A banking business risk control method and device

Abstract

The present invention provides a method and device for controlling risks in bank business processing, which belongs to big data. The method comprises: determining the processing steps of bank business according to the bank's historical business processing data; determining, for each processing step, a set of pre-steps and a set of post-steps corresponding to the processing step; determining, according to the set of pre-steps and the set of post-steps, an initial step node and an end step node; executing each processing step of the initial step node when processing business in real time; looping and executing the following steps until the end step node is executed: when the node where the processing step is located is executed, judging whether each processing step in the set of post-steps corresponding to the executed processing step meets the execution condition; determining, according to the bank's historical business processing data, the risk type to be controlled at the current moment; and performing risk control on each processing step in the set of post-steps according to the risk type to be controlled at the current moment and the corresponding risk control model.

Description

Technical Field

[0001] The present invention relates to the technical field of computer data processing, and in particular to a method and device for controlling risks in bank business handling. Background Art

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

[0003] Currently, when conducting business on the banking system, the various steps of the business are executed serially, which often leads to long waiting times for customers and a poor customer experience. In addition, the risk control of the business is manually set and lacks a data basis.

[0004] Therefore, how to provide a new solution that can solve the above technical problems is a technical problem that needs to be solved urgently in this field. Summary of the Invention

[0005] The embodiment of the present invention provides a banking business risk control method, which can reduce the execution time of business processing and shorten the waiting time of customers by executing business steps in parallel. At the same time, it can effectively control the risks of the business and improve the security of banking business, including:

[0006] Determine the steps for handling banking business based on the bank's historical business handling data;

[0007] For each processing step, determine the set of pre-steps and post-steps corresponding to the processing step;

[0008] Determine the initial step node and the end step node according to the preceding step set and the following step set;

[0009] When handling business in real time, execute each processing step of the initial step node;

[0010] Loop through the following steps until the end step is reached:

[0011] When the execution of the node where the processing step is located is completed, each processing step in the set of subsequent steps corresponding to the completed processing step is judged to see whether the execution condition is met; if there is a processing step in the set of subsequent steps corresponding to the completed processing step that meets the execution condition, then the processing step is executed; the execution condition is whether all the preceding steps in the set of preceding steps corresponding to the processing step have been completed;

[0012] Based on the bank's historical business processing data, the type of risk to be controlled at the current moment is determined. Based on the type of risk to be controlled at the current moment and the corresponding risk control model, risk control is performed on the execution of each processing step in the set of subsequent steps.

[0013] An embodiment of the present invention further provides a banking business risk control device, comprising:

[0014] The banking business processing step determination module is used to determine the banking business processing steps based on the bank's historical business processing data;

[0015] A module for determining a set of pre-steps and a set of post-steps, for determining, for each processing step, a set of pre-steps and a set of post-steps corresponding to the processing step;

[0016] An initial step node and an end step node determination module, configured to determine an initial step node and an end step node according to a set of preceding steps and a set of following steps;

[0017] The processing step execution module is used to execute each processing step of the initial step node when processing business in real time;

[0018] The loop execution module is used to loop through the following steps until the end step node is reached:

[0019] An execution judgment module is used to judge whether the execution condition is met for each processing step in the set of subsequent steps corresponding to the completed processing step when the processing step is completed; if there is a processing step in the set of subsequent steps corresponding to the completed processing step that meets the execution condition, then the processing step is executed; the execution condition is whether all the preceding steps in the set of preceding steps corresponding to the processing step have been completed;

[0020] The risk control module is used to determine the type of risk to be controlled at the current moment based on the bank's historical business processing data, and to perform risk control on the execution of each processing step in the post-step set based on the type of risk to be controlled at the current moment and the corresponding risk control model.

[0021] 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 above-mentioned banking business risk control method when executing the computer program.

[0022] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the above-mentioned banking business risk control method.

[0023] 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 above-mentioned banking business risk control method.

[0024] A banking business risk control method and device provided by an embodiment of the present invention include: determining the banking business processing steps based on the bank's historical business processing data; for each processing step, determining the corresponding pre-step set and post-step set of the processing step; determining the initial step node and the end step node based on the pre-step set and post-step set; when processing the business in real time, executing each processing step of the initial step node; looping and executing the following steps until the end step node is executed: when the node where the processing step is located is completed, judging whether the execution condition is met for each processing step in the post-step set corresponding to the completed processing step; if there is a processing step in the post-step set corresponding to the completed processing step that meets the execution condition, then executing the processing step; the execution condition is whether all pre-steps in the pre-step set corresponding to the processing step have been completed; determining the risk type to be controlled at the current moment based on the bank's historical business processing data, and performing risk control on the execution of each processing step in the post-step set based on the risk type to be controlled at the current moment and the corresponding risk control model. The embodiment of the present invention can reduce the execution time of business processing and the waiting time of customers by executing business steps in parallel, and can also effectively control the risks of the business and improve the security of banking business. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] 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:

[0026] Figure 1 The figure is a schematic diagram of a banking business risk control method according to an embodiment of the present invention.

