Method and apparatus for risk control of customer transactions

Abstract

The application provides a risk control method and device for customer transaction, which is applied to the technical field of finance, and comprises the following steps: determining a first functional relationship between a transaction threshold and a security coefficient of a non-line terminal and a second functional relationship between the transaction threshold and the security coefficient according to transaction data of the non-line terminal in daytime and nighttime; when a customer performs a transaction on the non-line terminal at night, determining a transaction threshold corresponding to the transaction according to the first functional relationship and the second functional relationship; and performing risk control on the transaction according to the transaction threshold corresponding to the transaction. The application can perform risk control when a transaction is performed on the non-line terminal.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of financial technology, in particular to a risk control method and device for customer transaction.

[0002] It should be noted that the risk control method and device for customer transaction can be used in the field of finance, and can also be used in any field other than the field of finance, and the application field of the risk control method and device for customer transaction is not limited. BACKGROUND

[0003] The off-site terminal is a self-service device away from the bank site. Since the off-site terminal is away from the bank site, the risk control of the bank on the off-site terminal is relatively weak, especially at night, and there are more uncontrollable factors at night, so the risk of the off-site terminal at night is relatively high. SUMMARY

[0004] The embodiment of the present application provides a risk control method for customer transaction, which is used for risk control when transaction is performed on the off-site terminal, and the method comprises the following steps:

[0005] According to the transaction data of the off-site terminal in the daytime and at night, a first function relationship between the transaction threshold and the safety coefficient of the off-site terminal and a second function relationship between the transaction threshold and the safety coefficient are determined;

[0006] When a customer performs transaction on the off-site terminal at night, the transaction threshold corresponding to the transaction is determined according to the first function relationship and the second function relationship;

[0007] According to the transaction threshold corresponding to the transaction, the risk control on the transaction is performed.

[0008] The embodiment of the present application provides a risk control device for customer transaction, which is used for risk control when transaction is performed on the off-site terminal, and the device comprises the following steps:

[0009] The function relationship determination module is configured to determine a first function relationship between the transaction threshold and the safety coefficient of the off-site terminal and a second function relationship between the transaction threshold and the safety coefficient according to the transaction data of the off-site terminal in the daytime and at night;

[0010] The transaction threshold determination module is configured to determine the transaction threshold corresponding to the transaction according to the first function relationship and the second function relationship when a customer performs transaction on the off-site terminal at night.

[0011] The risk control module is configured to perform risk control on the transaction according to the transaction threshold corresponding to the transaction.

[0012] The embodiment of the present application further provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the risk control method for customer transaction when executing the computer program.

[0013] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the risk control method for customer transaction.

[0014] The embodiment of the present application further provides a computer program product, which comprises a computer program, wherein the computer program is executed by a processor to implement the risk control method for customer transaction.

[0015] In the embodiment of the present application, the first function relationship between the transaction threshold and the security coefficient of the off-line terminal and the second function relationship between the transaction threshold and the security coefficient of the off-line terminal are determined according to the transaction data of the off-line terminal in the daytime and the nighttime; when the customer performs a transaction on the off-line terminal at night, the transaction threshold corresponding to the transaction is determined according to the first function relationship and the second function relationship; and the risk of the transaction is controlled according to the transaction threshold corresponding to the transaction. In the above process, the transaction threshold corresponding to the transaction is determined through the first function relationship between the transaction threshold and the security coefficient of the off-line terminal and the second function relationship between the transaction threshold and the security coefficient of the off-line terminal, so as to control the risk of the transaction. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor. In the drawings:

[0017] Figure 1 The flow chart of the risk control method for customer transaction in the embodiment of the present application;

[0018] Figure 2 The flow chart of obtaining transaction data in the embodiment of the present application;

[0019] Figure 3 The flow chart of determining the similar off-line terminal of the off-line terminal in the embodiment of the present application;

[0020] Figure 4 The flow chart of determining the function relationship in the embodiment of the present application;

[0021] Figure 5A flow chart for determining a transaction threshold corresponding to the current transaction in the embodiment of the present application;

[0022] Figure 6 Another flow chart for risk control of transactions of off-line terminals in the embodiment of the present application;

[0023] Figure 7 Still another flow chart for risk control of transactions of off-line terminals in the embodiment of the present application;

[0024] Figure 8 Another flow chart for risk control of transactions of off-line terminals in the embodiment of the present application;

[0025] Figure 9 A schematic diagram of the risk control device for customer transactions in the embodiment of the present application Figure 1 ;

[0026] Figure 10 A schematic diagram of the risk control device for customer transactions in the embodiment of the present application Figure 2 ;

[0027] Figure 11 A schematic diagram of the risk control device for customer transactions in the embodiment of the present application Figure 3 . DETAILED DESCRIPTION

[0028] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the embodiments of the present application are further described in detail below with reference to the drawings. Herein, the schematic embodiments of the present application and the descriptions thereof are used to explain the present application, but not as a limitation of the present application.

