Method, device, and medium for batch payment

Abstract

The present disclosure relates to a method for batch payment, the method comprising: receiving a plurality of payment information; classifying the payment information according to a preset feature; determining a plurality of in-memory databases according to the classification, wherein each in-memory database among the plurality of in-memory databases corresponds to each payment information among the plurality of payment information; and processing the plurality of payment information in parallel in the determined plurality of in-memory databases.

Description

Technical Field

[0001] The present disclosure relates to the field of communication billing, and more particularly to batch payment by users. Background Art

[0002] With the development of terminal technology, terminals (e.g., mobile phones) have become important communication tools for people. During or after the communication process using terminals, communication service operators need to bill users for their communications. In the prior art, the billing system of communication service operators calculates the service charges based on their own operation and billing strategies for users' consumption records. Users can make offline payments at business halls or online payments through various platform entrances.

[0003] Currently, there is still a need for technologies to improve the processing efficiency of users' payment data. Summary of the Invention

[0004] According to one aspect of the present disclosure, there is provided a method for batch payment, the method including: receiving a plurality of payment information; classifying the payment information according to preset features; determining a plurality of in-memory databases according to the classification, where each in-memory database in the plurality of in-memory databases corresponds to each piece of payment information in the plurality of payment information; and processing the plurality of payment information in parallel in the determined plurality of in-memory databases.

[0005] According to another aspect of the present disclosure, there is provided an electronic device, including: a memory storing instructions thereon; and a processor configured to execute the instructions stored on the memory to cause the electronic device to perform the following operations: receiving a plurality of payment information; classifying the payment information according to preset features; determining a plurality of in-memory databases according to the classification, where each in-memory database in the plurality of in-memory databases corresponds to each piece of payment information in the plurality of payment information; and processing the plurality of payment information in parallel in the determined plurality of in-memory databases.

[0006] According to still another aspect of the present disclosure, there is provided a computer-readable storage medium including computer-executable instructions, which when executed by one or more processors, cause the one or more processors to execute the method according to the above aspects of the present disclosure.

[0007] The above-provided summary is only for providing a basic understanding of various aspects of the subject matter described herein. Therefore, the technical features in the above solutions are only examples and should not be construed as limiting the scope or spirit of the subject matter described herein in any way. Other features, aspects, and advantages of the subject matter described herein will become clear from the following detailed description in conjunction with the accompanying drawings. Brief Description of the Drawings

[0008] A better understanding of the present disclosure can be obtained when considering the following detailed description of embodiments in conjunction with the accompanying drawings. The same or similar reference numerals are used in the various drawings to denote the same or similar components and operations. Among them:

[0009] Figure 1 is a schematic diagram showing an exemplary distributed memory database according to an embodiment of the present disclosure;

[0010] Figure 2 shows a schematic diagram of payment through a distributed memory database according to an embodiment of the present disclosure;

[0011] Figure 3 shows an exemplary payment processing flow chart according to an embodiment of the present disclosure;

[0012] Figure 4 shows an exemplary payment processing flow chart according to an embodiment of the present disclosure; and

[0013] Figure 5 shows an exemplary configuration of a computing device 1200 capable of implementing an embodiment of the present disclosure. Detailed Embodiments

[0014] The following describes specific examples of various aspects such as the methods and systems according to the present disclosure. These examples are described only to add context and help understand the described embodiments. Therefore, it is clear to those skilled in the art that the described embodiments can be implemented without some or all of the specific details. In other cases, well-known operations are not described in detail to avoid unnecessarily obscuring the described embodiments. Other applications are possible, and the solutions of the present disclosure are not limited to these specific examples.

[0015] As described above, users can make payments through various platform entrances. The writing, reading, processing, generation, and triggering of traditional user payment data are based on a physical database. The specific steps are as follows: 1) After the user makes a payment, the data is preliminarily processed by a preprocessing program, and then the processed data is written into a centralized physical database; 2) The user payment data is read, and after passing through a parsing program, the physical database interacts with the memory database to query the user's basic information and account information, and provides it to the foreground application through a data interface; 3) According to the user payment data transmitted back through the data interface, information is obtained through an interaction program, and the payment information is stored in the database to complete the data interaction in the billing domain.

