Cross-border e-commerce loan monitoring method, system, medium and equipment

Abstract

The invention relates to the technical field of financial management, and provides a cross-border e-commerce loan monitoring method and system, a computer readable medium and electronic equipment. Acquiring information of associated shops of the cross-border e-commerce, acquiring operation information of the cross-border e-commerce through the graph database, verifying whether historical transactions of the associated shops under the cross-border e-commerce are legal and affiliated, and generating a verification result; and according to the industry and commerce registration information and the historical operation data of the cross-border e-commerce, in combination with the macroeconomic indexes, analyzing market information representing the industry trend and the overall market risk condition. The graph database is constructed to comprehensively integrate the operation information of the cross-border e-commerce and the associated shops thereof, the legality and authenticity of historical transactions are ensured through strict verification, the accurate credit rating and credit line are generated for the cross-border e-commerce, the efficiency and accuracy of credit decision making are improved, the credit risk is effectively reduced, and the user experience is improved. And powerful data support is provided for healthy development of cross-border e-commerce.

Description

Technical Field

[0001] The present application relates to the field of financial management technology, and more specifically, to a cross-border e-commerce loan monitoring method, system, computer-readable medium and electronic device. Background Art

[0002] The background technology of the cross-border e-commerce loan monitoring method mainly stems from the rapid development of e-commerce and the innovation of financial technology. With the continuous expansion of the global e-commerce market, more and more cross-border e-commerce companies are facing the problem of capital shortage, and traditional financing channels are often unable to meet their fast and flexible capital needs. Therefore, cross-border e-commerce loans came into being and became an important way to solve the financing problems of cross-border e-commerce companies.

[0003] In the prior art, cross-border e-commerce involves a wide range of data sources, including e-commerce platform transaction data, logistics data, customs data, financial data, etc. These data formats are diverse and the standards are different, which brings great restrictions to the credit evaluation and monitoring of the cross-border e-commerce loan process, resulting in the problem of low efficiency of credit evaluation and monitoring of the cross-border e-commerce loan process. Summary of the invention

[0004] The embodiments of the present application provide a cross-border e-commerce loan monitoring method, system, computer-readable medium and electronic device, which can at least to some extent solve the problem of low credit assessment and monitoring efficiency in the cross-border e-commerce loan process.

[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0006] According to one aspect of the present application, a cross-border e-commerce loan monitoring method is provided, including: obtaining information of associated stores of the cross-border e-commerce, constructing a graph database based on the information of the associated stores, so as to obtain the operation information of the cross-border e-commerce through the graph database; verifying whether the historical transactions of the associated stores under the cross-border e-commerce are legal and true according to the operation information, and generating a verification result; analyzing market information representing industry trends and the overall market risk situation according to the industrial and commercial registration information and historical operating data of the cross-border e-commerce, combined with macroeconomic indicators; generating the credit rating of the cross-border e-commerce according to the operation information, the verification result and the market information; and determining the credit limit of the cross-border e-commerce according to the credit rating of the cross-border e-commerce through a preset chain prediction model.

[0007] In the present application, based on the aforementioned scheme, the information of the associated stores of the cross-border e-commerce is obtained, and a graph database is constructed based on the information of the associated stores to obtain the operation information of the cross-border e-commerce through the graph database, including: obtaining the information of the associated stores of the cross-border e-commerce; based on the information of the associated stores, a relationship graph between the cross-border e-commerce and the associated stores is constructed through a graph database; according to the relationship graph, the first operation information of each of the associated stores is identified and extracted from the information of the associated stores; the first operation information of the associated stores is integrated to generate the second operation information of the cross-border e-commerce, and the second operation information includes transaction information, customs declaration information, logistics information, tax refund information and foreign exchange settlement information; the second operation information of the cross-border e-commerce is encrypted and stored in the graph database.

[0008] In the present application, based on the aforementioned scheme, the historical transactions of the associated stores under the cross-border e-commerce are verified to be legal and true based on the operation information, and a verification result is generated, including: based on the operation information, verifying the integrity and authenticity of the operation information through a blockchain-based smart contract to generate a first verification result; performing big data analysis on the operation information to verify the legality of the historical transactions and generate a second verification result.

[0009] In the present application, based on the aforementioned scheme, the market information characterizing industry trends and the overall market risk situation is analyzed based on the business registration information and historical operating data of the cross-border e-commerce, combined with macroeconomic indicators, including: predicting industry trends based on the business registration information and historical operating data of the cross-border e-commerce, combined with historical macroeconomic indicators, using long short-term memory networks and attention mechanisms; using topic models to analyze industry news and determine consumer dynamics; analyzing key market events through event detection algorithms to generate risk information; generating the market information based on the industry trends, the consumer dynamics and the risk information.

[0010] In the present application, based on the aforementioned scheme, the credit rating of the cross-border e-commerce is generated according to the operation information, the verification results and the market information, including: calculating the credit score through hierarchical analysis according to the operation information, the verification results and the market information; based on the credit score, dynamically adjusting the credit rating of the cross-border e-commerce according to the historical credit record and real-time operation information of the cross-border e-commerce.

[0011] In the present application, based on the aforementioned scheme, the credit limit of the cross-border e-commerce is determined according to the credit rating of the cross-border e-commerce through a preset chain prediction model, including: constructing a chain prediction model based on a deep learning framework, and optimizing model parameters through a learning mechanism; inputting the credit rating of the cross-border e-commerce into the chain prediction model, and outputting the credit limit of the cross-border e-commerce.

[0012] In the present application, based on the aforementioned solution, it also includes: real-time monitoring of the operation information of the cross-border e-commerce; when abnormal transactions are detected through the operation information, risk control measures are automatically triggered.

