CN117217897A

CN117217897A - Resource change data early warning method, device, computer equipment and storage medium

Info

Publication number: CN117217897A
Application number: CN202311213280.XA
Authority: CN
Inventors: 史杰; 赵庆; 樊笑冰; 郭晨; 李二壮
Original assignee: Bank of China Ltd
Current assignee: Bank of China Ltd
Priority date: 2023-09-19
Filing date: 2023-09-19
Publication date: 2023-12-12

Abstract

The application relates to the technical field of artificial intelligence, in particular to a resource change data early warning method, a device, computer equipment and a storage medium. The method comprises the following steps: acquiring real-time transaction data of a current time period and forecast resource change data of the current time period; monitoring the real-time resource change data in the current time period according to the real-time transaction data and the forecast resource change data, and generating a resource change data monitoring result in the current time period; and carrying out early warning based on the resource change data monitoring result in the current time period, and generating a resource change data early warning result. By adopting the method, the resource change data of the account can be early warned in real time when the resource change data of the account is insufficient.

Description

Resource change data early warning method, device, computer equipment and storage medium

Technical Field

The present application relates to the field of artificial intelligence technologies, and in particular, to a method and apparatus for early warning of resource change data, a computer device, and a storage medium.

Background

The resource change data includes fund position data, the fund position is simply referred to as position, and the position refers to the amount of funds owned or borrowed by the investor, i.e. the position can be understood as available money. In order to know the available money data of the account more accurately, the resource change data of the account needs to be monitored and pre-warned to avoid funds clearing or transaction failure caused by insufficient resource change data of the account, so that negative effects on banks and payment institutions are avoided.

In the traditional method, when each transaction is carried out, the resource change data of the account is required to be monitored and pre-warned manually so as to determine whether the condition of insufficient resource change data occurs.

However, the conventional method of manually pre-warning the resource change data cannot ensure that the resource change data is monitored and pre-warned in real time. Therefore, the traditional resource change data early warning method has the problem that real-time early warning cannot be performed when the resource change data of the account is insufficient.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a resource change data early warning method, apparatus, computer device, and storage medium that can early warn in real time when the resource change data of an account is insufficient.

In a first aspect, the present application provides a method for early warning of resource variation data. The method comprises the following steps:

acquiring real-time transaction data of a current time period and forecast resource change data of the current time period;

monitoring the real-time resource change data of the current time period according to the real-time transaction data and the forecast resource change data, and generating a resource change data monitoring result of the current time period;

And carrying out early warning based on the resource change data monitoring result in the current time period, and generating a resource change data early warning result.

In one embodiment, the forecast resource variation data includes a single batch of forecast resource variation data and cumulative forecast resource variation data, and the real-time transaction data includes a single batch of real-time transaction data and cumulative real-time transaction data; the monitoring of the real-time resource variation data of the current time period according to the real-time transaction data and the forecast resource variation data generates a resource variation data monitoring result of the current time period, including:

comparing the single forecast resource change data in the current time period with the single real-time transaction data in the current time period to generate a first comparison result;

comparing according to the accumulated forecast resource change data in the current time period and the accumulated real-time transaction data in the current time period to generate a second comparison result;

and monitoring the real-time resource change data in the current time period according to the first comparison result and the second comparison result, and generating a resource change data monitoring result in the current time period.

In one embodiment, the monitoring the real-time resource variation data in the current time period according to the first comparison result and the second comparison result, and generating the resource variation data monitoring result in the current time period includes:

judging whether the first comparison result and the second comparison result meet a preset condition or not; the preset condition includes that the first comparison result is that single forecast resource change data in the current time period is smaller than single real-time transaction data in the current time period, and/or the second comparison result is that accumulated forecast resource change data in the current time period is smaller than accumulated real-time transaction data in the current time period;

if the first comparison result and the second comparison result meet the preset condition, monitoring the real-time resource change data in the current time period to generate a first resource change data monitoring result; the first resource change data monitoring result is used for representing that the resource change data of the current time period is smaller than a preset resource change data threshold value;

if the first comparison result and the second comparison result do not meet the preset condition, monitoring the real-time resource change data in the current time period to generate a second resource change data monitoring result; and the second resource change data monitoring result is used for representing that the resource change data of the current time period is larger than or equal to a preset resource change data threshold value.

In one embodiment, the method further comprises:

predicting forecast resource change data in the current time period according to historical transaction data in the preset time period and a preset neural network model; the current time period is a time period after the preset time period.

In one embodiment, the predicting the forecast resource variation data in the current time period according to the historical transaction data in the preset time period and the preset neural network model includes:

acquiring historical transaction data in a preset time period according to a preset dimension; the preset dimension comprises at least one of currency type, transaction amount and clearing financial institution identification;

according to the preset dimension, historical transaction data in the preset time period are input into the preset neural network model for prediction, and single forecast resource change data in the current time period are generated;

and calculating based on the single forecast resource change data in the current time period to obtain the accumulated forecast resource change data in the current time period.