[0016] The processing efficiency of the traditional method is as follows: 1) If 1000 users make payments in batches, the processing time from the initiation of payment to receiving a text message reminder is 1-2 hours; 2) User data is stored in a centralized database. When processing user data in batches, repeated operations are performed through an iterative algorithm, and the data interaction time is relatively long.

[0017] The traditional payment methods have at least the following deficiencies: 1) Online payment does not consider the situation of batch users making payments in the same time period. When multiple users initiate payment requests in the same time period, the interaction between the physical database and the memory database becomes congested, resulting in delayed user payments. 2) Offline payment considers the situation of batch user payments initiated simultaneously, but there are performance problems. Although offline payment takes into account the situation of simultaneous payments, it is based on queries and comparisons in the physical database, which affects the performance of payment. In scenarios where high timeliness of payment is required, it is difficult to meet the real-time requirements. 3) There are problems with the data storage and interaction mechanisms of traditional physical databases. The centralized database stores the comprehensive information of users across the province uniformly. A large amount of data is centrally stored in a single database. When interacting, it is necessary to check and traverse a large number of data using a queue, and the efficiency of the cache interaction method is relatively low. The data interaction efficiency is low, the response time is long, and it is difficult to support the efficient processing of a large amount of data. Moreover, the traditional physical database uses caching for data interaction, which has a certain data synchronization error, and may cause inconsistent user data.

[0018] In view of the long response time, low processing efficiency, and insufficient timeliness guarantee for the payment data of a large number of users, the present disclosure provides a method for improving the batch payment efficiency of users. In the present disclosure, the process of user payment adopts the method of directly accessing the distributed memory database, replacing the method of accessing the physical database and then interacting with the memory database, saving the processing time and interaction process, avoiding the delay situation when users initiate payments at the same time, and also solving the performance problems existing in the implementation process, greatly shortening the payment time. Using the method of the present disclosure, the processing time for 1000 users to make batch payments is improved from the original 2 hours to within half an hour, and the payment efficiency is significantly improved.

[0019] In addition, in the present disclosure, the efficiency of batch user payment can be improved through classification algorithms. Parallel processing is carried out according to the divided regions, business types, and balance situations, enabling the system to have a good processing strategy when facing batch data, and greatly improving the batch data processing efficiency. Compared with the processing method for centralized databases in the prior art, in the distributed processing method of the present disclosure, the user information of multiple cities is stored separately. When processing data, batch data can be processed in parallel, saving the replacement time of the physical database and the cache system. At the same time, by parallel processing payment information, the error rate of data synchronization is reduced, and the comprehensive performance of the system is improved.

[0020] Figure 1It is a schematic diagram showing an exemplary distributed in-memory database according to an embodiment of the present disclosure. In the shown distributed in-memory database, 20 machines can be included, and a mode of one main machine and two standby machines can be adopted. For example, user account information from different cities can be stored on different machines. With the development of memory technology, through distributed caching, directly accessing the database, canceling the traditional cache physical library mechanism, the access performance is improved, and the advantage of super-fast access speed is exerted.

[0021] As Figure 1 shown in the figure, the system can also include a procurement and pre-center cluster, a pricing center cluster, a financial center cluster, and a distributed file library cluster. Among them, the procurement and pre-center cluster can include 9 machines, the pricing center cluster can include 9 machines, the financial center cluster can include 18 machines, and the distributed file library cluster can include 9 machines.

[0022] Figure 2 It shows a schematic diagram of payment through a distributed in-memory database according to an embodiment of the present disclosure. As shown in this figure, different customers initiate multiple payment and recharge actions in the business hall, generating batch payment information. The received batch user payment data can be classified and corresponding to different distributed in-memory databases for parallel processing in the corresponding different distributed in-memory databases.