[0029] In the description of the present specification, "comprise", "include", "have", "contain" and the like are all open terms, i.e. meaning containing but not limited to. The description referring to the terms "one embodiment", "one specific embodiment", "some embodiments", "for example" and the like means that the specific features, structures or characteristics described in connection with the embodiment or example are contained in at least one embodiment or example of the present application. In the present specification, the schematic description of the above terms does not necessarily mean the same embodiment or example. Moreover, the specific features, structures or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. The order of steps involved in the embodiments is used to illustrate the embodiments of the present application, and the order of steps is not limited, and can be adjusted as needed.

[0030] Figure 1 A flow chart for the risk control method of customer transactions in the embodiment of the present application, as shown in Figure 1 , includes:

[0031] Step 101, according to the transaction data of the off-line terminal in the daytime and the transaction data of the off-line terminal in the nighttime, a first function relationship between the transaction threshold and the security coefficient of the off-line terminal is determined, and a second function relationship between the transaction threshold and the security coefficient is determined;

[0032] Step 102, when a customer performs a transaction on the off-line terminal in the nighttime, according to the first function relationship and the second function relationship, a transaction threshold corresponding to the transaction is determined;

[0033] Step 103, according to the transaction threshold corresponding to the transaction, risk control is performed on the transaction.

[0034] Figure 2 For the flowchart of obtaining transaction data in the embodiment of the application, in an embodiment, the method further comprises:

[0035] Step 201, when the data amount of the transaction data of the off-line terminal in the daytime is less than a set transaction amount threshold, the transaction data of similar off-line terminals in the daytime of the off-line terminal is added to the transaction data of the off-line terminal in the daytime;

[0036] Step 202, when the data amount of the transaction data of the off-line terminal in the nighttime is less than a set transaction amount threshold, the transaction data of similar off-line terminals in the nighttime of the off-line terminal is added to the transaction data of the off-line terminal in the nighttime.

[0037] Figure 3 For the flowchart of determining the similar off-line terminal of the off-line terminal in the embodiment of the application, in an embodiment, the method further comprises:

[0038] The similar off-line terminal of the off-line terminal is determined according to the following method:

[0039] Step 301, a business space and a customer space are constructed, wherein the dimensions of the business space and the business categories of the off-line terminal one-to-one correspond, and the dimensions of the customer space and the customer categories one-to-one correspond;

[0040] Step 302, for each off-line terminal, according to the business processing data and the customer data of the off-line terminal, coordinate values of the off-line terminal in the business space and the customer space are determined; wherein the coordinate value of each dimension of the off-line terminal in the business space is equal to the number of the business category corresponding to the dimension in the business processing data of the off-line terminal, and the coordinate value of each dimension of the off-line terminal in the customer space is equal to the number of the customer category corresponding to the dimension in the customer data of the off-line terminal;

[0041] Step 303, for any two off-line terminals, the distance of the coordinate values of the two off-line terminals in the business space is taken as the business distance of the two off-line terminals, and the distance of the coordinate values of the two off-line terminals in the customer space is taken as the customer distance of the two off-line terminals.

[0042] Step 304, for each off-line terminal, determining the partial order of the off-line terminal, wherein for any two off-line terminals other than the off-line terminal, if the first off-line terminal is closer to the off-line terminal than the second off-line terminal in terms of business distance and the first off-line terminal is closer to the off-line terminal than the second off-line terminal in terms of customer distance, then the partial order determines that the first off-line terminal is closer to the off-line terminal than the second off-line terminal;

[0043] Step 305, for each off-line terminal, determining the similar off-line terminal of the off-line terminal according to the partial order of the off-line terminal.

[0044] In an embodiment, for each off-line terminal, determining the similar off-line terminal of the off-line terminal according to the partial order of the off-line terminal comprises:

[0045] initializing the pending off-line terminal set and the comparison off-line terminal set as all off-line terminals;

[0046] performing the following three steps in a loop until the pending off-line terminal set is empty:

[0047] selecting the off-line terminal A with the minimum business distance from the pending off-line terminal set, and comparing the off-line terminal A with each off-line terminal B in the comparison off-line terminal set other than the off-line terminal A according to the partial order of the off-line terminal;

[0048] if the off-line terminal B is closer to the off-line terminal A, then deleting the off-line terminal A from the pending off-line terminal set; if the off-line terminal A is closer to the off-line terminal B, then deleting the off-line terminal B from the pending off-line terminal set and taking the off-line terminal B as the secondary off-line terminal of the off-line terminal A; if the off-line terminal B is not closer to the off-line terminal A and the off-line terminal A is not closer to the off-line terminal B, then keeping the pending off-line terminal set unchanged;

[0049] if confirming that each off-line terminal in the comparison off-line terminal set other than the off-line terminal A is not closer to the off-line terminal A, then taking the off-line terminal A as the similar off-line terminal of the off-line terminal, and deleting all secondary off-line terminals of the off-line terminal A from the comparison off-line terminal set.