In one embodiment, the method further comprises:

acquiring historical transaction data in the historical time period and historical resource change data in the historical time period according to the preset dimension;

Inputting the historical transaction data in the historical time period into an initial neural network model for prediction, and generating predicted resource change data in the historical time period;

training the initial neural network model according to the predicted resource change data and the historical resource change data to generate the preset neural network model.

In a second aspect, the application further provides a resource change data early warning device. The device comprises:

the acquisition module is used for acquiring real-time transaction data of the current time period and forecast resource change data of the current time period;

the monitoring module is used for monitoring the real-time resource change data of the current time period according to the real-time transaction data and the forecast resource change data and generating a resource change data monitoring result of the current time period;

and the early warning module is used for carrying out early warning based on the resource change data monitoring result in the current time period and generating a resource change data early warning result.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the steps of the method in any of the embodiments of the first aspect described above when the processor executes the computer program.

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method in any of the embodiments of the first aspect described above.

In a fifth aspect, the present application also provides a computer program product. The computer program product comprising a computer program which, when executed by a processor, implements the steps of the method in any of the embodiments of the first aspect described above.

The resource change data early warning method, the resource change data early warning device, the computer equipment and the storage medium acquire real-time transaction data of the current time period and forecast resource change data of the current time period; monitoring the real-time resource change data in the current time period according to the real-time transaction data and the forecast resource change data, and generating a resource change data monitoring result in the current time period; and carrying out early warning based on the resource change data monitoring result in the current time period, and generating a resource change data early warning result. The method and the device can acquire the forecast resource change data of the current time period in advance and acquire the real-time transaction data of the current time period in real time, so that the method and the device can acquire the real-time transaction data and the forecast resource change data acquired in advance according to the real-time transaction data acquired in real time. And carrying out real-time monitoring on the real-time resource change data in the current time period to generate a real-time monitoring result of the resource change data in the current time period. And then, carrying out real-time early warning based on the real-time monitoring result of the resource change data in the current time period, and generating a real-time early warning result of the resource change data. Therefore, the application can intelligently monitor the resource change data of the current time period in real time, and can perform real-time early warning on the real-time resource change data of the current time period under the condition of insufficient resource change data, and can win the time for business personnel to take corresponding measures, thereby avoiding the risk that cross-border funds clearing cannot be completed on time due to insufficient resource change data and reducing the funds loss and credit influence of banks and third party payment institutions.

Drawings

FIG. 1 is an application environment diagram of a resource change data pre-warning method in one embodiment;

FIG. 2 is a flow chart of a method for early warning of resource change data in one embodiment;

FIG. 3 is a flow chart of a monitoring step in one embodiment;

FIG. 4 is a flow chart illustrating the judging step in one embodiment;

FIG. 5 is a flowchart illustrating steps for generating forecast resource variation data in one embodiment;

FIG. 6 is a flowchart illustrating a pre-set neural network model generation step according to another embodiment;

FIG. 7 is a flow chart of an alternative embodiment of a method for pre-warning resource variation data;

FIG. 8 is a block diagram illustrating a resource change data pre-warning device according to an embodiment;

fig. 9 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

However, the conventional method of manually pre-warning the resource change data cannot ensure that the resource change data is monitored and pre-warned in real time. Therefore, when the cross-border money transfer transaction data exceeds the resource change data, the business personnel cannot find out at the first time and cannot take measures in time to cope with the problem of insufficient resource change data, so that the cross-border funds are influenced to be cleared to the outside in a specified time, and negative effects such as funds loss or credit reduction are caused to banks and payment institutions. The third party payment authority or bank may also face a regulatory penalty if a substantial amount of funds are involved and the clearing is not complete. Therefore, the traditional resource change data early warning method has the problem that real-time early warning cannot be performed when the resource change data of the account is insufficient.

The resource change data early warning method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The server 104 acquires real-time transaction data of the current time period and forecast resource change data of the current time period; the server 104 monitors the real-time resource change data in the current time period according to the real-time transaction data and the forecast resource change data, and generates a resource change data monitoring result in the current time period; the server 104 performs early warning based on the resource change data monitoring result in the current time period, and generates a resource change data early warning result. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.

In one embodiment, as shown in fig. 2, a resource change data early warning method is provided, and the method is applied to the server 104 in fig. 1 for illustration, and includes the following steps:

s220, acquiring real-time transaction data of the current time period and forecast resource change data of the current time period.

The current time period is a time period for carrying out real-time monitoring and real-time early warning on the resource change data. The real-time transaction data of the current time period refers to transaction data obtained during the transaction performed in the current time period. In an embodiment of the present application, the transaction process may include, but is not limited to, a process of a cross-border money transfer transaction, where a scenario of the cross-border money transfer transaction refers to a business scenario in which a third party payment mechanism cooperates with a bank to conduct a centralized cross-border money transfer. The forecast resource change data of the current time zone refers to resource change data obtained by predicting the resource change data of the current time zone in a time zone before the current time zone. The forecast resource change data for the current time period is used to characterize the predicted balance available for the current time period. Position refers to the amount of funds owned or borrowed by an investor, i.e., position can be understood as an available term or available funds.

