Intelligent payment routing method and device

Abstract

The embodiment of the invention provides an intelligent payment routing method and device which can be applied to the technical field of computers, and the method comprises the steps: obtaining the attribute information of a plurality of candidate payment channels when a payment routing request is received; for each candidate payment channel, obtaining a target evaluation value of the candidate payment channel based on transaction content associated with the payment routing request and attribute information of the candidate payment channel; selecting a target payment channel meeting the processing condition of the transaction content from the plurality of candidate payment channels based on the respective target evaluation values of the plurality of candidate payment channels; in the embodiment of the invention, the routing decision result corresponding to the payment routing request is generated based on the target payment channel, and the routing decision result is returned, so that the routing accuracy is improved, and the execution efficiency of the subsequent payment transaction request is ensured.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an intelligent payment routing method and device. Background Art

[0002] With the integration and development of computer technology and other fields, more and more scenarios involve payment routing. Among them, payment routing refers to the process of sending payment transaction requests to designated recipients through service channels. In related technologies, the network status or response time is usually used to select a suitable service channel, and then the payment transaction request is sent through the service channel for processing.

[0003] The above solution only relies on network status or response time to screen service channels, which easily selects service channels with low success rates, resulting in reduced processing efficiency of payment transaction requests. Summary of the invention

[0004] The embodiments of the present application provide an intelligent payment routing method and device to improve the execution efficiency of payment transaction requests.

[0005] On the one hand, an embodiment of the present application provides an intelligent payment routing method, the method comprising:

[0006] When receiving a payment routing request, obtaining attribute information of multiple candidate payment channels;

[0007] For each candidate payment channel, based on the transaction content associated with the payment routing request and the attribute information of the candidate payment channel, obtaining a target evaluation value of the candidate payment channel;

[0008] Based on the target evaluation values ​​of the multiple candidate payment channels, a target payment channel that meets the processing conditions of the transaction content is selected from the multiple candidate payment channels;

[0009] A routing decision result corresponding to the payment routing request is generated based on the target payment channel, and the routing decision result is returned.

[0010] Optionally, obtaining a target evaluation value of the candidate payment channel based on the transaction content associated with the payment routing request and the attribute information of the candidate payment channel includes:

[0011] Based on the transaction content associated with the payment routing request and the attribute information of the candidate payment channel, obtaining dimension evaluation values ​​of the candidate payment channel in multiple dimensions;

[0012] The dimension evaluation values ​​of the multiple dimensions are weighted and summed to obtain the target evaluation value of the candidate payment channel.

[0013] Optionally, the dimension evaluation values ​​of the multiple dimensions include: the payment upper limit value of the candidate payment channel, the payment consumption value of the candidate payment channel, the health of the candidate payment channel, the transaction proportion of the candidate payment channel, and the payment amount in the transaction content.

[0014] Optionally, the attribute information of the candidate payment channel includes: a channel payment rule of the candidate payment channel;

[0015] The payment consumption value of the candidate payment channel is obtained in the following manner:

[0016] Based on the transaction content and the channel payment rule of the candidate payment channel, the payment consumption value of the candidate payment channel is obtained.

[0017] Optionally, the attribute information of the candidate payment channel includes: a plurality of routing indicator values ​​associated with the execution status of the candidate payment channel;

[0018] The health of the candidate payment channel is obtained in the following way:

[0019] Performing weighted summation on the multiple routing indicator values ​​to obtain a first state evaluation value;

[0020] Inputting the multiple routing indicator values ​​into a thread regression model for processing to obtain a second state evaluation value;

[0021] The first status evaluation value and the second status evaluation value are averaged to obtain the health of the candidate payment channel.

[0022] Optionally, the multiple routing indicator values ​​include:

[0023] The execution time efficiency information of the candidate payment channel, the execution success rate of the candidate payment channel, the retry rate of the candidate payment channel, and the network time consumption of the candidate payment channel.

[0024] Optionally, selecting a target payment channel that meets the processing condition of the transaction content from the multiple candidate payment channels based on the target evaluation values ​​of each of the multiple candidate payment channels includes:

[0025] Based on the health of the candidate payment channel, obtaining a health grade label of the candidate payment channel;

[0026] When the health level label of the candidate payment channel is an abnormal label, the candidate payment channel is excluded from the multiple candidate payment channels; and based on the target evaluation values ​​of the remaining candidate payment channels respectively, a target payment channel that meets the processing conditions of the transaction content is selected from the remaining candidate payment channels.

[0027] Optionally, when it is determined that the health level label of the candidate payment channel is an abnormal label, regularly perform health detection on the candidate payment channel to obtain the health of the candidate payment channel;

[0028] When the health of the candidate payment channel is greater than a preset threshold, the health grade label of the candidate payment channel is updated.

[0029] Optionally, selecting a target payment channel that meets the processing condition of the transaction content from the multiple candidate payment channels based on the target evaluation values ​​of each of the multiple candidate payment channels includes:

[0030] From the multiple candidate payment channels, a candidate payment channel corresponding to the largest target evaluation value is selected as the target payment channel.

[0031] On the one hand, an embodiment of the present application provides an intelligent payment routing device, the device comprising:

[0032] An acquisition module, used for acquiring attribute information of multiple candidate payment channels upon receiving a payment routing request;

[0033] A processing module, configured to obtain, for each candidate payment channel, a target evaluation value of the candidate payment channel based on the transaction content associated with the payment routing request and the attribute information of the candidate payment channel;

[0034] Based on the target evaluation values ​​of the multiple candidate payment channels, a target payment channel that meets the processing conditions of the transaction content is selected from the multiple candidate payment channels;

[0035] A return module is used to generate a routing decision result corresponding to the payment routing request based on the target payment channel, and return the routing decision result.

