CN117009529A

CN117009529A - SWIFT message intelligent classification method, SWIFT message intelligent classification device, SWIFT message intelligent classification equipment and storage medium

Info

Publication number: CN117009529A
Application number: CN202311015261.6A
Authority: CN
Inventors: 丁锐
Original assignee: Bank of China Ltd
Current assignee: Bank of China Ltd
Priority date: 2023-08-11
Filing date: 2023-08-11
Publication date: 2023-11-07

Abstract

The application discloses a SWIFT message intelligent classification method, a SWIFT message intelligent classification device, SWIFT message intelligent classification equipment and a storage medium, which can be applied to the field of artificial intelligence or the field of finance. When the method is executed, SWIFT messages to be classified are acquired firstly, then the SWIFT messages to be classified are subjected to message type analysis by utilizing a SWIFT message intelligent classification model, and then the SWIFT messages are sent to corresponding service departments according to the type analysis results of the SWIFT messages to be classified. Therefore, the SWIFT message to be classified is subjected to the message classification analysis by utilizing the SWIFT message intelligent classification model, the manual classification analysis on the SWIFT message is not needed, and particularly when the SWIFT message quantity to be classified is large, the SWIFT message intelligent classification model is utilized for classification, so that the burden of workers can be reduced, and the error rate caused by manual classification is reduced.

Description

SWIFT message intelligent classification method, SWIFT message intelligent classification device, SWIFT message intelligent classification equipment and storage medium

Technical Field

The present application relates to the field of artificial intelligence, and in particular, to a method, an apparatus, a device, and a storage medium for intelligent classification of SWIFT messages.

Background

The global banking and financial telecommunication association (Society for Worldwide Interbank Financial Telecommunications, SWIFT) is an international cooperative organization that does not benefit from the international banking and is a standardized message transmission mechanism, that is, a channel for transmitting financial information between financial institutions, and information transmission between banks and payment institutions, including payment instructions, information confirmation, etc., is completed through SWIFT messages.

In the scene of performing international settlement business, foreground staff can receive a large number of SWIFT format messages related to international settlement every day, and the foreground staff needs to distribute the messages to different departments for processing according to the content of the messages, so that the process of completely manually distributing the messages consumes a large amount of manpower, and the distribution is easy to make mistakes by using manpower.

Disclosure of Invention

In view of this, the application provides a method, a device, equipment and a storage medium for intelligent classification of SWIFT messages, which aim to solve the problems that when SWIFT messages are classified manually, a lot of manpower is consumed due to the fact that the number of the messages is too large, and the classification result is wrong by utilizing manual classification.

In a first aspect, the present application provides a method for intelligently classifying SWIFT messages, including:

acquiring SWIFT messages of global banking and financial telecommunication associations to be classified;

performing message type analysis on the SWIFT message to be classified by using an SWIFT message intelligent classification model;

and sending the SWIFT message to a corresponding service department according to the class analysis result of the SWIFT message to be classified.

Optionally, before the intelligent classification model of the SWIFT messages is used to perform the analysis of the message types of the SWIFT messages to be classified, the method further includes: training the SWIFT message intelligent classification model;

the training of the SWIFT message intelligent classification model comprises the following steps:

acquiring a plurality of historical SWIFT messages received in a preset time period;

processing the obtained historical SWIFT message;

and inputting the processed historical SWIFT message into a SWIFT message intelligent classification model.

Optionally, after obtaining the historical SWIFT message, the method further includes:

and setting a plurality of different labels for each SWIFT message in the historical SWIFT messages, wherein each historical SWIFT message is provided with the same label.

Optionally, the processing the obtained historical SWIFT message includes:

extracting keywords from each SWIFT message in the historical SWIFT messages, wherein the keywords are words in a preset keyword word list, and the keywords comprise a plurality of words;

screening the extracted keywords, and removing stop words, wherein the stop words are words belonging to a word list of the preset keywords, but are words not used for training the SWIFT message intelligent classification model;

and calculating word frequency and inverse document frequency of the words after the keywords are screened.