Alternatively, the server 104 may directly obtain the forecast resource change data for the current time period. Alternatively, the server 104 may acquire real-time transaction data in a period of time preceding the current period of time in real-time during the period of time preceding the current period of time. Then, the server 104 may predict the forecast resource variation data of the current time period according to the real-time transaction data of the time period before the current time period. Of course, the method for obtaining the forecast resource change data is not limited in this embodiment.

Alternatively, the server 104 may directly obtain real-time transaction data for the current time period. Or, the server 104 may also accept the batch cross-border money transfer transaction initiated by the third party payment mechanism in the current time period, and trade the batch cross-border money transfer transaction, generate the transaction data in the current time period, and record the transaction data in the current time period in the preset database. Second, the server 104 may obtain, according to the preset dimension, a single real-time transaction data in the current time period from the transaction data in the current time period. The predetermined dimension may include, but is not limited to, at least one of a coin type, a transaction amount, and a clearing financial institution identification. The single real-time transaction data refers to real-time transaction data corresponding to each transaction. The server 104 may then calculate based on the single real-time transaction data during the current time period, resulting in cumulative real-time transaction data during the current time period. The calculation method may include, but is not limited to, summation, weighted summation, and the like. The accumulated real-time transaction data refers to real-time transaction data obtained by calculating each transaction. Of course, the method of acquiring the real-time transaction data is not limited in this embodiment.

And S240, monitoring the real-time resource change data in the current time period according to the real-time transaction data and the forecast resource change data, and generating a resource change data monitoring result in the current time period.

Optionally, the server 104 may monitor the real-time resource variation data in the current time period according to the real-time transaction data and the forecast resource variation data, so as to generate a resource variation data monitoring result in the current time period. For example, the server 104 may obtain real-time transaction data in real-time each time a transaction is conducted during the current time period. Thus, the server 104 can compare the real-time transaction data with the forecast resource variation data for the current time period to generate a comparison result. Then, the server 104 may monitor the real-time resource change data in the current time period according to the comparison result, and generate a resource change data monitoring result in the current time period. Wherein the real-time resource change data of the current time period refers to the real-time available balance remaining after the transaction in the current time period. The monitoring result of the resource change data in the current time period is used for representing the situation that the real-time resource change data in the current time period is left or the resource change data is insufficient. The condition of insufficient resource change data is used for representing the condition that the transaction cannot be carried out due to insufficient resource change data or available balance.

And S260, early warning is carried out based on the resource change data monitoring result of the current time period, and a resource change data early warning result is generated.

For example, the server 104 may determine whether the real-time resource variation data of the current time period is insufficient based on the monitoring result of the resource variation data of the current time period. If it is determined that the real-time resource change data in the current time period is insufficient, the server 104 may perform early warning on the real-time resource change data in the current time period, and generate a resource change data early warning result. The resource change data early warning result is a prompt message for informing that the resource change data is insufficient. Therefore, the server 104 may send the resource change data early-warning result to the terminal 102, so that the terminal 102 sends the resource change data early-warning result to the service personnel through a display interface such as a short message or a line message, so as to output the early-warning information of insufficient resource change data to the service personnel. The financial service platform is used for transmitting information among operators.

Therefore, business personnel can take countermeasures in time according to the early warning information. Among these countermeasures may include, but are not limited to, adjusting the position, placing the transaction on the next day, etc. Then, assuming that the countermeasure is to allocate a position, the server 104 may acquire position allocation data (i.e., allocated resource change data) according to the countermeasure, and update the forecast resource change data of the current time period according to the position allocation data, that is, determine the result of summing the forecast resource change data of the current time period and the position allocation data as the updated forecast resource change data of the current time period. Therefore, the server 104 can monitor and pre-warn the real-time resource change data of the current time period according to the updated forecast resource change data of the current time period.

In the resource change data early warning method, real-time transaction data in the current time period and forecast resource change data in the current time period are obtained; monitoring the real-time resource change data in the current time period according to the real-time transaction data and the forecast resource change data, and generating a resource change data monitoring result in the current time period; and carrying out early warning based on the resource change data monitoring result in the current time period, and generating a resource change data early warning result. The method and the device can acquire the forecast resource change data of the current time period in advance and acquire the real-time transaction data of the current time period in real time, so that the method and the device can acquire the real-time transaction data and the forecast resource change data acquired in advance according to the real-time transaction data acquired in real time. And carrying out real-time monitoring on the real-time resource change data in the current time period to generate a real-time monitoring result of the resource change data in the current time period. And then, carrying out real-time early warning based on the real-time monitoring result of the resource change data in the current time period, and generating a real-time early warning result of the resource change data. Therefore, the application can intelligently monitor the resource change data of the current time period in real time, and can perform real-time early warning on the real-time resource change data of the current time period under the condition of insufficient resource change data, and can win the time for business personnel to take corresponding measures, thereby avoiding the risk that cross-border funds clearing cannot be completed on time due to insufficient resource change data and reducing the funds loss and credit influence of banks and third party payment institutions.

