Intelligent payment routing method and device based on big data

Abstract

The invention discloses an intelligent payment routing method and device based on big data, and relates to the technical field of electronic payment. According to the scheme, the method comprises the following steps: a computer device obtains historical data corresponding to each candidate payment route; the computer equipment determines a first weight of each index of each candidate payment route based on the historical data; the computer equipment determines a target weight of each index of each candidate payment route based on the first weight and a manually evaluated second weight; the computer equipment calculates the current score of each candidate payment route based on the preset score and the target weight of each index; the computer device determines a target payment route based on the current score of each candidate payment route. According to the invention, the accuracy of payment route evaluation under the condition that the transaction data volume is small can be improved, and the efficiency and stability of payment are further improved.

Description

Technical Field

[0001] The present invention relates to the field of electronic payment technology, and more specifically, to a big data-based intelligent payment routing method and device. Background Art

[0002] Smart payment routing is an important part of the payment system. By setting a specific path, the payer's payment instructions are transmitted to the corresponding payee, ensuring that the payment instructions can be efficiently and accurately transmitted from the payer's account to the payee's account. Smart payment routing can automatically select the optimal payment channel based on different payment requirements, rate standards, security and other factors to ensure efficient and stable payment.

[0003] Chinese patent publication number CN115829557A, publication date 2023.03.21, discloses a payment channel selection method, device and related media based on fuzzy comprehensive evaluation. For each payment channel, it uses multiple evaluation index systems such as channel module, rate rule module, transaction limit module, system evaluation stability module, channel type module and service quality module to evaluate transaction parameters, and obtain multiple scores accordingly; normalize all scores to obtain module index values ​​of different evaluation index systems, and use the module index values ​​as single factor evaluation values; construct a factor set by using all single factor evaluation values ​​as evaluation factors; calculate the factor weight of each evaluation factor in the factor set by using entropy weight method; establish an evaluation set based on the historical evaluation results of each payment channel; confirm the membership of each evaluation factor in the factor set with the evaluation set; based on the maximum membership principle, assign weights to each evaluation factor in the factor set according to the factor weight, so as to construct the fuzzy comprehensive evaluation matrix; output the comprehensive evaluation result of each payment channel based on the fuzzy comprehensive evaluation matrix, and select the corresponding payment channel according to the comprehensive evaluation result. Although this patent can automatically evaluate each payment channel and select a suitable payment channel based on the evaluation results, its evaluation is based on historical transaction parameters. When the historical transaction parameter data of the payment channel is relatively small, the accuracy of the calculated payment route evaluation results will be affected, affecting the efficiency and stability of payment. Summary of the invention

[0004] In view of this, the present invention provides an intelligent payment routing method and device based on big data, which can improve the accuracy of payment routing evaluation when the amount of transaction data is small, thereby improving the efficiency and stability of payment.

[0005] In order to achieve the above object, the present invention adopts the following technical scheme:

[0006] In a first aspect, the present invention provides an intelligent payment routing method based on big data, the method comprising:

[0007] The computer device obtains the historical data corresponding to each candidate payment route respectively;

[0008] The computer device determines, based on the historical data, a first weight of each indicator of each candidate payment route;

[0009] The computer device determines the target weight of each indicator of each candidate payment route based on the first weight and the manually evaluated second weight;

[0010] The computer device calculates the current score of each candidate payment route based on the preset score and target weight of each indicator;

[0011] The computer device determines a target payment route based on the current score of each candidate payment route.

[0012] The method provided by the present invention collects various historical data that affect the payment routing score through big data technology, automatically calculates the first weight of each indicator that affects the payment routing score, and combines the second weight of manual evaluation to achieve the combination of subjective and objective factors, so that the selection of payment routing is more comprehensive and reasonable. By calculating the preset score of each indicator and the target weight, the influence of multiple indicators on the payment routing performance can be comprehensively considered, avoiding the one-sidedness of single indicator evaluation. It is suitable for the situation where the amount of transaction data is small, and can improve the accuracy of payment routing evaluation, thereby improving the efficiency and stability of payment.