Optionally, after the processed historical SWIFT message is input into the SWIFT message intelligent classification model, the method further includes:

respectively classifying each SWIFT message in the historical SWIFT messages for multiple times by using a classification algorithm to obtain multiple classification results;

selecting a result with highest confidence coefficient from the plurality of classification results according to the word frequency and the inverse document frequency;

and taking the label in the result with the highest confidence as the label of the SWIFT message.

In a second aspect, the present application provides an intelligent classification device for SWIFT messages, where the device includes:

the SWIFT message acquisition module is used for acquiring SWIFT messages of the global same-industry bank financial telecommunication associations to be classified;

the SWIFT message classification module is used for carrying out message type analysis on the SWIFT messages to be classified by utilizing the SWIFT message intelligent classification model;

and the SWIFT message sending module is used for sending the SWIFT message to the corresponding service department according to the category analysis result of the SWIFT message to be classified.

Optionally, the apparatus further includes: the SWIFT message intelligent classification model training module is used for training the SWIFT message intelligent classification model;

the SWIFT message intelligent classification model training module specifically comprises:

the historical SWIFT message acquisition word module is used for acquiring a plurality of historical SWIFT messages received in a preset time period;

a history SWIFT message processing sub-module, configured to process the obtained history SWIFT message;

and the history SWIFT message input sub-module is used for inputting the processed history SWIFT message into the SWIFT message intelligent classification model.

Optionally, the SWIFT message intelligent classification model training module further includes:

the SWIFT message label setting sub-module is used for setting a plurality of different labels for each SWIFT message in the historical SWIFT messages, and each historical SWIFT message is provided with the same label.

Optionally, the history SWIFT message processing sub-module is specifically configured to:

the SWIFT message classification sub-module is used for respectively classifying each SWIFT message in the historical SWIFT message for multiple times by utilizing a classification algorithm to obtain multiple classification results;

In a third aspect, the present application provides an apparatus, where the apparatus includes a memory and a processor, where the memory is configured to store a computer program, and the processor is configured to implement the SWIFT message intelligent classification method according to the first aspect when the computer program is executed.

In a fourth aspect, the present application provides a computer readable storage medium, where a computer program is stored, where the computer program is executed by a processor to implement the SWIFT message intelligent classification method according to the first aspect.

The application provides an intelligent SWIFT message classification method. When the method is executed, SWIFT messages of the global banking and financial telecommunication society to be classified are acquired, then the SWIFT messages to be classified are subjected to message type analysis by utilizing a SWIFT message intelligent classification model, and then the SWIFT messages are sent to corresponding service departments according to the type analysis results of the SWIFT messages to be classified. Therefore, the SWIFT message to be classified is subjected to the message classification analysis by utilizing the SWIFT message intelligent classification model, the manual classification analysis on the SWIFT message is not needed, and particularly when the SWIFT message quantity to be classified is large, the SWIFT message intelligent classification model is utilized for classification, so that the burden of workers can be reduced, and the error rate caused by manual classification is reduced.

Drawings

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

FIG. 1 is a flow chart of a SWIFT message intelligent classification method provided by the embodiment of the application;

FIG. 2 is a flowchart of another intelligent SWIFT message classification method according to an embodiment of the present application;

FIG. 3 is a schematic structural diagram of an intelligent SWIFT message classification device according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of a computer device according to an embodiment of the present application.

Detailed Description

As described in the background art of the present application, in the scenario of performing international settlement service, a foreground worker receives a large number of SWIFT messages every day, and needs to perform classification processing on the SWIFT messages, and send the SWIFT messages to a relevant responsible department for processing, so that the process of manually performing classification consumes a large amount of time, and the accuracy of the classification result is low.

