Cross-border financial service method and system based on big data mining

Abstract

The invention discloses a cross-border financial service method and system based on big data mining. The method comprises the following steps: acquiring a first type of financial data at a data supplier, and acquiring a second type of financial data at a cooperative financial institution; receiving a query question, and if the query question comprises a first preset keyword related to the first type of financial data and the second type of financial data, displaying data corresponding to the first preset keyword; obtaining target data in a cross-border remittance system, a foreign exchange transaction system and a cross-border financial management system in the enterprise through the enterprise service bus; and receiving a query question, if the query question comprises a second preset keyword related to the target data, verifying the target data, marking or rejecting the target data which does not pass the verification, and displaying data corresponding to the second preset keyword and a verification result. The technical problems of low cross-border financial service processing efficiency and insufficient accuracy caused by data islands and information delay are solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and more specifically, to a cross-border financial service method and system based on big data mining. Background Art

[0002] With the acceleration of global trade and capital flows, cross-border financial services such as foreign exchange transactions, international payments, and trade financing have become increasingly frequent and complex. However, the traditional financial system faces technical bottlenecks in information acquisition when responding to these challenges: cross-border business involves various data sources, including internal business system records, real-time market data provided by external data suppliers, and end-of-day reports of cooperative financial institutions. The dispersion of this information and the ever-changing policy environment make it very difficult for customers to obtain and understand this information when conducting cross-border transactions, increasing the difficulty and time cost of business processing. However, these data are often distributed in different systems, forming data islands, which are difficult to integrate and share in real time. In addition, the time delay in data transmission and processing, from submitting a transaction application to completing payment, involves multiple links and different entities, including enterprises, banks, regulators, etc., resulting in banks being unable to obtain the latest market information, affecting the timeliness and accuracy of transaction decisions.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The present application provides a cross-border financial service method and system based on big data mining, so as to at least solve the technical problems of low efficiency and insufficient accuracy in cross-border financial service processing caused by data silos and information delays.

[0005] According to one aspect of the present application, a cross-border financial service method based on big data mining is provided, comprising: obtaining a first type of financial data from a data supplier, and obtaining a second type of financial data from a cooperative financial institution, wherein the first type of financial data includes at least one of the following: real-time foreign exchange quotes, international stock market prices, global interest rate data, and real-time metal prices, and the second type of financial data includes at least: end-of-day trading reports; receiving a query question, and if the query question includes a first preset keyword related to the first type of financial data and the second type of financial data, displaying data corresponding to the first preset keyword; obtaining target data in the cross-border remittance system, foreign exchange trading system, and cross-border financial management system within the enterprise through an enterprise service bus; receiving a query question, and if the query question includes a second preset keyword related to the target data, verifying the target data, and marking or rejecting the target data that fails the verification, and displaying the data corresponding to the second preset keyword and the verification result.

[0006] Optionally, obtaining the first category of financial data from a data supplier and obtaining the second category of financial data from a cooperative financial institution includes: obtaining the first category of financial data from the data supplier through an application program interface; determining a storage location of the second category of financial data at the cooperative financial institution, and determining a data extraction method for the second category of financial data based on the storage location; determining a first time interval for extracting the second category of financial data, and when a preset extraction time is reached, accessing the storage location based on the data extraction method, wherein if the second category of financial data is stored in a file transfer protocol server of the cooperative financial institution, accessing the file transfer protocol server through a pre-registered username and password, and if the second category of financial data is stored in a database of the cooperative financial institution, accessing the file transfer protocol server through a pre-configured username and password. The connection string and authentication information are used to access the database; after successful access, if the storage location is a file transfer protocol server, navigate to the directory storing the second type of financial data, use the download function to download the second type of financial data to the target storage location, and if the storage location is a database, query the table or view storing the second type of financial data, use the query statement to extract the second type of financial data from the table or view, and transmit it to the target storage location through the network; obtain error information that occurs in the process of connecting to the data source, extracting data, and storing data, and perform target actions for the error information, wherein the error information includes: network failure, insufficient authority, and data format error, and the target actions include: recording an error log, sending an alarm message, and trying to re-extract data.

[0007] Optionally, target data in the cross-border remittance system, foreign exchange trading system and cross-border financial management system within the enterprise are obtained through the enterprise service bus, including: configuring a first connection string corresponding to the cross-border remittance system in the enterprise service bus, connecting the cross-border remittance system through the first connection string, and obtaining the target data generated in the cross-border remittance system, wherein the first connection string includes the IP address information, port information, database name information, and first authentication information of the cross-border remittance system, and the first authentication information includes: a digital certificate and biometric information; configuring a second connection string corresponding to the foreign exchange trading system in the enterprise service bus, connecting the foreign exchange trading system through the second connection string, and obtaining the target data generated in the foreign exchange trading system, wherein the second connection string includes the IP address information, port information, database name information, and second authentication information of the foreign exchange trading system, and the second authentication information includes: a dynamic password; configuring a third connection string corresponding to the cross-border financial management system in the enterprise service bus, connecting the cross-border financial management system through the third connection string, and obtaining the target data generated in the cross-border financial management system, wherein the third connection string includes the IP address information, port information, database name information, and third authentication information of the cross-border financial management system, and the third authentication information includes: a user name and a password.

[0008] Optionally, verify the target data and mark or reject the target data that fails the verification, including: verifying whether the remittance amount in the cross-border remittance transaction data in the cross-border remittance system is within a first numerical range, whether the account formats of the remittance object and the recipient are correct, and verifying whether the cross-border trade financing transaction data is complete, and when the cross-border trade financing transaction data is incomplete, searching for missing document data in the business system associated with the transaction number in the cross-border trade financing transaction data; determining the data format type of each type of target data in the foreign exchange trading system, wherein the data format type of each type of target data includes: currency data is a first preset format string, and date data is a second preset format string; setting a first verification rule based on the data format type, and when the target data is updated, triggering a verification action based on the first verification rule, marking or rejecting the target data that does not comply with the first verification rule; determining the second numerical range of the exchange rate data in the foreign exchange trading system based on market conditions and currency types, and verifying whether the exchange rate data is within the second numerical range; According to the minimum and maximum subscription threshold ranges of different wealth management products, determine the third numerical range of the wealth management amount data in the cross-border wealth management system, and determine the fourth numerical range of the expected annualized rate of return in the cross-border wealth management system according to the market conditions and product risk levels; verify whether the wealth management amount data is within the third numerical range, and verify whether the expected annualized rate of return is within the fourth numerical range; determine the association relationship of target data in the cross-border wealth management system, wherein the association relationship includes: the matching relationship between customer information and the wealth management products purchased, the association between the wealth management amount and the customer's asset status and risk tolerance, and the logical relationship between the investment period of the wealth management product and the expected rate of return; determine the second verification rule based on the association relationship, wherein the second verification rule includes: for the customer's purchase of wealth management products, verify whether the customer's risk tolerance matches the risk level of the purchased product, and whether the wealth management amount is within the customer's available funds; set a second verification rule based on the association relationship, and when the target data is updated, trigger a verification action based on the second verification rule, and mark or reject the target data that does not meet the second verification rule.

