Multi-account payment method and device based on blockchain and prediction
Through the multi-account payment method based on blockchain, the payment data and risk vector relationships stored in prediction and blockchain are used to select the payment combination with the lowest risk, which solves the problems of cumbersome operations and difficult to assess risks in multi-account payment, and realizes the problem of Efficient and secure multi-account payment.
Patent Information
- Application Number
- CN202210434641.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-24
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2042-04-24
AI Technical Summary
In the multi-account payment scenario, the balance in each card of the customer does not support a single transaction, which causes the customer to transfer money between multiple cards, which is complicated and when there are many accounts, the number of payment combinations is exponential. , it is difficult to quickly select low-risk payment combinations, affecting efficiency and security.
Using a multi-account payment method based on blockchain and prediction, by obtaining transaction payment data, determining a subset of payment data and transaction risk vector, selecting a payment combination with the lowest risk coefficient for payment, and using blockchain to store pre-calculated payment methods and The relationship between risk vectors, optimize the payment process.
It improves the efficiency and security of multi-account payment, simplifies user experience, reduces system workload, and ensures transaction risk control.
Smart Images

Figure CN114782186B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of blockchain technology, and in particular to a multi-account payment method and device based on blockchain and prediction. Background Art
[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.
[0003] In actual payment transactions, it often happens that the balance in each card of the customer does not support a single transaction (for example, the balance in each card is less than the payment amount). In this case, the customer may need to transfer money between multiple cards, which is cumbersome and does not provide a good customer experience.
[0004] When a customer has multiple accounts, the same payment transaction may have multiple payment combination options, and the number of payment combinations is exponential. When the number of customer accounts is relatively large, the number of payment combinations is very large, so how to quickly select a payment combination with low transaction risk and then perform multi-account payments efficiently and safely is an urgent problem to be solved. Summary of the invention
[0005] The embodiment of the present invention provides a multi-account payment method based on blockchain and prediction, which is used to efficiently and safely perform multi-account payment. Multiple account payment participants constitute a blockchain. The method includes:
[0006] When a user determines that a multi-account payment is required during a transaction payment, the current transaction payment data is obtained;
[0007] According to the current transaction payment data, multiple payment data subsets pre-stored on the blockchain and the prototype sample point information corresponding to each payment data subset, determine the payment data subset to which the current transaction payment data belongs;
[0008] Determine the transaction risk vector of the current transaction payment data according to the payment data subset to which the current transaction payment data belongs and the corresponding relationship between the payment data subset pre-stored on the blockchain and the transaction risk vector;
[0009] Determine the payment method combination corresponding to the current transaction payment data according to the current transaction payment data, the transaction risk vector of the current transaction payment data, and the corresponding relationship between the payment method and the transaction risk vector pre-stored on the blockchain;
[0010] Make multi-account payments based on the payment method combination corresponding to the current transaction payment data.
[0011] The embodiment of the present invention also provides a multi-account payment device based on blockchain and prediction, which is used to efficiently and safely perform multi-account payment. Multiple account payment participants constitute a blockchain, and the device includes:
[0012] An acquisition unit, used to acquire current transaction payment data when it is determined that a multi-account payment is required during a transaction payment by a user;
[0013] A subset determination unit, configured to determine the payment data subset to which the current transaction payment data belongs based on the current transaction payment data, a plurality of payment data subsets pre-stored on the blockchain, and prototype sample point information corresponding to each payment data subset;
[0014] A transaction risk vector determination unit, configured to determine the transaction risk vector of the current transaction payment data according to the payment data subset to which the current transaction payment data belongs and the corresponding relationship between the payment data subset and the transaction risk vector pre-stored on the blockchain;
[0015] A payment method prediction unit, used to determine a payment method combination corresponding to the current transaction payment data according to the current transaction payment data, the transaction risk vector of the current transaction payment data, and the correspondence between the payment method and the transaction risk vector pre-stored on the blockchain;
[0016] The payment unit is used to perform multi-account payment according to the payment method combination corresponding to the current transaction payment data.
[0017] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the multi-account payment method based on blockchain and prediction when executing the computer program.
[0018] An embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned multi-account payment method based on blockchain and prediction.
[0019] An embodiment of the present invention also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the above-mentioned multi-account payment method based on blockchain and prediction.
[0020] In an embodiment of the present invention, a multi-account payment scheme based on blockchain and prediction is implemented by: obtaining current transaction payment data when it is determined that multi-account payment is required during a transaction payment by a user; determining the payment data subset to which the current transaction payment data belongs based on the current transaction payment data, multiple payment data subsets pre-stored on the blockchain, and prototype sample point information corresponding to each payment data subset; determining the transaction risk vector of the current transaction payment data based on the payment data subset to which the current transaction payment data belongs, and the correspondence between the payment data subset pre-stored on the blockchain and the transaction risk vector; determining the payment method combination corresponding to the current transaction payment data based on the current transaction payment data, the transaction risk vector of the current transaction payment data, and the correspondence between the payment method pre-stored on the blockchain and the transaction risk vector; and performing multi-account payment based on the payment method combination corresponding to the current transaction payment data. Multi-account payment can be performed efficiently and securely, thereby improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:
[0022] Figure 1 It is a flowchart of a multi-account payment method based on blockchain and prediction in an embodiment of the present invention;
[0023] Figure 2 This is a flow chart of pre-storing the correspondence between a payment data subset and a transaction risk vector on a blockchain in an embodiment of the present invention;
[0024] Figure 3 This is a flow chart of pre-storing the correspondence between payment methods and transaction risk vectors on a blockchain in an embodiment of the present invention;
[0025] Figure 4 It is a schematic diagram of a process of determining a transaction risk vector corresponding to a payment method according to historical payment data of the payment method in an embodiment of the present invention;
[0026] Figure 5 Schematic diagram of a process for determining a partial order of payment methods according to a transaction risk vector in an embodiment of the present invention;
[0027] Figure 6 A schematic diagram of a process for determining a payment method combination corresponding to current transaction payment data in an embodiment of the present invention;
[0028] Figure 7 Schematic diagram of the structure of a multi-account payment device based on blockchain and prediction in an embodiment of the present invention. DETAILED DESCRIPTION
[0029] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.