[0013] According to one aspect of the present application, a cross-border e-commerce loan monitoring system is provided, comprising: An acquisition unit, used to acquire information of associated stores of a cross-border e-commerce company, and to construct a graph database based on the information of the associated stores, so as to acquire operation information of the cross-border e-commerce company through the graph database; A verification unit, used to verify whether the historical transactions of the associated stores under the cross-border e-commerce are legal and true according to the operation information, and generate a verification result; A market unit, which is used to analyze market information representing industry trends and overall market risks based on the business registration information and historical operating data of the cross-border e-commerce company in combination with macroeconomic indicators; A credit unit, configured to generate a credit rating of the cross-border e-commerce company based on the operation information, the verification result and the market information; The credit limit unit is used to determine the credit limit of the cross-border e-commerce company according to the credit rating of the cross-border e-commerce company through a preset chain prediction model.

[0014] In the present application, based on the aforementioned scheme, the information of the associated stores of the cross-border e-commerce is obtained, and a graph database is constructed based on the information of the associated stores to obtain the operation information of the cross-border e-commerce through the graph database, including: obtaining the information of the associated stores of the cross-border e-commerce; based on the information of the associated stores, a relationship graph between the cross-border e-commerce and the associated stores is constructed through a graph database; according to the relationship graph, the first operation information of each of the associated stores is identified and extracted from the information of the associated stores; the first operation information of the associated stores is integrated to generate the second operation information of the cross-border e-commerce, and the second operation information includes transaction information, customs declaration information, logistics information, tax refund information and foreign exchange settlement information; the second operation information of the cross-border e-commerce is encrypted and stored in the graph database.

[0015] In the present application, based on the aforementioned scheme, the historical transactions of the associated stores under the cross-border e-commerce are verified to be legal and true based on the operation information, and a verification result is generated, including: based on the operation information, verifying the integrity and authenticity of the operation information through a blockchain-based smart contract to generate a first verification result; performing big data analysis on the operation information to verify the legality of the historical transactions and generate a second verification result.

[0016] In the present application, based on the aforementioned scheme, the market information characterizing industry trends and the overall market risk situation is analyzed based on the business registration information and historical operating data of the cross-border e-commerce, combined with macroeconomic indicators, including: predicting industry trends based on the business registration information and historical operating data of the cross-border e-commerce, combined with historical macroeconomic indicators, using long short-term memory networks and attention mechanisms; using topic models to analyze industry news and determine consumer dynamics; analyzing key market events through event detection algorithms to generate risk information; generating the market information based on the industry trends, the consumer dynamics and the risk information.

[0017] In the present application, based on the aforementioned scheme, the credit rating of the cross-border e-commerce is generated according to the operation information, the verification results and the market information, including: calculating the credit score through hierarchical analysis according to the operation information, the verification results and the market information; based on the credit score, dynamically adjusting the credit rating of the cross-border e-commerce according to the historical credit record and real-time operation information of the cross-border e-commerce.

[0018] In the present application, based on the aforementioned scheme, the credit limit of the cross-border e-commerce is determined according to the credit rating of the cross-border e-commerce through a preset chain prediction model, including: constructing a chain prediction model based on a deep learning framework, and optimizing model parameters through a learning mechanism; inputting the credit rating of the cross-border e-commerce into the chain prediction model, and outputting the credit limit of the cross-border e-commerce.

[0019] In the present application, based on the aforementioned solution, it also includes: real-time monitoring of the operation information of the cross-border e-commerce; when abnormal transactions are detected through the operation information, risk control measures are automatically triggered.

[0020] According to one aspect of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the cross-border e-commerce loan monitoring method as described in the above embodiment is implemented.

[0021] According to one aspect of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the cross-border e-commerce loan monitoring method as described in the above embodiments.

[0022] According to one aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the cross-border e-commerce loan monitoring method provided in the above various optional implementations.

[0023] The technical solution of this application obtains the information of the associated stores of the cross-border e-commerce, and constructs a graph database based on the information of the associated stores to obtain the operation information of the cross-border e-commerce through the graph database; according to the operation information, verify whether the historical transactions of the associated stores under the cross-border e-commerce are legal and true, and generate verification results; according to the industrial and commercial registration information and historical operating data of the cross-border e-commerce, combined with macroeconomic indicators, analyze the market information that characterizes the overall situation of industry trends and market risks; according to the operation information, the verification results and the market information, generate the credit rating of the cross-border e-commerce; according to the credit rating of the cross-border e-commerce, determine the credit limit of the cross-border e-commerce through a preset chain prediction model. By constructing a graph database to comprehensively integrate the operation information of the cross-border e-commerce and its associated stores, the legality and authenticity of historical transactions are ensured through strict verification. At the same time, in-depth analysis of industry trends and market risks is conducted in combination with macroeconomic indicators to generate accurate credit ratings for cross-border e-commerce. Finally, based on the credit rating, the credit limit is scientifically determined through a chain prediction model. This process not only improves the efficiency and accuracy of credit decision-making, but also effectively reduces credit risks, providing strong data support for the healthy development of cross-border e-commerce.

[0024] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 A flowchart of a cross-border e-commerce loan monitoring method in an embodiment of the present application is schematically shown.

[0027] Figure 2 A flowchart for obtaining cross-border e-commerce operation information in an embodiment of the present application is schematically shown.

[0028] Figure 3A schematic diagram of a cross-border e-commerce loan monitoring system in an embodiment of the present application is schematically shown.

