CN110400138A

CN110400138A - The method of mobile payment and device of illegal

Info

Publication number: CN110400138A
Application number: CN201910694659.4A
Authority: CN
Inventors: 李志勇; 王卓成; 漆英; 彭灿
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2019-07-30
Filing date: 2019-07-30
Publication date: 2019-11-01

Abstract

The method of mobile payment and device of illegal provided by the invention, this method comprises: being obtained according to the payment code payment request of consumer and showing payment code；Payment scene image is acquired according to the payment code payment request；It whether identifies in the payment scene image comprising payment code scanner；Mobile payment process is controlled according to recognition result, wherein, pass through the front camera of the mobile terminal using consumer, when consumer shows payment code to trade company, open simultaneously front camera, payment scene is imaged, utilize image recognition algorithm, it recognizes in payment scene image after the payment code scanner comprising trade company, it just can be carried out payment code payment, to effectively improve the safety and compliance of payment, guarantee consumers' rights and interests, the mobile payment environment of maintaining healthy, while supporting rapid payment.

Description

The method of mobile payment and device of illegal

Technical field

The present invention relates to mobile payment technical field more particularly to the method for mobile payment and device of a kind of illegal.

Background technique

With quick universal, the mobile payment means of the fast development and intelligent movable equipment of IT technology and e-commerce It rises extensively at home.

It also leads to the problem of thereupon: for example, consumer can point out payment code queuing etc. in advance in trade company's gathering Wait payment, in order to achieve the purpose that quickly to collect money, small amount payment do not need consumer test it is close, criminal utilize this feature, When consumer is lined up, the camera shooting sweeping consumer's two dimensional code or utilizing above consumer is stolen behind consumer by mobile terminal Head takes the photograph the two dimensional code of consumer steathily, completes to steal brush, causes consumer's monetary losses.

Summary of the invention

For the problems of the prior art, the present invention provides the method for mobile payment, device, electronic equipment of a kind of illegal And computer readable storage medium, problems of the prior art can at least be partially solved.

To achieve the goals above, the present invention adopts the following technical scheme:

In a first aspect, providing a kind of method of mobile payment of illegal, comprising:

It is obtained according to the payment code payment request of consumer and shows payment code；

Payment scene image is acquired according to the payment code payment request；

It whether identifies in the payment scene image comprising payment code scanner；

Mobile payment process is controlled according to recognition result.

Further, this controls mobile payment process according to recognition result, comprising:

If in the payment scene image including payment code scanner, allow to carry out mobile payment using the payment code；

If not including payment code scanner in the payment scene image, whether forbid utilizing the payment to consumer's push Code carries out the message of mobile payment, according to the feedback control mobile payment process of consumer.

It further, whether include payment code scanner in the identification payment scene image, comprising:

It whether is identified in the payment scene image using the convolutional neural networks model of pre-training comprising payment code scanner.

Further, which includes:

Input layer, for receiving input picture；

Convolutional layer, for extracting the feature of the input picture；

Sample level, it is down-sampled for being carried out to this feature；

Full articulamentum is in the tag characterization input picture for being classified to obtain label to the feature after down-sampled No includes payment code scanner.

Further, the method for mobile payment of illegal further include:

Construct convolutional neural networks model；

The convolutional neural networks model is trained to obtain the convolution of the pre-training using the image pattern of known label Neural network model.

Further, which is trained to obtain this pre- to the convolutional neural networks model Trained convolutional neural networks model, comprising:

The image pattern of known label is inputted into the convolutional neural networks model, and is tied the output of the model as training Fruit；

The corresponding training result of each image pattern is compared with its known label；

The parameter that convolutional neural networks model is adjusted according to comparison result, obtains the convolutional neural networks mould of the pre-training Type.

Further, the method for mobile payment of illegal further include:

Obtain the test sample of known label；

The convolutional neural networks mould of the pre-training is tested using the test sample of the known label, and by the model Output as test result；

Based on the test result and known label, judge whether the convolutional neural networks mould of pre-training meets preset requirement；

If so, using "current" model as the object module of payment code scanner for identification；

If it is not, then being optimized to "current" model and/or re-starting model training using updated training sample set.

Further, the method for mobile payment of illegal further include:

Current location is obtained according to the payment code payment request；

Identify the bar code in the payment scene image on payment code scanner, to obtain Merchants register information, the trade company Registration information includes: Merchants register address；

Judge whether the current location and the Merchants register address are consistent；

If it is not, then generating warning information.

Further, trade company's essential information further include: name of firm, trade company's working group；

The method of mobile payment of the illegal further include:

After paying successfully, the name of firm, trade company's working group are pushed to consumer and is checked for consumer.

Further, which includes: two dimensional code and/or bar code.

Second aspect provides a kind of mobile payment device of illegal, comprising:

Payment code generation module obtains according to the payment code payment request of consumer and shows payment code；

Scene image acquisition module is paid, payment scene image is acquired according to the payment code payment request；

Whether payment code scanner recognition module identifies in the payment scene image comprising payment code scanner；

Mobile payment control module controls mobile payment process according to recognition result.

Further, which includes:

Mobile payment unit, if in the payment scene image include payment code scanner, allow using the payment code into Row mobile payment；

Mobile payment confirmation unit pushes if not including payment code scanner in the payment scene image to consumer Whether the message that using the payment code carries out mobile payment is forbidden, according to the feedback control mobile payment process of consumer.

Further, which includes:

Model recognition unit, using the convolutional neural networks model of pre-training identify in the payment scene image whether include Payment code scanner.

