Risk control method and device in online banking business processing

Abstract

The present invention discloses a risk control method and device for online banking business processing, which relates to the financial field. The method comprises: receiving a user's online banking business processing request; the business includes multiple transaction steps; in each transaction step of the online banking business processing, the following operations are performed until all transaction steps are completed: determining the risk type to be controlled for the current transaction step based on the relationship between the risk type and the transaction step pre-established in the blockchain, multiple executed steps, and multiple risk types that have not been risk controlled; determining the risk control method corresponding to the current transaction step based on the risk type to be controlled for the current transaction step and the pre-established relationship between the risk type and the risk control method; and performing risk control on the current transaction step based on the risk control method corresponding to the current transaction step. The present invention can efficiently control the risk of each link in the business processing and improve the security of the business processing.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to a risk control method and device for online banking business processing. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. No statement herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] Banking scenarios consist of a series of transactions. For example, a foreign currency exchange transaction involves the following steps: customer identity verification, temporary account creation, foreign currency exchange, transaction review, and delivery of foreign currency to the customer. Risk management must be rigorously implemented at every step of the transaction. Failure to identify issues during customer identity verification and transaction review, or the teller's misconduct in other transactions, can pose risks to both the bank and the customer. Summary of the Invention

[0004] An embodiment of the present invention provides a risk control method for online banking business processing, which is used to efficiently control the risk of each link in the business processing. The method includes:

[0005] Receive a user's request for an online banking transaction, wherein the transaction includes multiple transaction steps;

[0006] In each transaction step of online banking, perform the following operations until all transaction steps are completed:

[0007] Based on the pre-established correspondence between risk types and transaction steps in the blockchain, multiple executed steps, and multiple risk types that have not been risk-controlled, determine the risk type to be controlled for the current transaction step;

[0008] Determine the risk control method corresponding to the current transaction step based on the risk type to be controlled in the current transaction step and the pre-established correspondence between risk type and risk control method;

[0009] Perform risk control on the current transaction step based on the risk control method corresponding to the current transaction step.

[0010] The embodiment of the present invention further provides a risk control device for online banking business processing, which is used to efficiently control the risk of each link in the business processing. The device includes:

[0011] A receiving unit, configured to receive a user's request for an online banking service; the service includes multiple transaction steps;

[0012] The processing unit is used to perform the following operations in each transaction step of the online banking business until all transaction steps are completed:

[0013] Based on the pre-established correspondence between risk types and transaction steps in the blockchain, multiple executed steps, and multiple risk types that have not been risk-controlled, determine the risk type to be controlled for the current transaction step;

[0014] Determine the risk control method corresponding to the current transaction step based on the risk type to be controlled in the current transaction step and the pre-established correspondence between risk type and risk control method;

[0015] Perform risk control on the current transaction step based on the risk control method corresponding to the current transaction step.

[0016] 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. When the processor executes the computer program, the risk control method for online banking business processing described above is implemented.

[0017] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the computer program implements the above-mentioned risk control method in online banking business processing.

[0018] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the risk control method in online banking business processing.

[0019] In an embodiment of the present invention, a risk control scheme in online banking business processing is provided by: receiving a user's online banking business processing request; the business includes multiple transaction steps; in each transaction step of the online banking business processing, the following operations are performed: determining the risk type to be controlled of the current transaction step based on the correspondence between the risk type and the transaction step pre-established in the blockchain, multiple executed steps, and multiple risk types that have not been risk controlled; determining the risk control method corresponding to the current transaction step based on the risk type to be controlled of the current transaction step and the pre-established correspondence between the risk type and the risk control method; and performing risk control on the current transaction step based on the risk control method corresponding to the current transaction step, thereby efficiently controlling the risk of each link in the business processing and improving the security of the business processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] 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 the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0021] Figure 1 This is a flow chart of a risk control method for online banking services according to an embodiment of the present invention;

[0022] Figure 2 This is a flowchart of pre-storing the correspondence between risk types and transaction steps in a blockchain in an embodiment of the present invention;

[0023] Figure 3 A schematic diagram of a process for determining a risk control method corresponding to a current transaction step in an embodiment of the present invention;

[0024] Figure 4 A schematic diagram of determining a risk control method corresponding to a current transaction step based on a selection probability in an embodiment of the present invention;

[0025] Figure 5 Schematic diagram of the structure of the risk control device in online banking business processing according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] To make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below with reference to 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.