[0029] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0030] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0031] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, systems, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0032] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0033] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0034] The implementation details of the technical solution of this application are described in detail below: Figure 1 A flow chart of a cross-border e-commerce loan monitoring method according to an embodiment of the present application is shown. Figure 1 As shown, the cross-border e-commerce loan monitoring method includes at least steps S110 to S150, which are described in detail as follows: In step S110, the information of the associated stores of the cross-border e-commerce is obtained, and a graph database is constructed based on the information of the associated stores, so as to obtain the operation information of the cross-border e-commerce through the graph database.

[0035] In one embodiment of the present application, a cross-border e-commerce may include multiple associated stores to carry out specific production, sales and operation work. In order to fully understand and monitor the operation status of cross-border e-commerce, firstly, the detailed information of its associated stores is widely collected, including but not limited to transactions between stores, ownership relationships and supply chain connections. Subsequently, this information is used to build a sophisticated graph database, which graphically and intuitively displays the intricate network relationship between cross-border e-commerce and its associated stores. Through this graph database, the operation information of cross-border e-commerce can be tracked and analyzed, thereby achieving deep insight and real-time monitoring of the operation status of cross-border e-commerce.

[0036] like Figure 2 As shown, in one embodiment of the present application, information of associated stores of a cross-border e-commerce is obtained, and a graph database is constructed based on the information of the associated stores, so as to obtain operation information of the cross-border e-commerce through the graph database, including: S210, obtaining information of associated stores of the cross-border e-commerce; S220, constructing a graph database based on the information of the associated stores, and constructing a relationship graph between the cross-border e-commerce and the associated stores through the graph database; S230, identifying and extracting first operation information of each of the associated stores from the information of the associated stores according to the relationship graph; S240, integrating the first operation information of the associated stores to generate second operation information of the cross-border e-commerce, wherein the second operation information includes transaction information, customs declaration information, logistics information, tax refund information, and foreign exchange settlement information; S250, encrypting the second operation information of the cross-border e-commerce and storing it in the graph database.

[0037] In this embodiment, information of all stores that have direct or indirect relationship with cross-border e-commerce is collected. The information can be obtained from the internal database of the cross-border e-commerce platform, or from other e-commerce platforms or partners through a data transmission interface. The method of obtaining the information is not specifically limited here.

[0038] Optionally, in addition to the internal database and data transmission interface of the e-commerce platform, social media, industry reports, government public data, etc. can also be considered as supplementary data sources.

[0039] Select a suitable graph database based on the data scale and query performance requirements. Use a batch import tool to import the information of related stores into the graph database, and create indexes for key attributes to improve query efficiency. The method of building a graph database can be selected from existing technologies, which will not be described here.

[0040] According to the relationship graph of the graph database, text recognition is used to perform sentiment analysis and theme recognition on the product descriptions and user comments of the associated stores to obtain the first operation information of the associated stores. Text recognition refers to the extraction of text from images or documents through technical means and converting them into editable and processable text form.

[0041] The relationship graph in a graph database is a visual representation of the relationship between nodes. Nodes represent entities, such as people, places, events, and other objects. Relationships represent the connections between these nodes, such as "belongs to", "associated with", "friends", "colleagues", etc. The relationship graph can clearly show the complex network of associations between different entities.

[0042] For example, according to the transaction records in the first operation information of each associated store, the total sales, transaction volume, average order amount and other indicators of cross-border e-commerce are calculated as the second operation information. Combined with customs data and logistics interface, information such as customs declaration status, logistics track and estimated arrival time are extracted. Through the tax and banking system interface, data such as tax refund application status, tax refund amount and foreign exchange settlement record are obtained, and the above data are summarized as the second operation information of cross-border e-commerce.

[0043] In one embodiment of the present application, encrypting the second operation information of the cross-border e-commerce and storing it in the graph database includes: Performing hash processing on various types of data in the second operation information to obtain a hash value set consisting of multiple hash values; Performing linear operations on multiple hash values ​​in the hash value set to generate a backup key; The backup key is subjected to nonlinear transformation and obfuscation processing to generate an encryption key, and the second operation information of the cross-border e-commerce is encrypted by the encryption key and stored in the graph database.

[0044] Specifically, in this embodiment, the SHA-256 hash function is selected to perform hash processing on various types of data in the second operation information, and the output is a 256-bit hash value to ensure the high security and uniqueness of the hash value.

[0045] For each type of data M in the second operation information, calculate its hash value , the generated hash value set is ,in i is the data identifier, n is the number of data categories.

[0046] A linear operation is performed on multiple hash values ​​in the hash value set to generate an intermediate value S, which is used as a backup key: in, is the linear coefficient, represents the remainder operation, p is a large prime number.

[0047] Backup key S Perform nonlinear transformation to generate the first parameter , the first parameter for: in, is a nonlinear function, for example, a polynomial transformation.

[0048] After that, the first parameter is iterated multiple times, and each iteration applies nonlinear transformation and confusion operation to generate the second parameter for: in, g and h is a nonlinear function, represents the exclusive OR operation, j is the number of iterations.

[0049] For the first parameter t After iterations, the intermediate key is obtained . For the intermediate key Perform the last nonlinear transformation to generate the encryption key for: in, F It is a nonlinear function, such as a permutation operation or a diffusion operation. By introducing complex mathematical formulas and algorithms, the technical complexity and logical coherence of the encryption process can be ensured. These complex mathematical methods and algorithms provide higher security and reliability for the encryption process.

[0050] In this embodiment, by obtaining the associated store information of the cross-border e-commerce and building a graph database based on this information, the complex relationship between the cross-border e-commerce and its associated stores can be clearly displayed. The structure of the graph database makes the retrieval and integration of information efficient, and helps to quickly generate the second operation information of the cross-border e-commerce. The second operation information includes transactions, customs declarations, logistics, tax refunds, and foreign exchange settlement. By encrypting and storing the second operation information, the confidentiality and integrity of the information are ensured, and the risk of information leakage and tampering is prevented.

