CN112669154B

CN112669154B - Foreign currency exchange business development prediction implementation method and device and computer equipment

Info

Publication number: CN112669154B
Application number: CN202011626428.9A
Authority: CN
Inventors: 黄文强; 胡传杰; 胡玮; 黄雅楠; 徐晨敏
Original assignee: Bank of China Ltd
Current assignee: Bank of China Ltd
Priority date: 2020-12-31
Filing date: 2020-12-31
Publication date: 2024-03-29
Anticipated expiration: 2040-12-31
Also published as: CN112669154A

Abstract

Before a target financial institution issues a foreign currency exchange service, passenger flow of the target financial institution, first service handling data of a first-level customer and waiting prediction data of exchange consultation information of the foreign currency exchange service can be obtained through the computer equipment, after the characteristics of the waiting prediction data are extracted to obtain corresponding data characteristics, the data characteristics can be analyzed based on service issuing conditions corresponding to the target financial institution to determine whether the target financial institution is suitable for issuing a prediction result of the foreign currency exchange service, the problem that the target financial institution does not directly issue the foreign currency exchange service without investigation and analysis, and the problem that the clients of the target financial institution handling the financial institution are very few and service loss occurs easily is avoided.

Description

Foreign currency exchange business development prediction implementation method and device and computer equipment

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a method and an apparatus for implementing foreign currency exchange service development prediction, and a computer device.

Background

To facilitate customer funds, financial institutions (e.g., banking sites) are now typically exposed to a variety of transactions, such as foreign currency exchange transactions, which are typically currency beyond the present currency system. Foreign currency exchange is a counter service provided to individual customers, including buying a foreign currency, selling a foreign currency, and exchanging one foreign currency for another. For financial institutions, it is possible to make a profit by varying exchange rates between different currencies.

However, in practical applications, the cost of dispatching the foreign currency to the individual financial institutions is often relatively high, but the service fee charged by some financial institutions for the customer to transact the foreign currency exchange service is lower than the dispatching cost fee, so that the financial institutions can lose money when the foreign currency exchange service is offered.

Disclosure of Invention

In view of the above, in order to solve the above technical problems, the present application provides the following technical solutions:

in one aspect, the present application proposes a method for implementing foreign currency exchange business development prediction, where the method includes:

obtaining data to be predicted of a target financial institution, wherein the data to be predicted comprises passenger flow in a first duration, first business handling data of a first-level customer and exchange consultation information aiming at foreign currency exchange business;

Respectively extracting characteristics of the passenger flow volume, the first business handling data and the exchange consultation information to obtain corresponding data characteristics;

and analyzing the obtained data characteristics based on service issuing conditions corresponding to the target financial institutions to obtain a prediction result of whether the target financial institutions are suitable for issuing the foreign currency exchange service, wherein the service issuing conditions at least comprise service profit and loss conditions and service handling client conditions.

Optionally, the analyzing the obtained plurality of data features based on the service issuing conditions corresponding to the target financial institution to obtain a prediction result of whether the target financial institution is suitable for issuing the foreign currency exchange service, includes:

inputting the obtained data characteristics into a foreign currency exchange business prediction model to obtain a prediction result of whether the target financial institution is suitable for issuing the foreign currency exchange business;

the foreign currency exchange business prediction model is obtained by training sample data features according to business operation conditions corresponding to the target financial institutions based on a neural network algorithm.

Optionally, the inputting the obtained plurality of data features into a foreign currency conversion service prediction model to obtain a prediction result of whether the target financial institution is suitable for issuing the foreign currency conversion service, including:

Inputting the obtained data characteristics into a foreign currency exchange business prediction model to obtain target prediction scores which are suitable for issuing the foreign currency exchange business for the target financial institutions;

obtaining a score threshold corresponding to the region where the target financial institution is located;

detecting whether the target prediction score is larger than the score threshold value or not to obtain a corresponding detection result;

and generating prediction prompt information corresponding to the detection result, and sending the prediction prompt information to a preset terminal associated with the target financial institution.

Optionally, the inputting the obtained plurality of data features into a foreign currency conversion service prediction model to obtain a prediction result of whether the target financial institution is suitable for issuing the foreign currency conversion service, and further includes:

obtaining a prediction report matched with the detection result, wherein the prediction report comprises the influence weight of each piece of data to be predicted on the detection result;

wherein, when the detection result is that the target prediction score is less than or equal to the score threshold, the prediction report further includes a business establishment condition that the data feature of the target financial institution is not satisfied.

Optionally, the inputting the obtained plurality of data features into a foreign currency conversion service prediction model to obtain a target prediction score suitable for issuing the foreign currency conversion service for the target financial institution, including:

Inputting the obtained data features into a foreign currency exchange business prediction model to obtain feature prediction scores of the data features for the target financial institutions suitable for issuing the foreign currency exchange business;

and weighting the obtained characteristic prediction scores according to the respective prediction weights of the data characteristics to obtain target prediction scores of the target financial institutions suitable for issuing the foreign currency exchange business.

Optionally, the training process of the foreign currency exchange business prediction model includes:

acquiring sample institution identification information of a sample financial institution which has initiated the foreign currency exchange business;

obtaining data to be screened associated with the sample mechanism identification information, wherein the data to be screened comprises sample passenger flow volume, first sample identity attribute information, second sample identity attribute information, foreign currency profit information and foreign currency scheduling cost information which are generated in a first time period, and the first sample identity attribute information refers to identity attribute information of a first sample customer applying for handling any service in the sample financial institution in the first time period; the second sample identity attribute information refers to identity attribute information of a second sample client applying for transacting the foreign currency exchange business at the sample financial institution within the first time period;

Analyzing each piece of data to be screened, and screening sample data meeting training conditions, wherein the training conditions are that the influence value of the change of the corresponding screening data on foreign currency exchange business issued by the sample financial institution is larger than an influence threshold value;

respectively extracting the characteristics of the screened sample data to obtain corresponding sample characteristic vectors;

inputting the obtained multiple sample feature vectors into a preset neural network for learning until constraint conditions are met, and determining a foreign currency exchange business prediction model according to a neural network structure obtained through final learning;

the preset neural network comprises an error reverse propagation neural network based on a genetic algorithm.