[0036] Optionally, the processing module is specifically used for:

[0037] Based on the transaction content associated with the payment routing request and the attribute information of the candidate payment channel, obtaining dimension evaluation values ​​of the candidate payment channel in multiple dimensions;

[0038] The dimension evaluation values ​​of the multiple dimensions are weighted and summed to obtain the target evaluation value of the candidate payment channel.

[0039] Optionally, the dimension evaluation values ​​of the multiple dimensions include: the payment upper limit value of the candidate payment channel, the payment consumption value of the candidate payment channel, the health of the candidate payment channel, the transaction proportion of the candidate payment channel, and the payment amount in the transaction content.

[0040] Optionally, the processing module is specifically used for:

[0041] The attribute information of the candidate payment channel includes: the channel payment rule of the candidate payment channel;

[0042] The payment consumption value of the candidate payment channel is obtained in the following manner:

[0043] Based on the transaction content and the channel payment rule of the candidate payment channel, the payment consumption value of the candidate payment channel is obtained.

[0044] Optionally, the processing module is specifically used for:

[0045] The attribute information of the candidate payment channel includes: a plurality of routing indicator values ​​associated with the execution status of the candidate payment channel;

[0046] The health of the candidate payment channel is obtained in the following way:

[0047] Performing weighted summation on the multiple routing indicator values ​​to obtain a first state evaluation value;

[0048] Inputting the multiple routing indicator values ​​into a thread regression model for processing to obtain a second state evaluation value;

[0049] The first status evaluation value and the second status evaluation value are averaged to obtain the health of the candidate payment channel.

[0050] Optionally, the multiple routing indicator values ​​include:

[0051] The execution time efficiency information of the candidate payment channel, the execution success rate of the candidate payment channel, the retry rate of the candidate payment channel, and the network time consumption of the candidate payment channel.

[0052] Optionally, the processing module is specifically used for:

[0053] Based on the health of the candidate payment channel, obtaining a health grade label of the candidate payment channel;

[0054] When the health level label of the candidate payment channel is an abnormal label, the candidate payment channel is excluded from the multiple candidate payment channels; and based on the target evaluation values ​​of the remaining candidate payment channels respectively, a target payment channel that meets the processing conditions of the transaction content is selected from the remaining candidate payment channels.

[0055] Optionally, the processing module is specifically used for:

[0056] When it is determined that the health level label of the candidate payment channel is an abnormal label, regularly performing health detection on the candidate payment channel to obtain the health level of the candidate payment channel;

[0057] When the health of the candidate payment channel is greater than a preset threshold, the health grade label of the candidate payment channel is updated.

[0058] Optionally, the processing module is specifically used for:

[0059] From the multiple candidate payment channels, a candidate payment channel corresponding to the largest target evaluation value is selected as the target payment channel.

[0060] In one aspect, an embodiment of the present application provides a computer device, including:

[0061] Memory for storing computer programs;

[0062] The processor is used to call the computer program stored in the memory and execute the steps of the above-mentioned intelligent payment routing method according to the obtained program.

[0063] On the one hand, an embodiment of the present application provides a computer-readable storage medium storing a computer program executable by a computer device. When the program is run on a computer, the computer implements the steps of executing the above-mentioned intelligent payment routing method.

[0064] On the one hand, an embodiment of the present application provides a computer program product, including a computer program stored on a computer-readable storage medium, wherein the computer program includes program instructions, and when the program instructions are executed by a computer device, the computer device executes the steps of the above-mentioned intelligent payment routing method.

[0065] In an embodiment of the present application, based on the transaction content associated with the payment routing request and the attribute information of the candidate payment channel, the target evaluation value of the candidate payment channel is obtained, the attribute information of the payment channel is comprehensively considered, and the accuracy of the target evaluation value of the candidate payment channel is improved; based on the target evaluation value of the candidate payment channel, the target payment channel that meets the processing conditions of the transaction content is selected, which improves the accuracy of the routing and further improves the quality and execution efficiency of the payment routing. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0067] Figure 1 A system architecture diagram provided for an embodiment of the present invention;

[0068] Figure 2 A schematic diagram of a flow chart of an intelligent payment routing method provided by an embodiment of the present invention;

[0069] Figure 3 A flowchart of an intelligent payment routing method provided in an embodiment of the present application;

[0070] Figure 4 A flowchart of an intelligent payment routing method provided in an embodiment of the present application;

[0071] Figure 5 A flowchart of an intelligent payment routing method provided in an embodiment of the present application;

[0072] Figure 6 A schematic diagram of the structure of an intelligent payment routing device provided in an embodiment of the present application;

[0073] Figure 7 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0075] The following is a brief introduction to the system architecture diagram applicable to the technical solution of the embodiment of the present application. It should be noted that the process introduced below is only used to illustrate the embodiment of the present application and is not a limitation.

[0076] refer to Figure 1 , which is a system architecture diagram applicable to an embodiment of the present application, and the system architecture at least includes a business processing system 101 and a routing system 102.

[0077] The business processing system 101 and the routing system 102 can be independent physical servers, or a server cluster or distributed system composed of multiple physical servers. They can also be cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), as well as big data and artificial intelligence platforms, but are not limited to these.

