Cross-border remittance method, device, equipment and medium

Abstract

The present disclosure provides a cross-bank remittance method, relating to the financial field. The method comprises: obtaining N current remittance elements of a to-be-remitted business; obtaining a remittance success rate of each current remittance element in the N current remittance elements based on a pre-obtained remittance prediction set, predicting a remittance result of the to-be-remitted business according to the remittance success rate of each current remittance element; and if the remittance result is successful, handling the to-be-remitted business according to the N remittance elements. The present disclosure can perform pre-check before cross-bank remittance, improve the success rate of cross-bank remittance, reduce the operation cost and time cost wasted due to the failure of remittance business handling, and improve the customer experience. The present disclosure also provides a cross-bank remittance device, equipment, storage medium and program product.

Description

Technical Field

[0001] This disclosure relates to the financial sector, and more specifically, to a method, apparatus, equipment, medium, and procedure for interbank remittance. Background Technology

[0002] In interbank remittances, customers can transfer funds from the remitting bank to the receiving bank's account through systems such as the People's Bank of China's online banking interconnection system. Some banks, acting as receiving banks, impose special restrictions on transactions using the online banking interconnection system; for example, certain receiving accounts are not permitted to use this system. Since neither the remitting bank nor the customer can predict the remittance outcome beforehand—for example, they may not be able to identify account issues in advance—this situation can frequently lead to interbank remittance failures when the remitting bank conducts online banking interconnection transactions with the aforementioned receiving banks. Receiving a remittance failure notification from the receiving bank after the remittance transaction is completed wastes operational and time costs during the remittance process and also reduces customer experience. Summary of the Invention

[0003] In view of the above problems, this disclosure provides an interbank remittance method, apparatus, equipment, medium and program product that can predict the remittance results of pending remittance transactions in advance.

[0004] One aspect of this disclosure provides a method for interbank remittance, comprising: obtaining N current remittance elements for a pending remittance transaction, wherein the N current remittance elements are generated based on the remitter's remittance operation; obtaining a remittance success rate for each of the N current remittance elements based on a pre-obtained remittance prediction set, wherein the remittance prediction set includes M remittance success rates corresponding one-to-one with M historical remittance elements, the M historical remittance elements including some or all of the N current remittance elements, and M and N being integers greater than or equal to 1; predicting the remittance result of the pending remittance transaction based on the remittance success rate of each current remittance element; and if the remittance result is successful, processing the pending remittance transaction based on the N remittance elements.

[0005] According to an embodiment of this disclosure, obtaining the remittance success rate of each of the N current remittance elements based on a pre-obtained remittance prediction set includes: determining the remittance period of the pending remittance business; and determining the remittance success rate of each current remittance element under the corresponding historical period from the remittance prediction set according to the remittance period; wherein the remittance prediction set includes S historical periods, and each historical period corresponds to M remittance success rates that correspond one-to-one with M historical remittance elements, and S is an integer greater than or equal to 1.

[0006] According to embodiments of this disclosure, before obtaining the remittance success rate of each of the N current remittance elements, the method further includes pre-obtaining the remittance prediction set, specifically including: obtaining a first sample space based on historical remittance data within a first preset time period, wherein the historical remittance data includes at least one historical remittance transaction within the first preset time period, and each remittance transaction has at least one historical remittance element; obtaining a second sample space based on historical remittance data within a second preset time period, wherein the second preset time period is earlier than the first preset time period; determining historical remittance data for S historical time periods that are at a specific distance from the first sample space from the second sample space, wherein the S historical time periods are S sub-time periods within the second preset time period; and obtaining the remittance prediction set based on the historical remittance data for the S historical time periods.

[0007] According to embodiments of this disclosure, the length of the second preset time period is greater than or equal to at least two lengths of the first preset time period. The step of determining the historical remittance data of the S historical time periods that have a specific distance from the first sample space from the second sample space includes: obtaining a first remittance sequence of historical remittance transactions under a first sub-time period based on the remittance time point; obtaining at least two second remittance sequences of historical remittance transactions under at least two second sub-time periods respectively; determining K second remittance sequences from the at least two second remittance sequences using a classification algorithm based on the first remittance sequence, wherein the K second remittance sequences have the specific distance from the first remittance sequence, and K is an integer greater than or equal to 1; wherein the first sub-time period is any one of the first preset time periods, and the at least two second sub-time periods are sub-time periods in the second preset time period that have the same position as the first sub-time period, and the position includes time positions within the same time granularity.

[0008] According to embodiments of this disclosure, obtaining the remittance prediction set based on historical remittance data from the S historical time periods includes: for each of the M historical remittance elements, obtaining the remittance result of each historical remittance element from the K second remittance sequences; and determining the remittance success rate of each historical remittance element based on the average of the remittance results of each historical remittance element.