[0027] Figure 2 The figure is a schematic diagram of an embodiment of a method for controlling risk in banking business according to an embodiment of the present invention.

[0028] Figure 3 The figure is a schematic diagram of an embodiment of a method for controlling risk in banking business according to an embodiment of the present invention.

[0029] Figure 4 The figure is a schematic diagram of an embodiment of a method for controlling risk in banking business according to an embodiment of the present invention.

[0030] Figure 5 A schematic diagram of a computer device for running a banking business risk control method implemented by the present invention.

[0031] Figure 6 The figure is a schematic diagram of a banking business risk control device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] 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.

[0033] This invention belongs to big data. Figure 1 FIG. 1 is a schematic diagram of a method for controlling risk in banking business according to an embodiment of the present invention. Figure 1 As shown, an embodiment of the present invention provides a banking business risk control method, including:

[0034] Step 101: Determine the steps for handling banking business based on the bank's historical business handling data;

[0035] Step 102: For each processing step, determine the set of pre-processing steps and post-processing steps corresponding to the processing step;

[0036] Step 103: Determine the initial step node and the end step node according to the preceding step set and the following step set;

[0037] Step 104: When handling the business in real time, execute each handling step of the initial step node;

[0038] Step 105: Loop through the following steps until the end step is reached:

[0039] Step 106: When the node where the processing step is located is completed, each processing step in the set of subsequent steps corresponding to the completed processing step is determined to determine whether the execution condition is met; if there is a processing step in the set of subsequent steps corresponding to the completed processing step that meets the execution condition, the processing step is executed; the execution condition is whether all the preceding steps in the set of preceding steps corresponding to the processing step have been completed;

[0040] Step 107: Determine the current risk type to be controlled based on the bank's historical business processing data, and perform risk control on the execution of each processing step in the post-step set based on the current risk type to be controlled and the corresponding risk control model.

[0041] A banking business processing risk control method provided by an embodiment of the present invention includes: determining the processing steps of the banking business based on the bank's historical business processing data; for each processing step, determining the pre-step set and post-step set corresponding to the processing step; determining the initial step node and the end step node based on the pre-step set and post-step set; when processing the business in real time, executing each processing step of the initial step node; looping and executing the following steps until the end step node is executed: when the node where the processing step is located is completed, judging whether the execution condition is met for each processing step in the post-step set corresponding to the completed processing step; if there is a processing step in the post-step set corresponding to the completed processing step that meets the execution condition, then executing the processing step; the execution condition is whether all pre-steps in the pre-step set corresponding to the processing step have been completed; determining the risk type to be controlled at the current moment based on the bank's historical business processing data, and performing risk control on the execution of each processing step in the post-step set based on the risk type to be controlled at the current moment and the corresponding risk control model. The embodiment of the present invention can reduce the execution time of business processing and the waiting time of customers by executing business steps in parallel, and can also effectively control the risks of the business and improve the security of banking business.

[0042] When implementing a banking business risk control method provided by an embodiment of the present invention, in one embodiment, the method includes:

[0043] Determine the steps for handling banking business based on the bank's historical business handling data;

[0044] For each processing step, determine the set of pre-steps and post-steps corresponding to the processing step;

[0045] Determine the initial step node and the end step node according to the preceding step set and the following step set;

[0046] When handling business in real time, execute each processing step of the initial step node;

[0047] Loop through the following steps until the end step is reached:

[0048] When the execution of the node where the processing step is located is completed, each processing step in the set of subsequent steps corresponding to the completed processing step is judged to see whether the execution condition is met; if there is a processing step in the set of subsequent steps corresponding to the completed processing step that meets the execution condition, then the processing step is executed; the execution condition is whether all the preceding steps in the set of preceding steps corresponding to the processing step have been completed;

[0049] Based on the bank's historical business processing data, the type of risk to be controlled at the current moment is determined. Based on the type of risk to be controlled at the current moment and the corresponding risk control model, risk control is performed on the execution of each processing step in the set of subsequent steps.

[0050] Figure 2 FIG. 1 is a schematic diagram of an embodiment of a method for controlling risk in banking business according to an embodiment of the present invention. Figure 2 As shown, when implementing a banking business risk control method provided by an embodiment of the present invention, in one embodiment, the banking business handling steps include input and output;

[0051] For each processing step, determine the corresponding set of pre-steps and post-steps, including:

[0052] Step 201: Determine whether the output of a banking service processing step is the input of each subsequent processing step. If the output of the processing step is the input of the subsequent processing step, a direct relationship is established between the two processing steps.

[0053] Step 202: defining the processing step of establishing the direct relationship as a pre-step of the direct relationship, and defining the subsequent processing step of establishing the direct relationship as a post-step of the direct relationship, wherein the post-step is dependent on the pre-step;

[0054] Step 203: polling the processing steps of the banking business, and forming all direct relationships into a direct relationship set;

[0055] Step 204: According to the direct relationship set, determine the corresponding pre-step set and post-step set for each processing step.