Optionally, the acquiring process of the service initiation condition includes:

obtaining foreign currency transaction data of the area where the target financial institution is located, and transacting the average passenger flow of the foreign currency exchange business in the first duration in the financial institution where the foreign currency exchange business is initiated in the same-level area;

determining business earning and losing conditions and business handling client conditions for a financial institution to issue a foreign currency exchange business based on the foreign currency transaction data and the average passenger flow;

And determining the business establishment condition aiming at the target financial institution according to the business profit and loss conditions and the business handling client condition.

Optionally, the obtaining the data to be predicted of the target financial institution includes:

receiving a foreign currency exchange business prediction request sent by a business terminal of a target financial institution, wherein the foreign currency exchange business prediction request carries target institution identification information of the target financial institution;

and responding to the foreign currency exchange business prediction request, and inquiring data to be predicted associated with the target institution identification information.

In yet another aspect, the present application proposes a foreign currency exchange business development prediction implementation apparatus, the apparatus including:

the system comprises a to-be-predicted data acquisition module, a target financial institution and a target financial institution, wherein the to-be-predicted data acquisition module is used for acquiring to-be-predicted data of a target financial institution, and the to-be-predicted data comprises passenger flow in a first duration, first business handling data of a first-level customer and exchange consultation information aiming at foreign currency exchange business;

the feature extraction module is used for respectively extracting features of the passenger flow volume, the first business handling data and the exchange consultation information to obtain corresponding data features;

and the analysis and prediction module is used for analyzing the obtained data characteristics based on the service issuing conditions corresponding to the target financial institution to obtain a prediction result of whether the target financial institution is suitable for issuing the foreign currency exchange service, wherein the service issuing conditions at least comprise service profit and loss conditions and service handling client conditions.

In yet another aspect, the present application proposes a computer device comprising: at least one communication interface, at least one memory, and at least one processor, wherein:

the memory is used for storing a program for realizing the foreign currency exchange business development prediction realization method;

the processor is used for loading and executing the program stored in the memory to realize the steps of the foreign currency exchange business development prediction implementation method.

Therefore, before the target financial institution initiates the foreign currency exchange business, the method, the device and the computer equipment for implementing the foreign currency exchange business initiation prediction can acquire the passenger flow of the target financial institution, the first business transaction data of the first-level customers and the exchange consultation information waiting prediction data of the foreign currency exchange business through the computer equipment, after the characteristics of the data to be predicted are extracted, the data characteristics can be analyzed based on the business initiation conditions corresponding to the target financial institution to determine whether the target financial institution is suitable for initiating the prediction result of the foreign currency exchange business, so that the problem that the target financial institution does not directly initiate the foreign currency exchange business in investigation and analysis, and the problem that the customers transacting the financial institution with the target financial institution are very few in business loss easily occurs is avoided.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings may be obtained according to the provided drawings without inventive effort to a person skilled in the art.

FIG. 1 is a flow diagram illustrating an alternative example of a foreign currency conversion service development prediction implementation method proposed by the present application;

FIG. 2 is a flow chart of yet another alternative example of a foreign currency conversion service development prediction implementation method proposed by the present application;

FIG. 3 is a flow chart illustrating yet another alternative example of a foreign currency conversion service development prediction implementation method proposed by the present application;

FIG. 4 is a flow chart of yet another alternative example of a foreign currency conversion service development prediction implementation method proposed by the present application;

FIG. 5 is a schematic diagram showing an alternative example of a foreign currency exchange business development prediction implementation device according to the present application;

fig. 6 shows a schematic hardware architecture of an alternative example of a computer device suitable for implementing the foreign currency exchange business development prediction method and apparatus proposed in the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

For convenience of description, only a portion related to the present invention is shown in the drawings. Embodiments and features of embodiments in this application may be combined with each other without conflict.

It should be appreciated that "system," "apparatus," "unit" and/or "module" as used in this application is one method for distinguishing between different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the word can be replaced by other expressions.

As used in this application and in the claims, the terms "a," "an," "the," and/or "the" are not specific to the singular, but may include the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus. The inclusion of an element defined by the phrase "comprising one … …" does not exclude the presence of additional identical elements in a process, method, article, or apparatus that comprises an element.

Wherein, in the description of the embodiments of the present application, "/" means or is meant unless otherwise indicated, for example, a/B may represent a or B; "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In addition, in the description of the embodiments of the present application, "plurality" means two or more than two. The following terms "first", "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature.

Additionally, flowcharts are used in this application to describe the operations performed by systems according to embodiments of the present application. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.

Referring to fig. 1, a flowchart of an alternative example of a foreign currency exchange service development prediction implementation method provided in the present application may be applied to a computer device, where the computer device may be a server or a service terminal with a certain data processing capability, and the product form of the computer device is not limited in the embodiment of the present application. As shown in fig. 1, the method may include:

step S11, obtaining data to be predicted of a target financial institution;

in order to avoid the problems that the financial institution naturally opens the foreign currency exchange business, the number of clients for the financial institution to transact the foreign currency exchange business is small, the service fee for the transacted business is far lower than the dispatching cost fee, and the defect phenomenon can occur when the financial institution opens the foreign currency exchange business. The embodiment of the application provides that before a financial institution opens a foreign currency exchange business, whether the financial institution is suitable for opening the financial institution is predicted.

