WO2020177479A1

WO2020177479A1 - Method and system for account processing, and computing device

Info

Publication number: WO2020177479A1
Application number: PCT/CN2020/070509
Authority: WO
Inventors: 黄治龙
Original assignee: 阿里巴巴集团控股有限公司
Priority date: 2019-03-05
Filing date: 2020-01-06
Publication date: 2020-09-10
Also published as: CN110020850A; TW202034259A

Abstract

Embodiments of the present description provide a method and system for account processing, and a computing device. The method comprises: receiving a state query request for a target account from a service system; determining the balance of the target account; determining availability information of the target account on the basis of the balance, the availability information being used for indicating whether the target account is currently available; and sending a state query response to the service system, so that the service system processes a deduction task of the target account on the basis of the state query response, the state query response at least comprising the availability information.

Description

Method, system and computing device for account processing

Technical field

The embodiments of this specification relate to the field of financial data processing, and more specifically, to methods, systems, and computing devices for account processing.

Background technique

With the rapid growth of electronic transaction business, hot accounts may generate hundreds of millions of changes every day. In some scenarios, it may be necessary to perform massive concurrent update operations on certain accounts every second or even every millisecond. In this case, any delay in the update operation may cause account overdraft problems, ranging from affecting business to regulatory risks. Therefore, how to effectively prevent account overdraft has become one of the urgent problems to be solved.

Summary of the invention

Taking into account the above-mentioned problems of the prior art, the embodiments of this specification provide a method, system and computing device for account processing.

On the one hand, the embodiments of this specification provide a method for account processing, wherein the method is executed by a decision system, and the method includes: receiving a status query request for a target account from a business system; determining the target The balance of the account; based on the balance, determine the availability information of the target account, where the availability information is used to indicate whether the target account is currently available; send a status query response to the business system so that the The business system processes the deduction task of the target account based on the status query response, wherein the status query response at least includes the availability information.

On the other hand, the embodiments of this specification provide a method for account processing, wherein the method is executed by a metering system, and the method includes: obtaining real-time flow data of a target account from a streaming computing platform; Real-time flow data to calculate the balance of the target account, wherein the balance of the target account is used by the decision system to determine the availability information of the target account, and the availability information is used to indicate whether the target account is currently available , The availability information is used by the business system as a basis for processing the deduction task of the target account.

On the other hand, the embodiment of this specification provides a system for account processing, including: a receiving unit, configured to: receive a status query request for a target account from a business system; and a determining unit, configured to: determine the target The balance of the account; based on the balance, determine the availability information of the target account, where the availability information is used to indicate whether the target account is currently available; a sending unit is used to: send the status to the business system Query response, so that the business system processes the deduction task of the target account based on the status query response, wherein the status query response at least includes the availability information.

On the other hand, the embodiment of this specification provides a system for account processing, including: an obtaining unit, configured to: obtain real-time flow data of a target account from a streaming computing platform; and a computing unit, configured to: Flow data to calculate the balance of the target account, wherein the balance of the target account is used by the decision system to determine the availability information of the target account, and the availability information is used to indicate whether the target account is currently available, The availability information is used by the business system as a basis for processing the deduction task of the target account.

On the other hand, the embodiments of the present specification provide a computing device, including: at least one processor; a memory in communication with the at least one processor, and executable instructions stored thereon, the executable instructions being When the at least one processor is executed, the at least one processor implements the method executed by the decision system.

On the other hand, the embodiments of the present specification provide a computing device, including: at least one processor; a memory in communication with the at least one processor, and executable instructions stored thereon, the executable instructions being When the at least one processor is executed, the at least one processor implements the method executed by the metering system.

It can be seen that in this technical solution, after receiving the status query request of the business system for the target account, the decision-making system can obtain the availability information about whether the target account is available based on the balance of the target account, so that the business system can at least base on the availability information. Handle deduction tasks. In this way, the risk of account overdraft can be greatly reduced.

Description of the drawings

Through a more detailed description of the embodiments of this specification in conjunction with the accompanying drawings, the above and other objectives, features and advantages of the embodiments of this specification will become more apparent. Among them, in the embodiments of this specification, the same reference numerals Usually represent the same element.

Figure 1 is a schematic diagram of an exemplary architecture for account processing according to one embodiment.

Fig. 2A is a schematic flowchart of a method for account processing according to an embodiment.