In order to solve the technical problems, an embodiment of the present application provides an intelligent classification method for a SWIFT message, which includes: the method comprises the steps of firstly obtaining SWIFT messages of the global banking and financial telecommunication society to be classified, then carrying out message type analysis on the SWIFT messages to be classified by utilizing a SWIFT message intelligent classification model, and then sending the SWIFT messages to corresponding business departments according to the type analysis results of the SWIFT messages to be classified. Therefore, the SWIFT message to be classified is subjected to the message classification analysis by utilizing the SWIFT message intelligent classification model, the manual classification analysis on the SWIFT message is not needed, and particularly when the SWIFT message quantity to be classified is large, the SWIFT message intelligent classification model is utilized for classification, so that the burden of workers can be reduced, and the error rate caused by manual classification is reduced.

It should be noted that the method, the device, the equipment and the storage medium for intelligent classification of SWIFT messages provided by the application can be used in the big data field or the financial field. The foregoing is merely an example, and the application fields of the method, the device, the equipment and the storage medium for intelligent classification of the SWIFT messages provided by the application are not limited.

In order to make the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

Fig. 1 is a flowchart of a method for intelligently classifying SWIFT messages according to an embodiment of the present application. Referring to fig. 1, the intelligent classification method for SWIFT messages provided by the embodiment of the present application may include:

s101, acquiring SWIFT messages of the global banking and financial telecommunication society to be classified.

SWIFT is a global banking financial telecommunication society, (Society for Worldwide Interbank Financial Telecommunications), SWIFT messages can be suitable for different application scenes, and SWIFT messages are divided into ten major categories according to actual operation of banks: including customer remittance and check, such as: MT101, MT103, MT110, etc.; banked cun place transfer, such as: MT200, MT201, etc.; foreign exchange marketing, money market and derivative tools such as: MT300, MT305; and (3) collection, such as: MT400, MT410, MT412, etc.; securities business; silver loans and precious metal business; documentary credit and warranty, such as: MT700/701, MT705, etc.; a traveler's check; banking and customer accounts, such as: MT900, MT910, etc.; SWIFT system telegrams.

The SWIFT message to be classified refers to a SWIFT message which is received by a bank foreground staff and is not classified, and it is required to be noted that SWIFT messages of different types need to be separated to relevant responsible staff for processing.

S102, performing report type analysis on the SWIFT messages to be classified by using a SWIFT message intelligent classification model.

After receiving a large number of SWIFT messages to be classified, a bank foreground worker needs to perform classification processing, if the SWIFT messages are identified through experience of the worker and sent to related responsible personnel, the process can consume a large amount of time and generate classification errors, and therefore SWIFT messages can be classified through a SWIFT message intelligent classification model. The staff inputs the SWIFT message to be classified into the SWIFT message intelligent classification model, so that the SWIFT message can be classified.

S103, according to the category analysis result of the SWIFT message to be classified, the SWIFT message is sent to a corresponding service department.

After the SWIFT message is classified by the SWIFT message intelligent classification model, the type of the SWIFT message is fed back to staff, and the staff directly sends the SWIFT message to related staff for processing according to the classification result.

Different service departments are responsible for processing different messages, for example, when the SWIFT message type is A, the SWIFT message is sent to the department responsible for processing the SWIFT message of the A type for processing.

The embodiment provides the SWIFT message intelligent classification method, the SWIFT message can be classified through the SWIFT message intelligent classification model, the time waste caused by manual classification is reduced, and the accuracy of SWIFT message classification can be further improved.

It can be understood that before the intelligent SWIFT message classification model is used to perform the message classification analysis on the SWIFT message to be classified, a SWIFT message intelligent classification model needs to be trained to be capable of classifying the SWIFT message to be classified. In this regard, the embodiment of the present application provides another intelligent classification method for SWIFT messages, and the intelligent classification method for SWIFT messages is described below with reference to the embodiment and the accompanying drawings, respectively.

