CN117273890A

CN117273890A - Transaction code-based service prediction method and device, storage medium and electronic equipment

Info

Publication number: CN117273890A
Application number: CN202311219876.0A
Authority: CN
Inventors: 赵迪; 张朋; 管婷婷
Original assignee: Bank of China Ltd
Current assignee: Bank of China Ltd
Priority date: 2023-09-20
Filing date: 2023-09-20
Publication date: 2023-12-22

Abstract

The application provides a business prediction method and device based on transaction codes, a storage medium and electronic equipment, and the field of big data or finance. Wherein the method comprises the following steps: acquiring a dynamic tag of a current client, wherein the dynamic tag is used for indicating the current service state of the current client; acquiring at least one business prediction result by using the dynamic tag and a pre-trained business prediction model, wherein the business prediction model is obtained by training a plurality of customer portrait data of a customer class to which the current customer belongs; and obtaining the transaction codes corresponding to the at least one service prediction result respectively according to the mapping relation between the service and the transaction codes. By utilizing the method, accurate service can be realized, and the business handling efficiency and the user experience are improved.

Description

Transaction code-based service prediction method and device, storage medium and electronic equipment

Technical Field

The present disclosure relates to the field of big data technologies, and in particular, to a business prediction method and apparatus based on transaction codes, a storage medium, and an electronic device.

Background

Nowadays, with the continuous development of banking business, the types of business that customers can transact at banks are more flexible and various, and teller can transact transfer business, deposit and withdraw business, open transact debit card, examine loan, pension Jin Dai, and transact financial transaction for customers at a counter.

Although a lot of business can be handled, a customer comes to a bank many times, a bank teller firstly inquires about what business the customer needs to handle, and the customer leaves after the bank processes the business for the customer. That is, the current passive service providing method has the problems of low service handling efficiency and poor user experience.

Disclosure of Invention

In order to solve the technical problems in the prior art, the application provides a business prediction method, a business prediction device, a storage medium and electronic equipment based on transaction codes, which can realize accurate service and improve business handling efficiency and user experience.

In a first aspect, the present application provides a transaction code-based service prediction method, where the method includes: acquiring a dynamic tag of a current client, wherein the dynamic tag is used for indicating the current service state of the current client; acquiring at least one business prediction result by using the dynamic tag and a pre-trained business prediction model, wherein the business prediction model is obtained by training a plurality of customer portrait data of a customer class to which the current customer belongs; and obtaining the transaction codes corresponding to the at least one service prediction result respectively according to the mapping relation between the service and the transaction codes.

By the method, the dynamic label of the current customer is firstly obtained, and then the service prediction result is obtained by using the service prediction model and the dynamic label which are obtained by pre-training. And then, according to the service and transaction code mapping set, the transaction code corresponding to the service prediction result is obtained, so that a teller can quickly preview the service set which can be handled by the client, and the complicated inquiry of what service the client wants to handle is not needed, so that the service is changed into initiative, accurate service is realized, and the service handling efficiency and the user experience are improved.

In one possible implementation manner, the obtaining the dynamic tag of the current client specifically includes:

acquiring the identity information of the current client;

and acquiring a corresponding current dynamic tag from the portrait data of the current client according to the identity information.

In one possible implementation manner, before the obtaining the identity information of the current client, the method further includes:

pre-establishing a portrait system of clients with different client categories, wherein the portrait system of the client categories is personal clients and comprises at least one of the following data: demographic characteristic data, personal interest data, personal customer consumption capability data, personal customer risk preference data; the portrait system with the client class being the enterprise client comprises at least one of the following data: enterprise operation data, enterprise sales data, and enterprise-related industry chain data.

In one possible implementation manner, before the obtaining the dynamic tag of the current client, the method further includes:

obtaining portrait data of a plurality of clients in each client class;

and training to obtain a business prediction model corresponding to each client class by using the acquired portrait data.

In one possible implementation, the method further includes:

and presenting each transaction code to an operation interface of a teller.