Further, which includes:

Input layer, for receiving input picture；

Convolutional layer, for extracting the feature of the input picture；

Sample level, it is down-sampled for being carried out to this feature；

Further, the mobile payment device of illegal further include:

Model construction module constructs convolutional neural networks model；

Model training module is trained this to the convolutional neural networks model using the image pattern of known label The convolutional neural networks model of pre-training.

Further, which includes:

The image pattern of known label is inputted the convolutional neural networks model by training sample input unit, and by the mould The output of type is as training result；

The corresponding training result of each image pattern is compared by as a result comparing unit with its known label；

Parameter adjustment unit adjusts the parameter of convolutional neural networks model according to comparison result, obtains the volume of the pre-training Product neural network model.

Further, the mobile payment device of illegal further include:

Test sample obtains module, obtains the test sample of known label；

Model measurement module surveys the convolutional neural networks mould of the pre-training using the test sample of the known label Examination, and using the output of the model as test result；

Test judgment module, be based on the test result and known label, judge pre-training convolutional neural networks mould whether Meet preset requirement；

Model release module, if the convolutional neural networks mould of pre-training meets preset requirement, using "current" model as use In the object module of identification payment code scanner；

Model adjusts module, if the convolutional neural networks mould of pre-training does not meet preset requirement, carries out to "current" model Optimize and/or re-starts model training using updated training sample set.

Further, the mobile payment device of illegal further include:

Locating module obtains current location according to the payment code payment request；

Bar code recognition module identifies the bar code in the payment scene image on payment code scanner, to obtain trade company Registration information, the Merchants register information include: Merchants register address；

Address judgment module judges whether the current location and the Merchants register address are consistent；

Alarm module generates warning information if the current location and the Merchants register address are inconsistent.

The mobile payment device of the illegal further include:

Order information pushing module after paying successfully, pushes the name of firm, trade company's working group for disappearing to consumer The person's of expense verification.

Further, which includes: two dimensional code and/or bar code.

The third aspect, provides a kind of electronic equipment, including memory, processor and storage on a memory and can handled The computer program run on device, the processor realize the step of the method for mobile payment of above-mentioned illegal when executing the program Suddenly.

Fourth aspect provides a kind of computer readable storage medium, is stored thereon with computer program, the computer program The step of method of mobile payment of above-mentioned illegal is realized when being executed by processor.

Method of mobile payment, device, electronic equipment and the computer readable storage medium of illegal provided by the invention, This method comprises: being obtained according to the payment code payment request of consumer and showing payment code；It is adopted according to the payment code payment request Collection payment scene image；It whether identifies in the payment scene image comprising payment code scanner；It is controlled and is moved according to recognition result Payment flow, wherein by using consumer mobile terminal front camera, when consumer to trade company show payment code, Front camera is opened simultaneously, payment scene is imaged, using image recognition algorithm, recognizes and is wrapped in payment scene image After payment code scanner containing trade company, payment code payment just can be carried out, to effectively improve the safety and compliance of payment, protect Consumers' rights and interests, the mobile payment environment of maintaining healthy are demonstrate,proved, while supporting rapid payment.

For above and other objects, features and advantages of the invention can be clearer and more comprehensible, preferred embodiment is cited below particularly, And cooperate institute's accompanying drawings, it is described in detail below.

Detailed description of the invention

In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the application Some embodiments for those of ordinary skill in the art without creative efforts, can also basis These attached drawings obtain other attached drawings.In the accompanying drawings:

Fig. 1 shows a kind of scene of method of mobile payment using illegal provided in an embodiment of the present invention；

Fig. 2 is the flow diagram one of the method for mobile payment of the illegal in the embodiment of the present invention；

Fig. 3 shows the structure of the convolutional neural networks model used in the embodiment of the present invention；

Fig. 4 is the flow diagram two of the method for mobile payment of the illegal in the embodiment of the present invention；

Fig. 5 is the flow diagram three of the method for mobile payment of the illegal in the embodiment of the present invention；

Fig. 6 shows the sectional view that the scanner scanning lens in the embodiment of the present invention goes out；

Fig. 7 shows the system architecture of the method for mobile payment using illegal provided in an embodiment of the present invention；

Fig. 8 is the structural block diagram of the mobile payment device of the illegal in the embodiment of the present invention；

Fig. 9 is the structure chart of electronic equipment of the embodiment of the present invention.

Specific embodiment

In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only The embodiment of the application a part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people Member's every other embodiment obtained without making creative work, all should belong to the model of the application protection It encloses.

Although this application provides the method operating procedure as described in embodiment or flow chart, based on conventional or noninvasive The labour for the property made may include more or less operating procedure.The step of enumerating in embodiment sequence is only numerous steps One of execution sequence mode, does not represent and unique executes sequence.When device or consumer end product in practice executes, Can be executed according to embodiment or the execution of method shown in the drawings sequence or parallel (such as parallel processor or multithreading The environment of processing).

It should be noted that term " includes " and " tool in the description and claims of this application and above-mentioned attached drawing Have " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing a series of steps or units Process, method, system, product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include without clear Other step or units listing to Chu or intrinsic for these process, methods, product or equipment.

It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

Currently, consumer can point out payment code in advance and wait in line to pay, fast in order to reach when carrying out payment code payment Speed gathering purpose, small amount payment do not need consumer test it is close, criminal utilize this feature, consumer be lined up when, lead to It crosses mobile terminal and steals the camera sweeping consumer's two dimensional code or utilizing above consumer behind consumer, take the photograph the two of consumer steathily Code is tieed up, completes to steal brush, causes consumer's monetary losses.