Fig. 2B is a schematic flowchart of a method for account processing according to an embodiment.

Fig. 3A is a schematic block diagram of a system for account processing according to an embodiment.

Fig. 3B is a schematic block diagram of a system for account processing according to an embodiment.

Fig. 4A is a hardware structure diagram of a computing device for account processing according to an embodiment.

Fig. 4B is a hardware structure diagram of a computing device for account processing according to an embodiment.

detailed description

The subject described herein will now be discussed with reference to various embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and not to limit the scope of protection, applicability or examples set forth in the claims. The function and arrangement of the discussed elements can be changed without departing from the scope of protection of the claims. Various embodiments may omit, replace or add various processes or components as needed.

With the rapid growth of electronic transaction business, the journal volume of many accounts has reached more than 10 million. For example, some accounts may generate hundreds of millions of changes every day. These accounts can be called hotspot accounts. In other words, a hot account may refer to an account that performs high-frequency deductions and entry operations during the transaction process. In some scenarios, massive concurrent updates of hotspot accounts are required every second or even every millisecond. For hot accounts, one of the most important problems is to avoid overdrafts. The overdraft of hotspot accounts will not only affect business, but even bring regulatory risks.

In view of this, the embodiments of this specification provide a technical solution for account processing. In this technical solution, the decision system can determine the balance of the target account after receiving the status query request for the target account from the business system. For example, the target account may be a hotspot account. In addition, the target account can also be a non-hot account.

Then, the decision system determines whether the target account is currently available based on the balance, and obtains the availability information of the target account. Subsequently, a status query response including at least the availability information is sent to the business system, so that the business system can process the deduction task of the target account based on the status query response.

It can be seen that in this technical solution, after receiving the status query request for the target account from the business system, the decision-making system obtains the availability information about whether the target account is available based on the balance of the target account, so that the business system can at least base on the availability information. Handle deduction tasks. For example, if the account is available, the business system can perform deduction tasks; if the account is not available, the business system can suspend the deduction tasks, and so on. In this way, the risk of account overdraft can be greatly reduced.

The above technical solutions will be described in detail below in conjunction with specific embodiments.

In the example shown in FIG. 1, the data synchronization middleware can obtain various data of the data source, for example, messages related to each account, log records (for example, real-time account flow data), and so on. The data synchronization middleware can synchronize the data of the data source to the streaming computing platform.

The streaming computing platform can aggregate the data provided by the data synchronization middleware, and then provide it to the metering system.

The metering system can obtain real-time account flow data from the data provided by the streaming computing platform, such as real-time account inflow and outflow data. Then, the metering system can calculate the account balance based on the real-time flow data of the account.

It is understandable that the data synchronization middleware, the streaming computing platform and the metering system can interact in real time and continuously, so that the metering system can always get the latest balance of the account.

The machine learning platform can build an account prediction model based on the business scenario of the account, and obtain the predicted value of the net outflow rate of the account based on the prediction model. For example, the machine learning platform can build predictive models based on any applicable deep learning frameworks, such as Tensorflow, Caffe, MXNet, and so on.

The machine learning platform can provide the predicted value of the account net outflow rate to the metering system, and the metering system will store it. In addition, the machine learning platform can update the predicted value of the account net outflow rate in real time based on the prediction model, and continuously provide the updated value to the metering system.

The accounting system can manage the information of each account, can create new accounts, can cancel accounts, and so on.

The decision-making system can interact with the business system, the measurement system and the accounting system.

The business system can send a status query request for the account to the decision system. For example, the business system can send a status query request at a certain frequency. The decision-making system can determine the balance of the account after receiving the status query request. For example, the decision system can obtain the balance of the account from the metering system or the accounting system. Then, the decision system can determine whether the account is currently available with availability information based on the balance of the account. After that, the decision system can provide the business system with a status query response including at least availability information. The specific functions and operations of the decision system will be described in detail below.

The business system can process various tasks for the corresponding account according to the status query response, such as account entry and deduction tasks.

The following describes the technical solution of this specification in detail from the perspective of the decision-making system.

Fig. 2A is a schematic flowchart of a method for account processing according to an embodiment. The method of Figure 2A can be executed by a decision system.

As shown in FIG. 2A, in step 202A, a status query request for the target account is received from the business system.

In step 204A, the balance of the target account is determined.

