Method and device for determining transaction risk level based on block chain

Abstract

The invention discloses a method and device for determining a transaction risk level based on a block chain, and relates to the technical field of block chains and the field of financial science and technology, and the method comprises the steps: collecting first data, second data and third data of a target transaction after the authorization information of a participating object corresponding to the target transaction is received, the first data at least comprises a transaction limit, a transaction product, transaction time and a participation object address of a target transaction stored on the block chain, the second data is historical transaction data between participation objects corresponding to the target transaction, and the third data is satellite live data of the participation object address corresponding to the target transaction; and determining L target risk factors based on the first data, and determining a risk level corresponding to the target transaction based on the second data, the third data, the L target risk factors and the weight value of each target risk factor. The technical problem of low accuracy of predicting the cross-border transaction risk level based on expert experience in the prior art is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of blockchains and the technical field of financial technology, in particular, to a method and device for determining a transaction risk level based on a blockchain. BACKGROUND

[0002] With the deepening development of globalization, cross-border transactions are becoming increasingly frequent, and their inherent risks are becoming complex and changeable. Financial institutions traditionally rely on expert experience, historical data analysis, and credit rating methods when assessing cross-border transaction risks. However, in the face of growing transaction volumes, rapidly changing market environments, and emerging risk types, relying solely on expert experience for risk level prediction is increasingly insufficient in terms of accuracy and difficulty in capturing long-range dependencies and potential market signals, resulting in the technical problem of low accuracy in predicting cross-border transaction risk levels based on expert experience.

[0003] To address the above problems, no effective solutions have been proposed so far. SUMMARY

[0004] The present application provides a method and device for determining a transaction risk level based on a blockchain to at least solve the technical problem of low accuracy in predicting cross-border transaction risk levels based on expert experience in the prior art.

[0005] According to one aspect of the present application, a method for determining a transaction risk level based on a blockchain is provided, comprising: after receiving authorization information of a target transaction corresponding participant, collecting first data, second data, and third data of the target transaction, wherein the first data at least includes transaction amount, transaction product, transaction time, and participant address of the target transaction stored on the blockchain, the second data is historical transaction data between participants corresponding to the target transaction, and the third data is satellite live data of the participant address corresponding to the target transaction; determining L target risk factors based on the first data, wherein L is a positive integer, and each target risk factor in the L target risk factors corresponds to a weight value; determining a risk level corresponding to the target transaction based on the second data, the third data, the L target risk factors, and the weight value of each target risk factor.

[0006] Optionally, the step of collecting the first data and the second data of the target transaction comprises: determining, by the first module, a transaction identifier of the target transaction, wherein the first module is connected with a block chain for storing transaction information between participating objects of the target transaction, the transaction identifier is in a hash string format recognizable by the block chain; searching in the block chain based on the transaction identifier to obtain original encrypted data, wherein the original encrypted data is the transaction information and historical transaction information of the target transaction stored in the block chain after being encrypted; and decrypting, by the first module, the original encrypted data to determine the first data and the second data according to a decryption result.

[0007] Optionally, the step of collecting the third data of the target transaction comprises: obtaining a port identifier, a factory identifier and an address identifier corresponding to the target transaction, wherein the port identifier is an identifier of a port for transporting a transaction product corresponding to the target transaction, the factory identifier is an identifier of a factory for producing the transaction product corresponding to the target transaction, and the address identifier is an identifier of an address to which a participating object corresponding to the target transaction belongs; collecting first sub-data, second sub-data and third sub-data based on the port identifier, the factory identifier and the address identifier, wherein the first sub-data is used to represent a satellite live of the port corresponding to the port identifier, the second sub-data is used to represent a satellite live of the factory corresponding to the factory identifier, and the third sub-data is used to represent a satellite live of the address corresponding to the address identifier; and taking the first sub-data, the second sub-data and the third sub-data as the third data.

[0008] Optionally, the step of determining the L target risk factors based on the first data comprises: performing data cleaning on the first data to obtain first cleaning data corresponding to the first data, wherein the data cleaning is at least used to remove abnormal data and invalid data in the first data; performing a desensitization operation on the first cleaning data to obtain first desensitization data corresponding to the first cleaning data, wherein the desensitization operation is at least used to update sensitive parameter values in the first cleaning data; performing format conversion on the first desensitization data to obtain first quantum data, wherein the format conversion is used to update the first desensitization data into data in a quantum bit format; and analyzing, by a preset quantum platform, the first quantum data based on a preset algorithm to obtain the L target risk factors.

[0009] Optionally, the step of determining the risk level corresponding to the target transaction based on the second data, the third data, the L target risk factors and the weight value of each target risk factor comprises: performing feature extraction on the second data to obtain first features, wherein the first features are used to at least represent the historical transaction amount corresponding to the historical transaction data, the historical transaction frequency and the historical credit score of the participating object; performing feature extraction on the third data to obtain second features, wherein the second features are used to at least represent the cargo throughput of the port corresponding to the target transaction, the product production of the factory and the economic activity of the address to which the participating object belongs; inputting the first features, the second features, the L target risk factors and the weight value of each target risk factor into a target model to obtain the risk level corresponding to the target transaction, wherein the target model is a neural network model trained based on all historical transaction information stored on the blockchain and satellite live data of the participating object address corresponding to the historical transaction.

[0010] Optionally, the training step of the target model comprises: grouping all historical transaction data stored on the blockchain and satellite live data of the participating object address corresponding to the historical transaction based on the identification of the participating object of the historical transaction to obtain P data sets, wherein P is a positive integer, each data set corresponds to a group of participating object identifications, and each data set includes all historical transaction data corresponding to a group of participating objects and satellite live data of the address; performing feature extraction on the P data sets to obtain P first historical features and P second historical features, wherein each first historical feature is used to represent the characteristics of the historical transaction data in different dimensions in the corresponding data set, and each second historical feature is used to represent the characteristics of the satellite live data in different dimensions in the corresponding data set; training an initial neural network model based on the P first historical features and the P second historical features to obtain the target model.

[0011] Optionally, after determining the risk level corresponding to the target transaction based on the second data, the third data, the L target risk factors and the weight value of each target risk factor, the transaction risk level determination method based on the blockchain further comprises: generating prompt information based on the L target risk factors and the risk level, wherein the prompt information at least includes the risk type of the target transaction and the transaction decision suggestion.