Specifically, any financial institution desiring to issue a foreign currency exchange service may be referred to as a target financial institution, and the target financial institution may initiate a foreign currency exchange service prediction request to the computer device through the service terminal, so that the computer device queries each piece of data to be predicted associated with the target institution identification information, i.e. relevant data for predicting whether the target financial institution is suitable for issuing a foreign currency exchange service, according to target institution identification information, such as a unique identifier, such as an institution code, of the target financial institution carried by the request.

The obtained data to be predicted may include contents such as passenger flow in a first time period (for example, one day, one week, etc., the specific value of the first time period is not limited in the present application), first business handling data (for example, total business handling times, etc.) of a first-level customer, and exchange consultation information (for example, consultation times) of a foreign currency exchange business, etc., and the content included in the data to be predicted is not limited in the present application, and may be determined according to circumstances. The first-level clients may be important clients such as VIP clients of the target financial institutions, and the level division manner of the target financial institutions will not be described in detail in the present application.

Step S12, respectively extracting characteristics of passenger flow volume, first business handling data and exchange consultation information contained in the data to be predicted to obtain corresponding data characteristics;

in practical application, for the data types and the representation modes of different types of data to be predicted, even unquantized data content, for facilitating subsequent processing, feature extraction can be performed on each acquired data to be predicted to obtain corresponding feature values, and the specific feature extraction method is not limited in the application, and feature extraction can be realized by using a machine learning algorithm such as a neural network algorithm to obtain data features composed of binary numbers, but is not limited to the data features, and can be determined according to conditions.

In some embodiments, the data features obtained after the feature extraction may be digitized features obtained by feature extraction of corresponding data to be predicted, and then the corresponding feature vectors may be obtained by normalization processing; or directly extracting the characteristics of each piece of data to be predicted to obtain a corresponding characteristic vector, that is, the data characteristics can be the characteristic vector or can be characteristic parameters capable of indicating the corresponding data to be predicted, and the content of the data characteristics is not limited in the application.

And step S13, analyzing the obtained data characteristics based on the business issuing conditions corresponding to the target financial institutions to obtain a prediction result of whether the target financial institutions are suitable for issuing foreign currency exchange business.

In this embodiment of the present application, the service issuing conditions may include at least a service profit and loss condition and a service handling client condition, that is, in the case of evaluating whether a financial institution is suitable for issuing a foreign currency exchange service, it is necessary to consider not only whether the financial institution issues a foreign currency exchange service to be able to profit, but also information such as a passenger flow volume that may possibly apply to the financial institution for handling a foreign currency exchange service, and of course, when evaluating whether the financial institution is suitable for issuing a foreign currency exchange service, the application is not limited to the two service issuing conditions that need to be considered.

In practical applications, the business development conditions may be comprehensively determined by combining the information such as the scale of the target financial institution, the economic development condition of the area where the target financial institution is located, and the regulations, so that the corresponding business development conditions may be different for different financial institutions, or there may be a plurality of financial institutions with the same business development conditions, and the content of the business development conditions and the determination method thereof corresponding to each financial institution are not limited as the case may be.

After determining the content of the service issuing condition for the target financial institution in the above manner, the obtained multiple aspects of data features of the target financial institution may be analyzed according to the content to determine whether the current operation condition of each aspect of the target financial institution meets the service issuing condition, for example, how much the matching degree with the service issuing condition reaches, so as to obtain a prediction result of whether the target financial institution is suitable for issuing a foreign currency exchange service. If the matching degree reaches a certain threshold, the obtained prediction result can comprise parameters such as matching conditions of the target financial institution suitable for issuing foreign currency exchange business and the like for each business issuing condition according to requirements.

Correspondingly, if the obtained matching degree does not reach the threshold, the obtained prediction result may include parameters such as a matching condition of the target financial institution unsuitable for issuing the foreign currency exchange service, and may further include parameters such as a matching condition of each service issuing condition according to needs, so that the target financial institution can obtain an improvement scheme for the current operation condition according to the obtained prediction result content under the condition that the target financial institution wishes to be able to continue issuing the foreign currency exchange service, so that the current operation condition can be more and more matched with the service issuing condition, and the specific implementation process is not described in detail in the application.

In summary, in this embodiment of the present application, before a target financial institution issues a foreign currency exchange service, the computer device may be used to obtain, for example, a passenger flow volume of the target financial institution in a first period, first service handling data of a first-level customer, and waiting prediction data for exchange consultation information of the foreign currency exchange service, and after extracting features of the waiting prediction data to obtain corresponding data features, the data features may be analyzed based on service issuing conditions corresponding to the target financial institution, so as to determine whether the target financial institution is suitable for issuing a prediction result of the foreign currency exchange service, thereby avoiding that the target financial institution does not directly issue the foreign currency exchange service without investigation and analysis, so that very few customers handling the financial institution by the target financial institution easily occur, and a service loss problem occurs.

Referring to fig. 2, which is a schematic flow chart of yet another alternative example of the foreign currency exchange service operation prediction implementation method proposed in the present application, this embodiment may be an alternative refinement implementation manner of the foreign currency exchange service operation prediction implementation method described in the foregoing embodiment, and as shown in fig. 2, the method may include:

step S21, obtaining data to be predicted of a target financial institution;

step S22, respectively extracting characteristics of passenger flow volume, first business handling data and exchange consultation information contained in the data to be predicted to obtain corresponding data characteristics;

regarding the implementation process of step S21 and step S22, reference may be made to the descriptions of the corresponding parts of the above embodiments, which are not repeated in this embodiment.