[0027] Figure 1 FIG. 1 is a flow chart of a risk control method for online banking business processing according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0028] Step 101: Receive a user's online banking service request; the service includes multiple transaction steps;

[0029] Step 102: In each transaction step of the online banking service, the following operations are performed:

[0030] Step 1021: Determine the risk type to be controlled for the current transaction step based on the pre-established correspondence between risk types and transaction steps in the blockchain, multiple executed steps, and multiple risk types that have not been risk controlled;

[0031] Step 1022: Determine the risk control method corresponding to the current transaction step based on the risk type to be controlled in the current transaction step and the pre-established correspondence between risk type and risk control method;

[0032] Step 1023: Perform risk control on the current transaction step according to the risk control method corresponding to the current transaction step.

[0033] The risk control method for online banking transactions provided by an embodiment of the present invention operates by: receiving a user's request for online banking transactions; the transaction includes multiple transaction steps; and performing the following operations in each transaction step: determining the risk type to be controlled for the current transaction step based on a pre-established correspondence between risk types and transaction steps in the blockchain, multiple executed steps, and multiple uncontrolled risk types; determining the corresponding risk control method for the current transaction step based on the pre-established correspondence between the risk type to be controlled for the current transaction step and the pre-established correspondence between the risk type and the risk control method; and performing risk control on the current transaction step based on the corresponding risk control method. This method can effectively control the risks at every stage of the transaction process and improve the security of the transaction. The following is a detailed description of the risk control method for online banking transactions.

[0034] In one embodiment, Figure 2 As shown, the risk control method for online banking business processing may further include pre-storing the correspondence between risk types and transaction steps in the blockchain according to the following method:

[0035] Step 201: Determine the dependencies between different transaction steps of each banking business;

[0036] Step 202: Determine, based on the execution data of each transaction step, the risk type involved in the transaction step and the probability of each risk type involved in the transaction step;

[0037] Step 203: Based on the dependencies between different transaction steps and the probabilities of various risk types associated with each transaction step, a transaction step dependency graph corresponding to the banking business is constructed, wherein the nodes of the graph include a starting point, an end point, and a transaction step;

[0038] Step 204: Determine the correspondence between risk types and transaction steps based on the transaction step dependency graph;

[0039] Step 205: Pre-store the correspondence between risk types and transaction steps in the blockchain.

[0040] In one embodiment, step 202 determines the risk type involved in each transaction step and the probability of each risk type involved in the transaction step based on the execution data of the transaction step, including:

[0041] Determining the risk category contained in the execution data of the transaction step as the risk type involved in the transaction step;

[0042] Divide the execution data of the transaction step into multiple execution data subsets, so that the amount of data contained in each execution data subset is greater than a set value;

[0043] For each risk category involved in the transaction step, determining a proportion of execution data involved in the risk category in each execution data subset, and determining a variance of the probability of the risk type based on the determined multiple proportions;

[0044] Determine the sample threshold corresponding to the probability of the risk type based on the variance of the probability of the risk type;

[0045] The maximum value of the sample thresholds corresponding to the probabilities of all risk types is determined as the sample threshold;

[0046] The following steps are repeated until the number of execution data subsets obtained is greater than the sample threshold:

[0047] Obtain new execution data for the transaction step; divide the new execution data into multiple new execution data subsets, such that the amount of data contained in each new execution data subset is greater than a set value; and for each risk category, determine the proportion of execution data related to the risk category in each new execution data subset;

[0048] When the number of obtained execution data subsets is greater than the sample threshold, for each risk category, the probability that the transaction step corresponds to the risk type is determined as the mean of all proportions corresponding to the risk category.

[0049] In one embodiment, determining a sample threshold corresponding to the probability of the risk type based on the variance of the probability of the risk type may include:

[0050] Set an acceptable probability error threshold and the probability that the acceptable probability error is greater than the probability error threshold;

[0051] Based on the variance of the probability of the risk type, the probability error threshold, and the probability that the acceptable probability error is greater than the probability error threshold, the sample threshold corresponding to the probability of the risk type is determined. For example, the sample threshold is determined as: Where σ is the variance of the probability of the risk type, ε is the acceptable error in the risk probability, and P is the probability that the acceptable error in the risk probability is greater than ε.

[0052] In specific implementation, the above-mentioned implementation method of pre-storing the correspondence between risk types and transaction steps in the blockchain can accurately determine the risk type that needs to be controlled in each transaction step, providing a data basis for subsequent risk control.