[0030] In actual payment transactions, it often happens that the balance in each card of the customer does not support a single transaction (for example, the balance in each card is less than the payment amount). In this case, the customer may need to transfer money between multiple cards, which is cumbersome and does not provide a good customer experience.
[0031] When a customer has multiple accounts, the same payment transaction may have multiple payment combination options, and the number of payment combinations is exponential. When the number of customer accounts is large, the number of payment combinations is very large. If the risk of each payment combination is evaluated, the system workload will be very large.
[0032] In view of the above technical problems, the inventor proposes a multi-account payment scheme based on blockchain and prediction, in which the transaction payment data of the customer is predicted based on the customer's transaction data. Based on different account payment combinations, the risk data of each account payment combination is determined. The predicted payment data and the account payment combination with the lowest risk coefficient in the risk data are stored on the blockchain. When the customer initiates a payment transaction, it is determined whether the transaction data is stored in the blockchain. If it exists, the corresponding payment combination stored in the blockchain is directly used for payment. If not, the most similar predicted payment transaction data is found according to the similarity algorithm. Then, according to the risk coefficient of each account, the lowest priority principle is followed until an account payment combination that can meet this payment is found. Then, from the most similar and the above-mentioned lowest priority selected payment combinations, the payment combination with the lowest risk coefficient is selected. The following is a detailed introduction to the multi-account payment scheme based on blockchain and prediction.
[0033] Figure 1 FIG. 1 is a flow chart of a multi-account payment method based on blockchain and prediction in an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:
[0034] Step 101: when it is determined that a multi-account payment is required during a transaction payment by a user, current transaction payment data is obtained;
[0035] Step 102: Determine the payment data subset to which the current transaction payment data belongs based on the current transaction payment data, multiple payment data subsets pre-stored on the blockchain, and prototype sample point information corresponding to each payment data subset;
[0036] Step 103: Determine the transaction risk vector of the current transaction payment data according to the payment data subset to which the current transaction payment data belongs and the corresponding relationship between the payment data subset and the transaction risk vector pre-stored on the blockchain;
[0037] Step 104: Determine a payment method combination corresponding to the current transaction payment data according to the current transaction payment data, the transaction risk vector of the current transaction payment data, and the correspondence between the payment method and the transaction risk vector pre-stored on the blockchain;
[0038] Step 105: Perform multi-account payment according to the payment method combination corresponding to the current transaction payment data.
[0039] The multi-account payment method based on blockchain and prediction provided by the embodiment of the present invention, when working: when it is determined that multi-account payment is required during the process of transaction payment by the user, the current transaction payment data is obtained; according to the current transaction payment data, multiple payment data subsets pre-stored on the blockchain and the prototype sample point information corresponding to each payment data subset, the payment data subset to which the current transaction payment data belongs is determined; according to the payment data subset to which the current transaction payment data belongs, and the corresponding relationship between the payment data subset pre-stored on the blockchain and the transaction risk vector, the transaction risk vector of the current transaction payment data is determined; according to the current transaction payment data, the transaction risk vector of the current transaction payment data, and the corresponding relationship between the payment method pre-stored on the blockchain and the transaction risk vector, the payment method combination corresponding to the current transaction payment data is determined; according to the payment method combination corresponding to the current transaction payment data, multi-account payment can be made efficiently and safely, which improves the user experience. The multi-account payment method based on blockchain and prediction is introduced in detail below.
[0040] First, the preparatory steps are introduced, that is, the process of uploading each corresponding relationship to the chain in advance.
[0041] In one embodiment, Figure 2 As shown, the multi-account payment method based on blockchain and prediction may also include pre-storing the corresponding relationship between the payment data subset and the transaction risk vector on the blockchain according to the following method:
[0042] Step 201: for each payment data subset, determine the customer set corresponding to the payment data subset;
[0043] Step 202: for each customer in the customer set, selecting payment data corresponding to the customer from the payment data subset; determining the risk coefficient of the customer for each risk type as the proportion of payment data involving the corresponding risk type in the payment data corresponding to the customer;
[0044] Step 203: for each risk type, determining the risk coefficient of the payment data subset with respect to the risk type as the average of the risk coefficients of all customers in the customer set with respect to the risk type;
[0045] Step 204: setting a transaction risk vector corresponding to the payment data subset, wherein each component of the transaction risk vector corresponds to each risk type one by one, and the value of each component is equal to the risk coefficient of the payment data subset with respect to the risk type corresponding to the component;
[0046] Step 205: Store the payment data subset and the transaction risk vector corresponding to the payment data subset on the blockchain.
[0047] Before performing step 201, the bank's payment data needs to be classified to obtain multiple payment data subsets. Specifically:
[0048] 1. For each payment data, determine two vectors corresponding to the payment data, wherein the first vector of the two vectors is the transaction category vector corresponding to the customer of the payment data, and the second vector of the two vectors is the transaction category vector corresponding to the counterparty of the payment data;
[0049] 2. Determine a distance function of the payment data, where the independent variable of the distance function is any two payment data, and the corresponding function value is the sum of the distance between the two first vectors corresponding to the two payment data and the distance between the two second vectors corresponding to the two payment data;
[0050] 3. Cluster the payment data of the bank according to the distance function of the payment data to obtain multiple payment data subsets. At this time, the prototype sample point corresponding to each payment data subset can be the mean center corresponding to the payment data subset, and the mean center corresponds to two vectors, the first vector of the two vectors is the mean of the first vectors corresponding to all the payment data of the payment data subset, and the second vector of the two vectors is the mean of the second vectors corresponding to all the payment data of the payment data subset.
