Method and device for determining cross-border remittance service mode

The minimum-cost remittance service method is determined through the cross-border remittance service selection model, which solves the problem of uncertain fees due to multiple intermediate nodes in cross-border remittances, improves efficiency and accuracy, and promotes intelligent operations.

CN113592474BActive Publication Date: 2024-11-12INDUSTRIAL AND COMMERCIAL BANK OF CHINA
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202110875924.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-07-30
Publication Date
2024-11-12
Estimated Expiration
2041-07-30

AI Technical Summary

Technical Problem

During the cross-border remittance process, the remittance process involves multiple intermediate nodes, and the charging situation of each agent bank is uncertain, resulting in the remitter or remittance bank that needs to bear higher fees or operating costs.

Method used

The pre-created cross-border remittance service selection model calculates the received remittance request and remittance path, determines the lowest cost cross-border remittance service method, and generates remittance messages based on the reasonable verification results and sends them to the remittance message route. network.

Benefits of technology

It greatly reduces the manual query process, improves remittance efficiency, reduces error rate, promotes intelligent operations, has adaptability and dynamic update capabilities, which is better than the method of setting up a rule base.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113592474B_ABST
    Figure CN113592474B_ABST
Patent Text Reader

Abstract

The present invention provides a method and device for determining a cross-border remittance service mode, and relates to machine learning technology and the financial field. The method includes: using a pre-created cross-border remittance service selection model to calculate the cost of the received remittance request and remittance path, and obtaining a first cross-border remittance service mode; verifying the rationality of the first cross-border remittance service mode according to a preset remittance rule; determining the actual cross-border remittance service mode according to the rationality verification result, and generating a remittance message according to the remittance request, the remittance path and the actual cross-border remittance service mode; sending the remittance message to the remittance message routing network. This application greatly reduces the manual query link, reduces the manual selection of business, improves the efficiency of remittance, reduces the error rate, and promotes the intelligent operation process of our bank.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to machine learning technology and the financial field, and in particular to a method and device for determining a cross-border remittance service mode. Background Art

[0002] At present, the cross-border remittance process mainly includes two remittance methods: full amount remittance and full amount payment remittance. Among them, when full amount remittance is adopted, after the agent bank receives the cross-border remittance message, it can ensure that the funds are remitted to the receiving bank in full, and the payee can receive the remittance amount in full. The agent bank will bear the subsequent remittance fee collection fees of other agent banks and receiving banks; when full amount payment remittance is adopted, after the agent bank receives the cross-border remittance message, it only ensures that the funds are remitted to the next node in full. The subsequent agent bank and receiving bank may deduct fees from the remittance message, and the payee may not receive the full amount of the remittance.

[0003] Since the remittance process involves many intermediate nodes and the charging situation of each agent bank is uncertain, the remitter has to pay higher remittance fees or the remittance bank needs to invest higher operating costs. Summary of the invention

[0004] In order to solve the problems existing in the prior art, the present application provides a method for determining a cross-border remittance service mode, including:

[0005] Using a pre-created cross-border remittance service selection model, a fee calculation is performed on the received remittance request and the remittance path to obtain a first cross-border remittance service method;

[0006] Verify the rationality of the first cross-border remittance service method according to the preset remittance rules;

[0007] Determine the actual cross-border remittance service method according to the rationality verification result, and generate a remittance message according to the remittance request, the remittance path and the actual cross-border remittance service method;

[0008] The remittance message is sent to a remittance message routing network.

[0009] In one embodiment, determining the actual cross-border remittance service mode according to the rationality verification result, and generating a remittance message according to the remittance request, the remittance path and the actual cross-border remittance service mode, includes:

[0010] When the rationality verification passes, a remittance message is generated according to the remittance request, the remittance path and the first cross-border remittance service method.

[0011] In one embodiment, the determining the actual cross-border remittance service mode according to the rationality verification result, and generating a remittance message according to the remittance request, the remittance path and the actual cross-border remittance service mode, further includes:

[0012] When the rationality verification fails, a second cross-border remittance service method is determined according to the remittance rule, and a remittance message is generated according to the remittance request, the remittance path and the second cross-border remittance service method.