[0051] In step S120, based on the operation information, it is verified whether the historical transactions of the associated stores under the cross-border e-commerce are legal and true, and a verification result is generated.

[0052] In one embodiment of the present application, after obtaining the operating information of the cross-border e-commerce and its associated stores, a series of strict verification procedures are used to verify the legitimacy and authenticity of the historical transactions of these associated stores. This includes but is not limited to a detailed comparison of transaction records, a review of the qualifications of both parties to the transaction, and a comprehensive verification of the logistics, payment, and tax information involved in the transaction process. Through these measures, a detailed verification result can be generated, which clearly shows whether the historical transactions of the associated stores comply with relevant laws and regulations, and whether they are true and accurately reflect the actual operation of the cross-border e-commerce.

[0053] In one embodiment of the present application, based on the operation information, verify whether the historical transactions of the associated stores under the cross-border e-commerce are legal and true, and generate a verification result, including: According to the operation information, verify the integrity and authenticity of the operation information through a smart contract based on blockchain to generate a first verification result; Perform big data analysis on the operation information, verify the legitimacy of the historical transactions, and generate a second verification result.

[0054] In one embodiment of the present application, the operation information includes the first operation information and the second operation information. A smart contract is designed according to the characteristics of the operation information and the verification requirements. This smart contract contains verification rules, data format requirements, and conditions for triggering verification. The smart contract must ensure that the data cannot be tampered with once it is on the chain, and use its decentralized and transparent characteristics to ensure the integrity of the information.

[0055] Before the operation information is recorded, its hash value is calculated. This hash value will be used as the unique identifier of the operation information and stored on the blockchain. The calculation of the hash value should use a secure hash function to ensure the uniqueness and irreversibility of the data. When the integrity and authenticity of the operation information needs to be verified, the hash value of the operation information is first calculated. Then, this newly calculated hash value is compared with the hash value stored on the blockchain. If the two are consistent, the smart contract will generate the first verification result, indicating that the operation information has not been tampered with since it was uploaded to the chain, and the integrity and authenticity are maintained.

[0056] Extract historical transaction data related to operational information from the graph database. Clean, format, and standardize these historical transaction data to ensure data accuracy and consistency. Use machine learning or deep learning technology to build a big data analysis model. This model can identify transaction patterns, abnormal behaviors, and potential risks. During the model training process, a large amount of historical transaction data will be used as training samples to improve the accuracy and generalization ability of the model. Input the historical transaction data in the operational information to be verified into the big data analysis model. The model will perform big data analysis on these transactions and output an evaluation result indicating whether these transactions meet the expected legality and compliance standards. Generate a second verification result based on the model's evaluation results. If the transaction is judged to be legal, the second verification result is positive; otherwise, it is negative.

[0057] The first verification result and the second verification result are integrated to form a comprehensive verification report. This verification report will be used to guide subsequent decision-making, risk management and compliance checks. If the verification results show that there are any problems or risks in the operational information, the corresponding early warning mechanism will be triggered immediately and necessary corrective measures will be taken. By combining blockchain smart contracts and big data analysis technology, we can build an efficient, secure and reliable operational information verification system. This operational information verification system can not only ensure the integrity and authenticity of the information, but also identify potential risks and abnormal behaviors, providing strong support for the company's operational decisions.

[0058] In the above process, the integrity and authenticity of the operation information are verified through the smart contract based on blockchain, and the first verification result is generated. The immutability of blockchain provides a strong guarantee for the authenticity of the information. Big data analysis is performed on the operation information to verify the legitimacy of historical transactions and generate the second verification result. Big data analysis can dig out potential risks and abnormal patterns in transactions, thereby ensuring the legitimacy of transactions.

[0059] In step S130, based on the business registration information and historical operating data of the cross-border e-commerce, combined with macroeconomic indicators, market information representing the overall situation of industry trends and market risks is analyzed.

[0060] In one embodiment of the present application, in-depth analysis and comprehensive evaluation are conducted based on the business registration information of cross-border e-commerce and the accumulated historical operating data, while integrating macroeconomic indicators. This process aims to comprehensively analyze the industry trends in which cross-border e-commerce is located, including the growth potential of the market, changes in the competitive landscape, and the development trends of emerging technologies. At the same time, we also pay close attention to various factors that may cause market risks, such as policy adjustments, exchange rate fluctuations, changes in the global economic situation, etc., so as to comprehensively extract market information that can accurately reflect the future direction of the industry and the overall risk status of the market.

[0061] In this embodiment, macroeconomic indicators are quantitative indicators that reflect the operation status and development trend of the macroeconomy, and mainly include gross domestic product, gross national product, producer price index, inflation rate, unemployment rate, trade balance, investment index, consumption index, financial index and fiscal index, etc. Macroeconomic indicators play an important role in the analysis and reference of macroeconomic forecasts.

[0062] In one embodiment of the present application, based on the business registration information and historical operating data of the cross-border e-commerce, combined with macroeconomic indicators, market information characterizing industry trends and overall market risks is analyzed, including: Based on the business registration information and historical operating data of the cross-border e-commerce, combined with historical macroeconomic indicators, long short-term memory networks and attention mechanisms are used to predict industry trends; Use topic models to analyze industry news and identify consumer trends; Analyze key market events through event detection algorithms to generate risk information; The market information is generated according to the industry trend, the consumer dynamics and the risk information.