[0056] Figure 3 FIG. 1 is a schematic diagram of an embodiment of a method for controlling risk in banking business according to an embodiment of the present invention. Figure 3 As shown, when implementing a banking business risk control method provided by an embodiment of the present invention, in one embodiment, a corresponding set of pre-steps and post-steps is determined for each processing step based on a set of direct relationships, including:

[0057] Step 301: Filter out all direct relationships whose corresponding subsequent steps are the processing step from the direct relationship set, and use the set consisting of all preceding steps of all the filtered direct relationships as the preceding step set corresponding to the processing step;

[0058] Step 302: Filter out all direct relationships whose corresponding predecessor steps are the processing steps from the direct relationship set, and use the set consisting of all subsequent steps of all the filtered direct relationships as the subsequent step set corresponding to the processing step.

[0059] When implementing a banking business risk control method provided by an embodiment of the present invention, in one embodiment, determining an initial step node and an end step node based on a set of pre-steps and a set of post-steps includes:

[0060] According to the set of preceding steps and the set of following steps, the processing steps that are not in the set of following steps corresponding to any processing step are determined as initial step nodes, and the processing steps that are not in the set of preceding steps corresponding to any processing step are determined as ending step nodes.

[0061] Figure 4 FIG. 1 is a schematic diagram of an embodiment of a method for controlling risk in banking business according to an embodiment of the present invention. Figure 4 As shown, when implementing a banking business risk control method provided by an embodiment of the present invention, in one embodiment, before determining the risk type to be controlled at the current moment based on the bank's historical business processing data, the method further includes:

[0062] Step 401: Determine auxiliary processing steps based on the bank's historical business processing data;

[0063] Step 402: During the execution of each processing step in the set of preceding steps corresponding to the auxiliary processing step, the input of the auxiliary processing step is predicted based on the output of the processing step and the bank customer data. Based on the predicted input of the auxiliary processing step, the auxiliary processing step is pre-executed to obtain the output of the auxiliary processing step.

[0064] Step 403: When executing the auxiliary processing step, determine whether the input of the auxiliary processing step currently being executed is consistent with the input of the predicted auxiliary processing step; if they are consistent, use the output of the auxiliary processing step obtained by pre-execution as the execution output of the auxiliary processing step; otherwise, execute the auxiliary processing step based on the input of the auxiliary processing step currently being executed to obtain the execution output of the auxiliary processing step.

[0065] When implementing a banking business risk control method provided by an embodiment of the present invention, in one embodiment, determining auxiliary processing steps based on historical bank business processing data includes:

[0066] For each processing step, determine the risk probability of each dimension corresponding to the processing step based on the bank's historical processing data for the processing step;

[0067] Determine a partial order of the processing steps, where, for any two processing steps, if, for each dimension, the risk probability of the first processing step of the two processing steps corresponding to that dimension is less than or equal to the risk probability of the second processing step of the two processing steps corresponding to that dimension, and the risk probability of the first processing step corresponding to each dimension is less than a specified threshold, then the first processing step is determined to be superior to the second processing step;

[0068] According to the partial order of the processing steps, a maximum processing step of the partial order is determined, and the maximum processing step is determined as an auxiliary processing step, wherein the maximum processing step is a maximum element of the partial order.

[0069] A maximum element in a partial order means that there are no other elements other than the maximum element in the set corresponding to the partial order, so that other elements are superior to the maximum element.

[0070] In one embodiment, for each processing step, the risk probability of each dimension corresponding to the processing step is determined based on the bank's historical processing data for the processing step, including:

[0071] Select the processing data corresponding to each dimension from the bank's historical processing data for this processing step;

[0072] Divide the processing data corresponding to each dimension into multiple processing data subsets corresponding to the dimension;

[0073] The proportion of risk-related processing data in each processing data subset corresponding to each dimension is used as the risk sample of the processing step corresponding to the dimension;

[0074] Determine the quantity threshold based on the risk samples obtained for each dimension of the handling steps;

[0075] For each dimension, if the number of risk samples corresponding to the processing step for that dimension is less than the quantity threshold, the following steps are executed in a loop until the number of risk samples corresponding to the processing step for that dimension is greater than or equal to the quantity threshold:

[0076] Obtain new bank processing data for the processing step, and select new processing data corresponding to the dimension from the new bank processing data;

[0077] Divide the new processing data corresponding to the dimension into multiple new processing data subsets corresponding to the dimension;

[0078] The proportion of risk-related processing data in each new processing data subset corresponding to the dimension is used as the risk sample of the processing step corresponding to the dimension;

[0079] For each dimension, when the number of risk samples corresponding to the dimension for the handling step is greater than or equal to a quantity threshold, the risk probability of the handling step corresponding to the dimension is determined as the mean value of the risk samples corresponding to the dimension for the handling step.