Step S23, inputting the obtained multiple data characteristics into a foreign currency exchange business prediction model to obtain target prediction scores suitable for issuing foreign currency exchange business for target financial institutions;

therefore, in the embodiment of the present application, the sample data features may be trained according to the service opening conditions corresponding to the target financial institution based on the neural network algorithm, so as to obtain the foreign currency conversion service prediction model, so that in practical application, before any financial institution who does not open the foreign currency conversion service wants to open the foreign currency conversion service, the foreign currency conversion service prediction model obtained by training in advance may be utilized to continuously process the multiple data features of the input model, so as to obtain the prediction result of whether the input model is suitable for opening the foreign currency conversion service, but the implementation method of the pretraining process of the foreign currency conversion service prediction model is not limited in the present application.

In some embodiments presented herein, as shown in fig. 3, the training process of the foreign currency conversion business prediction model described above may include, but is not limited to, the following steps:

step S31, sample institution identification information of a sample financial institution which has issued a foreign currency exchange business is obtained;

in practical application, the relevant operation information of the sample financial institutions which have already issued the foreign currency exchange business at present can be collected to form sample data for training the foreign currency exchange business prediction model, and in general, in order to improve the training reliability of the foreign currency exchange business prediction model and the accuracy of the prediction result thereof, sample data of a plurality of sample financial institutions can be obtained, and the required foreign currency exchange business prediction model can be obtained through repeated training.

Therefore, the embodiment of the application can firstly determine the sample financial institutions to which the sample data to be acquired belong, for example, determine the sample financial institutions according to the operation scale of the target financial institutions, the economic development level of the region and other aspects of information; of course, the application can also randomly select a sample financial institution from financial institutions which have issued foreign currency exchange business to realize training of a prediction model, and the application does not limit the determination mode of the sample financial institution, and can be determined according to circumstances.

After determining the required sample financial institution, in order to conveniently obtain various business information of the sample financial institution, the unique identification information of the sample financial institution can be determined first and recorded as sample institution identification information for distinguishing and identifying different financial institutions. The sample institution identification information can be identification information with unique characteristics such as institution codes, nano tax numbers, credit codes and the like, and the specific content of the sample institution identification information is not limited.

Step S32, obtaining data to be screened associated with sample mechanism identification information;

in this embodiment of the present application, the acquired data to be screened may include, but is not limited to, the content of the data to be screened listed in this embodiment, where appropriate, the sample passenger flow volume generated during the first time period (such as one day, one week, etc.), the first sample identity attribute information, the second sample identity attribute information, the foreign currency profit information, and the foreign currency scheduling cost information (such as the cost required by the sample financial institution to dial the foreign currency from the customer's hand during each first time period).

The first identity attribute information may be identity attribute information of a first sample client applying for handling any business in the sample financial institution within the first duration, such as professional, academic, age, etc. information of the corresponding first sample client; the second sample identity attribute information may refer to identity attribute information of a second sample customer applying for handling a foreign currency exchange service at the sample financial institution within the first period, such as professional, academic, age, etc. information of the second sample customer, where the content included in the identity attribute information of the customer is not limited, and may be determined according to circumstances.

It will be appreciated that in the embodiment of the present application, for convenience of description, a customer applying for transacting any business at the sample financial institution is referred to as a first sample customer, and a customer applying for transacting foreign currency exchange business at the sample financial institution is referred to as a second sample customer, and it is possible that the first sample customer group includes a second sample customer group, and the present application is not limited to the specific first sample customer and second sample customer.

In some embodiments of the present application, since the passenger volumes of handling foreign currency exchange services in different quarters are often different in one year, in order to further improve the accuracy of the prediction model obtained by training, when the data to be screened is acquired, the data to be screened associated with the identification information of the sample institution may be specifically acquired from a corresponding period of time of the past adjacent year, and a specific acquisition process is not described in detail.

Step S33, analyzing each piece of data to be screened, and screening sample data meeting training conditions;

in practical application, for each data to be screened obtained above, there may be some data, which has little influence on whether the corresponding sample financial institution initiates the foreign currency exchange service, and almost negligible data, and such data is basically useless for training the foreign currency exchange service prediction model, so the application may determine the training condition of the sample data for constructing the prediction model in advance according to the data, such as changing the corresponding screening data, where the influence value on the foreign currency exchange service initiated by the sample financial institution is greater than the influence threshold (the specific value is not limited, and may be determined according to the situation), but is not limited to this content of the training condition.

And then, the computer equipment can analyze the acquired data to be screened according to the training conditions, reject useless data which does not meet the training conditions, screen out the data which meets the training conditions as sample data, specifically, can acquire the influence value of each data to be screened on foreign currency exchange business initiated by the corresponding sample financial institution based on the content of the training conditions described above, screen out the data with the influence value larger than the influence threshold as sample data, but the method is not limited to the screening mode, and the application does not limit the specific acquisition mode of the influence value.

Step S34, respectively extracting the characteristics of the screened sample data to obtain corresponding sample characteristic vectors;

with respect to the implementation procedure of step S34, reference may be made to, but not limited to, the description of the corresponding parts of step S12 above.

And S35, inputting the obtained multiple sample feature vectors into a preset neural network for learning until constraint conditions are met, and determining a foreign currency exchange business prediction model according to the neural network structure obtained through final learning.

In some embodiments presented herein, the predetermined neural network may include a genetic algorithm (Genetic Algorithm, GA) -based error back propagation (Backward Propagation, BP) neural network, but is not limited to this neural network structure, as the case may be. This application illustrates the model training process by way of example only.