[0050] Figure 4 For the flowchart of determining the functional relationship in the embodiment of the present application, in an embodiment, determining the first functional relationship between the transaction threshold and the security coefficient of the off-line terminal and the second functional relationship between the transaction threshold and the security coefficient of the off-line terminal according to the transaction data of the off-line terminal in the daytime and the nighttime comprises:

[0051] Step 401, setting a plurality of discrete monetary values;

[0052] Step 402, for each discrete amount value, determining the proportion of transactions that do not involve risks in the transaction data of the off-line terminal in the daytime when the transaction threshold is set as the discrete amount value, taking the proportion as the first security coefficient corresponding to the discrete amount value; determining the proportion of transactions that do not involve risks in the transaction data of the off-line terminal in the nighttime when the transaction threshold is set as the discrete amount value, taking the proportion as the second security coefficient corresponding to the discrete amount value;

[0053] Step 403, constructing a first amount security function and a second amount security function, wherein the independent variable of the first amount security function and the second amount security function is the set of discrete amount values, the function value of the first amount security function corresponding to each discrete amount value is equal to the first security coefficient corresponding to the discrete amount value, and the function value of the second amount security function corresponding to each discrete amount value is equal to the second security coefficient corresponding to the discrete amount value;

[0054] Step 404, continuously processing the first amount security function and the second amount security function, taking the continuous function corresponding to the first amount security function as the first function relationship between the transaction threshold and the security coefficient of the off-line terminal, and taking the continuous function corresponding to the second amount security function as the second function relationship between the transaction threshold and the security coefficient of the off-line terminal.

[0055] Figure 5 For the flowchart of determining the transaction threshold corresponding to the current transaction in the embodiment of the present application, in an embodiment, when the customer performs a transaction on the off-line terminal in the nighttime, the transaction threshold corresponding to the current transaction is determined according to the first function relationship and the second function relationship, including:

[0056] Step 501, obtaining the transaction threshold pre-stored by the customer in the bank server;

[0057] Step 502, determining the potential security coefficient corresponding to the customer according to the first function relationship and the transaction threshold pre-stored by the customer in the bank server;

[0058] Step 503, determining the potential transaction threshold corresponding to the customer according to the second function relationship and the potential security coefficient corresponding to the customer;

[0059] Step 504, determining the transaction threshold corresponding to the current transaction according to the potential transaction threshold corresponding to the customer.

[0060] Figure 6 For another flowchart of the method of controlling the risk of the transaction of the off-line terminal in the embodiment of the present application, in an embodiment, the method further includes:

[0061] Step 601, for each similar off-line terminal of the off-line terminal, determining a security indicator corresponding to each data dimension of the similar off-line terminal according to the business data of the similar off-line terminal;

[0062] Step 602, determining a partial order of the similar off-line terminals of the off-line terminal, wherein the partial order is used to determine whether a first similar off-line terminal is less than a second similar off-line terminal among any two similar off-line terminals of the off-line terminal; if the security indicator corresponding to each data dimension of the first similar off-line terminal is less than or equal to the security indicator corresponding to each data dimension of the second similar off-line terminal, the partial order determines that the first similar off-line terminal is less than the second similar off-line terminal;

[0063] Step 603, performing risk control on the transaction of the off-line terminal according to the partial order of the similar off-line terminals of the off-line terminal.

[0064] In an embodiment, for each similar off-line terminal of the off-line terminal, determining a security indicator corresponding to each data dimension of the similar off-line terminal according to the business data of the similar off-line terminal comprises:

[0065] selecting the business data corresponding to each data dimension from the business data of the similar off-line terminal;

[0066] dividing the business data corresponding to each data dimension into a plurality of business data subsets corresponding to the data dimension according to time sequence, wherein each business data subset contains a number of businesses greater than a set business quantity threshold;

[0067] taking the proportion of businesses not involving risks in each business data subset corresponding to each data dimension as a security proportion sample of the similar off-line terminal corresponding to the data dimension;

[0068] determining the security indicator corresponding to each data dimension of the similar off-line terminal as the mean value of the security proportion sample of the similar off-line terminal corresponding to the data dimension.

[0069] Figure 7 For another flowchart of the embodiment of the present application for performing risk control on the transaction of the off-line terminal, in an embodiment, performing risk control on the transaction of the off-line terminal according to the partial order of the similar off-line terminals of the off-line terminal comprises:

[0070] Step 701, taking the greatest element of the partial order of the similar off-line terminals of the off-line terminal as a first similar off-line terminal;

[0071] Step 702, training a prediction model according to the business data of the first similar off-line terminal with risk as a prediction identifier to obtain a risk prediction model of the off-line terminal;

[0072] Step 703, according to the risk prediction model of the off-line terminal, the transaction of the off-line terminal is risk predicted.