[0078] It should be noted that the method in the embodiment of the present application can be executed by the business processing system 101 and / or the routing system 102.

[0079] In the embodiment of the present application, the business processing system 101 and the routing system 102 can be directly or indirectly connected to each other through one or more networks. The network can be a wired network or a wireless network, for example, the wireless network can be a mobile cellular network, or a wireless fidelity (Wireless-Fidelity, WIFI) network, and of course, it can be other possible networks, which are not limited in the embodiment of the present application.

[0080] The following is based on Figure 1 The system architecture diagram shown in FIG. 1 shows an example of an embodiment of the present application, which provides a process of an intelligent payment routing method. The process of the method can be Figure 1 The routing system 102 shown performs, as Figure 2 As shown, the following steps are included:

[0081] Step 201, upon receiving a payment routing request, obtaining attribute information of multiple candidate payment channels.

[0082] Specifically, before processing a payment transaction request, the business processing system (ie, the upstream business end) first sends a payment routing request to the routing system, wherein the payment transaction request is sent from the payment client to the business processing system.

[0083] Payment routing refers to the process of sending a payment transaction request from a source address to a target address through a payment channel, where the source address can be the payee's address and the target address is the recipient's address. A payment routing request is a request to select the most suitable payment channel for a payment transaction request.

[0084] In addition, the attribute information of the multiple candidate payment channels includes: channel payment rules of the candidate payment channels, multiple routing indicators associated with the execution status of the candidate payment channels, payment limits of the candidate payment channels, and transaction proportions of the candidate payment channels.

[0085] Specifically, before obtaining multiple candidate payment channels, all payment channels are preliminarily screened, and according to the scenario of the payment routing request, payment channels that do not support transactions in the current time period, do not support user bank cards, have abnormal health levels, have load limits (that is, the number of requests undertaken has exceeded the agreed upper limit), and have amount ranges are eliminated, thereby screening out multiple candidate payment channels that support the current payment routing request.

[0086] Step 202: for each candidate payment channel, based on the transaction content associated with the payment routing request and the attribute information of the candidate payment channel, obtain a target evaluation value of the candidate payment channel.

[0087] In some embodiments, based on the transaction content associated with the payment routing request and the attribute information of the candidate payment channel, the dimensional evaluation values ​​of the candidate payment channel in multiple dimensions are obtained; the dimensional evaluation values ​​of the multiple dimensions are weighted and summed to obtain the target evaluation value of the candidate payment channel.

[0088] Specifically, the transaction content associated with the payment routing request includes information such as the payment amount and the transaction type.

[0089] In some embodiments, the dimension evaluation values ​​of multiple dimensions include: the payment upper limit value of the candidate payment channel, the payment consumption value of the candidate payment channel, the health of the candidate payment channel, the transaction proportion of the candidate payment channel, and the payment amount in the transaction content.

[0090] Specifically, the payment upper limit value of the candidate payment channel refers to: the maximum single amount supported by the candidate payment channel; the payment consumption value of the candidate payment channel refers to: the cost that needs to be paid for routing the payment transaction request through the candidate payment channel; the transaction proportion of the candidate payment channel refers to: the maximum transaction proportion that the candidate payment channel can bear; the payment amount in the transaction content refers to: the amount that the user actually wants to pay in the payment reason request.

[0091] According to the historical data records of the dimension evaluation values ​​of multiple dimensions, the weights of the dimensions are obtained, and the sum of the weights of the multiple dimensions is 1. Specifically, for the historical data records of the payment upper limit value, the payment amount of the transaction content, the payment consumption value, the health degree, and the transaction proportion of the candidate payment channel, the weight of the payment upper limit value of the candidate payment channel ω1, the weight of the payment amount of the transaction content ω2, the weight of the payment consumption value ω3, the weight of the health degree ω4, and the weight of the transaction proportion ω5 are obtained respectively. The calculation formula of the target evaluation value is shown in the following formula (1):

[0092] S target =ω1·L+ω2·F+ω3·S cost +ω4·S final +ω5·P………………(1)

[0093] Among them, S target represents the target evaluation value of the candidate payment channel; L represents the maximum single transaction amount supported by the candidate payment channel; F represents the payment amount in the transaction content (i.e., the actual amount to be paid by the user); S cost Indicates the payment consumption value of the candidate payment channel; S final Indicates the health of the candidate payment channel; P indicates the transaction proportion of the candidate payment channel.

[0094] Step 203, based on the target evaluation values ​​of the multiple candidate payment channels respectively, a target payment channel that meets the processing conditions of the transaction content is selected from the multiple candidate payment channels.

[0095] In some embodiments, from multiple candidate payment channels, a candidate payment channel corresponding to the largest target evaluation value is selected as the target payment channel.

[0096] Specifically, the target evaluation values ​​are sorted in descending order to obtain a sorting result, and the candidate payment channel corresponding to the target evaluation value ranked first in the sorting result is selected as the target candidate channel.

[0097] Step 204: Generate a routing decision result corresponding to the payment routing request based on the target payment channel, and return the routing decision result.

[0098] Specifically, the routing decision result is the relevant information corresponding to the target payment channel, such as the name or number of the target payment channel, etc. The routing system returns the routing decision result to the business processing system, and the business processing system sends a payment transaction request through the target payment channel based on the routing decision result, wherein the health of the candidate payment channel in the above steps is obtained based on the result of the completed payment transaction request.