[0051] Among them, for a customer (including a counterparty), the method for determining the transaction category vector corresponding to the customer is: obtain the customer's transaction data, and determine the number of transactions of each transaction category in the transaction data; determine the transaction category vector corresponding to the customer, each component of the transaction category vector corresponds one-to-one to each transaction category, and the component value of each component is equal to the number of transactions of the transaction category corresponding to the component in the customer's transaction data.
[0052] In order to ensure the accuracy of the payment data, the following steps can be performed on each payment data subset obtained above: obtain the transaction currency of each payment data in the payment data subset, and determine the proportion of transaction data of each transaction currency in the payment data subset, determine the maximum proportion of the proportion as the consistency index, and determine whether the payment data subset meets the following condition t: the consistency index of the payment data subset is greater than the specified threshold (0.8); if not, continue to cluster the payment data subset until each payment data subset obtained meets the above condition t.
[0053] In one embodiment, based on the current transaction payment data, multiple payment data subsets pre-stored on the blockchain and the prototype sample point information corresponding to each payment data subset, the payment data subset to which the current transaction payment data belongs is determined. Specifically, for the current transaction payment number, two vectors corresponding to the current transaction payment number are determined according to the above method, and then the distance between the current transaction payment number and the prototype sample points corresponding to each payment data subset is determined according to the distance function of the payment data, and the payment data subset with the smallest corresponding distance is determined as the payment data subset to which the current transaction payment data belongs.
[0054] According to the law of large numbers, the more samples there are, the more accurate the statistical estimate is. Step 203 For each risk type, the risk coefficient of the payment data subset with respect to the risk type is determined as the mean of the risk coefficients of all customers in the customer set with respect to the risk type, or can be:
[0055] For each risk type, the risk coefficients of all customers in the customer set with respect to the risk type are regarded as multiple samples of the same distribution, and the variance of the risk type is determined based on the multiple samples;
[0056] Set the variance of all risk types to δ, select θ to indicate the tolerable risk coefficient error threshold, and select P as the probability that the tolerable risk coefficient error is greater than θ; determine the customer number boundary value to be
[0057] When the number of customers in the customer set corresponding to the payment data subset is greater than or equal to the customer number boundary value, the risk coefficient of the payment data subset with respect to the risk type is determined as the average of the risk coefficients of all customers in the customer set corresponding to the payment data subset with respect to the risk type;
[0058] When the number of customers in the customer set corresponding to the payment data subset is less than the customer number boundary value, multiple customers who do not belong to the customer set corresponding to the payment data subset and whose distances to the prototype sample point information corresponding to the payment data subset are less than a specified threshold are selected from the customer sets corresponding to other payment data subsets, so that the number of the multiple customers is greater than the difference between the customer number boundary value and the number of customers in the customer set corresponding to the payment data subset. At this time, the risk coefficient of the payment data subset with respect to the risk type is determined as the average of the risk coefficients of all customers in the customer set corresponding to the payment data subset and the multiple customers with respect to the risk type.
[0059] In specific implementation, the above step of pre-storing the correspondence between the payment data subset and the transaction risk vector on the blockchain can predict the risk of payment data through data analysis, and can reduce the prediction time, further improving the efficiency and security of subsequent multi-account payments.
[0060] In one embodiment, Figure 3 As shown, the multi-account payment method based on blockchain and prediction may also include pre-storing the corresponding relationship between the payment method and the transaction risk vector on the blockchain according to the following method:
[0061] Step 301: For each payment method supported by the blockchain, determine the transaction risk vector corresponding to the payment method based on the historical payment data of the payment method;
[0062] Step 302: Determine a partial order of payment methods based on the transaction risk vector; wherein, for any two payment methods, the partial order can be used to determine whether a first payment method of the two payment methods is better than a second payment method;
[0063] Step 303: Determine multiple maximum payment methods of all payment methods supported by the blockchain according to the partial order of the payment methods, wherein the maximum payment method is a maximum element of the partial order;
[0064] Step 304: The maximum payment method and the transaction risk vector corresponding to the maximum payment method are stored on the blockchain as a correspondence between the payment method and the transaction risk vector.
[0065] It should be noted that the maximum element of the partial order is that in the set corresponding to the partial order, there is no other element that is better than the maximum element. In this application, each maximum payment method of all payment methods supported by the blockchain specifically refers to the absence of other payment methods supported by the blockchain, making the other payment method better than the maximum payment method.
[0066] In specific implementation, according to the partial order of payment methods, a method for determining multiple maximum payment methods of all payment methods supported by the blockchain is as follows:
[0067] 1. Initialize the maximum flag corresponding to each payment method of all payment methods to possible, and initialize the comparison flag corresponding to each payment method to yes;
[0068] 2. For each payment method of all the payment methods, if the maximum mark corresponding to the payment method is possible, select multiple other payment methods with corresponding comparison marks of yes from all other payment methods except the payment method in all the payment methods, and then set the payment method to be compared corresponding to the payment method to the selected multiple other payment methods, and then execute the following step 3; if the maximum mark corresponding to the payment method is not possible, continue to execute step 2 for the next payment method;
[0069] 3. Select each payment method to be compared corresponding to the payment method in turn, and confirm whether the payment method to be compared is better than the payment method; if the payment method to be compared is better than the payment method, set the maximum value flag corresponding to the payment method to be compared to no, and then continue to perform the above step 2 for the next payment method; if the payment method is better than the payment method to be compared, set the maximum value flag corresponding to the payment method to be compared to no, and determine the payment method to be compared as the secondary payment method of the payment method; otherwise, the maximum value flag corresponding to the payment method and the maximum value flag corresponding to the payment method to be compared remain unchanged;
[0070] 4. If it is confirmed that all the payment methods to be compared are not better than the payment method (that is, after comparing the payment method and each corresponding payment method to be compared in turn, the maximum identification corresponding to the payment method is still possible), then the payment method is determined as the maximum payment method among all payment methods, and the comparison identification of each sub-payment method of the maximum payment method is updated to no.