[0009] According to an embodiment of this disclosure, obtaining the remittance result of each historical remittance element from the K second remittance sequences includes: for each historical remittance element, taking the remittance result of the historical remittance business containing that historical remittance element as the remittance result of each historical remittance element, wherein the historical remittance element includes at least one of receiving bank, receiving account, remittance time, remittance amount, and remittance method.

[0010] According to embodiments of this disclosure, predicting the remittance result of the pending remittance transaction based on the remittance success rate of each current remittance element includes: determining the lowest or highest remittance success rate among the N remittance success rates corresponding to the N current remittance elements; and predicting the remittance result of the pending remittance transaction based on the lowest or highest remittance success rate.

[0011] Another aspect of this disclosure provides an interbank remittance device, comprising: an element acquisition module, configured to acquire N current remittance elements for a pending remittance transaction, wherein the N current remittance elements are generated based on the remitter's remittance operation; a success rate module, configured to acquire a remittance success rate for each of the N current remittance elements based on a pre-acquired remittance prediction set, wherein the remittance prediction set includes M remittance success rates corresponding one-to-one with M historical remittance elements, the M historical remittance elements including some or all of the N current remittance elements, and M and N being integers greater than or equal to 1; a remittance result module, configured to predict the remittance result of the pending remittance transaction based on the remittance success rate of each current remittance element; and a transaction processing module, configured to process the pending remittance transaction based on the N remittance elements if the remittance result is successful.

[0012] Another aspect of this disclosure provides an electronic device, including: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors perform the method as described above.

[0013] Another aspect of this disclosure provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the method described above.

[0014] Another aspect of this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the method described above.

[0015] One or more of the above embodiments have the following beneficial effects: By utilizing a remittance prediction set formed using the remittance success rate corresponding to historical remittance elements as a prediction benchmark, the remittance success rate of each of the N current remittance elements for the remittance transaction is obtained one by one, thereby determining the remittance result of the transaction. Only when the remittance is predicted to be successful is the transaction processed for interbank remittance. This allows for pre-checking before interbank remittance, improving the success rate of interbank remittances, reducing operational and time costs wasted due to failed remittance transactions, and improving customer experience. Attached Figure Description

[0016] The foregoing contents, as well as other objects, features, and advantages of this disclosure, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0017] Figure 1 This diagram illustrates an application scenario of the interbank remittance method according to an embodiment of the present disclosure.

[0018] Figure 2 A flowchart illustrating an interbank remittance method according to an embodiment of the present disclosure is shown schematically;

[0019] Figure 3 A flowchart illustrating blacklist matching according to an embodiment of this disclosure is shown schematically;

[0020] Figure 4 A flowchart illustrating the process of obtaining remittance success rate according to an embodiment of this disclosure is shown schematically;

[0021] Figure 5 A flowchart illustrating the prior acquisition of a remittance forecast set according to an embodiment of the present disclosure is shown schematically;

[0022] Figure 6 This illustration schematically shows a flowchart for determining historical remittance data for S historical time periods according to an embodiment of the present disclosure;

[0023] Figure 7 A flowchart illustrating the determination of remittance success rate for each historical remittance element according to an embodiment of this disclosure is shown schematically.

[0024] Figure 8 A flowchart illustrating the prediction of remittance results for pending remittance transactions according to embodiments of the present disclosure is shown schematically.

[0025] Figure 9 A schematic diagram illustrating the structure of an interbank remittance device according to an embodiment of the present disclosure; and

[0026] Figure 10 A block diagram schematically illustrates an electronic device suitable for implementing an interbank remittance method according to an embodiment of the present disclosure. Detailed Implementation

[0027] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0028] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0029] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0030] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0031] It should be noted that the interbank remittance methods, apparatus, devices, media, and program products of this disclosure can be used in the financial field for interbank remittance-related aspects, and can also be used in any field other than the financial field for transactions or data interaction between two related parties. The application fields of the interbank remittance methods, apparatus, devices, media, and program products of this disclosure are not limited.

[0032] In the technical solutions disclosed herein, user authorization or consent is obtained before acquiring or collecting user personal information (such as remittance data). The collection, storage, use, processing, transmission, provision, disclosure, and application of user personal information comply with relevant laws and regulations, necessary confidentiality measures are taken, and they do not violate public order and good morals.

[0033] Figure 1 The diagram illustrates an application scenario of the interbank remittance method according to an embodiment of the present disclosure.

