CN108932614B - Payment channel routing method and system - Google Patents

Payment channel routing method and system Download PDF

Info

Publication number
CN108932614B
CN108932614B CN201810834209.6A CN201810834209A CN108932614B CN 108932614 B CN108932614 B CN 108932614B CN 201810834209 A CN201810834209 A CN 201810834209A CN 108932614 B CN108932614 B CN 108932614B
Authority
CN
China
Prior art keywords
payment
channel
vector
service
service level
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.)
Active
Application number
CN201810834209.6A
Other languages
Chinese (zh)
Other versions
CN108932614A (en
Inventor
徐艳婷
史佳乐
张鑫
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Payment & Clearing Network Co ltd Cpcn
Original Assignee
China Payment & Clearing Network Co ltd Cpcn
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Payment & Clearing Network Co ltd Cpcn filed Critical China Payment & Clearing Network Co ltd Cpcn
Priority to CN201810834209.6A priority Critical patent/CN108932614B/en
Publication of CN108932614A publication Critical patent/CN108932614A/en
Application granted granted Critical
Publication of CN108932614B publication Critical patent/CN108932614B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06Q20/08—Payment architectures
    • G06Q20/085—Payment architectures involving remote charge determination or related payment systems
    • 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
    • G06Q20/08—Payment architectures
    • G06Q20/12—Payment architectures specially adapted for electronic shopping systems

Abstract

The invention discloses a payment channel routing method and a payment channel routing system, which can be based on a payment request of a user and a merchantThe service level of the payment system is that a payment channel with cheap price and high quality is dynamically selected to process the payment transaction, so that the payment experience of a user is improved, and the channel use cost of a payment organization is reduced. The method comprises the steps that a first model is built based on basic service parameters of a payment organization accessed to a payment channel, and a second model is built based on quality service parameters; establishing a service level vector QR corresponding to the quality service level of the current merchant by referring to the historical transaction record of the current merchant, wherein the service level vector QR has the same dimension as any vector in the second model; obtaining a payment request of a user, screening a payment channel ID supporting the payment request from the first model, and outputting a corresponding matching vector Qs from the second model based on the payment channel IDi(ii) a According to the service level vector QR and the matching vector QsiAnd calculating and matching the optimal payment channel ID. The system comprises the method provided by the scheme.