[0013] In a possible implementation, the computer device determines the target weight of each indicator of each candidate payment route based on the first weight and the manually evaluated second weight, including:

[0014] If the absolute value of the difference between the first weight and the second weight is greater than a preset threshold, the computer device acquires a third weight and determines the third weight as a target weight;

[0015] If the absolute value of the difference between the first weight and the second weight is not greater than a preset threshold, the computer device determines the first weight as the target weight.

[0016] In a possible implementation, the computer device determines the first weight of each indicator of each candidate payment route based on historical data, including:

[0017] For any indicator of any candidate payment route, the computer device extracts a plurality of feature values ​​corresponding to the indicator from historical data corresponding to the candidate payment route;

[0018] The computer device obtains the probability of each characteristic value respectively;

[0019] The computer device calculates the entropy value of the indicator based on the probabilities of all eigenvalues;

[0020] The computer device calculates a first weight of the indicator based on entropy values ​​of all indicators of the candidate payment route.

[0021] In a possible implementation, for any indicator of any candidate payment route, the computer device extracts multiple feature values ​​corresponding to the indicator from historical data corresponding to the candidate payment route, including:

[0022] The computer device extracts preset keywords from the historical data;

[0023] The computer device determines the characteristic values ​​of the indicator in different time periods based on preset keywords belonging to the same time period and the same indicator.

[0024] In a possible implementation, the candidate payment routes include the current payment route and other payment routes; the computer device determines the target payment route based on the current score of each candidate payment route, including:

[0025] The computer device determines the priority corresponding to the current score of each candidate payment route respectively;

[0026] The computer device determines whether there is a situation where the priority corresponding to the current score of other payment routes is higher than the priority corresponding to the current score of the current payment route;

[0027] If so, the computer device selects the candidate payment route with the highest current score as the target payment route from other payment routes with a priority higher than the priority corresponding to the current score of the current payment route;

[0028] If not, the computer device determines the current payment route as the target payment route.

[0029] In a possible implementation, the candidate payment routes include the current payment route and other payment routes; the computer device determines the target payment route based on the current score of each candidate payment route, including:

[0030] If the current score of the current payment route is less than the first score, the computer device selects the candidate payment route with the highest current score from other payment routes with current scores not less than the second score as the target payment route;

[0031] The first score is the product of the last score of the current payment route and the first preset percentage; the second score is the product of the current score of the current payment route and the second preset percentage.

[0032] In one possible implementation, the indicators include at least one of payment success rate, revenue, request success rate, request success business failure rate, order completion rate, risk control rate, order completion time, network time consumption, communication timeout, request failure rate, system processor occupancy rate, system memory occupancy rate, and system load score.

[0033] In a second aspect, the present invention provides an intelligent payment routing device based on big data, comprising: a historical data acquisition module, a first weight determination module, a target weight determination module, a score calculation module and a routing determination module; wherein,

[0034] A historical data acquisition module, connected to the first weight determination module, is used for the computer device to respectively acquire historical data corresponding to each candidate payment route;

[0035] A first weight determination module, connected to the historical data acquisition module and the target weight determination module, respectively, for the computer device to determine the first weight of each indicator of each candidate payment route based on the historical data;

[0036] A target weight determination module, connected to the first weight determination module and the score calculation module respectively, for the computer device to determine the target weight of each indicator of each candidate payment route based on the first weight and the manually evaluated second weight;

[0037] A score calculation module, connected to the target weight determination module and the route determination module, respectively, for calculating the current score of each candidate payment route based on the preset score and target weight of each indicator by the computer device;

[0038] The route determination module is connected to the score calculation module and is used for the computer device to determine the target payment route based on the current score of each candidate payment route.

