CN109670797A - Pay route selecting method, apparatus, equipment and storage medium - Google Patents
Pay route selecting method, apparatus, equipment and storage medium Download PDFInfo
- Publication number
- CN109670797A CN109670797A CN201811060994.0A CN201811060994A CN109670797A CN 109670797 A CN109670797 A CN 109670797A CN 201811060994 A CN201811060994 A CN 201811060994A CN 109670797 A CN109670797 A CN 109670797A
- Authority
- CN
- China
- Prior art keywords
- payment
- routing
- model
- current
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000003066 decision tree Methods 0.000 claims abstract description 35
- 238000013507 mapping Methods 0.000 claims description 20
- 230000015654 memory Effects 0.000 claims description 15
- 238000003062 neural network model Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 abstract description 5
- 238000012216 screening Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
Classifications
-
- 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
- G06Q20/02—Payment architectures, schemes or protocols involving a neutral party, e.g. certification authority, notary or trusted third party [TTP]
- G06Q20/027—Payment architectures, schemes or protocols involving a neutral party, e.g. certification authority, notary or trusted third party [TTP] involving a payment switch or gateway
Abstract
The invention discloses a kind of payment route selecting method, apparatus, equipment and storage mediums.The described method includes: receiving the current payment request that user sends, payment routing can be used by obtaining several；Objective decision tree-model corresponding with current payment request is searched in the preset database；Can be screened with payment routing by being then based on objective decision tree-model by several, and the available payment filtered out routing is paid as target payment routing, by first determining that several can use payment routing and decision-tree model thus according to the current payment request received, then several got can be carried out screening with payment routing by decision-tree model and the payment routing of the target by filtering out is paid, staff's manual configuration routing policy is eliminated to choose the troublesome operation of payment routing, while the payment for guaranteeing to filter out routes high reliability, also achieve the rapid configuration to payment routing, improve payment experience.
Description
Technical field
The present invention relates to financial technology fields more particularly to a kind of payment route selecting method, apparatus, equipment and storage to be situated between
Matter.
Background technique
Currently, the routing factor of the intelligence payment route system in financial industry is (as to account rate, paid timeliness, the amount of money
Threshold value etc.) excessively, cause the payment routing rule of different platform also more.
In addition, existing payment route system is when choosing payment routing, corresponding routing rule calculates in real time mostly, nothing
Normal plane can not be routed to the payment request of high concurrent, and when facing banking system maintenance and other anomalous events
Switching, while existing payment route system excessively relies on staff's by virtue of experience hand when carrying out the selection of payment routing
The routing policy of dynamic configuration, specific aim is poor, reliability is low, and whole process time-consuming is also longer, and user experience is bad.Therefore, how
For different payment requests, realizes the rapid configuration of payment routing and complete to pay, be a urgent problem to be solved.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide a kind of payment route selecting method, apparatus, equipment and storage mediums, it is intended to
Different payment requests can not be directed to by solving the prior art, realize the technical issues of rapid configuration of payment routing is paid.
To achieve the above object, it the present invention provides a kind of payment route selecting method, the described method comprises the following steps:
The current payment request that user sends is received, payment routing can be used by obtaining several；
Objective decision tree-model corresponding with the current payment request is searched in the preset database；
Described several can be screened with payment routing based on the objective decision tree-model, and can by what is filtered out
Payment routing is used to be paid as target payment routing.
Preferably, the step of current payment request for receiving user and sending, payment routing can be used by obtaining several, packet
It includes:
The current payment request that user sends is received, the user identifier carried in the current payment request is extracted；
Several payment routings to be selected corresponding with the user identifier are searched in the first mapping relations, described first reflects
Penetrating storage in relationship has user identifier and the corresponding relationship to be selected paid between routing；
It is current whether in connected state to detect each payment routing to be selected, by all payment roads to be selected in connected state
By as can use payment route.
Preferably, it is described receive user send current payment request, obtain several can with payment routing the step of it
Before, the method also includes:
All preset payments are obtained from the presetting database routes corresponding historical trading data；
Neural network model is trained according to the historical trading data, and is determined according to training result several
Routing rule；
The several routing rule is respectively put into decision tree to construct the corresponding decision tree mould of different routing rules
Type.
Preferably, described to search corresponding with current payment request objective decision tree-model in the preset database
Step, comprising:
The corresponding target service type of the current payment request is obtained, and target is determined according to the target service type
Routing rule；
According to the target routing rule, is searched by the second mapping relations and routed with the target in the preset database
The corresponding objective decision tree-model of rule, storage has pair between routing rule and decision-tree model in second mapping relations
Relationship.