[0099] In an embodiment of the present application, based on the transaction content associated with the payment routing request and the attribute information of the candidate payment channel, the target evaluation value of the candidate payment channel is obtained, the attribute information of the candidate payment channel is comprehensively considered, and the accuracy of the target evaluation value of the candidate payment channel is improved; based on the target evaluation value of the candidate payment channel, the target payment channel that meets the processing conditions of the transaction content is selected, which improves the accuracy of the routing and further improves the quality and execution efficiency of the payment routing.

[0100] In order to explain the execution process in the above steps more clearly, the following introduces an intelligent payment routing method based on the system architecture composed of the business processing system and the routing system. Figure 3 .

[0101] The business processing system (upstream business end) includes the functions of request sending, business processing, and result notification. Request sending refers to sending a payment routing request to the routing decision module in the routing system. Business processing refers to sending an actual payment transaction request to the target payment channel corresponding to the result returned by the routing decision module based on the result returned by the routing decision module. Result notification refers to the processing result of the payment transaction request returned by the routing decision module or the target payment channel received by the business system.

[0102] The routing system includes: routing management module, routing decision module, routing data module, health level module and routing indicator module. Among them, the routing management module is responsible for managing and configuring the routing rules of the entire system, including pre-set channel configuration, channel rules, scenario configuration, and routing rules. Channel configuration refers to the definition of different channels, and does not set specific parameters for each channel; channel rules refer to the policies or conditions set for different channels to determine how requests are executed; scenario configuration refers to configuration based on business scenarios to meet specific needs; routing rules refer to the definition of how payment routing requests flow in the system and where they should be directed.

[0103] The routing decision module in the routing system includes: channel screening, routing decision, and routing results. Among them, channel screening refers to eliminating payment channels that do not meet the transaction content such as time interval, amount interval, load limit, etc. based on the transaction content of the payment routing request, and obtaining multiple candidate payment channels. Routing decision is to calculate the scores of multiple candidate payment channels according to the pre-configured channel rules, routing rules and routing indicators in routing management (that is, the target evaluation value of each candidate payment channel in the above steps), and mark each candidate payment channel with a health level label according to the calculation results. The health registration label includes: normal, good, available and abnormal, and selects the target payment channel that meets the payment routing request based on the calculation results and returns it to the upstream business end. The routing indicators include: execution time, success rate, network time consumption and retry rate. These indicators are cached in the database, and the calculation results (target valuation) of each candidate payment channel are also saved in the database.

[0104] In some embodiments, the payment consumption value of the candidate payment channel is obtained in the following manner: based on the transaction content and the channel payment rule of the candidate payment channel, the payment consumption value of the candidate payment channel is obtained.

[0105] Specifically, the channel payment rules of the candidate payment channel include: channel handling fee rate, channel minimum handling fee, and channel capping handling fee. First, calculate the product of the payment amount in the transaction content associated with the payment routing request and the channel handling fee rate to obtain the consumption value of the payment amount in the transaction content based on the channel handling fee rate. Compare the consumption value with the channel capping handling fee to obtain the minimum value. Compare the minimum value with the channel minimum handling fee to obtain the maximum value of the two. Then subtract the ratio of the maximum value to the payment amount of the transaction content from the integer 1, and the resulting value is the payment consumption value of the candidate payment channel. The specific calculation formula is shown in the following formula (2):

[0106]

[0107] Among them, S costIt represents the payment consumption value of the candidate payment channel, F represents the payment amount in the transaction content, R represents the channel handling fee rate of the candidate payment channel, C represents the channel capped handling fee of the candidate payment channel, and M represents the minimum handling fee of the channel.

[0108] For example, the fee rate of candidate payment channel A is 0.1%, and there is no channel cap fee, while the fee rate of candidate payment channel B is 0.15%, and the channel cap fee is 50. When the transaction amount (that is, the payment amount in the transaction content) exceeds 50,000, candidate payment channel B is selected for payment transaction, and the payment consumption value is smaller, reducing user costs.

[0109] In the embodiment of the present application, the payment consumption value of each candidate payment channel is calculated based on the handling fee rate of the candidate payment channel and the actual amount to be paid by the user, so that the candidate payment channel with a smaller payment consumption value can be selected, thereby reducing the cost of payment routing and improving the user experience.

[0110] In some embodiments, the attribute information of the candidate payment channel includes: a plurality of routing indicator values ​​associated with the execution status of the candidate payment channel; the health of the candidate payment channel is obtained in the following manner:

[0111] Performing weighted summation on multiple routing indicator values ​​to obtain a first state evaluation value;

[0112] Inputting the multiple routing indicator values ​​into the thread regression model for processing to obtain a second state evaluation value;

[0113] The first status evaluation value and the second status evaluation value are averaged to obtain the health of the candidate payment channel.

[0114] In some embodiments, the plurality of routing metric values ​​include:

[0115] Execution time information of candidate payment channels, execution success rate of candidate payment channels, retry rate of candidate payment channels, and network time consumption of candidate payment channels.