In step 206A, based on the balance, the availability information of the target account is determined, where the availability information is used to indicate whether the target account is currently available.

In step 208A, a status query response is sent to the business system, so that the business system processes the deduction task of the target account based on the status query response, where the status query response at least includes availability information.

In one embodiment, in step 204A, the decision system may obtain the balance of the target account from the metering system. As mentioned above, the balance of the target account may be calculated by the metering system based on the real-time flow data of the target account. In this way, the balance of the target account obtained by the decision-making system is real-time and reliable, so that real-time and reliable account availability information can be provided to the business system, thereby avoiding account overdraft caused by the operation of the business system on the account.

In one embodiment, in step 204A, if the decision system fails to obtain the balance from the metering system within a predetermined period of time, the balance is obtained from the accounting system. The predetermined duration may be less than or equal to the maximum delay for the accounting system to update the balance of the target account.

Due to the distributed architecture, there may be some interaction delays between various systems. Usually these delays are very short-lived, but under certain abnormal circumstances, the delay may be amplified and cause account overdraft problems. Therefore, in this embodiment, if the decision-making system fails to obtain the balance of the target account from the metering system in real time due to the delay, the balance of the target account can be obtained from the accounting system. For example, the decision-making system can obtain the balance of the target account from the accounting system through Remote Procedure Call (RPC). In this way, the balance of the target account obtained by the decision system is at most the balance update delay at the accounting system, thereby avoiding inaccurate availability information of the target account.

After obtaining the balance of the target account, in step 206A, the decision system may determine whether the target account is currently available based on the balance.

For example, the decision system may determine whether the target account is currently available based on the balance and the upper limit of the balance level and the lower limit of the balance level for the target account. The upper limit of the balance level and the lower limit of the balance level can be set for each account. By setting the upper limit of the balance water level and the lower limit of the balance water level to determine the availability status of the target account, it is possible to avoid frequent switching of the status of the target account and jitter back and forth, resulting in system instability.

In an embodiment, the upper limit of the balance water level and the lower limit of the balance water level may be preset. For example, the upper limit of the balance water level and the lower limit of the balance water level can be set according to actual business scenarios, combined with requirements and experience.

In one embodiment, the upper limit of the balance level and the lower limit of the balance level can be dynamically updated through a machine learning model. This approach can better adapt to business changes.

Specifically, if the balance is lower than the lower limit of the balance level, the decision-making system can determine that the target account is unavailable. For example, if the balance is lower than the lower limit of the balance level, the target account is in an unavailable state, which can also be understood as entering the "water storage stage".

If the balance is higher than the upper limit of the balance level, the decision-making system can determine that the target account is available.

For the balance between the upper limit of the balance level and the lower limit of the balance level, there are two situations. For example, if the balance is between the lower limit of the balance water level and the upper limit of the balance water level due to a decline, the decision system can determine that the target account is available. Specifically, if the previous balance of the target account has undergone some deduction operations, resulting in the current balance being between the lower limit of the balance water level and the upper limit of the balance water level, in this case, the target account is in an available state.

If the balance is between the lower limit of the balance water level and the upper limit of the balance water level due to an increase, and the balance before the increase is lower than the lower limit of the balance water level, the decision-making system can determine that the target account is unavailable. Specifically, if the previous balance of the target account is lower than the lower limit of the balance level, that is, the target account was previously in an unavailable state, then the balance rises to between the lower limit of the balance level and the upper limit of the balance level, but the target account does not reach the upper limit of the balance level. The account is still unavailable. Until the balance rises to the upper limit of the balance level, the target account will not switch to an available state.

It can be seen that by setting the upper limit of the balance water level and the lower limit of the balance water level to determine the availability status of the target account, it is possible to avoid frequent switching of the status of the target account and jitter back and forth, resulting in system instability.

In one embodiment, if the target account is currently available, the status query response may also include the balance of the target account. In other words, if the target account is currently available, the decision system can send the availability information of the target account and the balance to the business system. In this way, the business system can process the deduction task of the target account based on this information.

In one embodiment, if the target account is currently available, the status query response may also include the available time of the target account. Specifically, the decision system can determine the available time of the target account. Before the available time expires, the business system can perform the deduction task of the target account; and when the available time expires, the business system suspends the deduction task of the target account.