In a second aspect, the present application further provides a transaction code-based service prediction apparatus, where the apparatus includes: the system comprises an acquisition unit, a service prediction unit and a transaction code mapping unit;

the acquisition unit is used for acquiring the dynamic label of the current client, and the dynamic label is used for indicating the current service state of the current client. The business prediction unit is used for obtaining at least one business prediction result by utilizing the dynamic label and a pre-trained business prediction model, and the business prediction model is obtained by training a plurality of customer portrait data of the customer category to which the current customer belongs. The transaction code mapping unit is used for obtaining the transaction codes corresponding to the at least one service prediction result respectively according to the mapping relation between the service and the transaction codes.

In a possible implementation manner, the obtaining unit is specifically configured to obtain identity information of the current client; and acquiring a corresponding current dynamic tag from the portrait data of the current client according to the identity information.

In a possible implementation, the apparatus further comprises a model training unit;

the model training unit is used for acquiring portrait data of a plurality of clients in each client category; and training to obtain a business prediction model corresponding to each client class by using the acquired portrait data.

In a possible implementation, the apparatus further comprises an image hierarchy building unit. The portrait architecture creation unit is used for creating a portrait architecture of clients of different client classes in advance. Wherein, the portrait system of the client category is an individual client and comprises at least one of the following data: demographic characteristic data, personal interest data, personal customer consumption capability data, personal customer risk preference data; the portrait system with the client class being the enterprise client comprises at least one of the following data: enterprise operation data, enterprise sales data, and enterprise-related industry chain data.

In one possible implementation, the apparatus further includes a display unit for presenting each transaction code to an operator interface of the teller.

In a third aspect, the present application further provides a storage medium, where a computer program is stored, where the computer program when executed by a processor implements a transaction code based business prediction method.

In a fourth aspect, the present application further provides an electronic device, where the electronic device is configured to execute a program, and the program executes a transaction code-based service prediction method when running.

Drawings

Fig. 1 is a flowchart of a business prediction method based on transaction codes according to an embodiment of the present application;

FIG. 2 is a flowchart of another business prediction method based on transaction codes according to an embodiment of the present application;

fig. 3 is a schematic diagram of a business prediction device based on transaction codes according to an embodiment of the present application;

FIG. 4 is a schematic diagram of another business prediction device based on transaction codes according to an embodiment of the present application;

fig. 5 is a schematic diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the person skilled in the art more clearly understand the application scheme, the application scenario of the application scheme is first described below.

Currently, bank teller typically passively provides services to customers when they are provided with services. However, with the improvement of the requirements on the service quality, for the bank, when the customer walks to the bank, the teller needs to have comprehensive cognition on the customer, and other related services which can be transacted by the bank for the customer are rapidly analyzed through the characteristics of the customer such as the demand, the motivation, the income, the consumption and the like, and the passive service providing is changed into the active service providing, so that the accurate service is realized.

In order to solve the above problems, embodiments of the present application provide a business prediction method, device, storage medium and electronic device based on transaction codes, where the method obtains a dynamic tag of a current customer. And then obtaining a service prediction result by using the service prediction model and the dynamic label which are obtained by pre-training. And then, according to the service and transaction code mapping set, the transaction code corresponding to the service prediction result is obtained, so that a teller can quickly preview the service set which can be transacted by the client, and the user does not need to be fussy to inquire about what service the client wants to transact, thereby realizing accurate service, and improving service transacting efficiency and user experience.

In order to make the technical solution more clearly understood by those skilled in the art, the following description will refer to the technical solution in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application.

The words "first," "second," and the like in the description herein are used for descriptive purposes only and are not to be interpreted as indicating or implying a relative importance or implicitly indicating the number of features indicated

The embodiment of the application provides a business prediction method based on transaction codes, and the business prediction method is specifically described below with reference to the accompanying drawings.

Referring to fig. 1, the figure is a flowchart of a business prediction method based on transaction codes according to an embodiment of the present application.

The method comprises the following steps:

s11: and acquiring the dynamic label of the current client.