[0063] In one embodiment of the present application, based on the business registration information and historical operating data of cross-border e-commerce, combined with historical macroeconomic indicators, features related to industry trends are extracted, such as the number of enterprise registrations, sales, growth rate, and inflation rate. These features will be used to construct the input of the long short-term memory network. On the basis of the long short-term memory network model, an attention mechanism is integrated to highlight data points that have an important impact on the prediction results. The attention mechanism enables the model to pay more attention to important historical information by calculating the weight of each time step. The long short-term memory network model is trained using historical data, and the model parameters are adjusted to minimize the prediction error. After the training is completed, the model is used to predict industry trends in the future.

[0064] In one embodiment of the present application, the long short-term memory network and attention mechanism are used to predict industry trends by combining the business registration information and historical operating data of cross-border e-commerce and historical macroeconomic indicators. This method can capture long-term dependencies and important features in the data and improve the accuracy of prediction.

[0065] Collect text data related to cross-border e-commerce from social media platforms and industry news websites. Use word embedding to convert text data into vector representation. Use topic modeling to model the vector representation of text data. Topic modeling can identify potential themes and topics in text data, thereby revealing consumer concerns and dynamics. Analyze the results of topic modeling to extract key topics and keywords.

[0066] Topic modeling is a technique used to discover potential topics from text data. The main principle of topic modeling is to represent text as a combination of some topics, and to identify topics by analyzing and counting a large amount of text to find some common word patterns.

[0067] Use topic models to analyze industry news and identify consumer trends; use event detection algorithms to analyze key market events and generate risk information. This helps cross-border e-commerce companies keep abreast of market trends and changes in consumer demand, as well as potential market risks.

[0068] There are many types of event detection algorithms, including rule-based algorithms, which rely on pre-set clear rules to capture specific events; there are also statistical pattern recognition algorithms, which discover event patterns through statistical analysis of data, such as clustering algorithms; machine learning algorithms also play an important role, such as support vector machines and decision trees, which can learn from data and detect events; deep learning algorithms are even more prominent, such as recurrent neural networks and their variants, which are good at processing sequence data to effectively detect events; in addition, dynamic time warping algorithms can compare time series similarities to assist in event detection, and hidden Markov models are suitable for handling event detection tasks with hidden states.

[0069] Optionally, use visualization tools to present the results of the thematic analysis to facilitate understanding of consumer dynamics.

[0070] The event detection algorithm is built using natural language processing and machine learning technology, which can identify key events in the text, such as policy changes, natural disasters, or market fluctuations. The detected key events are further analyzed to assess their impact on the cross-border e-commerce market. Based on the analysis results, risk information is generated, including risk type, impact range, potential losses, etc.

[0071] Integrate the results of industry trend forecasts, consumer dynamics analysis, and key market event analysis. Use data analysis tools to automatically collect, clean, analyze, and interpret these diverse data, identify the correlations and trends between data, extract key information and patterns, and then combine this information into intuitive, easy-to-understand reports or charts to reveal the overall market situation and future development trends. Generate a cross-border e-commerce market information report based on the results of the comprehensive analysis.

[0072] In step S140, the credit rating of the cross-border e-commerce is generated according to the operation information, the verification result and the market information.

[0073] In this embodiment, after comprehensively considering the operational information of cross-border e-commerce and the verification results of historical transactions of related stores, as well as the market information obtained by analyzing macroeconomic indicators, these complex and multi-dimensional data are deeply analyzed and carefully weighed. This process not only examines the actual operational performance, compliance and market performance of cross-border e-commerce, but also fully considers its competitive position in the industry and its ability to resist market risks. Based on these comprehensive considerations, an objective and fair credit rating can be accurately generated for cross-border e-commerce, which intuitively reflects its overall credit status and reliability.

[0074] In one embodiment of the present application, generating the credit rating of the cross-border e-commerce company according to the operation information, the verification result and the market information includes: Calculating a credit score through hierarchical analysis based on the operation information, the verification result and the market information; Based on the credit score, the credit rating of the cross-border e-commerce company is dynamically adjusted according to the historical credit record and real-time operation information of the cross-border e-commerce company.

[0075] In one embodiment of the present application, a hierarchical model is constructed based on the key factors of cross-border e-commerce credit. Generally, the hierarchical model includes a target layer (credit score), a criterion layer (such as operational performance, verification results, market adaptability, etc.) and an indicator layer (specific operational indicators, verification indicators and market indicators). The indicators at each level are compared pairwise to construct a judgment matrix. The elements of the judgment matrix represent the relative importance of the indicators. For example, the elements of the judgment matrix A are Representation Guidelines Relative to the criteria The degree of importance is usually expressed using a 1-9 scale.

[0076] A hierarchical model is a model that organizes and represents complex systems or data in a hierarchical relationship. In a hierarchical model, elements are arranged in layers, with the upper-level elements commanding and summarizing the lower-level elements, while the lower-level elements provide specific details and support for the upper-level elements. This model has a clear structure and a clear hierarchical relationship, which helps to better understand the overall architecture of the system and the relationship between its parts. It is often used in areas such as organizational management, classification systems, and software architecture design, and can make complex things more organized and easier to analyze and process.

[0077] The transposed matrix of judgment matrix A is , calculate the matrix parameters based on the judgment matrix and its transpose for: Calculate matrix parameters The eigenvalues ​​and eigenvectors of the matrix A are selected, and the eigenvector corresponding to the maximum eigenvalue is selected as the weight vector. Normalization is performed to obtain the weights corresponding to each indicator in each indicator layer. The weights are synthesized layer by layer from the bottom layer (indicator layer) to the top layer (target layer) to obtain the weight of each indicator relative to the total target. Based on the standardized data and indicator weights, the standardized value of each indicator is multiplied by the corresponding weight, and then the sum is calculated to obtain the credit score of the cross-border e-commerce.