[0034] like Figure 1 As shown, application scenario 100 according to this embodiment may include the People's Bank of China (PBOC) payment and clearing system 110, the remittance bank interbank clearing system 120, a big data platform 130, and an artificial intelligence platform 140. The PBOC payment and clearing system 110 is responsible for receiving and processing interbank remittance messages sent by the remittance bank interbank clearing system 120, such as sending them to the receiving bank, and responding accordingly to the processing results. The remittance bank interbank clearing system 120 is responsible for processing various types of customer interbank remittance requests and then sending them to the PBOC payment and clearing system 110. Figure 1As shown, the big data platform 130, the artificial intelligence platform 140, and the remittance bank interbank clearing system 120 are connected in pairs. The remittance bank interbank clearing system 120 provides historical interbank remittance data to the big data platform 130 for data analysis and to establish a relevant sample space. The artificial intelligence platform 140 receives the data transmitted by the big data platform 130, parses the data using appropriate algorithms (such as classification algorithms), obtains the characteristics of recent interbank remittance data, and provides services for the remittance bank interbank clearing system 120 to pre-verify future remittance transactions and determine whether to execute them based on the predicted remittance results.

[0035] The interbank clearing system 120, big data platform 130, and artificial intelligence platform 140 can be located on one or more servers. Users can use terminal devices to interact with the above one or more servers via the network to receive or send messages, etc. Various communication client applications can be installed on the terminal devices, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (for example only).

[0036] Terminal devices can be various electronic devices with a display screen and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0037] A server can be a server that provides various services, such as a backend management server that supports websites browsed by users using terminal devices (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0038] The following will be based on Figure 1 The described scene, through Figures 2-8 The interbank remittance method according to the embodiments of this disclosure will be described in detail.

[0039] Figure 2 A flowchart illustrating an interbank remittance method according to an embodiment of the present disclosure is shown schematically.

[0040] like Figure 2 As shown, the interbank remittance method in this embodiment includes operations S210 to S240.

[0041] In operation S210, N current remittance elements of the pending remittance transaction are obtained, wherein the N current remittance elements are generated based on the remitter's remittance operation.

[0042] For example, a remittance transaction refers to one or more interbank remittances initiated by a remitter (customer) through a remittance operation. A pending remittance transaction indicates that the remitting bank has not yet sent an interbank remittance message to the People's Bank of China's payment and clearing system 110. The remittance operation includes the remitter's method of remittance, the time of initiation of the interbank remittance, and the operation of filling in remittance information for each interbank remittance. Remittance elements include the remittance method, remittance time, and the remittance information filled in by the remitter, such as the payee, receiving bank, receiving account number, and remittance amount.

[0043] In operation S220, based on the pre-obtained remittance prediction set, the remittance success rate of each of the N current remittance elements is obtained. The remittance prediction set includes M remittance success rates that correspond one-to-one with M historical remittance elements. The M historical remittance elements include some or all of the elements in the N current remittance elements, and M and N are integers greater than or equal to 1.

[0044] For example, the sources of historical remittance elements and current remittance elements are different. Historical remittance elements are obtained by extracting completed interbank remittance transactions, while current remittance elements are obtained by extracting pending remittance transactions. The categories of historical and current remittance elements can be the same, such as remittance method, remittance time, payee, payee bank, payee account number, and remittance amount. For example, the remittance success rate corresponding to payee bank A in the remittance prediction set can be found using the payee bank A in the current remittance element.

[0045] In some embodiments, expert experience can be used to set corresponding remittance success rates for each of the M historical remittance elements.

[0046] In other embodiments, artificial intelligence algorithms can be used to learn the characteristics of each historical remittance element from historical remittance data and obtain the corresponding remittance success rate.

[0047] In some embodiments, if the M historical remittance elements include all N historical remittance elements, then N remittance success rates can be obtained from the remittance prediction set. If the M historical remittance elements include only some of the N historical remittance elements, then the remittance success rate corresponding to that portion of the elements can be obtained from the remittance prediction set. Other remittance success rates can be set according to actual needs to avoid affecting the final remittance result confirmation.

[0048] In operation S230, the remittance outcome of pending remittance transactions is predicted based on the remittance success rate of each current remittance element.

[0049] For example, the remittance result can be determined based on the average remittance success rate, the maximum or minimum remittance success rate, or by assigning different weights to each current remittance element and combining them with the corresponding remittance success rate to calculate the remittance result by comprehensively processing N calculated values. In some embodiments, the weight assigned to each current remittance element can be determined from the number of successful remittance transactions for that element; for example, if the number of successful remittance transactions for element A is greater than that for element B, then the weight is greater.

[0050] If the remittance result is successful when operating S240, proceed with the pending remittance business based on N remittance elements.

[0051] If the remittance is successful, an interbank remittance message is sent to the People's Bank of China's payment and clearing system 110 to process the pending remittance transaction. If the remittance fails, a notification is automatically generated to report to the customer, confirming whether the customer needs to continue processing, suggesting that the customer change some of the current remittance elements, or refusing to process the remittance for the customer. The automatically generated notification may include automatically identified reasons that led to the predicted remittance failure, such as a low success rate for a certain remittance element. The automatic identification process may also involve comparing the pending remittance transaction with historically failed remittance transactions, for example, using remittance element similarity calculations to identify the failed remittance transaction with the closest Euclidean distance, and returning the reason for the failure of that failed remittance transaction.

