International balance of payments online application data processing method, device, electronic equipment and storage medium
Through the combination of RPA technology and FastText intelligent review model, the online application data is automatically extracted and reviewed, which solves the problems of inefficiency and errors in the bank audit process, and achieves more efficient and accurate balance of payments data processing.
Patent Information
- Application Number
- CN202010610312.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-06-30
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2040-06-30
AI Technical Summary
In the existing technology, banks have low efficiency in online reporting of balance of payments data, and are prone to errors. Business personnel need to log in to the system frequently to ensure timeliness, resulting in manual review omissions and reporting of error data.
RPA technology is used to automatically extract the application information that customers have not reviewed on the online application system, and intelligently review it through the pre-trained FastText intelligent review model, output preliminary review results for business personnel to review, and finally RPA technology completes the audit result registration.
It improves the processing efficiency and review accuracy of the bank review process, reduces the number of repeated logins of business personnel, and ensures the timeliness and accuracy of the declaration data.
Smart Images

Figure CN111782809B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, electronic device and storage medium for processing international balance of payments online application data. Background Art
[0002] According to the foreign exchange management policy, when domestic individuals and enterprises conduct foreign-related payment and collection business through banks, they should make international balance of payments statistics declarations through the handling banks, and the banks shall perform duties such as reviewing and sending relevant information for international balance of payments statistics declarations to ensure the timeliness, accuracy and completeness of the declared data. There are two ways of submission: paper declaration and online declaration. For paper declaration, the customer submits the paper declaration voucher to the handling bank, and the bank business personnel enter the data through the bank system and submit it to the State Administration of Foreign Exchange Digital Foreign Exchange Management Platform (ASOne) through system docking; for online declaration, the customer directly logs in to the ASOne system to fill in the declaration information, and the bank business personnel log in to the ASOne system to review the customer's online declaration information. If the manual review is passed, the submission is successful. If the manual review is not passed, it will be returned to the customer for revision.
[0003] At present, in order to ensure timeliness of online bank review, bank staff need to log into the system repeatedly several times a day. In addition, manual review is inefficient and prone to errors and omissions in the reported data, resulting in erroneous data being submitted. Summary of the invention
[0004] In view of the problems in the prior art, the present invention provides a method, device, electronic device and storage medium for processing international balance of payments online application data, which can at least partially solve the problems existing in the prior art.
[0005] In order to achieve the above object, the present invention adopts the following technical solution:
[0006] In a first aspect, a method for processing international balance of payments online application data is provided, comprising:
[0007] Use RPA technology to obtain the declaration data filled in by customers on the online application system;
[0008] Conduct key point verification on the declared data according to the preset verification rules;
[0009] Review the declared data based on the pre-trained intelligent review model;
[0010] Feedback the key point verification and review results to the business terminal for business personnel to review.
[0011] Furthermore, the intelligent review model is a FastText model.
[0012] Furthermore, the application data is reviewed based on the pre-trained intelligent review model, including:
[0013] Perform word segmentation on the declared data;
[0014] The word sequence obtained by word segmentation is used as a feature vector and input into the pre-trained FastText model to obtain the review result.
[0015] Furthermore, the method for processing international balance of payments online application data also includes:
[0016] Obtain the review results from business personnel;
[0017] The review results are registered as the final review results in the online application system using RPA technology.
[0018] In a second aspect, a device for processing international balance of payments online application data is provided, comprising:
[0019] The online application data RPA collection module uses RPA technology to obtain the application data filled in by customers on the online application system;
[0020] Key point verification module, which conducts key point verification on the declared data according to preset verification rules;
[0021] The intelligent review module reviews the declared data based on the pre-trained intelligent review model;
[0022] The audit result output module feeds back the key verification results and review results to the business terminal for business personnel to review.
[0023] Furthermore, the intelligent review model is a FastText model.