[0053] In one embodiment, constructing a transaction step dependency graph corresponding to the banking business based on the dependency relationships between different transaction steps and the probabilities of various risk types involved in each transaction step may include:

[0054] Determining a plurality of first nodes and a plurality of second nodes according to the dependency relationship, wherein no other nodes exist in the dependency relationship for the first node, such that the first node depends on the other node, and no other nodes exist in the dependency relationship for the second node and depend on the non-dependent node;

[0055] Construct the transaction step dependency graph, in which there is an edge between the starting point and each first node, the direction of the edge is from the starting point to the first node, and the probability that the edge corresponds to each risk type is 0; there is an edge between the end point and each second node, the direction of the edge is from the second node to the end point, and the probability that the edge corresponds to each risk type is 0; there is an edge between two transaction steps if and only if there is a dependency relationship between the two transaction steps, and the direction of the edge is from the dependent step to the dependent step, and the probability that the edge corresponds to each risk type is the probability that the dependent step corresponds to each risk type.

[0056] In one embodiment, there is an edge between two transaction steps if and only if there is a dependency relationship between the two transaction steps, the direction of the edge is from the dependent step to the dependent step, and the probability of the edge corresponding to each risk type is the probability of the dependent step corresponding to each risk type, and further includes:

[0057] For each risk type, when the probability of the dependent step corresponding to the risk type is less than the probability threshold, the probability of the edge corresponding to the risk type is determined to be 0; otherwise, the probability of the edge corresponding to the risk type is determined to be the probability of the dependent step corresponding to the risk type.

[0058] In specific implementation, the above-mentioned implementation method of constructing the transaction step dependency graph corresponding to the banking business can accurately determine the dependency relationship between the steps, and provide a graph structure basis for subsequently determining the risk type that needs to be controlled in each step.

[0059] In one embodiment, determining the correspondence between risk types and transaction steps based on the transaction step dependency graph may include:

[0060] For the transaction step dependency graph, determine the safety distance of each edge corresponding to the risk type as: -lg(1-r), where r is the probability that the edge corresponds to the risk type;

[0061] For each risk type, determine the shortest distance between each transaction step and the end point corresponding to the risk type in the transaction step dependency graph based on the safety distance corresponding to the risk type;

[0062] The transaction step having the shortest distance from the end point corresponding to the risk type greater than 0 is determined as the transaction step corresponding to the risk type, and the corresponding relationship between the risk type and the transaction step is obtained.

[0063] In specific implementation, the above specific implementation method of determining the correspondence between risk types and transaction steps based on the transaction step dependency graph can find the steps associated with each risk type, providing a basis for subsequent risk control.

[0064] In one embodiment, based on the pre-established correspondence between risk types and transaction steps in the blockchain, multiple executed steps, and multiple risk types that have not been risk-controlled, determining the risk type to be controlled for the current transaction step may include:

[0065] For each risk type that has not been risk controlled, determine whether the transaction steps corresponding to the risk type are all included in the multiple steps that have been executed. If so, determine the risk type as the risk type to be controlled for the current transaction step.

[0066] In specific implementation, the above-mentioned method of determining the risk type to be controlled in the current transaction step can ensure timely risk control and guarantee the security of customer transactions.

[0067] In one embodiment, Figure 3 As shown, according to the risk type to be controlled in the current transaction step and the pre-established correspondence between the risk type and the risk control method, the risk control method corresponding to the current transaction step is determined, which may include:

[0068] Step 10221: Based on the pre-established risk type and risk control method, multiple risk control methods whose corresponding risk types include the risk type to be controlled in the current transaction step are selected from all risk control methods included in the corresponding relationship between risk types and risk control methods;

[0069] Step 10222: Determine the probability of selection corresponding to each selected risk control method;

[0070] Step 10223: Determine the risk control method corresponding to the current transaction step based on the probability of being selected.

[0071] In one embodiment, determining the probability of selection corresponding to each selected risk control method may include:

[0072] Obtain control data for each selected risk control method;

[0073] For each risk type to be controlled in the current transaction step, determine the risk indicators of each selected risk control method corresponding to the risk type to be controlled based on the control data of each selected risk control method;

[0074] For each selected risk control method, determine the risk distance of the risk control method; for example, determine the risk distance of the risk control method according to the following formula:

[0075]

[0076] Among them, d i is the risk distance of the ith risk control method, r ij is the risk indicator of the jth risk type to be controlled corresponding to the i-th risk control method, and l is the number of risk types to be controlled in the current transaction step;

[0077] Determine the probability of selection corresponding to the i-th risk control method as Among them, m is the number of risk control methods selected.

