CN112085495A

CN112085495A - Processing method and device of quota account data

Info

Publication number: CN112085495A
Application number: CN202010885009.0A
Authority: CN
Inventors: 谭新培; 周雨豪; 杨博; 张照胜
Original assignee: Yinqing Technology Co ltd
Current assignee: Yinqing Technology Co ltd
Priority date: 2020-08-28
Filing date: 2020-08-28
Publication date: 2020-12-15

Abstract

The invention discloses a method and a device for processing quota account data, wherein the method comprises the following steps: acquiring quota account data needing prediction, wherein the account data comprises: the system information and the predetermined date are included, and the system comprises one of the following: a small amount system and an online banking system; generating account data into time series data according to a predetermined period granularity; inputting the time series data into a trained time series model to output account prediction data of the quota account on a predetermined date, wherein the account prediction data comprises: account initiation amount data and account receiving amount data in the preset period granularity, and the time sequence model is trained on historical account data of the preset period granularity; and managing the quota account according to the account initiating amount data and the account receiving amount data. The invention can improve the processing efficiency of the payment service and improve the experience of the user.

Description

Processing method and device of quota account data

Technical Field

The invention relates to the field of data processing, in particular to a method and a device for processing quota account data.

Background

Second generation payment systems provide participants (e.g., banks) with very flexible liquidity management mechanisms for fund pools, account package queries, day-to-day auto-borrowing, day-to-day matchmaking, and the like.

The net debit limit is the highest amount that the micropayment system sets for the immediate participant who opened the clearing account, controlling the net debit balance at which payment takes place. The micropayment system sets a net debit limit for the direct participants for risk control. Credit and debit payment transaction receipts initiated by direct participants as well as affiliated indirect participants can only be paid within a net debit limit. When the net debit limit is insufficient, the direct participant can cause that the payment service can not be processed in time, the use of funds of the client and other banks is delayed, and the experience feeling of the user is reduced, so that the reasonable setting and adjustment of the net debit limit have great significance for the participant to normally participate in the clearing service.

However, there is currently no solution that can be rationally set and adjusted for net debit limit accounts.

Disclosure of Invention

In view of the above, the present invention provides a method and an apparatus for processing data of a quota account to solve at least one of the above-mentioned problems.

According to a first aspect of the invention, there is provided a method of processing quota account data, the method comprising:

acquiring quota account data needing prediction, wherein the account data comprises: the system information and the predetermined date, the system comprises one of the following: a small amount system and an online banking system;

generating the account data into time series data according to a predetermined cycle granularity;

inputting the time series data into a trained time series model to output account prediction data of the quota account on the predetermined date, the account prediction data comprising: account initiation amount data and account receipt amount data in the predetermined cycle granularity, the time series model being trained based on historical account data of the predetermined cycle granularity;

and managing the quota account according to the account initiating amount data and the account receiving amount data.

According to a second aspect of the present invention, there is provided an apparatus for processing quota account data, the apparatus comprising:

the prediction data acquisition unit acquires quota account data needing prediction, wherein the account data comprises: the system information and the predetermined date, the system comprises one of the following: a small amount system and an online banking system;

the time sequence data generation unit is used for generating the account data into time sequence data according to a preset cycle granularity;

a prediction unit inputting the time series data to a trained time series model to output account prediction data of the quota account on the predetermined date, the account prediction data including: account initiation amount data and account receipt amount data in the predetermined cycle granularity, the time series model being trained based on historical account data of the predetermined cycle granularity;

and the management unit is used for managing the quota account according to the account initiating amount data and the account receiving amount data.

According to a third aspect of the present invention, there is provided an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method when executing the program.

According to a fourth aspect of the invention, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.

According to the technical scheme, the acquired quota account data needing to be predicted is input into the time series model as the time series data, the time series model can predict the account data of the quota account on the preset date, so that the amount data flow condition of the quota account can be further predicted, the net debit quota account can be reasonably set and adjusted according to the predicted amount data flow condition, the processing efficiency of payment business can be improved, and the experience of a user is improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

FIG. 1 is a flow diagram of a method of processing quota account data according to an embodiment of the invention;

FIG. 2 is a detailed flow diagram of a method of processing quota account data according to an embodiment of the invention;

fig. 3 is a block diagram of a configuration of a processing apparatus of limit account data according to an embodiment of the present invention;

fig. 4 is a detailed configuration block diagram of a processing apparatus of limit account data according to an embodiment of the present invention;

fig. 5 is a schematic block diagram of a system configuration of an electronic apparatus 600 according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