[0078] Obtain the historical credit records and credit rating change history of cross-border e-commerce from the database. Monitor the operational information of cross-border e-commerce in real time, including but not limited to real-time changes in key indicators such as sales, user satisfaction and return rate. According to real-time operational information, historical credit records and current credit scores, combined with credit rating adjustment rules, dynamically adjust the credit rating of cross-border e-commerce. If the credit score rises or falls significantly, it may be necessary to trigger an upward adjustment of the credit rating. If negative events occur in the historical credit records, it may be necessary to trigger a downward adjustment of the credit rating.

[0079] In this embodiment, the credit score is calculated through hierarchical analysis based on the operational information, verification results and market information; and the credit rating of the cross-border e-commerce is dynamically adjusted based on the credit score, historical credit records and real-time operational information. This evaluation method takes into account both historical data and real-time information, ensuring the comprehensiveness and dynamism of the credit rating.

[0080] In step S150, the credit limit of the cross-border e-commerce company is determined according to the credit rating of the cross-border e-commerce company through a preset chain prediction model.

[0081] In this embodiment, after determining the credit rating of the cross-border e-commerce company, a pre-built and optimized chain prediction model is used to calculate and predict the credit rating as a key input variable, combined with multiple factors such as historical credit data, industry credit policies, and current financial market conditions. This process is intended to scientifically and reasonably evaluate the repayment ability and credit risk of the cross-border e-commerce company, so as to tailor a credit line that meets its actual needs and can effectively control risks, ensuring the optimal allocation of credit resources and the effectiveness of risk control.

[0082] In one embodiment of the present application, before determining the credit limit of the cross-border e-commerce company through a preset chain prediction model according to the credit rating of the cross-border e-commerce company, the method further includes: A chain prediction model is built based on the deep learning framework, and the model parameters are optimized through the learning mechanism.

[0083] In one embodiment of the present application, a chain prediction model is constructed based on a deep learning framework, and the chain model is generally composed of multiple layers, including an input layer, a hidden layer, and an output layer. The input layer receives the credit rating of the cross-border e-commerce as a feature. The hidden layer may include one or more fully connected layers, loop layers, or attention mechanism layers to capture the potential relationship and long-term dependency between credit ratings. The output layer outputs the predicted credit limit. Select a suitable loss function, such as mean square error or mean absolute error, to measure the difference between the model prediction value and the true value. Update the model parameters through the optimizer back propagation algorithm to minimize the loss function.

[0084] Collect historical data, including the credit ratings and corresponding credit limits of cross-border e-commerce companies. Divide the data into training, validation, and test sets. Encode the credit ratings and standardize or normalize the credit limits to improve the convergence speed and performance of the model. Use the training set data to train the chain prediction model. During the training process, calculate the gradients through the back-propagation algorithm and use the optimizer to update the model parameters. Regularly evaluate the model performance on the validation set, such as calculating the loss value and accuracy, to monitor whether the model is overfitting. Adjust the model architecture, loss function, and optimizer parameters based on the performance evaluation results on the validation set.

[0085] Receive credit rating input from cross-border e-commerce in real time. Encode and preprocess the input credit rating to ensure that it is consistent with the data format used during training. Input the preprocessed credit rating into the chain prediction model for real-time prediction. Obtain the predicted credit limit from the model and output it to the relevant decision-making system or user interface.

[0086] Through the above computer execution process, a chain prediction model based on a deep learning framework can be constructed to predict the credit limit based on the credit rating of cross-border e-commerce. After training and optimization, the model can be deployed in a production environment for real-time prediction, providing credit decision support for cross-border e-commerce platforms.

[0087] This embodiment builds a chain prediction model based on a deep learning framework and optimizes model parameters through a learning mechanism; the credit rating of cross-border e-commerce is input into the chain prediction model to output the credit limit. The deep learning model can capture the complex relationship between credit rating and credit limit, thereby outputting accurate credit limit recommendations.

[0088] In one embodiment of the present application, it also includes: real-time monitoring of the operation information of the cross-border e-commerce; when abnormal transactions are detected through the operation information, risk control measures are automatically triggered.

[0089] In one embodiment of the present application, a system is designed and built specifically for monitoring cross-border e-commerce operation information. The system should be able to collect, process and analyze key operation information such as transaction data, user behavior data, logistics data, etc. of the cross-border e-commerce platform in real time. According to business needs and risk management strategies, a series of risk control rules are set. These rules involve multiple dimensions such as transaction amount, transaction frequency, user behavior pattern, geographic location, etc.

[0090] The output of the anomaly detection algorithm is input into the real-time monitoring system. When the system detects an abnormal transaction, the alarm mechanism is immediately triggered to notify relevant personnel or system components. According to the risk control rules, corresponding risk control measures are configured, such as transaction interception, secondary verification, etc.

[0091] After implementing risk control measures, the system should be able to record the implementation of the measures and provide a feedback mechanism so that relevant personnel can evaluate and adjust the effectiveness of the measures. The above process monitors the operational information of cross-border e-commerce in real time and automatically triggers risk control measures when abnormal transactions are detected. This helps cross-border e-commerce companies to promptly identify and respond to potential risks and ensure the stable operation of their businesses.

[0092] The technical solution of this application obtains the information of the associated stores of the cross-border e-commerce, and constructs a graph database based on the information of the associated stores to obtain the operation information of the cross-border e-commerce through the graph database; according to the operation information, verify whether the historical transactions of the associated stores under the cross-border e-commerce are legal and true, and generate verification results; according to the industrial and commercial registration information and historical operating data of the cross-border e-commerce, combined with macroeconomic indicators, analyze the market information that characterizes the overall situation of industry trends and market risks; according to the operation information, the verification results and the market information, generate the credit rating of the cross-border e-commerce; according to the credit rating of the cross-border e-commerce, determine the credit limit of the cross-border e-commerce through a preset chain prediction model. By constructing a graph database to comprehensively integrate the operation information of the cross-border e-commerce and its associated stores, the legality and authenticity of historical transactions are ensured through strict verification. At the same time, in-depth analysis of industry trends and market risks is conducted in combination with macroeconomic indicators to generate accurate credit ratings for cross-border e-commerce. Finally, based on the credit rating, the credit limit is scientifically determined through a chain prediction model. This process not only improves the efficiency and accuracy of credit decision-making, but also effectively reduces credit risks, providing strong data support for the healthy development of cross-border e-commerce.