[0012] According to another aspect of the present application, a device for determining a risk level of a transaction based on a blockchain is also provided, comprising: a data acquisition unit configured to acquire first data, second data and third data of a target transaction after receiving authorization information of a participant corresponding to the target transaction, wherein the first data at least includes a transaction amount, a transaction product, a transaction time and a participant address of the target transaction stored on the blockchain, the second data is historical transaction data between participants corresponding to the target transaction, and the third data is satellite live data of the participant address corresponding to the target transaction; a first determination unit configured to determine L target risk factors based on the first data, wherein L is a positive integer, and each of the L target risk factors corresponds to a weight value; and a second determination unit configured to determine a risk level corresponding to the target transaction based on the second data, the third data, the L target risk factors and the weight value of each target risk factor.

[0013] According to another aspect of the present application, a computer program product is also provided, wherein the computer program product stores a computer program, and when the computer program runs, the computer program product controls the computer program to execute the method for determining a risk level of a transaction based on a blockchain according to any one of the above aspects.

[0014] According to another aspect of the present application, an electronic device is also provided, wherein the electronic device comprises one or more processors and a memory, and the memory is configured to store 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 method for determining a risk level of a transaction based on a blockchain according to any one of the above aspects.

[0015] In the present application, first, after receiving authorization information of a participant corresponding to a target transaction, first data, second data and third data of the target transaction are acquired, wherein the first data at least includes a transaction amount, a transaction product, a transaction time and a participant address of the target transaction stored on the blockchain, the second data is historical transaction data between participants corresponding to the target transaction, and the third data is satellite live data of the participant address corresponding to the target transaction, then, L target risk factors are determined based on the first data, wherein L is a positive integer, and each of the L target risk factors corresponds to a weight value, and finally, a risk level corresponding to the target transaction is determined based on the second data, the third data, the L target risk factors and the weight value of each target risk factor.

[0016] From the above, the application achieves the purpose of improving the accuracy of cross-border transaction risk assessment by integrating the transaction data, historical transaction data and satellite time data of the target transaction stored on the blockchain. Specifically, the transaction data stored on the blockchain ensures the authenticity and integrity of the transaction information. Then, the application performs quantum analysis on the real and complete transaction data through a preset quantum platform, thereby refining more systematic and objective target risk factors. Then, the application combines the real-time features of macro and geographical dimensions provided by the historical transaction data and satellite real-time data to perform risk assessment, thereby enhancing the comprehensiveness of risk assessment.

[0017] Therefore, the application achieves the purpose of reducing the financial risk assessment deviation caused by information lag through multi-source data fusion, thereby achieving the technical effect of improving the accuracy of risk prediction, and further solving the technical problem of low accuracy of predicting the risk level of cross-border transactions based on expert experience in the prior art. BRIEF DESCRIPTION OF DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the application, and form a part of the application. The illustrative embodiments of the application and their descriptions serve to explain the application, and do not constitute an improper limitation on the application. In the drawings:

[0019] Figure 1 is a flowchart of an optional method for determining a transaction risk level based on a blockchain according to an embodiment of the application;

[0020] Figure 2 is a schematic diagram of an optional device for determining a transaction risk level based on a blockchain according to an embodiment of the application;

[0021] Figure 3 is a structural block diagram of an electronic device according to an embodiment of the application. DETAILED DESCRIPTION

[0022] In order for those skilled in the art to better understand the application, the technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only a part of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the application.

[0023] 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 sequential order. 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 a sequence 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.

[0024] It should also be noted that the relevant information (including but not limited to information for display and analysis) and data (including but not limited to the first data, second data, and third data of the target transaction) involved in this application are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set up between this system and the relevant users or institutions. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned users or institutions through the interface, and obtain the relevant information after receiving the consent information fed back by the aforementioned users or institutions.

[0025] In addition, the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant information and data involved in this application comply with the relevant laws, regulations and standards of the relevant regions, and necessary confidentiality measures have been taken, and do not violate public order and good morals. In addition, this application provides corresponding operation entrances for users to choose to agree to authorization or refuse authorization. If the user chooses to refuse authorization, he / she will enter the corresponding expert decision-making process.

[0026] The professional terms involved in this application are explained as follows:

[0027] Quantum computing: Leveraging quantum parallel computing capabilities and quantum algorithms to process massive and complex cross-border financial transaction data and related risk factor data. For example, quantum annealing algorithms can be used to solve large-scale combinatorial optimization problems that are difficult for traditional computers to handle. In risk assessment models, relatively optimal risk factor combinations and weight distributions can be quickly found to more accurately assess risks. At the same time, the simulation capabilities of quantum computing can be used to simulate and predict various complex market scenarios and risk events, providing early insights into potential risk trends.

[0028] Blockchain: Utilizing the distributed ledger, immutability, and smart contract features of blockchain technology, the authenticity, integrity, and security of cross-border financial transaction data are ensured. Each cross-border financial transaction and related information in this application are recorded in encrypted form on the blockchain, forming an immutable transaction history to prevent data from being maliciously tampered with or forged.

[0029] Satellite real-time data: Satellite remote sensing technology is used to obtain geospatial data and macro-environmental data related to cross-border financial transactions, such as port cargo throughput, factory production activity data, city light brightness data, etc., in order to infer the activity of trade activities and the operating status of the real economy of the parties involved in the transaction.

[0030] Multi-source data fusion: Establish a unified data warehouse and data model to clean, convert and standardize data from different sources and formats so that they can be analyzed under the same framework.

[0031] Deep data analysis: Use deep learning and artificial intelligence algorithms to conduct in-depth mining and analysis of the integrated data. For example, use deep neural networks to build risk assessment models, automatically learn complex features and patterns in the data, and identify the correlations between different data, so as to more accurately assess the risk level of cross-border financial transactions. At the same time, use time series analysis algorithms to dynamically monitor and predict risk indicators, timely identify changing trends and abnormal fluctuations in risks, and implement risk warnings.

[0032] Decision support: Based on the type and degree of risk, the system can recommend corresponding risk management measures, such as adjusting transaction limits, increasing collateral requirements, optimizing investment portfolios, etc., to help users make scientific and reasonable decisions and reduce the risks of cross-border financial transactions.