[0052] According to embodiments of this disclosure, a remittance prediction set is formed using the remittance success rate corresponding to historical remittance elements as a prediction benchmark. The remittance success rate of each of the N current remittance elements for the pending remittance transaction is obtained, thereby determining the remittance outcome. Only when the remittance is predicted to be successful is the remittance processed, resulting in an interbank remittance. This allows for pre-checking before interbank remittances, improving the success rate, reducing operational and time costs wasted due to failed remittance transactions, and enhancing customer experience.

[0053] Figure 3 A flowchart illustrating blacklist matching according to an embodiment of this disclosure is shown schematically.

[0054] like Figure 3 As shown, this embodiment determines the remittance result of the remittance business by performing operations S310 to S340.

[0055] During operation S310, the remitter bank's interbank clearing system 120 calls the pre-check service.

[0056] For example, when the remitting bank's interbank clearing system 120 receives a remittance transaction, it calls the pre-check service to obtain the remittance prediction set provided by the artificial intelligence platform 140 to obtain the remittance success rate of each element.

[0057] In operation S320, confirm whether the input parameter matches the blacklist. If yes, proceed to operation S330. If not, proceed to operation S340.

[0058] For example, the input parameters may include N current remittance elements. A method to improve the efficiency of interbank remittances based on a blacklist database can be provided, such as collecting and analyzing remittance failure records, using artificial intelligence learning algorithms to form a blacklist model for pre-checking of interbank remittances, thereby improving the success rate of interbank remittances.

[0059] The blacklist model and the pre-obtained remittance prediction set can be parallel. For example, by modeling historical interbank remittance failure data, a remittance blacklist model can be obtained, thereby enabling pre-checking of interbank remittances before calling the remittance prediction set.

[0060] The blacklist model can also be included as part of the remittance prediction set. For example, the blacklist can include current remittance elements with low success rates.

[0061] Operation S330 returned a hit.

[0062] When operating S340, a miss was returned.

[0063] In some embodiments, a hit result can directly determine that the remittance result has failed, while a miss result can determine the remittance result based on N remittance success rates.

[0064] Figure 4 A flowchart illustrating the process of obtaining remittance success rate according to an embodiment of this disclosure is shown schematically.

[0065] like Figure 4 As shown, operation S220 obtains the remittance success rate of each of the N current remittance elements based on the pre-obtained remittance prediction set, including operations S410 to S420. The remittance prediction set includes S historical time periods, and each historical time period corresponds to M remittance success rates that are one-to-one with the M historical remittance elements, where S is an integer greater than or equal to 1.

[0066] This allows for the division of time periods (segments) based on different time granularities, such as year, month, day, or hour. For example, a day can be divided into 24 time periods by hour, and each time period contains a mapping relationship between M historical remittance elements and M remittance success rates. This takes into account the success rate of remittances at different times.

[0067] In operation S410, determine the remittance period for the pending remittance transaction.

[0068] In operation S420, based on the remittance period, the remittance success rate of each current remittance element under the corresponding historical period is determined from the remittance prediction set.

[0069] For example, if the remittance period is from 5 PM to 6 PM on the same day, then the historical period from 5 PM to 6 PM is determined from the remittance prediction set. This yields a mapping relationship between M historical remittance elements and M remittance success rates for that historical period. Based on this mapping relationship, the remittance success rate corresponding to the same historical remittance element as the current remittance element is determined.

[0070] According to embodiments of this disclosure, considering the impact of remittance time periods on remittance business, dividing the time into different or the same granularities to determine the remittance success rate of the current remittance element can further improve the accuracy of the predicted remittance results.

[0071] Figure 5 A flowchart illustrating the pre-obtaining of a remittance forecast set according to an embodiment of the present disclosure is shown.

[0072] like Figure 5 As shown, the pre-obtaining remittance forecast set in this embodiment includes operations S510 to S540.

[0073] In operation S510, a first sample space is obtained based on historical remittance data within a first preset time period, wherein the historical remittance data includes at least one historical remittance transaction within the first preset time period, and each remittance transaction has at least one historical remittance element.

[0074] In operation S520, a second sample space is obtained based on historical remittance data within a second preset time period, wherein the second preset time period is earlier than the first preset time period.

[0075] For example, the first preset time period can be the day before the current day of the remittance forecast set. The second preset time period can be several months or years prior to that previous day. For example, if the current day of the remittance forecast set is July 15th, the first preset time period is 24 hours within July 14th, and the second preset time period is from January 1st to July 13th (this is just an example). In some embodiments, the first and second preset time periods can be dynamically updated as time changes. For example, if the current day is July 16th, the first preset time period is July 15th, and the first sample space includes historical remittance data for July 15th. The second preset time period and the second sample space are also updated accordingly, such as from January 2nd to July 14th.

