Risk control method and device for new banking business types
Patent Information
- Application Number
- CN202210640179.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-06-08
- Publication Date
- 2024-11-05
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Banks are difficult to predict and control the possible risks when operating new business types, resulting in potential losses to banks and customers.
By analyzing each existing business type of the bank, obtaining its transaction interface, selecting feature information units to build an interface space, determining the coordinate values of the existing business type, and determining its reference services in the interface space based on the interface of the new business type type, thereby determining its risk type and risk control.
It has achieved effective control of risks of new business types, ensured the property safety of customers and banks, and provided technical support for banks' digital risk control.
Smart Images

Figure CN114926296B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of financial data processing, and in particular to a risk control method and device for a new banking business type. Background Art
[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.
[0003] In the daily operation of banks, many new business types will be added with the needs and development of operations. Since there is no actual data for new business types, it is impossible to predict their possible risks. This will make it impossible to effectively control the possible risks of new business types, causing losses to banks and customers.
[0004] In summary, there is an urgent need for a technical solution that can overcome the above-mentioned defects, analyze new types of banking business, and effectively control risks. Summary of the invention
[0005] In order to solve the problems existing in the prior art, the present invention proposes a risk control method and device for a new type of banking business.
[0006] In a first aspect of an embodiment of the present invention, a risk control method for a new banking business type is proposed, comprising:
[0007] For each existing business type of the bank, obtain the transactions included in the existing business type and the interface of each included transaction;
[0008] Selecting a plurality of characteristic information units from the information units of the interfaces of all transactions of the bank;
[0009] Based on the characteristic information unit, an interface space is constructed, wherein the dimension of the interface space corresponds one-to-one to the characteristic information unit;
[0010] Determine a first coordinate value and a second coordinate value of each existing business type in the interface space according to the transactions included in each existing business type and the interface of each included transaction;
[0011] Acquire transactions included in the new business type and the interface of each transaction included therein, and determine the third coordinate value and the fourth coordinate value of the new business type in the interface space according to the transactions included in the new business type and the interface of each transaction included therein;
[0012] Selecting a reference service type for the new service type from the existing service types according to the first coordinate value and the second coordinate value of each existing service type in the interface space and the third coordinate value and the fourth coordinate value of the new service type in the interface space;
[0013] Determine the risk type corresponding to the new business type based on the business data of the reference business type of the new business type;
[0014] Based on the risk type corresponding to the new business type, risk control is performed on the business data of the new business type.
[0015] In a second aspect of an embodiment of the present invention, a risk control device for a new banking business type is provided, comprising:
[0016] An acquisition module, used for acquiring, for each existing business type of the bank, the transactions included in the existing business type and the interface of each included transaction;
[0017] A characteristic information unit selection module is used to select multiple characteristic information units from the information units of all transaction interfaces of the bank;
[0018] A construction module, used to construct an interface space based on the feature information unit, wherein the dimension of the interface space corresponds to the feature information unit one by one;
[0019] An existing business type coordinate value determination module, used to determine the first coordinate value and the second coordinate value of the existing business type in the interface space according to the transactions included in each existing business type and the interface of each transaction included;
[0020] A new business type coordinate value determination module, used to obtain transactions included in the new business type and the interface of each transaction included, and determine the third coordinate value and the fourth coordinate value of the new business type in the interface space according to the transactions included in the new business type and the interface of each transaction included;
[0021] A reference business type selection module, used to select a reference business type of the new business type from the existing business types according to the first coordinate value and the second coordinate value of each existing business type in the interface space and the third coordinate value and the fourth coordinate value of the new business type in the interface space;
[0022] A risk type determination module, used to determine the risk type corresponding to the new business type based on the business data of the reference business type of the new business type;
[0023] The risk control module is used to perform risk control on business data of the new business type based on the risk type corresponding to the new business type.
[0024] In a third aspect of an embodiment of the present invention, a computer device is proposed, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a risk control method for a new type of banking business when executing the computer program.
[0025] In a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is proposed, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a risk control method for a new banking business type is implemented.
[0026] In a fifth aspect of an embodiment of the present invention, a computer program product is proposed. The computer program product includes a computer program. When the computer program is executed by a processor, a risk control method for a new banking business type is implemented.