According to the related art, when the net debit limit is insufficient, payment banking business cannot be processed timely, so that the use of funds of a customer and other banks is delayed, and the experience of the user is reduced. Thus, there is a need for a solution that can rationally set and adjust the net debit limit account. Based on the above, the embodiment of the present invention provides a processing scheme for quota account data, which can predict the change of net debit quota of a participant (i.e., a bank) in a period of time in the future according to the historical change of net debit quota of the participant, and can reasonably set and adjust the net debit quota account according to the predicted change of net debit quota, thereby improving the processing efficiency of payment service, improving the experience of a user, and simultaneously providing an important guiding function for reasonably allocating net debit quota and flexibly developing services for the participant. Embodiments of the present invention are described in detail below with reference to the accompanying drawings.

Fig. 1 is a flowchart of a processing method of limit account data according to an embodiment of the present invention, as shown in fig. 1, the method including:

step 101, acquiring quota account data needing prediction, wherein the account data comprises: the system information and the predetermined date, the system comprises one of the following: small amount system, online banking system.

The account data is generated as time series data according to predetermined cycle granularity (e.g., minute-scale granularity, hour-scale granularity, and day-scale granularity), step 102.

Step 103, inputting the time series data into a trained time series model to output account prediction data of the quota account on the predetermined date, wherein the account prediction data comprises: account initiation amount data and account receipt amount data in the predetermined cycle granularity, the time series model being trained based on historical account data of the predetermined cycle granularity.

And 104, managing the quota account according to the account initiating amount data and the account receiving amount data.

In actual operation, determining account net amount data according to the account initiating amount data and the account receiving amount data; and managing the quota account according to the account initiating amount data, the account receiving amount data and the account net amount data.

The acquired quota account data needing to be predicted is input into the time series model as time series data, and the time series model can predict the account data of the quota account on the preset date, so that the amount data flow condition of the quota account can be further predicted, and the net debit quota account can be reasonably set and adjusted according to the predicted amount data flow condition, so that the processing efficiency of payment business can be improved, and the experience of a user can be improved.

Preferably, the time series model is a prophet (a time series model), which may also be referred to as fbprophet model.

In practical operation, the training process of the time series model includes steps (1) to (3):

(1) obtaining historical account data, the historical account data comprising: date, historical account origination amount data and historical account receipt amount data at the predetermined period granularity (e.g., 15 minutes).

(2) And preprocessing the historical account data, and classifying the preprocessed historical account data into training set data and prediction set data.

The pretreatment here includes: deleting or filtering abnormal data in the historical account data; and then, smoothing the historical account data after the deleting or filtering processing is carried out.

(3) And training the time sequence model according to the training set data, and verifying the trained time sequence model according to the prediction set data to obtain the trained time sequence model.

In practical operation, the time series model may be trained by performing a parameter search operation on the time series model according to the training set data to obtain an optimal parameter, where the parameter search operation includes: a grid search operation, a random search operation, and a bayesian optimization operation. And then verifying the trained time series model according to the prediction set data and the optimal parameters based on a preset evaluation index so as to obtain the trained time series model.

The evaluation index here may include: MAPE (Mean Absolute Percentage Error), RMSE (ROOT Mean square Error), R2_ SCORE (an evaluation index), MAE (Mean Absolute Error).

In order to better understand the embodiment of the present invention, the embodiment of the present invention is described in detail below by taking banking as an example. In this example, the quota account data may be payment transaction data in a payment system, and the quota account flow situation of the target participant (e.g., bank) is predicted using prophet (or fbProphet) model, and the prediction data includes: according to the initiator amount (i.e. account initiating amount data), the receiver amount (i.e. account receiving amount data) and the net amount (i.e. account net amount data) of the limited account of the participant, the prediction is carried out according to the 15-minute granularity (also hour granularity and day granularity). This example is described below in conjunction with the detailed processing flow of the limit account data shown in fig. 2.

As shown in fig. 2, this example specifically includes the following flow:

(1) the original data is historical net debit limit account data of the participants, the original data is processed to obtain traffic statistical data with regular forms of minute-level granularity, hour-level granularity and day-level granularity, and the data can be used as intermediate data.

(2) And (4) performing data exploration on the intermediate data, and finding out data distribution rules, missing data, abnormal data, seasonal characteristics and the like.

(3) Preprocessing the intermediate data after data exploration, and respectively performing missing value processing, abnormal outlier rejection, standardization processing, smoothing processing and the like.