[0076] For example, when obtaining the sample space, firstly, historical remittance data within the corresponding preset time period is acquired, i.e., one or more interbank remittance transactions. Then, remittance elements within the sample space are set, such as the receiving bank, the receiving account, the remittance time, the remittance financial instrument, or the remittance method. Based on the above remittance samples, one or more interbank remittance transactions are organized to form the sample space. Both the first and second sample spaces can be obtained according to the above steps, the difference being that they target different preset time periods.

[0077] In operation S530, S historical remittance data for historical periods that are at a specific distance from the first sample space are determined from the second sample space, wherein the S historical periods are S sub-periods in the second preset period.

[0078] For example, the distance can be Euclidean distance or Manhattan distance, and a specific distance can be a distance threshold set according to actual needs.

[0079] In some embodiments, for example, the Euclidean distance can be calculated by comparing the overall sample (one or more historical remittance transactions) in the second sample space with the daily sample in the first sample space.

[0080] In other embodiments, for example, the overall sample (one or more historical remittance transactions) in the second sample space can be divided by hour, and the sample of each hour can be calculated with the sample of the same hour of each day in the first sample space to obtain the Euclidean distance.

[0081] In operation S540, a remittance prediction set is obtained based on historical remittance data for S historical time periods.

[0082] For example, M remittance success rates can be extracted from historical remittance data of S historical periods, corresponding one-to-one with M historical remittance elements.

[0083] According to the embodiments of this disclosure, historical remittance data in the first sample space is used as reference data, and similar historical remittance data in the second sample space can be found for statistical analysis. This can improve the timeliness and accuracy of the data and avoid misjudging the reasons for the receiving bank's remittance rejection due to excessive time.

[0084] Figure 6 A flowchart illustrating the determination of historical remittance data for S historical periods according to an embodiment of the present disclosure is shown.

[0085] like Figure 6As shown, operation S530 involves determining S historical remittance data from the second sample space that are at a specific distance from the first sample space, including operations S610 to S620. The length of the second preset time period is greater than or equal to the length of at least two first preset time periods. The first sub-time period is any one of the first preset time periods. The at least two second sub-time periods are sub-time periods in the second preset time period that share the same position as the first sub-time period, and the position includes time positions within the same time granularity.

[0086] Here, length refers to the duration of time within the same time granularity. For example, if the second preset time period is one day, then the second preset time period is at least two days. If the second preset time period is one month, then the second preset time period is at least two months. Sub-time periods are further divisions of preset time periods. For example, if the first sub-time period is one hour in a day, and its time position is between 8:00 and 9:00, then the second sub-time period is between 8:00 and 9:00 every day within the second preset time period. The remittance time points described below can be every minute, every second, or every 10 minutes between 8:00 and 9:00, without limitation.

[0087] In operation S610, based on the remittance time point, the first remittance sequence of historical remittance business under the first sub-period is obtained, and at least two second remittance sequences of historical remittance business under at least two second sub-periods are obtained respectively.

[0088] The training set T is obtained based on the historical remittance data in the second sample space, as shown below:

[0089] T=(X1, Y1), (X2, Y2),…(X i Y i )

[0090] Among them, X i The feature parameter of the input parameter is the remittance sequence corresponding to the i-th sub-time period, Y. i Let n be the sequence of remittance results corresponding to the i-th sub-time period, where n is the total number of sub-time periods.

[0091] The given dataset t is obtained based on the historical remittance data in the first sample space, as shown below:

[0092] t=(x1,y1),(x2,y2),…(x j y j )

[0093] Where, x j The feature parameter of the input parameter is the remittance sequence corresponding to the j-th sub-time period, y. j Let this be the remittance result sequence corresponding to the j-th sub-time period.

[0094] For example, for X i or xj This can be a sequence of remittance transactions within a specific sub-period, arranged chronologically by time points within that sub-period. It can be represented in matrix form, where each row represents a characteristic of a single remittance transaction. Alternatively, a remittance transaction can be randomly selected at each time point.

[0095] For example, (x1, y1) represents the samples from 8:00 AM to 9:00 AM (the first sub-period) within the first preset time period. x1 represents the first remittance sequence, and y1 represents the remittance result sequence from 8:00 AM to 9:00 AM. For instance, based on whether the remittance transaction was successful or failed, the remittance result in x1 is assigned a value of 1 or 0, resulting in the remittance result sequence. This is equivalent to all X values ​​in the training set T corresponding to 8:00 AM to 9:00 AM. i .

[0096] In operation S620, based on the first remittance sequence, a classification algorithm is used to determine K second remittance sequences from at least two second remittance sequences, wherein the K second remittance sequences have a specific distance from the first remittance sequence, and K is an integer greater than or equal to 1.

[0097] The classification algorithm can include Naive Bayes, Support Vector Machine, or KNN. For example, the KNN algorithm can be used to calculate the distance between the first remittance sequence and each of at least two second remittance sequences.