[0013] In one embodiment, the method of using a pre-created cross-border remittance service selection model to calculate the cost of a received remittance request and a remittance path to obtain a first cross-border remittance service method includes:

[0014] Inputting the remittance request and the remittance path into the cross-border remittance service selection model to determine the estimated fee amount of each bank node when providing different cross-border remittance services according to the charging rules of each bank node in the remittance path;

[0015] Calculate the estimated total amount of charges when choosing different cross-border remittance service methods based on the estimated amount of charges;

[0016] The cross-border remittance service method with the lowest total estimated fee amount is determined as the first cross-border remittance service method.

[0017] In one embodiment, the cross-border remittance service mode includes a full payment service and a full amount to account service;

[0018] The estimated total amount of charges when selecting different cross-border remittance service methods is calculated based on the estimated amount of charges, including:

[0019] Calculate the sum of the estimated charges for the full payment service provided by each bank node to obtain the estimated total charge amount corresponding to the full payment service method; and

[0020] Calculate the sum of the estimated charges for the full amount to account service provided by each bank node to obtain the total estimated charge amount corresponding to the full amount to account service method.

[0021] In one embodiment, the step of pre-creating the cross-border remittance service selection model includes:

[0022] Obtain remittance information and remittance routes of historical cross-border remittance transactions;

[0023] Extract the fee information of each bank node in the remittance path of historical cross-border remittance transactions;

[0024] The cross-border remittance service selection model is obtained by training according to the charging information.

[0025] The present application also provides a device for determining a cross-border remittance service mode, including:

[0026] A service mode recommendation module, used to calculate the cost of the received remittance request and remittance path using a pre-created cross-border remittance service selection model to obtain a first cross-border remittance service mode;

[0027] A service mode verification module, used to verify the rationality of the first cross-border remittance service mode according to preset remittance rules;

[0028] A remittance message generation module, used to determine the actual cross-border remittance service mode according to the rationality verification result, and generate a remittance message according to the remittance request, the remittance path and the actual cross-border remittance service mode;

[0029] The remittance message sending module is used to send the remittance message to the remittance message routing network.

[0030] In one embodiment, the remittance message generation module includes:

[0031] A service mode updating unit, configured to determine a second cross-border remittance service mode according to the remittance rule when the rationality verification fails;

[0032] A remittance message generating unit is used to generate a remittance message according to the remittance request, the remittance path and the first cross-border remittance service method when the rationality verification passes; and to generate a remittance message according to the remittance request, the remittance path and the second cross-border remittance service method when the rationality verification fails.

[0033] In one embodiment, the service mode recommendation module includes:

[0034] an estimated charge amount determination unit, configured to input the remittance request and the remittance path into the cross-border remittance service selection model, so as to determine the estimated charge amount of each bank node when providing different cross-border remittance services according to the charging rules of each bank node in the remittance path;

[0035] An estimated total amount of charges determining unit, used to calculate the estimated total amount of charges when different cross-border remittance service methods are selected according to the estimated amount of charges;

[0036] The service mode determination unit is used to determine the cross-border remittance service mode with the lowest estimated total fee amount as the first cross-border remittance service mode.

[0037] In one embodiment, the cross-border remittance service mode includes a full payment service and a full amount to account service;

[0038] The estimated total charge amount determination unit is specifically used for:

[0039] Calculate the sum of the estimated charges for the full payment service provided by each bank node to obtain the estimated total charge amount corresponding to the full payment service method; and

[0040] Calculate the sum of the estimated charges for the full amount to account service provided by each bank node to obtain the total estimated charge amount corresponding to the full amount to account service method.

[0041] In one embodiment, the cross-border remittance service mode determination device further includes a service selection model training module, which is used to:

[0042] Obtain remittance information and remittance routes of historical cross-border remittance transactions;

[0043] Extract the fee information of each bank node in the remittance path of historical cross-border remittance transactions;

[0044] The cross-border remittance service selection model is obtained by training according to the charging information.