[0039] In a third aspect, the present invention provides a computer device comprising a processor and a memory; the memory stores a computer program or computer instructions that can be loaded by the processor and executed such as the first aspect and any possible implementation thereof for an intelligent payment routing method based on big data.

[0040] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program or computer instructions that can be loaded by a processor and executed such as the first aspect and any possible implementation thereof for an intelligent payment routing method based on big data.

[0041] For the specific description of the second to fourth aspects and their various implementations in the present invention, reference can be made to the detailed description in the first aspect and its various implementations; and for the beneficial effects of the second to fourth aspects and their various implementations, reference can be made to the analysis of the beneficial effects in the first aspect and its various implementations, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.

[0043] Figure 1 It is a flowchart of an intelligent payment routing method based on big data according to an embodiment of the present invention;

[0044] Figure 2 It is a flowchart of the sub-steps of step S102 in a smart payment routing method based on big data according to an embodiment of the present invention;

[0045] Figure 3 It is a flowchart of the sub-steps of step S105 in a smart payment routing method based on big data according to an embodiment of the present invention;

[0046] Figure 4 It is a structural block diagram of an intelligent payment routing device based on big data according to an embodiment of the present invention;

[0047] Figure 5 It is a block diagram of the internal structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0048] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0049] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0050] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0051] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0052] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0053] Embodiment 1:

[0054] The embodiment of the present invention provides an intelligent payment routing method based on big data. Figure 1 , which is a flow chart of the intelligent payment routing method based on big data provided by an embodiment of the present invention. Figure 1 As shown, the intelligent payment routing method based on big data provided by the present invention mainly includes the following steps (steps S101 to S105):

[0055] Step S101, the computer device obtains the historical data corresponding to each candidate payment route respectively;

[0056] Step S102, the computer device determines the first weight of each indicator of each candidate payment route based on the historical data;

[0057] Step S103, the computer device determines the target weight of each indicator of each candidate payment route based on the first weight and the manually evaluated second weight;

[0058] Step S104, the computer device calculates the current score of each candidate payment route based on the preset score and target weight of each indicator;

[0059] Step S105: The computer device determines a target payment route based on the current score of each candidate payment route.

[0060] In this embodiment, historical data refers to payment-related data generated by electronic payment through each candidate payment route, which comes from multiple data sources such as servers, business logs, and business data. For example, data such as CPU usage, memory usage, network bandwidth, system load, etc. from the server data source, response time, network time consumption, number of risks, etc. from the business log data source, and payment success rate, payment income, completion time, etc. from the business data source.

[0061] For server data sources, you can use monitoring software to obtain real-time server data such as CPU usage, memory usage, network bandwidth, system load, etc. For business log data sources, you can use logstash, ElasticSearch, Filebeat and other log analysis and retrieval frameworks to analyze and filter the service logs according to specified rules, and synchronize the final useful data to the big data system. Among them, Logstash is an open source data collection engine with real-time pipeline function, Elasticsearch is a distributed, scalable, real-time search and data analysis engine, and Filebeat is a lightweight log data collector.

[0062] The massive data collected from different data sources are uniformly processed into the target format for storage to provide data support for subsequent feature value extraction.

[0063] The collected data can be divided into indicators such as payment success rate, revenue, request success rate, request success business failure rate, order completion rate, risk control rate, and order completion time according to business rules; according to system interaction rules, it can be divided into indicators such as network time consumption, communication timeout, request failure rate, system processor occupancy rate, system memory occupancy rate, and system load score.

[0064] The payment success rate refers to the proportion of successfully completed payments among all payment requests.

[0065] Revenue refers to the income obtained by a payment institution or individual through transaction fees, service fees, advertising fees, value-added service income, etc.

[0066] The request success rate refers to the proportion of all payment requests initiated that are successfully received and processed.

[0067] The successful request business failure rate refers to the proportion of transactions that fail due to business reasons (such as incomplete information, insufficient inventory, etc.) after the payment request successfully reaches the payment system.

[0068] The completion rate refers to the proportion of payment transactions that are ultimately completed among all payment requests.