Description

Payment channel routing method and system
Technical Field
The invention relates to the technical field of internet payment, in particular to a payment channel routing method and a payment channel routing system.
Background
With the continuous development of internet electronic commerce, online payment is one of the key links and development bottlenecks in the electronic commerce process, and payment organizations such as third-party payment and non-payment clearing platforms provide a feasible implementation approach for online payment. The payment organization is used as a fund 'middle platform' of a buyer and a seller in the transaction process, and realizes network transaction payment by signing and cooperating with various nationwide banks and calling various channel interfaces provided by the banks.
Usually, a payment organization accesses payment clearing channels of all banks in the country, and the transaction limit, the transaction rate, the supported account types, the card types, the transaction success rate and the like of different payment channels are different. How to select a payment channel with good consumer experience, low cost and high success rate from a plurality of payment channels by a payment organization is a key problem in the field of financial payment. Most of the existing payment channel selection methods configure transaction channel routes through preset fixed channels or based on preset channel weight high-low sequences, but the methods do not consider channel real-time states and channel cost, so that on one hand, the channel transaction failure rate is very high, and the experience of consumers is poor; on the other hand, the cost of the selected payment channel is high, which results in high payment transaction cost.
Disclosure of Invention
The invention aims to provide a payment channel routing method and a payment channel routing system, which can dynamically select a cheap and high-quality payment channel to process a payment transaction based on a payment request of a user and the service level of a merchant so as to improve the payment experience of the user and reduce the channel use cost of a payment organization.
In order to achieve the above object, an aspect of the present invention provides a payment channel routing method, including:
establishing a first model based on basic service parameters of a payment organization accessed to a payment channel, and establishing a second model based on quality service parameters;
establishing a service level vector QR corresponding to the quality service level of the current merchant by referring to the historical transaction record of the current merchant, wherein the service level vector QR has the same dimension as any vector in the second model;
obtaining a payment request of a user, screening a payment channel ID supporting the payment request from the first model, and outputting a corresponding matching vector Qs from the second model based on the payment channel IDi；
According to the service level vector QR and the matching vector QsiAnd calculating and matching the optimal payment channel ID.
Preferably, the first model is a matrix of n × m and the second model is a matrix of n × h;
n is the number of payment channel IDs accessed by a payment organization, m is the number of basic service parameters mapped by the payment channel IDs, and the basic service parameters corresponding to the ith payment channel comprise one or more of service type, quota limit, support card type, support account type and bank name;
h is the quantity of quality service parameters mapped by the payment channel ID, and the quality service parameters corresponding to the ith payment channel represent the channel payment cost score and t1Time slot channel average return time score, t2Time slot channel average return time score, t1Time slot channel payment success rate score and t2The time slot lane payment success score.
Preferably, the payment cost score of the ith payment channel is calculated by the formula
Figure BDA0001744127780000021
The calculation formula of the average return time score of the ith payment channel in the t period is as follows:
Figure BDA0001744127780000022
wherein, atiAverage return time, μ, for the ith payment channel during the most recent t periodtiPay the disk return time mean, σ, of channel i in the most recent t periodtiPaying the return time variance value of the ith channel in the latest t period;
the calculation formula of the payment success rate score of the ith payment channel in the t period is as follows:
Figure BDA0001744127780000023
wherein si is the state of the latest transaction of the ith payment channel,
Figure BDA0001744127780000024
pay for the ith channel the total number of transactions in the last t period,
Figure BDA0001744127780000031
and paying the number of successful transactions in the latest t minutes for the ith channel.
Further, the method for establishing a service level vector QR corresponding to the quality service level of the current merchant by referring to the historical transaction record of the current merchant, wherein the service level vector QR has the same dimension as any vector in the second model comprises the following steps:
extracting historical transaction records of the current merchant from a database, analyzing sensitivity to payment cost, t for the historical transaction records1Sensitivity of time slot channel average return time to t2Sensitivity of time slot channel average return time to t1Sensitivity to time slot lane payment success rate, to t2Sensitivity of time interval channel payment success rate;
and correspondingly assigning values according to the analysis result of the historical transaction record to obtain the service level vector QR.
Preferably, a payment request of a user is obtained, a payment channel ID supporting the payment request is screened out from the first model, and meanwhile, a corresponding matching vector Qs is output from the second model based on the payment channel IDiThe method comprises the following steps:
acquiring a payment request of a user, and extracting a payment transaction message;
extracting basic service requirement parameters from the payment transaction message, wherein the basic service requirement parameters comprise one or more of a payment organization ID, a service type, a quota limit, a support card type, a support account type and a bank name;
generating a payment demand vector BR based on the basic service demand parameter;
screening out a vector BS matched with the demand vector BR from the first modeliRecording the corresponding payment channel ID, and outputting the corresponding matching vector Qs from the second model based on the payment channel IDi。
Further, screening out a vector BS matched with the demand vector BR from the first modeliRecording the corresponding payment channel ID, and outputting the corresponding matching vector Qs from the second model based on the payment channel IDiThe method comprises the following steps:
by matching the demand vector BR with the vector BS corresponding to the ith payment channel in the first modeliPerforming dot product operation, when | | | BR. BSiWhen | | | BR | |, screen out the vector BS equal to demand vector BR lengthi；
Counting the vector BS until all the vector operations of the first model are completediA corresponding payment channel ID;