Specifically, the BP neural network structure can be determined according to the number of features of the sample feature vector input into the preset neural network, so as to determine the number of network parameters to be optimized by the genetic algorithm, then, a three-layer BP neural network can be constructed according to the kolmogorov principle, any mapping from n dimension to m dimension can be completed, a hidden layer is configured, specifically, for the neural network, the number of features contained in the obtained sample feature vector can be used as the number of nodes of the input layer, the prediction result of predicting whether the financial institution is suitable for issuing foreign currency exchange service is used as the number of nodes of the output layer, and the hidden layer node number is determined by adopting a trial-and-error method, so that the GA-BP neural network structure is determined. In order to improve accuracy and training efficiency of the prediction model, the optimal individual output by the genetic algorithm can be used as an initial weight and a threshold value of the BP neural network, and then the sample feature vector is continuously trained and learned to obtain the required foreign currency exchange business prediction model.

Constraints in the training process for the foreign currency conversion business prediction model described above may include: the output result of the model obtained by training is converged or stable, and/or the accuracy rate of the prediction result of the test data is greater than an accurate threshold value, and the neural network model obtained by training can be considered to meet constraint conditions; otherwise, the sample data can be utilized to continuously adjust and learn the network parameters until the constraint condition is met, and the neural network structure obtained by the last learning is used for determining the foreign currency exchange business prediction model. The training implementation process of the prediction model is not described in detail herein, and is not limited to such model training implementation described in the embodiments of the present application.

After the foreign currency exchange business prediction model is trained in advance according to the mode, the foreign currency exchange business prediction model can be stored in the computer equipment, so that after the computer equipment obtains a plurality of data characteristics of each target financial institution, the data characteristics can be directly input into the foreign currency exchange business prediction model to obtain target prediction scores of the target financial institution suitable for issuing the foreign currency exchange business, and in general, the larger the obtained target prediction scores are, the larger the probability that the target financial institution is suitable for issuing the foreign currency exchange business is, namely the higher the matching degree of the data characteristics and business issuing conditions is.

Step S24, obtaining a score threshold corresponding to the area where the target financial institution is located;

step S25, detecting whether the target prediction score is larger than a score threshold value, and obtaining a corresponding detection result;

based on the description of the corresponding parts of the above embodiments, for financial institutions in different areas, since the economic development level, the regulation system, the demand level for foreign currency exchange business, and the like of the area where the financial institutions are located are often different, in order to improve the prediction accuracy, according to these reference factors listed in this embodiment, the present application may configure corresponding score thresholds for the financial institutions in different areas in advance, that is, determine the predicted score threshold for the financial institutions in the area suitable for opening foreign currency exchange business, but the specific value of the score threshold is not limited in this application.

Therefore, after obtaining the target predicted score of the target financial institution, the computer equipment can compare the target predicted score with a score threshold corresponding to the area where the target financial institution is located, and if the target predicted score is greater than the score threshold, the target financial institution can be considered to be suitable for opening foreign currency exchange business; conversely, if the target predicted score is less than the score threshold, the target financial institution may be deemed unsuitable for opening a foreign exchange transaction.

In some embodiments of the present application, the detection result in the above step S25 may include, but is not limited to, a determination result that the target prediction score is smaller or larger than the score threshold, and may further include, if necessary, a main data feature that causes the determination result, so as to know a main factor that causes the target financial institution to be unsuitable for issuing the foreign currency exchange service, and if necessary, also assist in improving the operation situation of the target financial institution, so that the target financial institution is more suitable for issuing the foreign currency exchange service, and so on. Therefore, the specific content included in the detection result is not limited, and may be any case.

Step S26, generating prediction prompt information corresponding to the detection result, and sending the prediction prompt information to a preset terminal associated with the target financial institution.

In combination with the above analysis, the early warning prompt information may include, but is not limited to, the content of the detection result listed above, that is, the application may use a message output prompt mode to notify the relevant responsible person of the prediction result, but the specific output mode and content of the prediction prompt information are not limited, and may be determined according to circumstances.

The preset terminal associated with the target financial institution can be a prediction function aiming at whether a foreign currency exchange service is initiated or not, and the electronic equipment is pre-bound, such as a mobile phone of a related manager, a service terminal deployed in the target financial institution and the like.

In some embodiments provided in the present application, when it is required to predict whether the target financial institution is suitable for issuing the foreign currency exchange service, a foreign currency exchange service prediction request may be sent to the computer device through a service terminal of the target financial institution, where the foreign currency exchange service prediction request may carry target institution identification information of the target financial institution, so that the computer device may query, by responding to the foreign currency exchange service prediction request, data to be predicted associated with the target institution identification information, and a specific query implementation process will not be described in detail.

Based on this, in a possible implementation manner, in the implementation process that the obtained plurality of data features are input into the foreign currency exchange service prediction model to obtain whether the target financial institution is suitable for issuing the prediction result of the foreign currency exchange service, a prediction report matched with the detection result may also be obtained, where the prediction report may include an influence weight of each piece of data to be predicted on the detection result, for example, a value smaller than 1, but the application does not limit the value of the influence weight of each piece of data to be predicted on the detection result, and may be determined according to circumstances.

In general, the larger the contribution of the data to be predicted to the corresponding detection result obtained by the prediction model, the larger the influence weight of the data to be predicted; on the contrary, the smaller the contribution of the data to be predicted to the corresponding detection result obtained by the prediction model, the smaller the influence weight of the data to be predicted, and the influence weight can be determined according to the output result of the prediction model, but the method is not limited thereto, and the determination mode of the influence weight corresponding to each data to be predicted is not limited.

In combination with the above analysis, when the detection result is that the target prediction score is less than or equal to the score threshold, the prediction report may further include a service issuing condition that the data feature of the target financial institution is not satisfied, that is, when the prediction target financial institution is not suitable for issuing the foreign currency exchange service, what aspect of the target financial institution is specific to the fact that the target financial institution is not suitable for issuing the foreign currency exchange service, such as a profit problem, a passenger flow problem, and the like, where the content of the prediction report and the output mode thereof are not limited, and may be determined according to circumstances.