[0027] The risk control method and device for new bank business types proposed in the present invention analyze each existing business type of the bank to obtain transactions included in the existing business type and the interface of each transaction included; select multiple feature information units from the information units of the interfaces of all transactions of the bank; construct an interface space based on the feature information units, wherein the dimensions of the interface space correspond one-to-one to the feature information units; determine the first coordinate value and the second coordinate value of the existing business type in the interface space according to the transactions included in each existing business type and the interface of each transaction included; obtain the transactions included in the new business type and the interface of each transaction included, and determine the new business type in the interface space according to the transactions included in the new business type and the interface of each transaction included the third coordinate value and the fourth coordinate value of the new business type in the interface space; according to the first coordinate value and the second coordinate value of each existing business type in the interface space and the third coordinate value and the fourth coordinate value of the new business type in the interface space, a reference business type of the new business type is selected from the existing business types; according to the business data of the reference business type of the new business type, a risk type corresponding to the new business type is determined; based on the risk type corresponding to the new business type, risk control is performed on the business data of the new business type. The overall solution of the present invention can determine the risk type of the new business type by analyzing the relevant data of the new business type and the existing business types, thereby achieving effective control of the risk of the new business type, ensuring the property safety of customers and banks, and providing strong technical support for the digital risk control of banks. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0029] Figure 1 It is a flow chart of a risk control method for a new banking business type according to an embodiment of the present invention.
[0030] Figure 2It is a schematic diagram of a flow chart of selecting a plurality of characteristic information units from information units of all transaction interfaces of a bank according to an embodiment of the present invention.
[0031] Figure 3 It is a schematic diagram of a process of determining a first coordinate value and a second coordinate value of an existing service type in an interface space according to an embodiment of the present invention.
[0032] Figure 4 It is a schematic diagram of a process of determining the third coordinate value and the fourth coordinate value of a new service type in the interface space according to an embodiment of the present invention.
[0033] Figure 5 It is a schematic diagram of a process of selecting a reference service type for a new service type from existing service types according to an embodiment of the present invention.
[0034] Figure 6 It is a flowchart of determining the risk type corresponding to a new business type according to business data of a reference business type of the new business type according to an embodiment of the present invention.
[0035] Figure 7 It is a schematic diagram of the architecture of a risk control device for a new banking business type according to an embodiment of the present invention.
[0036] Figure 8 It is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0037] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.
[0038] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, device, apparatus, method or computer program product. Therefore, the present disclosure may be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.
[0039] According to an embodiment of the present invention, a risk control method and device for a new banking business type are proposed, which relate to the technical field of financial data processing.
[0040] The principle and spirit of the present invention are explained in detail below with reference to several representative embodiments of the present invention.
[0041] Figure 1FIG. 1 is a flow chart of a risk control method for a new banking business type according to an embodiment of the present invention. Figure 1 As shown, the method includes:
[0042] S1, for each existing business type of the bank, obtain the transactions included in the existing business type and the interface of each transaction included;
[0043] S2, selecting a plurality of characteristic information units from the information units of all transaction interfaces of the bank;
[0044] S3, constructing an interface space based on the feature information unit, wherein the dimension of the interface space corresponds to the feature information unit one by one;
[0045] S4, determining a first coordinate value and a second coordinate value of each existing business type in the interface space according to the transactions included in each existing business type and the interface of each transaction included;
[0046] S5, obtaining transactions included in the new business type and an interface of each transaction included therein, and determining a third coordinate value and a fourth coordinate value of the new business type in the interface space according to the transactions included in the new business type and the interface of each transaction included therein;
[0047] S6, selecting a reference service type for the new service type from the existing service types according to the first coordinate value and the second coordinate value of each existing service type in the interface space and the third coordinate value and the fourth coordinate value of the new service type in the interface space;
[0048] S7, determining the risk type corresponding to the new business type based on the business data of the reference business type of the new business type;
[0049] S8. Perform risk control on business data of the new business type based on the risk type corresponding to the new business type.
[0050] In order to explain more clearly the risk control methods for the above-mentioned new banking business types, each step is explained in detail below.
[0051] In S1, for each existing business type of the bank, the transactions included in the existing business type and the interface of each included transaction are obtained.
[0052] Each business type usually includes multiple transactions, and each transaction is the smallest unit of business conducted by a customer in a bank. For example, cash business includes deposit transactions, withdrawal transactions, and foreign currency scheduled cash withdrawal transactions.
[0053] Each transaction has input and output, similar to a function. For example, the input of a query transaction includes the customer's account, password, and the information category being queried, and the output includes the customer's account and the information corresponding to the information category. Usually, the output interface and input interface of a transaction are fixed. For example, the input of transaction A is 128 bits, the third bit is the customer's account, the 11th bit is the channel for handling the transaction, and so on. Each bit is an information unit.