[0073] Figure 8 For another flowchart of the risk control of the transaction of the off-line terminal in the embodiment of the application, in an embodiment, according to the partial order of the similar off-line terminal of the off-line terminal, the transaction of the off-line terminal is risk controlled, comprising:

[0074] Step 801, the minimum element of the partial order of the similar off-line terminal of the off-line terminal is taken as the second similar off-line terminal;

[0075] Step 802, according to the security index of each data dimension corresponding to each second similar off-line terminal, the security norm of the second similar off-line terminal is determined;

[0076] Step 803, according to the security norm of each second similar off-line terminal, the transaction of the off-line terminal is risk controlled.

[0077] In an embodiment, the method further comprises:

[0078] The index error upper bound of each similar off-line terminal corresponding to each data dimension is determined as the ratio of the square of the variance of the security proportion sample corresponding to the data dimension of the similar off-line terminal to the number of the security proportion sample corresponding to the data dimension of the similar off-line terminal;

[0079] For each similar off-line terminal, the maximum value of the index error upper bound corresponding to each data dimension of the similar off-line terminal is taken as the index error upper bound corresponding to the similar off-line terminal;

[0080] The set of similar off-line terminals corresponding to the index error upper bound less than the error threshold value is taken as the set of candidate similar off-line terminals.

[0081] In an embodiment, the maximum element of the partial order of the similar off-line terminal of the off-line terminal is taken as the first similar off-line terminal, comprising:

[0082] The maximum element of the partial order of the similar off-line terminal of the off-line terminal corresponding to the set of candidate similar off-line terminals is taken as the first similar off-line terminal.

[0083] In an embodiment, the minimum element of the partial order of the similar off-line terminal of the off-line terminal is taken as the second similar off-line terminal, comprising:

[0084] The minimum element of the partial order of the similar off-line terminal of the off-line terminal corresponding to the set of candidate similar off-line terminals is taken as the second similar off-line terminal.

[0085] In an embodiment, according to the security norm of each second similar off-line terminal, the transaction of the off-line terminal is risk controlled, comprising:

[0086] sequencing the second similar off-line terminals;

[0087] determining the priority end point corresponding to each second similar off-line terminal according to the following formula:

[0088]

[0089] l i is the priority end point corresponding to the i-th second similar off-line terminal, s k and s j are the security norms of the k-th and j-th second similar off-line terminals respectively, and f>0 is a real-valued decreasing function;

[0090] selecting a random number generator satisfying uniform distribution, wherein the value range of the random number generator is [0, 1];

[0091] for each transaction of the off-line terminal, generating a random number according to the generator, and taking the random number as the random number corresponding to the transaction;

[0092] selecting the maximum priority end point smaller than the random number corresponding to the transaction from the priority end points corresponding to the second similar off-line terminals;

[0093] controlling the transaction of the off-line terminal according to the real-time risk control method of the second similar off-line terminal whose corresponding priority end point is equal to the maximum priority end point.

[0094] In the method proposed in the embodiments of the present application, the first function relationship between the transaction threshold and the security coefficient of the off-line terminal and the second function relationship between the transaction threshold and the security coefficient are determined according to the transaction data of the off-line terminal in the daytime and the nighttime; when a customer performs a transaction on the off-line terminal at night, the transaction threshold corresponding to the transaction is determined according to the first function relationship and the second function relationship; and the transaction is controlled according to the transaction threshold corresponding to the transaction. In the above process, the transaction threshold corresponding to the transaction is determined through the first function relationship between the transaction threshold and the security coefficient of the off-line terminal and the second function relationship between the transaction threshold and the security coefficient, so as to control the transaction.

[0095] The embodiments of the present application also propose a risk control device for customer transaction, which has a similar principle to the risk control method for customer transaction, and thus will not be described herein.

[0096] Figure 9 Fig. 1 is a schematic diagram of the risk control device for customer transaction in the embodiments of the present application Figure 1 , which comprises:

[0097] The function relationship determining module 901 is configured to determine a first function relationship between the transaction threshold and the security coefficient of the off-line terminal and a second function relationship between the transaction threshold and the security coefficient of the off-line terminal according to the transaction data of the off-line terminal in the daytime and the transaction data of the off-line terminal at night.

[0098] The transaction threshold determining module 902 is configured to determine the transaction threshold corresponding to the current transaction according to the first function relationship and the second function relationship when the customer performs the transaction at the off-line terminal at night.

[0099] The risk control module 903 is configured to perform risk control on the current transaction according to the transaction threshold corresponding to the current transaction.

[0100] Figure 10 A schematic diagram of the risk control device for the customer transaction in the embodiment of the present application Figure 2 In an embodiment, the device further comprises a transaction data obtaining module 1001 configured to:

[0101] When the data amount of the transaction data of the off-line terminal in the daytime is less than the set transaction amount threshold, add the transaction data of the similar off-line terminal in the daytime of the off-line terminal to the transaction data of the off-line terminal in the daytime.

[0102] When the data amount of the transaction data of the off-line terminal at night is less than the set transaction amount threshold, add the transaction data of the similar off-line terminal at night of the off-line terminal to the transaction data of the off-line terminal at night.