[0080] The quantity threshold is determined based on the risk samples of each dimension corresponding to the obtained handling steps, including:

[0081] Determining the risk variance of each dimension corresponding to the processing step based on the risk samples of each dimension corresponding to the processing step;

[0082] The maximum value of the risk variance of each dimension corresponding to the handling steps is taken as the maximum variance φ;

[0083] The quantity threshold is determined as in, is the maximum value of the risk probability error, and p is the probability that the risk probability error is greater than β.

[0084] When implementing a banking business risk control method provided by an embodiment of the present invention, in one embodiment, based on the output of the processing step and bank customer data, the input of the auxiliary processing step is predicted, and based on the predicted input of the auxiliary processing step, the auxiliary processing step is pre-executed to obtain the output of the auxiliary processing step, including:

[0085] Based on the bank's historical business processing data, determine the conditional probability of each input of the auxiliary processing step, given that the output of each processing step in the set of preceding steps of the auxiliary processing step has been obtained;

[0086] Determining the probability of each input of the auxiliary processing step based on the output of the processing step and the conditional probability;

[0087] The auxiliary processing step is pre-executed using the input of the auxiliary processing step with the highest corresponding probability to obtain the output of the auxiliary processing step.

[0088] When implementing a banking business risk control method provided by an embodiment of the present invention, in one embodiment, the method further includes:

[0089] Determine the estimated execution time for each step of a banking transaction based on the bank's historical transaction data;

[0090] When multiple processing steps executed in parallel in real-time business processing require information input at the same time, the priority of each of the multiple processing steps executed in parallel is determined based on the estimated execution time, and the multiple processing steps executed in parallel are displayed based on the priority to obtain corresponding input information.

[0091] In one embodiment, determining the estimated execution time of each step of a banking transaction based on historical banking transaction data includes:

[0092] For each processing step of the banking business, the processing time data corresponding to the processing step is selected from the bank's historical business processing data;

[0093] Determine the estimated execution time of the processing step based on the processing time data corresponding to the processing step.

[0094] In one embodiment, determining a priority of each of a plurality of processing steps executed in parallel based on an estimated execution time, and displaying the plurality of processing steps executed in parallel based on the priority to obtain corresponding input information includes:

[0095] The priority of each of the multiple processing steps executed in parallel is determined according to the following formula:

[0096]

[0097] Among them, r i is the priority of the i-th processing step among multiple processing steps executed in parallel, r i and r j are the estimated execution times of the i-th and j-th processing steps in multiple processing steps executed in parallel, respectively. g is a function with a range greater than 0 and is a monotonically increasing function of the independent variable.

[0098] Select a function w and determine the integral value c of the domain of the function w;

[0099] Divide the domain of the function w into multiple real-valued intervals, where the intersection of any two real-valued intervals is empty, and the real-valued intervals correspond to the processing steps executed in parallel. The integral value of the function w in each real-valued interval is equal to the product of c and the priority of the processing step corresponding to the real-valued interval.

[0100] Based on function Generate random numbers and determine the real value interval in which the random numbers are located;

[0101] The processing steps corresponding to the real value interval in which the random number is located are displayed to obtain the corresponding input information.

[0102] When implementing a banking business risk control method provided by an embodiment of the present invention, in one embodiment, the type of risk to be controlled at the current moment is determined based on the bank's historical business processing data, and risk control is performed on the execution of each processing step in the set of subsequent steps based on the type of risk to be controlled at the current moment and the corresponding risk control model, including:

[0103] Determine, based on the bank's historical business processing data, multiple risk types corresponding to the processing steps; wherein each risk type corresponds to multiple processing steps, and a set of the multiple processing steps is determined as a set of processing steps corresponding to the risk type;

[0104] When a handling step is completed, multiple risk types corresponding to the completed handling step are obtained. For each obtained risk type, it is determined whether all handling steps in the corresponding handling step set have been completed. If all handling steps have been completed, the risk type is determined as the risk type to be controlled at the current moment.

[0105] For each risk type to be controlled, obtain the transaction data generated by each processing step in the corresponding processing step set, and determine all transaction data generated by all processing steps in the corresponding processing step set as relevant business data for the risk type to be controlled;

[0106] The risk control model corresponding to the risk type to be controlled at the current moment is used to perform risk control on the relevant business data of the risk type to be controlled.

[0107] The following briefly describes a banking business risk control method provided by an embodiment of the present invention in conjunction with a specific scenario:

[0108] Based on historical data, the auxiliary steps for each transaction are determined. Then, based on the inputs and outputs of each step and risk control requirements, the dependencies between the steps, as well as the start and end nodes, are determined. When a customer conducts a transaction in the banking system, the process proceeds sequentially from the start step. For each auxiliary step, the input is predicted, and then the auxiliary step is pre-executed to obtain the output. When the auxiliary step is reached, the current input and the predicted input are determined to be consistent. If they are consistent, the previously obtained output is directly obtained. If not, the auxiliary step is executed based on the current input.

[0109] Figure 5 A schematic diagram of a computer device for running a banking business risk control method implemented by the present invention, such as Figure 5 As shown, an embodiment of the present invention further provides a computer device 500, comprising a memory 510, a processor 520, and a computer program 530 stored in the memory and executable on the processor, wherein the processor implements the above-mentioned banking business risk control method when executing the computer program.