[0054] In S2, reference Figure 2 , multiple characteristic information units are selected from the information units of all transaction interfaces of the bank, including:
[0055] S201, obtaining historical transaction data of the bank;
[0056] S202, selecting multiple risk models, wherein the input of each risk model is an information unit and the output is a risk identifier;
[0057] S203, for each information unit combination, filter out data corresponding to the information unit combination from the bank's historical transaction data, train the data with the selected multiple risk models, and obtain multiple risk prediction models; determine the accuracy vector corresponding to the information unit combination, wherein the components of the accuracy vector correspond to the risk prediction model one-to-one, and the component value of each component is equal to the accuracy index of the risk prediction model corresponding to the component;
[0058] S204, determining a partial order of the information unit combinations based on the precision vector, wherein the partial order is used to determine whether a first information unit combination is better than a second information unit combination among any two information unit combinations;
[0059] S205, selecting a plurality of characteristic information unit combinations from all the information unit combinations according to the partial order of the information unit combinations, wherein each characteristic information unit combination satisfies that other information unit combinations except the characteristic information unit combination are not better than the characteristic information unit combination;
[0060] S206: The information unit included in the union of the information units included in all combinations of the characteristic information units is taken as the characteristic information unit.
[0061] It should be noted that the accuracy index of the risk prediction model can be selected from the evaluation index of the prediction model in machine learning, which includes at least AUC, precision, and accuracy.
[0062] In one embodiment, (S204) determining the partial order of the information unit combination based on the precision vector includes:
[0063] For any two information unit combinations, calculate the vector difference between the precision vector corresponding to the first information unit combination in the two information unit combinations and the precision vector corresponding to the second information unit combination in the two information unit combinations. If each component of the vector difference is greater than or equal to 0, it is determined that the first information unit combination is better than the second information unit combination.
[0064] In one embodiment, (S205) multiple characteristic information unit combinations are selected from all information unit combinations, including:
[0065] S2051, initializing the maximum authentication value corresponding to each information unit combination to "pending", and initializing the comparison Boolean value corresponding to each information unit combination to "yes";
[0066] S2052, selecting a component, and sorting all information unit combinations in descending order according to the value of the corresponding precision vector in the component;
[0067] S2053, executing the following steps for each information unit combination in sequence according to the sorting order until all information unit combinations have completed the following steps:
[0068] For each information unit combination, if the maximum authentication value corresponding to the information unit combination is not "pending", the comparable information unit combination corresponding to the information unit combination is set to empty; otherwise, the comparable information unit combination corresponding to the information unit combination is set to all information unit combinations whose corresponding comparison Boolean value is "yes" (if the comparison Boolean value corresponding to the information unit combination is "yes", the comparable information unit combination corresponding to the information unit combination does not include the information unit combination);
[0069] Determine the partial order comparison relationship between the information unit combination and each corresponding comparable information unit combination in turn: if the comparable information unit combination is better than the information unit combination, update the maximum authentication value corresponding to the information unit combination to "No"; if the information unit combination is better than the comparable information unit combination, update the maximum authentication value corresponding to the comparable information unit combination to "No", and determine the comparable information unit combination as the secondary information unit combination of the information unit combination; if the comparable information unit combination is not better than the information unit combination and the information unit combination is not better than the comparable information unit combination, the maximum authentication values corresponding to the two information unit combinations remain unchanged;
[0070] If it is determined that all comparable information unit combinations corresponding to the information unit combination are not superior to the information unit combination, the information unit combination is determined as a characteristic information unit combination, and the comparison Boolean values of all secondary information unit combinations of the information unit combination are updated to "No".
[0071] In actual application scenarios, since the number of information unit combinations is an exponential function of the number of information units, when the number of information units is very large, the number of information unit combinations will be very large. The above embodiment can reduce a large number of redundant calculations and also reduce the complexity of calculations.
[0072] In S3, an interface space is constructed based on the feature information units, wherein the dimensions of the interface space correspond one-to-one to the feature information units.
[0073] In S4, ref. Figure 3 , according to the transactions included in each existing business type and the interface of each transaction included, determining the first coordinate value and the second coordinate value of the existing business type in the interface space, including:
[0074] S401, for each existing business type, determining the number of transactions in which the corresponding input interface of the transactions included in the existing business type includes each characteristic information unit, and the number of transactions in which the corresponding output interface of the transactions included in the existing business type includes each characteristic information unit;
[0075] S402, the first coordinate value of each dimension of the existing business type in the interface space is equal to the number of transactions whose corresponding input interfaces in the transactions included in the existing business type include the characteristic information units corresponding to the dimension, and the second coordinate value of each dimension of the existing business type in the interface space is equal to the number of transactions whose corresponding output interfaces in the transactions included in the existing business type include the characteristic information units corresponding to the dimension.
[0076] In S5, ref. Figure 4 , obtaining the transactions included in the new business type and the interface of each transaction included therein, and determining the third coordinate value and the fourth coordinate value of the new business type in the interface space according to the transactions included in the new business type and the interface of each transaction included therein, including:
[0077] S501, determining the number of transactions in which the input interface corresponding to the transactions included in the new business type includes each characteristic information unit, and the number of transactions in which the output interface corresponding to the transactions included in the new business type includes each characteristic information unit;
[0078] S502, determining the third coordinate value of each dimension of the new business type in the interface space according to the transaction quantity of the feature information unit corresponding to each dimension included in the input interface corresponding to the transaction included in the new business type;
[0079] S503: Determine the fourth coordinate value of each dimension of the new business type in the interface space according to the transaction quantity of the feature information unit corresponding to each dimension contained in the output interface corresponding to the transaction contained in the new business type.