[0023] Figure 3 It shows an exemplary payment processing flow chart according to an embodiment of the present disclosure. In step 301, multiple payment information is received. The multiple payment information can come from multiple payment and recharge actions initiated by different customers in the business hall, or from online payment channels.

[0024] In step 302, the payment information is classified according to preset features.

[0025] In step 303, multiple in-memory databases are determined according to the classification, where each in-memory database among the multiple in-memory databases corresponds to each payment information among the multiple payment information. The determined multiple in-memory databases can be as Figure 2 shown.

[0026] Return Figure 3 , in step 304, the multiple payment information is processed in parallel in the determined multiple in-memory databases.

[0027] In the traditional technical solution of the prior art, the user initiates a batch payment and recharge action in the business hall, and then the client interface directly calls the accounting management middleware service to interact in the physical database. The accounting management accesses the unbilled phone charges in the accounting process through the payment service interface. The accounting management synchronizes the pre-deposit change information to the accounting process by inserting a small table. The accounting process writes a letter control log for the accounting management in the memory database. Then, the accounting management accesses the pricing package usage information and detailed list information in the physical database through the payment service interface. And the accounting management and the business front desk conduct business information interaction through the middleware service. The business front desk realizes the synchronization of data information to the accounting system through the message interface. The accounting management and the business front desk interface system conduct interaction through the middleware service. The business front desk system interface then conducts information interaction with the payment initiation system, thus completing the payment action.

[0028] The traditional technical solution writes and reads data from the physical database and then uses the cache mechanism for data interaction, which is inefficient and takes a long time. Moreover, in the case of a large amount of data interaction, the traditional technical solution stores data in a centralized database, with low time complexity and low space utilization rate, and cannot meet the requirements of a large amount of payment information interaction.

[0029] In the technical solution of the present disclosure, as Figure 1 shown, the distributed memory database loads data completely into the memory and manages the data in the memory. As a lightweight infrastructure software, it provides an easy-to-use, powerful interface and a widely used query language. Generally, the access speed of the memory database is about 5 to 10 times that of the physical database.

[0030] Based on the batch payment processing of the distributed memory database, on the one hand, the high-speed data interaction mechanism of the memory can give full play to the super speed advantage of memory access. On the other hand, the user payment data is distributedly stored on multiple servers, deployed on multiple nodes of the network, and provides a unified access interface. Since the user data is partitioned and stored in different distributed memory databases, when facing batch payment data, it can synchronize and process different data interaction information, with the characteristics of multiple nodes, high performance, and high availability, and can greatly improve the service performance and batch payment efficiency in the process of data comparison.

[0031] In an embodiment of the present disclosure, classifying the payment information according to the preset features may further include: determining the city to which the user number of the payment information belongs; and determining the memory database corresponding to the payment information according to the determined city to which it belongs.

[0032] In the present disclosure, the database cluster synchronously performs multi-data parallel processing. First, an algorithm can be used to optimize the classification of batch payment user data, which can greatly improve the processing and interaction efficiency of batch user payment data.

[0033] In one embodiment of the present disclosure, classifying payment information according to preset features may include classifying payment information based on a classification model.

[0034] In one embodiment of the present disclosure, the preset features may include one or more of a user number, a city of residence, a service type, and a balance of a user account.

[0035] In one embodiment of the present disclosure, four features of batch user data - user number U, city D, service type T, and balance V - may be used to establish an integrated model. The background algorithm divides the batch user payment data input into the system through a classification model function to confirm the user payment process and process the database. Among them, the classification model function of a single feature is as follows:

[0036]

[0037] In the above formula, H(x) is the feature classification of the prediction result for the x sample, and h i represents the corresponding decision tree model of a single user parameter, and ω is the base weight.