[0069] The risk control rate refers to the proportion of users whose accounts are restricted or frozen due to triggering risk control rules within a specific time period.

[0070] Completion time refers to the time required from the user initiating a payment request to the successful completion of the payment.

[0071] Network time refers to the time it takes for a payment request to be transmitted over the network, including the time it takes for the payment request to be sent from the client to the server and for the server to respond back to the client.

[0072] Communication timeout refers to the failure of a payment request to be completed within the scheduled time due to network delays or system processing delays.

[0073] The request failure rate refers to the proportion of payment requests initiated by users that are not successfully processed.

[0074] System processor utilization refers to the proportion of CPU resources occupied by the payment system when processing payment requests.

[0075] System memory usage refers to the proportion of memory resources occupied by the payment system during operation.

[0076] The system load score refers to the load of the payment system when processing payment requests, which is usually comprehensively evaluated through the usage of system resources such as CPU, memory, and disk I / O.

[0077] In some optional embodiments, if the absolute value of the difference between the first weight and the second weight is greater than a preset threshold, the computer device obtains a third weight and determines the third weight as the target weight; if the absolute value of the difference between the first weight and the second weight is not greater than the preset threshold, the computer device determines the first weight as the target weight.

[0078] The preset threshold can be set according to the actual situation, for example, 20%. The greater the difference between the first weight and the second weight, it means that at least one of them is in error, and it is necessary to manually analyze based on these two weights. If the first weight is inaccurate, it means that there is a problem with the algorithm model, which needs to be corrected and adjusted, and a new weight, namely the third weight, is given as the target weight, and correction and adjustment require more historical data. If the first weight is inaccurate and the second weight is accurate, the second weight can be directly used as the target weight. If the first weight is accurate, the first weight can be directly used as the target weight.

[0079] Generally speaking, the indicators corresponding to each candidate payment route are the same, so that each candidate payment route can be fairly evaluated under the same indicator evaluation system. Candidate payment routes include the current payment route in use and other payment routes that are not in use. Determining the target payment route actually means whether to switch the current payment route to other payment routes after scoring the current payment route and other payment routes. If not, the current payment route is the target payment route. If switched, the payment route after switching is the target payment route.

[0080] In this embodiment, the preset score is a score preset for each indicator of each candidate payment route, and the preset score of each indicator can be set to be the same.

[0081] In step S104, a weighted average algorithm may be used to calculate the current score of each candidate payment route. Assume there are n indicators, the current score The specific formula is as follows:

[0082]

[0083] Where W i ′ is the i-th index X i The target weight, y i is the i-th indicator X i The preset score of , i=1,2,…,n, n>1, and n is an integer. i The contribution of i ’ adjustment, the data point with larger weight has greater influence on the weighted average.

[0084] The method provided in this embodiment is applicable to most payment routing selection scenarios in the current market, and can choose to use different data sources according to its actual situation, separate and collect different indicator characteristic values, and finally form a payment routing evaluation model suitable for its own situation; its model is easy to build, and various indicators can be flexibly selected. According to the results of real-time calculation, it can be evaluated and analyzed whether there is a problem with the current payment route. If it is judged that there is a problem, the currently available optimal payment route can be intelligently selected; according to the data collected and processed by big data, the self-model can be continuously optimized, and through the evolution of its own model, the fastest and most accurate routing selection decision-making ability can be achieved, thereby ensuring the continuity of payment services and not causing business interruptions due to routing problems.

[0085] It is particularly suitable for scenarios where the amount of data from the electronic payment data source is small. By combining the automatically calculated first weight and the manually evaluated second weight, the target weight of each indicator is evaluated and adjusted to improve the accuracy of the quality evaluation of each payment route, thereby improving the efficiency and stability of the electronic payment system.