Fig. 2 is a flowchart of another intelligent classification method for SWIFT messages according to an embodiment of the present application. Referring to fig. 2, the intelligent classification method for the SWIFT message may specifically include:

s201: and acquiring SWIFT messages of the global banking and financial telecommunication society to be classified.

In the embodiment of the present application, the technical details of S201 may be referred to the description related to S101 in the above embodiment, which is not described herein.

S202: and carrying out message type analysis on the SWIFT messages to be classified by utilizing the SWIFT message intelligent classification model.

In the embodiment of the present application, the technical details of S202 may be referred to the description related to S102 in the above embodiment, which is not described herein.

S203: and training the SWIFT message intelligent classification model.

Training the SWIFT message intelligent classification model requires a large number of samples, and training the model by acquiring the historical SWIFT message as a sample. Specifically, a historical SWIFT message in a period of time may be obtained as a sample, for example, a historical SWIFT message in a month may be obtained, or a historical SWIFT message in a half year may be obtained as a sample to train the model, and specific time may be selected by those skilled in the art according to actual situations, which is not limited herein.

It can be understood that a large number of SWIFT messages are processed by a bank every day, so that the obtained historical SWIFT messages include a plurality of SWIFT messages, after the historical SWIFT messages are obtained, a plurality of different labels are required to be set for each SWIFT message in the obtained historical SWIFT messages, for example, a plurality of labels are set for the historical message a, the labels specifically include comfort electricity, expense, correction, information checking, remittance, due-time investigation, checking, no position, checking state, limited time, documents, fraud, notification electricity, checking and paying, other categories, and the SWIFT messages in different scenes belong to different business departments for processing. Different SWIFT messages have the same labels, for example, there are history messages a and B, wherein history message a has labels of placebo, fee, correction, check information, refund, due investigation, check, no position, check status, limit, document, fraud, notification, check and pay, and others, and history message B also has labels of placebo, fee, correction, check information, refund, due investigation, check, no position, check status, limit, document, fraud, notification, check and pay, and others.

After the SWIFT message is provided with the label, the content of the SWIFT message is required to be processed, each SWIFT message in the history SWIFT message is subjected to keyword extraction, the keywords are words in a preset keyword word list, the keywords comprise a plurality of words and correspond to the label type set for the message, the extracted keywords are screened, stop words are removed, the stop words are words in the preset keyword word list, but are words which are not used for training of an intelligent SWIFT message classification model, and word frequency and inverse document frequency calculation are carried out on the words after the keywords are screened.

For example, extracting keywords from the historical SWIFT message a to obtain keywords a, b, c, d, e, where the keywords a, b, c, d, e all belong to a preset keyword word list, and the keyword e belongs to a stop word, removing the keyword e, and calculating word Frequency (Term Frequency, TF) and inverse document Frequency (Inverse Document Frequency, IDF) for the keywords a, b, c, d, where the word Frequency refers to the number of times a certain word appears in a document that is a proportion of all words, for example, 300 words in total, and 50/300 is the word Frequency of the word a; the inverse document frequency refers to the number of times a document containing a word appears in the total document, for example, 1000 documents in total, where 300 documents appear for a word, the inverse document frequency=log [ document total/(document number containing the phrase+1) ].

After the TF value and the IDF value are obtained, the TF-IDF (term frequency-inverse document frequency) value is obtained by using the word frequency x inverse document frequency, and the larger the TF-IDF value is, the greater the importance of the feature word to the text is. Inputting the processed historical SWIFT message into a SWIFT message intelligent classification model, performing two classifications on the input historical SWIFT message labels, expanding the two classifications into multiple classifications, comparing TF-IDF values of keywords of each type, and obtaining the keyword with the highest confidence as the classification label of the message according to the comparison result, thereby realizing multi-classification of SWIFT messages.