[0103] Figure 11 A schematic diagram of the risk control device for the customer transaction in the embodiment of the present application Figure 3 In an embodiment, the device further comprises a similar off-line terminal determining module 1101 configured to:

[0104] The similar off-line terminal of the off-line terminal is determined by the following method:

[0105] A business space and a customer space are constructed, wherein the dimensions of the business space and the business categories of the off-line terminal are in one-to-one correspondence, and the dimensions of the customer space and the customer categories are in one-to-one correspondence;

[0106] For each off-line terminal, the coordinate values of the off-line terminal in the business space and the customer space are determined according to the business processing data and the customer data of the off-line terminal, wherein the coordinate value of each dimension of the off-line terminal in the business space is equal to the number of the business of the corresponding business category in the business processing data of the off-line terminal, and the coordinate value of each dimension of the off-line terminal in the customer space is equal to the number of the customer of the corresponding customer category in the customer data of the off-line terminal.

[0107] For any two off-line terminals, a distance between the two off-line terminals in the coordinate values of the service space is taken as a service distance of the two off-line terminals, and a distance between the two off-line terminals in the coordinate values of the customer space is taken as a customer distance of the two off-line terminals;

[0108] For each off-line terminal, a partial order of the off-line terminal is determined, wherein, for any two off-line terminals other than the off-line terminal, if a first off-line terminal of the two off-line terminals has a service distance to the off-line terminal less than or equal to a service distance of a second off-line terminal of the two off-line terminals to the off-line terminal, and the first off-line terminal has a customer distance to the off-line terminal less than or equal to a customer distance of the second off-line terminal to the off-line terminal, the partial order determines that the first off-line terminal is closer to the off-line terminal than the second off-line terminal;

[0109] For each off-line terminal, according to the partial order of the off-line terminal, a similar off-line terminal of the off-line terminal is determined.

[0110] In an embodiment, the function relationship determining module is specifically configured to:

[0111] a plurality of discrete amount values are set;

[0112] For each discrete amount value, a proportion of transactions involving no risk in the transaction data of the off-line terminal in the daytime when the transaction threshold is set as the discrete amount value is determined, and the proportion is taken as a first safety coefficient corresponding to the discrete amount value; a proportion of transactions involving no risk in the transaction data of the off-line terminal in the nighttime when the transaction threshold is set as the discrete amount value is determined, and the proportion is taken as a second safety coefficient corresponding to the discrete amount value;

[0113] a first amount safety function and a second amount safety function are constructed, wherein, the independent variables of the first amount safety function and the second amount safety function are the set plurality of discrete amount values, the function value of the first amount safety function corresponding to each discrete amount value is equal to the first safety coefficient corresponding to the discrete amount value, and the function value of the second amount safety function corresponding to each discrete amount value is equal to the second safety coefficient corresponding to the discrete amount value;

[0114] the first amount safety function and the second amount safety function are continuously processed, a continuous function corresponding to the first amount safety function is taken as a first function relationship between the transaction threshold and the safety coefficient of the off-line terminal, and a continuous function corresponding to the second amount safety function is taken as a second function relationship between the transaction threshold and the safety coefficient of the off-line terminal.

[0115] In an embodiment, the transaction threshold determining module is specifically configured to:

[0116] a transaction threshold pre-stored by a customer in a bank server is acquired;

[0117] determine a potential security coefficient corresponding to the client according to a first function relationship between a transaction threshold pre-stored by the client on a server of the bank and the first function relationship;

[0118] determine a potential transaction threshold corresponding to the client according to a second function relationship between the potential security coefficient corresponding to the client and the second function relationship;

[0119] determine a transaction threshold corresponding to the current transaction according to the potential transaction threshold corresponding to the client.

[0120] In an embodiment, the risk control module is further configured to:

[0121] for each similar off-line terminal of the off-line terminal, determine a security indicator corresponding to each data dimension of the similar off-line terminal according to service data of the similar off-line terminal;

[0122] determine a partial order of the similar off-line terminals of the off-line terminal, wherein the partial order is used to determine whether a first similar off-line terminal is less than a second similar off-line terminal among any two similar off-line terminals of the off-line terminal; if, for each data dimension, the security indicator corresponding to the data dimension of the first similar off-line terminal is less than or equal to the security indicator corresponding to the data dimension of the second similar off-line terminal, the partial order determines that the first similar off-line terminal is less than the second similar off-line terminal;

[0123] perform risk control on transactions of the off-line terminal according to the partial order of the similar off-line terminals of the off-line terminal.

[0124] In an embodiment, the risk control module is specifically configured to:

[0125] take a maximal element of the partial order of the similar off-line terminals of the off-line terminal as a first similar off-line terminal;

[0126] train a prediction model according to service data of the first similar off-line terminal to obtain a risk prediction model of the off-line terminal;

[0127] perform risk prediction on transactions of the off-line terminal according to the risk prediction model of the off-line terminal.