[0009] Optionally, the cross-border financial service method based on big data mining also includes: based on historical cross-border transaction data in the cross-border remittance system, foreign exchange trading system and cross-border financial management system, training a machine learning model for determining the risk assessment index of the current cross-border transaction data, and generating an alarm message when the risk assessment index of the current cross-border transaction data is greater than a preset threshold, wherein the above-mentioned training process includes: extracting historical cross-border transaction data from the cross-border remittance system, foreign exchange trading system and cross-border financial management system by extraction, conversion and loading, and loading the historical cross-border transaction data into a data warehouse; selecting a first preset number of first data in the data warehouse, removing duplicate data in the first data, correcting erroneous data in the first data and filling missing data in the first data, to obtain second data; classifying and labeling the second data according to the transaction type dimension, transaction area dimension and transaction time dimension to obtain third data, wherein the labeling content includes: whether the transaction has risks and the risk type; extracting target features related to the risk from the third data, wherein the target features include at least one of the following: transaction amount, transaction frequency, credit rating of the transaction object, and foreign exchange rate fluctuation range; using the target features to train the machine learning model, during the training process, calculating the difference between the predicted result and the actual label according to the loss function of the model, adjusting the parameters of the model through the stochastic gradient descent algorithm to minimize the loss function, so that the model continuously learns the risk feature pattern in the data, and when the loss function meets the preset conditions, a machine learning model that has completed the training is obtained.

[0010] Optionally, the cross-border financial service method based on big data mining also includes: selecting a second preset number of first data in a data warehouse; performing one-hot encoding conversion on non-numeric features in the first data and normalizing the numerical features in the first data to obtain second data; clustering the second data based on at least the transaction type dimension, the transaction area dimension, and the transaction time dimension to obtain clustering results, and according to the clustering results, dividing users into different transaction behavior clusters to obtain a set of transaction behavior clusters; mining transaction patterns with a frequency of occurrence greater than a preset frequency from the time series data of historical cross-border transaction data, and determining, based on the transaction patterns, the user's selection order and association relationship for different cross-border transaction products at different time points; integrating the transaction behavior cluster set, selection order, and association relationship to obtain a cross-border transaction habit portrait; obtaining the user's current transaction behavior, and generating target alarm information when the similarity between the current transaction behavior and the historical transaction behavior in the cross-border transaction habit portrait is less than a first preset threshold.

[0011] According to another aspect of the present application, a cross-border financial service system based on big data mining is also provided, including: a first acquisition module, used to obtain a first type of financial data from a data supplier, and to obtain a second type of financial data from a cooperative financial institution, wherein the first type of financial data includes at least one of the following: real-time foreign exchange quotes, international stock market prices, global interest rate data, real-time metal prices, and the second type of financial data includes at least: end-of-day trading reports; a first receiving module, used to receive query questions, and if the query questions include first preset keywords related to the first type of financial data and the second type of financial data, display data corresponding to the first preset keywords; a second acquisition module, used to obtain target data in the cross-border remittance system, foreign exchange trading system and cross-border financial management system within the enterprise through the enterprise service bus; a second receiving module, used to receive query questions, if the query questions include second preset keywords related to the target data, verify the target data, and mark or reject the target data that fails the verification, and display the data corresponding to the second preset keywords and the verification results.

[0012] According to another aspect of the present application, a non-volatile storage medium is also provided, the storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the above cross-border financial service method based on big data mining.

[0013] According to another aspect of the present application, there is also provided an electronic device, comprising: a memory and a processor, the processor being used to run a program stored in the memory, wherein the above cross-border financial service method based on big data mining is executed when the program is running.

[0014] According to another aspect of the present application, a computer program is also provided, wherein when the computer program is executed by a processor, the above cross-border financial service method based on big data mining is implemented.

[0015] According to another aspect of the present application, a computer program product is also provided, which includes a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned cross-border financial service method based on big data mining is implemented.

[0016] In the present application, a first type of financial data is obtained from a data supplier, and a second type of financial data is obtained from a cooperative financial institution, wherein the first type of financial data includes at least one of the following: real-time foreign exchange quotes, international stock market prices, global interest rate data, and real-time metal prices, and the second type of financial data includes at least: end-of-day trading reports; receiving query questions, if the query questions include first preset keywords related to the first type of financial data and the second type of financial data, displaying data corresponding to the first preset keywords; obtaining target data in the cross-border remittance system, foreign exchange trading system, and cross-border financial management system within the enterprise through the enterprise service bus; receiving query questions, if the query questions include second preset keywords related to the target data, verifying the target data, and marking or rejecting the target data that has not passed the verification, and displaying the data corresponding to the second preset keywords and the verification results. The purpose of optimizing data processing is achieved, thereby realizing the technical effect of improving the response speed of cross-border financial services and the accuracy of information, and further solving the technical problems of low efficiency and insufficient accuracy of cross-border financial service processing due to data islands and information delays. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 is a flow chart of a cross-border financial service method based on big data mining according to an embodiment of the present application;

[0019] Figure 2 is a structural diagram of a cross-border financial service system based on big data mining according to an embodiment of the present application;

[0020] Figure 3 It is a hardware structure block diagram of a computer terminal of a cross-border financial service method based on big data mining according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] 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.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device 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 devices.

[0023] In the related art, traditional data acquisition methods often rely on regular file transfers or manual queries, and the evaluation model is based on static historical data. Therefore, there is a problem of being unable to obtain market dynamics in real time and dynamically evaluate risk factors. In order to solve this problem, the embodiments of the present application provide relevant solutions, which are described in detail below.

[0024] According to an embodiment of the present application, a method embodiment of a cross-border financial service method based on big data mining is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] Figure 1 is a flow chart of a cross-border financial service method based on big data mining according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0026] Step S102, obtaining the first type of financial data from the data supplier and obtaining the second type of financial data from the cooperating financial institution, wherein the first type of financial data includes at least one of the following: real-time foreign exchange quotes, international stock market prices, global interest rate data, real-time metal prices, and the second type of financial data includes at least: end-of-day transaction reports.

[0027] Specifically, for the first type of financial data, an API interface is established with international financial data suppliers to achieve direct access to the first type of financial data, including but not limited to real-time foreign exchange quotes, international stock market prices, global interest rate data, real-time metal prices, etc. And through subscription services, the real-time and accuracy of the data are ensured. For the second type of financial data, a data sharing agreement is signed with the partner bank to obtain the second type of financial data, such as end-of-day transaction reports, through the SWIFT network or a dedicated cross-border data exchange system, while ensuring the security and compliance of data transmission and achieving periodic updates of data. The first and second types of financial data obtained are then integrated to build a cross-border transaction data warehouse, using a layered architecture to store data, including the original data layer, the cleaning and conversion layer, and the aggregation layer to ensure the integrity of the data.

[0028] Step S104, receiving a query question, and if the query question includes a first preset keyword related to the first category of financial data and the second category of financial data, displaying data corresponding to the first preset keyword.

[0029] In step S104, based on the natural language processing model of deep learning, the first preset keyword in the query question is identified. The keywords include but are not limited to "exchange rate", "metal price", etc. When the user enters the query question, the question text is parsed and the first preset keyword is identified. Subsequently, the first type of financial data corresponding to the keyword is extracted from the integrated data warehouse and displayed, such as a real-time exchange rate trend chart, a global interest rate trend table, a metal price list, etc.

[0030] Step S106, obtaining target data in the cross-border remittance system, foreign exchange transaction system and cross-border financial management system within the enterprise through the enterprise service bus.

[0031] Specifically, the bank's internal cross-border remittance system, foreign exchange trading system and cross-border financial management system are deeply integrated through ESB to achieve real-time data sharing and transmission. When data is updated, ESB is responsible for data format conversion and routing to ensure that the target data can be accurately transmitted to the relevant system. The internal target data obtained through ESB is standardized, and the data format and encoding are unified, such as unifying all transaction times into the format of "YYYY-MM-DD HH:MM:SS", unifying transaction amounts into specific currency units, and performing data cleaning to remove outliers or incomplete information to improve data quality.