[0086] Embodiment 2:

[0087] For step S102 in the first embodiment, the entropy weight method can be used to calculate the first weight of each indicator, such as Figure 2 As shown, the specific method is as follows:

[0088] Step S201, for any indicator of any candidate payment route, the computer device extracts a plurality of feature values ​​corresponding to the indicator from historical data corresponding to the candidate payment route;

[0089] Step S202, the computer device obtains the probability of each characteristic value respectively;

[0090] Step S203, the computer device calculates the entropy value of the indicator based on the probabilities of all eigenvalues;

[0091] Step S204: The computer device calculates a first weight of the indicator based on the entropy values ​​of all indicators of the candidate payment route.

[0092] In this embodiment, each indicator has its corresponding preset keyword. By extracting the preset keywords in the historical data, all the preset keywords of each indicator in different time periods are summarized, and then the characteristic value of the indicator is determined for all the preset keywords in each time period. The characteristic value is generally determined by substituting the numerical value corresponding to the extracted keyword into the preset formula for calculation. The number of characteristic values ​​is the same as the number of time periods, that is, each time period will correspond to a characteristic value, and these characteristic values ​​may be the same or different.

[0093] It should be noted that the division of time periods is generally equal time division, that is, the length of each time period is equal. For example, if the historical data is the data of the past thirty days, the time period can be set to one day, so that 30 feature values ​​can be obtained.

[0094] Taking the request success rate as an example, the print request log and channel response log in the business log are obtained. These logs contain field information such as request time, unique identifier, request channel, request channel parameters, channel return parameters, whether the request is successful, etc. By extracting and filtering the logs, these field information is stored in the database, and the request success rate of each channel, i.e., payment routing, is calculated separately. The calculation formula is request success rate = number of successful requests / total number of requests.

[0095] When calculating the first weight of the indicator, it is necessary to summarize the characteristic values ​​of all time periods of the indicator, calculate the distribution probability of each characteristic value, calculate the entropy value through the distribution probability, and then calculate the first weight of the indicator based on the entropy value.

[0096] Assume there are n indicators, the i-th indicator X i The value set of {x i1 ,x i2 ,…,x im}, where m is the index X i The number of eigenvalues ​​of . i The entropy value E(X i ) is calculated as follows:

[0097]

[0098] In the formula, p ij is the i-th indicator X i The jth eigenvalue x ij The probability of f ij is the i-th indicator X i The jth eigenvalue x ijThe frequency of occurrence, F i is the i-th indicator X i The total frequency of , j = 1, 2,…, m, m>1, and m is an integer.

[0099] Then, the i-th indicator X i The first weight W i The calculation formula is as follows:

[0100]

[0101] Formula (3);

[0102] In the formula, It is the sum of the information entropy of all indicators, k = 1, 2, …, n, n > 1, and n is an integer.

[0103] Embodiment three:

[0104] For step S105 in the first embodiment, the target payment route may be determined according to the priority level of the current score of each candidate payment route, such as Figure 3 As shown, the specific method is as follows:

[0105] Step S301, the computer device determines the priority corresponding to the current score of each candidate payment route;

[0106] Step S302, the computer device determines whether there is a situation where the priority corresponding to the current score of other payment routes is higher than the priority corresponding to the current score of the current payment route; if so, execute step S303, otherwise execute step S304;

[0107] Step S303, the computer device selects the candidate payment route with the highest current score as the target payment route from other payment routes with a priority higher than the priority corresponding to the current score of the current payment route;

[0108] Step S304: the computer device determines the current payment route as the target payment route.

[0109] In this embodiment, different scoring intervals are pre-assigned to different priorities. The higher the scoring value, the higher the priority, and the higher the priority of the candidate payment route. Although the current scores of two candidate payment routes are different, if they belong to the same scoring interval, they have the same priority. When one of the candidate payment routes is the current payment route, there is no need to switch.