[0024] Furthermore, the intelligent review module includes:
[0025] An analysis unit performs word segmentation on the declared data;
[0026] The intelligent review unit inputs the word sequence obtained by word segmentation as a feature vector into the pre-trained FastText model to obtain the review result.
[0027] Furthermore, the international balance of payments online application data processing device also includes:
[0028] Review result acquisition module, to obtain the review results of business personnel;
[0029] The online application data RPA automatic review module uses RPA technology to register the review results as the final review results into the online application system.
[0030] In a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the above-mentioned method for processing international balance of payments online application data are implemented.
[0031] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned method for processing international balance of payments online application data are implemented.
[0032] The present invention provides a method, device, electronic device and storage medium for processing international balance of payments online application data. The method includes: using RPA technology to obtain the application data filled in by the customer on the online application system; conducting key point verification on the application data according to preset verification rules; reviewing the application data according to a pre-trained intelligent review model; and feeding back the key point verification results and review results to the business terminal for business personnel to review. Among them, the RPA technology is used to automatically extract the application information that has been submitted but not reviewed by the customer on the online application system, and after intelligent review by the device, the review results are output, and the business personnel assist in confirmation, thereby improving the processing efficiency and the accuracy of the review, ensuring timeliness, and bank business personnel do not need to log in to the system repeatedly in the compartment.
[0033] In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:
[0035] Figure 1 A schematic diagram of an application architecture in an embodiment of the present invention;
[0036] Figure 2 Schematic diagram of the process of processing the international balance of payments online application data in the embodiment of the present invention Figure 1 ;
[0037] Figure 3 Shows Figure 2 The specific steps of step S300;
[0038] Figure 4 Schematic diagram of the process of processing the international balance of payments online application data in the embodiment of the present invention Figure 2 ;
[0039] Figure 5 The structure diagram of the robot based on RPA technology used in the embodiment of the present invention is shown;
[0040] Figure 6 It is the structural frame of the international balance of payments online application data processing device in the embodiment of the present invention. Figure 1 ;
[0041] Figure 7 It is the structural frame of the international balance of payments online application data processing device in the embodiment of the present invention. Figure 2 ;
[0042] Figure 8 4 is a structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0043] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.
[0044] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0045] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or apparatuses.
[0046] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0047] At present, in the process of online bank review, after the customer completes the declaration information in the ASOne system, the bank staff cannot be notified in real time for review. The bank staff needs to log in to the ASOne system to actively check whether there is any record information reported by the customer that has not been reviewed. In order to ensure timeliness, they need to log in to the system repeatedly several times a day. When reviewing the declared information, each piece of information is manually reviewed, which is inefficient. In addition, the manual review process depends on the skills of the bank staff, as well as the foreign exchange business-related systems and the degree of mastery of the data collection specifications of the State Administration of Foreign Exchange. It is easy to have errors in the review of the declared data, resulting in erroneous data being submitted. Urgently needed
[0048] The present invention provides an intelligent review technology for international balance of payments online application data based on RPA. By utilizing RPA (Robotic Process Automation) robot process automation + artificial intelligence algorithm, it can support the automatic extraction of customer's online application information that has been submitted but not reviewed through RPA technology, and after review by intelligent algorithm, the review result is output for confirmation by business personnel. The final result after confirmation is automatically reviewed by RPA, which can replace some predetermined and repetitive actions in the bank's review process, provide intelligent review results for review personnel for reference, and improve the processing efficiency and review accuracy of the bank's review process.
[0049] Figure 1 Schematic diagram of the application architecture in the embodiment of the present invention; Figure 1 As shown, the customer logs in to the ASOne system S1 (the digital foreign exchange management platform of the State Administration of Foreign Exchange) through the client device B1. After completing the filling of the declaration information, the international balance of payments online application data processing server S2 (the bank side, i.e., the server that executes the method provided by the present invention) uses the RPA technology to automatically log in to the ASOne system at a certain time interval according to the set time interval, query the customer's declared but unreviewed declaration data, automatically copy and store the element information of each field of the declaration information, obtain structured data information, conduct intelligent review, and push the preliminary review results to the business terminal B2 for review by the business personnel. The review results are fed back to the international balance of payments online application data processing server S2. The international balance of payments online application data processing server S2 is implemented by the RPA technology. According to the set time interval, it automatically logs in to the ASOne system at a certain time interval, query the customer's declared but unreviewed declaration data, and completes the review result registration according to the final review result.