[0045] The cross-border remittance service mode determination method and device of the present application utilize machine learning technology to realize the intelligent selection of full amount arrival service and full amount payment service, which can solve the problem that when sending cross-border remittance messages, it is impossible to obtain the charging situation of each node in the remittance route through which the message passes, and it is necessary to use various query systems or experience to judge whether the remittance should choose the full amount arrival service or the full amount payment service. The present application greatly reduces the manual query link, reduces the manual selection of business, improves the efficiency of remittance, reduces the error rate, and promotes the intelligent operation process of our bank; at the same time, the present application has the characteristics of self-adaptation, continuous learning, and updating of models, and can flexibly and dynamically perform self-update; it is better than the method of setting up a rule base. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art 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 work.

[0047] Figure 1 A schematic diagram of the method for determining the cross-border remittance service mode for this application.

[0048] Figure 2 Another schematic diagram of the method for determining cross-border remittance service mode.

[0049] Figure 3 Illustration of the steps to select a model for pre-creating a cross-border remittance service.

[0050] Figure 4 Another schematic diagram of the method for determining cross-border remittance service mode.

[0051] Figure 5 A schematic diagram of a device for determining a cross-border remittance service method.

[0052] Figure 6 Another schematic diagram of a device for determining a cross-border remittance service mode.

[0053] Figure 7 Another schematic diagram of a device for determining a cross-border remittance service mode.

[0054] Figure 8 Another schematic diagram of a device for determining a cross-border remittance service mode.

[0055] Fig. 9 A schematic diagram of an electronic device. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of 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.

[0057] This application provides a method for determining a cross-border remittance service mode, such as Figure 1 As shown, the method comprises the following steps:

[0058] Step S101, using a pre-created cross-border remittance service selection model to calculate the cost of the received remittance request and remittance path, to obtain a first cross-border remittance service method.

[0059] Specifically, the execution subject of the cross-border remittance service mode determination method can be a device for determining the cross-border remittance service mode in the cross-border remittance system. The above remittance request at least includes information such as the remitter, the remittance bank, the remittance amount, the payee, the receiving bank, the remittance path, and the blacklist verification result, wherein the selection of the remittance path and the blacklist verification operation are performed by the relevant devices of the cross-border remittance system. The focus of this application is on the selection of the cross-border remittance service mode, so how to realize the selection of the remittance path and the blacklist verification is not described in more detail here, and reference can be made to the relevant prior art.

[0060] The important basis for determining the cross-border remittance service mode in this application is the fee amount of each bank node in the remittance path. Therefore, step S101 will select a cross-border remittance service mode with the lowest fee amount.

[0061] Step S102: verifying the rationality of the first cross-border remittance service method according to preset remittance rules.

[0062] Specifically, step S102 verifies the rationality of the first cross-border remittance service method determined in step S101 to obtain a verification result.

[0063] Among them, the remittance rules define the cross-border remittance service methods that are preferentially adopted when multiple bank nodes execute cross-border remittances. The existing cross-border remittance service methods mainly include two types, one is a full amount arrival service method, and a full amount payment service method. The first cross-border remittance service method obtained in step S101 is one of the above two service methods. For some bank nodes, they give priority to providing full amount arrival service or full amount payment service. Therefore, when making cross-border remittances through these bank nodes, it is necessary to select the corresponding service method according to the services provided to avoid cross-border remittance failure. The corresponding relationship between each bank node and the cross-border remittance service it provides preferentially is stored in a table. When a bank node does not define a cross-border remittance service that is preferentially provided, the corresponding position in the table is empty, which means that it can provide any cross-border remittance service. For details, see Table 1.

[0064] Table 1: Correspondence table of cross-border remittance services provided by bank nodes first

[0065] Bank Node Priority cross-border remittance services Corresponding cross-border remittance service methods Bank Node 1 Full amount payment service Full amount payment service Bank Node 2 —— —— …… …… …… Bank Node n Full payment service Full payment service method

[0066] In step S102, the rationality verification is specifically as follows: obtaining the cross-border remittance service that each bank node in the remittance path preferentially provides; determining whether there is at least one bank node whose preferentially provided cross-border remittance service does not correspond to the first cross-border remittance service mode obtained in step S101, if so, the rationality verification fails; if not, the rationality verification passes. For a bank node that does not define a preferentially provided cross-border remittance service, it can provide any cross-border remittance service, so step S102 actually only verifies the bank node that defines the preferentially provided cross-border remittance service.