[0038] Based on the above, by extracting the user data set, effective user numbers U, cities D, service types T, and balances V are obtained, and a user data feature set

[0039] M = (U T , D T , T T , V T )

[0040] The establishment logic of the user data integrated classification model is as follows:

[0041] Step 1: The system obtains the batch user data set M, and the background algorithm randomly samples T samples from the data set M with replacement using the Bootstrap method, and k training sets are established through k samplings to obtain a new data input set M';

[0042] Step 2: In each attribute, each time n features are randomly selected from the feature attributes as the feature splitting attributes, and the best feature is selected from the n features according to the Gini coefficient for node splitting to establish an optimal CART (Classification And Regression Trees) decision model;

[0043] Step 3: Repeat Step 1 and Step 2 a total of k - 1 times to obtain the final integrated user data model, and enable a voting mechanism to classify information such as the user's place of residence, service type, and balance.

[0044] One of the great advantages of this algorithm is that while processing batch data, it continuously improves the feature integration model. The more data is processed, the more perfect the formed integration model becomes, and the data processing efficiency will not decrease due to the increase in user data, ensuring the efficiency of batch user payment processing.

[0045] Figure 4 An exemplary payment processing flowchart according to an embodiment of the present disclosure is shown. First, batch payment information of users is received, numbers are obtained, and the cities to which the numbers belong are obtained based on the number information to determine in which corresponding in-memory database to process. Next, during the processing, as Figure 4 shown, determine whether the business type of the payment information is a single-card service or a convergent service. In the convergent service, first determine whether the balance of the user account corresponding to the payment information is greater than zero; when the balance of the user account corresponding to the payment information is greater than zero, use the short process to preferentially process the payment information, and when the balance of the user account corresponding to the payment information is less than zero, process the payment information after performing write-off processing on the account. Similarly, in the single-card service, first determine whether the balance of the user account corresponding to the payment information is greater than zero; when the balance of the user account corresponding to the payment information is greater than zero, use the short process to preferentially process the payment information, and when the balance of the user account corresponding to the payment information is less than zero, process the payment information after performing write-off processing on a single user. Since when the balance of the user account is greater than zero, the processing of the payment information of this user is faster, preferentially processing such user payment information can avoid congestion and improve efficiency.

[0046] In the technical solution of the present disclosure for batch payment information, the client interface directly calls the accounting management service to interact and transmit batch data through a distributed cache. The user information is divided according to discriminant conditions through a classification algorithm and processed in parallel in the corresponding partition in-memory database. Moreover, the accounting management accesses the unaccounted phone charges for accounting processing, the accounting management gives the accounting synchronization pre-stored change information, the accounting processing completes the credit control trigger and write-off, and writes the credit control log to the accounting management, and the accounting management and the business front desk perform business information interaction through interface calls. The business front desk synchronizes the data information of the accounting system through message packets, and the business front desk interface then performs batch information interaction with the initiating payment system. The parallel processing results of each partition database are summarized and transmitted back to the front desk interface through a distributed cache, thereby completing the processing of batch payment data.

[0047] Figure 5 An exemplary configuration of a computing device 1200 that can implement an embodiment of the present disclosure is shown.

[0048] The computing device 1200 is an example of a hardware device capable of applying the above aspects of the present disclosure. The computing device 1200 can be any machine configured to perform processing and / or computing. The computing device 1200 can be, but is not limited to, a workstation, a server, a desktop computer, a laptop computer, a tablet computer, a personal data assistant (PDA), a smart phone, an in-vehicle computer, or a combination thereof.

[0049] As Figure 5 shown, the computing device 1200 can include one or more elements that can be connected to or communicate with a bus 1202 via one or more interfaces. The bus 2102 can include, but is not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an Enhanced ISA (EISA) bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus, among others. The computing device 1200 can include, for example, one or more processors 1204, one or more input devices 1206, and one or more output devices 1208. The one or more processors 1204 can be any type of processor and can include, but are not limited to, one or more general-purpose processors or special-purpose processors (such as special processing chips). The input device 1206 can be any type of input device capable of inputting information to the computing device and can include, but is not limited to, a mouse, a keyboard, a touch screen, a microphone, and / or a remote controller. The output device 1208 can be any type of device capable of presenting information and can include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer.