[0033] In an optional prior art embodiment, the prior art solution provides an optional risk analysis method based on traditional statistics, which includes:

[0034] (1) Ratio analysis: By calculating various financial ratios of cross-border enterprises or transaction entities, such as solvency ratios (current ratio, quick ratio, debt-to-asset ratio, etc.), profitability ratios (gross profit margin, net profit margin, etc.), operating capacity ratios (accounts receivable turnover rate, inventory turnover rate, etc.), and comparing them with industry standards or historical data, the asset health and risk level are assessed. If certain ratios deviate from the normal range, it may indicate the existence of risks.

[0035] (2) Regression analysis: Establish a regression model between risk indicators and influencing factors, for example, take macroeconomic factors such as exchange rate fluctuations, interest rate changes, etc. as independent variables, and take the income or loss of cross-border financial transactions as dependent variables, analyze the regression coefficients to assess the degree of influence of each factor on risk, and then predict the trend of risk changes.

[0036] However, the prior art embodiments have the following technical defects:

[0037] (1) Difficulty in capturing complex patterns: Traditional statistical methods (such as linear regression) are difficult to capture complex patterns and non-linear relationships in data, which is particularly important in cross-border financial transactions, as transaction data is usually highly complex and dynamic.

[0038] (2) Dependence on historical data: Traditional statistical methods mainly rely on historical data for analysis, making it difficult to respond to rapidly changing market environments and emerging risks.

[0039] (3) Lack of robustness: In the face of outliers, noisy data or model assumptions that do not hold, traditional statistical methods have poor robustness, which may lead to unreliable analysis results.

[0040] (4) Difficulty in handling high-dimensional data: As the size of the data increases, traditional statistical methods may encounter high computational complexity, overfitting and other problems when dealing with high-dimensional data.

[0041] According to the embodiments of the present application, an embodiment of a method for determining the risk level of a transaction based on a blockchain 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 herein can be executed in a different order.

[0042] The present application provides a determination system for determining the risk level of a transaction based on a blockchain (referred to as a determination system) for executing the method for determining the risk level of a transaction based on a blockchain in the present application, Figure 1 is an optional flowchart of a method for determining the risk level of a transaction based on a blockchain according to an embodiment of the present application, as Figure 1 shown, the method comprises the following steps:

[0043] Step S101, after receiving the authorization information of the target transaction corresponding to the participating object, collecting the first data, the second data and the third data of the target transaction, wherein the first data at least includes the transaction amount, the transaction product, the transaction time and the participating object address of the target transaction stored on the blockchain, the second data is the historical transaction data between the participating objects corresponding to the target transaction, and the third data is the satellite live data of the participating object address corresponding to the target transaction.

[0044] Optionally, the first data refers to target transaction information stored on the blockchain, including transaction amount, transaction product, transaction time, and participant address, wherein the participants include at least the initiator and the transaction party of the target transaction.

[0045] Optionally, the second data refers to historical transaction data between the participants, which covers detailed information of past transactions between the two parties. Analysis of historical data helps identify transaction patterns and potential risks. Similarly, the second data is also stored on the blockchain.

[0046] Optionally, since the information stored in the blockchain is tamper-proof, it ensures the authenticity and integrity of the data obtained by the determination system, providing a reliable basis for subsequent evaluation of target risk factors.

[0047] Optionally, the third data involves real-time geospatial information of the participant address, such as port activity and city light intensity. These data reflect the macroeconomic environment and entity activity, providing a new perspective for evaluating transaction risks.

[0048] Optionally, step S101 collects multi-source data related to the target transaction, providing information support for subsequent risk assessment and early warning. The determination system uses blockchain technology, historical record tracing technology, and satellite monitoring technology to ensure the breadth and depth of the risk assessment data, covering both micro details and macro environment of the transaction, thereby improving the accuracy of subsequent risk assessment.

[0049] Step S102 determines L target risk factors based on the first data, wherein L is a positive integer, and each of the L target risk factors corresponds to a weight value.

[0050] Optionally, the L target risk factors are a relatively ideal combination of risk factors determined by quantum evaluation of the first data on a pre-set quantum platform. Each factor represents a dimension of transaction risk, and each target risk factor corresponds to a weight value. The weight value quantifies the importance of the risk factor in the overall risk assessment, and is determined based on the contribution of the factor to the risk. The weight value can be set or adjusted through machine learning or expert systems.

[0051] Step S103 determines the risk level corresponding to the target transaction based on the second data, the third data, the L target risk factors, and the weight value of each target risk factor.

[0052] Optionally, the risk level is usually divided into multiple levels, such as low risk, medium risk, and high risk, to guide the decision-making and risk control strategy of financial institutions.

[0053] Optionally, step S103 considers the historical transaction data, satellite real-time monitoring data and quantum computing optimized risk factors and their weight values, and finally outputs the risk level of the target transaction through data analysis or model calculation. This step converts the information fusion of multi-source data into a visual risk assessment result for subsequent early warning and decision support, realizes a closed-loop process from data collection to risk assessment, and improves the accuracy and practicality of cross-border transaction risk assessment.

[0054] From the above, the present application integrates the transaction data, historical transaction data and satellite data of the target transaction stored on the blockchain to improve the accuracy of cross-border transaction risk assessment. Specifically, the transaction data stored on the blockchain ensures the authenticity and integrity of the transaction information. Then, the present application performs quantum analysis on the real and complete transaction data through a preset quantum platform to extract more systematic and objective target risk factors. Then, the present application combines the real-time features of macro and geographical dimensions provided by the historical transaction data and satellite real-time data to perform risk assessment, thereby enhancing the comprehensiveness of risk assessment.

[0055] Therefore, the present application realizes the purpose of reducing the financial risk assessment deviation caused by information lag through multi-source data fusion, thereby realizing the technical effect of improving the accuracy of risk prediction, and further solving the technical problem of low accuracy of predicting the risk level of cross-border transactions based on expert experience in the prior art.