Wherein the dynamic tag is used for indicating the current business state of the current client. The current business state may include expiration of a product, transaction actions, external events, and the like.

The dynamic labels of all users are prestored in a database of the bank system, and the states of the dynamic labels of all users are updated in the database in real time along with the business operation of the users.

In practical applications, the number of the obtained dynamic tags may be one or more, which is not specifically limited in the embodiments of the present application.

S12: and obtaining at least one business prediction result by using the dynamic label and a pre-trained business prediction model.

The business prediction model is trained by using a plurality of customer portrait data of the customer category to which the current customer belongs. The input dynamic label of the service prediction model, namely the service prediction model is specifically used for obtaining the service prediction result according to the dynamic label.

In practical applications, since the amount of portrait data of a single client is small and there may be a loss of some business data, training of a predictive model is generally achieved using portrait data of a plurality of clients.

It will be appreciated that for different classes of clients, it is necessary to train corresponding business prediction models separately.

For example, for an individual customer, it is necessary to train to obtain a business prediction model of the individual customer using portrait data of a plurality of individual customers; for enterprise clients, it is necessary to train and obtain business prediction models of the enterprise clients by using portrait data of a plurality of enterprise clients.

S13: and obtaining the transaction codes corresponding to the at least one service prediction result respectively according to the mapping relation between the service and the transaction codes.

And the transaction codes and the business have a one-to-one mapping relation and are used for indicating a business prediction result.

In the process of processing the business, the business corresponding to different transaction codes also corresponds to different operations, and after the predicted business obtained by aiming at the business prediction model is mapped with the transaction codes operated by the teller, the scheme of the application can further obtain an operation set corresponding to the different business.

By using the technical scheme provided by the embodiment of the application, the service prediction result is obtained by using the dynamic label of the current client and the service prediction model obtained by pre-training. And then, according to the service and transaction code mapping set, the transaction code corresponding to the service prediction result is obtained, so that a teller can quickly preview the service set which can be handled by the client, and the complicated inquiry of what service the client wants to handle is not needed, so that the service is changed into initiative, accurate service is realized, and the service handling efficiency and the user experience are improved.

The following description is made in connection with specific implementations.

According to the technical scheme, modeling is carried out on the bank customer portrait through a data mining technology, and the functions of business prediction and transaction code association display are achieved. Firstly, a customer portrait label system is established by mining customer characteristic information, customers are described from different dimensions, and the customer portrait system is established. And then, a service prediction model is obtained by using data training, so that service prediction is realized. And subdividing the banking business, and combining the customer portrait analysis result to form a business and transaction code mapping set.

The customer portrait system has low application value in banks at present, and has more customer portrait labels which do not accord with business dimension, and has no guiding significance to business. The customer portrayal system is based on the system description of customer information in a specific service scene, is an ordered set of customer labels in a specific service target, and is continuously optimized and perfected. Data mining techniques are often applied to analysis in a business domain, such as customer churn rate analysis, etc. in banks. The application aims to predict a set of services which can be transacted for a current client by a teller when binding dynamic data (transaction actions, external events and the like) of the current client during data analysis. By the application, the current demands of the clients are effectively acquired for the bank, targeted services are provided for the clients, and the accurate service level of the clients is improved.

Referring to fig. 2, a flowchart of another business prediction method based on transaction codes according to an embodiment of the present application is shown.

S21: a customer portrayal hierarchy is established.

The categories of customers in embodiments of the present application may include individual customers and enterprise customers. Wherein, the portrait system of the individual client is an individual client portrait system, and the portrait system of the enterprise client is an enterprise client portrait system.

To build an individual customer representation hierarchy, a first type of data corresponding to an individual customer is collected, including, but not limited to, demographic characteristic data, personal interest data, individual customer consumption capability data, individual customer risk preference data, and the like.

The personal statistics feature data can be obtained by counting the business data of a large number of personal clients through a banking system.

The personal interest data may be obtained by analyzing personal data that the individual customer authorizes for use by the bank.