[0078] In one embodiment, for each risk type to be controlled in the current transaction step, determining the risk indicator of each selected risk control method corresponding to the risk type to be controlled based on the control data of each selected risk control method may include:

[0079] For each selected risk control method, dividing the control data of the risk control method into a plurality of control data subsets;

[0080] For each risk type to be controlled, the proportion of control data related to the risk type to be controlled in each control data subset is determined as the sample of the risk type to be controlled corresponding to the risk control method;

[0081] The risk indicator of the risk control method corresponding to the risk type to be controlled is determined as the mean value of all samples of the risk control method corresponding to the risk type to be controlled.

[0082] In specific implementation, the above-mentioned implementation method of determining the risk control method corresponding to the current transaction step can avoid the occurrence of risks to a certain extent by introducing randomness, thereby improving the security of business processing.

[0083] In one embodiment, Figure 4 As shown, the above step 10223 determines the risk control method corresponding to the current transaction step based on the selection probability, which may include:

[0084] Step 301: sorting the selected risk control methods;

[0085] Step 302: For each selected risk control method, the sum of the selection probabilities of the risk control method and all risk control methods that precede the risk control method in the ranking is determined as the probability upper bound corresponding to the risk control method;

[0086] Step 303: Select a probability density function and determine the interval endpoint value corresponding to the risk control method, so that the integral from the minimum value of the probability density function corresponding to the independent variable to the interval endpoint value corresponding to the risk control method is equal to the probability upper bound corresponding to the risk control method;

[0087] Step 304: Generate a random number based on the selected probability density function;

[0088] Step 305: Determine the risk control method corresponding to the random number, so that the random number is less than or equal to the probability upper bound corresponding to the corresponding risk control method, and greater than the probability upper bound corresponding to the previous risk control method in the sorting process;

[0089] Step 306: Determine the risk control method corresponding to the random number as the risk control method corresponding to the current transaction step.

[0090] In order to facilitate understanding of how to implement the present invention, an example is given below for illustration.

[0091] The risk control method for online banking transactions provided by the embodiments of the present invention can be applied in scenarios where a banking transaction consists of a series of transactions. For example, a foreign currency exchange transaction involves the following steps: customer identity verification, temporary account creation, foreign currency exchange execution, transaction review, and foreign currency payment to the customer. In the embodiments of the present invention, these steps can be abstracted as s1, s2, ..., sn.

[0092] The risks in the embodiment of the present invention may be: various risks that may be encountered in bank business operations, such as fraud risk, staff operation risk, customer loss risk, transaction failure risk, etc.

[0093] In the risk control method for online banking business processing provided by an embodiment of the present invention, the risk types involved in banking business and the transaction steps involved in each risk type are determined, and a correspondence between risk types and transaction steps is established; based on the above correspondence and the dependency relationship between different transaction steps, the risk type to be controlled for each transaction step is confirmed so that the subsequent steps of the step do not have the risk type to be controlled; at each step, the risk prediction data of the transaction risk to be controlled for this banking business in relation to the step is determined; based on the relationship between the risk type (including the above risk prediction data) and the risk control means, the risk control means of the banking business for the risk type is determined.

[0094] At each step, the specific process of obtaining the risk prediction data of the transaction risk to be controlled for this banking business at that step is as follows:

[0095] At each step of a customer's business transaction, determine whether the backend system has performed risk control on the corresponding risk type of the transaction step and store the confirmation result in the blockchain;

[0096] At the same time, in each step of the customer's business transaction, the corresponding transaction risk to be controlled is determined, and based on the confirmation data stored in the blockchain, it is confirmed whether all steps corresponding to the transaction risk to be controlled have undergone risk analysis for the transaction risk to be controlled. If so, the risk warning model is not used; if not, the risk warning model is used for risk prediction;

[0097] Aggregate the risk prediction data of the risk early warning model and the risk analysis data of the backend system for the risk type to obtain the risk analysis data of the bank's business for the risk type;

[0098] The risk control method for online banking business processing provided by the embodiment of the present invention includes:

[0099] 1. For a banking business, determine the dependencies between multiple steps. This means that the execution of one step depends on the completion of other steps. The simplest dependency is a linear structure (one step depends on only one other step), while more complex dependency structures are graph structures.

[0100] 2. For a certain banking business, obtain the historical risk data involved. Based on this historical risk data, determine the risk types involved in the banking business and the transaction steps involved in each risk type.

[0101] 3. Establish a correspondence between risk types and transaction steps. Transaction steps can be obtained based on risk types, or risk types can be determined based on transaction steps. This correspondence is stored in the blockchain.

[0102] 4. Based on the above correspondence and the dependencies between different transaction steps, identify the uncontrolled transaction risk for each transaction step, so that subsequent steps do not have the same uncontrolled transaction risk. Each transaction risk is only the uncontrolled transaction risk for a specific transaction step.