[0080] In S6, reference Figure 5 , according to the first coordinate value and the second coordinate value of each existing service type in the interface space and the third coordinate value and the fourth coordinate value of the new service type in the interface space, a reference service type of the new service type is selected from the existing service types, including:
[0081] S601, for each existing service type, determining a first distance corresponding to the existing service type according to a third coordinate value of the new service type in the interface space and a first coordinate value of the existing service type in the interface space, and determining a second distance corresponding to the existing service type according to a fourth coordinate value of the new service type in the interface space and a second coordinate value of the existing service type in the interface space;
[0082] S602, determining a partial order of existing business types, wherein, for any two existing business types, if a first distance corresponding to a first existing business type of the two existing business types is less than or equal to a first distance corresponding to a second existing business type of the two existing business types, and a second distance corresponding to the first existing business type is less than or equal to a second distance corresponding to the second existing business type, then it is determined that the first existing business type is superior to the second existing business type;
[0083] S603, according to the partial order of the existing business types, for each existing business type, if there is no other existing business type other than the existing business type, such that the other existing business type is superior to the existing business type, then the existing business type is used as a reference business type for the new business type.
[0084] In S7, reference Figure 6 , based on the business data of the reference business type of the new business type, determine the risk type corresponding to the new business type, including:
[0085] S701, determining the probability of the new business type corresponding to each risk type based on the business data of the reference business type of the new business type;
[0086] S702: For each risk type, if the probability that the new business type corresponds to the risk type is greater than a specified threshold, the risk type is used as the risk type corresponding to the new business type.
[0087] In one embodiment, (S701) determining the probability of the new business type corresponding to each risk type according to the business data of the reference business type of the new business type includes:
[0088] S7011, splitting the service data of the reference service type of the new service type into multiple service data subsets in chronological order;
[0089] S7012, taking the proportion of the number of businesses involving each risk type in the businesses included in each business data subset as a probability sample of the new business type corresponding to the risk type;
[0090] S7013, determining a quantity threshold corresponding to each risk type based on a probability sample of each risk type corresponding to the new business type;
[0091] S7014: For each risk type, when the number of probability samples of the new business type corresponding to the risk type is less than the number threshold corresponding to the risk type, the following steps are executed repeatedly until the number of probability samples of the new business type corresponding to the risk type is greater than or equal to the number threshold corresponding to the risk type:
[0092] S7015, obtaining new business data of a reference business type for the new business type; splitting the new business data into multiple new business data subsets in chronological order; and taking the proportion of the number of businesses involving the risk type in the businesses included in each new business data subset as a probability sample of the new business type corresponding to the risk type;
[0093] S7016, for each risk type, when the number of probability samples of the new business type corresponding to the risk type is greater than or equal to the number threshold corresponding to the risk type, the probability of the new business type corresponding to the risk type is determined as the mean of the probability samples of the new business type corresponding to the risk type.
[0094] Wherein, (S7013) determining the quantity threshold corresponding to each risk type based on the probability sample of each risk type corresponding to the new business type includes:
[0095] S70131, determining the variance of each risk type corresponding to the new business type based on the probability sample of each risk type corresponding to the new business type;
[0096] S70132, setting a maximum value of the probability error and a maximum probability that the probability error is greater than the maximum value, and determining the product of the square of the maximum value and the maximum probability;
[0097] S70133: For each risk type, calculate the ratio of the square of the variance of the new business type corresponding to the risk type to the product, and determine the quantity threshold corresponding to the risk type as the smallest integer greater than the ratio.
[0098] In S8, based on the risk type corresponding to the new business type, risk control is performed on the business data of the new business type, including:
[0099] For each risk type corresponding to the new business type, risk control is performed on the business data of the new business type based on the risk control method corresponding to the risk type of the reference business type of the new business type.
[0100] It should be noted that, although the operations of the method of the present invention are described in a specific order in the above embodiments and the accompanying drawings, this does not require or imply that the operations must be performed in the specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.
[0101] After introducing the method of the exemplary embodiment of the present invention, next, refer to Figure 7 A risk control device for a new banking business type according to an exemplary embodiment of the present invention is introduced.
[0102] The implementation of the risk control device for the new business type of the bank can refer to the implementation of the above method, and the repeated parts will not be repeated. The term "module" or "unit" used below can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.