In actual operation, there may be a missing record or missing value labeled as 'UNKNOWN/NaN/NULL/-' in the original data, and such data may be left unprocessed or such record may be deleted directly.

Such records may be deleted in actual practice for the case where consecutive outliers, such as consecutive weekly/monthly data, are constant values.

The method can automatically process accidental outlier prophet models, and if data outliers are frequent and distributed irregularly, related filtering algorithms can be used for modulating or directly removing the records. For example, for the case that the data has asymmetric distribution, obvious fluctuation and skewed distribution, the filtering process can be performed by adopting an Adjusted Boxplot (Adjusted Boxplot) algorithm.

The data with large absolute value and severe fluctuation can be smoothed. Specifically, the volatility of the data can be reduced by normalization or taking a logarithm operation.

(4) And carrying out data division on the preprocessed data to obtain a training data set and a test data set.

(5) Training a model by using training data, and performing parameter search operation of the model, wherein the search method specifically comprises the following steps: grid search, random search and bayesian optimization. And performing cross validation on the model after the parameter search to finally obtain the model with the optimal parameter combination for the service data.

(6) And using the test data and the optimal parameters as the input of the fbProphet model, wherein the output of the model is service prediction data of corresponding data granularity.

(7) And (3) evaluating the prediction data output in the step (6), wherein evaluation indexes comprise MAPE, RMSE, R2_ SCORE, MAE and the like, and further adjusting the parameters of fbProphet according to the evaluation result to obtain the trained fbProphet model.

(8) And predicting net debit quota account data according to the trained fbProphet model, and storing and visualizing the prediction result.

In one embodiment, for constructing the Prophet model, the input data form is simple, and only the data structure of the data frame containing the 'ds' timestamp and the 'y' value to be predicted is needed, and modeling prediction is respectively carried out on the filtered and logarithmized 15-minute participant receiving amount and sending amount by combining the prediction target.

In actual practice, the fbProphet algorithm mainly considers the following four terms, namely:

y(t)＝g(t)+s(t)+h(t)+∈_t

wherein, g (t) represents a trend item, which represents the variation trend of the time series on the non-periodic top; s (t) represents a period term, alternatively referred to as a seasonal term, typically in units of weeks or years; h (t) represents a holiday term which represents whether holidays exist on the same day;_trepresenting an error term or a residue term. The fbProphet algorithm is to fit these terms and then add them together to obtain a predicted value of the time series.

Therefore, for the Prophet model, the following aspects are mainly considered:

(1) trending assembly

The trend component is used for describing trend changes of the data, and in the embodiment of the invention, a 'linear' model is adopted for data characteristics of the business system.

(2) Seasonal assembly

In the data exploration stage, the seasonal characteristics of data with different periods can be found, and corresponding components can be added.

(3) Festival and holiday effect assembly

The addition of a holiday component can make the model more sensitive to data changes during holidays.

In one embodiment, for the model parameter tuning operation, a bayesian optimization + cross validation method may be adopted to perform parameter search on the model, where the target is an optimization objective function value, and the objective function may be the inverse of RMSE or MAPE. Finally, the parameter combination with the maximum target value is obtained and can be used as the optimal parameter, namely the model parameter.

According to the embodiment of the invention, historical net debit limit account data of the participant is used as time sequence data, and the fbProphet model is used for analyzing and predicting the historical net debit limit account data, so that the net debit limit change of the participant in a future period of time is predicted, and the method has an important guiding function on reasonable allocation of the net debit limit of the participant and flexible service development.

Based on similar inventive concepts, the embodiment of the present invention further provides a device for processing quota account data, and preferably, the device is configured to implement the processes in the above method embodiments.

Fig. 3 is a block diagram showing a configuration of a limited-account data processing apparatus according to an embodiment of the present invention, as shown in fig. 3, the apparatus including: a prediction data acquisition unit 31, a time-series data generation unit 32, a prediction unit 33, and a management unit 34, wherein:

a prediction data acquisition unit 31 that acquires quota account data that needs to be predicted, the account data including: the system information and the predetermined date, the system comprises one of the following: a small amount system and an online banking system;

a time series data generating unit 32 for generating the account data as time series data according to a predetermined cycle granularity;

a prediction unit 33, which inputs the time series data into the trained time series model to output account prediction data of the quota account on the predetermined date, wherein the account prediction data comprises: account initiation amount data and account receipt amount data in the predetermined cycle granularity, the time series model being trained based on historical account data of the predetermined cycle granularity;

and the management unit 34 is used for managing the quota account according to the account initiating amount data and the account receiving amount data.