The personal customer consumption capability data may be obtained by analyzing personal consumption data and personal account data used by the personal customer authorized bank.

The personal client risk preference data may be obtained by conducting a risk preference questionnaire on the personal client. Among them, risk preference questionnaires include, but are not limited to, off-line paper questionnaires or on-line electronic questionnaires. In addition, the personal client risk preference data can be obtained by analyzing historical purchase records of financial products used by the authorized bank of the personal client.

In order to build an enterprise customer portrayal hierarchy, a second class of data corresponding to the enterprise customer needs to be collected, where the second class of data includes, but is not limited to, enterprise operation data, enterprise sales data, enterprise related industry chain data, and the like.

The enterprise operation data includes data generated by planning, organizing, implementing, controlling and other processes of the operation process, and data generated in various management works closely related to product production and service creation.

The enterprise sales data includes only enterprise product sales related data.

The enterprise-related industry chain data may include enterprise data for upstream and downstream enterprises that have business associations.

When the first type data and the second type data are collected, the granularity requirement of the data can be determined according to actual conditions, the granularity is used for representing the detail degree of the data, and the coarser the granularity is, the less the detail is, and more abstract generalizations are indicated; finer granularity indicates more detailed and more precise data.

Through describing the clients in different dimensions and granularity, a client tag system is formulated according to service requirements, a perfect client portrait tag system structure is established, tag contents are enriched gradually, and a unified client portrait system of a bank is established.

S22: and establishing a business prediction model.

The service prediction model is established through the steps of data acquisition, data sampling, model establishment, model deployment, model training, model evaluation and the like, and is used for acquiring a service prediction result, and is specifically described below.

And based on the customer portrait system established in the S21, acquiring the dynamic label of the current customer.

Dynamic tags are used to indicate the current business status of the customer, including, but not limited to, expiration of financial products, transaction actions of the customer, external events, and the like.

When the model is built, the data are sampled, the relation between the data is clarified, the data are rearranged, and the data are preprocessed, so that sample data required by the training model are obtained. The preprocessing comprises removing data without analysis value, integrating valuable data according to business prediction targets and the like.

And analyzing the data by different analysis methods (such as association rule method, decision tree and the like), comparing the data results of the different analysis methods, and selecting the most suitable analysis mode to establish a model. The specific type of the business prediction model is not limited, and may be, for example, a linear regression model, a decision tree model, a support vector machine model, a neural network model, a random forest model, and the like.

When the business prediction model is trained, the sample data is divided into training sample data and test sample data. Training the model by using training sample data, and gradually adjusting model parameters of the model in the training process. And after training is completed, testing and evaluating the trained model by using test sample data. And after the test evaluation meets the preset requirement, finishing model training to obtain a service prediction model.

The input dynamic label of the service prediction model, namely the service prediction model is specifically used for obtaining the service prediction result according to the dynamic label.

After the business prediction model is stabilized in the database, the business prediction model is put into practical use, the business prediction model is evaluated regularly, and the business prediction model can be updated regularly.

It will be appreciated that for different classes of clients, it is necessary to train corresponding business prediction models separately. For example, for an individual customer, it is necessary to train to obtain a business prediction model of the individual customer using portrait data of a plurality of individual customers; for enterprise clients, it is necessary to train and obtain business prediction models of the enterprise clients by using portrait data of a plurality of enterprise clients.

S23: and acquiring the current dynamic label corresponding to the user according to the identity information of the user.

There is a correspondence between the dynamic tag and the identity information of the user.

The embodiment of the application does not specifically limit the identity information of the user. For example, the identity information may be one or more of a user's identification card number, a user's bank card number, or a user's telephone number, etc.

When the teller handles business for the user, the corresponding current dynamic label can be obtained from the database in a summarizing way according to the identity information provided by the user. The current dynamic label is the last updated dynamic label, namely the latest dynamic label.

S24: and obtaining the current business prediction results by using the business prediction model and the current dynamic tag.

And after the current dynamic label is acquired according to whether the user information is received, the current dynamic label is used as the input of a service prediction model, and a service prediction result is obtained by prediction of the service prediction model.