At least partly to solve above-mentioned technical problem in the prior art, the embodiment of the present invention provides a kind of shifting of illegal Dynamic method of payment, by the front camera of the mobile terminal using consumer, when consumer shows payment code to trade company, simultaneously Front camera is opened, payment scene is imaged, using image recognition algorithm, is recognized in payment scene image comprising quotient After the payment code scanner at family, payment code payment just can be carried out, to effectively improve the safety and compliance of payment.

Fig. 1 shows a kind of scene of method of mobile payment using illegal provided in an embodiment of the present invention.Such as Fig. 1 institute Show, the mobile terminal 01 of consumer can be smart phone or tablet computer etc., which connects for interacting with consumer The payment code payment request of consumer's triggering is received, which is showing payment code 03 (such as two dimensional code, bar code etc.) When, while starting front camera 04, when trade company holds payment code scanner 02 (such as two-dimensional code scanning rifle) scanning payment code When 03, payment code scanner 02 is in the imaging area 05 of 01 front camera 04 of mobile terminal naturally, at this point, front camera 04 captures one or more payment scene image, using the payment code scanner in image recognition algorithm identification image, works as identification When to payment code scanner, success can be paid.

It will be appreciated by persons skilled in the art that generating payment code according to payment code payment request, triggering camera is opened Open, image recognition and etc. can be executed in the mobile terminal side of consumer, can also execute in the server.

When above-mentioned steps are when mobile terminal side executes, mobile terminal receives consumption by processing routine prefabricated in it The payment code payment request of person's triggering, when showing payment code 03 (such as two dimensional code, bar code etc.), that triggers in it preposition is taken the photograph As the unlatching of head 04, when trade company holds payment code scanner 02 (such as two-dimensional code scanning rifle) scanning payment code 03, payment code is swept Retouch device 02 naturally be in 01 front camera 04 of mobile terminal imaging area 05, at this point, front camera 04 capture one or Multiple payment scene images, mobile terminal identify the payment code scanner in image, and root using built-in image recognition algorithm Payment control is carried out according to recognition result.

When above-mentioned steps execute on the server, payment code payment request is sent to server by mobile terminal, service Device is opened according to the front camera that payment code payment request triggers mobile terminal or mobile terminal is asked according to payment code payment The front camera triggered in it is asked to open, acquisition payment scene image, and payment scene image is sent to server progress Image recognition, and corresponding message is fed back to mobile terminal according to recognition result.

Fig. 2 is the flow diagram one of the method for mobile payment of the illegal in the embodiment of the present invention.As shown in Fig. 2, should The method of mobile payment of illegal may include the following contents:

Step S100: it is obtained according to the payment code payment request of consumer and shows payment code.

Wherein, which includes two dimensional code, bar code and/or payment yardage word etc..

It is worth noting that the technology for generating two dimensional code, bar code/or yardage word of paying the bill is that this field is very mature Technology, therefore repeat no more here.

Step S200: payment scene image is acquired according to the payment code payment request.

Specifically, front camera triggering command is generated according to payment code payment request, to trigger front camera unlatching, Utilize the one or more payment scene image of front camera acquisition of the mobile terminal of consumer.

Whether step S300: including payment code scanner in the identification payment scene image；

Wherein, identify in payment scene image whether include payment code scanner using image recognition algorithm.Wherein, the figure As machine learning model can be used in recognizer, image recognition software (such as Baidu AI image recognition software, Python) is realized.

Step S400: mobile payment process is controlled according to recognition result.

Wherein, if including payment code scanner in the payment scene image, allow to be moved using the payment code Dynamic payment；

Because since consumer's operating reason may not be able to collect trade company's payment code scanner when acquiring image, alternatively, Consumer needs to be paid and (such as pay to the personal terminal of businessman) feelings in the case where trade company does not have payment code scanner Shape, therefore, the application is in order to facilitate consumer's use, if not including payment code scanner in the payment scene image, to Whether consumer's push forbids the message that mobile payment is carried out using the payment code, according to the mobile branch of the feedback control of consumer Pay process.

For example, " failing to detect payment to consumer's push when not including payment code scanner in paying scene image Whether code scanner, PLSCONFM continue ", if consumer clicks " continuation ", prompt " whether PLSCONFM trade company is to be swept with payment code Retouch device ", and "Yes" is provided, two options of "No", by payment scene image deposit server, are made if consumer selects "Yes" To have marked the picture of scanner containing payment code, so that following model training uses, so that the accuracy of model identification is continuously improved, And consumer is prompted to be confirmed whether to complete this payment, if consumer selects to complete payment, success of withholing.

It is worth noting that since the front camera that the payment code scanner of trade company must be located at consumer's mobile terminal is taken the photograph As that could be collected image and be identified in regional scope, to effectively avoid in the stolen brush of the unware situation of consumer A possibility that, such as following scenario described: (1) criminal sweeps consumer with its mobile terminal robber behind the consumer being lined up Robber's brush that the payment code shown on mobile terminal screen occurs, the mobile terminal of criminal may not be in consumer's mobile terminal In front camera region, fail to collect image, thus cannot complete to pay；(2) in the careless situation of consumer, no Method molecule is stolen with its mobile terminal and sweeps payment code, and the mobile terminal of criminal is just also preposition in the mobile terminal of consumer In camera imaging area and it is collected photo, but because payment code scanner cannot be identified as, cannot complete to pay；(3) when The payment code that criminal attempts to be scanned the monitoring camera shooting above consumer with payment code scanner (may be illegal point Son in the dark arrangement or illegal acquisitions coherent video content) carry out steal brush when, because the mobile terminal of consumer can not collect trade company Payment code scanner, thus also it is unable to complete payment.Therefore, the present invention can effectively reduce payment two dimensional code and steal brush situation, from And guarantee the fund security of consumer.