[0032] Step S108, receiving a query question. If the query question includes a second preset keyword related to the target data, verify the target data, mark or reject the target data that fails the verification, and display the data corresponding to the second preset keyword and the verification result.

[0033] In step S108, after receiving the query question, the second preset keyword related to the target data is identified, such as "account balance" and "transaction status". Based on the keywords, the target data is extracted from the data warehouse for verification, and the automatic verification mechanism is enabled, including checks such as data format correctness, numerical range compliance, and historical record consistency. For example, a reasonable data range and value domain are set to check whether the target data meets expectations. If the verification fails, the target data that has not passed the verification is automatically marked or rejected, and the abnormal reason is recorded, such as insufficient account balance, illegal transaction status, etc. At the same time, an abnormal data processing process is provided, such as notifying business personnel to review, requiring users to supplement information, etc., to ensure the accuracy of the data and the compliance of the operation. When the second preset keyword is included in the query question, not only the target data corresponding to the keyword is displayed, but also the verification results, such as "sufficient account balance" and "normal transaction status", or abnormal data tags and specific abnormal information are displayed to enhance the understanding of the data status by business personnel and customers.

[0034] According to the above steps, by obtaining the first type of financial data from the data supplier and the second type of financial data from the cooperative financial institution, wherein the first type of financial data includes at least one of the following: real-time foreign exchange quotes, international stock market prices, global interest rate data, real-time metal prices, and the second type of financial data includes at least: end-of-day trading reports; receiving query questions, if the query questions include first preset keywords related to the first type of financial data and the second type of financial data, displaying data corresponding to the first preset keywords; obtaining target data in the cross-border remittance system, foreign exchange trading system and cross-border financial management system within the enterprise through the enterprise service bus; receiving query questions, if the query questions include second preset keywords related to the target data, verifying the target data, and marking or rejecting the target data that fails the verification, and displaying the data corresponding to the second preset keywords and the verification results, the purpose of optimizing data processing is achieved, thereby achieving the technical effect of improving the response speed of cross-border financial services and the accuracy of information.

[0035] The following Figure 1 The steps shown are exemplary and explanatory.

[0036] According to some optional embodiments of the present application, obtaining the first category of financial data from a data supplier and obtaining the second category of financial data from a cooperative financial institution can be achieved through the following steps: obtaining the first category of financial data from a data supplier through an application program interface; determining the storage location of the second category of financial data at the cooperative financial institution, and determining a data extraction method for the second category of financial data based on the storage location; determining a first time interval for extracting the second category of financial data, and when a preset extraction time is reached, accessing the storage location based on the data extraction method, wherein, if the second category of financial data is stored in a file transfer protocol server of the cooperative financial institution, accessing the file transfer protocol server through a pre-registered username and password; if the second category of financial data is stored in the data of the cooperative financial institution, database, access the database through the preconfigured connection string and authentication information; after successful access, if the storage location is a file transfer protocol server, navigate to the directory storing the second type of financial data, use the download function to download the second type of financial data to the target storage location, if the storage location is a database, query the table or view storing the second type of financial data, use the query statement to extract the second type of financial data from the table or view, and transmit it to the target storage location through the network; obtain error information that occurs in the process of connecting to the data source, extracting data, and storing data, and perform target actions for the error information, wherein the error information includes: network failure, insufficient authority, and data format error, and the target actions include: recording an error log, sending an alarm message, and trying to re-extract data.

[0037] In the above embodiment, first, data suppliers are selected, which provide services such as real-time foreign exchange quotes, international stock market prices, global interest rate data, and real-time metal prices. When technically connecting with the selected data supplier, API interface parameters are configured, including access tokens, data request formats, return formats, etc., to ensure data transmission security and format consistency. According to business needs, data request logic is defined, such as requesting real-time foreign exchange quotes for specific currency pairs, querying historical market price data for a certain stock, etc. According to the defined data request logic, the first category of financial data is obtained from the data supplier in real time through the API interface and stored in a local data warehouse or database.

[0038] Then, establish a data sharing relationship with cooperative banks and other financial institutions, obtain the second type of financial data such as end-of-day transaction reports and settlement data, and confirm the storage location of the second type of financial data, which can be in the form of files on the FTP server, tables or views in the database, etc. It should be noted that if the second type of financial data is stored on the FTP server, design the FTP access logic, including identity authentication using the pre-registered user name and password. If the data is stored in the database, configure the database connection string, including the server address, port, database name, user name and password, and design SQL query statements to extract data from specific tables or views. In addition, set scheduled tasks according to the frequency of data updates, such as extracting the end-of-day transaction report data of cooperative financial institutions at 23:00 every night.

[0039] When the preset scheduled task execution time is reached, the pre-registered user name and password are used to log in to the FTP server, and the second category of financial data is stored in the directory according to the storage location. Then, the download function of FTP is used to download the second category of financial data files to the target storage location within the bank, such as a specific data warehouse directory. If the data is stored in the database of the cooperative financial institution, the pre-configured connection string and authentication information are used to establish a database connection, execute SQL query statements, extract the second category of financial data from the table or view, and transmit the data extracted from the database to the target storage location within the bank through the network.

[0040] Finally, in the process of data extraction, error information is captured, such as network failure (unable to connect to the FTP server or database), insufficient permissions (unable to access specific directories or query data), data format errors (data file format does not meet expectations), etc. For the captured error information, predefined target actions are executed, such as recording detailed error logs, sending alarm messages to relevant personnel, or trying to re-establish the connection and re-extract data to ensure the continuity and integrity of data acquisition.

[0041] Through the above steps, it is possible to obtain the first type of financial data from data suppliers in real time, and to extract the second type of financial data from cooperative financial institutions on a regular and secure basis. In addition, various errors that occur during the data acquisition process are effectively monitored and handled, ensuring the stability and reliability of cross-border financial data processing.

[0042] According to some other optional embodiments of the present application, obtaining target data in the cross-border remittance system, foreign exchange trading system and cross-border financial management system within the enterprise through the enterprise service bus can be achieved through the following steps: configuring a first connection string corresponding to the cross-border remittance system in the enterprise service bus, connecting the cross-border remittance system through the first connection string, and obtaining the target data generated in the cross-border remittance system, wherein the first connection string includes the IP address information, port information, database name information, and first authentication information of the cross-border remittance system, and the first authentication information includes: digital certificate and biometric information; configuring a second connection string corresponding to the foreign exchange trading system in the enterprise service bus, connecting the foreign exchange trading system through the second connection string, and obtaining the target data generated in the foreign exchange trading system, wherein the second connection string includes the IP address information, port information, database name information, and second authentication information of the foreign exchange trading system, and the second authentication information includes: dynamic password; configuring a third connection string corresponding to the cross-border financial management system in the enterprise service bus, connecting the cross-border financial management system through the third connection string, and obtaining the target data generated in the cross-border financial management system, wherein the third connection string includes the IP address information, port information, database name information, and third authentication information of the cross-border financial management system, and the third authentication information includes: user name and password.

[0043] In the above embodiment, first, obtain the basic information of the cross-border remittance system, such as the IP address, port number, database name, and the first authentication information required by the system, including digital certificates and biometric information (such as fingerprint recognition, facial recognition, etc.). In the management interface of the ESB, configure the first connection string according to the IP address, port, database name, and other information of the cross-border remittance system. At the same time, add the digital certificate and biometric information to the security authentication configuration of the ESB to ensure secure identity authentication during data transmission. Use the configured first connection string to try to connect to the cross-border remittance system and check whether the connection is successfully established. Specifically, by sending a test request, verify whether the authentication process of the digital certificate and biometric information is smooth to ensure the stability and security of subsequent data acquisition.