[0050] It is understandable that the client device B1 and the service terminal B2 may include a smart phone, a tablet electronic device, a portable computer, a desktop computer, etc.
[0051] Any suitable network protocol may be used for communication between the ASOne system server and the client device, between the ASOne system server and the international balance of payments online application data processing server S2, and between the international balance of payments online application data processing server S2 and the business terminal B2, including network protocols that have not yet been developed on the filing date of this application. The network protocol may include, for example, TCP / IP protocol, UDP / IP protocol, HTTP protocol, HTTPS protocol, etc. Of course, the network protocol may also include, for example, RPC protocol (Remote Procedure Call Protocol) and REST protocol (Representational State Transfer) used on top of the above protocols.
[0052] Figure 2 Schematic diagram of the process of processing the international balance of payments online application data in the embodiment of the present invention Figure 1 ;like Figure 2 As shown, the method for processing international balance of payments online application data may include the following contents:
[0053] Step S100: Use RPA technology to obtain the declaration data filled in by the customer on the online application system.
[0054] Through RPA technology, the system automatically logs into the ASOne system at set intervals to query the customer's declared but unreviewed declaration data, automatically copy and store the information of each field element of the declaration information, and automatically extract structured data information.
[0055] It is worth noting that the online declaration information involves standard format elements required by the relevant data collection specifications formulated by the State Administration of Foreign Exchange. For example, the structure of "foreign-related income declaration information" is shown in Table 1:
[0056] Table 1
[0057]
[0058]
[0059]
[0060] Step S200: Check the key points of the declared data according to the preset checking rules;
[0061] Specifically, problem points are extracted according to preset verification rules; for example, when a customer declares, transaction code 2 is filled in, but related amount 2 is not filled in, then the output prompt "If transaction code 2 is filled in, related amount 2 must be filled in"; if the sum of the amounts corresponding to the two transaction codes is not equal to the income amount of the basic information, then the output prompt "The sum of the amounts corresponding to the two transaction codes must be equal to the income amount must be equal to the income amount."
[0062] Among them, the verification rules are set by developers according to relevant rules.
[0063] Step S300: reviewing the declared data according to the pre-trained intelligent review model;
[0064] Specifically, for information without clear rules, such as Transaction Remarks 1 and Transaction Remarks 2, this information is a detailed description of the nature of the transaction corresponding to Transaction Code 1 by the reporting entity. When filling in the information, there are differences in the expressions of the reporting entity, and it is necessary to review them one by one to see if there are any discrepancies with the transaction code. In this case, it is necessary to use an intelligent review model to identify the discrepancies between the transaction remarks of the reporting information and the transaction code.
[0065] Among them, the accuracy and completeness review of the declared information elements is completed through step S200 and step S300, and the error details and review results are registered.
[0066] Step S400: Feedback the key point verification results and review results to the business terminal for business personnel to review.
[0067] The result information of the declared information review will be actively pushed to the business personnel, including whether there is any missing declared information, wrong declared information, and detailed information of the error. The push method can be various methods such as email or business system.
[0068] Specifically, the results of the intelligent audit, error points, and discrepancies between the transaction remarks and the transaction code are displayed to bank personnel for auxiliary confirmation, as well as modification instructions when returning the modified declaration information to the customer, as shown in Table 2.
[0069] Table 2
[0070]
[0071] By adopting the above technical solution, RPA technology is used to automatically extract the declared but unreviewed declaration information of customers in the online application system. After intelligent review by the device, the review results are output and confirmed by business personnel. This improves the processing efficiency and the accuracy of the review, ensures timeliness, and eliminates the need for bank business personnel to repeatedly log into the system multiple times in separate compartments.