In the above embodiments, the monitoring of the real-time resource change data in the current time period according to the real-time transaction data and the forecast resource change data is related to generating the monitoring result of the resource change data in the current time period, and the specific method thereof is described below. In one embodiment, as shown in fig. 3, the forecast resource variation data includes a single piece of forecast resource variation data and an accumulated forecast resource variation data, the real-time transaction data includes a single piece of real-time transaction data and an accumulated real-time transaction data, and S240 includes:

s320, comparing the single forecast resource change data in the current time period with the single real-time transaction data in the current time period to generate a first comparison result.

S340, comparing the accumulated forecast resource change data in the current time period with the accumulated real-time transaction data in the current time period to generate a second comparison result.

Optionally, since the forecast resource variation data of the current time period includes a single forecast resource variation data of the current time period and an accumulated forecast resource variation data of the current time period, the real-time transaction data of the current time period includes a single real-time transaction data of the current time period and an accumulated real-time transaction data of the current time period. Thus, the server 104 may compare the single forecast resource change data during the current time period with the single real-time transaction data during the current time period to generate a first comparison result. And the server 104 may compare the accumulated forecast resource variation data during the current time period with the accumulated real-time transaction data during the current time period to generate a second comparison result. The first comparison result is used for representing the size relation between single forecast resource change data and single real-time transaction data, and the second comparison result is used for representing the size relation between accumulated forecast resource change data and accumulated real-time transaction data. It should be noted that, in the embodiment of the present application, the sequence of generating the first comparison result and the second comparison result is not limited, and it can be understood that the first comparison result is generated first and the second comparison result is regenerated; or, the second comparison result is generated first, and the first comparison result is generated; alternatively, the first comparison result and the second comparison result may be generated simultaneously.

And S360, monitoring the real-time resource change data in the current time period according to the first comparison result and the second comparison result, and generating a resource change data monitoring result in the current time period.

Optionally, the server 104 may monitor the real-time resource variation data in the current time period according to the first comparison result and the second comparison result, and generate a resource variation data monitoring result in the current time period. Wherein the real-time resource change data of the current time period refers to the real-time available balance remaining after the transaction in the current time period. The monitoring result of the resource change data in the current time period is used for representing the situation that the real-time resource change data in the current time period is left or the resource change data is insufficient.

In one alternative embodiment, as shown in fig. 4, S360 includes:

s420, judging whether the first comparison result and the second comparison result meet preset conditions; the preset condition includes that the first comparison result is that the single forecast resource change data in the current time period is smaller than the single real-time transaction data in the current time period, and/or the second comparison result is that the accumulated forecast resource change data in the current time period is smaller than the accumulated real-time transaction data in the current time period.

Alternatively, according to the first comparison result and the second comparison result, the server 104 may determine whether the first comparison result and the second comparison result satisfy the preset condition. The preset condition includes that the first comparison result is that the single forecast resource change data in the current time period is smaller than the single real-time transaction data in the current time period, and/or the second comparison result is that the accumulated forecast resource change data in the current time period is smaller than the accumulated real-time transaction data in the current time period. It can be understood that the preset condition is satisfied when the single forecast resource change data in the current time period is smaller than the single real-time transaction data in the current time period, or the accumulated forecast resource change data in the current time period is smaller than the accumulated real-time transaction data in the current time period. It should be noted that, in the embodiment of the present application, the order of judging the first comparison result and judging the second comparison result is not limited, and it can be understood that the first comparison result is judged first and then the second comparison result is judged; or, the second comparison result may be judged first, and then the first comparison result may be judged; alternatively, the first comparison result and the second comparison result may be determined simultaneously.

S440, if the first comparison result and the second comparison result meet the preset conditions, monitoring the real-time resource change data in the current time period to generate a first resource change data monitoring result; the first resource change data monitoring result is used for representing that the resource change data of the current time period is smaller than a preset resource change data threshold value.

Optionally, if the first comparison result and the second comparison result meet the preset condition, it is indicated that the real-time resource change data in the current time period has insufficient resource change data, and the server 104 may monitor the real-time resource change data in the current time period to generate a first resource change data monitoring result. The first resource change data monitoring result is used for representing that the resource change data in the current time period is smaller than a preset resource change data threshold, namely, representing that the real-time resource change data in the current time period has insufficient resource change data. The preset resource change data threshold may be 0, or may be set according to actual situations, and of course, the embodiment of the present application does not limit the preset resource change data threshold.