[0056] In an optional embodiment, the determination system first determines the transaction identifier of the target transaction through the first module, wherein the first module is connected with the blockchain for storing the transaction information between the participants of the target transaction. The transaction identifier is in the form of a hash string that can be recognized by the blockchain. Then, the determination system performs a search in the blockchain based on the transaction identifier to obtain the original encrypted data, wherein the original encrypted data is the encrypted transaction information and historical transaction information of the target transaction stored in the blockchain. Then, the determination system decrypts the original encrypted data through the first module, and determines the first data and the second data according to the decryption result.

[0057] Optionally, the first module refers to a functional module responsible for interacting with the blockchain, querying and decrypting data.

[0058] Optionally, the transaction identifier specifically refers to a hash string that can uniquely identify the target transaction. The hash string format ensures the uniqueness and irreversibility of the transaction identifier. The determination of the transaction identifier is the basis of the entire data query process. The transaction identifier can locate and obtain the transaction data corresponding to the target transaction from the huge blockchain database, and also ensures the data security of the transaction data.

[0059] Optionally, the original encrypted data refers to the target transaction information and related historical transaction data existing on the blockchain and processed by the blockchain technology, and the encryption technology can protect the security and privacy of the transaction data, and ensure that the data is not illegally accessed or tampered with during data transmission and storage.

[0060] Optionally, the first module decrypts the original encrypted data, where decryption refers to the process of restoring the encrypted data obtained from the blockchain to a readable format. Decryption requires the use of a corresponding private key or decryption algorithm, and only authorized parties with the correct key can complete this process.

[0061] In the above embodiment, the first module uses a pre-set decryption method to restore the obtained original encrypted data to its original readable state, obtaining non-encrypted transaction information and historical transaction records. The decryption process ensures the privacy and security of the data, and also ensures the legality and authorized scope of data use. The decrypted first data and second data not only contain real-time information of the target transaction, but also cover the past transaction behavior of the transaction subject, thereby providing a detailed data basis for subsequent risk factor analysis and risk level determination.

[0062] In an optional embodiment, the determination system first acquires a port identifier, a factory identifier, and an address identifier corresponding to the target transaction, wherein the port identifier is an identifier of a port transporting a transaction product corresponding to the target transaction, the factory identifier is an identifier of a factory producing the transaction product corresponding to the target transaction, and the address identifier is an identifier of an address to which a participant of the target transaction belongs. Then, the determination system collects first sub-data, second sub-data, and third sub-data based on the port identifier, the factory identifier, and the address identifier, wherein the first sub-data is used to represent satellite live of the port corresponding to the port identifier, the second sub-data is used to represent satellite live of the factory corresponding to the factory identifier, and the third sub-data is used to represent satellite live of the address corresponding to the address identifier. Then, the determination system takes the first sub-data, the second sub-data, and the third sub-data as the third data.

[0063] Optionally, the port identifier is used to locate and identify geographical location information directly related to the transportation of the transaction product; the factory identifier is an identifier of a factory producing a commodity or service involved in the target transaction, and is used to trace the origin of the commodity and evaluate the production capacity and stability of the factory; and the address identifier is an identifier of a geographical location of a participant of the target transaction, i.e., a buyer or a seller, so that the determination system can comprehensively analyze the macro regional economic conditions and macro dimension economic risks of the participant.

[0064] Optionally, the first, second and third sub-data respectively correspond to satellite live data of the port, the factory and the address of the participating object, including but not limited to cargo throughput of the port, production activity status (such as cargo production throughput) of the factory and macro-dimension economic data of the area where the participating object is located (such as economic level of the area through night light intensity feedback).

[0065] Optionally, the determination system collects satellite live data corresponding to the identifiers through a satellite data receiving module, and the live data provides intuitive evidence of macro-dimension economic environment and entity activity behind the cross-border transaction, such as busy degree of the port, production status of the factory and macro-dimension economic status of the area, thereby providing a risk analysis perspective that traditional financial data cannot reflect. By collecting the above data, the determination system can examine the transaction risk from a broader geographical space and macro-dimension economic perspective, thereby providing strong supplementary information for subsequent deep data analysis and risk assessment.

[0066] In an optional embodiment, the determination system first performs data cleaning on the first data to obtain first cleaning data corresponding to the first data, wherein the data cleaning is at least used to remove abnormal data and invalid data in the first data, then the determination system performs a desensitization operation on the first cleaning data to obtain first desensitization data corresponding to the first cleaning data, wherein the desensitization operation is at least used to update sensitive parameter values in the first cleaning data, then the determination system performs format conversion on the first desensitization data to obtain the first quantum data, wherein the format conversion is used to update the first desensitization data to data in a quantum bit format, and the determination system analyzes the first quantum data based on a preset algorithm through a preset quantum platform to obtain the L target risk factors.

[0067] Optionally, the determination system performs deep cleaning on the first data obtained from the blockchain, identifies and excludes abnormal data and invalid data that may interfere with the analysis result through an automatic or semi-automatic algorithm, thereby avoiding negative impact of noise data on subsequent analysis and improving risk prediction accuracy.

[0068] Optionally, the desensitization operation performs fuzzing or encoding conversion on the sensitive parameter values, so that the first desensitization data still retains effective information for risk factor analysis while protecting privacy, thereby balancing the legal use of data and the demand for privacy protection.

[0069] Optionally, format conversion refers to converting the first desensitized data into a format processable by a quantum computer, namely a qubit format. Format conversion is a critical bridge between classical data processing and quantum computing. Because the input data format of a quantum computer differs significantly from that of a traditional computer, converting the first desensitized data into a qubit format is necessary to facilitate quantum algorithm computation. This ensures that quantum computing resources are fully utilized, significantly improving the speed and complexity of data processing and providing efficient data processing capabilities for the subsequent risk factor determination.

[0070] Optionally, the preset algorithm is a quantum annealing algorithm.

[0071] Optionally, the determination system runs a preset algorithm on the quantum computing platform to conduct an in-depth analysis of the first quantum data, from which L target risk factors are extracted. Through the parallel processing and quantum superposition principles of quantum computing, it can quickly identify those factors that have a decisive influence on risk assessment, and determine the corresponding weight values, providing a scientific basis for subsequent risk level determination and improving the accuracy and efficiency of risk assessment.