[0110] For example, the scoring intervals [0,50], (50,70], (70,90] and (90,100] have higher and higher priorities. The current score of the current payment route is 85, which belongs to the scoring interval (70,90]. If there is another payment route with a current score of 95, which belongs to the scoring interval (90,100], the priority of the other payment route is higher than the current payment route. At this time, the other payment route is set as the target payment route; if the current score of the other payment route is 88, although it is higher than the current score of 85 of the current payment route, it still belongs to the same interval (70,90]. At this time, there is no need to switch routes, that is, the current payment route is set as the target payment route.

[0111] In addition, if the score of the current payment route fluctuates significantly downward, it means that the current payment route has unstable factors and should not be used any more. In this case, the route switching operation will be triggered. Specifically, if the current score of the current payment route is less than the first score, the computer device selects the candidate payment route with the highest current score as the target payment route from other payment routes whose current scores are not less than the second score. The first score is the product of the last score of the current payment route and the first preset percentage; the second score is the product of the current score of the current payment route and the second preset percentage.

[0112] Optionally, the first preset percentage is 80% and the second preset percentage is 10%.

[0113] In this embodiment, the computer device will periodically score all candidate payment routes, the current score of the current payment route is the scoring operation performed this time, and the last score of the current payment route is the scoring operation performed last time.

[0114] Although the score of the current payment route has fluctuated downward significantly, there may be other payment routes whose current scores are lower than the current score of the current payment route. In this case, you can find other payment routes with lower current scores than the current payment route to switch to.

[0115] Embodiment 4:

[0116] Based on the same inventive concept, the embodiment of the present invention also provides a smart payment routing device based on big data for implementing the smart payment routing method based on big data involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations of one or more embodiments of the smart payment routing device based on big data provided below can refer to the limitations of the smart payment routing method based on big data above, and will not be repeated here.

[0117] Figure 4FIG. 4 shows a block diagram of a smart payment routing device 400 based on big data. Figure 4 As shown, the intelligent payment routing device 400 based on big data includes: a historical data acquisition module 401, a first weight determination module 402, a target weight determination module 403, a score calculation module 404 and a routing determination module 405; wherein,

[0118] The historical data acquisition module 401 is connected to the first weight determination module 402 and is used for the computer device to respectively acquire the historical data corresponding to each candidate payment route;

[0119] A first weight determination module 402, connected to the historical data acquisition module 401 and the target weight determination module 403, respectively, for the computer device to determine the first weight of each indicator of each candidate payment route based on the historical data;

[0120] A target weight determination module 403, connected to the first weight determination module 402 and the score calculation module 404, respectively, for the computer device to determine the target weight of each indicator of each candidate payment route based on the first weight and the manually evaluated second weight;

[0121] The score calculation module 404 is connected to the target weight determination module 403 and the route determination module 405 respectively, and is used for the computer device to calculate the current score of each candidate payment route based on the preset score and target weight of each indicator;

[0122] The route determination module 405 is connected to the score calculation module 404 and is used by the computer device to determine the target payment route based on the current score of each candidate payment route.

[0123] In some optional embodiments, the target weight determination module 403 is specifically used to, if the absolute value of the difference between the first weight and the second weight is greater than a preset threshold, the computer device obtains a third weight and determines the third weight as the target weight; if the absolute value of the difference between the first weight and the second weight is not greater than the preset threshold, the computer device determines the first weight as the target weight.

[0124] In some optional embodiments, the first weight determination module 402 includes:

[0125] A feature value extraction module, for extracting, for any indicator of any candidate payment route, a plurality of feature values ​​corresponding to the indicator from historical data corresponding to the candidate payment route by the computer device;

[0126] A probability acquisition module, used for the computer device to respectively acquire the probability of each characteristic value;

[0127] An entropy value calculation module is used for the computer device to calculate the entropy value of the indicator based on the probability of all characteristic values;

[0128] The weight calculation module is used for the computer device to calculate the first weight of the indicator based on the entropy values ​​of all indicators of the candidate payment route.