[0116] Specifically, the execution time efficiency information of the candidate payment channel refers to: the time required from receiving a request to responding to the request, including: the execution time of the candidate payment channel, that is, the difference between the payment completion time and the payment initiation time of the candidate payment channel; the average time efficiency of the candidate payment channel, that is, the ratio of the cumulative execution time of the candidate payment channel to the cumulative number of executed payments; the maximum time efficiency of the candidate payment channel, that is, the ratio of the cumulative execution time of the top 100 execution times of the candidate payment channel to 100. The specific calculation formulas are shown in the following formulas (3), (4), and (5):

[0117] Execution time = payment completion time - payment initiation time………………(3)

[0118] Average time = cumulative execution time / cumulative number of executions (4)

[0119] Maximum time limit = the cumulative value of the first 100 execution times / 100…………………(5)

[0120] According to formulas (3), (4) and (5), the calculation formula for obtaining the execution time information of the candidate payment channel is shown in the following formula (6):

[0121]

[0122] Among them, E score Indicates the execution time information of the candidate payment channel, T max represents the maximum timeliness of the candidate payment channel; T max_avg represents the average value of the maximum time of all candidate payment channels; T avg represents the average time efficiency of candidate payment channels; T avg_all Represents the average of the average time of all candidate payment channels.

[0123] Specifically, the execution success rate of the candidate payment channel refers to the proportion of successfully completed requests, including: success rate and retry success rate. The specific calculation formulas (7), (8), and (9) of the execution success rate of the candidate payment channel are as follows:

[0124] Success rate = number of successful executions / (number of successful executions + number of failed executions) ……………………(7) Retry success rate = number of successful retries / number of successful executions ………………(8)

[0125] S score =SR×100……………………(9)

[0126] In formula (9), S score It represents the execution success rate of the candidate payment channel, and SR represents the success rate.

[0127] Specifically, the calculation formula of the retry rate of the candidate payment channel is shown in the following formulas (10) and (11): Retry rate = number of retry executions / cumulative number of channel request times (10)

[0128] R score =100-(RR×100)…………………(11)

[0129] Among them, R score Represents the retry rate of the candidate payment channel, and RR represents the retry rate.

[0130] Specifically, the network time of the candidate payment channel refers to the time it takes for the data in the payment transaction request to be transmitted on the network, including: single network time, average time, and maximum time. The network time of the candidate payment channel is calculated using formulas (12), (13), (14), and (15) as shown below:

[0131] Single network time = payment request end time - payment request start time ……………………(12)Average time = cumulative execution network time / cumulative number of executions ………………(13)

[0132] Maximum time consumption = cumulative value of the first 100 network execution times / 100…………………(14)

[0133]

[0134] In formula (15), N score represents the network time of the candidate payment channel; t max represents the maximum time consumption of the candidate payment channel; t max_avg represents the average of the maximum time consumption of all candidate payment channels; t avg represents the average time consumed by candidate payment channels; t avg_all Represents the average of the average time consumed by all candidate payment channels.

[0135] Specifically, the weights of the multiple routing indicators are determined according to the historical evaluation values ​​of the multiple routing indicators of the candidate payment channels; the historical evaluation values ​​of the multiple routing indicators are fitted according to the linear regression model to obtain the regression coefficients of the multiple routing indicators. The calculation formulas of the first state evaluation value and the second state evaluation value are shown in the following formulas (16) and (17), respectively:

[0136] S w =α1×E score +α2×S score +α3×R score +α4×N score ………………(16)

[0137] S r =β1×E score +β2×S score +β3×R score +β4×N score ………………(17)

[0138] Among them, S w represents the first state evaluation value, S r represents the second state evaluation value; E score Indicates the execution time information of the candidate payment channel; S scorerepresents the execution success rate of the candidate payment channel; R score Represents the retry rate of the candidate payment channel; N score represents the network time consumption of the candidate payment channel; α1, α2, α3, and α4 represent the execution time information, execution success rate, retry rate, and network time consumption weights of the candidate payment channel respectively;

[0139] β1, β2, β3, and β4 represent the regression coefficients of the execution time information, execution success rate, retry rate, and network time consumption of the candidate payment channel, respectively; the weights and regression coefficients satisfy the following formula (18):

[0140] α1+α2+α3+α4=β1+β2+β3+β4=1………………(18)

[0141] The first status evaluation value and the second status evaluation value are averaged to obtain the health of the candidate payment channel, as shown in the following formula (19):

[0142]

[0143] Among them, S final Indicates the health of the candidate payment channel, S w represents the first state evaluation value, S r Represents the second state evaluation value.

[0144] For example, when the network consumption of channel A is 100ms and the network consumption of payment channel B is 500ms, if the health assessment is performed only based on the network consumption in the prior art, the payment transaction request will be given priority to channel A for processing. However, the execution success rate of channel A may be much lower than that of channel B. Therefore, in the health assessment of payment channels, this application not only considers the network consumption, but also more comprehensively considers the execution timeliness, success rate, and retry rate of the payment channels, so as to select the target payment channel for the payment transaction request to achieve the optimal solution for execution efficiency.

[0145] In the embodiment of the present application, the health of the candidate payment channel is calculated by calculating the execution time, execution success rate, retry rate and network time of the candidate payment channel, and the current status information of the candidate payment channel is fully and comprehensively considered, rather than just considering the response time of the channel in the traditional method, so as to select a more suitable target payment channel in real time for the payment routing request; the corresponding weights are determined by using the historical data of multiple routing indicators of the candidate payment channel, and the regression coefficient is obtained by fitting a linear regression model, and then the health of the candidate payment channel is obtained based on multiple routing indicators in combination with the weight and the regression coefficient, forming a complete and effective health scoring mechanism, which can cover routing indicators other than network time, improve the accuracy of the health of the candidate payment channel, and further improve the quality of payment routing.