Preferably, described that described several can be screened with payment routing based on the objective decision tree-model, and
The step of available payment filtered out routing is paid as target payment routing, comprising:
Obtain the current routing parameter of each available payment routing；
The current routing parameter is sent in the objective decision tree-model, determines each available payment routing pair respectively
The desired value answered；
It routes corresponding desired value to each available payment by preset rules to be ranked up, and if according to ranking results from described
Dry item can be paid with target payment routing is filtered out in payment routing.
Preferably, described that the current routing parameter is sent in the objective decision tree-model, determination respectively may be used respectively
The step of routing corresponding desired value with payment, comprising:
The historical failure rate, is lower than the available payment of preset threshold by the historical failure rate for obtaining each available payment routing
Routing is as effectively payment routing；
Effective payment is routed corresponding current routing parameter to be sent in the objective decision tree-model, it is true respectively
Fixed each effective payment routes corresponding desired value；
Correspondingly, described corresponding desired value is routed to each available payment by preset rules to be ranked up, and according to sequence
As a result the step of being paid can be routed with target payment is filtered out in payment routing from described several, comprising:
Corresponding desired value is routed to each effective payment by preset rules to be ranked up, and is had according to ranking results from described
Target payment routing is filtered out in effect payment routing to be paid.
Preferably, described corresponding desired value is routed to each effective payment by preset rules to be ranked up, and according to sequence
As a result from being filtered out in the effective payment routing after target payment routing paid, the method also includes:
An effectively payment routing, which is chosen, from remaining effective payment routing according to the ranking results is used as spare road
By；
When detecting that carrying out payment by target payment routing occurs abnormal, the target is paid into route handoff
It is paid for the alternate routing.
In addition, to achieve the above object, the present invention also proposes a kind of payment route selecting device, and described device includes: to ask
Ask respond module, model determining module and routing determining module；
The ask respond module, for receiving the current payment request of user's transmission, payment road can be used by obtaining several
By；
The model determining module is determined for searching target corresponding with the current payment request in the preset database
Plan tree-model；
The routing determining module, for based on the objective decision tree-model to described several can be routed with payment into
Row screening, and the available payment filtered out routing is paid as target payment routing.
In addition, to achieve the above object, the present invention also proposes a kind of payment route selecting equipment, and the equipment includes: to deposit
Reservoir, processor and the payment route selecting program that is stored on the memory and can run on the processor, it is described
The step of payment route selecting program is arranged for carrying out payment route selecting method as described above.
In addition, to achieve the above object, the present invention also proposes a kind of storage medium, payment is stored on the storage medium
Route selecting program, the payment route selecting program realize payment route selecting side as described above when being executed by processor
The step of method.
The current payment request that the present invention is sent by receiving user, payment routing can be used by obtaining several；In present count
According to lookup objective decision tree-model corresponding with current payment request in library；Being then based on objective decision tree-model can to several
It is screened with payment routing, and the available payment filtered out routing is paid as target payment routing, due to being root
First determine that several can use payment routing and decision-tree model, then pass through decision tree according to the current payment request received
Model can be carried out screening with payment routing to several got and the payment routing of the target by filtering out is paid, and exempts from
Staff's manual configuration routing policy has been removed to choose the troublesome operation of payment routing, in the payment routing height for guaranteeing to filter out
While reliability, the rapid configuration to payment routing is also achieved, improves payment experience.
Detailed description of the invention
Fig. 1 is the structural representation of the payment route selecting equipment for the hardware running environment that the embodiment of the present invention is related to
Figure；
Fig. 2 is the flow diagram of present invention payment route selecting method first embodiment；
Fig. 3 is the flow diagram of present invention payment route selecting method second embodiment；
Fig. 4 is the flow diagram of present invention payment route selecting method 3rd embodiment；
Fig. 5 is the structural block diagram of present invention payment route selecting device first embodiment.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that described herein, specific examples are only used to explain the present invention, is not intended to limit the present invention.
Referring to Fig.1, Fig. 1 is the payment route selecting device structure for the hardware running environment that the embodiment of the present invention is related to
Schematic diagram.
As shown in Figure 1, the payment route selecting equipment may include: processor 1001, such as central processing unit
(Central Processing Unit, CPU), communication bus 1002, user interface 1003, network interface 1004, memory
1005.Wherein, communication bus 1002 is for realizing the connection communication between these components.User interface 1003 may include display
Shield (Display), input unit such as keyboard (Keyboard), optional user interface 1003 can also include that the wired of standard connects
Mouth, wireless interface.Network interface 1004 optionally may include standard wireline interface and wireless interface (such as Wireless Fidelity
(WIreless-FIdelity, WI-FI) interface).Memory 1005 can be the random access memory (Random of high speed
Access Memory, RAM) memory, be also possible to stable nonvolatile memory (Non-Volatile Memory,
), such as magnetic disk storage NVM.Memory 1005 optionally can also be the storage device independently of aforementioned processor 1001.