[0098] In some embodiments, such as when the first remittance sequence and the second remittance sequence are matrices of the same dimension, pairwise calculations can be performed on historical remittance business features within the same row (the same time point within a sub-period), and the Euclidean distance calculation formula can be input to obtain the Euclidean distance between the sequences. The pairwise calculations between historical remittance business features can be the summation of the differences between each feature obtained from each remittance element, or the difference between the total features obtained by extracting and integrating multiple remittance elements.

[0099] In other embodiments, the geometric distance d from the first remittance sequence to the second remittance sequence is calculated separately. n :

[0100]

[0101] Where n is the number of samples in the second remittance sequence, and the correlation coefficient of the second remittance sequence is r. n The remittance success rate is b n The remittance success rate is calculated as follows: r = r * ... n Alternatively, b can be obtained by summing the remittance result sequence and then averaging it.

[0102] The formula for calculating the correlation coefficient is as follows:

[0103]

[0104] Wherein, Cov(x) j y j ) is used to find x j and y j The covariance between them, Var|x j | x is obtained based on the characteristics of each historical remittance transaction. j The variance, Var|y j |for y j The variance of r. n The calculation is performed as described above, and will not be repeated here.

[0105] According to embodiments of this disclosure, obtaining historical remittance data from K sub-time periods similar to the first sub-time period from historical remittance transactions in the second preset time period can reduce data noise and improve the reliability of the remittance prediction set.

[0106] Figure 7 A flowchart illustrating the determination of remittance success rate for each historical remittance element according to an embodiment of this disclosure is shown.

[0107] like Figure 7 As shown, the remittance prediction set obtained from historical remittance data for S historical periods in operation S540 includes operations S710 to S720.

[0108] In operation S710, for each of the M historical remittance elements, the remittance result for each historical remittance element is obtained from the K second remittance sequences.

[0109] According to embodiments of this disclosure, for each historical remittance element, the remittance result of the historical remittance business containing that historical remittance element is taken as the remittance result of each historical remittance element, wherein the historical remittance element includes at least one of the following: receiving bank, receiving account, remittance time, remittance amount, and remittance method.

[0110] For example, regarding remittance methods, these include third-party channels such as WeChat Pay, Alipay, and UnionPay QuickPass, or the remittance bank's online, counter, and ATM channels. When the remittance method is counter remittance, find one or more historical remittance transactions that used counter remittance, and use the remittance result of each historical remittance transaction as the remittance result of the counter remittance.

[0111] In operation S720, the remittance success rate of each historical remittance element is determined based on the average remittance result of each historical remittance element.

[0112] For example, if there are 100 historical remittance transactions using over-the-counter remittance from K second remittance sequences, and 50 remittances failed (assigned a value of 0) and 50 remittances succeeded (assigned a value of 1), the average value is 0.5. The success rate of over-the-counter remittance as a historical remittance element is 50%.

[0113] According to embodiments of this disclosure, the average value of all corresponding data for the same receiving bank, recipient account, etc., is calculated to obtain the mean of each interbank remittance result corresponding to the same receiving bank, recipient account, etc. This mean is used as the interbank remittance success rate for that receiving bank, recipient account, etc., thus obtaining a set of correlations between receiving bank, recipient account, etc., and interbank remittance success rates, which can be used as a remittance prediction set.

[0114] Figure 8 A flowchart illustrating the prediction of remittance results for pending remittance transactions according to an embodiment of this disclosure is shown schematically.

[0115] like Figure 8 As shown, operation S230 predicts the remittance result of the pending remittance business based on the remittance success rate of each current remittance element, including operations S810 to S820.

[0116] In operation S810, determine the lowest or highest remittance success rate among the N remittance success rates corresponding to the N current remittance elements.

[0117] When operating the S820, the remittance outcome of pending remittance transactions is predicted based on the minimum or maximum remittance success rate.

[0118] According to embodiments of this disclosure, the remittance result is predicted based on the upper and lower limits of N remittance success rates. For example, if the upper limit (the highest remittance success rate) is too low, the remittance result is a failure, or if any success rate is too low, the remittance result is a failure. In this case, the lower limit (the lowest remittance success rate) can be determined.

[0119] According to embodiments of this disclosure, if the minimum remittance success rate is less than a first threshold, or the maximum remittance success rate is less than a second threshold, the remittance result of the pending remittance transaction is predicted to be a failure. If the minimum remittance success rate is greater than or equal to a third threshold, or the maximum remittance success rate is greater than or equal to a fourth threshold, the remittance result of the pending remittance transaction is predicted to be successful.

[0120] Based on the above-mentioned interbank remittance methods, this disclosure also provides an interbank remittance device. The following will be combined with... Figure 9 The device is described in detail.

[0121] Figure 9 A schematic block diagram of an interbank remittance device according to an embodiment of the present disclosure is shown.

[0122] like Figure 9 As shown, the interbank remittance device 900 of this embodiment includes an element acquisition module 910, a success rate module 920, a remittance result module 930, and a business processing module 940.