[0044] After the connection is successful, a data request is sent to the cross-border remittance system through ESB to request specific target data, such as cross-border remittance transaction records, account balance information, etc. After receiving the data request, the cross-border remittance system encrypts the target data and transmits it to ESB. After receiving the data, ESB decrypts and converts the data format to ensure that the data can be correctly read and processed by other internal systems and modules.

[0045] Then, configure the second connection string corresponding to the foreign exchange trading system in the ESB. Specifically, obtain the basic information of the foreign exchange trading system, such as the IP address, port number, database name, and the second authentication information required by the system, such as the dynamic password. Then, in the management interface of the ESB, configure the second connection string, add the generation and verification mechanism of the dynamic password to the security authentication configuration of the ESB, use the configured second connection string to try to connect to the foreign exchange trading system, send a test request and verify the authentication process of the dynamic password to ensure a stable connection and secure data transmission.

[0046] After the connection is successful, a data request is sent to the foreign exchange trading system through ESB to request foreign exchange trading data, such as foreign exchange trading records, real-time exchange rate information, etc. It should be noted that during the data transmission process, the ESB and the foreign exchange trading system perform real-time authentication through dynamic passwords to ensure that only authenticated requests can obtain target data, thereby enhancing data security. The foreign exchange trading system transmits the encrypted target data to ESB, which decrypts and converts the format, and stores or passes the data to other modules after standardization, such as the real-time data analysis and prediction module.

[0047] Finally, configure the third connection string corresponding to the cross-border financial management system in ESB. Specifically, obtain the basic information of the cross-border financial management system, such as the IP address, port number, database name, and the third authentication information required by the system, such as the user name and password. In the management interface of ESB, configure the third connection string, and add the authentication mechanism of the user name and password to the security authentication configuration of ESB to ensure the authentication security of each data request. Then use the configured third connection string to try to connect to the cross-border financial management system, and ensure the stability and security of the connection and data transmission by sending a test request and verifying the authentication process of the user name and password. After the connection is successful, send a data request to the cross-border financial management system through ESB to request to obtain target data such as cross-border financial management product information and customer asset status. During the data transmission process, ESB and the cross-border financial management system are authenticated by the user name and password to ensure the legitimacy of the data request and prevent unauthorized access. The cross-border financial management system transmits the encrypted data to ESB, which decrypts and converts the format, and uniformly stores or passes the data to other modules, such as the intelligent interaction module, to support services such as customer consultation and product recommendation.

[0048] Through the above steps, the connection with the cross-border remittance system, foreign exchange trading system, and cross-border financial management system can be configured safely and efficiently in the enterprise service bus, and the target data can be safely acquired and processed, providing a solid data foundation for the intelligentization and automation of cross-border financial services. At the same time, by adopting a multi-level security authentication mechanism, such as digital certificates, biometrics, dynamic passwords, and usernames and passwords, the security of data during transmission and storage is ensured, meeting the compliance requirements of the financial industry.

[0049] In some optional embodiments of the present application, verifying the target data and marking or rejecting the target data that fails the verification can be achieved through the following steps: verifying whether the remittance amount in the cross-border remittance transaction data in the cross-border remittance system is within a first numerical range, whether the account formats of the remittance object and the recipient are correct, and verifying whether the cross-border trade financing transaction data is complete, and when the cross-border trade financing transaction data is incomplete, searching for missing document data in the business system associated with the transaction number in the cross-border trade financing transaction data; determining the data format type of each type of target data in the foreign exchange trading system, wherein the data format type of each type of target data includes: currency data is a first preset format string, and date data is a second preset format string; setting a first verification rule based on the data format type, and when the target data is updated, triggering a verification action based on the first verification rule, marking or rejecting the target data that does not comply with the first verification rule; determining the second numerical range of the exchange rate data in the foreign exchange trading system based on market conditions and currency types, and verifying whether the exchange rate data is in the first preset format string; The method comprises the following steps: determining the third numerical range of the wealth management amount data in the cross-border wealth management system according to the minimum and maximum subscription threshold ranges of different wealth management products, and determining the fourth numerical range of the expected annualized rate of return in the cross-border wealth management system according to the market conditions and the risk level of the products; verifying whether the wealth management amount data is within the third numerical range, and verifying whether the expected annualized rate of return is within the fourth numerical range; determining the association relationship of the target data in the cross-border wealth management system, wherein the association relationship includes: the matching relationship between the customer information and the wealth management products purchased, the association between the wealth management amount and the customer's asset status and risk tolerance, and the logical relationship between the investment period of the wealth management product and the expected rate of return; determining the second verification rule according to the association relationship, wherein the second verification rule includes: for the customer's purchase of wealth management products, verifying whether the customer's risk tolerance matches the risk level of the purchased product, and whether the wealth management amount is within the customer's available funds; setting the second verification rule based on the association relationship, and triggering the verification action based on the second verification rule when the target data is updated, and marking or rejecting the target data that does not meet the second verification rule.

[0050] In the above embodiment, first, the cross-border remittance transaction data in the cross-border remittance system is obtained, including the remittance amount, the remittance object and the account information of the recipient. Define the first numerical range, and determine the reasonable range according to the business rules and historical data analysis, such as the small transaction range is 100 to 10,000, and the large transaction range is more than 100,000. Then check whether the remittance amount is within the first numerical range. If it exceeds the range, it is marked as an abnormal transaction, the transaction is suspended, and an alarm is triggered to notify the business personnel to handle it. At the same time, define the correct account format, such as international bank accounts should follow the SWIFT format or the bank account rules of a specific country, and check whether the account format of the remittance object and the recipient is correct. Data that does not conform to the format will be marked and required to be supplemented or corrected.

[0051] Then, verify the cross-border trade financing transaction data. Specifically, obtain the transaction data in the cross-border trade financing system, including transaction numbers, document information, etc. Check the integrity of the transaction data, especially key document information, such as bills of lading, invoices, etc. When the data is incomplete, link it to the relevant business system (such as supply chain management system, customs declaration system, etc.) through the transaction number to automatically find the missing document data. If the data is still missing after the search, the system will mark the transaction data as incomplete, suspend the corresponding financing operations, and notify the business personnel to complete the document information.

[0052] Next, determine the data format type of each type of target data, such as currency data should be a string in the format of "XXX.XXX", and date data should be a string in the format of "YYYY-MM-DD". Specifically, set the first verification rule, including data format verification and value range verification. When the target data is updated, these verification rules are triggered, such as automatically checking whether all currency data uses the preset format and whether the date data conforms to the preset format. Non-compliant data will be marked or rejected. At the same time, based on market conditions and currency types, determine the second value range for verifying exchange rate data. If the exchange rate exceeds the normal fluctuation range, it will be marked as abnormal and trigger further review.

[0053] Finally, the third numerical range is determined based on the minimum and maximum subscription thresholds of different wealth management products. At the same time, the fourth numerical range of the expected annualized rate of return is determined in combination with the market conditions and the product risk level. Specifically, check whether the wealth management amount data is within the third numerical range and whether the expected annualized rate of return is within the fourth numerical range. Data outside the range will be marked as abnormal and related operations will be suspended. At the same time, determine the association between target data, such as the matching of customer information and the purchased wealth management products, the association between the wealth management amount and the customer's asset status and risk tolerance, and the logical relationship between the investment period and the expected rate of return. Based on these associations, define the second verification rule, for example, check whether the risk tolerance of the customer matches the product risk level when purchasing the wealth management product, and whether the wealth management amount does not exceed a certain proportion of the customer's available funds. Specifically, set an automatic verification mechanism based on the second verification rule. When the target data in the cross-border wealth management system is updated, the verification is triggered, and the data that does not meet the rules is marked or rejected to ensure that all wealth management operations meet the interests of customers and the compliance requirements of the bank.