[0103] 4.1 If the dependency relationship between different transaction steps is linear, for a certain risk type r1, the last step s1 corresponding to risk type r1 is selected, and the transaction risk to be controlled in step s1 includes risk type r1;

[0104] 4.2 If the dependency is a graph dependency, for a certain risk type r2, select the last step in each linear relationship that contains the risk type, and then select the first step s2 executed among all the common subsequent steps of the last step. The transaction risk to be controlled in step s2 then contains the risk type r2.

[0105] 5. For each risk type of the bank’s business, a risk warning model is established based on the acquired risk data and stored in the blockchain.

[0106] 6. In each transaction step of the customer's business, check whether there is risk prediction data for the risk type corresponding to the transaction step in the transaction feedback data returned by the backend system corresponding to the transaction. If there is, the risk prediction data will be stored in the blockchain.

[0107] 7. In the above steps, the corresponding transaction risk to be controlled is queried based on the relationship stored in the blockchain. Then, the transaction step corresponding to each transaction risk to be controlled is determined. Then, it is determined whether the blockchain contains risk prediction data for the corresponding bank backend system for the transaction step for the risk type. If there is no such risk prediction data for a certain transaction step, risk prediction is performed based on the previously trained risk warning model and the business data corresponding to the bank business (that is, if there is a backend system in the backend system of the transaction step that does not perform risk analysis for the risk type, the risk warning model will perform risk analysis on it).

[0108] 8. Based on the risk prediction data and the risk prediction data for this risk type fed back by the bank backend stored in the blockchain, a risk prediction summary is performed to obtain the risk prediction data for this risk type for the bank's business.

[0109] 9. Based on the relationship between risk type (including the above-mentioned risk prediction data) and risk control measures, determine the risk control measures for the bank's business for that risk type.

[0110] In summary, the embodiments of the present invention can effectively control the risks in every link of business processing and realize digital risk control of banks.

[0111] The acquisition, storage, use, and processing of data in this application's technical solution comply with relevant national laws and regulations.

[0112] The present invention also provides a risk control device for online banking transactions, as described in the following embodiments. Because the principles underlying the device are similar to those of the risk control method for online banking transactions, the implementation of the device can be referenced to the implementation of the risk control method for online banking transactions, and any repetitions will not be repeated.

[0113] Figure 5 FIG. 1 is a schematic diagram of the structure of a risk control device for online banking business processing according to an embodiment of the present invention. Figure 5 As shown, the device includes:

[0114] Receiving unit 01 is used to receive a user's online banking service request; the service includes multiple transaction steps;

[0115] Processing unit 02 is configured to perform the following operations in each transaction step of an online banking transaction until all transaction steps are completed:

[0116] Based on the pre-established correspondence between risk types and transaction steps in the blockchain, multiple executed steps, and multiple risk types that have not been risk-controlled, determine the risk type to be controlled for the current transaction step;

[0117] Determine the risk control method corresponding to the current transaction step based on the risk type to be controlled in the current transaction step and the pre-established correspondence between risk type and risk control method;

[0118] Perform risk control on the current transaction step based on the risk control method corresponding to the current transaction step.

[0119] In one embodiment, the risk control device for online banking transactions may further include an on-chain unit configured to pre-store the correspondence between risk types and transaction steps in a blockchain according to the following method:

[0120] Identify the dependencies between the different transaction steps for each banking operation;

[0121] Determine, based on the execution data of each transaction step, the risk type involved in the transaction step and the probability of each risk type involved in the transaction step;

[0122] Based on the dependencies between different transaction steps and the probabilities of various risk types involved in each transaction step, a transaction step dependency graph corresponding to the banking business is constructed, where the nodes of the graph include a starting point, an end point, and a transaction step;

[0123] Determine the correspondence between risk types and transaction steps based on the transaction step dependency graph;

[0124] The correspondence between risk types and transaction steps is pre-stored in the blockchain.

[0125] In one embodiment, constructing a transaction step dependency graph corresponding to the banking business based on the dependency relationships between different transaction steps and the probabilities of various risk types involved in each transaction step may include:

[0126] Determining a plurality of first nodes and a plurality of second nodes according to the dependency relationship, wherein no other nodes exist in the dependency relationship for the first node, such that the first node depends on the other node, and no other nodes exist in the dependency relationship for the second node and depend on the non-dependent node;

[0127] Construct the transaction step dependency graph, in which there is an edge between the starting point and each first node, the direction of the edge is from the starting point to the first node, and the probability that the edge corresponds to each risk type is 0; there is an edge between the end point and each second node, the direction of the edge is from the second node to the end point, and the probability that the edge corresponds to each risk type is 0; there is an edge between two transaction steps if and only if there is a dependency relationship between the two transaction steps, and the direction of the edge is from the dependent step to the dependent step, and the probability that the edge corresponds to each risk type is the probability that the dependent step corresponds to each risk type.