It will be understood by those skilled in the art that structure shown in Fig. 1 does not constitute the limit to payment route selecting equipment
It is fixed, it may include perhaps combining certain components or different component layouts than illustrating more or fewer components.
As shown in Figure 1, as may include operating system, data storage mould in a kind of memory 1005 of storage medium
Block, network communication module, Subscriber Interface Module SIM and payment route selecting program.
In payment route selecting equipment shown in Fig. 1, network interface 1004 is mainly used for being counted with background server
According to communication；User interface 1003 is mainly used for carrying out data interaction with user；The present invention pays the processing in route selecting equipment
Device 1001, memory 1005 can be set in payment route selecting equipment, and the payment route selecting equipment passes through processor
The payment route selecting program stored in 1001 calling memories 1005, and execute payment routing choosing provided in an embodiment of the present invention
Take method.
The embodiment of the invention provides a kind of payment route selecting methods, are present invention payment routing choosing referring to Fig. 2, Fig. 2
Take the flow diagram of method first embodiment.In the present embodiment, it the described method comprises the following steps:
Step S10: receiving the current payment request that user sends, and payment routing can be used by obtaining several；
It should be noted that the executing subject of the present embodiment method can be with network communication, data processing and journey
The server of sort run function, or equipment or system with similar functions.The server can in real time with corresponding client
And financial system carries out information exchange, the response to user's payment request is completed, hereafter using server as executing subject to branch
Each embodiment for paying route selecting method is illustrated.
It should be understood that the current payment request can be the payment request that user is sent by client, and described
Current payment request is also possible to several payment requests that same timing node server receives, if when server is receiving
Clustering first can be carried out to these payment requests when dry payment request, and classified based on the analysis results, then obtained again
The corresponding available payment routing of sorted each payment request.It is described to can be current time with payment routing and be in connected state
The payment route or channel of state.
It will be appreciated that the same server is often the application program of multiple and different types in certain special scenes
(or client) offer service, and the subsequent operation actually carried out for the data server of different application passes
Or processing may be not identical, and such as: server A is respectively that application program 1, application program 2 and application program 3 provide finance
Service, but since application program 1, application program 2 and application program 3 are belonging respectively to different application fields, (such as electric business is protected
Danger, small amount debt-credit), therefore the Stability and dependability in order to guarantee financial transaction, staff can be used one in the present embodiment
It is in advance the multiple corresponding payment routings of these three types of application program configurations in server side to more modes, in order to which server exists
When receiving the payment request that these three types of application programs are sent, the corresponding payment routing of these application programs is chosen to realize
Response to payment request.Specifically, the step S10 can include: the current payment request that user sends is received, described in extraction
The user identifier carried in current payment request；In the first mapping relations search it is corresponding with the user identifier several to
Choosing payment routes, and storage has the corresponding relationship between user identifier and payment routing to be selected in first mapping relations；Detection
Whether each payment routing to be selected is current is in connected state, and all payment to be selected routing conducts in connected state can be used branch
Pay routing.
Wherein, the user identifier can be the corresponding identification code of each application program (or client), which can be pre-
It first configures, and its form of expression may include number, letter, and/or combination of digits plus letters etc., the present embodiment does not limit this
System.First mapping relations can be the corresponding relationship between the user identifier pre-established and payment routing to be selected, described
It is user identifier that end source is mapped in first mapping relations, and target side source is payment to be selected routing.
In the concrete realization, server receives the current payment request that user is sent by client, and then basis is deserved
Preceding payment request, which obtains corresponding several, can use payment routing.
Step S20: objective decision tree-model corresponding with the current payment request is searched in the preset database；
It should be noted that the presetting database can be the data space pre-established, can be used for storing not
(such as transaction success rate pays consumption, transaction when routing availability, trading for same decision-tree model and all kinds of historical trading datas
Expense etc.).
In addition, the present embodiment pays route selecting method further include: from the presetting database before executing this step
It is middle to obtain the corresponding historical trading data of all preset payments routings；According to the historical trading data to neural network model into
Row training, and several routing rule is determined according to training result；The several routing rule is respectively put into decision tree
In to construct the corresponding decision-tree model of different routing rules.It should be understood that the preset payment routing can be Faculty of Finance
All established payment routes or channel in uniting.Neural network model is trained specifically according to the historical trading data
It can be the ginseng such as consumption and/or tranaction costs when routing availability, transaction according to the transaction success rate in historical trading data, payment
Several pairs of neural network models are trained.
In the concrete realization, server can be after receiving current payment request, and it is right therewith to search in the preset database
The decision-tree model answered, i.e., the described decision-tree model.
Step S30: described several can be screened with payment routing based on the objective decision tree-model, and will sieve
The available payment routing selected is paid as target payment routing.