[0067] Step S103, determining the actual cross-border remittance service mode according to the rationality verification result, and generating a remittance message according to the remittance request, the remittance path and the actual cross-border remittance service mode.

[0068] Specifically, the rationality verification result in step S102 includes two types: verification passed and verification failed. When the verification result is verification passed, the actual cross-border remittance service mode is the first cross-border remittance service mode obtained in step S101, and when the verification result is verification failed, the actual cross-border remittance service mode is determined according to the cross-border remittance service preferentially provided by each bank node. Finally, a remittance message is generated according to the received remittance request, remittance path and the determined actual cross-border remittance service mode.

[0069] Step S104, sending the remittance message to a remittance message routing network.

[0070] Among them, the cross-border remittance message is transmitted to the next bank node in the remittance path through the remittance message routing network (such as the SWIFT network).

[0071] The cross-border remittance service mode determination method of the present application utilizes machine learning technology to realize intelligent selection of full amount arrival service and full amount payment service, which can solve the problem that when sending cross-border remittance messages, it is impossible to obtain the charging situation of each node in the remittance route through which the message passes, and it is necessary to use various query systems or rely on experience to determine whether the remittance should choose the full amount arrival service or the full amount payment service.

[0072] In one embodiment, if Figure 2 As shown, step S103, determining the actual cross-border remittance service mode according to the rationality verification result, and generating a remittance message according to the remittance request, the remittance path and the actual cross-border remittance service mode, includes step S1031:

[0073] When the rationality verification passes, a remittance message is generated according to the remittance request, the remittance path and the first cross-border remittance service method.

[0074] Specifically, when the rationality verification in step S102 passes, the first cross-border remittance service mode determined in step S101 is used as the actual cross-border remittance service mode, and a remittance message is generated according to the remittance request, the remittance path and the first cross-border remittance service mode.

[0075] In one embodiment, if Figure 2 As shown, the step S103 further includes step S1032:

[0076] When the rationality verification fails, a second cross-border remittance service method is determined according to the remittance rule, and a remittance message is generated according to the remittance request, the remittance path and the second cross-border remittance service method.

[0077] Specifically, when the rationality verification in step S102 fails, the cross-border remittance service mode output by the cross-border remittance service selection model is not selected, but the second cross-border remittance service mode is re-determined according to the remittance rule, and at this time, the second cross-border remittance service mode is the actual cross-border remittance service mode. A remittance message is generated according to the remittance request, the remittance path and the second cross-border remittance service mode.

[0078] For example, assuming that the cross-border remittance service selection model outputs the cross-border remittance service mode as a full payment service mode based on the information of each bank node in the remittance path, during the rationality verification, it is obtained that bank node A in the remittance path defines that the priority cross-border remittance service is the full amount arrival service, and the other bank nodes have not defined the priority cross-border remittance service. At this time, since the full amount arrival service and the full payment service mode are not corresponding, it is necessary to update the actual cross-border remittance service mode to the full amount arrival service mode according to the priority cross-border remittance service defined by bank node A.

[0079] For another example, suppose that the cross-border remittance service selection model outputs the cross-border remittance service mode as the full payment service mode according to the information of each bank node in the remittance path. During the rationality verification, it is obtained that the bank node A in the remittance path defines the cross-border remittance service provided as the full amount arrival service, and the bank nodes B, C and D define the cross-border remittance service provided as the full amount payment service. The remaining bank nodes do not define the cross-border remittance service provided as the priority. At this time, it includes both bank nodes that give priority to full amount arrival services and bank nodes that give priority to full amount payment services. According to the remittance rules, since the number of bank nodes that give priority to full amount payment services is greater than the number of bank nodes that give priority to full amount arrival services, the actual cross-border remittance service mode is updated to the full amount payment service mode. When the number of bank nodes that give priority to full amount payment services is equal to the number of bank nodes that give priority to full amount arrival services, any cross-border remittance service mode can be randomly selected as the actual cross-border remittance service mode.