[0054] Through the above steps, various target data in the cross-border financial system can be verified comprehensively and in real time, effectively preventing data errors and abnormal operations, and ensuring the accuracy and security of cross-border financial business.

[0055] As some optional embodiments of the present application, the above-mentioned cross-border financial service method based on big data mining also includes the following steps: based on historical cross-border transaction data in the cross-border remittance system, foreign exchange trading system and cross-border financial management system, training a machine learning model for determining the risk assessment index of the current cross-border transaction data, and generating an alarm message when the risk assessment index of the current cross-border transaction data is greater than a preset threshold, wherein the above-mentioned training process includes: extracting historical cross-border transaction data from the cross-border remittance system, foreign exchange trading system and cross-border financial management system by extraction, conversion and loading, and loading the historical cross-border transaction data into a data warehouse; selecting a first preset number of first data in the data warehouse, removing duplicate data in the first data, correcting erroneous data in the first data, and filling in the first data. The missing data is obtained to obtain the second data; the second data is classified and labeled according to the transaction type dimension, the transaction area dimension and the transaction time dimension to obtain the third data, wherein the annotation content includes: whether the transaction has risks and the risk type; the target features related to the risk are extracted from the third data, wherein the target features include at least one of the following: transaction amount, transaction frequency, credit rating of the transaction object, and foreign exchange rate fluctuation range; the machine learning model is trained using the target features, and during the training process, the difference between the predicted result and the true annotation is calculated according to the loss function of the model, and the parameters of the model are adjusted through the stochastic gradient descent algorithm to minimize the loss function, so that the model continuously learns the risk feature pattern in the data, and when the loss function meets the preset conditions, a machine learning model that has completed the training is obtained.

[0056] In the above embodiment, first, through ESB or direct database connection, historical remittance records are extracted from the cross-border remittance system, including transaction amount, time, remittance and payment object information, etc.; historical foreign exchange transaction data, such as transaction currency pairs, transaction volume, transaction time, etc. are extracted from the foreign exchange transaction system; and the transaction history of financial products is obtained from the cross-border financial management system, including financial management amount, expected rate of return, transaction party information, product type, etc. The extracted historical transaction data is converted into a format, such as converting the transaction time uniformly into the format of "YYYY-MM-DD HH:MM:SS". Specifically, duplicate records in the data are checked and removed to avoid deviations during model training; erroneous data are corrected, such as repairing unreasonable transaction amounts, etc.; missing data are filled using prediction models or statistical methods to ensure data integrity. The cleaned and converted data is loaded into the enterprise-level data warehouse to provide a unified data storage system for subsequent data analysis and model training.

[0057] Then, select a certain amount (the first preset amount) of historical transaction data in the data warehouse as the data set for training the model, use the deduplication function provided by the data warehouse, or write SQL query statements to identify and remove duplicate records in the data set. Correct or exclude the erroneous data found, such as abnormal transaction amounts, illegal transaction object information, etc., to ensure data quality. Use the statistical function in the data warehouse, or use machine learning methods, such as predicting missing values ​​based on other features, to fill in the missing values ​​in the data set. Classify the data by transaction type (remittance, foreign exchange transactions, financial product transactions), transaction area, transaction time and other dimensions, and have professionals mark the data to determine whether each transaction has risks and the type of risk, such as exchange rate risk, credit risk, etc.

[0058] Finally, target features related to risk assessment are extracted from the labeled data, including but not limited to transaction amount, transaction frequency, credit rating of the transaction object, foreign exchange rate fluctuation range, etc. The machine learning model is trained using the extracted features and labeled risk labels. Specifically, supervised learning algorithms such as logistic regression, support vector machine, random forest, neural network, etc. are used to select the appropriate model according to the size of the data set and the feature type. During the training process, the difference between the model prediction results and the actual labeled risk type is evaluated by calculating the loss function of the model (such as binary cross entropy loss). The model parameters are adjusted using stochastic gradient descent or other optimization algorithms to minimize the loss function so that the model can better fit the risk feature pattern in the data. When the model training meets the preset conditions (such as the loss function is stable and the performance of the validation set meets the standard), the training is stopped, the model parameters are saved, and the machine learning model that has completed the training is obtained. When new cross-border transaction data enters the system, the data is cleaned and converted to conform to the model input format, and the trained risk assessment model is used to analyze the current cross-border transaction data in real time, and the risk assessment indicators are calculated based on the transaction characteristics. Specifically, the threshold of the risk assessment indicator is set. When the indicator value exceeds the preset threshold, the system automatically generates an alarm message, including key information such as transaction details, risk type, indicator value, etc., and pushes it to the corresponding business department or management personnel to facilitate rapid response and action.

[0059] Through the above steps, an accurate risk assessment model can be trained based on historical transaction data, and potential risks can be timely identified and warned in real-time transactions, effectively improving the security and compliance of cross-border financial business.

[0060] In some optional embodiments of the present application, the above-mentioned cross-border financial service method based on big data mining also includes the following steps: selecting a second preset number of first data in the data warehouse; performing one-hot encoding conversion on non-numeric features in the first data and normalizing the numerical features in the first data to obtain second data; clustering the second data based on at least the transaction type dimension, the transaction area dimension and the transaction time dimension to obtain clustering results, and according to the clustering results, dividing the users into different transaction behavior clusters to obtain a transaction behavior cluster set; mining transaction patterns with a frequency of occurrence greater than a preset frequency from the time series data of historical cross-border transaction data, and determining the user's selection order and association relationship for different cross-border transaction products at different time points based on the transaction pattern; integrating the transaction behavior cluster set, selection order and association relationship to obtain a cross-border transaction habit portrait; obtaining the user's current transaction behavior, and generating target alarm information when the similarity between the current transaction behavior and the historical transaction behavior in the cross-border transaction habit portrait is less than a first preset threshold.

[0061] In the above embodiment, first, a second preset amount of historical transaction data is selected in the data warehouse, which covers various cross-border business types such as cross-border remittances, foreign exchange transactions, cross-border financial management, and transaction information in different regions of the world. For non-numerical features in the first data, such as transaction type (remittance, foreign exchange transactions, financial management, etc.), transaction area (country, region code), transaction object, etc., unique hot encoding is used to convert them into numerical features so that they can be processed by the machine learning algorithm. For example, the transaction type "remittance" is encoded as [1,0,0], "foreign exchange transactions" are encoded as [0,1,0], and "financial management" is encoded as [0,0,1]. The numerical features in the first data, such as transaction amount, transaction frequency, timestamp, etc., are normalized, and all numerical features are scaled to the same numerical range, usually between [0,1]. Normalization can use methods such as Min-Max scaling and Z-Score standardization to ensure that the features will not deviate due to different dimensions or ranges during model training.