It can be understood that the service prediction results predicted by the service prediction model may be one or more, and the specific number is determined according to the output result number parameter of the service prediction model.

S25: and acquiring transaction codes corresponding to the business prediction results.

The corresponding relation between business and transaction code is stored in the database of bank system in advance. For example, the transaction code mapping relationship contained in the customer information maintenance major class is: 0001 maintains transactions corresponding to customer complex information. The transaction code map contained by the customer pricing classes is: 0002 corresponds to the agreement interest rate transaction, 0003 corresponds to the exchange rate offer transaction.

Because the service prediction result is a prediction result of a service possibly handled by the user, the corresponding transaction codes are acquired one by one from the stored corresponding relations according to the acquired service prediction results.

S26: and presenting each transaction code to an operation interface of a teller.

For example, when a customer transacts business with a bank, the financial management of the customer is due, the risk preference is moderate, and the business prediction model obtains that the probability of transacting the business of the financial management product of the risk again is high, the corresponding transaction code is determined and then presented on the operation interface of the teller.

Therefore, the teller can easily preview the business set which can be handled by the client, and the complex inquiry of what business the client wants to handle is not needed, so that the service is changed into initiative, accurate service and targeted service are realized, and the business handling efficiency and the user experience are improved.

Based on the transaction code-based service prediction method provided in the above embodiment, the embodiment of the present application further provides a transaction code-based service prediction device, which is specifically described below with reference to the accompanying drawings.

Referring to fig. 3, the diagram is a schematic diagram of a business prediction device based on transaction codes according to an embodiment of the present application.

The device comprises: an acquisition unit 301, a traffic prediction unit 302, and a transaction code mapping unit 303.

The acquiring unit 301 is configured to acquire a dynamic tag of a current client, where the dynamic tag is used to indicate a current service state of the current client.

The business prediction unit 302 is configured to obtain at least one business prediction result by using the dynamic tag and a pre-trained business prediction model, where the business prediction model is obtained by training a plurality of customer portrait data of a customer class to which the current customer belongs.

The transaction code mapping unit 303 is configured to obtain transaction codes corresponding to the at least one service prediction result according to a mapping relationship between the service and the transaction codes.

By using the device, a teller can acquire the transaction code corresponding to the service prediction result, so that the service set which can be transacted by the client can be previewed rapidly, the user does not need to be fussy to inquire about what service the client wants to transact, the service is changed into initiative, the accurate service is realized, and the service transacting efficiency and the user experience are improved.

Referring to fig. 4, a schematic diagram of another business prediction device based on transaction codes according to an embodiment of the present application is shown.

The traffic prediction device differs from the device shown in fig. 3 in that: also included are a portrayal hierarchy building unit 304 and a model training unit 305.

Wherein, the portrait architecture creation unit 304 is used for creating a portrait architecture of clients of different client classes in advance.

The portrait system with the client class being the individual client comprises at least one of the following data: demographic characteristic data, personal interest data, personal customer consumption capability data, personal customer risk preference data.

The portrait system with the client class being the enterprise client comprises at least one of the following data: enterprise operation data, enterprise sales data, and enterprise-related industry chain data.

A model training unit 305 for acquiring portrait data of a plurality of clients in each client category; and training to obtain a business prediction model corresponding to each client class by using the acquired portrait data. The specific operation principle of the model training unit 305 may be referred to the description of S22 above, and will not be described herein.

The business prediction device based on the transaction code comprises a processor and a memory, wherein the portrait system establishment unit, the model training unit, the acquisition unit, the business prediction unit, the transaction code mapping unit and the like are all stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one, and business prediction based on transaction codes is realized by adjusting kernel parameters.

The embodiment of the invention provides a storage medium, on which a program is stored, which when executed by a processor, implements the transaction code-based business prediction method.

The embodiment of the invention provides a processor which is used for running a program, wherein the business prediction method based on transaction codes is executed when the program runs.