[0080] It should be noted that in cross-border remittances, after the actual cross-border remittance service method is determined, each bank node in the remittance path provides the cross-border remittance service corresponding to the actual cross-border remittance service method, that is, the cross-border remittance services provided by each bank node in the remittance path are the same, all are full amount arrival services or all are full amount payment services, rather than some bank nodes providing full amount payment services and other bank nodes providing full amount arrival services.

[0081] In one embodiment, if Figure 3 As shown, the steps of pre-creating the cross-border remittance service selection model include:

[0082] Step S301, obtaining remittance information and remittance paths of historical cross-border remittance transactions.

[0083] Specifically, the remittance information of historical cross-border remittance transactions includes the remitter, the remitting bank, the remittance amount, the payee and the receiving bank, etc.; the remittance path includes each bank node passed through in the cross-border remittance.

[0084] Step S302, extracting the charging information of each bank node in the remittance path of the historical cross-border remittance transaction.

[0085] Specifically, when the remitting bank, receiving bank, remittance amount and cross-border remittance service method in the remittance information are different, the charges of each bank node in the remittance path are different. Therefore, for each historical cross-border remittance transaction record, the charging information of each bank node in the remittance path corresponding to the transaction record under the remittance information corresponding to the transaction record is extracted as training data for the cross-border remittance service selection model.

[0086] Step S303: obtaining the cross-border remittance service selection model through training according to the charging information.

[0087] The cross-border remittance service selection model is trained according to the training data in step S302. The input data of the trained cross-border remittance service selection model is the remittance information, and the output data is the first cross-border remittance service mode.

[0088] It can be understood that a commonly used machine learning model in the art can be selected as the initial model of the cross-border remittance service selection model, and the initial model can be trained according to the above steps S301 to S303 to obtain the cross-border remittance service selection model used in this application.

[0089] Each time the cross-border remittance service selection model is used to obtain the first cross-border remittance service method corresponding to the remittance request and the remittance path, the input result of the cross-border remittance service selection model is fed back to the cross-border remittance service selection model, so that the cross-border remittance service selection model can continuously learn and dynamically update.

[0090] In one embodiment, if Figure 4 As shown, step S101, using a pre-created cross-border remittance service selection model to calculate the cost of the received remittance request and the remittance path, to obtain a first cross-border remittance service method, including:

[0091] Step S1011, inputting the remittance request and the remittance path into the cross-border remittance service selection model to determine the estimated charge amount of each bank node when providing different cross-border remittance services according to the charging rules of each bank node in the remittance path.

[0092] Specifically, when the remittance bank, beneficiary bank, remittance amount and other information in the remittance request are different, the fee charged by each bank node in the remittance path may be different. Therefore, the remittance request and remittance path are input into the cross-border remittance service selection model, which will calculate the estimated fee charged by each bank node in the remittance path for remittance operations according to the remittance request when the full amount arrival service mode is selected; and the estimated fee charged by each bank node in the remittance path for remittance operations according to the remittance request when the full amount payment service mode is selected.

[0093] Therefore, after step S1011 is executed, the estimated charging amount of each bank node in the remittance path when providing full amount arrival service and the estimated charging amount when providing full amount payment service can be obtained. For details, please refer to Table 2.

[0094] Table 2: Estimated fees for different cross-border remittance services provided by various bank nodes

[0095]

[0096]

[0097] Step S1012, calculating the estimated total amount of charges when different cross-border remittance service modes are selected according to the estimated amount of charges.

[0098] Specifically, the estimated fee amount of each bank node in the remittance path when providing the full amount to account service is obtained, and the sum of the estimated fee amounts of each bank node when providing the full amount to account service is calculated to obtain the total estimated fee amount corresponding to the full amount to account service mode (see Table 2); and

[0099] Obtain the estimated fee amount of each bank node in the remittance path when providing full payment service, calculate the sum of the estimated fee amount of each bank node when providing full payment service, and obtain the estimated total fee amount corresponding to the full payment service method (see Table 2).