[0103] Based on the same inventive concept, the present invention also proposes a risk control device for a new type of banking business, such as Figure 7 As shown, the device comprises:
[0104] An acquisition module 710 is used to acquire, for each existing business type of the bank, transactions included in the existing business type and an interface for each transaction included;
[0105] The characteristic information unit selection module 720 is used to select a plurality of characteristic information units from the information units of the interfaces of all transactions of the bank;
[0106] A construction module 730 is used to construct an interface space based on the feature information unit, wherein the dimension of the interface space corresponds to the feature information unit one by one;
[0107] An existing business type coordinate value determination module 740 is used to determine a first coordinate value and a second coordinate value of the existing business type in the interface space according to transactions included in each existing business type and interfaces of each transaction included;
[0108] A new business type coordinate value determination module 750 is used to obtain transactions included in the new business type and the interface of each transaction included therein, and determine the third coordinate value and the fourth coordinate value of the new business type in the interface space according to the transactions included in the new business type and the interface of each transaction included therein;
[0109] A reference service type selection module 760 is used to select a reference service type of the new service type from the existing service types according to the first coordinate value and the second coordinate value of each existing service type in the interface space and the third coordinate value and the fourth coordinate value of the new service type in the interface space;
[0110] A risk type determination module 770, configured to determine the risk type corresponding to the new business type based on the business data of the reference business type of the new business type;
[0111] The risk control module 780 is used to perform risk control on the business data of the new business type based on the risk type corresponding to the new business type.
[0112] In one embodiment, the feature information unit selection module is specifically used to:
[0113] Obtain historical transaction data of the bank;
[0114] Selecting multiple risk models, wherein the input of each risk model is an information unit and the output is a risk indicator;
[0115] For each information unit combination, data corresponding to the information unit combination is screened out from the historical transaction data of the bank, and the data is trained using the selected multiple risk models to obtain multiple risk prediction models; the accuracy vector corresponding to the information unit combination is determined, wherein the components of the accuracy vector correspond to the risk prediction models one-to-one, and the component value of each component is equal to the accuracy index of the risk prediction model corresponding to the component;
[0116] Determine a partial order of the information unit combinations based on the precision vector, wherein the partial order is used to determine whether a first information unit combination is better than a second information unit combination among any two information unit combinations;
[0117] According to the partial order of the information unit combinations, multiple characteristic information unit combinations are selected from all the information unit combinations, wherein each characteristic information unit combination satisfies that other information unit combinations except the characteristic information unit combination are not better than the characteristic information unit combination;
[0118] The information unit included in the union of the information units included in all combinations of the characteristic information units is taken as the characteristic information unit.
[0119] In one embodiment, the feature information unit selection module determines the partial order of the information unit combination based on the precision vector, including:
[0120] For any two information unit combinations, calculate the vector difference between the precision vector corresponding to the first information unit combination in the two information unit combinations and the precision vector corresponding to the second information unit combination in the two information unit combinations. If each component of the vector difference is greater than or equal to 0, it is determined that the first information unit combination is better than the second information unit combination.
[0121] In one embodiment, the existing service type coordinate value determination module is specifically used for:
[0122] For each existing business type, determine the number of transactions whose corresponding input interfaces in the transactions included in the existing business type include each characteristic information unit, and the number of transactions whose corresponding output interfaces in the transactions included in the existing business type include each characteristic information unit;
[0123] The first coordinate value of each dimension of the existing business type in the interface space is equal to the number of transactions whose corresponding input interfaces in the transactions included in the existing business type contain the characteristic information units corresponding to the dimension, and the second coordinate value of each dimension of the existing business type in the interface space is equal to the number of transactions whose corresponding output interfaces in the transactions included in the existing business type contain the characteristic information units corresponding to the dimension.
[0124] In one embodiment, the new service type coordinate value determination module is specifically used for:
[0125] Determine the number of transactions in which the input interface corresponding to the transactions included in the new business type includes each characteristic information unit, and the number of transactions in which the output interface corresponding to the transactions included in the new business type includes each characteristic information unit;
[0126] Determine the third coordinate value of each dimension of the new business type in the interface space according to the transaction quantity of the feature information unit corresponding to each dimension included in the input interface corresponding to the transaction included in the new business type;
[0127] According to the transaction quantity of the characteristic information unit corresponding to each dimension contained in the output interface corresponding to the transaction contained in the new business type, the fourth coordinate value of each dimension of the new business type in the interface space is determined.
[0128] In one embodiment, the reference service type selection module is specifically used for:
[0129] For each existing service type, a first distance corresponding to the existing service type is determined according to a third coordinate value of the new service type in the interface space and a first coordinate value of the existing service type in the interface space, and a second distance corresponding to the existing service type is determined according to a fourth coordinate value of the new service type in the interface space and a second coordinate value of the existing service type in the interface space;
[0130] Determine a partial order of the existing business types, wherein, for any two existing business types, if a first distance corresponding to a first existing business type of the two existing business types is less than or equal to a first distance corresponding to a second existing business type of the two existing business types, and a second distance corresponding to the first existing business type is less than or equal to a second distance corresponding to the second existing business type, then determine that the first existing business type is superior to the second existing business type;
[0131] According to the partial order of existing business types, for each existing business type, if there is no other existing business type other than the existing business type, such that the other existing business type is superior to the existing business type, the existing business type is used as a reference business type for the new business type.