It can be seen that the available time can provide a time point for the business system to perform the deduction task of the target account. In this way, the interaction delay between distributed architectures can be taken into account. For example, if the status query request sent by the business system before the available time fails to be responded in time, the corresponding deduction task can also be performed based on the available time, and when the available time expires, the deduction task is suspended to avoid continuing The operation caused an account overdraft problem.

In one embodiment, the decision system may obtain the predicted value of the net outflow rate of the target account from the metering system. As mentioned above, the predicted value of the account net outflow rate can be obtained through the prediction model of the machine learning platform. Then, the available time is determined based on the last update time of the balance, the predicted value of the balance and the net outflow rate of the account.

For example, the available time may be equal to the most recent update time of the balance + the predicted value of the balance/account net outflow rate.

It can be seen that by providing the business system with the balance, availability information, and available time of the target account, the risk of account overdraft caused by the interaction delay of the distributed architecture can be reduced to a certain extent.

It can be seen from the above that in one implementation, in the decision-making system, the following fields can be maintained: AccountNo (account number of the account), UpperWaterLine (the upper limit of the balance water level, the unit can be "yuan"), LowerWaterLine (the lower limit of the balance water level, the unit It can be "yuan"), Status (status, which includes available or unavailable), AvgLendingRates (predicted value of account net outflow rate, the unit can be "yuan/minute").

The following describes from the perspective of the metering system. Fig. 2B is a schematic flowchart of a method for account processing according to an embodiment. The method of FIG. 2B can be executed by a metering system.

As shown in FIG. 2B, in step 202B, the real-time flow data of the target account is obtained from the streaming computing platform.

In step 204B, the balance of the target account is calculated based on the real-time flow data.

The balance of the target account can be used by the decision system to determine the availability information of the target account, the availability information is used to indicate whether the target account is currently available, and the availability information is used by the business system as a basis for processing the deduction task of the target account.

It can be seen that in this technical solution, the balance of the target account is obtained based on the real-time flow data of the target account, so that the decision-making system can obtain relatively reliable availability information based on the balance, so that the business system can perform reliable reliability at least based on the availability information. Operation, thereby reducing the overdraft risk of the target account.

In one embodiment, the metering system may obtain the predicted value of the net outflow rate of the target account obtained through the prediction model from the machine learning platform. The predicted value of the account net outflow rate can be determined by the decision system combining the balance and the latest update time of the balance to determine the available time of the target account.

Among them, before the available time expires, the business system can perform the deduction task of the target account; when the available time expires, the business system suspends the deduction task of the target account.

It can be seen that by providing the business system with the time point for executing the deduction task of the target account, the risk of account overdraft caused by the interaction delay of the distributed architecture can be reduced to a certain extent.

Fig. 3A is a schematic block diagram of a system for account processing according to an embodiment. For example, the system 300A may be the aforementioned decision-making system.

As shown in FIG. 3A, the system 300A may include a receiving unit 302A, a determining unit 304A, and a sending unit 306A.

The receiving unit 302A may receive a status query request for the target account from the business system. The determining unit 304A can determine the balance of the target account. The determining unit 304A may also determine the availability information of the target account based on the balance, where the availability information is used to indicate whether the target account is currently available. The sending unit 306A may send a status query response to the business system, so that the business system can process the deduction task of the target account based on the status query response, where the status query response at least includes availability information.

In one embodiment, the determining unit 304A may obtain the balance from the metering system. The balance can be calculated by the metering system based on the real-time flow data of the target account.

In another embodiment, if the balance cannot be obtained from the metering system within a predetermined period of time, the determining unit 304A may obtain the balance from the accounting system, where the predetermined period of time is less than or equal to the account system’s balance update of the target account. Maximum delay.

In another embodiment, if the target account is currently available, the status query response may also include the balance.

In another embodiment, if the target account is currently available, the determining unit 304A may also determine the available time of the target account. The status query response may also include the available time. Among them, before the available time expires, the business system can perform the deduction task of the target account; when the available time expires, the business system suspends the deduction task of the target account.

In another embodiment, the determining unit 304A may obtain the predicted value of the net outflow rate of the target account from the metering system, where the predicted value of the net outflow rate of the account is obtained through the prediction model of the machine learning platform. The determining unit 304A may determine the available time based on the most recent update time of the balance, the predicted value of the balance and the net outflow rate of the account.