The embodiment of the application provides an electronic device, and the electronic device is specifically described below with reference to the accompanying drawings.

Referring to fig. 5, a schematic diagram of an electronic device according to an embodiment of the present application is provided.

The electronic device comprises at least one processor 501, at least one memory 502 connected to the processor 501, and a bus 503.

The processor 501 and the memory 502 complete communication with each other through the bus 503.

The processor 501 is configured to invoke the program instructions in the memory 502 to perform the transaction code based business prediction method described above. The device herein may be a server, PC, PAD, cell phone, etc.

The present application also provides a computer program product adapted to perform a program initialized with the transaction code based business prediction method steps when executed on a data processing device.

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

In one typical configuration, the device includes one or more processors (CPUs), memory, and a bus. The device may also include input/output interfaces, network interfaces, and the like.

The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (parameter random access memory, PRAM), static random access memory (static random access memory, SRAM), dynamic random access memory (dynamic random access memory, DRAM), other types of random access memory (random access memory, RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory, or other memory technology.

The business prediction method and device based on the transaction code, the storage medium and the electronic equipment provided by the invention can be used in the big data field or the financial field. The foregoing is merely an example, and the application fields of the transaction code-based service prediction method, the device, the storage medium and the electronic device provided by the invention are not limited.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.

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

It should be understood that in this application, "at least one" means one or more, and "a plurality" means two or more. "and/or" for describing the association relationship of the association object, the representation may have three relationships, for example, "a and/or B" may represent: only a, only B and both a and B are present, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b or c may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. The apparatus embodiments described above are merely illustrative, wherein the units and modules illustrated as separate components may or may not be physically separate. In addition, some or all of the units and modules can be selected according to actual needs to achieve the purpose of the embodiment scheme. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

The foregoing is merely exemplary of the application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the application and are intended to be comprehended within the scope of the application.

Claims

1. A business prediction method based on transaction codes, the method comprising:

acquiring a dynamic tag of a current client, wherein the dynamic tag is used for indicating the current service state of the current client;

acquiring at least one business prediction result by using the dynamic tag and a pre-trained business prediction model, wherein the business prediction model is obtained by training a plurality of customer portrait data of a customer class to which the current customer belongs;

and obtaining the transaction codes corresponding to the at least one service prediction result respectively according to the mapping relation between the service and the transaction codes.

2. The method for predicting service according to claim 1, wherein the obtaining the dynamic tag of the current client specifically includes:

acquiring the identity information of the current client;

3. The business prediction method according to claim 1, wherein before the obtaining the identity information of the current client, the method further comprises:

4. The traffic prediction method according to claim 1, wherein before the dynamic tag of the current client is obtained, the method further comprises:

obtaining portrait data of a plurality of clients in each client class;

5. The traffic prediction method according to claim 1, characterized in that the method further comprises:

and presenting each transaction code to an operation interface of a teller.

6. A transaction code-based business prediction device, the device comprising: the system comprises an acquisition unit, a service prediction unit and a transaction code mapping unit;

the acquisition unit is used for acquiring a dynamic tag of a current client, wherein the dynamic tag is used for indicating the current service state of the current client;

the business prediction unit is used for obtaining at least one business prediction result by utilizing the dynamic tag and a pre-trained business prediction model, and the business prediction model is obtained by utilizing a plurality of customer portrait data training of a customer class to which the current customer belongs;

the transaction code mapping unit is used for obtaining the transaction codes corresponding to the at least one service prediction result respectively according to the mapping relation between the service and the transaction codes.

7. The traffic prediction device according to claim 6, wherein the obtaining unit is specifically configured to obtain identity information of the current client; and acquiring a corresponding current dynamic tag from the portrait data of the current client according to the identity information.

8. The traffic prediction device according to claim 1, characterized in that the device further comprises a model training unit;

9. A storage medium having stored thereon a computer program which, when executed by a processor, implements the transaction code based transaction prediction method of any of claims 1-5.

10. An electronic device for running a program, wherein the program is operative to perform the transaction code-based business prediction method of any one of claims 1-5.