[0093] The following describes an embodiment of the device of the present application, which can be used to execute the cross-border e-commerce loan monitoring method in the above embodiment of the present application. It is understandable that the device can be a computer program (including program code) running in a computer device, for example, the device is an application software; the device can be used to execute the corresponding steps in the method provided in the embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the cross-border e-commerce loan monitoring method in the above embodiment of the present application.

[0094] Figure 3 A block diagram of a cross-border e-commerce loan monitoring system according to an embodiment of the present application is shown.

[0095] Reference Figure 3 As shown, a cross-border e-commerce loan monitoring system according to an embodiment of the present application includes: The acquisition unit 310 is used to acquire information of associated stores of the cross-border e-commerce, and to construct a graph database based on the information of the associated stores, so as to acquire operation information of the cross-border e-commerce through the graph database; A verification unit 320 is used to verify whether the historical transactions of the associated stores under the cross-border e-commerce are legal and true according to the operation information, and generate a verification result; The market unit 330 is used to analyze the market information representing the overall situation of industry trends and market risks based on the business registration information and historical operating data of the cross-border e-commerce and in combination with macroeconomic indicators; A credit unit 340, configured to generate a credit rating of the cross-border e-commerce company based on the operation information, the verification result and the market information; The credit limit unit 350 is used to determine the credit limit of the cross-border e-commerce company according to the credit rating of the cross-border e-commerce company through a preset chain prediction model.

[0096] In the present application, based on the aforementioned scheme, the information of the associated stores of the cross-border e-commerce is obtained, and a graph database is constructed based on the information of the associated stores to obtain the operation information of the cross-border e-commerce through the graph database, including: obtaining the information of the associated stores of the cross-border e-commerce; based on the information of the associated stores, a relationship graph between the cross-border e-commerce and the associated stores is constructed through a graph database; according to the relationship graph, the first operation information of each of the associated stores is identified and extracted from the information of the associated stores; the first operation information of the associated stores is integrated to generate the second operation information of the cross-border e-commerce, and the second operation information includes transaction information, customs declaration information, logistics information, tax refund information and foreign exchange settlement information; the second operation information of the cross-border e-commerce is encrypted and stored in the graph database.

[0097] In the present application, based on the aforementioned scheme, the historical transactions of the associated stores under the cross-border e-commerce are verified to be legal and true based on the operation information, and a verification result is generated, including: based on the operation information, verifying the integrity and authenticity of the operation information through a blockchain-based smart contract to generate a first verification result; performing big data analysis on the operation information to verify the legality of the historical transactions and generate a second verification result.

[0098] In the present application, based on the aforementioned scheme, the market information characterizing industry trends and the overall market risk situation is analyzed based on the business registration information and historical operating data of the cross-border e-commerce, combined with macroeconomic indicators, including: predicting industry trends based on the business registration information and historical operating data of the cross-border e-commerce, combined with historical macroeconomic indicators, using long short-term memory networks and attention mechanisms; using topic models to analyze industry news and determine consumer dynamics; analyzing key market events through event detection algorithms to generate risk information; generating the market information based on the industry trends, the consumer dynamics and the risk information.

[0099] In the present application, based on the aforementioned scheme, the credit rating of the cross-border e-commerce is generated according to the operation information, the verification results and the market information, including: calculating the credit score through hierarchical analysis according to the operation information, the verification results and the market information; based on the credit score, dynamically adjusting the credit rating of the cross-border e-commerce according to the historical credit record and real-time operation information of the cross-border e-commerce.

[0100] In the present application, based on the aforementioned scheme, the credit limit of the cross-border e-commerce is determined according to the credit rating of the cross-border e-commerce through a preset chain prediction model, including: constructing a chain prediction model based on a deep learning framework, and optimizing model parameters through a learning mechanism; inputting the credit rating of the cross-border e-commerce into the chain prediction model, and outputting the credit limit of the cross-border e-commerce.

[0101] In the present application, based on the aforementioned solution, it also includes: real-time monitoring of the operation information of the cross-border e-commerce; when abnormal transactions are detected through the operation information, risk control measures are automatically triggered.

[0102] The technical solution of this application obtains the information of the associated stores of the cross-border e-commerce, and constructs a graph database based on the information of the associated stores to obtain the operation information of the cross-border e-commerce through the graph database; according to the operation information, verify whether the historical transactions of the associated stores under the cross-border e-commerce are legal and true, and generate verification results; according to the industrial and commercial registration information and historical operating data of the cross-border e-commerce, combined with macroeconomic indicators, analyze the market information that characterizes the overall situation of industry trends and market risks; according to the operation information, the verification results and the market information, generate the credit rating of the cross-border e-commerce; according to the credit rating of the cross-border e-commerce, determine the credit limit of the cross-border e-commerce through a preset chain prediction model. By constructing a graph database to comprehensively integrate the operation information of the cross-border e-commerce and its associated stores, the legality and authenticity of historical transactions are ensured through strict verification. At the same time, in-depth analysis of industry trends and market risks is conducted in combination with macroeconomic indicators to generate accurate credit ratings for cross-border e-commerce. Finally, based on the credit rating, the credit limit is scientifically determined through a chain prediction model. This process not only improves the efficiency and accuracy of credit decision-making, but also effectively reduces credit risks, providing strong data support for the healthy development of cross-border e-commerce.