[0128] In one embodiment, determining the correspondence between risk types and transaction steps based on the transaction step dependency graph may include:

[0129] For the transaction step dependency graph, determine the safety distance of each edge corresponding to the risk type as: -lg(1-r), where r is the probability that the edge corresponds to the risk type;

[0130] For each risk type, determine the shortest distance between each transaction step and the end point corresponding to the risk type in the transaction step dependency graph based on the safety distance corresponding to the risk type;

[0131] The transaction step having the shortest distance from the end point corresponding to the risk type greater than 0 is determined as the transaction step corresponding to the risk type, and the corresponding relationship between the risk type and the transaction step is obtained.

[0132] In one embodiment, based on the pre-established correspondence between risk types and transaction steps in the blockchain, multiple executed steps, and multiple risk types that have not been risk-controlled, determining the risk type to be controlled for the current transaction step may include:

[0133] For each risk type that has not been risk controlled, determine whether the transaction steps corresponding to the risk type are all included in the multiple steps that have been executed. If so, determine the risk type as the risk type to be controlled for the current transaction step.

[0134] In one embodiment, based on the risk type to be controlled in the current transaction step and the pre-established correspondence between the risk type and the risk control method, determining the risk control method corresponding to the current transaction step may include:

[0135] According to a pre-established risk type and risk control method approach, multiple risk control methods whose corresponding risk types include the risk type to be controlled in the current transaction step are selected from all risk control methods included in the corresponding relationship between risk types and risk control methods;

[0136] Determine the probability of selection corresponding to each selected risk control method;

[0137] Based on the probability of being selected, determine the risk control method corresponding to the current transaction step.

[0138] In one embodiment, determining the risk control method corresponding to the current transaction step based on the selection probability may include:

[0139] Sort the selected multiple risk control methods;

[0140] For each selected risk control method, the sum of the selection probabilities of the risk control method and all risk control methods that are ranked before the risk control method in the ranking is determined as the probability upper bound corresponding to the risk control method;

[0141] Select a probability density function and determine the endpoint value of the interval corresponding to the risk control method, so that the integral from the minimum value of the probability density function corresponding to the independent variable to the endpoint value of the interval corresponding to the risk control method is equal to the probability upper bound corresponding to the risk control method;

[0142] Generate random numbers based on the selected probability density function;

[0143] Determine the risk control method corresponding to the random number, so that the random number is less than or equal to the probability upper bound corresponding to the corresponding risk control method, and greater than the probability upper bound corresponding to the previous risk control method in the ranking;

[0144] The risk control method corresponding to the random number is determined as the risk control method corresponding to the current transaction step.

[0145] 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. When the processor executes the computer program, the risk control method for online banking business processing described above is implemented.

[0146] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the computer program implements the above-mentioned risk control method in online banking business processing.

[0147] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the risk control method in online banking business processing.

[0148] In an embodiment of the present invention, a risk control scheme in online banking business processing is provided by: receiving a user's online banking business processing request; the business includes multiple transaction steps; in each transaction step of the online banking business processing, the following operations are performed: determining the risk type to be controlled of the current transaction step based on the correspondence between the risk type and the transaction step pre-established in the blockchain, multiple executed steps, and multiple risk types that have not been risk controlled; determining the risk control method corresponding to the current transaction step based on the risk type to be controlled of the current transaction step and the pre-established correspondence between the risk type and the risk control method; and performing risk control on the current transaction step based on the risk control method corresponding to the current transaction step, thereby efficiently controlling the risk of each link in the business processing and improving the security of the business processing.

[0149] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, 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 magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0150] 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 flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, 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 flowcharts and / or block diagrams. 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.

[0151] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 1The function specified in one or more boxes.