S460, if the first comparison result and the second comparison result do not meet the preset condition, monitoring the real-time resource change data in the current time period to generate a second resource change data monitoring result; and the second resource change data monitoring result is used for representing that the resource change data of the current time period is larger than or equal to a preset resource change data threshold value.

Optionally, if the first comparison result and the second comparison result do not meet the preset condition, it is indicated that the real-time resource change data in the current time period remains, that is, it is indicated that the real-time resource change data in the current time period can meet the transaction requirement, and the server 104 can monitor the real-time resource change data in the current time period and generate the second resource change data monitoring result. The second resource change data monitoring result is used for representing that the resource change data in the current time period is larger than or equal to a preset resource change data threshold, namely, representing that the real-time resource change data in the current time period can meet the transaction requirement. The preset resource change data threshold may be 0, or may be set according to actual situations, and of course, the embodiment of the present application does not limit the preset resource change data threshold.

In the embodiment, a more accurate first comparison result is generated according to the single forecast resource change data in the current time period and the single real-time transaction data in the current time period; and comparing the accumulated forecast resource change data in the current time period with the accumulated real-time transaction data in the current time period to generate a more accurate second comparison result. The real-time resource change data in the current time period can be monitored in real time more accurately according to the more accurate first comparison result and the more accurate second comparison result, so that the resource change data monitoring result in the current time period can be generated more accurately. Furthermore, whether the real-time resource change data in the current time period is insufficient or not can be accurately determined.

In the above embodiments, the acquisition of the real-time transaction data of the current time period and the forecast resource variation data of the current time period are involved, and a specific method for acquiring the forecast resource variation data of the current time period is described below. In one embodiment, the resource change data early warning method further includes:

predicting forecast resource change data in the current time period according to historical transaction data in the preset time period and a preset neural network model; the current time period is a time period after a preset time period.

Alternatively, the server 104 may obtain a preset neural network model in advance, and may obtain historical transaction data for a preset period of time in advance. Then, the server 104 may predict the forecast resource variation data in the current time period according to the historical transaction data in the preset time period and the preset neural network model. The current time period is a time period after the preset time period, that is, the preset time period is a time period before the current time period. The historical transaction data within the preset time period refers to transaction data before the current time period, which has been subjected to transactions. The preset neural network model is used for predicting forecast resource change data in the current time period based on historical transaction data in the preset time period. The preset neural network model may be any one of the neural network models for which model training has been completed. For example, the pre-set neural network model includes, but is not limited to, a dense neural network model, a convolutional neural network model, a recurrent neural network model, and the like.

In this embodiment, since the preset neural network model is a neural network model that has completed model training, the prediction effect of the preset neural network model is good. Therefore, the forecast resource change data in the current time period can be accurately predicted based on the historical transaction data in the preset time period and the accurate preset neural network model. Furthermore, more accurate forecast resource change data in the current time period can be obtained.

In the above embodiment, the prediction of the forecast resource change data in the current time period according to the historical transaction data in the preset time period and the preset neural network model is referred to, and the specific method thereof is described below. In one embodiment, as shown in fig. 5, predicting the forecast resource variation data in the current time period according to the historical transaction data in the preset time period and the preset neural network model includes:

s520, acquiring historical transaction data in a preset time period according to a preset dimension; the preset dimension includes at least one of a currency type, a transaction amount, and a clearing financial institution identification.

Alternatively, the server 104 may obtain historical transaction data for a predetermined period of time directly from a predetermined database. Alternatively, the server 104 may acquire the historical transaction data in real time within a preset time period. Then, the server 104 may classify the historical transaction data in the preset time period according to the preset dimension, so as to obtain the historical transaction data in the preset time period acquired according to the preset dimension. Wherein the predetermined dimension includes at least one of a currency type, a transaction amount, and a clearing financial institution identification. Different clearing financial institution identifications correspond to different clearing lines.

S540, according to the preset dimension, the historical transaction data in the preset time period are input into a preset neural network model for prediction, and single forecast resource change data in the current time period are generated.

Optionally, according to the preset dimension, the server 104 may input the historical transaction data in the preset time period into the preset neural network model to predict, and generate single forecast resource change data in the current time period. For each currency type, the server 104 may sequentially input historical transaction data in a preset time period corresponding to each currency type into a preset neural network model to predict, and generate single forecast resource change data in a current time period corresponding to each currency type. The single forecast resource change data refers to forecast resource change data corresponding to each transaction.

S560, calculating based on the single forecast resource change data in the current time period to obtain the accumulated forecast resource change data in the current time period.

Alternatively, the server 104 may calculate based on the single forecast resource variation data in the current time period, to obtain the accumulated forecast resource variation data in the current time period. The calculation method of the single forecast resource change data can include, but is not limited to, summation, weighted summation and the like. Of course, the calculation mode of the single forecast resource change data is not limited in this embodiment. The cumulative forecast resource change data refers to forecast resource change data obtained by calculating each transaction.