[0128] In an embodiment, the risk control module is further configured to:

[0129] take a minimal element of the partial order of the similar off-line terminals of the off-line terminal as a second similar off-line terminal;

[0130] determine a security norm of the second similar off-line terminal according to the security indicator corresponding to each data dimension of each second similar off-line terminal;

[0131] perform risk control on transactions of the off-line terminal according to the security norm of each second similar off-line terminal.

[0132] In summary, in the device provided by the embodiment of the present application, the first function relationship between the transaction threshold and the security coefficient of the off-line terminal and the second function relationship between the transaction threshold and the security coefficient of the off-line terminal are determined according to the transaction data of the off-line terminal in the daytime and at night; when the customer performs a transaction on the off-line terminal at night, the transaction threshold corresponding to the transaction is determined according to the first function relationship and the second function relationship; and the risk of the transaction is controlled according to the transaction threshold corresponding to the transaction. In the above process, the transaction threshold corresponding to the transaction is determined through the first function relationship between the transaction threshold and the security coefficient of the off-line terminal and the second function relationship between the transaction threshold and the security coefficient of the off-line terminal, so as to control the risk of the transaction.

[0133] The embodiment of the present application further provides a computer device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor realizes the risk control method of the customer transaction when executing the computer program.

[0134] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program realizes the risk control method of the customer transaction when executed by a processor.

[0135] The embodiment of the present application further provides a computer program product, which comprises a computer program, and the computer program realizes the risk control method of the customer transaction when executed by a processor.

[0136] Those skilled in the art should understand that the embodiment of the present application can be provided as a method, a system or a computer program service system. Therefore, the present application can adopt a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can adopt a computer program service system implemented on one or more computer usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer usable program code.

[0137] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system) and computer program service system according to the embodiment of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be realized by computer program instructions. These computer program instructions can be provided to the 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 produce a machine that realizes the function of the flowcharts and / or block diagrams. Figure 1 one flow or multiple flows and / or blocks Figure 1apparatuses that carry out functions specified in one or more blocks or multiple blocks.

[0138] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flow Figure 1 one or more flows and / or blocks Figure 1 functions specified in one or more blocks.

[0139] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that are executed on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 one or more flows and / or blocks Figure 1 steps of functions specified in one or more blocks.

[0140] The above specific embodiments are described to further explain the purpose, technical solutions and beneficial effects of the present application. It should be understood that the above description is only a specific embodiment of the present application and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method of risk control for a client transaction, characterized by, The method comprises: determining a first function relationship between a transaction threshold and a security coefficient of a self-service terminal and a second function relationship between the transaction threshold and the security coefficient according to transaction data of the self-service terminal in daytime and nighttime; setting a plurality of discrete amount values; for each discrete amount value, determining a proportion of transactions involving no risk in the transaction data of the self-service terminal in daytime when the transaction threshold is set as the discrete amount value, taking the proportion as a first security coefficient corresponding to the discrete amount value; determining a proportion of transactions involving no risk in the transaction data of the self-service terminal in nighttime when the transaction threshold is set as the discrete amount value, taking the proportion as a second security coefficient corresponding to the discrete amount value; determining the first function relationship according to the first security coefficient and determining the second function relationship according to the second security coefficient; when a customer performs a transaction on the self-service terminal in nighttime, determining a transaction threshold corresponding to the transaction according to the first function relationship and the second function relationship; when the customer performs the transaction on the self-service terminal in nighttime, determining the transaction threshold corresponding to the transaction according to the first function relationship and the second function relationship, comprising: obtaining a transaction threshold pre-stored by the customer on a bank server; determining a potential security coefficient corresponding to the customer according to the transaction threshold pre-stored by the customer on the bank server and the first function relationship; determining a potential transaction threshold corresponding to the customer according to the potential security coefficient corresponding to the customer and the second function relationship; determining the transaction threshold corresponding to the transaction according to the potential transaction threshold corresponding to the customer; controlling risk of the transaction according to the transaction threshold corresponding to the transaction.

2. The method of claim 1, wherein, The method further comprises: when a data amount of the transaction data of the self-service terminal in daytime is less than a set transaction amount threshold, adding transaction data of similar self-service terminals in daytime to the transaction data of the self-service terminal in daytime; when a data amount of the transaction data of the self-service terminal in nighttime is less than a set transaction amount threshold, adding transaction data of similar self-service terminals in nighttime to the transaction data of the self-service terminal in nighttime.