In another embodiment, the determining unit 304A may determine whether the target account is currently available based on the balance and the upper limit of the balance level and the lower limit of the balance level for the target account.

In another embodiment, if the balance is lower than the lower limit of the balance level, the determining unit 304A may determine that the target account is unavailable. If the balance is higher than the upper limit of the balance level, the determining unit 304A may determine that the target account is available. If the balance is between the lower limit of the balance water level and the upper limit of the balance water level due to a decline, the determining unit 304A can determine that the target account is available. If the balance is between the lower limit of the balance level and the upper limit of the balance level due to an increase, and the balance before the increase is lower than the lower limit of the balance level, the determining unit 304A can determine that the target account is unavailable.

In another embodiment, the upper limit of the balance water level and the lower limit of the balance water level may be preset. Alternatively, the upper limit of the balance water level and the lower limit of the balance water level may be dynamically updated through a machine learning model.

Each unit of the system 300A can execute the corresponding steps in the method embodiments of FIGS. 1 and 2A. Therefore, for brevity of description, the specific operations and functions of each unit of the device 300A will not be repeated here.

Fig. 3B is a schematic block diagram of a system for account processing according to an embodiment. For example, the system 300B may be the aforementioned metering system.

As shown in FIG. 3B, the system 300B may include an acquisition unit 302B and a calculation unit 304B.

The obtaining unit 302B may obtain the real-time flow data of the target account from the streaming computing platform. The calculation unit 304B may calculate the balance of the target account based on the real-time flow data, where the balance of the target account is used by the decision-making system to determine the availability information of the target account, the availability information is used to indicate whether the target account is currently available, and the availability information is determined by the business The system is used as the basis for processing the deduction task of the target account.

In an embodiment, the obtaining unit 302B may also obtain the predicted value of the net outflow rate of the target account obtained through the prediction model from the machine learning platform, where the predicted value of the net outflow rate of the account is combined with the balance and the latest update time of the balance by the decision-making system To determine the available time of the target account. Among them, before the available time expires, the business system can perform the deduction task of the target account; when the available time expires, the business system suspends the deduction task of the target account.

Each unit of the system 300B can execute corresponding steps in the method embodiments of FIGS. 1 and 2B. Therefore, for the sake of brevity of description, the specific operations and functions of each unit of the device 300B will not be repeated here.

The aforementioned systems 300A and 300B can be implemented by hardware, software, or a combination of software and hardware. For example, when the system 300A or 300B is implemented by software, it can be formed by reading the corresponding executable instructions in the memory (such as non-volatile memory) into the memory by the processor of the device where it is located and running it.

Fig. 4A is a hardware structure diagram of a computing device for account processing according to an embodiment. As shown in FIG. 4A, the computing device 400A may include at least one processor 410A, memory 420A, memory 430A, and communication interface 440A, and at least one processor 410A, memory 420A, memory 430A, and communication interface 440A are connected together via a bus 450A. At least one processor 410A executes at least one executable instruction (that is, the above-mentioned element implemented in the form of software) stored or encoded in the memory 420A.

In one embodiment, the executable instructions stored in the memory 420A, when executed by the at least one processor 410A, enable the computing device to implement the various processes described above in conjunction with FIGS. 1 and 2A.

The computing device 400A can be implemented in any suitable form in the art, for example, it includes, but is not limited to, a desktop computer, a laptop computer, a smart phone, a tablet computer, a consumer electronic device, a wearable smart device, and so on.

For example, the computing device 400A can implement various functions and operations of the aforementioned decision-making system.

Fig. 4B is a hardware structure diagram of a computing device for account processing according to an embodiment. As shown in FIG. 4B, the computing device 400B may include at least one processor 410B, memory 420B, memory 430B, and communication interface 440B, and at least one processor 410B, memory 420B, memory 430B, and communication interface 440B are connected together via a bus 450B. At least one processor 410B executes at least one executable instruction (that is, the above-mentioned element implemented in the form of software) stored or encoded in the memory 420B.

In one embodiment, the executable instructions stored in the memory 420B, when executed by the at least one processor 410B, enable the computing device to implement the various processes described above in conjunction with FIGS. 1 and 2B.

The computing device 400B can be implemented in any suitable form in the art, for example, it includes but is not limited to a desktop computer, a laptop computer, a smart phone, a tablet computer, a consumer electronic device, a wearable smart device, and so on.