[0072] In an optional embodiment, the determination system first performs feature extraction on the second data to obtain a first feature, wherein the first feature is at least used to characterize the historical transaction amount, historical transaction frequency and historical credit score of the participating object corresponding to the historical transaction data. Afterwards, the determination system performs feature extraction on the third data to obtain a second feature, wherein the second feature is at least used to characterize the cargo throughput of the port corresponding to the target transaction, the product production volume of the factory and the economic activity of the address to which the participating object belongs. Then, the determination system inputs the first feature, the second feature, L target risk factors and the weight value of each target risk factor into the target model to obtain the risk level corresponding to the target transaction, wherein the target model is a neural network model trained based on satellite live data of all historical transaction information stored on the blockchain and the addresses of the participating objects corresponding to the historical transactions.

[0073] Optionally, the first feature refers to a quantitative indicator that can characterize the core attributes of historical transaction data, including historical transaction amount, historical transaction frequency, and historical credit score of the participants. These indicators reflect the financial health, transaction behavior patterns and credit history of the transaction subjects.

[0074] Optionally, through deep learning technology, the system is determined to automatically analyze and screen features in the second data that are highly relevant to risk assessment. The extraction of the first feature essentially converts complex transaction history data into indicators that the model can understand and analyze, which helps to capture the behavioral patterns and credit status of transaction entities and provide a micro-level basis for determining risk levels.

[0075] Optionally, the second feature is a set of features extracted based on satellite live data (third data), covering macro dimensions and geographic spatial dimensions such as cargo throughput of the target transaction related port, product production of the factory, and economic activity of the address to which the subject belongs, thereby reflecting market trends and regional economic health behind the transaction, providing macro-level support for risk level determination.

[0076] In an optional embodiment, the training step of the target model comprises:

[0077] First, the system determines the grouping of all historical transaction data stored on the blockchain and satellite live data of the addresses corresponding to the historical transactions based on the identities of the subjects corresponding to the historical transactions, obtaining P data sets, where P is a positive integer, each data set corresponds to a group of subject identities, and each data set includes all historical transaction data corresponding to a group of subjects and satellite live data of the addresses to which they belong. After that, the system extracts features from the P data sets to obtain P first historical features and P second historical features, wherein each first historical feature is used to represent the characteristics of the historical transaction data in different dimensions in the corresponding data set, and each second historical feature is used to represent the characteristics of the satellite live data in different dimensions in the corresponding data set. Then, the system trains the initial neural network model based on the P first historical features and the P second historical features to obtain the target model.

[0078] Optionally, the determination system aggregates the associated transaction history and satellite live data in P data sets by grouping based on the subject identifier. Through this data arrangement method, it is helpful to further explore the behavior patterns of specific transaction subjects and market environment in subsequent analysis, ensuring the relevance and completeness of the data, and laying a solid data foundation for model training.

[0079] Optionally, the extraction of first historical features and second historical features not only focuses on the micro behavior of transaction subjects, but also considers the macro influence of transaction environment, providing rich data dimensions and analysis perspectives for building a comprehensive risk assessment model.

[0080] Optionally, the iterative training process of the target model enables the target model to learn risk patterns from historical transactions and satellite data, so that it can make accurate risk level predictions even when faced with new and complex data sets.

[0081] In an optional embodiment, after determining the risk level corresponding to the target transaction based on the second data, the third data, the L target risk factors, and the weight value of each target risk factor, the determination system generates prompt information based on the L target risk factors and the risk level, wherein the prompt information at least includes the risk type of the target transaction and the transaction decision suggestion.

[0082] Optionally, after determining the risk level of the target transaction and identifying the key risk factors, the determination system automatically generates prompt information, which contains the risk type of the target transaction (such as credit risk, market risk, operational risk, etc.) and the transaction decision suggestion based on the risk assessment result (such as adjusting the transaction amount, increasing the guarantee, suspending high-risk transactions, etc.). By converting the complex risk assessment result into intuitive and easy-to-understand prompt information, the financial institution can quickly grasp the nature and degree of transaction risk, so as to take corresponding risk management measures and avoid potential economic losses.

[0083] From the above, it can be seen that the determination system achieves the purpose of improving the accuracy of cross-border transaction risk assessment by integrating the transaction data, historical transaction data and satellite moment data of the target transaction stored on the blockchain. Specifically, the transaction data stored on the blockchain ensures the authenticity and integrity of the transaction information. Then, the determination system performs quantum analysis on the real and complete transaction data through the pre-set quantum platform, so as to refine more systematic and objective target risk factors. Then, the determination system combines the real-time features of macro dimension and geographical space dimension provided by the historical transaction data and satellite real-time data for risk assessment, so as to enhance the comprehensiveness of risk assessment.

[0084] Therefore, the determination system achieves the purpose of reducing the financial risk assessment deviation caused by information lag by means of multi-source data fusion, thereby achieving the technical effect of improving the accuracy of risk prediction, and further solving the technical problem of low accuracy of predicting the risk level of cross-border transactions based on expert experience in the prior art.

[0085] According to another aspect of the embodiments of the present application, a determination device for transaction risk level based on blockchain is also provided, Figure 2 is a schematic diagram of an optional determination device for transaction risk level based on blockchain according to an embodiment of the present application, as Figure 2 shown, the determination device for transaction risk level based on blockchain includes a data acquisition unit 201, a first determination unit 202 and a second determination unit 203.

[0086] Optionally, the data collection unit is used to collect first data, second data and third data of the target transaction after receiving authorization information of the participating object corresponding to the target transaction, wherein the first data includes at least the transaction amount, transaction product, transaction time and participating object address of the target transaction stored on the blockchain, the second data is the historical transaction data between the participating objects corresponding to the target transaction, and the third data is the satellite real-time data of the participating object address corresponding to the target transaction; the first determination unit is used to determine L target risk factors based on the first data, wherein L is a positive integer, and each of the L target risk factors corresponds to a weight value; the second determination unit is used to determine the risk level corresponding to the target transaction based on the second data, the third data, the L target risk factors and the weight value of each target risk factor.

[0087] In an optional embodiment, the data acquisition unit includes: a first determination subunit, a search subunit, and a decryption subunit.