It should be understood that decision-tree model is generally used in Sequence Decision, usually with maximum return desired value or minimum
Expected cost is solved the benefit value of all kinds of schemes at different conditions by graphic mode, then passes through ratio as decision rule
Compared with making a policy.Since decision tree (model) is substantially a kind of classification method, and the classification of every group of classification samples is true in advance
Fixed, therefore the present embodiment establishes different decision trees previously according to the corresponding classification of different payment requests (such as type of service)
Model, the corresponding each of payment request is then calculated further according to decision-tree model to use the desired value of payment routing, finally
The routing of payment corresponding to the desired value for meeting preset condition is paid as target payment routing again.
In the concrete realization, server can determine after determining the corresponding decision-tree model of current payment request according to this
Plan tree-model can screen several obtained in advance with payment routing, then by the payment of the target that filters out route into
Row payment.
The current payment request that the present embodiment is sent by receiving user, payment routing can be used by obtaining several；Default
Objective decision tree-model corresponding with current payment request is searched in database；It is available to several based on objective decision tree-model
Payment routing screened, and by the available payment filtered out routing as target payment routing pay, by thus according to
The current payment request received first determines available payment routing and decision-tree model, then by decision-tree model to obtaining
The available payment routing got screen and the routing of the payment by filtering out is paid, so as to guarantee to finally screen
Payment routing out has stronger specific aim and higher reliability, realizes the rapid configuration of payment routing, improves
Payment experience.
It is the flow diagram of present invention payment route selecting method second embodiment with reference to Fig. 3, Fig. 3.
Based on above-mentioned first embodiment, the payment route selecting method that the present embodiment proposes can have in the step S20
Body includes:
Step S201: the corresponding target service type of the current payment request is obtained, and according to the target service class
Type determines target routing rule；
It will be appreciated that routing rule corresponding to the financial transaction of type of service different in financial industry may be simultaneously
It is not identical.For example, the corresponding routing rule of business 1 is minimum to consume when transaction, i.e., transactions velocity is most fast；The corresponding routing of business 2
Rule is that transaction cost is minimum；The corresponding routing rule of business 3 is that transaction failure rate is most low.Therefore in the present embodiment, work
Corresponding routing rule can be configured to different type of service in advance by making personnel, in order to which server is asked receiving current payment
When asking, type of service belonging to the payment request and the corresponding routing rule of the type of service are quickly determined.
Step S202: it according to the target routing rule, is searched in the preset database by the second mapping relations and institute
The corresponding objective decision tree-model of target routing rule is stated, storage has routing rule and decision tree mould in second mapping relations
Between type to relationship.
It should be noted that can be established in the server in advance to improve the efficiency of entire payment route selecting process
Corresponding relationship between routing rule and decision-tree model, i.e., described second mapping relations, so that server is determining current branch
When paying corresponding routing rule (the i.e. described target routing rule) of request, realized according to second mapping relations to objective decision
The quick determination of tree-model.
The present embodiment is determined by obtaining the corresponding target service type of current payment request, and according to target service type
Target routing rule is searched and target road in the preset database then according to target routing rule by the second mapping relations
By the corresponding objective decision tree-model of rule, the quick lookup to objective decision tree-model is realized, improves payment routing choosing
The efficiency taken.
It is the flow diagram of present invention payment route selecting method 3rd embodiment with reference to Fig. 4, Fig. 4.
In the payment route selecting method proposed based on the various embodiments described above, the present embodiment, the step S30 is specifically included
Following steps:
Step S301: the current routing parameter of each available payment routing is obtained；
It should be noted that the current routing parameter can be consumption when current time payment routes corresponding transaction, hand over
The transaction data such as easy expense, transaction success rate, payment routing availability.Wherein, consumption completes every transaction institute when the payment
The duration of consuming, such as 8 seconds/, 12 seconds/；The payment expense is to complete the tranaction costs of every transaction；It is described transaction at
Power is the chance of success for completing every transaction；The payment routing availability is to pay what routing current time can also be performed
The ratio of transaction count and total degree has been completed 30 times at present for example, the transaction total degree that payment routed for 1 today is 100 times
Transaction, then paying the current payment routing availability of routing 1 is (100-30)/100=0.7.Certainly, the present embodiment is to current road
By parameter specific list item and be not particularly limited.
In the concrete realization, server obtains each available payment routing by being scanned to each available payment routing
Current routing parameter.