[0110] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the above-mentioned banking business risk control method.

[0111] 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 above-mentioned banking business risk control method.

[0112] The present invention also provides a banking risk control device, as described in the following embodiments. Since the principle of the device is similar to that of a banking risk control method, the implementation of the device can refer to the implementation of a banking risk control method, and the repeated parts will not be repeated.

[0113] Figure 6 Schematic diagram of a banking business risk control device according to an embodiment of the present invention. Figure 6 As shown, the embodiment of the present invention also provides a banking business risk control device;

[0114] When implementing a banking business risk control device provided by an embodiment of the present invention, in one embodiment, the device includes:

[0115] The banking business processing step determination module 601 is used to determine the banking business processing steps based on the bank's historical business processing data;

[0116] The module 602 for determining a set of pre-steps and a set of post-steps is used to determine, for each processing step, a set of pre-steps and a set of post-steps corresponding to the processing step;

[0117] An initial step node and an end step node determination module 603 is configured to determine an initial step node and an end step node according to a set of preceding steps and a set of following steps;

[0118] The processing step execution module 604 is used to execute each processing step of the initial step node when processing business in real time;

[0119] The loop execution module 605 is used to loop through the following steps until the end step node is reached:

[0120] The execution judgment module 606 is used to determine whether the execution condition is met for each processing step in the set of subsequent steps corresponding to the completed processing step when the processing step is completed. If there is a processing step in the set of subsequent steps corresponding to the completed processing step that meets the execution condition, the processing step is executed. The execution condition is whether all the preceding steps in the set of preceding steps corresponding to the processing step have been completed.

[0121] The risk control module 607 is used to determine the type of risk to be controlled at the current moment based on the bank's historical business processing data, and to perform risk control on the execution of each processing step in the post-step set based on the type of risk to be controlled at the current moment and the corresponding risk control model.

[0122] When implementing a banking business risk control device provided by an embodiment of the present invention, in one embodiment, the banking business processing steps include input and output;

[0123] The module for determining the set of pre-steps and the set of post-steps is used to:

[0124] Determine whether the output of a processing step of a banking service is the input of each subsequent processing step of the processing step, and if the output of the processing step is the input of the subsequent processing step, establish a direct relationship between the two processing steps;

[0125] The processing step of establishing the direct relationship is defined as the preceding step of the direct relationship, and the subsequent processing step of establishing the direct relationship is defined as the following step of the direct relationship, wherein the following step depends on the preceding step;

[0126] Poll the steps of handling banking business and group all direct relationships into direct relationship sets;

[0127] According to the direct relationship set, the corresponding pre-step set and post-step set are determined for each processing step.

[0128] When implementing a banking business risk control device provided by an embodiment of the present invention, in one embodiment, the module for determining a set of pre-steps and a set of post-steps is further configured to:

[0129] From the direct relationship set, filter out all direct relationships whose corresponding subsequent steps are the processing step, and use the set consisting of all preceding steps of all the filtered direct relationships as the preceding step set corresponding to the processing step;

[0130] From the direct relationship set, all direct relationships whose corresponding predecessor steps are the processing steps are screened out, and a set consisting of all subsequent steps of all the screened direct relationships is used as the subsequent step set corresponding to the processing step.

[0131] When implementing a banking business risk control device provided by an embodiment of the present invention, in one embodiment, the initial step node and the end step node determination module are specifically configured to:

[0132] According to the set of preceding steps and the set of following steps, the processing steps that are not in the set of following steps corresponding to any processing step are determined as initial step nodes, and the processing steps that are not in the set of preceding steps corresponding to any processing step are determined as ending step nodes.

[0133] When implementing a banking business risk control device provided by an embodiment of the present invention, in one embodiment, it further includes an auxiliary step processing module for:

[0134] Determine auxiliary processing steps based on the bank's historical business processing data;

[0135] During the execution of each processing step in the set of preceding steps corresponding to the auxiliary processing step, the input of the auxiliary processing step is predicted based on the output of the processing step and the bank customer data; based on the predicted input of the auxiliary processing step, the auxiliary processing step is pre-executed to obtain the output of the auxiliary processing step;

[0136] When executing the auxiliary processing step, determine whether the input of the auxiliary processing step currently being executed is consistent with the input of the predicted auxiliary processing step; if they are consistent, use the output of the auxiliary processing step obtained by pre-execution as the execution output of the auxiliary processing step; otherwise, execute the auxiliary processing step based on the input of the auxiliary processing step currently being executed to obtain the execution output of the auxiliary processing step.