correspondingly outputting a matching vector Qs from the second model based on the screened payment channel IDi。
Preferably, the method is based on the service level vector QR and the matching vector QsiThe method for calculating and matching the optimal payment channel ID comprises the following steps:
using optimal channel calculation formula
Figure BDA0001744127780000041
Calculating the service level vector QR and each matching vector Qs respectivelyiWherein f is the number of screened payment channel IDs, qrjFor the jth basic service element, qs, in the service level vector QRijMatching vector Qs corresponding to ith payment channeliThe jth quality of service element;
and selecting the payment channel ID corresponding to the maximum value from the similarity values as an optimal channel.
Compared with the prior art, the payment channel routing method provided by the invention has the following beneficial effects:
the method comprises the steps of obtaining payment channels accessed by a current payment organization, constructing a first model reflecting the basic service capability of each payment channel by analyzing the basic service parameters of each payment channel, and constructing a second model reflecting the quality service capability of each payment channel by analyzing the quality service parameters of each payment channel, wherein the basic service parameters are basic elements of the payment channel which can complete the payment transaction, namely whether the transaction request is supported or not, and generally comprise a service type, a limit amount, a support card type, a support account type, a bank name and the like; the quality service parameters are elements for evaluating the quality of the payment transaction service completed by the payment channel, and are used for reflecting the payment experience of the user or the payment organization, and generally include payment cost, response time, payment success rate, and the like.
In addition, the service level of the current merchant is graded according to the historical transaction record of the current merchant, and the grade is obtainedIn actual operation, the value of the service level vector QR can be manually adjusted by a payment organization according to the strategic relationship of a merchant, when a payment request of a user is received after the first model, the second model and the service level vector QR are determined, a payment channel ID supporting the payment request is screened from the first model, and then a corresponding matching vector Qs is found from the second model based on the screened payment channel IDiAnd then, respectively calculating the similarity values of the service level vector QR and each matching vector by using an optimal channel calculation formula, extracting the maximum similarity value, setting the corresponding payment channel ID as the optimal payment channel ID, and processing the payment request transaction.
Therefore, as the payment transaction continuously occurs, the historical transaction record of the current merchant also dynamically changes, so that the payment channel supporting the payment transaction also dynamically changes, and in order to ensure that each payment transaction can bring the best payment experience to the user and reduce the channel cost of the payment organization as much as possible, the service level vector QR of the merchant is updated in real time based on the dynamically changed historical transaction record, and the matching vector Qs with the maximum similarity value is screened from the dynamically changed second modeliThe payment transaction is completed by using the optimal payment channel, so that the stability of the payment service is improved, the cost reduction and the efficiency improvement of a payment organization are facilitated, and the continuous development and the continuous operation of the business are realized.
Another aspect of the present invention provides a payment channel routing system, which is applied to the payment channel routing method in the foregoing technical solution, and the system includes:
the payment organization comprises a modeling unit and a quality service unit, wherein the modeling unit is used for constructing a first model based on basic service parameters of a payment organization accessed to a payment channel and constructing a second model based on quality service parameters;
the service level evaluation unit is used for establishing a service level vector QR corresponding to the quality service level of the current commercial tenant by referring to the historical transaction record of the current commercial tenant, and the service level vector QR has the same dimension as any vector in the second model;
a basic capability screening unit for screening the basic capability,the system is used for acquiring a payment request of a user, screening a payment channel ID supporting the payment request from the first model, and outputting a corresponding matching vector Qs from the second model based on the payment channel IDi；
An optimal channel selection unit for selecting the optimal channel according to the service level vector QR and the matching vector QsiAnd calculating and matching the optimal payment channel ID.
Preferably, the service level assessment unit comprises a first extraction module, a sensitivity setting module and a value assignment module;
the first extraction module is used for extracting the historical transaction records of the current payment organization from a database;
the sensitivity setting module is used for extracting the historical transaction record of the current merchant from the database, and analyzing the sensitivity to the payment cost and the sensitivity to t from the historical transaction record1Sensitivity of time slot channel average return time to t2Sensitivity of time slot channel average return time to t1Sensitivity to time slot lane payment success rate, to t2Sensitivity of time interval channel payment success rate;
and the assignment module is used for assigning values correspondingly according to the analysis result of the historical transaction record to obtain the service level vector QR.
Preferably, the basic capability screening unit comprises a payment request acquisition module, a second extraction module, a transaction requirement conversion module and a matching screening module;
the payment request acquisition module is used for acquiring a payment request of a user and extracting a payment transaction message;
the second extraction module is used for extracting basic service requirement parameters from the payment transaction message, wherein the basic service requirement parameters comprise one or more of service type, quota limit, support card type, support account type and bank name;
the transaction demand conversion module is used for generating a payment demand vector BR based on the basic service demand parameter;
the matching screening module is used for screening the first modelScreening out the vector BS matched with the demand vector BRiRecording the corresponding payment channel ID, and outputting the corresponding matching vector Qs from the second model based on the payment channel IDi。
Compared with the prior art, the beneficial effects of the payment channel routing system provided by the invention are the same as those of the payment channel routing method provided by the technical scheme, and are not repeated herein.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a schematic flow chart illustrating a payment channel routing method according to an embodiment of the present invention;