Step S302: the current routing parameter is sent in the objective decision tree-model, is determined respectively each available
Payment routes corresponding desired value；
It will be appreciated that server will can currently route after the current routing parameter for getting each available payment routing
Parameter is sent in objective decision tree-model, determines that each available payment routes corresponding desired value respectively.For example, in current goal
There are two under routing rule (as consumed when trading) can use payment routing: payment routing A and payment routing B, it is assumed that transaction
Benchmark when consumption be 10 seconds/, if the success rate that is paid of current time payment routing A is 0.4, and while pay successfully, corresponds to
Transaction success when consumption be 8 seconds/, payment failure when corresponding Fail Transaction when consumption be 20 seconds/；Payment routing B is propped up
The success rate paid is 0.8, and while pay successfully it is corresponding consume when trade successfully for 12 seconds/, pay corresponding transaction when failing
Consumption is 15 seconds/when failure, then according to objective decision tree-model, " [success rate * is (when trading successfully when consumption-benchmark for desired value=a*
Consumption)+(1- success rate) * (being consumed when consumption-benchmark when Fail Transaction)], wherein a is default weight coefficient " and, payment routing can be calculated
The desired value of A are as follows: 0.8* [0.4* (8-10)+0.6 (20-10)]=4.16；The desired value of payment routing B are as follows: 0.8* [0.8*
(12-10)+0.2 (15-10)]=2.08.In the transaction of payment routing B, consumption (desired value) will be far below payment routing A's
It is time-consuming when transaction, if server determines that consuming minimum payment when needing to find routes, and can choose branch according to current payment request
Routing B is paid to be paid.
Step S303: corresponding desired value is routed to each available payment by preset rules and is ranked up, and is tied according to sequence
Fruit can be paid from described several with target payment routing is filtered out in payment routing.
It should be noted that the preset rules can be ordering rule corresponding with target routing rule, for example, if
Target routing rule is that tranaction costs are minimum, then the preset rules are just to route by sequence from small to large to each available payment
Corresponding desired value is ranked up；If target routing rule is transaction success rate highest, the preset rules are just by from big
Corresponding desired value is routed to each available payment to small sequence to be ranked up.In the present embodiment, the preset rules are according to mesh
Mark the difference of routing rule and different.
Further, it is contemplated that under certain special screnes, payment routing is it is possible that abnormal conditions.The present embodiment mentions
The payment route selecting method of confession is before the calculating for carrying out desired value, the historical data that will also be routed according to each available payment,
Judge payment routing whether (such as bank, which runs, batch causes service ability to decline, and trades the future may appear failure or abnormal conditions
Failure etc.).Specifically, the historical failure rate that server can be routed by obtaining each available payment, low by the historical failure rate
It is routed in the available payment routing of preset threshold as effectively payment；Effective payment is routed into corresponding current routing parameter
It is sent in the objective decision tree-model, determines that each effective payment routes corresponding desired value respectively；By preset rules to each
Effectively payment routes corresponding desired value and is ranked up, and filters out target from effective payment routing according to ranking results
Payment routing is paid.Wherein, the preset threshold can be set according to actual conditions, such as 20%, 30%, and specific value is not
It is restricted.
It will be appreciated that paid even with the target payment routing filtered out from effective payment routing,
It is also the same to there is the possibility for payment exception occur.Therefore in order to guarantee in most cases, payment can be favorably accomplished,
In the present embodiment, server be can also continue to according to the ranking results after filtering out target payment routing from remaining
An effectively payment routing is effectively chosen in payment routing is used as alternate routing；Detect by the target payment route into
It is that the alternate routing is paid by the target payment route handoff when row payment occurs abnormal.Certain spare road
By quantity and be only limitted to one, can be a plurality of, and when there are a plurality of alternate routing, server can be tied according to sequence
Fruit preferentially chooses the forward corresponding alternate routing of desired value that sorts and switches over, and that guarantees payment goes on smoothly.
The current routing parameter that the present embodiment is routed by obtaining each available payment；Current routing parameter is sent to target
In decision-tree model, determine that each available payment routes corresponding desired value respectively；By preset rules to each available payment routing pair
The desired value answered is ranked up, and can be carried out from several with target payment routing is filtered out in payment routing according to ranking results
Payment, the target payment routing so as to ensure to filter out is payment routing optimal under target routing rule, and then more preferable
It is that user provides payment services.
In addition, the embodiment of the present invention also proposes a kind of storage medium, payment route selecting is stored on the storage medium
Program, the payment route selecting program realize the step of payment route selecting method as described above when being executed by processor
Suddenly.
It is the structural block diagram of present invention payment route selecting device first embodiment referring to Fig. 5, Fig. 5.
As shown in figure 5, the payment route selecting device that the embodiment of the present invention also proposes includes: ask respond module 501, mould
Type determining module 502 and routing determining module 503；
The ask respond module 501, for receiving the current payment request of user's transmission, payment can be used by obtaining several
Routing；
It should be understood that the current payment request can be the payment request that user is sent by client, and described
Current payment request also can refer to several payment requests that same timing node payment route selecting device receives, when payment routes
Selecting device when receiving several payment requests can first to these payment requests carry out clustering, and based on the analysis results into
Then row classification obtains the corresponding available payment routing of sorted each payment request again.It is described to be can be with payment routing
Current time is in the payment route or channel of connected state.