For example, the computing device 400B can implement various functions and operations of the aforementioned metering system.

The embodiments of the present specification also provide a machine-readable storage medium. The machine-readable storage medium may store executable instructions, and the executable instructions, when executed by the machine, cause the machine to implement the specific process of the method embodiment described above with reference to FIGS. 1 and 2A.

The embodiments of the present specification also provide a machine-readable storage medium. The machine-readable storage medium may store executable instructions, and the executable instructions, when executed by a machine, cause the machine to implement the specific process of the method embodiment described above with reference to FIGS. 1 and 2B.

For example, the foregoing machine-readable storage medium may include, but is not limited to, random access memory (RAM), read-only memory (Read-Only Memory, ROM), and electrically erasable programmable read-only memory (Electrically-Erasable). Programmable Read-Only Memory, EEPROM), Static Random Access Memory (SRAM), hard disk, flash memory, etc.

It should be understood that the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on descriptions that are similar to other embodiments. the difference. For example, for the above-mentioned embodiments about the device, the embodiment about the computing device, and the embodiment about the machine-readable storage medium, since they are basically similar to the method embodiment, the description is relatively simple, and the relevant parts are referred to the method implementation Part of the example can be explained.

The specific embodiments of this specification are described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than in the embodiments and still achieve desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

It should be understood that for those of ordinary skill in the art, various modifications to the embodiments in this specification will be obvious, and the definitions defined herein can be changed without departing from the scope of protection of the claims. The general principles apply to other variants.

Claims

A method for account processing, wherein the method is executed by a decision system, and the method includes:

Receive a status query request for the target account from the business system;

Determine the balance of the target account;

Determine the availability information of the target account based on the balance, where the availability information is used to indicate whether the target account is currently available;

Sending a status query response to the business system, so that the business system processes the deduction task of the target account based on the status query response, wherein the status query response includes at least the availability information.
The method according to claim 1, wherein the determining the balance of the target account comprises:

The balance is obtained from a metering system, wherein the balance is calculated by the metering system based on real-time flow data of the target account.
The method according to claim 2, wherein the determining the balance of the target account comprises:

If the balance cannot be obtained from the measurement system within a predetermined time period, the balance is obtained from the accounting system, wherein the predetermined time period is less than or equal to the accounting system to update the balance of the target account The maximum delay.
The method according to any one of claims 1 to 3, wherein, if the target account is currently available, the status query response further includes the balance.
The method according to any one of claims 1 to 4, wherein, if the target account is currently available, the method further comprises:

Determine the available time of the target account, wherein, before the available time expires, the business system can perform the deduction task of the target account; when the available time expires, the business system suspends all Describe the deduction task of the target account;

Wherein, the status query response also includes the available time.
The method according to claim 5, wherein the determining the available time of the target account comprises:

Obtaining the predicted value of the net outflow rate of the target account from the metering system, where the predicted value of the net outflow rate of the account is obtained through a prediction model of a machine learning platform;

The available time is determined based on the most recent update time of the balance, the balance and the predicted value of the account net outflow rate.
The method according to any one of claims 1 to 6, wherein the determining the availability information of the target account based on the balance comprises:

Based on the balance and the upper limit of the balance level and the lower limit of the balance level for the target account, it is determined whether the target account is currently available.
The method according to claim 7, wherein said determining whether said target account is currently available comprises:

If the balance is lower than the lower limit of the balance level, determining that the target account is unavailable;

If the balance is higher than the upper limit of the balance level, it is determined that the target account is available;

If the balance is between the lower limit of the balance level and the upper limit of the balance level due to a decline, it is determined that the target account is available;

If the balance is between the lower limit of the balance level and the upper limit of the balance level due to an increase, and the balance before the increase is lower than the lower limit of the balance level, it is determined that the target account is unavailable.
The method according to claim 7 or 8, wherein:

The upper limit of the balance water level and the lower limit of the balance water level are preset; or

The upper limit of the balance level and the lower limit of the balance level are dynamically updated through a machine learning model.
A method for account processing, wherein the method is executed by a metering system, and the method includes:

Obtain real-time flow data of the target account from the streaming computing platform;

Based on the real-time flow data, the balance of the target account is calculated, wherein the balance of the target account is used by the decision-making system to determine the availability information of the target account, and the availability information is used to indicate whether the target account is currently Is available, and the availability information is used by the business system as a basis for processing the deduction task of the target account.
The method according to claim 10, further comprising:

Obtain the predicted value of the net outflow rate of the target account from the machine learning platform through the prediction model, where the predicted value of the net outflow rate of the account is determined by the decision system in combination with the balance and the most recent update time of the balance Determine the available time of the target account;

Wherein, before the available time expires, the business system can execute the deduction task of the target account; when the available time expires, the business system suspends the deduction task of the target account.
A system for account processing, including:

The receiving unit is configured to: receive a status query request for the target account from the business system;

A determining unit, configured to: determine the balance of the target account; determine availability information of the target account based on the balance, wherein the availability information is used to indicate whether the target account is currently available;

A sending unit, configured to send a status query response to the business system, so that the business system can process the deduction task of the target account based on the status query response, wherein the status query response at least includes the availability information.
The system according to claim 12, wherein the determining unit is specifically configured to: when determining the balance of the target account:

The balance is obtained from a metering system, wherein the balance is calculated by the metering system based on real-time flow data of the target account.
The system according to claim 13, wherein when the determining unit determines the balance of the target account, it is specifically configured to:

If the balance cannot be obtained from the measurement system within a predetermined time period, the balance is obtained from the accounting system, wherein the predetermined time period is less than or equal to the accounting system to update the balance of the target account The maximum delay.
The system according to any one of claims 12 to 14, wherein, if the target account is currently available, the status query response further includes the balance.
The system according to any one of claims 12 to 15, wherein, if the target account is currently available, the determining unit is further configured to:

Determine the available time of the target account, wherein, before the available time expires, the business system can perform the deduction task of the target account; when the available time expires, the business system suspends all Describe the deduction task of the target account;

Wherein, the status query response also includes the available time.
The system according to claim 16, wherein when the determining unit determines the available time of the target account, it is specifically configured to:

Obtaining the predicted value of the net outflow rate of the target account from the metering system, where the predicted value of the net outflow rate of the account is obtained through a prediction model of a machine learning platform;

The available time is determined based on the most recent update time of the balance, the balance and the predicted value of the account net outflow rate.
The system according to any one of claims 12 to 17, wherein the determining unit is specifically configured to: when determining the availability information of the target account based on the balance:

Based on the balance and the upper limit of the balance level and the lower limit of the balance level for the target account, it is determined whether the target account is currently available.
The system according to claim 18, wherein the determining unit is specifically configured to: when determining whether the target account is currently available:

If the balance is lower than the lower limit of the balance level, determining that the target account is unavailable;

If the balance is higher than the upper limit of the balance level, it is determined that the target account is available;

If the balance is between the lower limit of the balance level and the upper limit of the balance level due to a decline, it is determined that the target account is available;

If the balance is between the lower limit of the balance level and the upper limit of the balance level due to an increase, and the balance before the increase is lower than the lower limit of the balance level, it is determined that the target account is unavailable.
The system according to claim 18 or 19, wherein:

The upper limit of the balance water level and the lower limit of the balance water level are preset; or

The upper limit of the balance level and the lower limit of the balance level are dynamically updated through a machine learning model.
A system for account processing, including:

The obtaining unit is used to: obtain the real-time flow data of the target account from the streaming computing platform;

The calculation unit is configured to: calculate the balance of the target account based on the real-time flow data, wherein the balance of the target account is used by the decision system to determine the availability information of the target account, and the availability information is used to indicate Whether the target account is currently available, the availability information is used by the business system as a basis for processing the deduction task of the target account.
The system according to claim 21, wherein the acquiring unit is further configured to:

Obtain the predicted value of the net outflow rate of the target account from the machine learning platform through the prediction model, where the predicted value of the net outflow rate of the account is determined by the decision system in combination with the balance and the most recent update time of the balance Determine the available time of the target account;

Wherein, before the available time expires, the business system can execute the deduction task of the target account; when the available time expires, the business system suspends the deduction task of the target account.
A computing device including:

At least one processor;

The memory in communication with the at least one processor has executable instructions stored thereon, and when the executable instructions are executed by the at least one processor, the at least one processor realizes according to claims 1 to 9 Any one of the methods.
A computing device including:

At least one processor;

A memory that communicates with the at least one processor has executable instructions stored thereon, and when the executable instructions are executed by the at least one processor, the at least one processor realizes the method according to claim 10 or 11. The method described.