fig. 2 is a block diagram of a payment channel routing system according to a second embodiment of the present invention.
Reference numerals:
1-modeling unit, 2-service level evaluation unit;
3-basic capability screening unit, 4-optimal channel selection unit;
21-a first extraction module, 22-a sensitivity setting module;
23-assignment module, 31-payment request acquisition module;
32-a second extraction module, 33-a transaction requirement conversion module;
34-match filter module.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
Fig. 1 is a schematic flow chart of a payment channel routing method according to an embodiment of the present invention. Referring to fig. 1, the present embodiment provides a payment channel routing method, including:
establishing a first model based on basic service parameters of a payment organization accessed to a payment channel, and establishing a second model based on quality service parameters; establishing a service level vector QR corresponding to the quality service level of the current merchant by referring to the historical transaction record of the current merchant, wherein the service level vector QR has the same dimension as any vector in the second model; obtaining a payment request of a user, screening a payment channel ID supporting the payment request from the first model, and outputting a corresponding matching vector Qs from the second model based on the payment channel IDi(ii) a According to the service level vector QR and the matching vector QsiAnd calculating and matching the optimal payment channel ID.
In specific implementation, a payment channel accessed by a current payment organization is obtained, a first model reflecting the basic service capability of each payment channel is constructed by analyzing the basic service parameters of each payment channel, and a second model reflecting the quality service capability of each payment channel is constructed by analyzing the quality service parameters of each payment channel, wherein the basic service parameters are basic elements of the payment channel which can complete the payment transaction, namely whether the transaction request is supported or not, and generally comprise a service type, a limit amount, a support card type, a support account type, a bank name and the like; the quality service parameters are elements for evaluating the quality of the payment transaction service completed by the payment channel, and are used for reflecting the payment experience of the user or the payment organization, and generally include payment cost, response time, payment success rate, and the like.
In addition, the service level of the current merchant is graded according to the historical transaction record of the current merchant, and the grading result is converted into a service level vector QR, wherein in the actual operation, the service level vector QR is obtainedThe value can also be manually adjusted by a payment organization according to the strategic relationship of merchants, when a payment request of a user is received after a first model, a second model and a service level vector QR are determined, a payment channel ID supporting the payment request is screened from the first model, and then a corresponding matching vector Qs is found from the second model based on the screened payment channel IDiAnd then, respectively calculating the similarity values of the service level vector QR and each matching vector by using an optimal channel calculation formula, extracting the maximum similarity value, setting the corresponding payment channel ID as the optimal payment channel ID, and processing the payment request transaction.
Therefore, as the payment transaction continuously occurs, the historical transaction record of the current merchant also dynamically changes, so that the payment channel supporting the payment transaction also dynamically changes, and in order to ensure that each payment transaction can bring the best payment experience to the user and reduce the channel cost of the payment organization as much as possible, the service level vector QR of the merchant is updated in real time based on the dynamically changed historical transaction record, and the matching vector Qs with the maximum similarity value is screened from the dynamically changed second modeliThe payment transaction is completed by using the optimal payment channel, so that the stability of the payment service is improved, the cost reduction and the efficiency improvement of a payment organization are facilitated, and the continuous development and the continuous operation of the business are realized.
Illustratively, the first model is a matrix of n m, and the second model is a matrix of n h; n is the number of payment channel IDs accessed by a payment organization, m is the number of basic service parameters mapped by the payment channel IDs, and the basic service parameters corresponding to the ith payment channel comprise one or more of service type, quota limit, support card type, support account type and bank name; h is the quantity of quality service parameters mapped by the ID of the payment channel, and the quality service parameters corresponding to the ith payment channel represent the payment cost score and t of the channel1Time slot channel average return time score, t2Time slot channel average return time score, t1Time slot channel payment success rate score and t2The time slot lane payment success score.
In specific implementation, the basic service vector corresponding to the ith payment channel in the first model is as follows:
BSi＝
[BTi1，…，BTip，AMi1，…，AMiq，ACi1，…ACir，CTi1，…CTis，BIDi1，…，BIDit]；
the basic service vector is 1 × m, where m is p + q + r + s + t, it should be noted that p, q, r, s, and t are the number of feature values corresponding to each basic service parameter, BT represents a service type, and if the service type includes BT paymenti1Query BTi2Verification of BTi3If the type is 3, the value of p is 3; AM represents the quota limit, if the quota limit comprises [1, 5000 ]]AMi1、[5000，10000]AMi2、[10000，50000]AMi3、[500000，MAX]AMi4If the sum is 4 grades of quota, the value of q is corresponding to 4; the AC represents a supported card type, if the supported card type comprises a personal account ACi1Enterprise account ACi2In the 2 types, the value of r is 2; CT represents a support account type, if the support account type includes debit card CTi1Credit card CTi2For these 2 types, s takes the value of 2; BID is the name of the bank, if including BID of China Banki1BID of agricultural banki2BID of industrial and commercial banki3BID for building banki4BID for central banki5And the value of t is 5 for the 5 banks. In the actual operation process, the number of items and feature values of the basic service parameters is not limited in this embodiment, and those skilled in the art can freely increase and decrease according to the needs.
The quality service vector corresponding to the ith payment channel in the second model is as follows:
QSi＝[Coi，SuRt1，SuRt2，RpTt1，RpTt2](ii) a Wherein, CoiRepresenting a channel payment cost score, SuRt1 representing t1Time interval channel average response time score, SuRt2 for t2Time interval channel average response time score, RpTt1 denotes t1Time period channel payment success rate score, RpTt2 denotes t2Time slot channel paymentAnd (6) scoring the success rate.