Further, the ask respond module 501 is also used to receive the current payment request of user's transmission, extracts institute
State the user identifier carried in current payment request；Several corresponding with the user identifier are searched in the first mapping relations
Payment to be selected routes, and storage has the corresponding relationship between user identifier and payment routing to be selected in first mapping relations；Inspection
It is current whether in connected state to survey each payment routing to be selected, by all payment to be selected routings in connected state as available
Payment routing.
Wherein, the user identifier can be the corresponding identification code of each application program (or client), which can be pre-
It first configures, and its form of expression may include number, letter, and/or combination of digits plus letters etc., the present embodiment does not limit this
System.First mapping relations can be the corresponding relationship between the user identifier pre-established and payment routing to be selected, described
It is user identifier that end source is mapped in first mapping relations, and target side source is payment to be selected routing.
The model determining module 502, for searching mesh corresponding with the current payment request in the preset database
Mark decision-tree model；
It should be noted that the presetting database can be the data space pre-established, can be used for storing not
(such as transaction success rate pays consumption, transaction when routing availability, trading for same decision-tree model and all kinds of historical trading datas
Expense etc.).
In addition, the model determining module 502, is also used to obtain all preset payment routings from the presetting database
Corresponding historical trading data；Neural network model is trained according to the historical trading data, and according to training result
Determine several routing rule；The several routing rule is respectively put into decision tree to construct different routing rules pair
The decision-tree model answered.It should be understood that the preset payment routing can be all established pay lines in financial system
Road or channel.Being trained according to the historical trading data to neural network model specifically can be according to historical trading data
In transaction success rate, payment routing availability, transaction when consumption and/or the parameters such as tranaction costs neural network model is instructed
Practice.
The routing determining module 503, for payment road can be used to described several based on the objective decision tree-model
It is paid by being screened, and by the available payment filtered out routing as target payment routing.
In the concrete realization, the routing determining module 503 is determining the corresponding decision-tree model of current payment request
Afterwards, obtain in advance several can be screened with payment routing according to the decision-tree model, then by filtering out
Target payment routing is paid.
The present embodiment pays the current payment request that route selecting device is sent by receiving user, and acquisition several available
Payment routing；Objective decision tree-model corresponding with current payment request is searched in the preset database；Based on objective decision tree
Model can screen several with payment routing, and the available payment filtered out routing is carried out as target payment routing
Then payment is led to by first determining available payment routing and decision-tree model thus according to the current payment request received
Decision-tree model is crossed the available payment routing got screen and is paid by the payment that filters out routing, thus
The payment routing that can guarantee that finishing screen is selected has stronger specific aim and higher reliability, realizes payment routing
Rapid configuration improves payment experience.
The present invention pays the other embodiments of route selecting device or specific implementation and can refer to above-mentioned each method and implement
Example, details are not described herein again.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
(in such as read-only memory (Read Only Memory, ROM/RAM, magnetic disk, CD), including some instructions are used so that one
Terminal device (can be mobile phone, computer, server, air conditioner or the network equipment etc.) executes each embodiment of the present invention
The method.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of payment route selecting method, which is characterized in that the described method includes:
The current payment request that user sends is received, payment routing can be used by obtaining several；
Objective decision tree-model corresponding with the current payment request is searched in the preset database；
The available branch that described several can be screened with payment routing, and will be filtered out based on the objective decision tree-model
Routing is paid to be paid as target payment routing.
2. the method as described in claim 1, which is characterized in that the current payment request for receiving user and sending, if obtaining
The step of dry item can be with payment routing, comprising:
The current payment request that user sends is received, the user identifier carried in the current payment request is extracted；
Several payment routings to be selected corresponding with the user identifier are searched in the first mapping relations, first mapping is closed
Storage has the corresponding relationship between user identifier and payment routing to be selected in system；
It is current whether in connected state to detect each payment routing to be selected, all payments to be selected in connected state are routed and are made
For available payment routing.
3. method according to claim 2, which is characterized in that the current payment request for receiving user and sending, if obtaining
Before the step of dry item can be routed with payment, the method also includes:
All preset payments are obtained from the presetting database routes corresponding historical trading data；
Neural network model is trained according to the historical trading data, and several routing is determined according to training result
Rule；
The several routing rule is respectively put into decision tree to construct the corresponding decision-tree model of different routing rules.
4. method as claimed in claim 3, which is characterized in that described search in the preset database is asked with the current payment
The step of seeking corresponding objective decision tree-model, comprising:
The corresponding target service type of the current payment request is obtained, and determines that target routes according to the target service type
Rule；
According to the target routing rule, searched in the preset database by the second mapping relations and the target routing rule
Corresponding objective decision tree-model, in second mapping relations storage have between routing rule and decision-tree model to pass
System.