[0146] In some embodiments, based on the health of the candidate payment channel, obtaining a health grade label of the candidate payment channel;

[0147] When the health level label of a candidate payment channel is an abnormal label, the candidate payment channel is excluded from multiple candidate payment channels; and based on the respective target evaluation values ​​of the remaining candidate payment channels, a target payment channel that meets the processing conditions of the transaction content is selected from the remaining candidate payment channels.

[0148] Specifically, a mapping relationship between a health interval and a health grade label is predefined. According to the health of the candidate payment channel and the preset mapping relationship, the health grade label of the candidate payment channel is obtained. For example, the candidate payment channel with a health grade in the interval greater than or equal to 90 has a corresponding health grade label of normal; the candidate payment channel with a health grade in the interval [75,89] has a corresponding health grade label of good; the candidate payment channel with a health grade in the interval [65,74] has a corresponding health grade label of available; the candidate payment channel with a health grade in the interval less than 60 has a corresponding health grade label of abnormal, indicating that the candidate payment channel is unavailable.

[0149] When the health level label of a candidate payment channel is an abnormal label, it indicates that the candidate payment channel is unavailable. Therefore, the candidate payment channel can be directly excluded, that is, the candidate payment channel is no longer considered in the subsequent process of selecting a target payment channel.

[0150] In some embodiments, when it is determined that the health level label of the candidate payment channel is an abnormal label, health detection is performed on the candidate payment channel regularly to obtain the health of the candidate payment channel;

[0151] When the health of the candidate payment channel is greater than a preset threshold, the health level label of the candidate payment channel is updated.

[0152] Specifically, when the health level label of a candidate payment channel is an abnormal label, a health detection is performed on the candidate payment channel at increasing time intervals, such as 30 minutes, 60 minutes, 120 minutes, and other increasing time intervals, to regain the health of the candidate payment channel. When the health level is greater than or equal to 60, the health level label of the candidate payment channel is updated according to the health level label corresponding to the health level.

[0153] In some cases, the health of a candidate payment channel is a slowly changing routing indicator. When multiple consecutive payment transaction requests in a candidate payment channel fail for unexpected reasons, the health level label of the candidate payment channel is directly adjusted to an abnormal label. Channels with abnormal health level labels are eliminated in the initial screening stage and will not be selected as candidate payment channels.

[0154] In an embodiment of the present application, a health level label is determined based on the health of a candidate payment channel, the current health status of the candidate payment channel can be quickly identified, and the health level label can be adjusted in a timely manner. Based on the health level label, it is determined whether the candidate payment channel is in an available state, and abnormalities of the candidate payment channel can be removed and automatically recovered. The costs and benefits of health detection can be balanced, the compatibility between payment routing requests and candidate payment channels is enhanced, and the processing efficiency and quality of subsequent payment transaction requests are improved.

[0155] In order to better explain the embodiment of the present application, a payment routing method provided by the embodiment of the present application is introduced below in combination with an actual scenario. The process of the method is as follows: Figure 1 The routing system shown in the figure performs the following steps: Figure 4 shown.

[0156] Step 401, upon receiving a payment routing request, obtaining attribute information of multiple candidate payment channels.

[0157] Step 402, weighted summing of multiple routing indicator values ​​associated with the execution status of each candidate payment channel is performed to obtain a first status evaluation value; multiple routing status indicators are input into a linear regression model for processing to obtain a second status evaluation value; and the first status evaluation value and the second status evaluation value are averaged to obtain the health of the candidate payment channel.

[0158] Step 403, based on the health of the candidate payment channel, obtain a health grade label of the candidate payment channel; when the health grade label is an abnormal label, exclude the candidate payment channel from the multiple candidate payment channels.

[0159] Step 404: for each remaining candidate payment channel, perform the following steps 4041-4042:

[0160] Step 4041, based on the transaction content associated with the payment routing request and the channel payment rule of the candidate payment channel, the payment consumption value of the candidate payment channel is obtained.

[0161] Step 4042, performing weighted summation on the payment upper limit value, payment consumption value, health, transaction proportion and transaction amount in the transaction content associated with the payment routing request of the candidate payment channel to obtain the target evaluation value of the candidate payment channel.

[0162] Step 405 , based on the target evaluation values ​​of the remaining candidate payment channels, a candidate payment channel corresponding to the largest target evaluation value is selected from the remaining candidate payment channels as the target payment channel.

[0163] For example, refer to Figure 5After receiving the payment routing request sent by the business processing system, the routing system performs routing calculation for the payment routing request, specifically including: routing acceptance, channel screening and routing calculation; wherein routing acceptance refers to the preparation work for the payment routing request; channel screening refers to eliminating payment channels that do not meet the transaction content such as time interval, amount interval, load limit, etc. based on the transaction content of the payment routing request before routing calculation, and obtaining multiple candidate payment channels; routing calculation refers to calculating the comprehensive score (i.e., target evaluation value) of each candidate payment channel based on the payment upper limit value of the candidate payment channel, the payment amount of the transaction content of the payment routing request, the payment consumption value, health and transaction proportion of the candidate payment channel for the multiple candidate payment channels obtained by the channel screening, determining a target payment channel based on the maximum value of the score, and returning the relevant information of the target payment channel to the business processing system.

[0164] The business processing system sends a payment transaction request through a target payment channel among N channels (i.e., multiple candidate payment channels) for processing and obtains a transaction processing result.

