verification success rate Yu benchmark success rate;
Determine the third ratio of the air control triggering times Yu benchmark triggering times;
By first ratio, second ratio and the third ratio weighted sum, the first weight coefficient is obtained.
5. method according to any one of claims 1 to 4, which is characterized in that it is described in registered face account, it determines
One or more target accounts, comprising:
According to the checking request that the first account is triggered when the brush face payment platform is traded in the registered face account,
Payment verification is carried out to first account, the payment verification includes face verification and auxiliary verifying;
If first account is verified and meets first condition, first account is determined as target account, described
One condition includes one of following conditions or a variety of;
First similarity of the human face data carried in the checking request and the human face data registered in first account is big
In similarity threshold;
Air control triggering times during the payment verification are less than the first frequency threshold value;
The difference that first similarity subtracts the second similarity is greater than difference threshold, and second similarity is first account
The similarity for the human face data registered in the human face data registered in number, with the fixed target account.
6. method according to any one of claims 1 to 4, which is characterized in that after determining one or more target accounts,
The method also includes:
The target account is obtained within the third period in the transaction data of the brush face payment platform;
The reliability score value of the target account is determined based on the transaction data;
If the reliability score value is less than point threshold, prompting message is sent to the terminal for logging in the target account, it is described to mention
Show that message updates the human face data registered in the target account for prompting;
Wherein, the transaction data includes one of following data or a variety of: the target account is completed by face verification
First number of payment verification, the target account by face verification and auxiliary verifying complete payment verification second number,
The human face data carried in the checking request of the target account triggering when completing payment verification by face verification every time and institute
State the third similarity for the human face data registered in target account;
The reliability score value is positively correlated with described first time number, negatively correlated with described second time number, with the third similarity
Variation degree it is negatively correlated.
7. according to the method described in claim 6, it is characterized in that, described determine the target account based on the transaction data
Reliability score value, comprising:
Determine that first number subtracts described second time several number difference;
Similarity slope and confidence level are determined according to the first time several third similarities;
Determine the product of the similarity slope, the confidence level and the second weight coefficient;
The sum of the product and the number difference are determined as reliability score value.
8. according to the method described in claim 6, it is characterized in that, determining the target account in registered face account
Later, if the number of the fixed target account is greater than the number threshold value, the method also includes:
The minimum target account of reliability score value in the fixed target account is determined as non-targeted account.
9. method according to any one of claims 1 to 4, which is characterized in that after determining one or more target accounts,
The method also includes:
If the second account in one or more target accounts is unsatisfactory for second condition, second account is determined as non-targeted
Account, the second condition include one of following conditions or a variety of:
The checking request that the terminal of second account is triggered when the brush face payment platform is traded within the 4th period
Number is greater than the second frequency threshold value;
Second account is not nullified;
The air control triggering times of second account are less than third frequency threshold value.
10. a kind of determining device of the target account of brush face payment platform, which is characterized in that described device includes:
Module is obtained, for obtaining business datum of the brush face payment platform in first time period;
First determining module is handed in second time period in the brush face payment platform for determining according to the business datum
Easily when without carry out auxiliary verifying target account number threshold value, the second time period be the first time period after
Period;
Second determining module, in registered face account, determining one or more target account, the target account
Number be less than or equal to the number threshold value.
11. a kind of target account of brush face payment platform locking equipment really characterized by comprising memory and is deposited processor
The computer program on the memory is stored up, the processor realizes such as claim 1 to 9 when executing the computer program
The determination method of the target account of any brush face payment platform.
12. a kind of computer readable storage medium, which is characterized in that instruction is stored in the computer readable storage medium,
When the computer readable storage medium is run on computers, so that computer is executed as described in claim 1 to 9 is any
Brush face payment platform target account determination method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910487967.XA CN110223080A (en) | 2019-06-05 | 2019-06-05 | The determination method and device of the target account of brush face payment platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910487967.XA CN110223080A (en) | 2019-06-05 | 2019-06-05 | The determination method and device of the target account of brush face payment platform |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110223080A true CN110223080A (en) | 2019-09-10 |
Family
ID=67819472
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910487967.XA Pending CN110223080A (en) | 2019-06-05 | 2019-06-05 | The determination method and device of the target account of brush face payment platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110223080A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111382410A (en) * | 2020-03-23 | 2020-07-07 | 支付宝(杭州)信息技术有限公司 | Face brushing verification method and system |
CN113140083A (en) * | 2020-01-18 | 2021-07-20 | 四川回银网络科技有限公司 | Face-brushing payment cashier system |
-
2019
- 2019-06-05 CN CN201910487967.XA patent/CN110223080A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113140083A (en) * | 2020-01-18 | 2021-07-20 | 四川回银网络科技有限公司 | Face-brushing payment cashier system |
CN111382410A (en) * | 2020-03-23 | 2020-07-07 | 支付宝(杭州)信息技术有限公司 | Face brushing verification method and system |
CN111382410B (en) * | 2020-03-23 | 2022-04-29 | 支付宝(杭州)信息技术有限公司 | Face brushing verification method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021000577A1 (en) | Method and apparatus for face-swiping payment | |
US7434063B2 (en) | Authentication method, apparatus, and system | |
CN107103218B (en) | Service implementation method and device | |
JP6961003B2 (en) | Biological feature database establishment method and equipment | |
CN109816521A (en) | A kind of banking processing method, apparatus and system | |
CN109977765A (en) | Facial image recognition method, device and computer equipment | |
CN110276892A (en) | Self-service method, apparatus, equipment and storage medium | |
CN110428555A (en) | Shared charging equipment gives back method and device | |
US11818126B2 (en) | Using common identifiers related to location to link fraud across mobile devices | |
WO2015062290A1 (en) | Methods and systems for authentications and online transactions | |
CN110991249A (en) | Face detection method, face detection device, electronic equipment and medium | |
CN110135850A (en) | A kind of information processing method and relevant apparatus | |
CN110223080A (en) | The determination method and device of the target account of brush face payment platform | |
CN109145590A (en) | A kind of function hook detection method, detection device and computer-readable medium | |
CN107688940A (en) | Bio-identification transaction processing method and system | |
CN112801670A (en) | Risk assessment method and device for payment operation | |
CN108243154A (en) | A kind of identifying code data processing method and device | |
CN110555692A (en) | virtual resource transfer method, device and storage medium | |
CN108694663A (en) | A kind of credit methods, apparatus and system | |
CN115640074A (en) | Service data processing method and device and intelligent counter terminal | |
CN105631673A (en) | Cloud payment method, payment terminal, cloud payment platform and cloud payment system | |
CN114004639A (en) | Preferential information recommendation method and device, computer equipment and storage medium | |
CN109785107B (en) | Method for flexibly configuring fund duty ratio and related products | |
CN112581249A (en) | Credit score management system and method based on credit commitment and fulfillment | |
CN115906028A (en) | User identity verification method and device and self-service terminal |
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 |