It can be understood that the first model is a 0-1 matrix, and the parameter value is 0 or 1, where 1 represents support and 0 represents non-support; the value of the second model parameter is [0,1], and the closer to 1, the better the service quality of the parameter is.
It should be noted that, in the above embodiment, the formula for calculating the payment cost score of the ith payment channel is
Figure BDA0001744127780000091
Among them, CostiPaying the channel payment cost for the ith channel.
The calculation method of the average closing time score of the ith payment channel in the t period comprises the steps of obtaining the average closing time of the t period through historical trading closing time of each channel, calculating the average value and the variance of the t period, and updating the closing time score of the t period in the latest t period through a probability formula according to the closing time of the latest trading, wherein the calculation formula is
Figure BDA0001744127780000092
Wherein, atiAverage return time, μ, for the ith payment channel during the most recent t periodtiPay the disk return time mean, σ, of channel i in the most recent t periodtiPaying the return time variance value of the ith channel in the latest t period;
the calculation method of the payment success rate score of the ith payment channel in the t period comprises the following steps of calculating the payment success rate of the payment channel in the latest t period according to the state of the historical transaction of each channel, and then updating the channel success rate in the latest t period according to the state of the latest payment transaction, wherein the calculation formula is as follows:
Figure BDA0001744127780000101
wherein si is the state of the latest transaction of the ith payment channel,
Figure BDA0001744127780000102
total transaction pen for ith payment channel in recent t periodThe number of the first and second groups is,
Figure BDA0001744127780000103
and paying the number of successful transactions in the latest t minutes for the ith channel.
Further, in the above embodiment, the method for establishing the service level vector QR corresponding to the quality service level of the current merchant by referring to the historical transaction record of the current merchant, where the service level vector QR and any vector in the second model have the same dimension includes:
extracting historical transaction records of the current merchant from a database, analyzing sensitivity to payment cost, t for the historical transaction records1Sensitivity of time slot channel average return time to t2Sensitivity of time slot channel average return time to t1Sensitivity to time slot lane payment success rate, to t2Sensitivity of time interval channel payment success rate; and correspondingly assigning values according to the analysis result of the historical transaction record to obtain the service level vector QR.
It should be emphasized that, in actual operation, besides the above method of obtaining the service level vector QR by referring to the historical transaction record assignment of the current merchant, the service level vector QR may be manually adjusted by the payment organization according to the strategic relationship of the merchant, so as to increase the flexibility of assignment.
In specific implementation, the method for obtaining the service level vector QR by assigning the historical transaction records of the current merchants comprises the following steps of extracting the historical transaction records of all merchants from a database for statistical analysis, correspondingly dividing the quality service levels of all merchants into A, B, C, D, E levels in total according to data such as transaction amount and transaction amount in a certain time period in the historical transaction records, and manually assigning the merchants falling into the corresponding levels to form the service level vector. The above assignment range is [ -1, 1], and the closer the assignment result is to 1, the higher the sensitivity is, the closer to-1, the more the rejection of the index is, such as a defaulting merchant or a risk event, etc., the closer to 0, the lower the sensitivity is, and when the assignment value is equal to 0, the completely disregarding of the index is represented, and the assignment is usually used for the major high-quality merchant. By rating the quality service level of the current merchant, the configuration of the payment channel of the current merchant can be allocated in real time, and the merchant is forced to optimize the service capability of the merchant; illustratively, the level-to-service level correspondence is as follows:
emphasis on grade a: disregarding payment cost, t1Time period low response time, t2Time period low response time, t1High payment success rate in time period, t2The payment success rate is high in time interval;
grade B is emphasized: disregarding payment cost, t1Time interval lower response time, t2Time interval lower response time, t1High payment success rate in time period, t2The payment success rate is high in time interval;
common grade C: low and medium payment cost, t1Medium response time, t, in time interval2Medium response time, t, in time interval1Higher payment success rate in time period t2The payment success rate is higher in time interval;
ordinary grade D: low payment cost, t1Medium response time, t, in time interval2Medium response time, t, in time interval1Moderate payment success rate, t, in time periods2A medium payment success rate in a time period;
poor E grade: low payment cost, t1Time interval high response time, t2Time interval high response time, t1Time period low payment success rate, t2The time interval is low in payment success rate.
Exemplarily, t1The time period is taken for 3 minutes, t2The time interval is 30 minutes, and vectors formed by manual assignment are as follows;
the service level vector corresponding to the key level A is as follows:
QRA＝[0、0.9、0.9、0.9、0.9]；
the service level vector corresponding to the key B level is as follows:
QRB＝[0、0.8、0.7、0.9、0.9，]；
the service level vector corresponding to the common C level is:
QRC＝[0.6、0.5、0.5、0.8、0.8]；
the service level vector corresponding to the common D level is:
QRD＝[0.9、0.5、0.5、0.5、0.5]；
the service level vector corresponding to the severe E level is:
QRE＝[0.9、0.3、0.3、-0.5、-0.5]。
specifically, in the above embodiment, the payment request of the user is obtained, the payment channel ID supporting the payment request is screened from the first model, and the corresponding matching vector Qs is output from the second model based on the payment channel IDiThe method comprises the following steps:
acquiring a payment request of a user, and extracting a payment transaction message; extracting basic service requirement parameters from the payment transaction message, wherein the basic service requirement parameters comprise one or more of a payment organization ID, a service type, a quota limit, a support card type, a support account type and a bank name; generating a payment demand vector BR based on the basic service demand parameter; screening out a vector BS matched with a demand vector BR from the first modeliRecording the corresponding payment channel ID, and outputting the corresponding matching vector Qs from the second model based on the payment channel IDi。