For example, keywords a, b, c, d are classified as ((a), b, c, d); the method comprises the steps of (a), b, c, d) ((b), a, b, d) ((d), b, c, a) and selecting the highest TF-IDF value in a, b, c, d as the final label of the message. Specifically, taking a bank as an example to classify a SWIFT message, taking the message A, B, C, D as a historical SWIFT message, setting a placebo, expense, correction, information checking, remittance, due job investigation, checking, no position, checking state, limiting period, document, fraud, notification electricity and checking and paying the labels, calculating a TF-IDF value of a keyword (corresponding to the label set by the message) in each message content, first classifying the message A, and using a classifier such as light Gradient Boosting Machine, namely, lightGBM, first classifying the SWIFT message to obtain different classification results, wherein the classification results are as follows:

((placebo), (fee, correction, information search, refund, due investigation, urge search, no position, state search, limit, document, fraud, notification, search Jie Fu)); ((expense), (comfort electricity, correction, information checking, remittance, due investigation, checking, no position, checking status, limit, document, fraud, notification electricity, check Jie Fu)); ((correction), (fee, comfort, information, refund, due investigation, urge investigation, no position, state, limit, document, fraud, notification, jie Fu)); ((check information), (expense, comfort, correction, refund, due investigation, urge check, no position, check status, limit, document, fraud, notification, check Jie Fu)); (remix), (fee, comfort, information, correction, due investigation, checking, no position, checking status, limit, document, fraud, notification, check Jie Fu)), … ((check Jie Fu), (fee, comfort, information, correction, due investigation, checking, no position, checking status, limit, document, fraud, notification, remix)), etc., it is noted that the classification results include items in which a certain label is a class and other labels are a class, respectively, and the classification results are partially exemplified in the above examples. Then using one-to-many algorithm, (OneVSRest, ovR) to compare multiple classification results, comparing the TF-IDF value of the first keyword in the classification results, selecting the largest TF-IDF value as the label of the message, for example, if the TF-IDF value of the keyword of the message A is largest, the label type of the message A is considered as "key electricity", and if the TF-IDF value of the keyword of the "expense" is largest, the label of the message A is considered as "expense". The model is trained by using a large amount of sample data, and the model is optimized until the classification accuracy of the model is required to be preset, and the trained model is obtained.

S204: and sending the SWIFT message to a corresponding service department according to the class analysis result of the SWIFT message to be classified.

In the embodiment of the present application, the technical details of S204 may be referred to the description related to S103 in the above embodiment, which is not described herein.

The embodiment provides an intelligent SWIFT message classification method, wherein before a SWIFT message intelligent classification model is used for classifying messages, historical SWIFT messages are required to be obtained to be used as model training samples, a large number of samples are used for training the models, and then a trained model is obtained, so that when new SWIFT messages are classified, the trained model can be used for directly classifying the messages, the model does not need to be classified manually according to experience, the workload of related personnel can be reduced, and classification errors can be avoided to a certain extent by classifying the models.

The embodiments of the present application provide some specific implementation manners of the intelligent classification method for the SWIFT messages, and based on this, the present application also provides a corresponding device. The apparatus provided by the embodiment of the present application will be described in terms of functional modularization.

Fig. 3 is a schematic structural diagram of an intelligent classification device for SWIFT messages according to an embodiment of the present application. Referring to fig. 3, an intelligent classification device 300 for SWIFT messages provided in an embodiment of the present application includes:

the SWIFT message obtaining module 310 is configured to obtain SWIFT messages of the global same bank financial telecommunication society to be classified;

the SWIFT message classification module 320 is configured to perform a message classification analysis on the SWIFT message to be classified by using a SWIFT message intelligent classification model;

and the SWIFT message sending module 330 is configured to send the SWIFT message to a corresponding service department according to a result of analyzing the class of the SWIFT message to be classified.