[0088] Optionally, the first determination subunit is used to determine the transaction identifier of the target transaction through the first module, wherein the first module is interconnected with the blockchain used to store transaction information between the participants of the target transaction, and the transaction identifier is a hash string format that can be recognized by the blockchain; the search subunit is used to search in the blockchain based on the transaction identifier to obtain the original encrypted data, wherein the original encrypted data is the encrypted transaction information and historical transaction information of the target transaction stored in the blockchain; the decryption subunit is used to decrypt the original encrypted data through the first module, and determine the first data and the second data based on the decryption result.

[0089] In an optional embodiment, the data acquisition unit further includes: a first acquisition subunit, a first collection subunit, and a second determination subunit.

[0090] Optionally, the first acquisition sub-unit is used to obtain the port identifier, factory identifier and address identifier corresponding to the target transaction, wherein the port identifier is the identifier of the port that transports the transaction product corresponding to the target transaction, the factory identifier is the identifier of the factory that produces the transaction product corresponding to the target transaction, and the address identifier is the identifier of the address of the participating object corresponding to the target transaction; the first collection sub-unit is used to collect first sub-data, second sub-data and third sub-data based on the port identifier, factory identifier and address identifier, wherein the first sub-data is used to characterize the satellite status of the port corresponding to the port identifier, the second sub-data is used to characterize the satellite status of the factory corresponding to the factory identifier, and the third sub-data is used to characterize the satellite status of the address corresponding to the address identifier; the second determination sub-unit is used to use the first sub-data, the second sub-data and the third sub-data as the third data.

[0091] In an optional embodiment, the first determining unit comprises a data cleaning subunit, a desensitization subunit, a format conversion subunit, and a quantum analysis subunit.

[0092] Optionally, the data cleaning subunit is configured to perform data cleaning on the first data to obtain first cleaning data corresponding to the first data, wherein the data cleaning is at least used to remove abnormal data and invalid data in the first data; the desensitization subunit is configured to perform a desensitization operation on the first cleaning data to obtain first desensitization data corresponding to the first cleaning data, wherein the desensitization operation is at least used to update sensitive parameter values in the first cleaning data; the format conversion subunit is configured to perform format conversion on the first desensitization data to obtain first quantum data, wherein the format conversion is used to update the first desensitization data into data in a quantum bit format; and the quantum analysis subunit is configured to analyze the first quantum data based on a preset algorithm through a preset quantum platform to obtain the L target risk factors.

[0093] In an optional embodiment, the second determining unit comprises a first extraction subunit, a second extraction subunit, and an input subunit.

[0094] Optionally, the first extraction subunit is configured to perform feature extraction on the second data to obtain first features, wherein the first features are at least used to represent historical transaction amounts, historical transaction frequencies, and historical credit scores of the participating objects corresponding to the historical transaction data; the second extraction subunit is configured to perform feature extraction on the third data to obtain second features, wherein the second features are at least used to represent cargo throughput of the port, product production of the factory, and economic activity of the address to which the participating object belongs corresponding to the target transaction; and the input subunit is configured to input the first features, the second features, the L target risk factors, and weight values of each target risk factor into a target model to obtain a risk level corresponding to the target transaction, wherein the target model is a neural network model trained based on all historical transaction information stored on the blockchain and satellite live data of the participating object addresses corresponding to the historical transactions.

[0095] In an optional embodiment, the device for determining a transaction risk level based on a blockchain further comprises a grouping unit, a feature extraction unit, and a training unit.

[0096] Optionally, the grouping unit is configured to group all historical transaction data stored on the blockchain and satellite live data of addresses of participants corresponding to the historical transaction based on the identities of the participants corresponding to the historical transaction to obtain P data sets, wherein P is a positive integer, each data set corresponds to a group of participant identities, and each data set includes all historical transaction data of the group of participants and satellite live data of the addresses of the group of participants; the feature extraction unit is configured to extract features from the P data sets to obtain P first historical features and P second historical features, wherein each first historical feature is used to represent the historical transaction data in different dimensions in the corresponding data set, and each second historical feature is used to represent the satellite live data in different dimensions in the corresponding data set; and the training unit is configured to train an initial neural network model based on the P first historical features and the P second historical features to obtain a target model.

[0097] In an optional embodiment, the device for determining a risk level of a transaction based on a blockchain further includes an information generation unit.

[0098] Optionally, the information generation unit is configured to generate prompt information based on the L target risk factors and the risk level, wherein the prompt information at least includes a risk type of the target transaction and a transaction decision suggestion.

[0099] As can be seen from the above, the determination device integrates the transaction data, historical transaction data, and satellite data at the moment of the target transaction stored on the blockchain, thereby achieving the purpose of improving the accuracy of cross-border transaction risk assessment. Specifically, the transaction data stored on the blockchain ensures the authenticity and integrity of the transaction information. Then, the determination device performs quantum analysis on the authentic and complete transaction data through a preset quantum platform, thereby refining more systematic and objective target risk factors. Then, the determination device combines the real-time features in the macro dimension and the geographical space dimension provided by the historical transaction data and satellite live data to perform risk assessment, thereby enhancing the comprehensiveness of risk assessment.

[0100] Therefore, the determination device achieves the purpose of reducing the deviation of financial risk assessment caused by information lag through multi-source data fusion, thereby achieving the technical effect of improving the accuracy of risk prediction, and further solving the technical problem of low accuracy of predicting the risk level of cross-border transactions based on expert experience in the prior art.

[0101] According to another aspect of the embodiments of the present application, a computer program product is also provided, which includes a stored computer program. When the computer program runs, the computer program product controls the computer program product to perform the determination method of the risk level of a transaction based on a blockchain in any of the above aspects.

[0102] According to another aspect of an embodiment of the present application, an electronic device is also provided, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any of the above-mentioned methods for determining the blockchain-based transaction risk level by executing the executable instructions.

[0103] An embodiment of the present application may provide an electronic device, Figure 3 This is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 3 As shown, the electronic device may include: one or more ( Figure 3 Only one is shown) processor 302, memory 304, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0104] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, implementing the above-mentioned method. The memory 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 instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal 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.