[0152] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0153] 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 risk control method for online banking business processing, characterized in that: include: Receive a user's request for an online banking transaction, wherein the transaction includes multiple transaction steps; In each transaction step of online banking, perform the following operations until all transaction steps are completed: Based on the pre-established correspondence between risk types and transaction steps in the blockchain, multiple executed steps, and multiple risk types that have not been risk-controlled, determine the risk type to be controlled for the current transaction step; Determine the risk control method corresponding to the current transaction step based on the risk type to be controlled in the current transaction step and the pre-established correspondence between risk type and risk control method; Perform risk control on the current transaction step according to the risk control method corresponding to the current transaction step; The risk control method for online banking business processing also includes pre-storing the correspondence between risk types and transaction steps in the blockchain according to the following method: determining the dependency between different transaction steps of each banking business; determining the risk type involved in the transaction step and the probability of each risk type involved in the transaction step based on the execution data of each transaction step; constructing a transaction step dependency graph corresponding to the banking business based on the dependency between different transaction steps and the probability of each risk type involved in each transaction step, wherein the nodes of the graph include a starting point, an end point and a transaction step; determining the correspondence between the risk type and the transaction step based on the transaction step dependency graph relationship; pre-storing the correspondence between the risk type and the transaction step in the blockchain; determining the correspondence between the risk type and the transaction step based on the transaction step dependency graph, including: for the transaction step dependency graph, determining the safety distance of each edge corresponding to the risk type as: -lg(1-r), where r is the probability that the edge corresponds to the risk type; for each risk type, determining the shortest distance between each transaction step in the transaction step dependency graph and the end point corresponding to the risk type based on the safety distance corresponding to the risk type; determining the transaction step whose shortest distance to the end point corresponding to the risk type is greater than 0 as the transaction step corresponding to the risk type, thereby obtaining the correspondence between the risk type and the transaction step.

2. The risk control method for online banking business processing according to claim 1, characterized in that: Based on the dependencies between different transaction steps and the probability of each risk type involved in each transaction step, a transaction step dependency graph corresponding to the banking business is constructed, including: Determining a plurality of first nodes and a plurality of second nodes according to the dependency relationship, wherein no other nodes exist in the dependency relationship for the first node, such that the first node depends on the other node, and no other nodes exist in the dependency relationship for the second node and depend on the non-dependent node; Construct the transaction step dependency graph, in which there is an edge between the starting point and each first node, the direction of the edge is from the starting point to the first node, and the probability that the edge corresponds to each risk type is 0; there is an edge between the end point and each second node, the direction of the edge is from the second node to the end point, and the probability that the edge corresponds to each risk type is 0; there is an edge between two transaction steps if and only if there is a dependency relationship between the two transaction steps, and the direction of the edge is from the dependent step to the dependent step, and the probability that the edge corresponds to each risk type is the probability that the dependent step corresponds to each risk type.

3. The risk control method for online banking business processing according to claim 1, characterized in that: Based on the pre-established correspondence between risk types and transaction steps in the blockchain, multiple executed steps, and multiple risk types that have not been risk-controlled, the risk type to be controlled for the current transaction step is determined, including: For each risk type that has not been risk controlled, determine whether the transaction steps corresponding to the risk type are all included in the multiple steps that have been executed. If so, determine the risk type as the risk type to be controlled for the current transaction step.

4. The risk control method for online banking business processing according to claim 1, characterized in that: Based on the risk type to be controlled in the current transaction step and the pre-established correspondence between risk type and risk control method, the risk control method corresponding to the current transaction step is determined, including: According to a pre-established risk type and risk control method approach, multiple risk control methods whose corresponding risk types include the risk type to be controlled in the current transaction step are selected from all risk control methods included in the corresponding relationship between risk types and risk control methods; Determine the probability of selection corresponding to each selected risk control method; Based on the probability of being selected, determine the risk control method corresponding to the current transaction step.

5. The risk control method for online banking business processing according to claim 4, characterized in that: Based on the probability of being selected, determine the risk control method corresponding to the current transaction step, including: Sort the selected multiple risk control methods; For each selected risk control method, the sum of the selection probabilities of the risk control method and all risk control methods that are ranked before the risk control method in the ranking is determined as the probability upper bound corresponding to the risk control method; Select a probability density function and determine the endpoint value of the interval corresponding to the risk control method, so that the integral from the minimum value of the probability density function corresponding to the independent variable to the endpoint value of the interval corresponding to the risk control method is equal to the probability upper bound corresponding to the risk control method; Generate random numbers based on the selected probability density function; Determine the risk control method corresponding to the random number, so that the random number is less than or equal to the probability upper bound corresponding to the corresponding risk control method, and greater than the probability upper bound corresponding to the previous risk control method in the ranking; The risk control method corresponding to the random number is determined as the risk control method corresponding to the current transaction step.