In one implementation manner of the embodiment of the present application, the apparatus further includes: the SWIFT message intelligent classification model training module is used for training the SWIFT message intelligent classification model;

In an implementation manner of the embodiment of the present application, the SWIFT message intelligent classification model training module further includes:

In one implementation manner of the embodiment of the present application, the history SWIFT message processing sub-module is specifically configured to:

The embodiment of the application also provides corresponding equipment and a computer storage medium, which are used for realizing the scheme provided by the embodiment of the application.

As shown in fig. 4, the computer device 01 is in the form of a general purpose computing device. The components of the computer device 01 may include, but are not limited to: one or more processors or processing units 03, a system memory 08, and a bus 04 that connects the various system components (including the system memory 08 and processing units 03).

Bus 04 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, and a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

The computer device 01 typically includes a variety of computer system readable media. Such media can be any available media that can be accessed by the computer device 01 and includes both volatile and nonvolatile media, removable and non-removable media.

The system memory 08 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 09 and/or cache memory 10. The computer device 01 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 11 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 4, commonly referred to as a "hard disk drive"). Although not shown in fig. 4, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be coupled to bus 04 through one or more data medium interfaces. The memory 08 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of the embodiments of the application.

A program/utility 12 having a set (at least one) of program modules 13 may be stored in, for example, memory 08, such program modules 13 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 13 typically carry out the functions and/or methods of the embodiments described herein.

The computer device 01 may also communicate with one or more external devices 02 (e.g., keyboard, pointing device, display 07, etc.), one or more devices that enable a user to interact with the computer device 01, and/or any devices (e.g., network card, modem, etc.) that enable the computer device 01 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 06. Moreover, the computer device 01 may also communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through the network adapter 05. As shown in fig. 4, the network adapter 05 communicates with other modules of the computer device 01 via the bus 04. It should be appreciated that although not shown in fig. 4, other hardware and/or software modules may be used in connection with the computer device 01, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

The processor unit 03 executes various functional applications and data processing by running a program stored in the system memory 08, for example, to implement a SWIFT message intelligent classification method provided by the embodiment of the present application.

From the above description of embodiments, it will be apparent to those skilled in the art that all or part of the steps of the above described example methods may be implemented in software plus general hardware platforms. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a storage medium, such as a read-only memory (ROM)/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network communication device such as a router) to perform the method according to the embodiments or some parts of the embodiments of the present application.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, 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 the element.

It should be further noted that, in the present 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. In particular, for the apparatus and device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points. The apparatus and device embodiments described above are merely illustrative, wherein elements illustrated as separate elements may or may not be physically separate, and elements presented as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present application without undue burden.

The foregoing is only one specific embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the technical scope of the present application should be included in the scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An intelligent SWIFT message classification method is characterized by comprising the following steps:

2. The method of claim 1, wherein before performing a packet classification analysis on the SWIFT messages to be classified using the SWIFT message intelligent classification model, the method further comprises: training the SWIFT message intelligent classification model;

processing the obtained historical SWIFT message;

3. The method of claim 2, wherein after obtaining the historical SWIFT message, the method further comprises:

4. The method of claim 2, wherein the processing the acquired historical SWIFT messages comprises:

5. The method of claim 4, wherein after the step of inputting the processed historical SWIFT messages into the SWIFT message intelligent classification model, the method further comprises:

6. An intelligent classification device for SWIFT messages, the device comprising:

7. The apparatus of claim 6, wherein the apparatus further comprises: the SWIFT message intelligent classification model training module is used for training the SWIFT message intelligent classification model;

8. The apparatus of claim 7, wherein the history SWIFT message processing sub-module is specifically configured to:

9. A computing device, the device comprising: a memory, a processor;

the memory is used for storing a computer program;

the processor is configured to implement the SWIFT message intelligent classification method according to any one of claims 1 to 5 when executing the computer program.

10. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the intelligent classification method of SWIFT messages according to any one of claims 1 to 5 is implemented.