3. The method of claim 2, wherein, The method further comprises: determining similar self-service terminals of a self-service terminal according to the following method: constructing a business space and a customer space, wherein dimensions of the business space and business categories of the self-service terminal correspond to each other one by one, and dimensions of the customer space and customer categories correspond to each other one by one; for each self-service terminal, determining coordinate values of the self-service terminal in the business space and the customer space according to business processing data and customer data of the self-service terminal; wherein the coordinate value of each dimension of the self-service terminal in the business space is equal to a number of a business category corresponding to the dimension among businesses included in the business processing data of the self-service terminal, and the coordinate value of each dimension of the self-service terminal in the customer space is equal to a number of a customer category corresponding to the dimension among customers included in the customer data of the self-service terminal; for any two self-service terminals, taking a distance of the coordinate values of the two self-service terminals in the business space as a business distance of the two self-service terminals, and taking a distance of the coordinate values of the two self-service terminals in the customer space as a customer distance of the two self-service terminals; For each off-line terminal, determine a partial order of the off-line terminal, wherein for any two off-line terminals other than the off-line terminal, if a first off-line terminal of the two off-line terminals is closer to the off-line terminal in business distance and customer distance than a second off-line terminal of the two off-line terminals, the partial order determines that the first off-line terminal is closer to the off-line terminal than the second off-line terminal; For each off-line terminal, determine a similar off-line terminal of the off-line terminal according to the partial order of the off-line terminal.

4. The method of claim 1, wherein, According to the transaction data of the off-line terminal in the daytime and the nighttime, determine a first functional relationship between the transaction threshold and the security coefficient of the off-line terminal and a second functional relationship between the transaction threshold and the security coefficient, including: Construct a first amount security function and a second amount security function, wherein the independent variables of the first amount security function and the second amount security function are a plurality of discrete amount values set, the function value of the first amount security function corresponding to each discrete amount value is equal to the first security coefficient corresponding to the discrete amount value, and the function value of the second amount security function corresponding to each discrete amount value is equal to the second security coefficient corresponding to the discrete amount value; Continuously process the first amount security function and the second amount security function, take the continuous function corresponding to the first amount security function as the first functional relationship between the transaction threshold and the security coefficient of the off-line terminal, and take the continuous function corresponding to the second amount security function as the second functional relationship between the transaction threshold and the security coefficient of the off-line terminal.

5. The method of claim 3, wherein, Further comprising: For each similar off-line terminal of the off-line terminal, determine a security indicator corresponding to each data dimension of the similar off-line terminal according to the business data of the similar off-line terminal; Determine a partial order of the similar off-line terminals of the off-line terminal, wherein the partial order is used to determine whether a first similar off-line terminal of any two similar off-line terminals of the off-line terminal is less than a second similar off-line terminal; if the security indicator corresponding to each data dimension of the first similar off-line terminal is less than or equal to the security indicator corresponding to each data dimension of the second similar off-line terminal, the partial order determines that the first similar off-line terminal is less than the second similar off-line terminal; According to the partial order of the similar off-line terminals of the off-line terminal, perform risk control on the transaction of the off-line terminal.

6. The method of claim 5, wherein, According to the partial order of the similar off-line terminals of the off-line terminal, perform risk control on the transaction of the off-line terminal, including: Take the maximum element of the partial order of the similar off-line terminals of the off-line terminal as a first similar off-line terminal; According to the business data of the first similar off-line terminal, train a prediction model with risk as a prediction identifier to obtain a risk prediction model of the off-line terminal; According to the risk prediction model of the off-line terminal, perform risk prediction on the transaction of the off-line terminal.

7. The method of claim 5, wherein, According to the partial order of the similar off-line terminals of the off-line terminal, perform risk control on the transaction of the off-line terminal, including: Take the minimum element of the partial order of the similar off-line terminals of the off-line terminal as a second similar off-line terminal; According to the security indicator corresponding to each data dimension of each second similar off-line terminal, determine a security norm of the second similar off-line terminal; According to the security norms of each second similar off-terminal, the transaction of the off-terminal is controlled.

8. A risk control apparatus for a client transaction, characterized by, Comprise: The function relationship determining module is used for determining the first function relationship between the transaction threshold and the security coefficient of the off-terminal and the second function relationship between the transaction threshold and the security coefficient according to the transaction data of the off-terminal in the daytime and the nighttime; setting multiple discrete amount values; for each discrete amount value, determining the proportion of the transaction not involving risk in the transaction data of the off-terminal in the daytime when the transaction threshold is set as the discrete amount value, taking the proportion as the first security coefficient corresponding to the discrete amount value; determining the proportion of the transaction not involving risk in the transaction data of the off-terminal in the nighttime when the transaction threshold is set as the discrete amount value, taking the proportion as the second security coefficient corresponding to the discrete amount value; The first function relationship is determined according to the first security coefficient, and the second function relationship is determined according to the second security coefficient; The transaction threshold determining module is used for determining the transaction threshold corresponding to the transaction when the customer performs the transaction on the off-terminal in the nighttime according to the first function relationship and the second function relationship; the transaction threshold corresponding to the transaction when the customer performs the transaction on the off-terminal in the nighttime is determined according to the first function relationship and the second function relationship, comprising: obtaining the transaction threshold pre-stored in the bank server by the customer; determining the potential security coefficient corresponding to the customer according to the transaction threshold pre-stored in the bank server by the customer and the first function relationship; determining the potential transaction threshold corresponding to the customer according to the potential security coefficient corresponding to the customer and the second function relationship; determining the transaction threshold corresponding to the transaction according to the potential transaction threshold corresponding to the customer; The risk control module is used for controlling the risk of the transaction according to the transaction threshold corresponding to the transaction.