[0050] The computing device 1200 may also include or be connected to a non-transitory storage device 1214, which can be any non-transitory storage device capable of implementing data storage, and may include but are not limited to disk drives, optical storage devices, solid-state memories, floppy disks, flexible disks, hard disks, magnetic tapes or any other magnetic media, compact disks or any other optical media, cache memories, and / or any other storage chips or modules, and / or any other medium from which a computer can read data, instructions, and / or code. The computing device 1200 may also include a random access memory (RAM) 1210 and a read-only memory (ROM) 1212. The ROM 1212 may store programs, utilities, or processes to be executed in a non-volatile manner. The RAM 1210 may provide volatile data storage and store instructions related to the operation of the computing device 1200. The computing device 1200 may also include a network / bus interface 1216 coupled to a data link 1218. The network / bus interface 1216 can be any type of device or system capable of enabling communication with external devices and / or networks, and may include but are not limited to modems, network cards, infrared communication devices, wireless communication devices, and / or chip sets (such as Bluetooth™ devices, 802.11 devices, WiFi devices, WiMax devices, cellular communication facilities, etc.).

[0051] The present disclosure may be implemented as any combination of a device, a system, an integrated circuit, and a computer program on a non-transitory computer-readable medium. One or more processors may be implemented as an integrated circuit (IC), an application-specific integrated circuit (ASIC), or a large-scale integrated circuit (LSI), a system LSI, a super LSI, or a super LSI component that executes some or all of the functions described in the present disclosure.

[0052] The present disclosure includes the use of software, applications, computer programs, or algorithms. The software, applications, computer programs, or algorithms may be stored on a non-transitory computer-readable medium to cause a computer such as one or more processors to execute the steps described above and the steps in the drawings. For example, one or more memories store software or algorithms in executable instructions, and one or more processors may execute a set of instructions associated with the software or algorithm to provide various functions according to the embodiments described in the present disclosure.

[0053] Software and computer programs (which may also be referred to as programs, software applications, applications, components, or code) include machine instructions for a programmable processor and can be implemented in a high-level procedural language, an object-oriented programming language, a functional programming language, a logic programming language, or an assembly language or machine language. The term "computer-readable medium" refers to any computer program product, apparatus, or device for providing machine instructions or data to a programmable data processor, such as a magnetic disk, an optical disk, a solid-state storage device, a memory, and a programmable logic device (PLD), including a computer-readable medium that receives the machine instructions as a computer-readable signal.

[0054] By way of example, a computer-readable medium may include a dynamic random access memory (DRAM), a random access memory (RAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disk storage, a magnetic disk storage, or other magnetic storage devices, or any other medium that can be used to carry or store the desired computer-readable program code in the form of instructions or data structures and that can be accessed by a general-purpose or special-purpose computer or a general-purpose or special-purpose processor. As used herein, a disk or disc includes a compact disc (CD), a laser disc, an optical disc, a digital versatile disc (DVD), a floppy disk, and a Blu-ray disc, where a disk typically replicates data magnetically, while a disc replicates data optically by laser. Combinations of the above are also included within the scope of computer-readable media.

[0055] The subject matter of the present disclosure is provided as examples of apparatuses, systems, methods, and programs for performing the features described in the present disclosure. However, other features or variations may be expected in addition to the above features. It is expected that the implementation of the components and functions of the present disclosure can be accomplished with any emerging technology that may replace any of the above-described implementations.

[0056] In addition, the above description provides examples without limiting the scope, applicability, or configuration set forth in the claims. Changes may be made to the functions and arrangements of the elements discussed without departing from the spirit and scope of the present disclosure. Various embodiments may appropriately omit, substitute, or add various processes or components. For example, features described with respect to certain embodiments may be combined in other embodiments.