Through the above technical solution it is known that the method for mobile payment of illegal provided in an embodiment of the present invention, passes through Using the front camera of the mobile terminal of consumer, when consumer shows payment code to trade company, front camera is opened simultaneously, Payment scene is imaged, using image recognition algorithm, the payment code comprising trade company in payment scene image is recognized and scans After device, payment code payment just can be carried out, to effectively improve the safety and compliance of payment.

In an alternative embodiment, the convolutional neural networks model that pre-training can be used identifies the payment scene figure It whether include payment code scanner as in, which carries out model learning using General Neural Network classifier And classification, model structure is as shown in figure 3, the convolutional neural networks model includes: for receiving the input layer of input picture, being used for Extract the convolutional layer of the feature of the input picture, for carrying out down-sampled sample level, for down-sampled to the feature Whether feature afterwards is classified the full articulamentum for obtaining label, scan comprising payment code in the tag characterization input picture Device.

Specifically, referring to Fig. 3:

Input picture A01 is the image with mark in training picture library.

Convolution kernel A02 is usually the matrix of N × N (N is odd number), also known as filter (filter), such as 3 × 3 convolution kernel Are as follows:

1	0	1
			0	1	0
1	0	1

Convolutional layer A04 is used to carry out convolution algorithm, the form of calculation of convolution algorithm A03 to input picture according to convolution kernel Are as follows:The number of plies where wherein l is indicated, k is convolution kernel, M_jFor the same as filter of input layer The subregion of size, the i.e. sliding window of input picture, f are Sigmoid activation primitive, and B is the bias term in neural network.

Convolutional layer A04 is the output after convolution algorithm.

Sample level A06 carries out down-sampled operation, the form of calculation of down-sampled operation A05 to the output of convolutional layer are as follows:Wherein f is Sigmoid activation primitive, and β is weight coefficient, and p is sampling function.

Sample level A06 is output layer of the convolutional layer after down-sampled.By multiple convolution and it is down-sampled after will obtain Several characteristic images.

Full articulamentum (also referred to as output layer) is used to the output of sample level A06 being attached operation A07, and characteristic image is turned Become a column vector, particular image is substantially a two-dimensional matrix, and one 3 × 3 matrix is changed into column vector, that is, is taken every One column sequence arranges, and will become column vector of the dimension for 9.

Full articulamentum A08 be by multiple convolution and it is down-sampled after a multidimensional characteristic table being formed.

Neural network classifier A09, i.e. generalized regression nerve networks (General Regression Neural Network, GRNN), it is a kind of mutation of artificial neural network, is the nonlinear regression nerve net based on non-parametric estmation Network has very strong Nonlinear Mapping and generalization ability, is suitable for Small Sample Database, and final convergence and sample are assembled more excellent Change face.It is made of 4 layer networks, respectively input layer, mode layer, summation layer and output layer.Wherein, input layer is from image sample The feature vector dimension extracted in this, and mode layer is passed to, mode layer neuron number is identical as input layer, different nerves The corresponding different sample datas of member, summation layer use full connection type only there are two neuron, with upper layer neuron, and output layer is to asking It is calculated with layer, obtains model predication value.The estimated value of GRNNWherein X_i,Y_iFor sample data, σ is smoothing factor, and n is sample data.

Prediction result A10, that is, model prediction result.

In an alternative embodiment, referring to fig. 4, the method for mobile payment of the illegal can also include in following Hold:

Step S10: building convolutional neural networks model；

Step S20: the convolutional neural networks model is trained to obtain using the image pattern of known label described The convolutional neural networks model of pre-training.

Specifically:

Step I: the image pattern of known label is inputted into the convolutional neural networks model, and the output of the model is made For training result；

Step II: the corresponding training result of each image pattern is compared with its known label；

Step III: adjusting the parameter of convolutional neural networks model according to comparison result, obtains the convolution mind of the pre-training Through network model.

In an alternative embodiment, the method for mobile payment of the illegal can also include the following contents:

Step a: the test sample of known label is obtained；

Step b: the test sample of the application known label tests the convolutional neural networks mould of the pre-training, And using the output of the model as test result；

Step c: it is based on the test result and known label, it is pre- to judge whether the convolutional neural networks mould of pre-training meets If it is required that；

If so, executing step e；If it is not, executing step f.

Step e: using "current" model as the object module of payment code scanner for identification；

Step f: optimizing "current" model and/or re-starts model training using updated training sample set.

It is worth noting that all kinds of pictures for being labeled as payment code scanner shot by using a large amount of different angles (as positive example sample) and other pictures (as negative example sample) for not including payment code scanner are used as training sample and test Sample is trained model and tests, in use, for the payment scene for failing identification, if consumer is to branch It pays scene and has beaten the mark containing scanner, model self-teaching and liter can be used for using the payment scene image as training picture Grade further trains model by constantly collection positive example sample and negative example sample, the self study of implementation model, constantly Generalization ability, accuracy rate and the applicable scene of lift scheme.