[0072] In an optional embodiment, the intelligent review model is a FastText model.
[0073] Among them, the FastText model can be called in Python.
[0074] The FastText model inputs a sequence of words (obtained by segmenting the declared data) and outputs the probability that the sequence belongs to different categories, that is, the probability of corresponding to different discrepancy prompts. The words in the sequence form a feature vector, which is mapped to the middle layer through linear transformation, and the middle layer is mapped to the label.
[0075] In an optional embodiment, before step S200, a data preprocessing step may be included, specifically, including data filtering and data normalization, such as filtering out bad pixel data, missing data, etc.
[0076] In an alternative embodiment, see Figure 3 , the step S300 may include the following technical contents:
[0077] Step S310: segmenting the declared data;
[0078] Step S320: Input the word sequence obtained by word segmentation as a feature vector into the pre-trained FastText model to obtain the review result.
[0079] In an optional embodiment, the step S300 may further include: a data preprocessing step;
[0080] Specifically, preprocessing includes data cleaning; data cleaning is to convert all letters to uppercase, remove punctuation marks, and remove some English stop words.
[0081] In an optional embodiment, the method for processing international balance of payments online application data may further include a model training step, specifically including:
[0082] (1) Obtain sample data.
[0083] Specifically, the current stock online application data (i.e., training samples) and the discrepancy prompt information (i.e., the corresponding labels) are extracted;
[0084] Among them, when the data is not standardized, it needs to be labeled. For example, the transaction code contains 822030, but the transaction remarks do not contain the words "non-residents pay overseas" or "non-residents pay foreign exchange" or "non-residents remit overseas" or "non-residents remit overseas", which is marked as "the transaction remarks do not match the transaction code: the transaction remarks under transaction code 822030 should include "non-residents pay overseas" / "non-residents pay foreign exchange" / "non-residents remit overseas" / "non-residents remit overseas"; for another example, the record where the transaction remarks are consistent with the name of the reporting entity is marked as "the transaction remarks cannot be replaced by the name of the reporting entity".
[0085] (2) Data preprocessing.
[0086] Specifically, the sample data is processed and corrected. For example, since the transaction remarks and the transaction code are inconsistent, the transaction remarks are identified in the scenario where the transaction code is set, so the transaction remarks of the sample data need to be split.
[0087] (3) Model training.
[0088] Specifically, the sample data is segmented to obtain a word sequence, and the feature vector composed of the word sequence is input into the pre-established FastText model to output the probability that the word sequence belongs to different categories.
[0089] (4) Model evaluation.
[0090] Use the trained model to predict the samples in the validation set or test set to see whether the trained model meets the requirements. If so, get the trained model for data processing. If not, modify the model parameters or update the training sample set and then retrain.
[0091] In an alternative embodiment, see Figure 4 The method for processing international balance of payments online application data may also include:
[0092] Step S500: Obtaining the review result of the business personnel;
[0093] Bank business personnel confirm the key points of the verification results based on the output of the intelligent audit and provide feedback on the audit results as "pass" or "fail".
[0094] Step S600: Use RPA technology to register the review result as the final review result into the online application system.
[0095] Specifically, through RPA technology, according to the set time interval, the ASOne system is automatically logged in at regular intervals, and based on the final audit results, the customer's declared but unaudited declaration data is queried to complete the automatic review action, that is, the final audit results are registered in the online application system (that is, the above-mentioned ASOne system).
[0096] In an optional embodiment, a robot using RPA technology is used when obtaining the declaration technology using RPA technology and registering the review results to the online application system using RPA technology. Figure 5 , including: script unit 1, process unit 2 and task unit 3.
[0097] The script unit 1 is responsible for script design for each independent process unit of the present invention. The RPA script simulates the user's daily manual operations according to the established steps, such as mouse clicks, keyboard input, copy\paste, etc., completes a series of automated operations, and realizes the automatic processing of a single work step.