9. The apparatus of claim 8, wherein, Further comprising a transaction data obtaining module, which is used for: When the data amount of the transaction data of the off-terminal in the daytime is less than the set transaction amount threshold, adding the transaction data of the similar off-terminal of the off-terminal in the daytime to the transaction data of the off-terminal in the daytime; When the data amount of the transaction data of the off-terminal in the nighttime is less than the set transaction amount threshold, adding the transaction data of the similar off-terminal of the off-terminal in the nighttime to the transaction data of the off-terminal in the nighttime.

10. The apparatus of claim 9, wherein, Further comprising a similar off-terminal determining module, which is used for: Determining the similar off-terminal of the off-terminal according to the following method: Constructing a business space and a customer space, wherein the dimensions of the business space and the business categories of the off-terminal one-to-one correspond, and the dimensions of the customer space and the customer categories one-to-one correspond; For each off-terminal, determining the coordinate values of the off-terminal in the business space and the customer space according to the business processing data and the customer data of the off-terminal; wherein the coordinate value of each dimension of the off-terminal in the business space is equal to the number of the business category corresponding to the dimension in the business processing data of the off-terminal, and the coordinate value of each dimension of the off-terminal in the customer space is equal to the number of the customer category corresponding to the dimension in the customer data of the off-terminal. For any two off-line terminals, a distance between the two off-line terminals in coordinate values of the service space is taken as a service distance of the two off-line terminals, and a distance between the two off-line terminals in coordinate values of the customer space is taken as a customer distance of the two off-line terminals; For each off-line terminal, a partial order of the off-line terminal is determined, wherein, for any two off-line terminals other than the off-line terminal, if a service distance between a first off-line terminal of the two off-line terminals and the off-line terminal is less than or equal to a service distance between a second off-line terminal of the two off-line terminals and the off-line terminal, and a customer distance between the first off-line terminal and the off-line terminal is less than or equal to a customer distance between the second off-line terminal and the off-line terminal, the partial order determines that the first off-line terminal is closer to the off-line terminal than the second off-line terminal; For each off-line terminal, a similar off-line terminal of the off-line terminal is determined according to the partial order of the off-line terminal.

11. The apparatus of claim 8, wherein, The function relationship determining module is specifically configured to: construct a first amount security function and a second amount security function, wherein, the independent variables of the first amount security function and the second amount security function are a plurality of discrete amount values set, the function value of the first amount security function corresponding to each discrete amount value is equal to the first security coefficient corresponding to the discrete amount value, and the function value of the second amount security function corresponding to each discrete amount value is equal to the second security coefficient corresponding to the discrete amount value; continuously process the first amount security function and the second amount security function, take a continuous function corresponding to the first amount security function as a first function relationship between the transaction threshold and the security coefficient of the off-line terminal, and take a continuous function corresponding to the second amount security function as a second function relationship between the transaction threshold and the security coefficient of the off-line terminal.

12. The apparatus of claim 10, wherein, The risk control module is further configured to: for each similar off-line terminal of the off-line terminal, determine a security indicator of each data dimension corresponding to the similar off-line terminal according to the business data of the similar off-line terminal; determine a partial order of the similar off-line terminals of the off-line terminal, wherein, the partial order is used to determine whether a first similar off-line terminal is less than a second similar off-line terminal among any two similar off-line terminals of the off-line terminal; if, for each data dimension, the security indicator of the data dimension corresponding to the first similar off-line terminal is less than or equal to the security indicator of the data dimension corresponding to the second similar off-line terminal, the partial order determines that the first similar off-line terminal is less than the second similar off-line terminal; perform risk control on the transaction of the off-line terminal according to the partial order of the similar off-line terminals of the off-line terminal.

13. The apparatus of claim 12, wherein, The risk control module is specifically configured to: take a maximum element of the partial order of the similar off-line terminals of the off-line terminal as a first similar off-line terminal; train a prediction model according to the business data of the first similar off-line terminal, taking risk as a prediction identifier, to obtain a risk prediction model of the off-line terminal; perform risk prediction on the transaction of the off-line terminal according to the risk prediction model of the off-line terminal.

14. The apparatus of claim 12, wherein, The risk control module is further configured to: take a minimum element of the partial order of the similar off-line terminals of the off-line terminal as a second similar off-line terminal; determine a security norm of the second similar off-line terminal according to the security indicator of each data dimension corresponding to the second similar off-line terminal; According to the security norm of each second similar off-line terminal, the transaction of the off-line terminal is controlled.

15. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the method of any one of claims 1 to 7 when executing the computer program.

16. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the method of any one of claims 1 to 7.

17. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program is executed by the processor to implement the method of any one of claims 1 to 7.

Images