[0165] In an embodiment of the present application, based on the transaction content associated with the payment routing request and the attribute information of the candidate payment channel, a target evaluation value of the candidate payment channel is obtained, the attribute information of the payment channel is comprehensively considered, and the accuracy of the target evaluation value of the candidate payment channel is improved; based on the target evaluation value of the candidate payment channel, a target payment channel that meets the processing conditions of the transaction content is selected, the accuracy of the routing is improved, and the quality and execution efficiency of the payment routing are further improved; based on the health level label of the candidate payment channel, the candidate payment channel is removed and automatically recovered, so that the payment routing request is quickly located to a more suitable target payment channel, which helps to ensure the processing efficiency of subsequent payment transaction requests.

[0166] Based on the same technical concept, the embodiment of the present application provides a schematic diagram of the structure of a payment routing, such as Figure 6 As shown, the intelligent payment routing device 600 includes:

[0167] An acquisition module 601 is used to acquire attribute information of multiple candidate payment channels when receiving a payment routing request;

[0168] A processing module 602 is used to obtain, for each candidate payment channel, a target evaluation value of the candidate payment channel based on the transaction content associated with the payment routing request and the attribute information of the candidate payment channel;

[0169] Based on the target evaluation values ​​of the multiple candidate payment channels, a target payment channel that meets the processing conditions of the transaction content is selected from the multiple candidate payment channels;

[0170] The return module 603 is used to generate a routing decision result corresponding to the payment routing request based on the target payment channel, and return the routing decision result.

[0171] Optionally, the processing module 602 is specifically configured to:

[0172] Based on the transaction content associated with the payment routing request and the attribute information of the candidate payment channel, obtaining dimension evaluation values ​​of the candidate payment channel in multiple dimensions;

[0173] The dimension evaluation values ​​of the multiple dimensions are weighted and summed to obtain the target evaluation value of the candidate payment channel.

[0174] Optionally, the dimension evaluation values ​​of the multiple dimensions include: the payment upper limit value of the candidate payment channel, the payment consumption value of the candidate payment channel, the health of the candidate payment channel, the transaction proportion of the candidate payment channel, and the payment amount in the transaction content.

[0175] Optionally, the processing module 602 is specifically configured to:

[0176] The attribute information of the candidate payment channel includes: the channel payment rule of the candidate payment channel;

[0177] The payment consumption value of the candidate payment channel is obtained in the following manner:

[0178] Based on the transaction content and the channel payment rule of the candidate payment channel, the payment consumption value of the candidate payment channel is obtained.

[0179] Optionally, the processing module 602 is specifically configured to:

[0180] The attribute information of the candidate payment channel includes: a plurality of routing indicator values ​​associated with the execution status of the candidate payment channel;

[0181] The health of the candidate payment channel is obtained in the following way:

[0182] Performing weighted summation on the multiple routing indicator values ​​to obtain a first state evaluation value;

[0183] Inputting the multiple routing indicator values ​​into a thread regression model for processing to obtain a second state evaluation value;

[0184] The first status evaluation value and the second status evaluation value are averaged to obtain the health of the candidate payment channel.

[0185] Optionally, the multiple routing indicator values ​​include:

[0186] The execution time efficiency information of the candidate payment channel, the execution success rate of the candidate payment channel, the retry rate of the candidate payment channel, and the network time consumption of the candidate payment channel.

[0187] Optionally, the processing module 602 is specifically configured to:

[0188] Based on the health of the candidate payment channel, obtaining a health grade label of the candidate payment channel;

[0189] When the health level label of the candidate payment channel is an abnormal label, the candidate payment channel is excluded from the multiple candidate payment channels; and based on the target evaluation values ​​of the remaining candidate payment channels respectively, a target payment channel that meets the processing conditions of the transaction content is selected from the remaining candidate payment channels.

[0190] Optionally, the processing module 602 is specifically configured to:

[0191] When it is determined that the health level label of the candidate payment channel is an abnormal label, regularly performing health detection on the candidate payment channel to obtain the health level of the candidate payment channel;

[0192] When the health of the candidate payment channel is greater than a preset threshold, the health grade label of the candidate payment channel is updated.

[0193] Optionally, the processing module 602 is specifically configured to:

[0194] From the multiple candidate payment channels, a candidate payment channel corresponding to the largest target evaluation value is selected as the target payment channel.

[0195] Based on the same technical concept, the embodiment of the present application provides a computer device, which can be Figure 1 The server shown, such as Figure 7 As shown, it includes at least one processor 701 and a memory 702 connected to the at least one processor. The specific link medium between the processor 701 and the memory 702 is not limited in the embodiment of the present application. Figure 7 For example, the processor 701 and the memory 702 are connected via a bus. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0196] In the embodiment of the present application, the memory 702 stores instructions executed by at least one processor 701, and the at least one processor 701 can execute the steps of the above-mentioned intelligent payment routing method by executing the instructions stored in the memory 702.

[0197] Among them, the processor 701 is the control center of the computer device, which can use various interfaces and lines to connect various parts of the computer device, and realize intelligent payment routing by running or executing instructions stored in the memory 702 and calling data stored in the memory 702. Optionally, the processor 701 may include one or more processing modules, and the processor 701 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 701. In some embodiments, the processor 701 and the memory 702 may be implemented on the same chip, and in some embodiments, they may also be implemented separately on independent chips.

[0198] Processor 701 can be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware processor for execution, or can be executed by a combination of hardware and software modules in the processor.