In this embodiment, the historical transaction data in the preset time period is obtained according to the preset dimension, so that the historical transaction data in the preset time period corresponding to each currency type, each transaction amount and each clearing financial institution identifier can be obtained more accurately. And then, according to the preset dimension, inputting the historical transaction data in the preset time period into a preset neural network model for prediction, and generating single forecast resource change data in the current time period. Because the preset neural network model is the neural network model with model training completed, the prediction result of the preset neural network model is accurate. Therefore, based on a more accurate preset neural network model, more accurate single forecast resource change data in the current time period can be generated. Therefore, the calculation is performed based on the accurate single forecast resource change data in the current time period, and the accurate accumulated forecast resource change data in the current time period can be obtained.

In the above embodiment, the method involves inputting the historical transaction data in the preset time period into the preset neural network model according to the preset dimension to predict, and generating the single forecast resource change data in the current time period, and the specific method for model training is described below. In one embodiment, as shown in fig. 6, the resource change data early warning method further includes:

S620, acquiring historical transaction data in a historical time period and historical resource change data in the historical time period according to a preset dimension.

Alternatively, the server 104 may obtain, from the terminal 102 or the preset database, historical transaction data in a historical time period and historical resource change data in the historical time period according to a preset dimension. The predetermined dimension may include, but is not limited to, at least one of a coin type, a transaction amount, and a clearing financial institution identification. The historical transaction data in the historical time period refers to transaction data obtained in the process of conducting transactions in the historical time period, and the historical transaction data is transaction data in which transactions have been completed. The historical resource change data in the historical time period refers to real resource change data in the historical time period, and the historical resource change data is used for representing real available balances in the historical time period.

And S640, inputting the historical transaction data in the historical time period into the initial neural network model for prediction, and generating predicted resource change data in the historical time period.

Alternatively, the server 104 may construct an initial neural network model using an existing neural network model. Exemplary initial neural network models include, but are not limited to, dense neural network models, convolutional neural network models, and recurrent neural network models, among others. Thus, the server 104 may input the historical transaction data in the historical time period as input data of the initial neural network model, and predict the input data in the initial neural network model to generate predicted resource change data in the historical time period. The predicted resource change data in the historical time period refers to predicted resource change data in the historical time period, and the historical resource change data is used for representing the predicted available balance in the historical time period.

And S660, training the initial neural network model according to the predicted resource change data and the historical resource change data to generate a preset neural network model.

Alternatively, the server 104 may calculate the value of the loss function according to the predicted resource change data and the historical resource change data. According to the calculated value of the loss function, the server can adjust the initial model parameters of the initial neural network model, so as to obtain intermediate model parameters and an intermediate neural network model corresponding to the intermediate model parameters. And inputting the historical transaction data in the historical time period into the intermediate neural network model to obtain the predicted resource change data in the new historical time period. And calculating the value of the new loss function again according to the historical resource change data and the new predicted resource change data until the value of the new loss function reaches the minimum value, and taking the intermediate model parameter corresponding to the value of the loss function at the moment as the target model parameter. Updating initial model parameters of the initial neural network model based on the target model parameters to generate a preset neural network model.

In this embodiment, historical transaction data in a historical time period and historical resource change data in the historical time period are obtained according to a preset dimension; inputting the historical transaction data in the historical time period into an initial neural network model for prediction, and generating predicted resource change data in the historical time period; training the initial neural network model according to the predicted resource change data and the historical resource change data to generate a preset neural network model. The trained preset neural network model is obtained by using historical transaction data in a historical time period and historical resource change data in the historical time period through multiple rounds of training, so that the preset neural network model has higher accuracy.

In order to facilitate understanding of those skilled in the art, the method for early warning resource change data provided by the present application is described in detail below, and as shown in fig. 7, the method may include:

s702, acquiring historical transaction data in a historical time period and historical resource change data in the historical time period according to a preset dimension;

s704, inputting historical transaction data in a historical time period into an initial neural network model for prediction, and generating predicted resource change data in the historical time period;

s706, training the initial neural network model according to the predicted resource change data and the historical resource change data to generate a preset neural network model;

s708, acquiring historical transaction data in a preset time period according to a preset dimension; the preset dimension comprises at least one of currency type, transaction amount and clearing financial institution identification;

s710, according to the preset dimension, inputting historical transaction data in a preset time period into a preset neural network model for prediction, and generating single forecast resource change data in the current time period;

s712, calculating based on single forecast resource change data in the current time period to obtain accumulated forecast resource change data in the current time period;