[0071] 5. Then continue to execute step 2 for the next payment method until the above steps are completed for all payment methods in the payment method list.
[0072] In specific implementation, the above step of pre-storing the correspondence between the payment method and the transaction risk vector on the blockchain can reduce the time for determining the risk of the payment method without affecting the accuracy of the risk analysis, further improving the efficiency and security of subsequent multi-account payments.
[0073] In one embodiment, Figure 4 As shown, for each payment method supported by the blockchain, the transaction risk vector corresponding to the payment method is determined based on the historical payment data of the payment method, which may include:
[0074] Step 3011: Determine the customer set corresponding to the payment method based on the historical payment data of the payment method;
[0075] Step 3012: for each customer in the customer set, selecting payment data corresponding to the customer from the historical payment data of the payment method; determining the risk coefficient corresponding to each risk type when the customer uses the payment method as the proportion of payment data involving the corresponding risk type in the payment data corresponding to the customer;
[0076] Step 3013: for each risk type, the risk coefficient of the payment method corresponding to the risk type is determined as the average of the risk coefficients corresponding to the risk type when all customers in the customer set use the payment method;
[0077] Step 3014: Set the transaction risk vector corresponding to the payment method; each component of the transaction risk vector corresponds to each risk type one by one, and the value of each component is equal to the risk coefficient of the payment method corresponding to the risk type corresponding to the component.
[0078] In specific implementation, the detailed steps of determining the transaction risk vector corresponding to the payment method can accurately determine the risk information of the payment method, providing a basis for the efficiency and security of subsequent multi-account payments.
[0079] In one embodiment, Figure 5 As shown, according to the transaction risk vector, the partial order of payment methods can include:
[0080] Step 3021: for any two payment methods, determine the difference between the transaction risk vector of the first payment method and the transaction risk vector of the second payment method;
[0081] Step 3022: If each component of the difference is less than or equal to zero, and each component of the first payment method is less than a threshold, it is determined that the first payment method is better than the second payment method.
[0082] In specific implementation, the above partial order of payment methods can determine the relative size of the risks of different payment methods, providing a calculation basis for the selection of subsequent payment methods. The risks of multiple maximum payment methods determined according to the partial order are relatively small, and selecting the maximum payment method can ensure the security of the transaction.
[0083] Next, the steps of using the pre-chained data to perform actual multi-account payment are introduced, namely, the above-mentioned steps 101 to 105.
[0084] The scenario of multi-account payment based on blockchain and prediction provided by the embodiment of the present invention can be: a customer has multiple accounts, such as current accounts, bank debit card accounts, credit card accounts, foreign currency accounts (such as US dollar accounts, Japanese yen accounts), passbook accounts, other bank accounts, and third-party accounts, such as WeChat, Alipay accounts, etc. Different accounts correspond to different businesses and systems, and their content processes, especially risk control processes, are different, resulting in different response capabilities for the same risk type.
[0085] Transaction elements have a significant impact on risk. For example, if a bank account has 100,000 in deposit, there is a clear difference between paying 100 and paying 10,000; if the two transactions are the same except for the time, then trading during normal hours is much safer than trading in the early hours; different counterparties may also have different corresponding money laundering risks. For example, the fraud risk of a counterparty in a certain country or industry is higher than that of other countries or industries.
[0086] In order to better understand the embodiments of the present invention, the terms involved in the embodiments of the present invention are first introduced.
[0087] 1. Risk type refers to the risk type of the bank, which may include: customer information leakage risk, account funds loss risk, customer loss risk, fraud risk, system risk, etc.
[0088] 2. The historical transaction data of payments refers to the transaction data of the customer's past payments. Each piece of data includes the customer, transaction amount, transaction currency, transaction time, transaction location, transaction channel, counterparty (the other party to whom the customer pays the amount, such as the merchant when the customer shops), risk identification (whether there is risk), risk category, payment method, etc.
[0089] In specific implementation, the above step 102 determines the payment data subset to which the current transaction payment data belongs according to the current transaction payment data, multiple payment data subsets pre-stored on the blockchain, and the prototype sample point information corresponding to each payment data subset, which may include: determining the cluster subset to which the current transaction payment data belongs according to the current transaction payment data, multiple transaction payment data cluster subsets pre-stored on the blockchain, and the prototype sample point information corresponding to each subset; the above step 103 determines the payment data subset to which the current transaction payment data belongs according to the payment data subset to which the current transaction payment data belongs, and the corresponding relationship between the payment data subset pre-stored on the blockchain and the transaction risk vector. The transaction risk vector may include: determining the transaction risk type of the current transaction payment data according to the cluster subset to which the current transaction payment data belongs, and the relationship between the cluster subset and the transaction risk type pre-stored on the blockchain; predicting the payment method combination corresponding to the current transaction payment data according to the transaction risk type of the current transaction payment data and the relationship between the transaction risk type and the payment method combination pre-stored on the blockchain in the above step 104 may include: determining the payment method combination corresponding to the current transaction payment data according to the current transaction payment data, the transaction risk vector of the current transaction payment data, and the corresponding relationship between the payment method pre-stored on the blockchain and the transaction risk vector.
[0090] During the specific implementation, cluster analysis is performed on the historical payment transaction data to determine several cluster subsets of transaction data, each of which corresponds to the same risk category; based on the historical transaction data, the risk category and risk probability corresponding to the payment method are determined; multiple payment methods that can cope with the risk category are determined; when a customer conducts a transaction, based on the current transaction data, the cluster subset to which the current transaction data belongs is determined, that is, the risk category is determined; based on the risk category and the transaction amount, a payment method combination is determined.