5. method as claimed in claim 4, which is characterized in that described to be based on the objective decision tree-model to described several
It can be screened with payment routing, and the step of available payment filtered out routing is paid as target payment routing,
Include:
Obtain the current routing parameter of each available payment routing；
The current routing parameter is sent in the objective decision tree-model, determines that each available payment routing is corresponding respectively
Desired value；
It routes corresponding desired value to each available payment by preset rules to be ranked up, and according to ranking results from described several
It can be paid with target payment routing is filtered out in payment routing.
6. method as claimed in claim 5, which is characterized in that described the current routing parameter is sent to the target to determine
In plan tree-model, the step of each available payment routes corresponding desired value is determined respectively, comprising:
The historical failure rate of each available payment routing is obtained, the available payment by the historical failure rate lower than preset threshold routes
As effective payment routing；
Effective payment is routed corresponding current routing parameter to be sent in the objective decision tree-model, is determined respectively each
Effectively payment routes corresponding desired value；
Correspondingly, described corresponding desired value is routed to each available payment by preset rules to be ranked up, and according to ranking results
From described several the step of being paid can be routed with target payment is filtered out in payment routing, comprising:
It routes corresponding desired value to each effective payment by preset rules to be ranked up, and according to ranking results from effective branch
Pay routing in filter out target payment routing paid.
7. method as claimed in claim 6, which is characterized in that described to route the corresponding phase to each effective payment by preset rules
Prestige value is ranked up, and is filtered out target payment routing from effective payment routing according to ranking results and carried out paying it
Afterwards, the method also includes:
An effectively payment routing, which is chosen, from remaining effective payment routing according to the ranking results is used as alternate routing；
It is institute by target payment route handoff when detecting that carrying out payment by target payment routing occurs abnormal
Alternate routing is stated to be paid.
8. a kind of payment route selecting device, which is characterized in that described device includes: ask respond module, model determining module
With routing determining module；
The ask respond module, for receiving the current payment request of user's transmission, payment routing can be used by obtaining several；
The model determining module, for searching objective decision tree corresponding with the current payment request in the preset database
Model；
The routing determining module, for that can be sieved with payment routing based on the objective decision tree-model to described several
Choosing, and the available payment filtered out routing is paid as target payment routing.
9. a kind of payment route selecting equipment, which is characterized in that the equipment includes: memory, processor and is stored in described
On memory and the payment route selecting program that can run on the processor, the payment route selecting program are configured to reality
Now the step of payment route selecting method as described in any one of claims 1 to 7.
10. a kind of storage medium, which is characterized in that be stored with payment route selecting program, the payment on the storage medium
Route selecting program realizes the step of payment route selecting method as described in any one of claim 1 to 7 when being executed by processor
Suddenly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811060994.0A CN109670797A (en) | 2018-09-11 | 2018-09-11 | Pay route selecting method, apparatus, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811060994.0A CN109670797A (en) | 2018-09-11 | 2018-09-11 | Pay route selecting method, apparatus, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109670797A true CN109670797A (en) | 2019-04-23 |
Family
ID=66141602
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811060994.0A Pending CN109670797A (en) | 2018-09-11 | 2018-09-11 | Pay route selecting method, apparatus, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109670797A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110378790A (en) * | 2019-07-19 | 2019-10-25 | 中国银行股份有限公司 | Transaction data call method and system |
| CN110414986A (en) * | 2019-06-21 | 2019-11-05 | 中国平安财产保险股份有限公司 | Cash register method for routing foundation and relevant device based on big data analysis |
| CN111080276A (en) * | 2019-12-31 | 2020-04-28 | 北京三快在线科技有限公司 | Payment method, device, equipment and storage medium for withholding order |
| CN111260371A (en) * | 2020-01-17 | 2020-06-09 | 中信银行股份有限公司 | Recommendation method and device for domestic service route, storage medium and electronic equipment |
| CN111583030A (en) * | 2020-05-12 | 2020-08-25 | 新分享科技服务(深圳)有限公司 | Payment routing method and device |
| CN111612442A (en) * | 2020-05-28 | 2020-09-01 | 杭州一骑轻尘信息技术有限公司 | Payment route configuration method, device and system |