[0137] When implementing a banking business risk control device provided by an embodiment of the present invention, in one embodiment, the auxiliary step processing module is further configured to:

[0138] For each processing step, determine the risk probability of each dimension corresponding to the processing step based on the bank's historical processing data for the processing step;

[0139] Determine a partial order of the processing steps, where, for any two processing steps, if, for each dimension, the risk probability of the first processing step of the two processing steps corresponding to that dimension is less than or equal to the risk probability of the second processing step of the two processing steps corresponding to that dimension, and the risk probability of the first processing step corresponding to each dimension is less than a specified threshold, then the first processing step is determined to be superior to the second processing step;

[0140] According to the partial order of the processing steps, a maximum processing step of the partial order is determined, and the maximum processing step is determined as an auxiliary processing step, wherein the maximum processing step is a maximum element of the partial order.

[0141] When implementing a banking business risk control device provided by an embodiment of the present invention, in one embodiment, the auxiliary step processing module is further configured to:

[0142] Based on the bank's historical business processing data, determine the conditional probability of each input of the auxiliary processing step, given that the output of each processing step in the set of preceding steps of the auxiliary processing step has been obtained;

[0143] Determining the probability of each input of the auxiliary processing step based on the output of the processing step and the conditional probability;

[0144] The auxiliary processing step is pre-executed using the input of the auxiliary processing step with the highest corresponding probability to obtain the output of the auxiliary processing step.

[0145] When implementing a banking business risk control device provided by an embodiment of the present invention, in one embodiment, the device further includes an execution time estimation module for:

[0146] Determine the estimated execution time for each step of a banking transaction based on the bank's historical transaction data;

[0147] When multiple processing steps executed in parallel in real-time business processing require information input at the same time, the priority of each of the multiple processing steps executed in parallel is determined based on the estimated execution time, and the multiple processing steps executed in parallel are displayed based on the priority to obtain corresponding input information.

[0148] When implementing a banking business risk control device provided by an embodiment of the present invention, in one embodiment, the risk control module is specifically configured to:

[0149] Determine, based on the bank's historical business processing data, multiple risk types corresponding to the processing steps; wherein each risk type corresponds to multiple processing steps, and a set of the multiple processing steps is determined as a set of processing steps corresponding to the risk type;

[0150] When a handling step is completed, multiple risk types corresponding to the completed handling step are obtained. For each obtained risk type, it is determined whether all handling steps in the corresponding handling step set have been completed. If all handling steps have been completed, the risk type is determined as the risk type to be controlled at the current moment.

[0151] For each risk type to be controlled, obtain the transaction data generated by each processing step in the corresponding processing step set, and determine all transaction data generated by all processing steps in the corresponding processing step set as relevant business data for the risk type to be controlled;

[0152] The risk control model corresponding to the risk type to be controlled at the current moment is used to perform risk control on the relevant business data of the risk type to be controlled.

[0153] In summary, an embodiment of the present invention provides a method and device for controlling bank business processing risks, including: determining the processing steps of the bank business based on the bank's historical business processing data; for each processing step, determining the corresponding pre-step set and post-step set of the processing step; determining the initial step node and the end step node based on the pre-step set and post-step set; when processing business in real time, executing each processing step of the initial step node; looping and executing the following steps until the end step node is executed: when the node where the processing step is located is completed, judging whether the execution condition is met for each processing step in the post-step set corresponding to the completed processing step; if there is a processing step in the post-step set corresponding to the completed processing step that meets the execution condition, then executing the processing step; the execution condition is whether all pre-steps in the pre-step set corresponding to the processing step have been completed; determining the risk type to be controlled at the current moment based on the bank's historical business processing data, and performing risk control on the execution of each processing step in the post-step set based on the risk type to be controlled at the current moment and the corresponding risk control model.

[0154] The embodiment of the present invention can reduce the execution time of business processing and the waiting time of customers by executing business steps in parallel, and can also effectively control the risks of the business and improve the security of banking business.

[0155] 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. Various types of data such as personal identity data, operation data, behavioral data, etc. related to individuals, customers, and groups obtained by this application have been authorized.

[0156] 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.

[0157] 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.

[0158] 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 1 The function specified in one or more boxes.

[0159] 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.

[0160] 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 banking business risk control method, characterized in that: include: Determine the steps for handling banking business based on the bank's historical business handling data; The steps of handling the banking business include input and output; For each processing step, determining a set of preceding steps and a set of following steps corresponding to the processing step, including: determining whether the output of a processing step of a banking business is the input of each subsequent processing step of the processing step; if the output of the processing step is the input of the subsequent processing step, establishing a direct relationship between the two processing steps; defining the processing step that establishes the direct relationship as the preceding step of the direct relationship, and defining the subsequent processing step that establishes the direct relationship as the following step of the direct relationship, wherein the following step depends on the preceding step; polling the processing steps of the banking business, and forming all direct relationships into a direct relationship set; filtering out from the direct relationship set all direct relationships whose corresponding following steps are the processing steps, and using the set consisting of all preceding steps of all the filtered direct relationships as the preceding step set corresponding to the processing step; filtering out from the direct relationship set all direct relationships whose corresponding preceding steps are the processing steps, and using the set consisting of all following steps of all the filtered direct relationships as the following step set corresponding to the processing step; Determining an initial step node and an end step node based on the set of preceding steps and the set of following steps includes: determining as an initial step node all processing steps that are not in the set of following steps corresponding to any processing step, and determining as an end step node all processing steps that are not in the set of preceding steps corresponding to any processing step; When handling business in real time, execute each processing step of the initial step node; Loop through the following steps until the end step is reached: When the node where the processing step is located is completed, each processing step in the set of subsequent steps corresponding to the completed processing step is judged to see whether the execution condition is met; if there is a processing step in the set of subsequent steps corresponding to the completed processing step that meets the execution condition, then the processing step is executed; the execution condition is whether all the preceding steps in the set of preceding steps corresponding to the processing step in the set of subsequent steps have been completed; Based on the bank's historical business processing data, the type of risk to be controlled at the current moment is determined. Based on the type of risk to be controlled at the current moment and the corresponding risk control model, risk control is performed on the execution of each processing step in the set of subsequent steps.