[0105] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: after receiving the authorization information of the participating object corresponding to the target transaction, collect the first data, second data and third data of the target transaction, wherein the first data at least includes the transaction amount, transaction product, transaction time and participating object address of the target transaction stored on the blockchain, the second data is the historical transaction data between the participating objects corresponding to the target transaction, and the third data is the satellite real-time data of the participating object address corresponding to the target transaction; determine L target risk factors based on the first data, wherein L is a positive integer, and each of the L target risk factors corresponds to a weight value; determine the risk level corresponding to the target transaction based on the second data, the third data, the L target risk factors and the weight value of each target risk factor.

[0106] The processor can call information and application programs stored in the memory through the transmission device to perform the following steps: determining, by the first module, a transaction identifier of a target transaction, wherein the first module is connected with a block chain for storing transaction information between a participant of the target transaction, the transaction identifier is in a hash string format recognizable by the block chain; searching in the block chain based on the transaction identifier to obtain original encrypted data, wherein the original encrypted data is encrypted transaction information and historical transaction information of the target transaction stored in the block chain; and decrypting, by the first module, the original encrypted data to determine first data and second data according to a decryption result.

[0107] The processor can call information and application programs stored in the memory through the transmission device to perform the following steps: obtaining a port identifier, a factory identifier and an address identifier corresponding to a target transaction, wherein the port identifier is an identifier of a port for transporting a transaction product corresponding to the target transaction, the factory identifier is an identifier of a factory for producing the transaction product corresponding to the target transaction, and the address identifier is an identifier of an address to which a participant of the target transaction belongs; collecting first sub-data, second sub-data and third sub-data based on the port identifier, the factory identifier and the address identifier, wherein the first sub-data is used to represent satellite live of the port corresponding to the port identifier, the second sub-data is used to represent satellite live of the factory corresponding to the factory identifier, and the third sub-data is used to represent satellite live of the address corresponding to the address identifier; and taking the first sub-data, the second sub-data and the third sub-data as third data.

[0108] The processor can call information and application programs stored in the memory through the transmission device to perform the following steps: performing data cleaning on the first data to obtain first cleaning data corresponding to the first data, wherein the data cleaning is at least used to remove abnormal data and invalid data in the first data; performing a desensitization operation on the first cleaning data to obtain first desensitization data corresponding to the first cleaning data, wherein the desensitization operation is at least used to update sensitive parameter values in the first cleaning data; performing format conversion on the first desensitization data to obtain first quantum data, wherein the format conversion is used to update the first desensitization data into data in a quantum bit format; and analyzing, by a preset quantum platform, the first quantum data based on a preset algorithm to obtain L target risk factors.

[0109] The processor can call information and application programs stored in the memory through the transmission device to perform the following steps: performing feature extraction on the second data to obtain first features, wherein the first features are used to at least represent historical transaction amounts, historical transaction frequencies, and historical credit scores of the participating objects corresponding to the historical transaction data; performing feature extraction on the third data to obtain second features, wherein the second features are used to at least represent cargo throughput of the port corresponding to the target transaction, product production of the factory, and economic activity of the address to which the participating object belongs; inputting the first features, the second features, L target risk factors, and weight values of each target risk factor into the target model to obtain a risk level corresponding to the target transaction, wherein the target model is a neural network model trained based on all historical transaction information stored on the blockchain and satellite live data of the participating object addresses corresponding to the historical transactions.

[0110] The processor can call information and application programs stored in the memory through the transmission device to perform the following steps: grouping all historical transaction data stored on the blockchain and satellite live data of the participating object addresses corresponding to the historical transactions based on the identities of the participating objects corresponding to the historical transactions to obtain P data sets, wherein P is a positive integer, each data set corresponds to a group of participating object identities, and each data set includes all historical transaction data corresponding to a group of participating objects and satellite live data of the addresses to which the participating objects belong; performing feature extraction on the P data sets to obtain P first historical features and P second historical features, wherein each first historical feature is used to represent the characteristics of the historical transaction data in different dimensions in the corresponding data set, and each second historical feature is used to represent the characteristics of the satellite live data in different dimensions in the corresponding data set; training an initial neural network model based on the P first historical features and the P second historical features to obtain a target model.

[0111] The processor can call information and application programs stored in the memory through the transmission device to perform the following steps: generating prompt information based on the L target risk factors and the risk level, wherein the prompt information at least includes a risk type of the target transaction and a transaction decision suggestion.

[0112] By adopting the embodiment of the present application, a technical scheme of a method for determining a transaction risk level based on a block chain is provided. The present application integrates the transaction data, the historical transaction data and the satellite time data of the target transaction stored on the block chain, so as to improve the accuracy of cross-border transaction risk assessment. Specifically, the transaction data stored on the block chain ensures the authenticity and integrity of the transaction information. Then, the present application performs quantum analysis on the authentic and complete transaction data through a preset quantum platform, so as to extract more systematic and objective target risk factors. Then, the present application performs risk assessment in combination with the real-time features of the macro dimension and the geographical space dimension provided by the historical transaction data and the satellite real-time data, so as to enhance the comprehensiveness of risk assessment.

[0113] Therefore, the present application realizes the purpose of reducing the financial risk assessment deviation caused by information lag through the way of multi-source data fusion, so as to realize the technical effect of improving the accuracy of risk prediction, and further solves the technical problem of low accuracy of predicting the cross-border transaction risk level based on expert experience in the prior art.

[0114] Those skilled in the art can understand that, Figure 3 The structure shown is only schematic, and the electronic device can also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, and the like. Figure 3 It does not limit the structure of the above-mentioned electronic device. For example, the electronic device can further include more or less components (such as a network interface, a display device, etc.) than those shown in the figure, or have a different configuration from that shown in the figure. Figure 3 It does not limit the structure of the above-mentioned electronic device. For example, the electronic device can further include more or less components (such as a network interface, a display device, etc.) than those shown in the figure, or have a different configuration from that shown in the figure. Figure 3 It does not limit the structure of the above-mentioned electronic device. For example, the electronic device can further include more or less components (such as a network interface, a display device, etc.) than those shown in the figure, or have a different configuration from that shown in the figure.

[0115] Those skilled in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by programs instructing the related hardware of the terminal device. The programs can be stored in a computer readable storage medium, which can include a flash disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, etc.

[0116] The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0117] In the above-mentioned embodiments of the present application, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0118] In several embodiments provided in the present application, it should be understood that the disclosed technology can be implemented by other ways. Among them, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, units or modules, and can be electrical or other forms.