[0098] The process unit 2 is used to connect all the script units 1 designed by the present invention to form a complete automated workflow. By executing this process, automatic collection and automatic review of online application data can be achieved.
[0099] Task unit 3 is used to design the operation strategy of process unit 2. Process unit 2 can be set as a task triggered by time or event for automatic execution. Users can configure the trigger time, event, execution times and other information by themselves. For example, set the task to be executed at 12:00 every weekday or every hour; automatically run every time a user logs in to RPA, etc.
[0100] Based on the same inventive concept, the embodiments of the present application also provide an international balance of payments online application data processing device, which can be used to implement the method described in the above embodiments, as described in the following embodiments. Since the principle of solving the problem by the international balance of payments online application data processing device is similar to the above method, the implementation of the international balance of payments online application data processing device can refer to the implementation of the above method, and the repeated parts will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements predetermined functions. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.
[0101] Figure 6 It is the structural frame of the international balance of payments online application data processing device in the embodiment of the present invention. Figure 1 ;like Figure 6 As shown, the international balance of payments online application data processing device specifically includes: an online application data RPA collection module 10, a key point verification module 20, an intelligent review module 30 and an audit result output module 40.
[0102] The online application data RPA collection module 10 uses RPA technology to obtain the application data filled in by the customer on the online application system;
[0103] The key point checking module 20 performs key point checking on the declared data according to preset checking rules;
[0104] The intelligent review module 30 reviews the declared data according to the pre-trained intelligent review model;
[0105] The audit result output module 40 feeds back the key point verification results and the review results to the business terminal so that the business personnel can review them.
[0106] By adopting the above technical solution, RPA technology is used to automatically extract the declared but unreviewed declaration information of customers in the online application system. After intelligent review by the device, the review results are output and confirmed by business personnel. This improves the processing efficiency and the accuracy of the review, ensures timeliness, and eliminates the need for bank business personnel to repeatedly log into the system multiple times in separate compartments.
[0107] In an optional embodiment, the intelligent review model is a FastText model.
[0108] In a further embodiment, the intelligent review module includes: an analysis unit and an intelligent review unit.
[0109] The analysis unit is used to segment the declared data;
[0110] The intelligent review unit is used to input the word sequence obtained by word segmentation as a feature vector into the pre-trained intelligent review model to obtain the review result.
[0111] In an alternative embodiment, see Figure 7 The international balance of payments online application data processing device may also include: a review result acquisition module 50 and an online application data RPA automatic review module 60.
[0112] The review result acquisition module 50 acquires the review result of the business personnel;
[0113] The online application data RPA automatic review module 60 uses RPA technology to register the review result as the final review result into the online application system.
[0114] The devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is an electronic device, and the electronic device may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0115] In a typical example, the electronic device specifically includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the above-mentioned method for processing international balance of payments online application data are implemented.
[0116] Reference below Figure 8 , which shows a schematic structural diagram of an electronic device 600 suitable for implementing an embodiment of the present application.
[0117] like Figure 8 As shown, electronic device 600 includes a central processing unit (CPU) 601, which can perform various appropriate operations and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage portion 608 into a random access memory (RAM) 603. In RAM 603, various programs and data required for the operation of system 600 are also stored. CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to bus 604.
[0118] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed as needed as the storage section 608.
[0119] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above-mentioned method for processing international balance of payments online application data when executed by a processor.
[0120] In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 609 , and / or installed from the removable medium 611 .
[0121] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0122] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.