Wherein, by using convolutional neural networks identification model, up to 95% or even 97% or more, online recognition consumes discrimination When less than 1.2 seconds, meet payment requirement of real time.

In an alternative embodiment, referring to Fig. 5, the method for mobile payment of the illegal can also include interior Hold:

Step S150: current location is obtained according to the payment code payment request.

Specifically, while opening front camera according to the payment code payment request, GPS open command is generated, So that the built-in GPS in the mobile terminal of consumer is opened, current location is positioned in real time.

Step S350: the bar code in the identification payment scene image on payment code scanner, to obtain Merchants register Information, the Merchants register information include: Merchants register address.

Specifically, the payment scene is identified containing after payment code scanner in recognizing the payment scene image Generally above the scanning window of scanner 20, scanner is arranged referring to Fig. 6 in bar code in image on payment code scanner Bar code 21, the bar code include that trade company, Merchants register address, the trade company of scanner registration manage the essential informations such as class row.

It will be appreciated by persons skilled in the art that the application scenarios more complicated in registration information, can pass through scan stripes Shape code obtains the mark of the scanner, is gone in registration information database to obtain corresponding Merchants register according to the mark of the scanner Information.

Step S360: judge whether the current location and the Merchants register address are consistent；

If so, executing step S400；If it is not, executing step S370.

Step S370: warning information is generated.

Wherein, generating warning information may include various ways, and a kind of mode is to forbid paying, directly generation warning information It is sent in server, so that relevant staff's understanding scanner uses address and the inconsistent situation in registered address；Separately On the one hand, in order to not influence the use of consumer, it can permit consumer and paid using payment code, it still, can be anti-to consumer Current location and the inconsistent information warning in Merchants register address are presented, for example " current location and Merchants register address are inconsistent Information warning, PLSCONFM whether continuous business "；Furthermore can permit consumer and normally paid using payment code, payment at After function, " if the scanner of discovery trade company is inconsistent using address and registered address, shopping receipt can be shot simultaneously to consumer feedback Upload ", when consumer has found when using address and registered address inconsistent of trade company's scanner, selection uploads shopping receipt, then Relevant information uploads application server, and uploads to the distributed cloud computing system and save, and is further processed, supplies so as to subsequent The tax authority verifies, and it is inconsistent for such as verifying, then carries out the proof of the tax authority or cancel the registration information of trade company's scanner, make Can not continue to use.

By using above-mentioned technical proposal, it can prevent from engaging in trade such as Chinese in businessman overseas, utilize sweeping for country's registration It retouches rifle and sweeps two dimensional code and paid, since transaction occurs overseas, fund then circulates at home, does not meet the supervision such as local tax revenue It is required that the problem of.

In an alternative embodiment, the method for mobile payment of the illegal can also include:

After paying successfully, the name of firm, trade company's working group, payment amount etc. are pushed for consumption to consumer Person's verification.

Specifically, by pushing payment amount to consumer, consumer can be made to understand consumption information in real time, prevents businessman The problems such as more brushes.

On the other hand, by pushing the information such as name of firm and trade company's working group to consumer, consumer can be made Business Information is fully understood, meanwhile, it can be pushed to consumer " not such as discovery trade company's working group and sold goods or service type Unanimously, shopping receipt can be shot and uploaded ".When consumer find trade company's scanner working group and sold goods and service not When consistent, selection uploads shopping receipt, then relevant information uploads to application server, and uploads to distributed cloud computing system and protect Deposit, be further processed so as to subsequent, verified for related personnel, such as verify the proof that the tax authority is then carried out not to be inconsistent transaction or The registration information for cancelling trade company's scanner, is allowed to not continue to use.

By using above- mentioned information, can help to find that illegal trade company is different using tax revenue is managed, such as Sales Tax and increment Tax scans payment code gathering using the scanner for being registered as the lower tax category, builds false pretax income, utilize to evade tax revenue The behavior that Sales Tax, the tax difference of value-added tax are evaded a tax.

Fig. 7 shows the system architecture of the method for mobile payment using illegal provided in an embodiment of the present invention.Such as Fig. 7 institute Show, which includes: payment code payment scene S001, application server S002 and distributed cloud computing system S003.

The payment code pays scene S001: when consumer is in merchant purchasing commodity or service, consumer can show branch Code, while the front camera and positioning system of the automatic person's of expanding consumption mobile terminal are paid, is scanned and is paid with scanner when trade company When code or criminal scan payment code with other means, initiation is withholdd, one or more payment ring of front camera crawl Border photo, the photo and location information etc. reach the application server S002.