6. A risk control device for online banking business processing, characterized in that: include: A receiving unit, configured to receive a user's request for an online banking service; the service includes multiple transaction steps; The processing unit is used to perform the following operations in each transaction step of the online banking business until all transaction steps are completed: Based on the pre-established correspondence between risk types and transaction steps in the blockchain, multiple executed steps, and multiple risk types that have not been risk-controlled, determine the risk type to be controlled for the current transaction step; Determine the risk control method corresponding to the current transaction step based on the risk type to be controlled in the current transaction step and the pre-established correspondence between risk type and risk control method; Perform risk control on the current transaction step according to the risk control method corresponding to the current transaction step; The risk control device for online banking business processing also includes an on-chain unit, which is used to pre-store the correspondence between risk types and transaction steps in the blockchain according to the following method: determining the dependency relationship between different transaction steps of each banking business; determining the risk type involved in the transaction step and the probability of each risk type involved in the transaction step based on the execution data of each transaction step; constructing a transaction step dependency graph corresponding to the banking business based on the dependency relationship between different transaction steps and the probability of each risk type involved in each transaction step, wherein the nodes of the graph include a starting point, an end point and a transaction step; determining the risk type and the transaction step based on the transaction step dependency graph The method comprises the steps of: pre-storing the correspondence between the risk type and the transaction step in the blockchain; determining the correspondence between the risk type and the transaction step based on the transaction step dependency graph, comprising: for the transaction step dependency graph, determining the safety distance of each edge corresponding to the risk type as: -lg(1-r), where r is the probability that the edge corresponds to the risk type; for each risk type, determining the shortest distance between each transaction step in the transaction step dependency graph and the end point corresponding to the risk type based on the safety distance corresponding to the risk type; determining the transaction step whose shortest distance to the end point corresponding to the risk type is greater than 0 as the transaction step corresponding to the risk type, and obtaining the correspondence between the risk type and the transaction step.

7. The risk control device for online banking business processing according to claim 6, characterized in that: Based on the dependencies between different transaction steps and the probability of each risk type involved in each transaction step, a transaction step dependency graph corresponding to the banking business is constructed, including: Determining a plurality of first nodes and a plurality of second nodes according to the dependency relationship, wherein no other nodes exist in the dependency relationship for the first node, such that the first node depends on the other node, and no other nodes exist in the dependency relationship for the second node and depend on the non-dependent node; Construct the transaction step dependency graph, in which there is an edge between the starting point and each first node, the direction of the edge is from the starting point to the first node, and the probability that the edge corresponds to each risk type is 0; there is an edge between the end point and each second node, the direction of the edge is from the second node to the end point, and the probability that the edge corresponds to each risk type is 0; there is an edge between two transaction steps if and only if there is a dependency relationship between the two transaction steps, and the direction of the edge is from the dependent step to the dependent step, and the probability that the edge corresponds to each risk type is the probability that the dependent step corresponds to each risk type.

8. The risk control device for online banking business processing according to claim 6, characterized in that: Based on the pre-established correspondence between risk types and transaction steps in the blockchain, multiple executed steps, and multiple risk types that have not been risk-controlled, the risk type to be controlled for the current transaction step is determined, including: For each risk type that has not been risk controlled, determine whether the transaction steps corresponding to the risk type are all included in the multiple steps that have been executed. If so, determine the risk type as the risk type to be controlled for the current transaction step.

9. The risk control device for online banking business processing according to claim 6, characterized in that: Based on the risk type to be controlled in the current transaction step and the pre-established correspondence between risk type and risk control method, the risk control method corresponding to the current transaction step is determined, including: According to a pre-established risk type and risk control method approach, multiple risk control methods whose corresponding risk types include the risk type to be controlled in the current transaction step are selected from all risk control methods included in the corresponding relationship between risk types and risk control methods; Determine the probability of selection corresponding to each selected risk control method; Based on the probability of being selected, determine the risk control method corresponding to the current transaction step.

10. The risk control device for online banking business processing according to claim 9, characterized in that: Based on the probability of being selected, determine the risk control method corresponding to the current transaction step, including: Sort the selected multiple risk control methods; For each selected risk control method, the sum of the selection probabilities of the risk control method and all risk control methods that are ranked before the risk control method in the ranking is determined as the probability upper bound corresponding to the risk control method; Select a probability density function and determine the endpoint value of the interval corresponding to the risk control method, so that the integral from the minimum value of the probability density function corresponding to the independent variable to the endpoint value of the interval corresponding to the risk control method is equal to the probability upper bound corresponding to the risk control method; Generate random numbers based on the selected probability density function; Determine the risk control method corresponding to the random number, so that the random number is less than or equal to the probability upper bound corresponding to the corresponding risk control method, and greater than the probability upper bound corresponding to the previous risk control method in the ranking; The risk control method corresponding to the random number is determined as the risk control method corresponding to the current transaction step.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

12. 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 5 is implemented.

13. 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 5 is implemented.

Images