[0062] Then, using the second data after one-hot encoding conversion and normalization, select features related to transaction behavior, such as transaction type code, transaction area code, transaction time, transaction amount, transaction frequency, etc. Select a clustering algorithm suitable for processing multi-dimensional data, such as K-Means, DBSCAN or spectral clustering, for clustering analysis of the second data. According to business needs and data characteristics, select the optimal clustering algorithm and parameters, such as K value. Perform clustering processing on the second data to obtain clustering results, and divide users into different transaction behavior clusters to form a set of transaction behavior clusters. Analyze the clustering results and identify the characteristics of different clusters, such as a cluster of users prefer to make small cross-border remittances in the morning on weekdays, and another cluster of users prefer foreign exchange transactions, and the transaction frequency and transaction amount are relatively high. Extract time series data from historical cross-border transaction data, such as the frequency of users' cross-border transactions, changes in amount, etc. Use time series analysis methods (such as ARIMA, seasonal decomposition, etc.) to mine seasonal, trend and cyclical characteristics in the data. Specifically, based on time series data, we identify transaction patterns that occur more frequently than a preset frequency, such as users conducting large foreign exchange transactions at the beginning of each month and increasing their purchases of wealth management products at the end of each year. We then analyze the patterns of the transaction patterns to determine the order and correlation of users' selection of different cross-border transaction products at different time points.

[0063] Finally, the information such as transaction behavior cluster set, selection order and association relationship is integrated to form a portrait of the user's cross-border transaction habits. The portrait includes the classification, characteristics and preferences of the user's transaction behavior, as well as the time series pattern of historical transaction behavior. The cross-border transaction habit portrait is regularly updated with new historical transaction data to reflect the changes in the user's transaction behavior and maintain the timeliness and accuracy of the portrait. Specifically, the user's current transaction behavior data is obtained in real time, including information such as transaction type, transaction area, transaction time, and transaction amount. The current transaction behavior data is preprocessed in the same way, including the unique hot encoding of non-numeric features and the normalization of numerical features, so that its format is consistent with the historical data and can be processed by the model. Using the constructed cross-border transaction habit portrait, the similarity between the user's current transaction behavior and historical transaction behavior is analyzed. The similarity can be determined by calculating the distance between the two sets of data (such as Euclidean distance, cosine similarity). And set a first preset threshold. If the similarity between the current transaction behavior and the historical transaction behavior is less than the first preset threshold, it indicates that the transaction behavior deviates from the normal pattern and there is risk or abnormality. The system will automatically generate target alarm information and take corresponding processing measures based on the severity and type of the alarm, such as further verifying transaction information, suspending transactions, notifying business departments, etc.

[0064] Through the above steps, it is possible to build a cross-border transaction habit profile based on the user's historical transaction data, analyze the user's transaction behavior in real time, and issue warning information in a timely manner when the transaction behavior deviates from the norm, effectively improving the risk control capabilities and user experience of cross-border financial services.

[0065] Figure 2 is a structural diagram of a cross-border financial service system based on big data mining according to an embodiment of the present application, such as Figure 2 As shown, the system includes:

[0066] The first acquisition module 20 is used to acquire the first type of financial data from the data supplier and the second type of financial data from the cooperating financial institution, wherein the first type of financial data includes at least one of the following: real-time foreign exchange quotes, international stock market prices, global interest rate data, real-time metal prices, and the second type of financial data includes at least: end-of-day transaction reports.

[0067] The first receiving module 22 is used to receive a query question, and if the query question includes a first preset keyword related to the first category of financial data and the second category of financial data, display data corresponding to the first preset keyword.

[0068] The second acquisition module 24 is used to acquire target data in the cross-border remittance system, foreign exchange transaction system and cross-border financial management system within the enterprise through the enterprise service bus.

[0069] The second receiving module 26 is used to receive a query question, and if the query question includes a second preset keyword related to the target data, verify the target data, mark or reject the target data that fails the verification, and display the data corresponding to the second preset keyword and the verification result.

[0070] Optionally, the first acquisition module 20 is further used to perform the following steps: obtain the first type of financial data from the data supplier through the application program interface; determine the storage location of the second type of financial data at the cooperative financial institution, and determine the data extraction method for the second type of financial data based on the storage location; determine a first time interval for extracting the second type of financial data, and when a preset extraction time is reached, access the storage location according to the data extraction method, wherein if the second type of financial data is stored in the file transfer protocol server of the cooperative financial institution, access the file transfer protocol server through a pre-registered user name and password; if the second type of financial data is stored in the database of the cooperative financial institution, access the file transfer protocol server through a pre-registered user name and password; if the second type of financial data is stored in the database of the cooperative financial institution, access the file transfer protocol server through a pre-configured connection string and authentication information. Access the database; after successful access, if the storage location is a file transfer protocol server, navigate to the directory storing the second type of financial data, use the download function to download the second type of financial data to the target storage location, if the storage location is a database, query the table or view storing the second type of financial data, use the query statement to extract the second type of financial data from the table or view, and transmit it to the target storage location through the network; obtain error information that occurs in the process of connecting to the data source, extracting data, and storing data, and perform target actions for the error information, wherein the error information includes: network failure, insufficient authority, and data format error, and the target actions include: recording an error log, sending an alarm message, and trying to re-extract data.

[0071] Optionally, the second acquisition module 24 is also used to perform the following steps: configuring a first connection string corresponding to the cross-border remittance system in the enterprise service bus, connecting the cross-border remittance system through the first connection string, and obtaining the target data generated in the cross-border remittance system, wherein the first connection string includes the IP address information, port information, database name information, and first authentication information of the cross-border remittance system, and the first authentication information includes: a digital certificate and biometric information; configuring a second connection string corresponding to the foreign exchange trading system in the enterprise service bus, connecting the foreign exchange trading system through the second connection string, and obtaining the target data generated in the foreign exchange trading system, wherein the second connection string includes the IP address information, port information, database name information, and second authentication information of the foreign exchange trading system, and the second authentication information includes: a dynamic password; configuring a third connection string corresponding to the cross-border financial management system in the enterprise service bus, connecting the cross-border financial management system through the third connection string, and obtaining the target data generated in the cross-border financial management system, wherein the third connection string includes the IP address information, port information, database name information, and third authentication information of the cross-border financial management system, and the third authentication information includes: a user name and a password.

[0072] Optionally, the second receiving module 26 is also used to perform the following steps: verify whether the remittance amount in the cross-border remittance transaction data in the cross-border remittance system is within a first numerical range, whether the account formats of the remittance object and the recipient are correct, and verify whether the cross-border trade financing transaction data is complete, and when the cross-border trade financing transaction data is incomplete, search for missing document data in the business system associated with the transaction number in the cross-border trade financing transaction data; determine the data format type of each type of target data in the foreign exchange trading system, wherein the data format type of each type of target data includes: currency data is a first preset format string, and date data is a second preset format string; set a first verification rule based on the data format type, and when the target data is updated, trigger a verification action based on the first verification rule, and mark or reject the target data that does not comply with the first verification rule; determine the second numerical range of the exchange rate data in the foreign exchange trading system based on market conditions and currency types, and verify whether the exchange rate data is within the second numerical range; according to different financial assets The method further comprises the following steps: determining the minimum and maximum subscription threshold ranges of the products, determining the third numerical range of the wealth management amount data in the cross-border wealth management system, and determining the fourth numerical range of the expected annualized rate of return in the cross-border wealth management system according to the market conditions and the product risk level; verifying whether the wealth management amount data is within the third numerical range, and verifying whether the expected annualized rate of return is within the fourth numerical range; determining the association relationship of the target data in the cross-border wealth management system, wherein the association relationship includes: the matching relationship between the customer information and the wealth management products purchased, the association between the wealth management amount and the customer's asset status and risk tolerance, and the logical relationship between the investment period of the wealth management product and the expected rate of return; determining the second verification rule based on the association relationship, wherein the second verification rule includes: for the customer's purchase of wealth management products, verifying whether the customer's risk tolerance matches the risk level of the purchased product, and whether the wealth management amount is within the customer's available funds; setting the second verification rule based on the association relationship, and triggering the verification action based on the second verification rule when the target data is updated, and marking or rejecting the target data that does not meet the second verification rule.