In specific implementation, a payee merchant can be identified through a merchant ID, a payment channel configured by the payee merchant is called to process the transaction request, basic elements in the transaction request are extracted, wherein the basic elements comprise one or more of service type, quota limit, support card type, support account type and bank name, and a demand vector formed on the basis of the basic elements
BR＝[BT1，...，BTp，AM1，...，AMq，AC1，...，ACr，CT1，...，CTs，BID1，...，BIDt]. The dimension of the demand vector BR is the same as that of the vector BSi in the first model, and the value corresponding to the vector element is 0, which indicates that the demand vector BR is not needed, and 1, which indicates that the demand vector BR is needed. For example, if the user pays 40000 yuan using a debit card of a personal construction bank, the corresponding demand vector BR is [1,0,0,1,1,1,0,1,0, 0,0,0,0,1,0]。
Further, the first model is screened out and selectedVector BS for calculating matching of vector BRiRecording the corresponding payment channel ID, and outputting the corresponding matching vector Qs from the second model based on the payment channel IDiThe method comprises the following steps:
by matching the demand vector BR with the vector BS corresponding to the ith payment channel in the first modeliPerforming dot product operation, when | | | BR. BSiWhen | | | BR | |, screen out the vector BS equal to demand vector BR lengthi(ii) a Until all the vector operations of the first model are completed, counting the vector BSiA corresponding payment channel ID; correspondingly outputting a matching vector Qs from the second model based on the screened payment channel IDi。
Furthermore, the embodiment is based on the service level vector QR and the matching vector QsiThe method for calculating and matching the optimal payment channel ID comprises the following steps:
using optimal channel calculation formula
Figure BDA0001744127780000121
Calculating service grade vector QR and each matching vector QsiWherein f is the number of screened payment channel IDs, qrjFor the jth basic service element, qs, in the service level vector QRijMatching vector Qs corresponding to ith payment channeliThe jth quality of service element; and selecting the payment channel ID corresponding to the maximum value from the similarity values as an optimal channel.
The payment channel with the lowest cost, the lowest response time and the higher success rate can be screened out through the optimal channel calculation formula to process the payment transaction, so that the transaction success rate can be greatly improved, and the payment transaction experience is improved; on the other hand, the most satisfactory payment channel with high quality and low price can be selected by the commercial tenant aiming at the tendency of different commercial tenants to the factors such as channel cost, success rate, return time and the like. The payment channel routing method provided by the embodiment can improve the stability of the payment service, help the payment organization reduce cost and improve efficiency, and maintain the stability of the merchant so as to realize the continuous development and continuous operation of the business.
Example two
Referring to fig. 1 and fig. 2, the present embodiment provides a payment channel routing system, including:
the payment organization comprises a modeling unit 1, a quality service parameter setting unit and a payment channel setting unit, wherein the modeling unit 1 is used for establishing a first model based on basic service parameters of a payment organization accessed to a payment channel and establishing a second model based on the quality service parameters;
the service level evaluation unit 2 is used for establishing a service level vector QR corresponding to the quality service level of the current commercial tenant by referring to the historical transaction record of the current commercial tenant, and the service level vector QR has the same dimension as any vector in the second model;
a basic capability screening unit 3, configured to obtain a payment request of a user, screen a payment channel ID supporting the payment request from the first model, and output a corresponding matching vector Qs from the second model based on the payment channel IDi；
An optimal channel selection unit 4 for selecting the optimal channel according to the service level vector QR and the matching vector QsiAnd calculating and matching the optimal payment channel ID.
Specifically, the service level assessment unit includes a first extraction module 21, a sensitivity setting module 22 and an assignment module 23;
the first extraction module 21 is used for extracting the historical transaction records of the current payment organization from the database;
the sensitivity setting module 22 is used for extracting the historical transaction record of the current merchant from the database, and analyzing the sensitivity to the payment cost and the sensitivity to t from the historical transaction record1Sensitivity of time slot channel average return time to t2Sensitivity of time slot channel average return time to t1Sensitivity to time slot lane payment success rate, to t2Sensitivity of time interval channel payment success rate;
and the assignment module 23 is used for assigning values correspondingly according to the analysis result of the historical transaction record to obtain a service level vector QR.
Specifically, the basic capability screening unit 3 includes a payment request obtaining module 31, a second extracting module 32, a transaction requirement transforming module 33 and a matching screening module 34;
the payment request acquisition module 31 is configured to acquire a payment request of a user and extract a payment transaction message;
the second extraction module 32 is configured to extract basic service requirement parameters from the payment transaction message, where the basic service requirement parameters include one or more of a service type, a quota, a support card type, a support account type, and a bank name;
the transaction demand conversion module 33 is configured to generate a payment demand vector BR based on the basic service demand parameter;
the matching screening module 34 is used for screening out the vector BS matched with the demand vector BR from the first modeliRecording the corresponding payment channel ID, and outputting the corresponding matching vector Qs from the second model based on the payment channel IDi。
Compared with the prior art, the beneficial effects of the payment channel routing system provided by the embodiment of the invention are the same as those of the payment channel routing method provided by the first embodiment, and are not described herein again.
It will be understood by those skilled in the art that all or part of the steps in the method for implementing the invention may be implemented by hardware instructions related to a program, the program may be stored in a computer-readable storage medium, and when executed, the program includes the steps of the method of the embodiment, and the storage medium may be: ROM/RAM, magnetic disks, optical disks, memory cards, and the like.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.