2. The method according to claim 1, wherein Before determining the current risk type to be controlled based on the bank's historical business data, the following steps are also required: Determine auxiliary processing steps based on the bank's historical business processing data; During the execution of each processing step in the set of preceding steps corresponding to the auxiliary processing step, the input of the auxiliary processing step is predicted based on the output of the processing step and the bank customer data; based on the predicted input of the auxiliary processing step, the auxiliary processing step is pre-executed to obtain the output of the auxiliary processing step; When executing the auxiliary processing step, determining whether the input of the auxiliary processing step currently being executed is consistent with the input of the predicted auxiliary processing step; if they are consistent, using the output of the auxiliary processing step obtained in the pre-execution as the execution output of the auxiliary processing step; otherwise, executing the auxiliary processing step based on the input of the auxiliary processing step currently being executed to obtain the execution output of the auxiliary processing step; Based on the bank's historical business processing data, determine the auxiliary processing steps, including: For each processing step, determine the risk probability of each dimension corresponding to the processing step based on the bank's historical processing data for the processing step; Determine a partial order of the processing steps, where, for any two processing steps, if, for each dimension, the risk probability of the first processing step of the two processing steps corresponding to that dimension is less than or equal to the risk probability of the second processing step of the two processing steps corresponding to that dimension, and the risk probability of the first processing step corresponding to each dimension is less than a specified threshold, then the first processing step is determined to be superior to the second processing step; According to the partial order of the processing steps, a maximum processing step of the partial order is determined, and the maximum processing step is determined as an auxiliary processing step, wherein the maximum processing step is a maximum element of the partial order.

3. The method according to claim 2, wherein The method includes predicting an input of an auxiliary processing step based on the output of the processing step and bank customer data, pre-executing the auxiliary processing step based on the predicted input of the auxiliary processing step, and obtaining an output of the auxiliary processing step, including: Based on the bank's historical business processing data, determine the conditional probability of each input of the auxiliary processing step, given that the output of each processing step in the set of preceding steps of the auxiliary processing step has been obtained; Determining the probability of each input of the auxiliary processing step based on the output of the processing step and the conditional probability; The auxiliary processing step is pre-executed using the input corresponding to the auxiliary processing step with the highest probability, and the output of the auxiliary processing step is obtained.

4. The method according to claim 1, wherein Also includes: Determine the estimated execution time for each step of a banking transaction based on the bank's historical transaction data; When multiple processing steps executed in parallel in real-time business processing require information input at the same time, the priority of each of the multiple processing steps executed in parallel is determined based on the estimated execution time, and the multiple processing steps executed in parallel are displayed based on the priority to obtain corresponding input information.

5. The method according to claim 1, wherein Based on the bank's historical business processing data, determine the current type of risk to be controlled. Based on the current type of risk to be controlled and the corresponding risk control model, perform risk control on the execution of each processing step in the post-step set, including: Determine, based on the bank's historical business processing data, multiple risk types corresponding to the processing steps; wherein each risk type corresponds to multiple processing steps, and a set of the multiple processing steps is determined as a set of processing steps corresponding to the risk type; When a handling step is completed, multiple risk types corresponding to the completed handling step are obtained. For each obtained risk type, it is determined whether all handling steps in the corresponding handling step set have been completed. If all handling steps have been completed, the risk type is determined as the risk type to be controlled at the current moment. For each risk type to be controlled, obtain the transaction data generated by each processing step in the corresponding processing step set, and determine all transaction data generated by all processing steps in the corresponding processing step set as relevant business data for the risk type to be controlled; The risk control model corresponding to the risk type to be controlled at the current moment is used to perform risk control on the relevant business data of the risk type to be controlled.