[0132] In one embodiment, the risk type determination module is specifically used to:
[0133] Determine the probability of the new business type corresponding to each risk type based on the business data of the reference business type of the new business type;
[0134] For each risk type, if the probability that the new service type corresponds to the risk type is greater than a specified threshold, the risk type is used as the risk type corresponding to the new service type.
[0135] In one embodiment, the risk control module is specifically used to:
[0136] For each risk type corresponding to the new business type, risk control is performed on the business data of the new business type based on the risk control method corresponding to the risk type of the reference business type of the new business type.
[0137] It should be noted that although several modules of the risk control device for the new business type of the bank are mentioned in the above detailed description, this division is only exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules described above can be concretized in one module. Conversely, the features and functions of one module described above can be further divided into multiple modules to be concretized.
[0138] Based on the above invention concept, Figure 8 As shown, the present invention also proposes a computer device 800, including a memory 810, a processor 820, and a computer program 830 stored in the memory 810 and executable on the processor 820, wherein the processor 820 implements the risk control method for the aforementioned new banking business type when executing the computer program 830.
[0139] Based on the aforementioned inventive concept, the present invention proposes 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 risk control method for the aforementioned new banking business type is implemented.
[0140] Based on the aforementioned inventive concept, the present invention proposes a computer program product, which includes a computer program, and when the computer program is executed by a processor, a risk control method for a new banking business type is implemented.
[0141] The risk control method and device for new bank business types proposed in the present invention analyze each existing business type of the bank to obtain transactions included in the existing business type and the interface of each transaction included; select multiple feature information units from the information units of the interfaces of all transactions of the bank; construct an interface space based on the feature information units, wherein the dimensions of the interface space correspond one-to-one to the feature information units; determine the first coordinate value and the second coordinate value of the existing business type in the interface space according to the transactions included in each existing business type and the interface of each transaction included; obtain the transactions included in the new business type and the interface of each transaction included, and determine the new business type in the interface space according to the transactions included in the new business type and the interface of each transaction included the third coordinate value and the fourth coordinate value of the new business type in the interface space; according to the first coordinate value and the second coordinate value of each existing business type in the interface space and the third coordinate value and the fourth coordinate value of the new business type in the interface space, a reference business type of the new business type is selected from the existing business types; according to the business data of the reference business type of the new business type, a risk type corresponding to the new business type is determined; based on the risk type corresponding to the new business type, risk control is performed on the business data of the new business type. The overall solution of the present invention can determine the risk type of the new business type by analyzing the relevant data of the new business type and the existing business types, thereby achieving effective control of the risk of the new business type, ensuring the property safety of customers and banks, and providing strong technical support for the digital risk control of banks.
[0142] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0143] The present invention is described with reference to flowcharts and / or block diagrams of methods and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0144] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0145] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0146] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims
1. A risk control method for a new banking business type, characterized in that: include: For each existing business type of the bank, obtain the transactions included in the existing business type and the interface of each included transaction; Selecting a plurality of characteristic information units from the information units of the interfaces of all transactions of the bank; Based on the characteristic information unit, an interface space is constructed, wherein the dimension of the interface space corresponds to the characteristic information unit one by one; Determine a first coordinate value and a second coordinate value of each existing business type in the interface space according to the transactions included in each existing business type and the interface of each included transaction; Acquire transactions included in the new business type and the interface of each transaction included therein, and determine the third coordinate value and the fourth coordinate value of the new business type in the interface space according to the transactions included in the new business type and the interface of each transaction included therein; Selecting a reference service type for the new service type from the existing service types according to the first coordinate value and the second coordinate value of each existing service type in the interface space and the third coordinate value and the fourth coordinate value of the new service type in the interface space; Determine the risk type corresponding to the new business type based on the business data of the reference business type of the new business type; Based on the risk type corresponding to the new business type, risk control is performed on the business data of the new business type; Wherein, according to the transactions included in each existing business type and the interface of each transaction included, determining the first coordinate value and the second coordinate value of the existing business type in the interface space includes: For each existing business type, determine the number of transactions whose corresponding input interfaces in the transactions included in the existing business type include each characteristic information unit, and the number of transactions whose corresponding output interfaces in the transactions included in the existing business type include each characteristic information unit; The first coordinate value of each dimension of the existing business type in the interface space is equal to the number of transactions whose corresponding input interface in the transactions included in the existing business type includes the feature information unit corresponding to the dimension, and the second coordinate value of each dimension of the existing business type in the interface space is equal to the number of transactions whose corresponding output interface in the transactions included in the existing business type includes the feature information unit corresponding to the dimension; The process of acquiring transactions included in the new business type and the interface of each transaction included therein, and determining the third coordinate value and the fourth coordinate value of the new business type in the interface space according to the transactions included in the new business type and the interface of each transaction included therein, includes: Determine the number of transactions in which the input interface corresponding to the transactions included in the new business type includes each characteristic information unit, and the number of transactions in which the output interface corresponding to the transactions included in the new business type includes each characteristic information unit; Determine the third coordinate value of each dimension of the new business type in the interface space according to the transaction quantity of the feature information unit corresponding to each dimension included in the input interface corresponding to the transaction included in the new business type; According to the transaction quantity of the characteristic information unit corresponding to each dimension contained in the output interface corresponding to the transaction contained in the new business type, the fourth coordinate value of each dimension of the new business type in the interface space is determined.