[0119] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0120] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0121] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art that contributes to the technical solutions or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0122] The above is only the preferred embodiment of the present application, and it should be pointed out that for ordinary skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A method for determining transaction risk level based on blockchain, characterized in that: include: After receiving authorization information from a participant in a target transaction, first data, second data, and third data of the target transaction are collected, wherein the first data includes at least the transaction amount, transaction product, transaction time, and address of the participant in the target transaction stored on the blockchain; the second data is historical transaction data between the participants in the target transaction; and the third data is live satellite data of the address of the participant in the target transaction; Determine L target risk factors based on the first data, where L is a positive integer, and each of the L target risk factors corresponds to a weight value; The risk level corresponding to the target transaction is determined based on the second data, the third data, the L target risk factors, and the weight value of each target risk factor.

2. The method for determining the transaction risk level based on blockchain according to claim 1, characterized in that: Collecting the first data and the second data of the target transaction includes: Determining a transaction identifier of the target transaction by a first module, wherein the first module is interconnected with a blockchain for storing transaction information between participants in the target transaction, and the transaction identifier is in a hash string format recognizable by the blockchain; Searching the blockchain based on the transaction identifier to obtain original encrypted data, wherein the original encrypted data is encrypted transaction information and historical transaction information of the target transaction stored in the blockchain; The original encrypted data is decrypted by the first module, and the first data and the second data are determined according to the decryption result.

3. The method for determining transaction risk level based on blockchain according to claim 1, characterized in that: Collecting third data of the target transaction includes: Obtaining the port identifier, factory identifier, and address identifier corresponding to the target transaction, wherein the port identifier is the identifier of the port that transports the transaction product corresponding to the target transaction, the factory identifier is the identifier of the factory that produces the transaction product corresponding to the target transaction, and the address identifier is the identifier of the address of the participant corresponding to the target transaction; collecting first sub-data, second sub-data, and third sub-data based on the port identifier, the factory identifier, and the address identifier, wherein the first sub-data is used to represent the satellite live status of the port corresponding to the port identifier, the second sub-data is used to represent the satellite live status of the factory corresponding to the factory identifier, and the third sub-data is used to represent the satellite live status of the address corresponding to the address identifier; The first sub-data, the second sub-data, and the third sub-data are used as the third data.

4. The method for determining transaction risk level based on blockchain according to claim 1, characterized in that: Determining L target risk factors based on the first data includes: performing data cleaning on the first data to obtain first cleaned data corresponding to the first data, wherein the data cleaning is at least used to remove abnormal data and invalid data in the first data; Performing a desensitization operation on the first cleaned data to obtain first desensitized data corresponding to the first cleaned data, wherein the desensitization operation is at least used to update a sensitive parameter value in the first cleaned data; Performing format conversion on the first desensitized data to obtain first quantum data, wherein the format conversion is used to update the first desensitized data into data in a quantum bit format; The first quantum data is analyzed based on a preset algorithm through a preset quantum platform to obtain the L target risk factors.

5. The method for determining transaction risk level based on blockchain according to claim 1, characterized in that: Determining a risk level corresponding to the target transaction based on the second data, the third data, the L target risk factors, and the weight value of each target risk factor includes: Performing feature extraction on the second data to obtain a first feature, wherein the first feature is used to characterize at least a historical transaction amount and a historical transaction frequency corresponding to the historical transaction data, and a historical credit score of the participant; Performing feature extraction on the third data to obtain a second feature, wherein the second feature is used to characterize at least the cargo throughput of the port corresponding to the target transaction, the product output of the factory, and the economic activity of the address to which the participant belongs; The first feature, the second feature, the L target risk factors, and the weight value of each target risk factor are input into a target model to obtain a risk level corresponding to the target transaction, wherein the target model is a neural network model trained based on satellite live data of all historical transaction information stored on the blockchain and the addresses of participating objects corresponding to the historical transactions.

6. The method for determining transaction risk level based on blockchain according to claim 5, characterized in that: The training steps of the target model include: Based on the identifiers of the participating objects corresponding to the historical transactions, all historical transaction data stored on the blockchain and the satellite live data of the participating object addresses corresponding to the historical transactions are grouped to obtain P data sets, where P is a positive integer, each data set corresponds to a group of participating object identifiers, and each data set includes all historical transaction data corresponding to a group of participating objects and the satellite live data of the addresses belonging to the participating objects; Performing feature extraction on the P data sets to obtain P first historical features and P second historical features, wherein each first historical feature is used to characterize features of historical transaction data in a corresponding data set at different dimensions, and each second historical feature is used to characterize features of live satellite data in a corresponding data set at different dimensions; An initial neural network model is trained based on the P first historical features and the P second historical features to obtain the target model.

7. The method for determining transaction risk level based on blockchain according to claim 1, characterized in that: After determining the risk level corresponding to the target transaction based on the second data, the third data, the L target risk factors, and the weight value of each target risk factor, the blockchain-based transaction risk level determination method further includes: Prompt information is generated based on the L target risk factors and the risk level, wherein the prompt information at least includes a risk type of the target transaction and a transaction decision suggestion.

8. A device for determining transaction risk level based on blockchain, characterized in that: include: A data collection unit, configured to collect first data, second data, and third data of the target transaction after receiving authorization information from a participant corresponding to the target transaction, wherein the first data includes at least the transaction amount, transaction product, transaction time, and participant address of the target transaction stored on the blockchain; the second data is historical transaction data between the participants corresponding to the target transaction; and the third data is live satellite data of the participant address corresponding to the target transaction; a first determining unit, configured to determine L target risk factors based on the first data, where L is a positive integer, and each of the L target risk factors corresponds to a weight value; The second determining unit is configured to determine a risk level corresponding to the target transaction based on the second data, the third data, the L target risk factors, and a weight value of each target risk factor.

9. A computer program product, characterized in that The computer program product includes a computer program, wherein when the computer program is running, the computer program product is controlled to execute the method for determining the blockchain-based transaction risk level according to any one of claims 1 to 7.

10. An electronic device, characterized in that: The system comprises one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the transaction risk level based on blockchain as described in any one of claims 1 to 7.

Images