[0073] Optionally, the above-mentioned cross-border financial service system based on big data mining is also used to perform the following steps: based on historical cross-border transaction data in the cross-border remittance system, foreign exchange trading system and cross-border financial management system, training a machine learning model for determining the risk assessment index of the current cross-border transaction data, and generating an alarm message when the risk assessment index of the current cross-border transaction data is greater than a preset threshold, wherein the above-mentioned training process includes: extracting historical cross-border transaction data from the cross-border remittance system, foreign exchange trading system and cross-border financial management system by extraction, conversion and loading, and loading the historical cross-border transaction data into a data warehouse; selecting a first preset number of first data in the data warehouse, removing duplicate data in the first data, correcting erroneous data in the first data, and filling in missing data in the first data The method comprises the following steps: first, classifying and labeling the second data according to the transaction type dimension, the transaction area dimension and the transaction time dimension to obtain the third data, wherein the labeling content includes: whether there is risk in the transaction and the risk type; extracting target features related to the risk from the third data, wherein the target features include at least one of the following: transaction amount, transaction frequency, credit rating of the transaction object, and fluctuation range of foreign exchange rate; using the target features to train the machine learning model, during the training process, calculating the difference between the predicted result and the true label according to the loss function of the model, adjusting the parameters of the model through the stochastic gradient descent algorithm to minimize the loss function, so that the model continuously learns the risk feature pattern in the data, and obtaining a machine learning model that has completed the training when the loss function meets the preset conditions.

[0074] Optionally, the above-mentioned cross-border financial service system based on big data mining is also used to perform the following steps: select a second preset number of first data in the data warehouse; perform one-hot encoding conversion on non-numeric features in the first data and normalize the numerical features in the first data to obtain second data; cluster the second data based on at least the transaction type dimension, the transaction area dimension and the transaction time dimension to obtain clustering results, and according to the clustering results, divide the users into different transaction behavior clusters to obtain a transaction behavior cluster set; mine transaction patterns with a frequency greater than a preset frequency from the time series data of historical cross-border transaction data, and determine the user's selection order and association relationship for different cross-border transaction products at different time points based on the transaction pattern; integrate the transaction behavior cluster set, selection order and association relationship to obtain a cross-border transaction habit portrait; obtain the user's current transaction behavior, and generate target alarm information when the similarity between the current transaction behavior and the historical transaction behavior in the cross-border transaction habit portrait is less than a first preset threshold.

[0075] It should be noted that the above Figure 2Each module in the can be a program module (for example, a set of program instructions that implement a specific function) or a hardware module. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above modules is a processor, or the functions of each of the above modules are implemented by a processor.

[0076] It should be noted that Figure 2 The preferred implementation of the illustrated embodiment can be found in Figure 1 The relevant description of the illustrated embodiment will not be repeated here.

[0077] Figure 3 The hardware structure block diagram of a computer terminal for implementing a cross-border financial service method based on big data mining is shown. Figure 3 As shown, the computer terminal 30 may include one or more (302a, 302b, ..., 302n are used to illustrate) processors 302 (the processor 302 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 304 for storing data, and a transmission module 306 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 3 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 3 More or fewer components as shown, or with Figure 3 Different configurations shown.

[0078] It should be noted that the one or more processors 302 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 30. As involved in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0079] The memory 304 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the cross-border financial service method based on big data mining in the embodiment of the present application. The processor 302 executes various functional applications and data processing by running the software programs and modules stored in the memory 304, that is, realizing the cross-border financial service method based on big data mining. The memory 304 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 304 may further include a memory remotely arranged relative to the processor 302, and these remote memories may be connected to the computer terminal 30 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0080] The transmission module 306 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 30. In one example, the transmission module 306 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission module 306 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0081] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 30 .

[0082] It should be noted that, in some optional embodiments, the above Figure 3 The computer terminal shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware elements and software elements. Figure 3 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computer terminal described above.

[0083] It should be noted that Figure 3 The computer terminal shown is used to execute Figure 1 The cross-border financial service method based on big data mining shown in the figure, therefore the relevant explanations and instructions in the execution method of the above order also apply to the electronic device and will not be repeated here.

[0084] An embodiment of the present application also provides a non-volatile storage medium, which includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the above cross-border financial service method based on big data mining.

[0085] A program for a non-volatile storage medium to perform the following functions: obtaining a first type of financial data from a data supplier, and obtaining a second type of financial data from a cooperative financial institution, wherein the first type of financial data includes at least one of the following: real-time foreign exchange quotes, international stock market prices, global interest rate data, and real-time metal prices, and the second type of financial data includes at least: end-of-day transaction reports; receiving a query question, and if the query question includes a first preset keyword related to the first type of financial data and the second type of financial data, displaying data corresponding to the first preset keyword; obtaining target data in an enterprise's internal cross-border remittance system, foreign exchange trading system, and cross-border financial management system through an enterprise service bus; receiving a query question, and if the query question includes a second preset keyword related to the target data, verifying the target data, and marking or rejecting the target data that fails the verification, and displaying data corresponding to the second preset keyword and the verification result.

[0086] An embodiment of the present application also provides an electronic device, including: a memory and a processor, the processor being used to run a program stored in the memory, wherein the above cross-border financial service method based on big data mining is executed when the program is running.

[0087] The processor is used to run a program that performs the following functions: obtaining a first type of financial data from a data supplier and a second type of financial data from a cooperative financial institution, wherein the first type of financial data includes at least one of the following: real-time foreign exchange quotes, international stock market prices, global interest rate data, and real-time metal prices, and the second type of financial data includes at least: end-of-day trading reports; receiving a query question, and if the query question includes a first preset keyword related to the first type of financial data and the second type of financial data, displaying data corresponding to the first preset keyword; obtaining target data in the cross-border remittance system, foreign exchange trading system, and cross-border financial management system within the enterprise through an enterprise service bus; receiving a query question, and if the query question includes a second preset keyword related to the target data, verifying the target data, marking or rejecting the target data that fails the verification, and displaying data corresponding to the second preset keyword and the verification result.

[0088] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0089] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0090] In the above-mentioned embodiments of the present application, the collected information is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary protection measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0091] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0092] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0093] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0094] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the relevant technology or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0095] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A cross-border financial service method based on big data mining, characterized in that: include: Obtaining first-category financial data from a data supplier and obtaining second-category financial data from a cooperative financial institution, wherein the first-category financial data includes at least one of the following: real-time foreign exchange quotes, international stock market prices, global interest rate data, and real-time metal prices, and the second-category financial data includes at least: end-of-day transaction reports; receiving a query question, and if the query question includes a first preset keyword related to the first category of financial data and the second category of financial data, displaying data corresponding to the first preset keyword; Obtain target data from the enterprise's internal cross-border remittance system, foreign exchange trading system, and cross-border financial management system through the enterprise service bus; A query question is received. If the query question includes a second preset keyword related to the target data, the target data is verified, and the target data that fails the verification is marked or rejected, and the data corresponding to the second preset keyword and the verification result are displayed.