2. The method according to claim 1, characterized in that A plurality of characteristic information units are selected from the information units of all transaction interfaces of the bank, including: Obtain historical transaction data of the bank; Selecting multiple risk models, wherein the input of each risk model is an information unit and the output is a risk indicator; For each information unit combination, data corresponding to the information unit combination is screened out from the historical transaction data of the bank, and the data is trained using the selected multiple risk models to obtain multiple risk prediction models; the accuracy vector corresponding to the information unit combination is determined, wherein the components of the accuracy vector correspond to the risk prediction models one-to-one, and the component value of each component is equal to the accuracy index of the risk prediction model corresponding to the component; Determine a partial order of the information unit combinations based on the precision vector, wherein the partial order is used to determine whether a first information unit combination is better than a second information unit combination among any two information unit combinations; According to the partial order of the information unit combinations, multiple characteristic information unit combinations are selected from all the information unit combinations, wherein each characteristic information unit combination satisfies that other information unit combinations except the characteristic information unit combination are not better than the characteristic information unit combination; The information unit included in the union of the information units included in all the characteristic information unit combinations is taken as the characteristic information unit; Wherein, based on the precision vector, determining the partial order of the information unit combination includes: For any two information unit combinations, calculate the vector difference between the precision vector corresponding to the first information unit combination in the two information unit combinations and the precision vector corresponding to the second information unit combination in the two information unit combinations. If each component of the vector difference is greater than or equal to 0, it is determined that the first information unit combination is better than the second information unit combination.
3. The method according to claim 1, characterized in that According to the first coordinate value and the second coordinate value of each existing service type in the interface space and the third coordinate value and the fourth coordinate value of the new service type in the interface space, a reference service type of the new service type is selected from the existing service types, including: For each existing service type, a first distance corresponding to the existing service type is determined according to a third coordinate value of the new service type in the interface space and a first coordinate value of the existing service type in the interface space, and a second distance corresponding to the existing service type is determined according to a fourth coordinate value of the new service type in the interface space and a second coordinate value of the existing service type in the interface space; Determine a partial order of the existing business types, wherein, for any two existing business types, if a first distance corresponding to a first existing business type of the two existing business types is less than or equal to a first distance corresponding to a second existing business type of the two existing business types, and a second distance corresponding to the first existing business type is less than or equal to a second distance corresponding to the second existing business type, then determine that the first existing business type is superior to the second existing business type; According to the partial order of existing business types, for each existing business type, if there is no other existing business type other than the existing business type, such that the other existing business type is superior to the existing business type, the existing business type is used as a reference business type for the new business type.
4. The method according to claim 1, characterized in that Based on the business data of the reference business type of the new business type, determine the risk type corresponding to the new business type, including: Determine the probability of the new business type corresponding to each risk type based on the business data of the reference business type of the new business type; For each risk type, if the probability that the new service type corresponds to the risk type is greater than a specified threshold, the risk type is used as the risk type corresponding to the new service type.
5. The method according to claim 1, characterized in that Based on the risk type corresponding to the new business type, risk control is performed on the business data of the new business type, including: For each risk type corresponding to the new business type, risk control is performed on the business data of the new business type based on the risk control method corresponding to the risk type of the reference business type of the new business type.