[0123] The element acquisition module 910 can perform operation S210 to obtain N current remittance elements of the remittance business to be remitted, wherein the N current remittance elements are generated according to the remitter's remittance operation.

[0124] The success rate module 920 can perform operation S220 to obtain the remittance success rate of each of the N current remittance elements based on the pre-obtained remittance prediction set. The remittance prediction set includes M remittance success rates that correspond one-to-one with M historical remittance elements. The M historical remittance elements include some or all of the N current remittance elements, and M and N are integers greater than or equal to 1.

[0125] According to embodiments of this disclosure, the success rate module 920 can perform operations S210 to S220, which will not be described in detail here.

[0126] The remittance result module 930 can perform operation S230 to predict the remittance result of the pending remittance business based on the remittance success rate of each current remittance element.

[0127] According to embodiments of this disclosure, the success rate module 920 can perform operations S810 to S820, which will not be described in detail here.

[0128] The business processing module 940 can execute operation S240, which is used to process the pending remittance business based on N remittance elements if the remittance result is successful.

[0129] According to embodiments of this disclosure, the interbank remittance device 900 may further include a remittance prediction aggregation module for performing operations S510 to S540, S610 to S620, and S710 to S720, which will not be described in detail here.

[0130] It should be noted that the implementation methods, technical problems solved, functions achieved, and technical effects of each module / unit / subunit in the device embodiments are the same as or similar to the implementation methods, technical problems solved, functions achieved, and technical effects of each corresponding step in the method embodiments, and will not be repeated here.

[0131] According to embodiments of this disclosure, any and multiple modules among the element acquisition module 910, success rate module 920, remittance result module 930, and business processing module 940 can be combined into one module, or any one of these modules can be split into multiple modules. Alternatively, at least some of the functions of one or more of these modules can be combined with at least some of the functions of other modules and implemented in one module.

[0132] According to embodiments of this disclosure, at least one of the element acquisition module 910, success rate module 920, remittance result module 930, and business processing module 940 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), programmable logic array (PLA), system-on-a-chip, system-on-a-substrate, system-on-package, application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three methods. Alternatively, at least one of the element acquisition module 910, success rate module 920, remittance result module 930, and business processing module 940 can be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0133] Figure 10 A block diagram schematically illustrates an electronic device suitable for implementing an interbank remittance method according to an embodiment of the present disclosure.

[0134] like Figure 10 As shown, an electronic device 1000 according to an embodiment of the present disclosure includes a processor 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage portion 1008 into a random access memory (RAM) 1003. The processor 1001 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1001 may also include onboard memory for caching purposes. The processor 1001 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0135] RAM 1003 stores various programs and data required for the operation of electronic device 1000. Processor 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. Processor 1001 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 1002 and / or RAM 1003. It should be noted that programs may also be stored in one or more memories other than ROM 1002 and RAM 1003. Processor 1001 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in one or more memories.

[0136] According to embodiments of this disclosure, the electronic device 1000 may further include an input / output (I / O) interface 1005, which is also connected to a bus 1004. The electronic device 1000 may also include one or more of the following components connected to the I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as needed. A removable medium 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 1010 as needed so that computer programs read from it can be installed into the storage section 1008 as needed.

[0137] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0138] According to embodiments of this disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this disclosure, the computer-readable storage medium may include ROM 1002 and / or RAM 1003 and / or one or more memories other than ROM 1002 and RAM 1003 described above.

[0139] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the methods provided in the embodiments of this disclosure.