2. The method according to claim 1, characterized in that The first type of financial data is obtained from data suppliers, and the second type of financial data is obtained from cooperative financial institutions, including: obtaining the first category of financial data from the data provider through an application programming interface; Determining a storage location of the second type of financial data at the cooperative financial institution, and determining a data extraction method for the second type of financial data based on the storage location; Determine a first time interval for extracting the second type of financial data, and when a preset extraction time is reached, access the storage location according to the data extraction method, wherein if the second type of financial data is stored in a file transfer protocol server of the cooperative financial institution, access the file transfer protocol server through a pre-registered user name and password, and if the second type of financial data is stored in a database of the cooperative financial institution, access the database through a pre-configured connection string and authentication information; After the access is successful, if the storage location is the file transfer protocol server, navigate to the directory storing the second type of financial data, use the download function to download the second type of financial data to the target storage location, and if the storage location is the database, query the table or view storing the second type of financial data, use the query statement to extract the second type of financial data from the table or view, and transmit it to the target storage location through the network; Obtain error information that occurs during the process of connecting to a data source, extracting data, and storing data, and perform target actions for the error information, wherein the error information includes: network failure, insufficient authority, data format error, and the target actions include: recording an error log, sending an alarm message, and attempting to re-extract data.

3. The method according to claim 1, characterized in that The target data in the cross-border remittance system, foreign exchange trading system and cross-border financial management system within the enterprise is obtained through the enterprise service bus, including: Configure a first connection string corresponding to the cross-border remittance system in the enterprise service bus, connect to the cross-border remittance system through the first connection string, and obtain target data generated in the cross-border remittance system, wherein the first connection string includes IP address information, port information, database name information, and first authentication information of the cross-border remittance system, and the first authentication information includes: digital certificate and biometric information; configuring a second connection string corresponding to the foreign exchange trading system in the enterprise service bus, connecting to the foreign exchange trading system through the second connection string, and acquiring target data generated in the foreign exchange trading system, wherein the second connection string includes IP address information, port information, database name information, and second authentication information of the foreign exchange trading system, and the second authentication information includes: a dynamic password; A third connection string corresponding to the cross-border financial management system is configured in the enterprise service bus, the cross-border financial management system is connected through the third connection string, and the target data generated in the cross-border financial management system is obtained, wherein the third connection string includes IP address information, port information, database name information, and third authentication information of the cross-border financial management system, and the third authentication information includes: user name and password.

4. The method according to claim 3, characterized in that: Verifying the target data and marking or rejecting the target data that fails the verification, including: Verify whether the remittance amount in the cross-border remittance transaction data in the cross-border remittance system is within the first numerical range, whether the account formats of the remittance recipient and the recipient are correct, and verify whether the cross-border trade financing transaction data is complete. If the cross-border trade financing transaction data is incomplete, search for missing document data in the business system associated with the transaction number in the cross-border trade financing transaction data; Determine the data format type of each type of target data in the foreign exchange trading system, wherein the data format type of each type of target data includes: currency data is a first preset format string, and date data is a second preset format string; set a first verification rule based on the data format type, and when the target data is updated, trigger a verification action based on the first verification rule, and mark or reject the target data that does not meet the first verification rule; determine the second value range of the exchange rate data in the foreign exchange trading system according to market conditions and currency types, and verify whether the exchange rate data is within the second value range; According to the minimum and maximum subscription threshold ranges of different wealth management products, a third numerical range of the wealth management amount data in the cross-border wealth management system is determined, and according to the market conditions and product risk levels, a fourth numerical range of the expected annualized rate of return in the cross-border wealth management system is determined; verify whether the wealth management amount data is within the third numerical range, and verify whether the expected annualized rate of return is within the fourth numerical range; determine the association relationship of target data in the cross-border wealth management system, wherein the association relationship includes: the matching relationship between customer information and the wealth management product purchased, the association between the wealth management amount and the customer's asset status and risk tolerance, and the logical relationship between the investment period of the wealth management product and the expected rate of return; determine a second verification rule based on the association relationship, wherein the second verification rule includes: for the customer's purchase of wealth management products, verify whether the customer's risk tolerance matches the risk level of the purchased product, and whether the wealth management amount is within the customer's available funds; set a second verification rule based on the association relationship, and when the target data is updated, trigger a verification action based on the second verification rule, and mark or reject the target data that does not meet the second verification rule.

5. The method according to claim 1, characterized in that The method further comprises: Based on the historical cross-border transaction data in the cross-border remittance system, the foreign exchange transaction system, and the cross-border financial management system, a machine learning model for determining the risk assessment index of the current cross-border transaction data is trained, and when the risk assessment index of the current cross-border transaction data is greater than a preset threshold, an alarm message is generated, wherein the training process includes: Extracting, converting and loading the historical cross-border transaction data from the cross-border remittance system, the foreign exchange transaction system and the cross-border financial management system, and loading the historical cross-border transaction data into a data warehouse; Selecting a first preset number of first data in the data warehouse, removing duplicate data in the first data, correcting erroneous data in the first data, and filling missing data in the first data to obtain second data; The second data is classified and labeled according to the transaction type dimension, the transaction region dimension, and the transaction time dimension to obtain third data, wherein the labeled content includes: whether there is a risk in the transaction and the risk type; Extracting target features related to risk from the third data, wherein the target features include at least one of the following: transaction amount, transaction frequency, credit rating of transaction counterparty, and fluctuation range of foreign exchange rate; The target features are used to train the machine learning model. During the training process, the difference between the predicted result and the true annotation is calculated according to the loss function of the model. The parameters of the model are adjusted through the stochastic gradient descent algorithm to minimize the loss function, so that the model continuously learns the risk feature patterns in the data, and when the loss function meets the preset conditions, a machine learning model that has completed the training is obtained.

6. The method according to claim 5, characterized in that The method further comprises: Selecting a second preset amount of first data in the data warehouse; performing one-hot encoding conversion on non-numeric features in the first data and normalizing the numeric features in the first data to obtain second data; performing clustering processing on the second data based at least on a transaction type dimension, a transaction region dimension, and a transaction time dimension to obtain a clustering result, and dividing the user into different transaction behavior clusters according to the clustering result to obtain a transaction behavior cluster set; Mining transaction patterns with a frequency greater than a preset frequency from the time series data of the historical cross-border transaction data, and determining the selection order and association relationship of users for different cross-border transaction products at different time points based on the transaction patterns; Integrate the transaction behavior cluster set, the selection order and the association relationship to obtain a cross-border transaction habit profile; The user's current transaction behavior is obtained, and when the similarity between the current transaction behavior and the historical transaction behavior in the cross-border transaction habit portrait is less than a first preset threshold, target alarm information is generated.

7. A cross-border financial service system based on big data mining, characterized in that: include: A first acquisition module is used to acquire first-category financial data from a data supplier and acquire second-category financial data from a cooperative financial institution, wherein the first-category financial data includes at least one of the following: real-time foreign exchange quotes, international stock market prices, global interest rate data, and real-time metal prices, and the second-category financial data includes at least: end-of-day transaction reports; A first receiving module, configured to receive a query question, and if the query question includes a first preset keyword related to the first category of financial data and the second category of financial data, display data corresponding to the first preset keyword; The second acquisition module is used to acquire target data in the cross-border remittance system, foreign exchange transaction system and cross-border financial management system within the enterprise through the enterprise service bus; The second receiving module is used to receive a query question. If the query question includes a second preset keyword related to the target data, the target data is verified, and the target data that fails the verification is marked or rejected, and the data corresponding to the second preset keyword and the verification result are displayed.

8. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the cross-border financial service method based on big data mining as described in any one of claims 1 to 6.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the program, when running, executes the cross-border financial service method based on big data mining as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the cross-border financial service method based on big data mining described in any one of claims 1 to 6 is implemented.

Images