It is deployed on the application server S002 through the image recognition model after convolutional neural networks training.By right Whether the identification of photo identifies in photo containing the bar code on scanner and scanner, obtains scanner by bar code Relevant information: the essential informations such as trade company, address, business classification of registration.(1) it if containing scanner in identification photo, and scans The registered address of device is consistent with the location information that mobile terminal returns (to be considered position error, allows location information and address etc. There are a certain range of errors), success of withholing.Simultaneously to the registration information of mobile terminal passback scanner: name of firm, operation Type, spending amount etc., and prompt consumer " as discovery trade company's working group and sold goods or service type it is inconsistent, can Shooting shopping receipt simultaneously uploads ".When consumer has found the working group of trade company's scanner with sold goods and inconsistent service, Selection uploads shopping receipt, then relevant information uploads to the application server S002, and uploads to the distributed cloud computing System S003 is saved, and is further processed so as to subsequent, is such as verified the proof for then carrying out the tax authority not to be inconsistent transaction or is cancelled quotient The registration information of family scanner is allowed to not continue to use.(2) if unidentified arrive scanner, Fail Transaction prompts consumer " failing to detect payment code scanner, whether PLSCONFM continues ".If consumer clicks " continuation ", " PLSCONFM trade company is prompted Whether scanned with payment code scanner ", and "Yes" is provided, two options of "No" move consumer if consumer selects "Yes" The photo that dynamic terminal obtains is stored in " the trade company's payment code scanner recognition image library " of the distributed cloud computing system S003, As the picture of scanner containing payment code has been marked, for model training use, so that the accuracy of model identification is continuously improved, and Prompt consumer is confirmed whether to complete this payment, if consumer selects to complete payment, success of withholing.It is mobile to consumer simultaneously The registration information of terminal passback scanner: name of firm, working group, spending amount etc., and prompt consumer " such as discovery trade company Working group and sold goods or service type are inconsistent, can shoot shopping receipt and upload ".When consumer has found trade company's scanning When the working group and sold goods of device and inconsistent service, selection uploads shopping receipt, then relevant information uploads to described answer It with server S 002, and uploads to the distribution cloud computing system S003 and saves, be further processed so as to subsequent, be as verified It is not inconsistent transaction, then carries out the proof of the tax authority or cancels the registration information of trade company's scanner, is allowed to not continue to use；If Consumer selects "No", shows deducted amount, consumer is asked to be confirmed whether to complete this payment, if consumer selects to complete branch It pays, then completion of trading, success of withholing.Simultaneously to the registration information of consumer's mobile terminal passback scanner: name of firm, operation Type, spending amount etc., and prompt consumer " as discovery trade company's working group and sold goods or service type it is inconsistent, can Shooting shopping receipt simultaneously uploads ".When consumer has found the working group of trade company's scanner with sold goods and inconsistent service, Selection uploads shopping receipt, then relevant information uploads to the application server S002, and uploads to the distributed cloud computing System S003 is saved, and is further processed so as to subsequent: being illegal transaction as verified, is then carried out the proof of the tax authority or cancel quotient The registration information of family scanner is allowed to not continue to use.If consumer's selection is endless at transaction, this transaction terminates, Payment code payment is re-initiated by consumer, is brushed to avoid stealing.

On the distribution cloud computing system S003, trade company's payment code scanner recognition algorithm is deployed, and store (or close It is linked to third party's picture library) all kinds of pictures and other pictures for being labeled as trade company's payment code scanner of a large amount of different angle shooting As training sample set and test sample collection, it is used for model training and verifying, trade company's payment code scanner recognition algorithm to use one Kind convolutional neural networks method carries out machine learning to the picture of picture library band mark, obtains model of the discrimination 95% or more, And training sample set and test sample are gathered as payment code payment transaction is continuously increased.In system dispose model training algorithm with Certain period (monthly or by week) progress model training, the self study of implementation model, the generalization ability of continuous lift scheme, and It is deployed on the application server S002 for identifying in real time.Payment code transaction is also stored in distributed cloud computing system simultaneously Information etc..

Based on the same inventive concept, the embodiment of the present application also provides a kind of mobile payment device of illegal, Ke Yiyong The method described in realization above-described embodiment, as described in the following examples.Since the mobile payment device of illegal solves The principle of problem is similar to the above method, therefore the implementation of the mobile payment device of illegal may refer to the reality of the above method It applies, overlaps will not be repeated.Used below, the software of predetermined function may be implemented in term " unit " or " module " And/or the combination of hardware.Although device described in following embodiment is preferably realized with software, hardware or soft The realization of the combination of part and hardware is also that may and be contemplated.

Fig. 8 is the structural block diagram of the mobile payment device of the illegal in the embodiment of the present invention.As shown in figure 8, this is antitheft The mobile payment device of brush specifically includes: payment code generation module 1000, payment scene image acquisition module 2000, payment code are swept Retouch device identification module 3000 and mobile payment control module 4000.

Payment code generation module 1000 obtains according to the payment code payment request of consumer and shows payment code.

It pays scene image acquisition module 2000 and payment scene image is acquired according to the payment code payment request.

Whether payment code scanner recognition module 3000 identifies in the payment scene image comprising payment code scanner.

Mobile payment control module 4000 controls mobile payment process according to recognition result.

Through the above technical solution it is known that the mobile payment device of illegal provided in an embodiment of the present invention, passes through Using the front camera of the mobile terminal of consumer, when consumer shows payment code to trade company, front camera is opened simultaneously, Payment scene is imaged, using image recognition algorithm, the payment code comprising trade company in payment scene image is recognized and scans After device, payment code payment just can be carried out, to effectively improve the safety and compliance of payment.

In an alternative embodiment, the mobile payment control module 4000 includes: mobile payment unit and shifting Dynamic payment affirmation unit.

When mobile payment unit includes payment code scanner in the payment scene image, allow to utilize the payment code Carry out mobile payment；

When mobile payment confirmation unit does not include payment code scanner in the payment scene image, pushed to consumer Whether the message that using the payment code carries out mobile payment is forbidden, according to the feedback control mobile payment process of consumer.

In an alternative embodiment, the payment code scanner recognition module 3000 includes: model recognition unit.

Model recognition unit identifies in the payment scene image whether wrap using the convolutional neural networks model of pre-training Scanner containing payment code.