Claims (5)

1. A payment channel routing method, comprising:
establishing a first model based on basic service parameters of a payment organization accessed to a payment channel, and establishing a second model based on quality service parameters;
establishing a service level vector QR corresponding to the quality service level of the current merchant by referring to the historical transaction record of the current merchant, wherein the service level vector QR has the same dimension as any vector in the second model;
obtaining a payment request of a user, screening a payment channel ID supporting the payment request from the first model, and outputting a corresponding matching vector Qs from the second model based on the payment channel IDi；
According to the service level vector QR and the matching vector QsiCalculating and matching an optimal payment channel ID;
obtaining a payment request of a user, screening a payment channel ID supporting the payment request from the first model, and outputting a corresponding matching vector Qs from the second model based on the payment channel IDiThe method comprises the following steps:
acquiring a payment request of a user, and extracting a payment transaction message;
extracting basic service requirement parameters from the payment transaction message, wherein the basic service requirement parameters comprise one or more of a payment organization ID, a service type, a quota limit, a support card type, a support account type and a bank name;
generating a payment demand vector BR based on the basic service demand parameter;
screening out a vector BS matched with the demand vector BR from the first modeliRecording the corresponding payment channel ID, and outputting the corresponding matching vector Qs from the second model based on the payment channel IDi；
Screening out a vector BS matched with the demand vector BR from the first modeliRecording the corresponding payment channel ID, and outputting the corresponding matching vector Qs from the second model based on the payment channel IDiThe method comprises the following steps:
by matching the demand vector BR with the vector BS corresponding to the ith payment channel in the first modeliPerforming dot product operation, when | | | BR. BSiWhen | | | BR | |, screen out the vector BS equal to demand vector BR lengthi；
Counting the vector BS until all the vector operations of the first model are completediA corresponding payment channel ID;
correspondingly outputting a matching vector Qs from the second model based on the screened payment channel IDi；
According to the service level vector QR and the matching vector QsiThe method for calculating and matching the optimal payment channel ID comprises the following steps:
using optimal channel calculation formula
Figure FDA0002692291210000021
Calculating the service level vector QR and each matching vector Qs respectivelyiWherein f is the number of screened payment channel IDs, qrjFor the jth basic service element, qs, in the service level vector QRijMatching vector Qs corresponding to ith payment channeliThe jth quality of service element;
and selecting the payment channel ID corresponding to the maximum value from the similarity values as an optimal channel.
2. The method of claim 1, wherein the first model is a matrix of n x m and the second model is a matrix of n x h;
n is the number of payment channel IDs accessed by a payment organization, m is the number of basic service parameters mapped by the payment channel IDs, and the basic service parameters corresponding to the ith payment channel comprise one or more of service type, quota limit, support card type, support account type and bank name;
h is the quantity of quality service parameters mapped by the payment channel ID, and the quality service parameters corresponding to the ith payment channel represent the channel payment cost score and t1Time slot channel average return time score, t2Time slot channel average return time score, t1Time slot channel payment success rate score and t2The time slot lane payment success score.
3. The method of claim 2, wherein the payment cost score for the ith payment channel is calculated as
Figure FDA0002692291210000022
The calculation formula of the average return time score of the ith payment channel in the t period is as follows:
Figure FDA0002692291210000023
wherein, atiAverage return time, μ, for the ith payment channel during the most recent t periodtiPay the disk return time mean, σ, of channel i in the most recent t periodtiPaying the return time variance value of the ith channel in the latest t period;
the calculation formula of the payment success rate score of the ith payment channel in the t period is as follows:
Figure FDA0002692291210000031
wherein si is the state of the latest transaction of the ith payment channel,
Figure FDA0002692291210000032
pay for the ith channel the total number of transactions in the last t period,
Figure FDA0002692291210000033
and paying the number of successful transactions in the latest t minutes for the ith channel.
4. The method according to claim 1, wherein establishing a service level vector QR corresponding to the quality service level of the current merchant by referring to the historical transaction record of the current merchant, and the method that the service level vector QR has the same dimension as any vector in the second model comprises:
extracting historical transaction records of current merchants from a database, and analyzing the historical transaction recordsSensitivity to payment cost, to t1Sensitivity of time slot channel average return time to t2Sensitivity of time slot channel average return time to t1Sensitivity to time slot lane payment success rate, to t2Sensitivity of time interval channel payment success rate;
and correspondingly assigning values according to the analysis result of the historical transaction record to obtain the service level vector QR.
5. A payment channel routing system, comprising:
the payment organization comprises a modeling unit and a quality service unit, wherein the modeling unit is used for constructing a first model based on basic service parameters of a payment organization accessed to a payment channel and constructing a second model based on quality service parameters;
the service level evaluation unit is used for establishing a service level vector QR corresponding to the quality service level of the current commercial tenant by referring to the historical transaction record of the current commercial tenant, and the service level vector QR has the same dimension as any vector in the second model;
a basic capability screening unit, configured to obtain a payment request of a user, screen a payment channel ID supporting the payment request from the first model, and output a corresponding matching vector Qs from the second model based on the payment channel IDi；
An optimal channel selection unit for selecting the optimal channel according to the service level vector QR and the matching vector QsiCalculating and matching an optimal payment channel ID;
the service level evaluation unit comprises a first extraction module, a sensitivity setting module and a value assignment module;
the first extraction module is used for extracting the historical transaction records of the current payment organization from a database;
the sensitivity setting module is used for extracting the historical transaction record of the current merchant from the database, and analyzing the sensitivity to the payment cost and the sensitivity to t from the historical transaction record1Sensitivity of time slot channel average return time to t2Sensitivity of time slot channel average return time to t1Time interval channel payment success rateSensitivity to t2Sensitivity of time interval channel payment success rate;
the assignment module is used for assigning values correspondingly according to the analysis result of the historical transaction record to obtain the service level vector QR;
the basic capability screening unit comprises a payment request acquisition module, a second extraction module, a transaction requirement conversion module and a matching screening module;
the payment request acquisition module is used for acquiring a payment request of a user and extracting a payment transaction message;
the second extraction module is used for extracting basic service requirement parameters from the payment transaction message, wherein the basic service requirement parameters comprise one or more of service type, quota limit, support card type, support account type and bank name;
the transaction demand conversion module is used for generating a payment demand vector BR based on the basic service demand parameter;
the matching screening module is used for screening out the vector BS matched with the demand vector BR from the first modeliRecording the corresponding payment channel ID, and outputting the corresponding matching vector Qs from the second model based on the payment channel IDi；
According to the service level vector QR and the matching vector QsiThe method for calculating and matching the optimal payment channel ID comprises the following steps:
using optimal channel calculation formula
Figure FDA0002692291210000041
Calculating the service level vector QR and each matching vector Qs respectivelyiWherein f is the number of screened payment channel IDs, qrjFor the jth basic service element, qs, in the service level vector QRijMatching vector Qs corresponding to ith payment channeliThe jth quality of service element;
and selecting the payment channel ID corresponding to the maximum value from the similarity values as an optimal channel.
CN201810834209.6A 2018-07-26 2018-07-26 Payment channel routing method and system Active CN108932614B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810834209.6A CN108932614B (en) 2018-07-26 2018-07-26 Payment channel routing method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810834209.6A CN108932614B (en) 2018-07-26 2018-07-26 Payment channel routing method and system