In one embodiment, the management unit 34 includes: net amount data determination module and management module, wherein:

the net amount data determining module is used for determining account net amount data according to the account initiating amount data and the account receiving amount data;

and the management module is used for managing the quota account according to the account initiating amount data, the account receiving amount data and the account net amount data.

The quota account data which needs to be predicted and is acquired by the prediction data acquisition unit 31 is input into the time series model through the prediction unit 33 as time series data, and the time series model can predict the account data of the quota account at a preset date, so that the management unit 34 can predict the flow condition of the amount data of the quota account, and can reasonably set and adjust the net debit quota account according to the predicted flow condition of the amount data, thereby improving the processing efficiency of payment business and improving the experience of users.

In actual practice, the time series model may be a prophet model.

Specifically, as shown in fig. 4, the quota account data processing apparatus further includes: a model training unit 35, configured to train the prediction model.

The model training unit 35 specifically includes: historical data acquisition module, preprocessing module, data classification module and training module, wherein:

a historical data acquisition module for acquiring the historical account data, wherein the historical account data comprises: date, historical account origination amount data, and historical account receipt amount data in the predetermined period granularity.

And the preprocessing module is used for preprocessing the historical account data. Specifically, the preprocessing module includes: an exception data processing sub-module and a smoothing sub-module, wherein: the abnormal data processing submodule is used for deleting or filtering abnormal data in the historical account data; and the smoothing sub-module is used for smoothing the historical account data after the deletion or the filtering.

And the data classification module is used for classifying the preprocessed historical account data into training set data and prediction set data.

And the training module is used for training the time sequence model according to the training set data and verifying the trained time sequence model according to the prediction set data so as to obtain the trained time sequence model.

In one embodiment, the training module comprises: a training submodule and a validation submodule, wherein:

a training submodule, configured to perform a parameter search operation on the time series model according to the training set data to obtain an optimal parameter, so as to train the time series model, where the parameter search operation includes: grid searching operation, random searching operation and Bayesian optimization operation;

and the verification sub-module is used for verifying the trained time series model according to the prediction set data and the optimal parameters based on a preset evaluation index.

For specific execution processes of the units, the modules, and the sub-modules, reference may be made to the description in the foregoing method embodiments, and details are not described here again.

In practical operation, the units, the modules and the sub-modules may be combined or may be arranged singly, and the present invention is not limited thereto.

The present embodiment also provides an electronic device, which may be a desktop computer, a tablet computer, a mobile terminal, and the like, but is not limited thereto. In this embodiment, the electronic device may be implemented by referring to the above method embodiment and the limited account data processing apparatus embodiment, and the contents thereof are incorporated herein, and repeated details are not repeated.

Fig. 5 is a schematic block diagram of a system configuration of an electronic apparatus 600 according to an embodiment of the present invention. As shown in fig. 5, the electronic device 600 may include a central processor 100 and a memory 140; the memory 140 is coupled to the central processor 100. Notably, this diagram is exemplary; other types of structures may also be used in addition to or in place of the structure to implement telecommunications or other functions.

In one embodiment, the limit account data processing functionality may be integrated into the central processor 100. The central processor 100 may be configured to control as follows:

As can be seen from the above description, in the electronic device provided in the embodiment of the present application, the acquired quota account data that needs to be predicted is input as time-series data to the time-series model, and the time-series model can predict account data of the quota account on a predetermined date, so that the money amount data flow condition of the quota account can be further predicted, and the net debit quota account can be reasonably set and adjusted according to the predicted money amount data flow condition, so that the processing efficiency of the payment service can be improved, and the experience of the user can be improved.

In another embodiment, the limit account data processing apparatus may be configured separately from the central processor 100, for example, the limit account data processing apparatus may be configured as a chip connected to the central processor 100, and the limit account data processing function is realized by the control of the central processor.

As shown in fig. 5, the electronic device 600 may further include: communication module 110, input unit 120, audio processing unit 130, display 160, power supply 170. It is noted that the electronic device 600 does not necessarily include all of the components shown in fig. 5; furthermore, the electronic device 600 may also comprise components not shown in fig. 5, which may be referred to in the prior art.

As shown in fig. 5, the central processor 100, sometimes referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, the central processor 100 receiving input and controlling the operation of the various components of the electronic device 600.

The memory 140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 100 may execute the program stored in the memory 140 to realize information storage or processing, etc.