[0103] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.

[0104] It should be noted that the computer system of the electronic device in this embodiment is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0105] In this embodiment, the computer system includes a central processing unit 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory 402 or the program loaded from the storage part 408 to the random access memory 403, such as executing the cross-border e-commerce loan monitoring method described in the above embodiment. In the random access memory 403, various programs and data required for system operation are also stored. The central processing unit 401, the read-only memory 402 and the random access memory 403 are connected to each other through the bus 404. The input / output interface 405 is also connected to the bus 404.

[0106] The following components are connected to the input / output interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0107] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 409, and / or installed from a removable medium 411. When the computer program is executed by the central processing unit 401, various functions defined in the system of the present application are executed.

[0108] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0109] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0110] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0111] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations.

[0112] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the cross-border e-commerce loan monitoring method described in the above embodiment.

[0113] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0114] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the implementation method of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation method of the present application.

[0115] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.

[0116] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A cross-border e-commerce loan monitoring method, characterized in that: include: Acquire information of associated stores of a cross-border e-commerce company, and build a graph database based on the information of the associated stores, so as to acquire operation information of the cross-border e-commerce company through the graph database; Verify whether historical transactions of the associated stores under the cross-border e-commerce are legal and true based on the operation information, and generate verification results; Analyze market information that represents industry trends and overall market risk based on the business registration information and historical operating data of the cross-border e-commerce company in combination with macroeconomic indicators; Generating a credit rating of the cross-border e-commerce company according to the operation information, the verification result and the market information; According to the credit rating of the cross-border e-commerce company, the credit limit of the cross-border e-commerce company is determined through a preset chain prediction model.

2. The cross-border e-commerce loan monitoring method according to claim 1, characterized in that: The obtaining of information about associated stores of the cross-border e-commerce and constructing a graph database based on the information about the associated stores includes: Obtaining information about the associated stores of the cross-border e-commerce company; Based on the information of the associated stores, a graph database is constructed, and a relationship graph between the cross-border e-commerce and the associated stores is constructed through the graph database; According to the relationship graph, identifying and extracting first operation information of each of the associated stores from the information of the associated stores; Integrate the first operation information of the associated stores to generate second operation information of the cross-border e-commerce, where the second operation information includes transaction information, customs declaration information, logistics information, tax refund information, and foreign exchange settlement information; The second operation information of the cross-border e-commerce is encrypted and stored in the graph database.

3. The cross-border e-commerce loan monitoring method according to claim 1 is characterized in that: The verification result includes a first verification result and a second verification result. The verification result is generated by verifying whether the historical transactions of the associated store under the cross-border e-commerce are legal and true based on the operation information, including: According to the operation information, verify the integrity and authenticity of the operation information through a blockchain-based smart contract to generate the first verification result; Perform big data analysis on the operation information, verify the legitimacy of the historical transactions, and generate the second verification result.

4. The cross-border e-commerce loan monitoring method according to claim 1, characterized in that: The market information representing the overall situation of industry trends and market risks is analyzed based on the business registration information and historical operating data of the cross-border e-commerce company, combined with macroeconomic indicators, including: Based on the business registration information and historical operating data of the cross-border e-commerce, combined with historical macroeconomic indicators, long short-term memory networks and attention mechanisms are used to predict industry trends; Use topic models to analyze industry news and identify consumer trends; Analyze key market events through event detection algorithms to generate risk information, and the consumer dynamics and risk information constitute the overall market risk situation; The market information is generated according to the industry trend, the consumer dynamics and the risk information.

5. The cross-border e-commerce loan monitoring method according to claim 1, characterized in that: Generating the credit rating of the cross-border e-commerce company according to the operation information, the verification result and the market information includes: Calculating a credit score through hierarchical analysis based on the operation information, the verification result and the market information; Based on the credit score, the credit rating of the cross-border e-commerce company is dynamically adjusted according to the historical credit record and real-time operation information of the cross-border e-commerce company.

6. The cross-border e-commerce loan monitoring method according to claim 1, characterized in that: Before determining the credit limit of the cross-border e-commerce company according to the credit rating of the cross-border e-commerce company through a preset chain prediction model, the method further includes: A chain prediction model is constructed based on a deep learning framework, and model parameters of the chain prediction model are optimized through a learning mechanism.

7. The cross-border e-commerce loan monitoring method according to claim 1, characterized in that: The method further comprises: Real-time monitoring of the cross-border e-commerce operation information; When abnormal transactions are detected through the operational information, risk control measures are automatically triggered.

8. A cross-border e-commerce loan monitoring system, characterized in that: include: An acquisition unit, used to acquire information of associated stores of a cross-border e-commerce company, and to construct a graph database based on the information of the associated stores, so as to acquire operation information of the cross-border e-commerce company through the graph database; A verification unit, used to verify whether the historical transactions of the associated stores under the cross-border e-commerce are legal and true according to the operation information, and generate a verification result; A market unit, which is used to analyze market information representing industry trends and overall market risks based on the business registration information and historical operating data of the cross-border e-commerce company in combination with macroeconomic indicators; A credit unit, configured to generate a credit rating of the cross-border e-commerce company based on the operation information, the verification result and the market information; The credit limit unit is used to determine the credit limit of the cross-border e-commerce company according to the credit rating of the cross-border e-commerce company through a preset chain prediction model.

9. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the cross-border e-commerce loan monitoring method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the cross-border e-commerce loan monitoring method as described in any one of claims 1 to 7.

Images