Publications (2)

Publication Number Publication Date
CN108932614A CN108932614A (en) 2018-12-04
CN108932614B true CN108932614B (en) 2020-12-25

Family

ID=64444739

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810834209.6A Active CN108932614B (en) 2018-07-26 2018-07-26 Payment channel routing method and system

Country Status (1)

Country Link
CN (1) CN108932614B (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109829704A (en) * 2018-12-07 2019-05-31 创发科技有限责任公司 Payment channel configuration method, device and computer readable storage medium
CN109784679A (en) * 2018-12-26 2019-05-21 拉卡拉支付股份有限公司 Settlement channel sequence, settlement method and device
CN110033247B (en) * 2019-01-04 2021-11-05 创新先进技术有限公司 Payment channel recommendation method and system
CN109858894A (en) * 2019-01-16 2019-06-07 深圳壹账通智能科技有限公司 A kind of payment result notification method, device, readable storage medium storing program for executing and server
CN111680998B (en) * 2020-08-17 2023-07-14 南京梦饷网络科技有限公司 Payment routing method, computing device, and computer-readable storage medium
CN113159746A (en) * 2021-05-13 2021-07-23 华世界数字科技(深圳)有限公司 Method and device for distributing payment channel based on merchant attribute
CN115829557A (en) * 2022-12-09 2023-03-21 深圳优讯科技有限公司 Payment channel selection method and device based on fuzzy comprehensive evaluation and related medium

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106845988A (en) * 2017-01-23 2017-06-13 杭州恒生云融网络科技有限公司 method and device for selecting payment channel
CN107871234A (en) * 2017-09-25 2018-04-03 上海壹账通金融科技有限公司 Electric paying method and application server

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE69638018D1 (en) * 1995-02-13 2009-10-15 Intertrust Tech Corp Systems and procedures for managing secure transactions and protecting electronic rights
CA2500881A1 (en) * 2005-03-14 2006-09-14 Cashcode Company Inc. Method and apparatus for optimizing a currency validator/dispenser
US10354237B2 (en) * 2012-12-17 2019-07-16 Capital One Services Llc Systems and methods for effecting personal payment transactions
CN106127460A (en) * 2016-06-15 2016-11-16 携程计算机技术（上海）有限公司 Pay route system and method
CN106127480A (en) * 2016-06-16 2016-11-16 上海携程商务有限公司 transaction payment method and system
CN106600243A (en) * 2016-08-30 2017-04-26 广州云融信息科技有限公司 Mobile payment method and system based on mixed mode
CN107169756B (en) * 2017-05-10 2020-12-08 北京凤凰理理它信息技术有限公司 Payment channel distribution method, device, storage medium and payment routing system
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
CN107346511A (en) * 2017-07-04 2017-11-14 贵州数据宝网络科技有限公司 A kind of big data method for secure transactions

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106845988A (en) * 2017-01-23 2017-06-13 杭州恒生云融网络科技有限公司 method and device for selecting payment channel
CN107871234A (en) * 2017-09-25 2018-04-03 上海壹账通金融科技有限公司 Electric paying method and application server

Also Published As

Publication number Publication date
CN108932614A (en) 2018-12-04

Similar Documents

Publication Publication Date Title
CN108932614B (en) Payment channel routing method and system
JP4244188B2 (en) Method and system for managing a mortgage securities index
US6873972B1 (en) Systems and methods for credit line monitoring
KR100766149B1 (en) Methods and systems for efficiently sampling portfolios for optimal underwriting
KR100766148B1 (en) Methods and systems for quantifying cash flow recovery and risk
KR100746107B1 (en) Cross correlation tool for automated portfolio descriptive statistics
KR101961899B1 (en) Method for providing auto-payment service considering exchange rate between virtual and flat money
US20090254469A1 (en) System for Cash, Expense And Withdrawal Allocation Across Assets and Liabilities to Maximize Net Worth Over a Specified Period
CN108596495A (en) A kind of retail credit business points-scoring system and method
US20100138325A1 (en) Methods and arrangements involving adaptive auditing and rating for disparate data processing
KR20010102455A (en) Rapid valuation of portfolios of assets such as financial instruments
WO2001050310A2 (en) Methods and systems for automated inferred valuation of credit scoring
JP2003526146A (en) Method and system for reducing risk by obtaining evaluation values
US8352358B2 (en) Bankruptcy evaluation service and system
JP6411562B2 (en) Information processing apparatus, information processing method, and program
CN110866821A (en) Financing method and system based on block chain and product life cycle, and storage medium
CN114943582A (en) Information recommendation method and system and recommendation server
CN111461863A (en) Data processing method and device, computer equipment and storage medium
US20020143679A1 (en) Methods and systems for implementing a profitability model
TWI776370B (en) Investment risk scoring method and system for fund commodities
CN109002551A (en) A kind of net value of stock fund determines method and system
JP2002329155A (en) Off-setting settlement processing system
JP6706584B2 (en) Information processing apparatus and information processing method
RU190382U1 (en) Automated device for evaluating the effectiveness of the conversion of industrial areas
JP4213692B2 (en) Loan asset management system

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
GR01 Patent grant
GR01 Patent grant