S714, acquiring real-time transaction data of the current time period and forecast resource change data of the current time period; the forecast resource change data comprises single forecast resource change data and accumulated forecast resource change data, and the real-time transaction data comprises single real-time transaction data and accumulated real-time transaction data;

s716, comparing the single forecast resource change data in the current time period with the single real-time transaction data in the current time period to generate a first comparison result;

s718, comparing the accumulated forecast resource change data in the current time period with the accumulated real-time transaction data in the current time period to generate a second comparison result;

s720, judging whether the first comparison result and the second comparison result meet preset conditions; the preset condition comprises that the first comparison result is that the single forecast resource change data in the current time period is smaller than the single real-time transaction data in the current time period, and/or the second comparison result is that the accumulated forecast resource change data in the current time period is smaller than the accumulated real-time transaction data in the current time period;

s722, if the first comparison result and the second comparison result meet the preset conditions, monitoring the real-time resource change data in the current time period to generate a first resource change data monitoring result; the first resource change data monitoring result is used for representing that the resource change data of the current time period is smaller than a preset resource change data threshold value;

S724, if the first comparison result and the second comparison result do not meet the preset conditions, monitoring the real-time resource change data in the current time period to generate a second resource change data monitoring result; the second resource change data monitoring result is used for representing that the resource change data of the current time period is larger than or equal to a preset resource change data threshold value;

s726, early warning is carried out based on the resource change data monitoring result of the current time period, and a resource change data early warning result is generated.

In the resource change data early warning method, the forecast resource change data of the current time period can be obtained in advance, and the real-time transaction data of the current time period can be obtained in real time, so that the forecast resource change data can be obtained in real time according to the real-time transaction data obtained in real time. And carrying out real-time monitoring on the real-time resource change data in the current time period to generate a real-time monitoring result of the resource change data in the current time period. And then, carrying out real-time early warning based on the real-time monitoring result of the resource change data in the current time period, and generating a real-time early warning result of the resource change data. Therefore, the application can intelligently monitor the resource change data of the current time period in real time, and can perform real-time early warning on the real-time resource change data of the current time period under the condition of insufficient resource change data, and can win the time for business personnel to take corresponding measures, thereby avoiding the risk that cross-border funds clearing cannot be completed on time due to insufficient resource change data and reducing the funds loss and credit influence of banks and third party payment institutions. In addition, the application can intelligently process the statistical transaction data, thereby saving the labor cost of the artificial statistical data. In addition, when the resource change data is monitored in real time, the application can monitor from two dimensions of single data and accumulated data, so that the real-time monitoring can be more comprehensively and accurately performed.

It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a resource change data early warning device for realizing the related resource change data early warning method. The implementation scheme of the device for solving the problem is similar to that described in the above method, so the specific limitation in the embodiments of the one or more resource change data early-warning devices provided below may refer to the limitation of the resource change data early-warning method hereinabove, and will not be repeated herein.

In one embodiment, as shown in fig. 8, there is provided a resource change data pre-warning device 800, including: acquisition module 820, monitoring module 840 and pre-warning module 860, wherein:

the acquiring module 820 is configured to acquire real-time transaction data of a current time period and forecast resource variation data of the current time period.

The monitoring module 840 is configured to monitor the real-time resource variation data in the current time period according to the real-time transaction data and the forecast resource variation data, and generate a resource variation data monitoring result in the current time period.

And the early warning module 860 is used for carrying out early warning based on the resource change data monitoring result in the current time period and generating a resource change data early warning result.

In one embodiment, the forecast resource variation data includes a single batch of forecast resource variation data and cumulative forecast resource variation data, and the real-time transaction data includes a single batch of real-time transaction data and cumulative real-time transaction data; the monitoring module 840 includes:

the first comparison unit is used for comparing the single forecast resource change data in the current time period with the single real-time transaction data in the current time period to generate a first comparison result;

the second comparison unit is used for comparing the accumulated forecast resource change data in the current time period with the accumulated real-time transaction data in the current time period to generate a second comparison result;

The monitoring unit is used for monitoring the real-time resource change data in the current time period according to the first comparison result and the second comparison result and generating a resource change data monitoring result in the current time period.

In one embodiment, the monitoring unit comprises:

the judging subunit is used for judging whether the first comparison result and the second comparison result meet the preset condition or not; the preset condition comprises that the first comparison result is that the single forecast resource change data in the current time period is smaller than the single real-time transaction data in the current time period, and/or the second comparison result is that the accumulated forecast resource change data in the current time period is smaller than the accumulated real-time transaction data in the current time period;

the first resource change data monitoring result generation subunit is used for monitoring the real-time resource change data in the current time period under the condition that the first comparison result and the second comparison result meet the preset condition to generate a first resource change data monitoring result; the first resource change data monitoring result is used for representing that the resource change data of the current time period is smaller than a preset resource change data threshold value;

the second resource change data monitoring result generating subunit is used for monitoring the real-time resource change data in the current time period to generate a second resource change data monitoring result under the condition that the first comparison result and the second comparison result do not meet the preset condition; and the second resource change data monitoring result is used for representing that the resource change data of the current time period is larger than or equal to a preset resource change data threshold value.

In one embodiment, the resource change data pre-warning device 800 further includes:

the prediction module is used for predicting forecast resource change data in the current time period according to the historical transaction data in the preset time period and the preset neural network model; the current time period is a time period after a preset time period.