[0100] Step S1013: determining the cross-border remittance service method with the lowest total estimated fee amount as the first cross-border remittance service method.

[0101] Specifically, the estimated total amount of charges corresponding to the full amount arrival service mode is compared with the estimated total amount of charges corresponding to the full amount payment service mode, and the cross-border remittance service mode with a smaller estimated total amount of charges is determined as the first cross-border remittance service mode and output.

[0102] The cross-border remittance service mode determination method and device of the present application utilize machine learning technology to realize the intelligent selection of full amount arrival service and full amount payment service, which can solve the problem that when sending cross-border remittance messages, it is impossible to obtain the charging situation of each node in the remittance route through which the message passes, and it is necessary to use various query systems or experience to judge whether the remittance should choose the full amount arrival service or the full amount payment service. The present application greatly reduces the manual query link, reduces the manual selection of business, improves the efficiency of remittance, reduces the error rate, and promotes the intelligent operation process of our bank; at the same time, the present application has the characteristics of self-adaptation, continuous learning, and updating of models, and can flexibly and dynamically perform self-update; it is better than the method of setting up a rule base.

[0103] Based on the same inventive concept, the embodiment of the present application also provides a cross-border remittance service mode determination device, which can be used to implement the method described in the above embodiment, as described in the following embodiment. Since the principle of the cross-border remittance service mode determination device to solve the problem is similar to the cross-border remittance service mode determination method, the implementation of the cross-border remittance service mode determination device can refer to the implementation of the cross-border remittance service mode determination method, and the repetitions are not repeated. As used below, the term "unit" or "module" can implement a combination of software and / or hardware of a predetermined function. Although the system described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0104] The present application also provides a device for determining a cross-border remittance service mode, such as Figure 5 As shown, the device comprises:

[0105] The service mode recommendation module 501 is used to calculate the cost of the received remittance request and remittance path using a pre-created cross-border remittance service selection model to obtain a first cross-border remittance service mode;

[0106] A service mode verification module 502, used to verify the rationality of the first cross-border remittance service mode according to a preset remittance rule;

[0107] A remittance message generation module 503, used to determine the actual cross-border remittance service mode according to the rationality verification result, and generate a remittance message according to the remittance request, the remittance path and the actual cross-border remittance service mode;

[0108] The remittance message sending module 504 is used to send the remittance message to the remittance message routing network.

[0109] In one embodiment, if Figure 6 As shown, the remittance message generation module 503 includes:

[0110] A service mode updating unit 5031, configured to determine a second cross-border remittance service mode according to the remittance rule when the rationality verification fails;

[0111] The remittance message generating unit 5032 is used to generate a remittance message according to the remittance request, the remittance path and the first cross-border remittance service method when the rationality verification passes; and to generate a remittance message according to the remittance request, the remittance path and the second cross-border remittance service method when the rationality verification fails.

[0112] In one embodiment, if Figure 7 As shown, the service mode recommendation module 501 includes:

[0113] An estimated charge amount determination unit 5011 is used to input the remittance request and the remittance path into the cross-border remittance service selection model, so as to determine the estimated charge amount of each bank node when providing different cross-border remittance services according to the charging rules of each bank node in the remittance path;

[0114] An estimated total amount of charges determining unit 5012, used to calculate the estimated total amount of charges when different cross-border remittance service modes are selected according to the estimated amount of charges;

[0115] The service mode determining unit 5013 is used to determine the cross-border remittance service mode with the lowest estimated total fee amount as the first cross-border remittance service mode.

[0116] In one embodiment, the cross-border remittance service mode includes a full payment service and a full amount to account service;

[0117] The estimated total charge amount determination unit 5011 is specifically used for:

[0118] Calculate the sum of the estimated charges for the full payment service provided by each bank node to obtain the estimated total charge amount corresponding to the full payment service method; and

[0119] Calculate the sum of the estimated charges for the full amount to account service provided by each bank node to obtain the total estimated charge amount corresponding to the full amount to account service method.