[0199] The memory 702 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory 702 may include at least one type of storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory, a random access memory (Random Access Memory, RAM), a static random access memory (Static Random Access Memory, SRAM), a programmable read-only memory (Programmable Read Only Memory, PROM), a read-only memory (Read Only Memory, ROM), an electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), a magnetic memory, a disk, an optical disk, etc. The memory 702 is any other medium that can be used to carry or store a desired program code in the form of an instruction or data structure and can be accessed by a computer device, but is not limited thereto. The memory 702 in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0200] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program executable by a computer device. When the program runs on the computer device, the computer device executes the steps of the above-mentioned intelligent payment routing method.

[0201] Based on the same inventive concept, an embodiment of the present application provides a computer program product, including a computer program stored on a computer-readable storage medium, wherein the computer program includes program instructions, and when the program instructions are executed by a computer device, the computer device executes the steps of the above-mentioned intelligent payment routing method.

[0202] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0203] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0204] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0205] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0206] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An intelligent payment routing method, characterized in that: include: When receiving a payment routing request, obtaining attribute information of multiple candidate payment channels; For each candidate payment channel, based on the transaction content associated with the payment routing request and the attribute information of the candidate payment channel, obtaining a target evaluation value of the candidate payment channel; Based on the target evaluation values ​​of the multiple candidate payment channels, a target payment channel that meets the processing conditions of the transaction content is selected from the multiple candidate payment channels; A routing decision result corresponding to the payment routing request is generated based on the target payment channel, and the routing decision result is returned.

2. The method according to claim 1, characterized in that The obtaining, based on the transaction content associated with the payment routing request and the attribute information of the candidate payment channel, a target evaluation value of the candidate payment channel comprises: Based on the transaction content associated with the payment routing request and the attribute information of the candidate payment channel, obtaining dimension evaluation values ​​of the candidate payment channel in multiple dimensions; The dimension evaluation values ​​of the multiple dimensions are weighted and summed to obtain the target evaluation value of the candidate payment channel.

3. The method according to claim 2, characterized in that The dimension evaluation values ​​of the multiple dimensions include: the payment upper limit value of the candidate payment channel, the payment consumption value of the candidate payment channel, the health of the candidate payment channel, the transaction proportion of the candidate payment channel, and the payment amount in the transaction content.

4. The method according to claim 3, characterized in that The attribute information of the candidate payment channel includes: the channel payment rule of the candidate payment channel; The payment consumption value of the candidate payment channel is obtained in the following manner: Based on the transaction content and the channel payment rule of the candidate payment channel, the payment consumption value of the candidate payment channel is obtained.

5. The method according to claim 3, characterized in that The attribute information of the candidate payment channel includes: a plurality of routing indicator values ​​associated with the execution status of the candidate payment channel; The health of the candidate payment channel is obtained in the following way: Performing weighted summation on the multiple routing indicator values ​​to obtain a first state evaluation value; Inputting the multiple routing index values ​​into a linear regression model for processing to obtain a second state evaluation value; The first status evaluation value and the second status evaluation value are averaged to obtain the health of the candidate payment channel.

6. The method according to claim 5, characterized in that The multiple routing indicator values ​​include: The execution time efficiency information of the candidate payment channel, the execution success rate of the candidate payment channel, the retry rate of the candidate payment channel, and the network time consumption of the candidate payment channel.

7. The method according to claim 3, characterized in that The selecting, based on the target evaluation values ​​of the plurality of candidate payment channels respectively, a target payment channel that satisfies the processing conditions of the transaction content from the plurality of candidate payment channels comprises: Based on the health of the candidate payment channel, obtaining a health grade label of the candidate payment channel; When the health level label of the candidate payment channel is an abnormal label, the candidate payment channel is excluded from the multiple candidate payment channels; and based on the target evaluation values ​​of the remaining candidate payment channels respectively, a target payment channel that meets the processing conditions of the transaction content is selected from the remaining candidate payment channels.

8. The method according to claim 7, characterized in that Also includes: When it is determined that the health level label of the candidate payment channel is an abnormal label, regularly performing health detection on the candidate payment channel to obtain the health level of the candidate payment channel; When the health of the candidate payment channel is greater than a preset threshold, the health grade label of the candidate payment channel is updated.

9. The method according to claim 1, characterized in that The selecting, based on the target evaluation values ​​of the plurality of candidate payment channels respectively, a target payment channel that satisfies the processing conditions of the transaction content from the plurality of candidate payment channels comprises: From the multiple candidate payment channels, a candidate payment channel corresponding to the largest target evaluation value is selected as the target payment channel.

10. An intelligent payment routing device, characterized in that: The device comprises: An acquisition module, used for acquiring attribute information of multiple candidate payment channels upon receiving a payment routing request; A processing module, configured to obtain, for each candidate payment channel, a target evaluation value of the candidate payment channel based on the transaction content associated with the payment routing request and the attribute information of the candidate payment channel; Based on the target evaluation values ​​of the multiple candidate payment channels, a target payment channel that meets the processing conditions of the transaction content is selected from the multiple candidate payment channels; A return module is used to generate a routing decision result corresponding to the payment routing request based on the target payment channel, and return the routing decision result.

11. A computer device, characterized in that: include: Memory for storing computer programs; A processor, configured to call a computer program stored in the memory, and execute the method according to any one of claims 1 to 9 according to the obtained program.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program executable by a computer device. When the computer program is run on a computer, the computer is enabled to implement the method according to any one of claims 1 to 9.

13. A computer program product, characterized in that The computer program product comprises a computer program stored on a computer-readable storage medium, wherein the computer program comprises program instructions, and when the program instructions are executed by a computer device, the computer device is caused to execute the steps of the method according to any one of claims 1 to 9.

Images