In one embodiment, the prediction module includes:

the historical transaction data acquisition unit is used for acquiring historical transaction data in a preset time period according to a preset dimension; the preset dimension comprises at least one of currency type, transaction amount and clearing financial institution identification;

the prediction unit is used for inputting historical transaction data in a preset time period into a preset neural network model for prediction according to a preset dimension, and generating single forecast resource change data in a current time period;

the accumulated forecast resource change data generation unit is used for calculating based on the single forecast resource change data in the current time period to obtain the accumulated forecast resource change data in the current time period.

the historical resource change data acquisition module is used for acquiring historical transaction data in a historical time period and historical resource change data in the historical time period according to a preset dimension;

The prediction resource change data generation module is used for inputting the historical transaction data in the historical time period into the initial neural network model for prediction, and generating the prediction resource change data in the historical time period;

the preset neural network model generation module is used for training the initial neural network model according to the predicted resource change data and the historical resource change data to generate a preset neural network model.

All or part of the modules in the resource change data early warning device can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 9. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing the resource change data early warning data. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor is used for realizing a resource change data early warning method.

It will be appreciated by persons skilled in the art that the architecture shown in fig. 9 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting as to the computer device to which the present inventive arrangements are applicable, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:

monitoring the real-time resource change data in the current time period according to the real-time transaction data and the forecast resource change data, and generating a resource change data monitoring result in the current time period;

In one embodiment, the forecast resource variation data includes a single batch of forecast resource variation data and cumulative forecast resource variation data, and the real-time transaction data includes a single batch of real-time transaction data and cumulative real-time transaction data; monitoring the real-time resource change data of the current time period according to the real-time transaction data and the forecast resource change data to generate a resource change data monitoring result of the current time period, wherein the processor further realizes the following steps when executing the computer program:

comparing the accumulated forecast resource change data in the current time period with the accumulated real-time transaction data in the current time period to generate a second comparison result;

In one embodiment, according to the first comparison result and the second comparison result, monitoring the real-time resource change data in the current time period to generate a resource change data monitoring result in the current time period, and when the processor executes the computer program, the following steps are further implemented:

judging whether the first comparison result and the second comparison result meet preset conditions or not; the preset condition comprises that the first comparison result is that the single forecast resource change data in the current time period is smaller than the single real-time transaction data in the current time period, and/or the second comparison result is that the accumulated forecast resource change data in the current time period is smaller than the accumulated real-time transaction data in the current time period;

In one embodiment, the processor when executing the computer program further performs the steps of:

In one embodiment, the prediction resource variation data in the current time period is predicted according to the historical transaction data in the preset time period and the preset neural network model, and the following steps are further implemented when the processor executes the computer program:

according to the preset dimension, historical transaction data in a preset time period are input into a preset neural network model for prediction, and single forecast resource change data in the current time period are generated;

acquiring historical transaction data in a historical time period and historical resource change data in the historical time period according to a preset dimension;

training the initial neural network model according to the predicted resource change data and the historical resource change data to generate a preset neural network model.

In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:

In one embodiment, the forecast resource variation data includes a single batch of forecast resource variation data and cumulative forecast resource variation data, and the real-time transaction data includes a single batch of real-time transaction data and cumulative real-time transaction data; monitoring the real-time resource change data of the current time period according to the real-time transaction data and the forecast resource change data to generate a resource change data monitoring result of the current time period, wherein the computer program further realizes the following steps when being executed by the processor:

In one embodiment, the monitoring of the real-time resource variation data in the current time period according to the first comparison result and the second comparison result generates a resource variation data monitoring result in the current time period, and the computer program when executed by the processor further realizes the following steps:

In one embodiment, the computer program when executed by the processor further performs the steps of:

In one embodiment, the prediction resource variation data in the current time period is predicted according to the historical transaction data in the preset time period and the preset neural network model, and the computer program when executed by the processor further realizes the following steps:

In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:

It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region.

Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims

1. The resource change data early warning method is characterized by comprising the following steps:

2. The method of claim 1, wherein the forecast resource variation data comprises a single batch of forecast resource variation data and cumulative forecast resource variation data, and the real-time transaction data comprises a single batch of real-time transaction data and cumulative real-time transaction data; the monitoring of the real-time resource variation data of the current time period according to the real-time transaction data and the forecast resource variation data generates a resource variation data monitoring result of the current time period, including:

3. The method of claim 2, wherein the monitoring the real-time resource variation data in the current time period according to the first comparison result and the second comparison result, and generating the resource variation data monitoring result in the current time period, includes:

4. A method according to any one of claims 1-3, characterized in that the method further comprises:

5. The method of claim 4, wherein predicting the forecast resource variation data for the current time period based on historical transaction data for the preset time period and a preset neural network model, comprises:

6. The method of claim 5, wherein the method further comprises:

7. A resource variation data pre-warning device, the device comprising:

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.

9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.