In still other embodiments of the present application, the obtained plurality of data features are input into a foreign currency conversion service prediction model, and feature prediction scores of each data feature for a target financial institution suitable for issuing a foreign currency conversion service may also be obtained, and then, a weighting operation may be performed on the obtained plurality of feature prediction scores according to respective prediction weights of the plurality of data features, so as to obtain a target prediction score of the target financial institution suitable for issuing the foreign currency conversion service. In this case, the output detection result may include the target prediction score and each feature prediction score, and may specifically be included in the prediction report to be output, so that the user who views the prediction report can intuitively learn, through each feature prediction score, which data features are unfavorable for the target financial institution to conduct the foreign currency exchange service.

It should be noted that the implementation process of obtaining the target prediction score is not limited to the two implementations listed above, as to how to use the foreign currency exchange business prediction model.

In summary, in this embodiment of the present application, before a target financial institution issues a foreign currency exchange service, a pre-trained foreign currency exchange service prediction model is used to analyze a passenger flow rate of the target financial institution, first service handling data of a first-level customer, and exchange consultation information waiting prediction data for the foreign currency exchange service, so as to obtain a target predicted score of the target financial institution suitable for issuing the foreign currency exchange service, and then, a size relationship of a score threshold corresponding to an area where the target financial institution is located is detected, and prediction prompt information corresponding to the obtained detection result is generated and sent to a preset terminal associated with the target financial institution, so as to assist a responsible person of the target financial institution in determining whether to issue the foreign currency exchange service, thereby avoiding situations that the target financial institution issues the foreign currency exchange service directly, customers of the target financial institution handling the financial institution are very few, and service loss occurs easily.

Referring to fig. 4, for a schematic flow chart of a further alternative example of the foreign currency exchange service operation prediction implementation method proposed in the present application, this embodiment may be a further alternative refinement implementation manner of the foreign currency exchange service operation prediction implementation method described in the foregoing embodiment, and as shown in fig. 4, the method may include:

step S41, obtaining data to be predicted of a target financial institution;

step S42, respectively extracting characteristics of passenger flow volume, first business handling data and exchange consultation information contained in the data to be predicted to obtain corresponding data characteristics;

with respect to the specific implementation procedure of step S41 and step S42, reference may be made to, but not limited to, the description of the corresponding parts of the above embodiments, which are not repeated herein.

Step S43, obtaining foreign currency transaction data of the area where the target financial institution is located, and handling the average passenger flow of the foreign currency exchange business in the first time period in the financial institutions which conduct the foreign currency exchange business in the same-level area;

step S44, based on the foreign currency transaction data and the average passenger flow volume, determining service profit and loss conditions and service handling client conditions for the financial institution to issue the foreign currency exchange service;

in connection with the description of the corresponding parts of the above embodiments, the contents of the service development conditions for determining whether the service development conditions are suitable for developing foreign currency exchange services are often different for financial institutions in different regions, so as to ensure that the specified service development conditions can be suitable for economic development of the region where the target financial institution is located, and particularly, the development of related services of the foreign currency can be involved. The implementation can combine the foreign currency transaction data of the area where the target financial institution is located, refer to the financial institution which has already set up foreign currency exchange business under the same condition, apply for handling the average passenger flow of the foreign currency exchange business, etc. in the first duration, these can indicate the information of the foreign currency demand situation of the user of the area where the corresponding financial institution is located, to formulate the business opening condition of the target financial institution, but not limited to the foreign currency transaction data and average passenger flow listed above, and can also include the profit data of the foreign currency exchange business, etc. according to the need, and the application is not described in detail here.

In practical applications, for the requirements of different areas, a certain profit may be required to be suitable for issuing the foreign currency exchange service, or the profit situation may be less concerned, but the passenger flow or the requirements of the client for handling the foreign currency exchange service are mainly concerned, and of course, other conditions may be considered. Therefore, the present application can combine the obtained foreign currency transaction data to determine the business profit and loss conditions of the foreign currency exchange business for the financial institution, if the profit value reaches the profit threshold, the foreign currency exchange business can be properly issued; and determining service handling client conditions for issuing foreign currency exchange services for the financial institutions in combination with the average passenger flow, wherein the foreign currency exchange services can be appropriately issued only if the passenger flow for handling the foreign currency exchange services reaches a flow threshold, but the method is not limited to the determining mode of the service profit and loss conditions and the service handling client conditions.

Step S45, determining service opening conditions aiming at a target financial institution according to service profit and loss conditions and service handling client conditions;

in the embodiment of the present application, the service issuing conditions for the target financial institution may be directly formed by the determined service profit and loss conditions and the service handling client conditions, or may be determined by combining other conditions on the basis of the service issuing conditions, where the service issuing conditions may be determined as appropriate, and the application is not limited to this.

And step S46, analyzing the obtained data characteristics based on the business issuing conditions corresponding to the target financial institutions to obtain a prediction result of whether the target financial institutions are suitable for issuing foreign currency exchange business.

The specific implementation process of step S46 may refer to, but is not limited to, the description of the corresponding portion of the above embodiment, for example, the foreign currency exchange service prediction model is obtained by training in advance based on the service initiation condition corresponding to the target financial institution, and then the obtained plurality of data features are input into the foreign currency exchange service prediction model to obtain the prediction result of whether the target financial institution is suitable for initiating the foreign currency exchange service.

In sum, according to the financial institutions in different areas, the data to be predicted are subjected to feature extraction, after corresponding multiple data features are obtained, the multiple data features of the corresponding financial institutions can be analyzed based on corresponding business development conditions formulated for the different financial institutions, so that whether the financial institutions are suitable for developing the prediction result of foreign currency exchange business or not is accurately and reliably determined, the financial institutions which do not develop the foreign currency exchange business are assisted, whether the foreign currency exchange business is required to be developed or not is determined, the situation that the target financial institutions directly develop the foreign currency exchange business is avoided, customers who deal with the financial institutions from the target financial institutions are very few, business loss occurs and the like is easily caused.