[0129] Optionally, a feature value extraction module is specifically used for a computer device to extract preset keywords from historical data; the computer device determines the feature values ​​of the indicator in different time periods based on the preset keywords belonging to the same time period and the same indicator.

[0130] In some optional embodiments, the route determination module 405 is specifically used for the computer device to determine the priority corresponding to the current score of each candidate payment route respectively; the computer device determines whether there is a situation where the priority corresponding to the current score of other payment routes is higher than the priority corresponding to the current score of the current payment route; if so, the computer device selects the candidate payment route with the highest current score as the target payment route from other payment routes with a priority higher than the priority corresponding to the current score of the current payment route; if not, the computer device determines the current payment route as the target payment route.

[0131] In some optional embodiments, the route determination module 405 is specifically used to select, if the current score of the current payment route is less than the first score, the candidate payment route with the highest current score from other payment routes whose current scores are not less than the second score as the target payment route by the computer device; wherein the first score is the product of the last score of the current payment route and the first preset percentage; and the second score is the product of the current score of the current payment route and the second preset percentage.

[0132] In some optional embodiments, the indicators include at least one of payment success rate, revenue, request success rate, request success business failure rate, order completion rate, risk control rate, order completion time, network time consumption, communication timeout, request failure rate, system processor occupancy rate, system memory occupancy rate, and system load score.

[0133] It should be noted that the above-mentioned functional modules can be integrated together to form an independent unit, for example, integrated into a processing unit, or each module can exist physically separately, or two or more modules can be integrated to form an independent unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0134] Embodiment five:

[0135] Based on the same inventive concept, the embodiment of the present invention further provides a computer device 500, the internal structure of the computer device 500 is as follows: Figure 5 The computer device 500 includes a memory 501 , a processor 502 and a communication bus 503 ; the memory 501 and the processor 502 are connected via the communication bus 503 .

[0136] The memory 501 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 501 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the smart payment routing method based on big data provided in the above embodiment, etc.; the data storage area may store data involved in a smart payment routing method based on big data provided in the above embodiment, etc.

[0137] The processor 502 may include one or more processing cores. The processor 502 executes various functions and processes data of the present invention by running or executing instructions, programs, code sets or instruction sets stored in the memory 501, calling the data stored in the memory 501. The processor 502 may be at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller and a microprocessor. It is understandable that for different devices, the electronic device used to implement the above-mentioned processor function may also be other, and the embodiment of the present invention is not specifically limited.

[0138] The communication bus 503 may include a path to transmit information between the above components. The communication bus 503 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The communication bus 503 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one double arrow is used in the diagram, but it does not mean that there is only one bus or one type of bus. Figure 5The computer device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0139] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0140] Embodiment six:

[0141] In particular, according to an embodiment of the present invention, the process described in the above flowchart may be implemented as a computer software program.

[0142] The technical solution of the present invention, in essence, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, that is, the embodiment of the present invention also provides a computer-readable storage medium, which includes a number of computer programs or computer instructions, which are used to enable a computer device (which can be a personal computer, server or network device, etc.) or a processor to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory, random access memory, disk or optical disk, etc., various media that can store program codes.

[0143] Embodiment seven:

[0144] An embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer readable medium, the computer program including a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), various functions defined in the present invention are performed.

[0145] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will be appreciated by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. An intelligent payment routing method based on big data, characterized in that: include: The computer device obtains the historical data corresponding to each candidate payment route respectively; The computer device determines, based on the historical data, first weights of the indicators of the candidate payment routes; The computer device determines the target weight of each of the indicators of each of the candidate payment routes based on the first weight and the manually evaluated second weight; The computer device calculates the current score of each of the candidate payment routes based on the preset score of each of the indicators and the target weight; The computer device determines a target payment route based on the current score of each of the candidate payment routes.

2. The intelligent payment routing method based on big data according to claim 1, characterized in that: The computer device determines the target weight of each indicator of each candidate payment route based on the first weight and the manually evaluated second weight, respectively, including: If the absolute value of the difference between the first weight and the second weight is greater than a preset threshold, the computer device acquires a third weight and determines the third weight as the target weight; If the absolute value of the difference between the first weight and the second weight is not greater than a preset threshold, the computer device determines the first weight as the target weight.