[0091] In specific implementation, determining the transaction risk type of the current transaction payment data according to the cluster subset to which the current transaction payment data belongs and the relationship between the cluster subset and the transaction risk type pre-stored on the blockchain may include: when determining that the current transaction payment data belongs to multiple pending cluster subsets, taking the risk type with the largest number among the risk types corresponding to the multiple pending cluster subsets as the transaction risk type of the current transaction payment data.
[0092] In specific implementation, the above-mentioned multi-account payment method based on blockchain and prediction may also include: when it is determined that the current transaction payment data does not belong to any cluster subset on the blockchain, determining the predicted payment transaction data that is most similar to the current transaction payment data according to a preset similarity algorithm, and using the payment method corresponding to the predicted payment transaction data as the payment method for this transaction.
[0093] In one embodiment, Figure 6 As shown, in the above step 104, according to the current transaction payment data, the transaction risk vector of the current transaction payment data, and the correspondence between the payment method and the transaction risk vector pre-stored on the blockchain, determining the payment method combination corresponding to the current transaction payment data may include:
[0094] Step 1041: for each payment method in the correspondence relationship between the payment method and the transaction risk vector, determine the risk distance between the payment method and the current transaction payment data according to the transaction risk vector corresponding to the payment method and the transaction risk vector of the current transaction payment data;
[0095] Step 1042: Determine a payment method combination corresponding to the current transaction payment data based on the current transaction payment data and the risk distance between each payment method and the current transaction payment data in accordance with the corresponding relationship between the payment method and the transaction risk vector.
[0096] In specific implementation, one method for determining the payment method combination corresponding to the current transaction payment data is: sort the various payment methods of the corresponding relationship in order of risk distance from the current transaction payment data from large to small; then determine in turn according to the sorting whether each payment method satisfies the following condition t: the sum of the balance of the account corresponding to the payment method and the balance of the accounts corresponding to all payment methods before the payment method in the sorting is greater than or equal to the payment amount corresponding to the current transaction payment data; if the above conditions are met, the combination of the payment method and all payment methods before the payment method in the sorting is determined as the payment method combination corresponding to the current transaction payment data, otherwise, confirm whether the next payment method in the sorting satisfies the above conditions until a payment method is found that satisfies the above conditions.
[0097] Another method is to set the weight of each payment method in the corresponding relationship according to the risk distance from the current transaction payment data, and satisfy the condition that the greater the distance, the greater the weight. For example, the weight is set according to the following formula: Where W i is the weight of the ith payment method, d i is the risk distance between the ith payment method and the current transaction payment data, and l is the number of payment methods included in the corresponding relationship.
[0098] To facilitate understanding of how the present invention is implemented, the following example introduces the detailed steps of the multi-account payment method based on blockchain and prediction in an embodiment of the present invention.
[0099] 1. Obtain key element data from historical payment transaction data (such as transaction amount, transaction currency, transaction time, transaction location, transaction channel, transaction counterparty, and risk category with the highest risk probability), and perform cluster analysis based on the determined distance function (the distance between two key elements) with risk category as the category identifier to obtain different cluster subsets of transaction data. The transaction data of each subset corresponds to the same risk category. The information of the subset (prototype sample points of each subset (prototype sample points can represent each cluster subset, such as average point), risk category) is stored in the blockchain.
[0100] 2. Extract payment methods, risk indicators and risk categories from historical payment transaction data, confirm the risk category corresponding to each payment method, and the probability corresponding to the risk category.
[0101] 3. For each risk type, determine the payment methods that do not contain the risk type (risk probability is 0) or have a low risk probability, form a payment method set that can deal with the risk category, and store it in the blockchain. The low risk probability can be less than or equal to a specified threshold. The threshold can be the proportion of data corresponding to the risk type in all payment transaction data (corresponding to all payment methods).
[0102] 4. When a customer makes a payment (or when the current payment transaction selected by the customer fails due to insufficient balance), the key element data is obtained based on the payment transaction data, and based on the distance between the key element data and multiple prototype sample points of the blockchain, the transaction data cluster subset to which the transaction data belongs (the subset with the smallest distance) is determined, and the risk category corresponding to the subset is used as the most likely risk category of the transaction data.
[0103] 5. Obtain a set of payment methods that can handle the risk category, and determine a combination of payment methods based on the transaction amount. Specifically, add the payment method with the lowest risk probability to this payment method set, and determine whether the account balance corresponding to the payment method is greater than the transaction amount of this payment transaction. If it is greater than or equal to, determine the payment method determined in this payment method set as the payment method for this transaction; if it is less than, select the remaining payment methods, and add the one with the lowest risk to this payment method set until it is greater than or equal to.
[0104] 6. The selected payment method set is pushed to the customer. After receiving the customer's confirmation information, the customer's payment transaction is completed according to the selected payment method set.
[0105] 7. When determining the clustered subsets of transaction data described in the transaction, it is possible that the distances between the key element data of the transaction and the prototype sample points of multiple subsets are roughly close. In this case, the risk type with the largest number among the risk types corresponding to the multiple subsets shall be used as the most likely risk category of the transaction data.
[0106] 8. Predict the customer’s transaction payment data based on historical transaction data, then extract the key element data and determine the transaction data cluster subset to which it belongs, that is, determine the risk category, and then determine the payment method of the predicted transaction payment data, and store the predicted transaction payment data and payment method on the blockchain.
[0107] 9. When a customer initiates a payment transaction, determine whether the key elements of the transaction data are stored in the blockchain. If so, directly use the corresponding payment combination stored in the blockchain to make the payment.
[0108] 10. If it does not exist, find the predicted payment transaction data that is most similar to the current transaction data based on the key elements of the transaction data and the similarity algorithm, and obtain the payment method corresponding to the predicted payment transaction data as the payment method for this transaction.
[0109] In summary, the multi-account payment method based on blockchain and prediction provided by the embodiment of the present invention can better control the payment transaction risks, while the customer's payment transaction time is shorter and the customer experience is good.