| CN112017028A (en) * | 2020-08-28 | 2020-12-01 | 中国银行股份有限公司 | Remittance path recommendation method and device |
| CN112488691A (en) * | 2020-11-30 | 2021-03-12 | 乐刷科技有限公司 | Merchant settlement charging method and device and computer readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105741088A (en) * | 2016-01-27 | 2016-07-06 | 广州唯品会信息科技有限公司 | Routing matching payment method and device |
| CN107292598A (en) * | 2017-05-31 | 2017-10-24 | 杭州大搜车汽车服务有限公司 | One kind pays method for routing and pays route middleware |
| CN107705118A (en) * | 2017-09-19 | 2018-02-16 | 深圳金融电子结算中心有限公司 | Transaction payment method, system, server and storage medium based on channel route |
| CN107967530A (en) * | 2017-06-22 | 2018-04-27 | 深圳市盈华讯方通信技术有限公司 | Channel of disbursement based on data analysis elects method and its system |
| CN108009805A (en) * | 2017-10-24 | 2018-05-08 | 广东康美通信息服务有限公司 | A kind of payment processing method, storage medium, device and payment route system |
-
2018
- 2018-09-11 CN CN201811060994.0A patent/CN109670797A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105741088A (en) * | 2016-01-27 | 2016-07-06 | 广州唯品会信息科技有限公司 | Routing matching payment method and device |
| CN107292598A (en) * | 2017-05-31 | 2017-10-24 | 杭州大搜车汽车服务有限公司 | One kind pays method for routing and pays route middleware |
| CN107967530A (en) * | 2017-06-22 | 2018-04-27 | 深圳市盈华讯方通信技术有限公司 | Channel of disbursement based on data analysis elects method and its system |
| CN107705118A (en) * | 2017-09-19 | 2018-02-16 | 深圳金融电子结算中心有限公司 | Transaction payment method, system, server and storage medium based on channel route |
| CN108009805A (en) * | 2017-10-24 | 2018-05-08 | 广东康美通信息服务有限公司 | A kind of payment processing method, storage medium, device and payment route system |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110414986A (en) * | 2019-06-21 | 2019-11-05 | 中国平安财产保险股份有限公司 | Cash register method for routing foundation and relevant device based on big data analysis |
| CN110378790A (en) * | 2019-07-19 | 2019-10-25 | 中国银行股份有限公司 | Transaction data call method and system |
| CN111080276A (en) * | 2019-12-31 | 2020-04-28 | 北京三快在线科技有限公司 | Payment method, device, equipment and storage medium for withholding order |
| CN111260371A (en) * | 2020-01-17 | 2020-06-09 | 中信银行股份有限公司 | Recommendation method and device for domestic service route, storage medium and electronic equipment |
| CN111583030A (en) * | 2020-05-12 | 2020-08-25 | 新分享科技服务(深圳)有限公司 | Payment routing method and device |
| CN111583030B (en) * | 2020-05-12 | 2024-03-19 | 新分享科技服务(深圳)有限公司 | Payment routing method and device |
| CN111612442A (en) * | 2020-05-28 | 2020-09-01 | 杭州一骑轻尘信息技术有限公司 | Payment route configuration method, device and system |
| CN112017028A (en) * | 2020-08-28 | 2020-12-01 | 中国银行股份有限公司 | Remittance path recommendation method and device |
| CN112488691A (en) * | 2020-11-30 | 2021-03-12 | 乐刷科技有限公司 | Merchant settlement charging method and device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109670797A (en) | Pay route selecting method, apparatus, equipment and storage medium | |
| CN104866484B (en) | A kind of data processing method and device | |
| CN106506454A (en) | Fraud business recognition method and device | |
| CN109615122B (en) | Distribution range generation method and device, electronic equipment and storage medium | |
| CN103679498B (en) | A kind of information-pushing method and its system to the network terminal | |
| CN106875078A (en) | transaction risk detection method, device and equipment | |
| CN105719045A (en) | Retention risk determiner | |
| CN102081774A (en) | Card-raising identification method and system | |
| CN109857936A (en) | A kind of big data collection analysis and service system | |
| CN110288350A (en) | User's Value Prediction Methods, device, equipment and storage medium | |
| CN109636013A (en) | Dispense generation method, device, electronic equipment and the storage medium of range | |
| CN108959048A (en) | The method for analyzing performance of modular environment, device and can storage medium | |
| CN108429776A (en) | Method for pushing, device, client, interactive device and the system of network object | |
| CN109769007A (en) | Serve resources management system and method | |
| KR100469495B1 (en) | Method for marketing support of service using geographic | |
| CN113052505A (en) | Cross-border travel recommendation method, device and equipment based on artificial intelligence | |
| CN109492863A (en) | The automatic generation method and device of financial document | |
| CN110197426A (en) | A kind of method for building up of credit scoring model, device and readable storage medium storing program for executing | |
| CN108898308A (en) | Methods of risk assessment, device, server and readable storage medium storing program for executing | |
| CN110009347A (en) | A kind of method and device of block chain Transaction Information audit | |
| CN110264171A (en) | Distributed bill processing method, device, equipment and computer readable storage medium | |
| CN109670964A (en) | Investment risk evaluating method, equipment, storage medium and device | |
| CN111626864B (en) | Information pushing method and device, storage medium and electronic device | |
| CN108280651A (en) | A kind of merchandise items checking method, apparatus and system | |
| CN109636611A (en) | Clear acquisition methods, server, storage medium and the device of configuration information |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190423 |