6. A banking business risk control device, characterized in that: include: The banking business processing step determination module is used to determine the banking business processing steps based on the bank's historical business processing data; The steps of handling the banking business include input and output; The module for determining a set of pre-steps and a set of post-steps is used to determine, for each processing step, the set of pre-steps and post-steps corresponding to the processing step, including: determining whether the output of a processing step of a banking business is the input of each subsequent processing step of the processing step; if the output of the processing step is the input of the subsequent processing step, establishing a direct relationship between the two processing steps; defining the processing step for which the direct relationship is established as the pre-step of the direct relationship, and defining the subsequent processing step for which the direct relationship is established as the post-step of the direct relationship, wherein the post-step is dependent on the pre-step; polling the processing steps of the banking business and forming all direct relationships into a direct relationship set; filtering out from the direct relationship set all direct relationships whose corresponding post-steps are the processing steps, and using the set consisting of all pre-steps of all the filtered direct relationships as the pre-step set corresponding to the processing step; filtering out from the direct relationship set all direct relationships whose corresponding pre-steps are the processing steps, and using the set consisting of all post-steps of all the filtered direct relationships as the post-step set corresponding to the processing step; The module for determining an initial step node and an end step node is configured to determine an initial step node and an end step node based on a set of preceding steps and a set of following steps, including: determining as an initial step node any processing step that is not in a set of following steps corresponding to any processing step, and determining as an end step node any processing step that is not in a set of preceding steps corresponding to any processing step; The processing step execution module is used to execute each processing step of the initial step node when processing business in real time; The loop execution module is used to loop through the following steps until the end step node is reached: An execution judgment module is used to judge whether the execution condition is met for each processing step in the set of subsequent steps corresponding to the completed processing step when the processing step is completed; if there is a processing step in the set of subsequent steps corresponding to the completed processing step that meets the execution condition, then the processing step is executed; the execution condition is whether all the preceding steps in the set of preceding steps corresponding to the processing step in the set of subsequent steps have been completed; The risk control module is used to determine the type of risk to be controlled at the current moment based on the bank's historical business processing data, and to perform risk control on the execution of each processing step in the post-step set based on the type of risk to be controlled at the current moment and the corresponding risk control model.

7. The device according to claim 6, characterized in that It also includes auxiliary step management modules for: Determine auxiliary processing steps based on the bank's historical business processing data; During the execution of each processing step in the set of preceding steps corresponding to the auxiliary processing step, the input of the auxiliary processing step is predicted based on the output of the processing step and the bank customer data; based on the predicted input of the auxiliary processing step, the auxiliary processing step is pre-executed to obtain the output of the auxiliary processing step; When executing the auxiliary processing step, determining whether the input of the auxiliary processing step currently being executed is consistent with the input of the predicted auxiliary processing step; If they are consistent, the output of the auxiliary processing step obtained in the pre-execution is used as the execution output of the auxiliary processing step; otherwise, the auxiliary processing step is executed according to the input of the auxiliary processing step currently being executed to obtain the execution output of the auxiliary processing step; The auxiliary step management module is also used to: For each processing step, determine the risk probability of each dimension corresponding to the processing step based on the bank's historical processing data for the processing step; Determine a partial order of the processing steps, where, for any two processing steps, if, for each dimension, the risk probability of the first processing step of the two processing steps corresponding to that dimension is less than or equal to the risk probability of the second processing step of the two processing steps corresponding to that dimension, and the risk probability of the first processing step corresponding to each dimension is less than a specified threshold, then the first processing step is determined to be superior to the second processing step; According to the partial order of the processing steps, a maximum processing step of the partial order is determined, and the maximum processing step is determined as an auxiliary processing step, wherein the maximum processing step is a maximum element of the partial order.

8. The device according to claim 7, wherein The auxiliary step management module is also used to: Based on the bank's historical business processing data, determine the conditional probability of each input of the auxiliary processing step, given that the output of each processing step in the set of preceding steps of the auxiliary processing step has been obtained; Determining the probability of each input of the auxiliary processing step based on the output of the processing step and the conditional probability; The auxiliary processing step is pre-executed using the input corresponding to the auxiliary processing step with the highest probability, and the output of the auxiliary processing step is obtained.

9. The device according to claim 6, wherein It also includes an execution time estimation module for: Determine the estimated execution time for each step of a banking transaction based on the bank's historical transaction data; When multiple processing steps executed in parallel in real-time business processing require information input at the same time, the priority of each of the multiple processing steps executed in parallel is determined based on the estimated execution time, and the multiple processing steps executed in parallel are displayed based on the priority to obtain corresponding input information.

10. The device according to claim 6, wherein The risk control module is specifically used to: Determine, based on the bank's historical business processing data, multiple risk types corresponding to the processing steps; wherein each risk type corresponds to multiple processing steps, and a set of the multiple processing steps is determined as a set of processing steps corresponding to the risk type; When a handling step is completed, multiple risk types corresponding to the completed handling step are obtained. For each obtained risk type, it is determined whether all handling steps in the corresponding handling step set have been completed. If all handling steps have been completed, the risk type is determined as the risk type to be controlled at the current moment. For each risk type to be controlled, obtain the transaction data generated by each processing step in the corresponding processing step set, and determine all transaction data generated by all processing steps in the corresponding processing step set as relevant business data for the risk type to be controlled; The risk control model corresponding to the risk type to be controlled at the current moment is used to perform risk control on the relevant business data of the risk type to be controlled.

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