[0110] The present invention also provides a multi-account payment device based on blockchain and prediction, as described in the following embodiments. Since the principle of solving the problem by the device is similar to that of the multi-account payment method based on blockchain and prediction, the implementation of the device can refer to the implementation of the multi-account payment method based on blockchain and prediction, and the repeated parts will not be repeated.
[0111] Figure 7 Schematic diagram of the structure of a multi-account payment device based on blockchain and prediction in an embodiment of the present invention. Figure 7 As shown, multiple account payment participants constitute a blockchain, and the device includes:
[0112] The acquisition unit 01 is used to acquire current transaction payment data when it is determined that a multi-account payment is required during a transaction payment by a user;
[0113] A subset determination unit 02, configured to determine the payment data subset to which the current transaction payment data belongs based on the current transaction payment data, a plurality of payment data subsets pre-stored on the blockchain, and prototype sample point information corresponding to each payment data subset;
[0114] The transaction risk vector determination unit 03 is used to determine the transaction risk vector of the current transaction payment data according to the payment data subset to which the current transaction payment data belongs and the corresponding relationship between the payment data subset and the transaction risk vector pre-stored on the blockchain;
[0115] The payment method prediction unit 04 is used to determine the payment method combination corresponding to the current transaction payment data according to the current transaction payment data, the transaction risk vector of the current transaction payment data, and the corresponding relationship between the payment method and the transaction risk vector pre-stored on the blockchain;
[0116] The payment unit 05 is used to perform multi-account payment according to the payment method combination corresponding to the current transaction payment data.
[0117] In one embodiment, the multi-account payment device based on blockchain and prediction may further include a first on-chain unit, which is used to pre-store the corresponding relationship between the payment data subset and the transaction risk vector on the blockchain according to the following method:
[0118] For each payment data subset, determine the customer set corresponding to the payment data subset;
[0119] For each customer in the customer set, selecting payment data corresponding to the customer from the payment data subset; determining the risk coefficient of the customer with respect to each risk type as the proportion of payment data involving the corresponding risk type in the payment data corresponding to the customer;
[0120] For each risk type, determining the risk coefficient of the payment data subset with respect to the risk type as the average of the risk coefficients of all customers in the customer set with respect to the risk type;
[0121] Set a transaction risk vector corresponding to the payment data subset, where each component of the transaction risk vector corresponds to each risk type one-to-one, and the value of each component is equal to the risk coefficient of the payment data subset with respect to the risk type corresponding to the component;
[0122] The payment data subset and the transaction risk vector corresponding to the payment data subset are stored on the blockchain.
[0123] In one embodiment, the multi-account payment device based on blockchain and prediction may further include a second on-chain unit, which is used to pre-store the corresponding relationship between the payment method and the transaction risk vector on the blockchain according to the following method:
[0124] For each payment method supported by the blockchain, determine the transaction risk vector corresponding to the payment method based on the historical payment data of the payment method;
[0125] Determine a partial order of payment methods based on the transaction risk vector; wherein, for any two payment methods, the partial order can be used to determine whether a first payment method of the two payment methods is better than a second payment method;
[0126] According to the partial order of payment methods, multiple maximum payment methods of all payment methods supported by the blockchain are determined, wherein the maximum payment method is a maximum element of the partial order;
[0127] The maximum payment method and the transaction risk vector corresponding to the maximum payment method are stored on the blockchain as the corresponding relationship between the payment method and the transaction risk vector.
[0128] In one embodiment, for each payment method supported by the blockchain, determining the transaction risk vector corresponding to the payment method based on the historical payment data of the payment method may include:
[0129] Determine the customer set corresponding to the payment method based on the historical payment data of the payment method;
[0130] For each customer in the customer set, the payment data corresponding to the customer is selected from the historical payment data of the payment method; the risk coefficient corresponding to each risk type when the customer uses the payment method is determined as the proportion of the payment data involving the corresponding risk type in the payment data corresponding to the customer;
[0131] For each risk type, the risk coefficient of the payment method corresponding to the risk type is determined as the average of the risk coefficients corresponding to the risk type when all customers in the customer set use the payment method;
[0132] A transaction risk vector corresponding to the payment method is set; each component of the transaction risk vector corresponds to each risk type one by one, and the value of each component is equal to the risk coefficient of the payment method corresponding to the risk type corresponding to the component.
[0133] In one embodiment, determining the partial order of payment methods according to the transaction risk vector may include:
[0134] For any two payment methods, determining the difference between a transaction risk vector of a first payment method and a transaction risk vector of a second payment method of the two payment methods;
[0135] If each component of the difference is less than or equal to zero, and each component of the first payment method is less than a threshold, it is determined that the first payment method is better than the second payment method.
[0136] In one embodiment, the payment method prediction unit is specifically used to:
[0137] For each payment method in the corresponding relationship between the payment method and the transaction risk vector, determine the risk distance between the payment method and the current transaction payment data according to the transaction risk vector corresponding to the payment method and the transaction risk vector of the current transaction payment data;
[0138] The payment method combination corresponding to the current transaction payment data is determined based on the risk distance between each payment method and the current transaction payment data according to the current transaction payment data and the corresponding relationship between the payment method and the transaction risk vector.
[0139] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.
[0140] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the multi-account payment method based on blockchain and prediction when executing the computer program.
[0141] An embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned multi-account payment method based on blockchain and prediction.
[0142] An embodiment of the present invention also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the above-mentioned multi-account payment method based on blockchain and prediction.