[0140] When the computer program is executed by the processor 1001, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0141] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 1009, and / or installed from a removable medium 1011. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0142] In such an embodiment, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by processor 1001, it performs the functions defined in the system of this disclosure embodiment. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0143] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0144] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0145] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0146] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A method for interbank remittance, comprising: Obtain N current remittance elements for the pending remittance transaction, wherein the N current remittance elements are generated based on the remitter's remittance operation; Determine the remittance period for the pending remittance business, and based on the pre-obtained remittance prediction set, obtain the remittance success rate of each of the N current remittance elements in the corresponding historical period; The remittance prediction set includes M remittance success rates that correspond one-to-one with M historical remittance elements. The M historical remittance elements include some or all of the N current remittance elements, where M and N are integers greater than or equal to 1. The remittance prediction set includes S historical time periods, and each historical time period corresponds to M remittance success rates that correspond one-to-one with M historical remittance elements, where S is an integer greater than or equal to 1. Based on the remittance success rate of each current remittance element, predict the remittance outcome of the pending remittance transaction; If the remittance result is successful, process the pending remittance business according to the N remittance elements; Before obtaining the remittance success rate of each of the N current remittance elements, the method further includes pre-obtaining the remittance prediction set, specifically including: A first sample space is obtained based on historical remittance data within a first preset time period, wherein the historical remittance data includes at least one historical remittance transaction within the first preset time period, and each remittance transaction has at least one historical remittance element. A second sample space is obtained based on historical remittance data within a second preset time period, wherein the second preset time period is earlier than the first preset time period; wherein the length of the second preset time period is greater than or equal to at least two lengths of the first preset time period; Historical remittance data for the S historical periods that are at a specific distance from the first sample space are determined from the second sample space, including: Based on the remittance time point, obtain the first remittance sequence of historical remittance transactions under the first sub-period, and obtain at least two second remittance sequences of historical remittance transactions under at least two second sub-periods respectively; Based on the first remittance sequence, a classification algorithm is used to determine K second remittance sequences from the at least two second remittance sequences, wherein the K second remittance sequences have a specific distance from the first remittance sequence, K is an integer greater than or equal to 1, the specific distance is a preset distance threshold, and the distance includes Euclidean distance or Manhattan distance; Wherein, the first sub-period is any sub-period in the first preset period, and the at least two second sub-periods are sub-periods in the second preset period that are in the same position as the first sub-period, and the position includes time positions within the same time granularity; Wherein, the S historical time periods are S sub-time periods in the second preset time period; The remittance prediction set is obtained based on the historical remittance data for the S historical periods, including: For each of the M historical remittance elements, the remittance result for each historical remittance element is obtained from the K second remittance sequences; Based on the average remittance result of each historical remittance element, the remittance success rate of each historical remittance element is determined, and the remittance prediction set is obtained.

2. The method according to claim 1, wherein, The remittance result obtained from the K second remittance sequences for each historical remittance element includes: for each historical remittance element, The remittance results of historical remittance transactions that include the historical remittance element are used as the remittance results for each historical remittance element, wherein the historical remittance element includes at least one of the following: receiving bank, receiving account, remittance time, remittance amount, and remittance method.

3. The method according to claim 2, wherein, The step of predicting the remittance outcome of the pending remittance transaction based on the remittance success rate of each current remittance element includes: Determine the lowest or highest remittance success rate among the N remittance success rates corresponding to the N current remittance elements; Based on the minimum or maximum remittance success rate, predict the remittance outcome of the pending remittance transaction.

4. A cross-bank remittance device, comprising: The element acquisition module is used to acquire N current remittance elements of the remittance business to be remitted, wherein the N current remittance elements are generated according to the remitter's remittance operation; The success rate module is used to determine the remittance period of the pending remittance transaction. Based on a pre-obtained remittance prediction set, it obtains the remittance success rate for each of the N current remittance elements in the corresponding historical period. The remittance prediction set includes M remittance success rates corresponding one-to-one with M historical remittance elements. The M historical remittance elements include some or all of the N current remittance elements, where M and N are integers greater than or equal to 1. The remittance prediction set includes S historical period periods, each corresponding to one of the M historical remittance elements, where S is an integer greater than or equal to 1. The method for obtaining the remittance prediction set in advance includes: obtaining a first sample space based on historical remittance data within a first preset time period, wherein the historical remittance data includes at least one historical remittance transaction within the first preset time period, and each remittance transaction has at least one historical remittance element; obtaining a second sample space based on historical remittance data within a second preset time period, wherein the second preset time period is earlier than the first preset time period; wherein the length of the second preset time period is greater than or equal to the length of at least two of the first preset time periods; and determining the historical data of the S historical time periods that are at a specific distance from the first sample space from the second sample space. Historical remittance data includes: obtaining a first remittance sequence for historical remittance transactions under a first sub-period based on the remittance time point; obtaining at least two second remittance sequences for historical remittance transactions under at least two second sub-periods; determining K second remittance sequences from the at least two second remittance sequences using a classification algorithm based on the first remittance sequence, wherein the K second remittance sequences have a specific distance from the first remittance sequence, K is an integer greater than or equal to 1, the specific distance is a preset distance threshold, and the distance includes Euclidean distance or Manhattan distance; wherein the first sub-period is any sub-period in the first preset period. The at least two second sub-periods are sub-periods in the second preset period that are in the same position as the first sub-period, and the position includes time positions within the same time granularity; wherein, the S historical periods are S sub-periods in the second preset period; the remittance prediction set is obtained based on the historical remittance data of the S historical periods, including: for each historical remittance element among the M historical remittance elements, obtaining the remittance result of each historical remittance element from the K second remittance sequences; determining the remittance success rate of each historical remittance element based on the average of the remittance results of each historical remittance element, and obtaining the remittance prediction set; The remittance result module is used to predict the remittance result of the pending remittance business based on the remittance success rate of each current remittance element. The business processing module is used to process the pending remittance business based on the N remittance elements if the remittance result is successful.

5. An electronic device, comprising: One or more processors; Storage device for storing one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors perform the method according to any one of claims 1 to 3.

6. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the method according to any one of claims 1 to 3.

7. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 3.

Images