[0123] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0124] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0125] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0126] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0127] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0128] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0129] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0130] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A method for processing international balance of payments online application data, characterized in that: include: Use RPA technology to obtain the declaration data filled in by customers on the online application system; Conduct key point verification on the declared data according to the preset verification rules; Reviewing the declared data according to a pre-trained intelligent review model, wherein the intelligent review model is a FastText model; Feedback the key point verification and review results to the business terminal for business personnel to review; Obtain the review results from business personnel; Using RPA technology, the review result is registered as the final review result in the online application system; The review of the declared data according to the pre-trained intelligent review model includes: Segmenting the declared data; The word sequence obtained by word segmentation is used as a feature vector and input into the pre-trained FastText model to obtain the review result; The training steps of the intelligent review model include: (1) Obtaining sample data, including extracting the current stock online application data training samples as training samples and the discrepancy prompt information as corresponding labels; Among them, it is necessary to label the data when it is not standardized, including marking the transaction code containing 822030, but the transaction remarks do not contain the words "non-residents pay overseas" or "non-residents pay overseas" or "non-residents remit overseas" or "non-residents remit overseas", as "the transaction remarks do not match the transaction code; the transaction remarks under the transaction code 822030 should contain "non-residents pay overseas" / "non-residents pay overseas" / "non-residents remit overseas" / "non-residents remit overseas"; the records where the transaction remarks are consistent with the name of the reporting entity are marked as "the transaction remarks cannot be replaced by the name of the reporting entity"; (2) Data preprocessing, including processing and correcting the sample data. Since the transaction remarks and transaction codes are inconsistent, the transaction remarks are identified in the scenario where the transaction codes are set, so the transaction remarks of the sample data need to be split. (3) Model training: This includes segmenting sample data to obtain word sequences, inputting the feature vector composed of the word sequence into the pre-established FastText model, and outputting the probability that the word sequence belongs to different categories; (4) Model evaluation: This includes using the trained model to predict samples on the validation set or test set to see whether the trained model meets the requirements. If so, the trained model is obtained and used for data processing. If not, the model parameters are modified or the training sample set is updated and retrained.
2. A device for processing international balance of payments online application data, characterized in that: include: The online application data RPA collection module uses RPA technology to obtain the application data filled in by customers on the online application system; A key point verification module, which performs key point verification on the declared data according to preset verification rules; An intelligent review module reviews the declared data according to a pre-trained intelligent review model, wherein the intelligent review model is a FastText model; The audit result output module feeds back the key point verification results and review results to the business terminal for business personnel to review; Review result acquisition module, to obtain the review results of business personnel; The online application data RPA automatic review module uses RPA technology to register the review results as the final review results into the online application system; The intelligent review module includes: An analysis unit, segmenting the declared data; The intelligent review unit uses the word sequence obtained by word segmentation as a feature vector and inputs it into the pre-trained FastText model to obtain the review result; The training steps of the intelligent review model include: (1) Obtaining sample data, including extracting the current stock online application data training samples as training samples and the discrepancy prompt information as corresponding labels; Among them, it is necessary to label the data when it is not standardized, including marking the transaction code containing 822030, but the transaction remarks do not contain the words "non-residents pay overseas" or "non-residents pay overseas" or "non-residents remit overseas" or "non-residents remit overseas", as "the transaction remarks do not match the transaction code; the transaction remarks under the transaction code 822030 should contain "non-residents pay overseas" / "non-residents pay overseas" / "non-residents remit overseas" / "non-residents remit overseas"; the records where the transaction remarks are consistent with the name of the reporting entity are marked as "the transaction remarks cannot be replaced by the name of the reporting entity"; (2) Data preprocessing, including processing and correcting the sample data. Since the transaction remarks and transaction codes are inconsistent, the transaction remarks are identified in the scenario where the transaction codes are set, so the transaction remarks of the sample data need to be split. (3) Model training: This includes segmenting sample data to obtain word sequences, inputting the feature vector composed of the word sequence into the pre-established FastText model, and outputting the probability that the word sequence belongs to different categories; (4) Model evaluation: This includes using the trained model to predict samples on the validation set or test set to see whether the trained model meets the requirements. If so, the trained model is obtained and used for data processing. If not, the model parameters are modified or the training sample set is updated and retrained.
3. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method for processing international balance of payments online application data described in claim 1 are implemented.
4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for processing international balance of payments online application data described in claim 1 are implemented.