[0057] In addition, in the description of the present disclosure, the terms "first", "second", "third", etc. are used for descriptive purposes only and should not be construed as indicating or implying relative importance or order.

[0058] Similarly, although operations are depicted in the drawings in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous.

[0059] Additionally, embodiments of the present disclosure may also include the following examples:

[0060] Item 1. A method for batch payment, the method comprising: receiving a plurality of payment information; classifying the payment information according to preset features; determining a plurality of in-memory databases according to the classification, wherein each in-memory database in the plurality of in-memory databases corresponds to each payment information in the plurality of payment information; and processing the plurality of payment information in parallel in the determined plurality of in-memory databases.

[0061] Item 2. The method according to Item 1, wherein classifying the payment information according to preset features includes classifying the payment information based on a classification model.

[0062] Item 3. The method according to Item 2, wherein the classification model for a single feature is as follows:

[0063] where H(x) is the feature classification of the prediction result for the x sample, h i represents the corresponding individual user parameter tree decision model, and ω is the base weight.

[0064] Item 4. The method according to Item 1, wherein the preset features include one or more of a user number, a city where the user belongs, a service type, and a balance status of the user account.

[0065] Item 5. The method according to Item 1, wherein classifying the payment information according to preset features includes: determining the city where the user belongs according to the user number of the payment information; and determining the in-memory database corresponding to the payment information according to the determined city where the user belongs.

[0066] Item 6. The method according to Item 5, wherein classifying the payment information according to preset features further includes determining whether the service type of the payment information is a single-card service or a convergent service.

[0067] Item 7. The method according to Item 6, wherein classifying the payment information according to preset features further includes determining whether the balance of the user account corresponding to the payment information is greater than zero; wherein when the balance of the user account corresponding to the payment information is greater than zero, the payment information is preferentially processed using a short process; and when the balance of the user account corresponding to the payment information is less than zero, the payment information is processed after account-level write-off processing.

[0068] Item 8. An electronic device, comprising: a memory storing instructions thereon; and a processor configured to execute the instructions stored on the memory to cause the electronic device to perform the following operations: receiving a plurality of payment information; classifying the payment information according to a preset feature; determining a plurality of in-memory databases according to the classification, wherein each in-memory database in the plurality of in-memory databases corresponds to each piece of payment information in the plurality of payment information; and processing the plurality of payment information in parallel in the determined plurality of in-memory databases.

[0069] Item 9. The device according to Item 8, wherein classifying the payment information according to a preset feature includes classifying the payment information based on a classification model.

[0070] Item 10. The device according to Item 9, wherein the classification model for a single feature is as follows:

[0071]

[0072] where H(x) is the feature classification of the prediction result for the x sample, h i represents the corresponding individual user parameter tree decision model, and ω is the base weight.

[0073] Item 11. The device according to Item 8, wherein the preset feature includes one or more of a user number, a city where the user belongs, a service type, and a balance of the user account.

[0074] Item 12. The device according to Item 8, wherein classifying the payment information according to a preset feature includes: determining the city where the user belongs according to the user number of the payment information; and determining the in-memory database corresponding to the payment information according to the determined city where the user belongs.

[0075] Item 13. The device according to Item 12, wherein classifying the payment information according to a preset feature further includes determining whether the service type of the payment information is a single-card service or a converged service.

[0076] Item 14. The device according to Item 13, wherein classifying the payment information according to a preset feature further includes determining whether the balance of the user account corresponding to the payment information is greater than zero; wherein when the balance of the user account corresponding to the payment information is greater than zero, the short process is used to preferentially process the payment information; and when the balance of the user account corresponding to the payment information is less than zero, the payment information is processed after account-level write-off processing.

[0077] Item 15. A computer-readable storage medium, comprising computer-executable instructions, which when executed by one or more processors, cause the one or more processors to execute the method according to any one of Items 1-7.