[0120] In one embodiment, if Figure 8 As shown, the cross-border remittance service mode determination device also includes a service selection model training module 505, which is used to:

[0121] Obtain remittance information and remittance routes of historical cross-border remittance transactions;

[0122] Extract the fee information of each bank node in the remittance path of historical cross-border remittance transactions;

[0123] The cross-border remittance service selection model is obtained by training according to the charging information.

[0124] The cross-border remittance service mode determination method and device of the present application utilize machine learning technology to realize the intelligent selection of full amount arrival service and full amount payment service, which can solve the problem that when sending cross-border remittance messages, it is impossible to obtain the charging situation of each node in the remittance route through which the message passes, and it is necessary to use various query systems or experience to judge whether the remittance should choose the full amount arrival service or the full amount payment service. The present application greatly reduces the manual query link, reduces the manual selection of business, improves the efficiency of remittance, reduces the error rate, and promotes the intelligent operation process of our bank; at the same time, the present application has the characteristics of self-adaptation, continuous learning, and updating of models, and can flexibly and dynamically perform self-update; it is better than the method of setting up a rule base.

[0125] The present invention also provides an electronic device, see Fig. 9 , the electronic device 100 specifically includes:

[0126] A central processing unit (processor) 110 , a memory (memory) 120 , a communication module (Communications) 130 , an input unit 140 , an output unit 150 and a power supply 160 .

[0127] The memory 120, the communication module 130, the input unit 140, the output unit 150 and the power supply 160 are respectively connected to the central processing unit 110. The memory 120 stores a computer program, and the central processing unit 110 can call the computer program. When the central processing unit 110 executes the computer program, all the steps in the method for determining the cross-border remittance service mode in the above embodiment are implemented.

[0128] The embodiment of the present application further provides a computer storage medium for storing a computer program, wherein the computer program can be executed by a processor. When the computer program is executed by the processor, any method for determining a cross-border remittance service mode provided by the present invention is implemented.

[0129] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts refer to the partial description of the method embodiment. In the description of this specification, the description of the reference term "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of this specification.

[0130] In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradicting each other. The above is only an embodiment of the embodiment of this specification and is not intended to limit the embodiment of this specification. For those skilled in the art, the embodiment of this specification may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiment of this specification shall be included in the scope of the claims of the embodiment of this specification.

Claims

1. A method for determining a cross-border remittance service mode, characterized in that: include: Using a pre-created cross-border remittance service selection model, a fee calculation is performed on the received remittance request and the remittance path to obtain a first cross-border remittance service method; Verify the rationality of the first cross-border remittance service method according to the preset remittance rules; Determine the actual cross-border remittance service method according to the rationality verification result, and generate a remittance message according to the remittance request, the remittance path and the actual cross-border remittance service method; Sending the remittance message to a remittance message routing network; The method of using a pre-created cross-border remittance service selection model to calculate the cost of the received remittance request and the remittance path to obtain the first cross-border remittance service method includes: Inputting the remittance request and the remittance path into the cross-border remittance service selection model to determine the estimated fee amount of each bank node when providing different cross-border remittance services according to the charging rules of each bank node in the remittance path; Calculate the estimated total amount of charges when selecting different cross-border remittance service methods based on the estimated amount of charges; the cross-border remittance service methods include full payment service and full amount to account service; The cross-border remittance service method with the lowest total estimated fee amount is determined as the first cross-border remittance service method.

2. The method for determining a cross-border remittance service mode according to claim 1, characterized in that: The determining of the actual cross-border remittance service mode according to the rationality verification result, and generating a remittance message according to the remittance request, the remittance path and the actual cross-border remittance service mode, includes: When the rationality verification passes, a remittance message is generated according to the remittance request, the remittance path and the first cross-border remittance service method.

3. The method for determining a cross-border remittance service mode according to claim 2, characterized in that: The determining of the actual cross-border remittance service mode according to the rationality verification result, and generating a remittance message according to the remittance request, the remittance path and the actual cross-border remittance service mode, further includes: When the rationality verification fails, a second cross-border remittance service method is determined according to the remittance rule, and a remittance message is generated according to the remittance request, the remittance path and the second cross-border remittance service method.