Referring to fig. 5, for a schematic structural diagram of an alternative example of the foreign currency exchange service development prediction implementation apparatus proposed in the present application, the apparatus may be adapted to a computer device, as shown in fig. 5, and the apparatus may include:

the to-be-predicted data obtaining module 11 is configured to obtain to-be-predicted data of a target financial institution, where the to-be-predicted data includes a passenger flow volume within a first duration, first business handling data of a first-level customer, and exchange consultation information for a foreign currency exchange business;

in one possible implementation manner, the data obtaining module to be predicted 11 may include:

a foreign currency exchange business prediction request receiving unit, configured to receive a foreign currency exchange business prediction request sent by a business terminal of a target financial institution, where the foreign currency exchange business prediction request carries target institution identification information of the target financial institution;

and the to-be-predicted data query unit is used for responding to the foreign currency exchange business prediction request and querying to-be-predicted data associated with the target mechanism identification information.

The feature extraction module 12 is configured to perform feature extraction on the passenger flow volume, the first business transaction data, and the exchange consultation information, so as to obtain corresponding data features;

And the analysis and prediction module 13 is configured to analyze the obtained plurality of data features based on service issuing conditions corresponding to the target financial institution, so as to obtain a prediction result of whether the target financial institution is suitable for issuing the foreign currency exchange service, where the service issuing conditions at least include a service profit and loss condition and a service handling client condition.

In one possible implementation manner, in order to obtain the service initiation condition, the apparatus may further include:

the condition data acquisition module is used for acquiring foreign currency transaction data of the area where the target financial institution is located and handling average passenger flow of the foreign currency exchange business in the first duration in the financial institution where the foreign currency exchange business is issued in the same-level area;

a sub-condition determining module for determining a business earning condition and a business handling client condition for a financial institution to issue a foreign currency exchange business based on the foreign currency transaction data and the average passenger flow volume;

and the business operation condition determining module is used for determining the business operation condition aiming at the target financial institution according to the business profit and loss condition and the business handling client condition.

In some embodiments, the analysis prediction module 13 may include:

the model prediction unit is used for inputting the obtained data characteristics into a foreign currency conversion service prediction model to obtain a prediction result of whether the target financial institution is suitable for issuing the foreign currency conversion service;

In one possible implementation, the model prediction unit may include

The target prediction score obtaining unit is used for inputting the obtained data characteristics into a foreign currency conversion service prediction model to obtain target prediction scores which are suitable for issuing the foreign currency conversion service for the target financial institutions;

alternatively, the target prediction score obtaining unit may include:

the feature prediction score obtaining subunit is used for inputting the obtained data features into a foreign currency exchange business prediction model to obtain feature prediction scores of the data features, which are suitable for the target financial institution to conduct the foreign currency exchange business;

and the weighting operation subunit is used for carrying out weighting operation on the obtained characteristic prediction scores according to the respective prediction weights of the data characteristics to obtain the target prediction score of the foreign currency exchange business, which is suitable for the target financial institution.

The score threshold value acquisition unit is used for acquiring a score threshold value corresponding to the area where the target financial institution is located;

the detection unit is used for detecting whether the target prediction score is larger than the score threshold value or not to obtain a corresponding detection result;

and the prediction prompt information generation unit is used for generating prediction prompt information corresponding to the detection result and sending the prediction prompt information to a preset terminal associated with the target financial institution.

In yet another possible implementation manner, the model prediction unit may further include:

a prediction report obtaining unit, configured to obtain a prediction report that matches the detection result, where the prediction report includes an influence weight of each piece of data to be predicted on the detection result;

In still other embodiments of the present application, in order to implement the training of the foreign currency exchange business prediction model, the foreign currency exchange business development prediction implementation device provided in the present application may further include:

A sample institution identification information acquisition module for acquiring sample institution identification information of a sample financial institution that has initiated the foreign currency conversion service;

the data to be screened obtaining module is used for obtaining data to be screened associated with the sample mechanism identification information;

the to-be-screened data comprises sample passenger flow, first sample identity attribute information, second sample identity attribute information, foreign currency profit information and foreign currency scheduling cost information which are generated in a first time period, wherein the first sample identity attribute information refers to identity attribute information of a first sample client which applies for transacting any business in the sample financial institution in the first time period; the second sample identity attribute information refers to identity attribute information of a second sample client applying for transacting the foreign currency exchange business at the sample financial institution within the first time period;

the sample data screening module is used for analyzing each piece of data to be screened and screening sample data meeting training conditions, wherein the training conditions are that the influence value of the change of the corresponding screening data on foreign currency exchange business issued by the sample financial institution is larger than an influence threshold value;

The sample feature vector obtaining module is used for respectively carrying out feature extraction on the screened sample data to obtain corresponding sample feature vectors;

the model training module is used for inputting the obtained multiple sample feature vectors into a preset neural network for learning until constraint conditions are met, and determining a foreign currency exchange business prediction model according to the neural network structure obtained by the last learning;

It should be noted that, regarding the various modules, units, and the like in the foregoing embodiments of the apparatus, the various modules and units may be stored as program modules in a memory, and the processor executes the program modules stored in the memory to implement corresponding functions, and regarding the functions implemented by each program module and the combination thereof, and the achieved technical effects, reference may be made to descriptions of corresponding parts of the foregoing method embodiments, which are not repeated herein.

The present application further provides a readable storage medium, on which a program is stored, where the program, when executed by a processor, implements each step of the method for implementing the foreign currency exchange service development prediction, and a specific implementation process may refer to descriptions of corresponding parts of the foregoing method embodiment, which is not repeated in this embodiment.