[0143] In an embodiment of the present invention, a multi-account payment scheme based on blockchain and prediction is implemented by: obtaining current transaction payment data when it is determined that multi-account payment is required during a transaction payment by a user; determining the payment data subset to which the current transaction payment data belongs based on the current transaction payment data, multiple payment data subsets pre-stored on the blockchain, and prototype sample point information corresponding to each payment data subset; determining the transaction risk vector of the current transaction payment data based on the payment data subset to which the current transaction payment data belongs, and the correspondence between the payment data subset pre-stored on the blockchain and the transaction risk vector; determining the payment method combination corresponding to the current transaction payment data based on the current transaction payment data, the transaction risk vector of the current transaction payment data, and the correspondence between the payment method pre-stored on the blockchain and the transaction risk vector; and performing multi-account payment based on the payment method combination corresponding to the current transaction payment data. Multi-account payment can be performed efficiently and securely, thereby improving user experience.
[0144] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0145] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0146] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0147] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0148] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A multi-account payment method based on blockchain and prediction, characterized in that: Multiple account payment participants constitute a blockchain, and the multi-account payment method based on blockchain and prediction includes: When a user determines that a multi-account payment is required during a transaction payment, the current transaction payment data is obtained; According to the current transaction payment data, multiple payment data subsets pre-stored on the blockchain and the prototype sample point information corresponding to each payment data subset, determine the payment data subset to which the current transaction payment data belongs; Determine the transaction risk vector of the current transaction payment data according to the payment data subset to which the current transaction payment data belongs and the corresponding relationship between the payment data subset pre-stored on the blockchain and the transaction risk vector; Determine the combination of payment methods corresponding to the current transaction payment data according to the current transaction payment data, the transaction risk vector of the current transaction payment data, and the correspondence between the payment method and the transaction risk vector pre-stored on the blockchain, which includes: for each payment method in the correspondence between the payment method and the transaction risk vector, determine the risk distance between the payment method and the current transaction payment data according to the transaction risk vector corresponding to the payment method and the transaction risk vector of the current transaction payment data; determine the combination of payment methods corresponding to the current transaction payment data according to the risk distance between each payment method in the correspondence between the current transaction payment data and the transaction risk vector and the current transaction payment data; Perform multi-account payment based on the payment method combination corresponding to the current transaction payment data; The multi-account payment method based on blockchain and prediction also includes pre-storing the corresponding relationship between the payment data subset and the transaction risk vector on the blockchain according to the following method: For each payment data subset, determine the customer set corresponding to the payment data subset; wherein, before determining the customer set corresponding to the payment data subset for each payment data subset, it is necessary to classify the payment data of the bank to obtain multiple payment data subsets, specifically: for each payment data, determine the two vectors corresponding to the payment data, wherein the first vector of the two vectors is the transaction category vector corresponding to the customer of the payment data, and the second vector of the two vectors is the transaction category vector corresponding to the counterparty of the payment data; determine the distance function of the payment data, the independent variable of the distance function is any two payment data, and the corresponding function value is the sum of the distance between the two first vectors corresponding to the two payment data and the distance between the two second vectors corresponding to the two payment data; cluster the payment data of the bank according to the distance function of the payment data to obtain multiple payment data subsets, at this time, the prototype sample point corresponding to each payment data subset can be the mean center corresponding to the payment data subset, and the mean center corresponds to two vectors, the first vector of the two vectors is the mean of the first vectors corresponding to all the payment data of the payment data subset, and the second vector of the two vectors is the mean of the second vectors corresponding to all the payment data of the payment data subset; For each customer in the customer set, selecting payment data corresponding to the customer from the payment data subset; determining the risk coefficient of the customer with respect to each risk type as the proportion of payment data involving the corresponding risk type in the payment data corresponding to the customer; For each risk type, determining the risk coefficient of the payment data subset with respect to the risk type as the average of the risk coefficients of all customers in the customer set with respect to the risk type; Set a transaction risk vector corresponding to the payment data subset, where each component of the transaction risk vector corresponds to each risk type one-to-one, and the value of each component is equal to the risk coefficient of the payment data subset with respect to the risk type corresponding to the component; storing the payment data subset and the transaction risk vector corresponding to the payment data subset on the blockchain; The multi-account payment method based on blockchain and prediction also includes pre-storing the corresponding relationship between the payment method and the transaction risk vector on the blockchain according to the following method: For each payment method supported by the blockchain, determine the transaction risk vector corresponding to the payment method based on the historical payment data of the payment method; Determine a partial order of payment methods based on the transaction risk vector; wherein, for any two payment methods, the partial order can be used to determine whether a first payment method of the two payment methods is better than a second payment method; According to the partial order of payment methods, multiple maximum payment methods of all payment methods supported by the blockchain are determined, wherein the maximum payment method is a maximum element of the partial order; The maximum payment method and the transaction risk vector corresponding to the maximum payment method are stored on the blockchain as a correspondence between the payment method and the transaction risk vector; For each payment method supported by the blockchain, the transaction risk vector corresponding to the payment method is determined based on the historical payment data of the payment method, including: Determine the customer set corresponding to the payment method based on the historical payment data of the payment method; For each customer in the customer set, the payment data corresponding to the customer is selected from the historical payment data of the payment method; the risk coefficient corresponding to each risk type when the customer uses the payment method is determined as the proportion of the payment data involving the corresponding risk type in the payment data corresponding to the customer; For each risk type, the risk coefficient of the payment method corresponding to the risk type is determined as the average of the risk coefficients corresponding to the risk type when all customers in the customer set use the payment method; A transaction risk vector corresponding to the payment method is set; each component of the transaction risk vector corresponds to each risk type one by one, and the value of each component is equal to the risk coefficient of the payment method corresponding to the risk type corresponding to the component.
2. The multi-account payment method based on blockchain and prediction as claimed in claim 1, characterized in that: Based on the transaction risk vector, the partial order of payment methods is determined, including: For any two payment methods, determining the difference between a transaction risk vector of a first payment method and a transaction risk vector of a second payment method of the two payment methods; If each component of the difference is less than or equal to zero, and each component of the first payment method is less than a threshold, it is determined that the first payment method is better than the second payment method.