The convolutional neural networks model carries out model learning and classification using General Neural Network classifier, and model structure is such as Shown in Fig. 3, which includes: for receiving the input layer of input picture, for extracting the input picture Feature convolutional layer, for carrying out down-sampled sample level, for classifying to the feature after down-sampled to the feature The full articulamentum of label is obtained, whether includes payment code scanner in the tag characterization input picture.

In an alternative embodiment, the mobile payment device of the illegal can also include: model construction module with And model training module.

Model construction module constructs convolutional neural networks model；

Model training module is trained to obtain using the image pattern of known label to the convolutional neural networks model The convolutional neural networks model of the pre-training.

In an alternative embodiment, the model training module includes: that training sample input unit, result are more single Member and parameter adjustment unit.

As a result the corresponding training result of each image pattern is compared by comparing unit with its known label；

In an alternative embodiment, the mobile payment device of the illegal can also include: that test sample obtains mould Block, model measurement module, test judgment module, model release module and model adjust module.

Test sample obtains the test sample that module obtains known label；

The test sample of known label described in model measurement module application to the convolutional neural networks mould of the pre-training into Row test, and using the output of the model as test result；

Test judgment module be based on the test result and known label, judge pre-training convolutional neural networks mould whether Meet preset requirement；

If the convolutional neural networks mould of model release module pre-training meets preset requirement, using "current" model as being used for Identify the object module of payment code scanner；

If the convolutional neural networks mould of model adjustment module pre-training does not meet preset requirement, "current" model is carried out excellent Change and/or re-starts model training using updated training sample set.

In an alternative embodiment, the mobile payment device of the illegal can also include: locating module, bar code Identification module, address judgment module and alarm module.

Specifically, the payment scene is identified containing after payment code scanner in recognizing the payment scene image Scanner bar code is arranged generally above the scanning window of scanner in bar code in image on payment code scanner, this Shape code includes that trade company, Merchants register address, the trade company of scanner registration manage the essential informations such as class row.

If the alarm module current location and the Merchants register address are inconsistent, warning information is generated.

In an alternative embodiment, trade company's essential information further include: name of firm, trade company's working group；

The mobile payment device of the illegal further include: order information pushing module after paying successfully, is pushed away to consumer The name of firm, trade company's working group is sent to check for consumer.

Device, module or the unit that above-described embodiment illustrates can specifically be realized, Huo Zheyou by computer chip or entity Product with certain function is realized.It is a kind of typical to realize that equipment is electronic equipment, specifically, electronic equipment for example can be with For personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media player, Any in navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or these equipment sets Standby combination.

Electronic equipment specifically includes memory, processor and storage on a memory and can in a typical example The computer program run on a processor, the processor realize following step when executing described program:

Mobile payment process is controlled according to recognition result.

As can be seen from the above description, electronic equipment provided in an embodiment of the present invention, passes through the mobile terminal using consumer Front camera, when consumer to trade company show payment code, open simultaneously front camera, to payment scene image, benefit It just can be carried out payment code branch after recognizing the payment code scanner paid in scene image comprising trade company with image recognition algorithm It pays, so that the safety and compliance of payment are effectively improved, guarantee consumers' rights and interests, the mobile payment environment of maintaining healthy, together When support rapid payment.

Below with reference to Fig. 9, it illustrates the structural representations for the electronic equipment 600 for being suitable for being used to realize the embodiment of the present application Figure.

As shown in figure 9, electronic equipment 600 includes central processing unit (CPU) 601, it can be according to being stored in read-only deposit Program in reservoir (ROM) 602 is loaded into random access storage device (RAM) from storage section 608) program in 603 and Execute various work appropriate and processing.In RAM603, also it is stored with system 600 and operates required various programs and data. CPU601, ROM602 and RAM603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to bus 604。

I/O interface 605 is connected to lower component: the importation 606 including keyboard, mouse etc.；It is penetrated including such as cathode The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 608 including hard disk etc.； And including such as LAN card, the communications portion 609 of the network interface card of modem etc..Communications portion 609 via such as because The network of spy's net executes communication process.Driver 610 is also connected to I/O interface 605 as needed.Detachable media 611, such as Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 610, in order to read from thereon Computer program be mounted as needed such as storage section 608.

Particularly, according to an embodiment of the invention, may be implemented as computer above with reference to the process of flow chart description Software program.For example, the embodiment of the present invention includes a kind of computer readable storage medium, it is stored thereon with computer program, The computer program realizes following step when being executed by processor:

Mobile payment process is controlled according to recognition result.

As can be seen from the above description, computer readable storage medium provided in an embodiment of the present invention, by utilizing consumer's The front camera of mobile terminal, when consumer to trade company show payment code, open simultaneously front camera, to payment scene into Row camera shooting after recognizing the payment code scanner paid in scene image comprising trade company, just can be carried out using image recognition algorithm Payment code payment guarantees consumers' rights and interests, the mobile payment of maintaining healthy to effectively improve the safety and compliance of payment Environment, while supporting rapid payment.

In such embodiments, which can be downloaded and installed from network by communications portion 609, And/or it is mounted from detachable media 611.

Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data. The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM), Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.

For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this The function of each unit can be realized in the same or multiple software and or hardware when application.

The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates, Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or The function of being specified in multiple boxes.

These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one The step of function of being specified in a box or multiple boxes.

It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want There is also other identical elements in the process, method of element, commodity or equipment.

It will be understood by those skilled in the art that embodiments herein can provide as method, system or computer program product. Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) Formula.