Referring to fig. 6, a schematic hardware structure of a computer device suitable for implementing the foreign currency exchange service development prediction method and apparatus provided in the present application is shown, where the computer device may be a service terminal or a server with a certain data processing capability. The server may be an independent physical server, may be a service cluster integrated by a plurality of physical servers, or may be a cloud server supporting cloud computing capability, where the service device may implement communication with a service terminal or other devices through a wired or wireless network, so as to meet actual data interaction requirements, and specific implementation may be optional.

The service terminal may be an electronic device deployed in a service processing system of a target financial institution for a worker to use to transact a service as a customer, or may be an electronic device capable of implementing internal management of the target financial institution, such as a smart phone, a tablet computer, a Personal Computer (PC), a netbook, a personal digital assistant (personal digital assistant, PDA), a desktop computer, etc., and the application does not limit a device class of the service terminal.

As shown in fig. 6, the computer device proposed in the present application may include: at least one communication interface 21, at least one memory 22 and at least one processor 23, wherein:

the communication interface 21, the memory 22 and the processor 23 may be connected to a communication bus to implement mutual data interaction, so that the connection relationship of the lines in the computer device is not described in detail, and can be determined according to the communication requirement of the actual application scenario.

The communication interface 21 may include an interface of a communication module, such as a GSM module, a WIFI module, an interface for implementing data communication of a mobile communication network (such as a 5G, 6G network), etc., so that the computer device implements data interaction with other devices through such a communication interface; of course, the communication interface 21 may also include interfaces such as a USB interface and a serial/parallel interface, so as to implement data interaction between internal components of the computer device, for example, various intermediate data generated or required in the execution process of the foreign currency exchange service development prediction implementation method provided in the present application may be determined according to the requirements of the actual application scenario, which is not described in detail in the present application.

The memory 22 may store a program composed of a plurality of instructions for implementing the foreign currency conversion service operation prediction implementation method provided in the embodiment of the present application, and the processor 23 invokes and loads the program stored in the memory 22, so as to implement the foreign currency conversion service operation prediction implementation method provided in the corresponding embodiment of the present application, and the specific implementation process may refer to, but is not limited to, the above description of the corresponding embodiment.

In embodiments of the present application, memory 22 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device or other volatile solid-state storage device. The processor 23 may be a central processing unit (Central Processing Unit, CPU), application-specific integrated circuit (ASIC), digital Signal Processor (DSP), application-specific integrated circuit (ASIC), off-the-shelf programmable gate array (FPGA), or other programmable logic device, etc.

Optionally, in the case that the computer device is a service terminal, the computer device provided in the embodiment of the present application may further include various input components, various output components, an alarm component, an image acquisition component, and the like, which may be determined according to a service function type supported by the service terminal, and the like, which is not described in detail herein.

It should be understood that the structure of the computer device described in the foregoing embodiments of the present application does not limit the computer device in the embodiments of the present application, and in practical applications, the computer device may include more or less components than those shown in fig. 6 and described in the foregoing embodiments, which are not listed herein.

Finally, it should be noted that, in the present description, each embodiment is described in a progressive or parallel manner, and each embodiment is mainly described as different from other embodiments, where identical and similar parts of each embodiment are referred to each other. For the apparatus and the computer device disclosed in the embodiments, the description is relatively simple, and the relevant places refer to the description of the method section because the apparatus and the computer device correspond to the methods disclosed in the embodiments.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for implementing a foreign currency conversion service development prediction, the method comprising:

analyzing the obtained data characteristics based on service issuing conditions corresponding to the target financial institutions to obtain a prediction result of whether the target financial institutions are suitable for issuing the foreign currency exchange service, wherein the service issuing conditions at least comprise service profit and loss conditions and service handling client conditions;

the step of analyzing the obtained plurality of data features based on the service issuing conditions corresponding to the target financial institution to obtain a prediction result of whether the target financial institution is suitable for issuing the foreign currency exchange service, includes:

2. The method of claim 1, wherein said inputting the resulting plurality of data features into a foreign exchange transaction prediction model to obtain a prediction of whether the target financial institution is suitable for conducting the foreign exchange transaction, comprises:

3. The method of claim 2, wherein said inputting the resulting plurality of data features into a foreign exchange transaction prediction model results in a prediction of whether the target financial institution is suitable for conducting the foreign exchange transaction, further comprising:

4. The method of claim 2, wherein said inputting the resulting plurality of data features into a foreign currency conversion business prediction model results in a target prediction score for the target financial institution that is suitable for conducting the foreign currency conversion business, comprising:

5. The method of any one of claims 1-4, wherein the training process of the foreign currency conversion business prediction model comprises:

6. The method according to any one of claims 1 to 4, wherein the acquiring process of the service initiation condition includes:

7. The method of any one of claims 1-4, wherein the obtaining data to be predicted for the target financial institution comprises:

8. A foreign currency exchange business development prediction implementation device, characterized in that the device comprises:

The analysis and prediction module is used for analyzing the obtained data characteristics based on the service issuing conditions corresponding to the target financial institution to obtain a prediction result of whether the target financial institution is suitable for issuing the foreign currency exchange service, wherein the service issuing conditions at least comprise service profit and loss conditions and service handling client conditions;

the analysis and prediction module is specifically used for:

9. A computer device, the computer device comprising: at least one communication interface, at least one memory, and at least one processor, wherein:

the memory for storing a program for implementing the foreign currency exchange business development prediction implementation method according to any one of claims 1 to 7;

the processor is configured to load and execute the program stored in the memory, so as to implement the steps of the foreign currency exchange business development prediction implementation method according to any one of claims 1 to 7.