3. A multi-account payment device based on blockchain and prediction, characterized in that: Multiple account payment participants constitute a blockchain, and the multi-account payment device based on blockchain and prediction includes: An acquisition unit, used to acquire current transaction payment data when it is determined that a multi-account payment is required during a transaction payment by a user; A subset determination unit, used to determine the payment data subset to which the current transaction payment data belongs based on the current transaction payment data, multiple payment data subsets pre-stored on the blockchain, and prototype sample point information corresponding to each payment data subset, wherein the prototype sample point corresponding to each payment data subset is the mean center corresponding to the payment data subset; A transaction risk vector determination unit, configured to determine the transaction risk vector of the current transaction payment data according to the payment data subset to which the current transaction payment data belongs and the corresponding relationship between the payment data subset and the transaction risk vector pre-stored on the blockchain; A payment method prediction unit is used to determine the payment method combination corresponding to the current transaction payment data according to the current transaction payment data, the transaction risk vector of the current transaction payment data, and the correspondence between the payment method and the transaction risk vector pre-stored on the blockchain, which includes: for each payment method in the correspondence between the payment method and the transaction risk vector, according to the transaction risk vector corresponding to the payment method and the transaction risk vector of the current transaction payment data, determining the risk distance between the payment method and the current transaction payment data; according to the risk distance between each payment method in the correspondence between the current transaction payment data and the transaction risk vector and the current transaction payment data, determining the payment method combination corresponding to the current transaction payment data; A payment unit, used to perform multi-account payment according to a combination of payment methods corresponding to the current transaction payment data; The multi-account payment device based on blockchain and prediction further includes a first on-chain unit, which is used to pre-store the corresponding relationship between the payment data subset and the transaction risk vector on the blockchain according to the following method: For each payment data subset, determine the customer set corresponding to the payment data subset; wherein, before determining the customer set corresponding to the payment data subset for each payment data subset, it is necessary to classify the payment data of the bank to obtain multiple payment data subsets, specifically: for each payment data, determine the two vectors corresponding to the payment data, wherein the first vector of the two vectors is the transaction category vector corresponding to the customer of the payment data, and the second vector of the two vectors is the transaction category vector corresponding to the counterparty of the payment data; determine the distance function of the payment data, the independent variable of the distance function is any two payment data, and the corresponding function value is the sum of the distance between the two first vectors corresponding to the two payment data and the distance between the two second vectors corresponding to the two payment data; cluster the payment data of the bank according to the distance function of the payment data to obtain multiple payment data subsets, at this time, the prototype sample point corresponding to each payment data subset can be the mean center corresponding to the payment data subset, and the mean center corresponds to two vectors, the first vector of the two vectors is the mean of the first vectors corresponding to all the payment data of the payment data subset, and the second vector of the two vectors is the mean of the second vectors corresponding to all the payment data of the payment data subset; For each customer in the customer set, selecting payment data corresponding to the customer from the payment data subset; determining the risk coefficient of the customer with respect to each risk type as the proportion of payment data involving the corresponding risk type in the payment data corresponding to the customer; For each risk type, determining the risk coefficient of the payment data subset with respect to the risk type as the average of the risk coefficients of all customers in the customer set with respect to the risk type; Set a transaction risk vector corresponding to the payment data subset, where each component of the transaction risk vector corresponds to each risk type one-to-one, and the value of each component is equal to the risk coefficient of the payment data subset with respect to the risk type corresponding to the component; storing the payment data subset and the transaction risk vector corresponding to the payment data subset on the blockchain; The multi-account payment device based on blockchain and prediction further includes a second on-chain unit, which is used to pre-store the corresponding relationship between the payment method and the transaction risk vector on the blockchain according to the following method: For each payment method supported by the blockchain, determine the transaction risk vector corresponding to the payment method based on the historical payment data of the payment method; Determine a partial order of payment methods based on the transaction risk vector; wherein, for any two payment methods, the partial order can be used to determine whether a first payment method of the two payment methods is better than a second payment method; According to the partial order of payment methods, multiple maximum payment methods of all payment methods supported by the blockchain are determined, wherein the maximum payment method is a maximum element of the partial order; The maximum payment method and the transaction risk vector corresponding to the maximum payment method are stored on the blockchain as a correspondence between the payment method and the transaction risk vector; For each payment method supported by the blockchain, the transaction risk vector corresponding to the payment method is determined based on the historical payment data of the payment method, including: Determine the customer set corresponding to the payment method based on the historical payment data of the payment method; For each customer in the customer set, the payment data corresponding to the customer is selected from the historical payment data of the payment method; the risk coefficient corresponding to each risk type when the customer uses the payment method is determined as the proportion of the payment data involving the corresponding risk type in the payment data corresponding to the customer; For each risk type, the risk coefficient of the payment method corresponding to the risk type is determined as the average of the risk coefficients corresponding to the risk type when all customers in the customer set use the payment method; A transaction risk vector corresponding to the payment method is set; each component of the transaction risk vector corresponds to each risk type one by one, and the value of each component is equal to the risk coefficient of the payment method corresponding to the risk type corresponding to the component.
4. The multi-account payment device based on blockchain and prediction as claimed in claim 3, characterized in that: Based on the transaction risk vector, the partial order of payment methods is determined, including: For any two payment methods, determining the difference between a transaction risk vector of a first payment method and a transaction risk vector of a second payment method of the two payment methods; If each component of the difference is less than or equal to zero, and each component of the first payment method is less than a threshold, it is determined that the first payment method is better than the second payment method.
5. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 2 is implemented.
6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 2 is implemented.
7. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 2 is implemented.
Citation Information
Patent Citations
Blockchain-based payment scheme determination method, device and system
CN112163846A
Cross-border payment settlement method, device and system, equipment and storage medium
CN113222750A
Payment risk identification method, device and equipment
CN113516480A
Mobile terminal payment method and device in network-free state
CN113627933A
Method for processing data of buy-now-pay-later transaction, device, processing apparatus, and server
WO2020019895A1