3. The intelligent payment routing method based on big data according to claim 1 or 2, characterized in that: The computer device determines, based on the historical data, first weights of the indicators of the candidate payment routes respectively, including: For any of the indicators of any of the candidate payment routes, the computer device extracts a plurality of feature values ​​corresponding to the indicator from historical data corresponding to the candidate payment route; The computer device obtains the probability of each of the characteristic values ​​respectively; The computer device calculates the entropy value of the indicator based on the probabilities of all the characteristic values; The computer device calculates a first weight of the indicator based on entropy values ​​of all the indicators of the candidate payment route.

4. The intelligent payment routing method based on big data according to claim 3 is characterized in that: For any of the indicators of any of the candidate payment routes, the computer device extracting a plurality of feature values ​​corresponding to the indicator from the historical data corresponding to the candidate payment route includes: The computer device extracts preset keywords from the historical data; The computer device determines the characteristic values ​​of the indicator in different time periods according to the preset keywords belonging to the same time period and the same indicator.

5. The intelligent payment routing method based on big data according to claim 1 or 2, characterized in that: The candidate payment routes include the current payment route and other payment routes; the computer device determines the target payment route based on the current score of each of the candidate payment routes, including: The computer device determines the priority corresponding to the current score of each of the candidate payment routes respectively; The computer device determines whether there is a situation where the priority corresponding to the current score of the other payment route is higher than the priority corresponding to the current score of the current payment route; If yes, the computer device selects the candidate payment route with the highest current score as the target payment route from other payment routes with a priority higher than the priority corresponding to the current score of the current payment route; If not, the computer device determines the current payment route as the target payment route.

6. The intelligent payment routing method based on big data according to claim 1 or 2, characterized in that: The candidate payment routes include the current payment route and other payment routes; the computer device determines the target payment route based on the current score of each of the candidate payment routes, including: If the current score of the current payment route is less than the first score, the computer device selects the candidate payment route with the highest current score as the target payment route from other payment routes whose current scores are not less than the second score; The first score is the product of the last score of the current payment route and a first preset percentage; the second score is the product of the current score of the current payment route and a second preset percentage.

7. The intelligent payment routing method based on big data according to claim 1 or 2, characterized in that: The indicators include at least one of payment success rate, revenue, request success rate, request success business failure rate, order completion rate, risk control rate, order completion time, network time consumption, communication timeout, request failure rate, system processor occupancy rate, system memory occupancy rate, and system load score.

8. An intelligent payment routing device based on big data, characterized in that: include: A historical data acquisition module, a first weight determination module, a target weight determination module, a score calculation module and a route determination module; wherein, The historical data acquisition module is connected to the first weight determination module and is used for the computer device to respectively acquire the historical data corresponding to each candidate payment route; The first weight determination module is connected to the historical data acquisition module and the target weight determination module respectively, and is used for the computer device to determine the first weight of each indicator of each candidate payment route based on the historical data; The target weight determination module is connected to the first weight determination module and the score calculation module respectively, and is used for the computer device to determine the target weight of each indicator of each candidate payment route based on the first weight and the manually evaluated second weight; The score calculation module is connected to the target weight determination module and the route determination module respectively, and is used for the computer device to calculate the current score of each of the candidate payment routes based on the preset score of each of the indicators and the target weight; The route determination module is connected to the score calculation module, and is used by the computer device to determine the target payment route based on the current score of each of the candidate payment routes.

9. A computer device, characterized in that: including a processor and a memory; The memory stores a computer program or computer instruction that can be loaded by the processor and execute the big data-based intelligent payment routing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program or computer instructions that can be loaded by a processor and execute the big data-based intelligent payment routing method as described in any one of claims 1 to 7.

Images