The application can describe in the general context of computer-executable instructions executed by a computer, such as program Module.Generally, program module includes routines performing specific tasks or implementing specific abstract data types, programs, objects, group Part, data structure etc..The application can also be practiced in a distributed computing environment, in these distributed computing environments, by Task is executed by the connected remote processing devices of communication network.In a distributed computing environment, program module can be with In the local and remote computer storage media including storage equipment.

All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method Part explanation.

The above description is only an example of the present application, is not intended to limit this application.For those skilled in the art For, various changes and changes are possible in this application.All any modifications made within the spirit and principles of the present application are equal Replacement, improvement etc., should be included within the scope of the claims of this application.

Claims

1. a kind of method of mobile payment of illegal characterized by comprising

Mobile payment process is controlled according to recognition result.

2. the method for mobile payment of illegal according to claim 1, which is characterized in that described to be controlled according to recognition result Mobile payment process, comprising:

3. the method for mobile payment of illegal according to claim 1, which is characterized in that the identification payment scene It whether include payment code scanner in image, comprising:

Identify in the payment scene image whether include payment code scanner using the convolutional neural networks model of pre-training.

4. the method for mobile payment of illegal according to claim 3, which is characterized in that the convolutional neural networks model Include:

Input layer, for receiving input picture；

Convolutional layer, for extracting the feature of the input picture；

Sample level, it is down-sampled for being carried out to the feature；

Full articulamentum, for being classified to obtain label to the feature after down-sampled, in the tag characterization input picture whether Include payment code scanner.

5. the method for mobile payment of illegal according to claim 4, which is characterized in that further include:

Construct convolutional neural networks model；

6. the method for mobile payment of illegal according to claim 5, which is characterized in that the figure using known label Decent is trained the convolutional neural networks model to obtain the convolutional neural networks model of the pre-training, comprising:

The parameter that convolutional neural networks model is adjusted according to comparison result, obtains the convolutional neural networks model of the pre-training.

7. the method for mobile payment of illegal according to claim 6, which is characterized in that further include:

Obtain the test sample of known label；

8. the method for mobile payment of illegal according to claim 1, which is characterized in that further include:

Current location is obtained according to the payment code payment request；

The bar code in the payment scene image on payment code scanner is identified, to obtain Merchants register information, the trade company Registration information includes: Merchants register address；

If it is not, then generating warning information.

9. the method for mobile payment of illegal according to claim 8, which is characterized in that trade company's essential information is also wrapped It includes: name of firm, trade company's working group；

The method of mobile payment of the illegal further include:

10. the method for mobile payment of illegal according to any one of claims 1 to 9, which is characterized in that the payment code It include: two dimensional code and/or bar code.

11. a kind of mobile payment device of illegal characterized by comprising

Payment code scanner recognition module identifies in the payment scene image whether include payment code scanner；

12. the mobile payment device of illegal according to claim 11, which is characterized in that the mobile payment controls mould Block includes:

Mobile payment confirmation unit, if not including payment code scanner in the payment scene image, pushing to consumer is The no message for forbidding carrying out mobile payment using the payment code, according to the feedback control mobile payment process of consumer.

13. the mobile payment device of illegal according to claim 11, which is characterized in that the payment code scanner is known Other module includes:

Whether model recognition unit is identified in the payment scene image using the convolutional neural networks model of pre-training comprising branch Pay code scanner.

14. the mobile payment device of illegal according to claim 13, which is characterized in that the convolutional neural networks mould Type includes:

Input layer, for receiving input picture；

Convolutional layer, for extracting the feature of the input picture；

Sample level, it is down-sampled for being carried out to the feature；

15. the mobile payment device of illegal according to claim 14, which is characterized in that further include:

Model construction module constructs convolutional neural networks model；

Model training module is trained to obtain described using the image pattern of known label to the convolutional neural networks model The convolutional neural networks model of pre-training.

16. the mobile payment device of illegal according to claim 15, which is characterized in that the model training module packet It includes:

The image pattern of known label is inputted the convolutional neural networks model by training sample input unit, and by the model Output as training result；

Parameter adjustment unit adjusts the parameter of convolutional neural networks model according to comparison result, obtains the convolution of the pre-training Neural network model.

17. the mobile payment device of illegal according to claim 16, which is characterized in that further include:

Test sample obtains module, obtains the test sample of known label；

Judgment module is tested, the test result and known label is based on, judges whether the convolutional neural networks mould of pre-training accords with Close preset requirement；

Model release module, if the convolutional neural networks mould of pre-training meets preset requirement, using "current" model as being used to know The object module of other payment code scanner；

Model adjustment module optimizes "current" model if the convolutional neural networks mould of pre-training does not meet preset requirement And/or model training is re-started using updated training sample set.

18. the mobile payment device of illegal according to claim 11, which is characterized in that further include:

Bar code recognition module identifies the bar code in the payment scene image on payment code scanner, to obtain trade company's note Volume information, the Merchants register information includes: Merchants register address；

19. the mobile payment device of illegal according to claim 18, which is characterized in that trade company's essential information is also It include: name of firm, trade company's working group；

The mobile payment device of the illegal further include:

20. the mobile payment device of 1 to 19 described in any item illegals according to claim 1, which is characterized in that the payment Code includes: two dimensional code and/or bar code.

21. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor Machine program, which is characterized in that the processor realizes the described in any item illegals of claims 1 to 10 when executing described program Method of mobile payment the step of.

22. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program quilt The step of method of mobile payment of the described in any item illegals of claims 1 to 10 is realized when processor executes.