4. The method for determining a cross-border remittance service mode according to claim 1, characterized in that: The estimated total amount of charges when selecting different cross-border remittance service methods is calculated based on the estimated amount of charges, including: Calculate the sum of the estimated charges for the full payment service provided by each bank node to obtain the estimated total charge amount corresponding to the full payment service method; and Calculate the sum of the estimated charges for the full amount to account service provided by each bank node to obtain the total estimated charge amount corresponding to the full amount to account service method.

5. The method for determining a cross-border remittance service mode according to any one of claims 1 to 3, characterized in that: The steps of pre-creating the cross-border remittance service selection model include: Obtain remittance information and remittance routes of historical cross-border remittance transactions; Extract the fee information of each bank node in the remittance path of historical cross-border remittance transactions; The cross-border remittance service selection model is obtained by training according to the charging information.

6. A device for determining a cross-border remittance service mode, characterized in that: include: A service mode recommendation module, used to calculate the cost of the received remittance request and remittance path using a pre-created cross-border remittance service selection model to obtain a first cross-border remittance service mode; A service mode verification module, used to verify the rationality of the first cross-border remittance service mode according to preset remittance rules; A remittance message generation module, used to determine the actual cross-border remittance service mode according to the rationality verification result, and generate a remittance message according to the remittance request, the remittance path and the actual cross-border remittance service mode; A remittance message sending module, used for sending the remittance message to a remittance message routing network; Wherein, the service mode recommendation module includes: an estimated charge amount determination unit, configured to input the remittance request and the remittance path into the cross-border remittance service selection model, so as to determine the estimated charge amount of each bank node when providing different cross-border remittance services according to the charging rules of each bank node in the remittance path; An estimated total amount of charges determining unit, used to calculate the estimated total amount of charges when different cross-border remittance service modes are selected according to the estimated amount of charges; the cross-border remittance service modes include full payment service and full amount to account service; The service mode determination unit is used to determine the cross-border remittance service mode with the lowest estimated total fee amount as the first cross-border remittance service mode.

7. The cross-border remittance service mode determination device according to claim 6, characterized in that: The remittance message generating module comprises: A service mode updating unit, configured to determine a second cross-border remittance service mode according to the remittance rule when the rationality verification fails; A remittance message generating unit is used to generate a remittance message according to the remittance request, the remittance path and the first cross-border remittance service method when the rationality verification passes; and to generate a remittance message according to the remittance request, the remittance path and the second cross-border remittance service method when the rationality verification fails.

8. The cross-border remittance service mode determination device according to claim 6, characterized in that: The estimated total charge amount determination unit is specifically used for: Calculate the sum of the estimated charges for the full payment service provided by each bank node to obtain the estimated total charge amount corresponding to the full payment service method; and Calculate the sum of the estimated charges for the full amount to account service provided by each bank node to obtain the total estimated charge amount corresponding to the full amount to account service method.

9. The cross-border remittance service mode determination device according to claim 6 or 7, characterized in that: Also includes a service selection model training module for: Obtain remittance information and remittance routes of historical cross-border remittance transactions; Extract the fee information of each bank node in the remittance path of historical cross-border remittance transactions; The cross-border remittance service selection model is obtained by training according to the charging information.

10. An electronic device, characterized in that: include: A central processing unit, a memory, and a communication module, wherein a computer program is stored in the memory, the central processing unit can call the computer program, and when the central processing unit executes the computer program, the method for determining the cross-border remittance service mode according to any one of claims 1 to 5 is implemented.

11. A computer storage medium for storing a computer program, characterized in that: When the computer program is executed by a processor, the method for determining a cross-border remittance service mode according to any one of claims 1 to 5 is implemented.

Citation Information

Patent Citations

  • Cross-border remittance method and device and electronic equipment

    CN111553790A

  • Remittance path recommendation method and device

    CN112017028A

  • Information recommendation method and device

    CN112037044A

  • Path generation method and device, storage medium and electronic equipment

    CN112183828A

  • Information verification method and device, equipment, medium and program product

    CN113159780A