The input unit 120 provides input to the cpu 100. The input unit 120 is, for example, a key or a touch input device. The power supply 170 is used to provide power to the electronic device 600. The display 160 is used to display an object to be displayed, such as an image or a character. The display may be, for example, an LCD display, but is not limited thereto.

The memory 140 may be a solid state memory such as Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 140 may also be some other type of device. Memory 140 includes buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application/function storage section 142, and the application/function storage section 142 is used to store application programs and function programs or a flow for executing the operation of the electronic device 600 by the central processing unit 100.

The memory 140 may also include a data store 143, the data store 143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by the electronic device. The driver storage portion 144 of the memory 140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging application, address book application, etc.).

The communication module 110 is a transmitter/receiver 110 that transmits and receives signals via an antenna 111. The communication module (transmitter/receiver) 110 is coupled to the central processor 100 to provide an input signal and receive an output signal, which may be the same as in the case of a conventional mobile communication terminal.

Based on different communication technologies, a plurality of communication modules 110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and receive audio input from the microphone 132 to implement general telecommunications functions. Audio processor 130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, an audio processor 130 is also coupled to the central processor 100, so that recording on the local can be enabled through a microphone 132, and so that sound stored on the local can be played through a speaker 131.

An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the steps of the limited account data processing method.

In summary, the embodiments of the present invention provide a processing scheme for quota account data, which can predict a change in net debit quota of a participant (i.e., a bank) in a future period of time according to a historical change in net debit quota of the participant, and can reasonably set and adjust a net debit quota account according to the predicted change in net debit quota, thereby improving processing efficiency of payment services, improving experience of users, and simultaneously providing an important guidance function for reasonably allocating net debit quota and flexibly conducting services for the participant.

The preferred embodiments of the present invention have been described above with reference to the accompanying drawings. The many features and advantages of the embodiments are apparent from the detailed specification, and thus, it is intended by the appended claims to cover all such features and advantages of the embodiments which fall within the true spirit and scope thereof. Further, since numerous modifications and changes will readily occur to those skilled in the art, it is not desired to limit the embodiments of the invention to the exact construction and operation illustrated and described, and accordingly, all suitable modifications and equivalents may be resorted to, falling within the scope thereof.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. A method for processing quota account data, the method comprising:

2. The method of claim 1, wherein the time series model is a prophet model, and wherein the time series model is trained by:

obtaining the historical account data, wherein the historical account data comprises: date, historical account origination amount data and historical account receipt amount data in the predetermined period granularity;

preprocessing the historical account data, and classifying the preprocessed historical account data into training set data and prediction set data;

and training the time sequence model according to the training set data, and verifying the trained time sequence model according to the prediction set data to obtain the trained time sequence model.

3. The method of claim 2, wherein preprocessing the historical account data comprises:

deleting or filtering abnormal data in the historical account data;

and smoothing the historical account data subjected to the deleting or filtering process.

4. The method of claim 2, wherein training the time series model from the training set data comprises:

performing parameter search operation on the time series model according to the training set data to obtain an optimal parameter, so as to train the time series model, wherein the parameter search operation comprises: a grid search operation, a random search operation, and a bayesian optimization operation.

5. The method of claim 4, wherein validating the trained time series model from the prediction set data comprises:

and verifying the trained time series model according to the prediction set data and the optimal parameters based on a preset evaluation index.

6. The method of claim 1, wherein managing the quota account based on the account origination amount data and the account receipt amount data comprises:

determining account net amount data according to the account initiating amount data and the account receiving amount data;

and managing the quota account according to the account initiating amount data, the account receiving amount data and the account net amount data.

7. An apparatus for processing quota account data, the apparatus comprising:

8. The apparatus of claim 7, wherein the time series model is a prophet model, the apparatus further comprising:

a model training unit for training the prediction model,

the model training unit specifically comprises:

a historical data acquisition module for acquiring the historical account data, wherein the historical account data comprises: date, historical account origination amount data and historical account receipt amount data in the predetermined period granularity;

the preprocessing module is used for preprocessing the historical account data;

the data classification module is used for classifying the preprocessed historical account data into training set data and prediction set data;

9. The apparatus according to claim 8, wherein the preprocessing module specifically comprises:

the abnormal data processing submodule is used for deleting or filtering abnormal data in the historical account data;

and the smoothing sub-module is used for smoothing the historical account data after the deletion or the filtering.

10. The apparatus of claim 8, wherein the training module specifically comprises:

11. The apparatus of claim 7, wherein the management unit comprises:

12. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 6 are implemented when the processor executes the program.

13. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.