6. A risk control device for a new banking business type, characterized in that: include: An acquisition module, used for acquiring, for each existing business type of the bank, the transactions included in the existing business type and the interface of each included transaction; A characteristic information unit selection module is used to select multiple characteristic information units from the information units of all transaction interfaces of the bank; A construction module, used to construct an interface space based on the feature information unit, wherein the dimension of the interface space corresponds to the feature information unit one by one; An existing business type coordinate value determination module, used to determine the first coordinate value and the second coordinate value of the existing business type in the interface space according to the transactions included in each existing business type and the interface of each transaction included; A new business type coordinate value determination module, used to obtain transactions included in the new business type and the interface of each transaction included, and determine the third coordinate value and the fourth coordinate value of the new business type in the interface space according to the transactions included in the new business type and the interface of each transaction included; A reference business type selection module, used to select a reference business type of the new business type from the existing business types according to the first coordinate value and the second coordinate value of each existing business type in the interface space and the third coordinate value and the fourth coordinate value of the new business type in the interface space; A risk type determination module, used to determine the risk type corresponding to the new business type based on the business data of the reference business type of the new business type; A risk control module, used to perform risk control on business data of the new business type based on the risk type corresponding to the new business type; Among them, the existing business type coordinate value determination module is specifically used for: For each existing business type, determine the number of transactions whose corresponding input interfaces in the transactions included in the existing business type include each characteristic information unit, and the number of transactions whose corresponding output interfaces in the transactions included in the existing business type include each characteristic information unit; The first coordinate value of each dimension of the existing business type in the interface space is equal to the number of transactions whose corresponding input interface in the transactions included in the existing business type includes the feature information unit corresponding to the dimension, and the second coordinate value of each dimension of the existing business type in the interface space is equal to the number of transactions whose corresponding output interface in the transactions included in the existing business type includes the feature information unit corresponding to the dimension; The new service type coordinate value determination module is specifically used for: Determine the number of transactions in which the input interface corresponding to the transactions included in the new business type includes each characteristic information unit, and the number of transactions in which the output interface corresponding to the transactions included in the new business type includes each characteristic information unit; Determine the third coordinate value of each dimension of the new business type in the interface space according to the transaction quantity of the feature information unit corresponding to each dimension included in the input interface corresponding to the transaction included in the new business type; According to the transaction quantity of the characteristic information unit corresponding to each dimension contained in the output interface corresponding to the transaction contained in the new business type, the fourth coordinate value of each dimension of the new business type in the interface space is determined.
7. The device according to claim 6, characterized in that The feature information unit selection module is specifically used for: Obtain historical transaction data of the bank; Selecting multiple risk models, wherein the input of each risk model is an information unit and the output is a risk indicator; For each information unit combination, data corresponding to the information unit combination is screened out from the historical transaction data of the bank, and the data is trained using the selected multiple risk models to obtain multiple risk prediction models; the accuracy vector corresponding to the information unit combination is determined, wherein the components of the accuracy vector correspond to the risk prediction models one-to-one, and the component value of each component is equal to the accuracy index of the risk prediction model corresponding to the component; Determine a partial order of the information unit combinations based on the precision vector, wherein the partial order is used to determine whether a first information unit combination is better than a second information unit combination among any two information unit combinations; According to the partial order of the information unit combinations, multiple characteristic information unit combinations are selected from all the information unit combinations, wherein each characteristic information unit combination satisfies that other information unit combinations except the characteristic information unit combination are not better than the characteristic information unit combination; The information unit included in the union of the information units included in all the characteristic information unit combinations is taken as the characteristic information unit; Wherein, based on the precision vector, determining the partial order of the information unit combination includes: For any two information unit combinations, calculate the vector difference between the precision vector corresponding to the first information unit combination in the two information unit combinations and the precision vector corresponding to the second information unit combination in the two information unit combinations. If each component of the vector difference is greater than or equal to 0, it is determined that the first information unit combination is better than the second information unit combination.
8. The device according to claim 6, characterized in that The reference business type selection module is specifically used for: For each existing service type, a first distance corresponding to the existing service type is determined according to a third coordinate value of the new service type in the interface space and a first coordinate value of the existing service type in the interface space, and a second distance corresponding to the existing service type is determined according to a fourth coordinate value of the new service type in the interface space and a second coordinate value of the existing service type in the interface space; Determine a partial order of the existing business types, wherein, for any two existing business types, if a first distance corresponding to a first existing business type of the two existing business types is less than or equal to a first distance corresponding to a second existing business type of the two existing business types, and a second distance corresponding to the first existing business type is less than or equal to a second distance corresponding to the second existing business type, then determine that the first existing business type is superior to the second existing business type; According to the partial order of existing business types, for each existing business type, if there is no other existing business type other than the existing business type, such that the other existing business type is superior to the existing business type, the existing business type is used as a reference business type for the new business type.
9. The device according to claim 6, characterized in that The risk type determination module is specifically used to: Determine the probability of the new business type corresponding to each risk type based on the business data of the reference business type of the new business type; For each risk type, if the probability that the new service type corresponds to the risk type is greater than a specified threshold, the risk type is used as the risk type corresponding to the new service type.
10. The device according to claim 6, characterized in that The risk control module is specifically used for: For each risk type corresponding to the new business type, risk control is performed on the business data of the new business type based on the risk control method corresponding to the risk type of the reference business type of the new business type.
11. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 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.