[0078] In addition, although the description of the present disclosure has included a description of one or more embodiments, configurations or aspects, certain variations and modifications, other variations, combinations and modifications are also within the scope of the present disclosure. For example, after those skilled in the art understand the present disclosure, this may be within their technical and knowledge scope. The present disclosure aims to obtain rights, which should include alternative embodiments, configurations or aspects within the allowable scope, including alternative, interchangeable and / or equivalent structures, functions, scopes or steps to those claimed, whether or not these alternative, interchangeable and / or equivalent structures, functions, scopes or steps are specifically described herein. The present disclosure is not intended to publicly contribute any patentable technical solutions.

Claims

1. A method for batch payment, the method comprising: Receiving a plurality of payment information generated in response to multiple payment recharge actions initiated by different customers; Classifying the payment information according to preset features, including: determining the city to which it belongs according to the user number of the payment information, and determining whether the balance of the user account corresponding to the payment information is greater than zero; Determining a plurality of distributed in-memory databases according to the classification, including: determining the in-memory database corresponding to the payment information according to the determined city to which it belongs, wherein each in-memory database among the plurality of in-memory databases corresponds to each of the plurality of payment information; and Parallel processing of the plurality of payment information in the determined plurality of in-memory databases, and summarizing the results of the parallel processing and transmitting them back to the front-end interface to complete the payment recharge action; Wherein the payment information is preferentially processed when the balance of the user account corresponding to the payment information is greater than zero; and When the balance of the user account corresponding to the payment information is less than zero, the payment information is processed after account-level write-off processing.

2. The method according to claim 1, wherein classifying the payment information according to preset features includes classifying the payment information based on a classification model.

3. The method according to claim 2, wherein the classification model for a single feature is as follows: where H(x) is the feature classification of the prediction result for sample x, h i represents the corresponding individual user parameter tree decision model, ω is the base weight, and k is the number of training sets.

4. The method according to claim 1, wherein the preset features include one or more of the city to which it belongs and the service type.

5. The method according to claim 1, wherein classifying the payment information according to preset features further includes determining whether the service type of the payment information is a single-card service or a converged service.

6. An electronic device, comprising: A memory on which instructions are stored; And A processor configured to execute the instructions stored on the memory to cause the electronic device to perform the following operations: Receiving a plurality of payment information generated in response to multiple payment recharge actions initiated by different customers; Classifying the payment information according to preset features, including: determining the city to which it belongs according to the user number of the payment information, and determining whether the balance of the user account corresponding to the payment information is greater than zero; Determining a plurality of distributed in-memory databases according to the classification, including: determining the in-memory database corresponding to the payment information according to the determined city to which it belongs, wherein each in-memory database among the plurality of in-memory databases corresponds to each of the plurality of payment information; and Parallel processing of the plurality of payment information in the determined distributed plurality of in-memory databases, and summarizing the results of the parallel processing and transmitting them back to the front-end interface to complete the payment recharge action; Wherein the payment information is preferentially processed when the balance of the user account corresponding to the payment information is greater than zero; and When the balance of the user account corresponding to the payment information is less than zero, the payment information is processed after account-level write-off processing.

7. The device according to claim 6, wherein classifying the payment information according to preset features includes classifying the payment information based on a classification model.

8. The device according to claim 7, wherein the classification model for a single feature is as follows: where H(x) is the feature classification of the prediction result for the x sample, h i represents the corresponding individual user parameter tree decision model, ω is the base weight, and k is the number of training sets.

9. The device according to claim 6, wherein the preset features include one or more of the city to which it belongs and the service type.

10. The device according to claim 6, wherein classifying the payment information according to the preset feature further includes determining whether the service type of the payment information is a single-card service or a converged service.

11. A computer-readable storage medium, including computer-executable instructions, which, when executed by one or more processors, cause the one or more processors to execute the method according to any one of claims 1-5.

Images