Customer quota automatic adjustment method and device

Abstract

The invention provides a customer quota automatic adjustment method and device, and relates to the technical field of big data and internet finance, and the method comprises the steps: obtaining the first transfer transaction volume and customer information of a customer to be subjected to quota adjustment in recent N years; establishing a customer individual transfer transaction prediction model based on the first transfer transaction volume and the customer information; obtaining second transfer transaction volumes and corresponding quota values of all customers in recent N years in a specified region range; obtaining a general correlation coefficient of the transfer transaction volume and the limit value based on the second transfer transaction volume and the corresponding limit value; obtaining a limit prediction model based on the general correlation coefficient and the personal transfer transaction prediction model; and outputting the transaction quota of the customer to be subjected to quota adjustment based on the quota prediction model. According to the invention, manual operation of a large number of business personnel is liberated, diversified transfer quota demands of customers are met, unnecessary quota adjustment operations of the customers are reduced, and the property safety of the customers is protected.

Description

Technical Field

[0001] The present invention relates to the field of big data and Internet financial technology, and in particular to a method and device for automatically adjusting customer limits. Background Art

[0002] At present, the limit setting of mobile banking is based on two conditions, region and star rating, and the business personnel manually judge and configure the unified limit parameters. This operation mode not only ignores the diversity of customers' own transaction behaviors, but also fails to take into account the needs of the bank's own security and customer funds security, and also lacks timely response to regulatory policies. In actual transactions, customers with large transaction volumes need to contact the bank frequently to review and increase their limits. For customers with small transaction volumes, banks cannot effectively control sudden large transfers and suspicious frequent transactions. Summary of the invention

[0003] In view of this, the present invention provides a method and device for automatically adjusting customer quota to solve at least one of the above-mentioned problems.

[0004] In order to achieve the above object, the present invention adopts the following scheme:

[0005] According to a first aspect of the present invention, there is provided a method for automatically adjusting customer limits, the method comprising: obtaining a first transfer transaction volume and customer information of a customer whose limit is to be adjusted in the past N years; establishing a customer personal transfer transaction prediction model based on the first transfer transaction volume and customer information; obtaining a second transfer transaction volume and corresponding limit value of all customers in a specified area in the past N years; obtaining a universal correlation coefficient between transfer transaction volume and limit value based on the second transfer transaction volume and corresponding limit value; obtaining a limit prediction model based on the universal correlation coefficient and the personal transfer transaction prediction model; and outputting the transaction limit of the customer whose limit is to be adjusted based on the limit prediction model.

[0006] As an embodiment of the present invention, the above method also includes: obtaining and analyzing the customer's subsequent active limit adjustment behavior to obtain the customer's transfer limit preference value, and inputting the transfer limit preference value into the limit prediction model to further improve the limit prediction model.

[0007] As an embodiment of the present invention, the above-mentioned customer information includes customer nature information, customer basic information and transaction behavior information. The customer nature information includes registration method, credit rating, star rating, and whether included in the restricted list; the customer basic information includes salary level, job type, completeness of contact information, and family relationships; the transaction behavior information includes deposit amount, loan amount, financial management amount, and daily consumption amount.

[0008] As an embodiment of the present invention, the establishment of the customer personal transfer transaction prediction model based on the first transfer transaction volume and customer information includes: using a multivariate linear regression method based on the customer information to obtain the following relationship between customer nature information, customer basic information, and transaction behavior information and their variables:

[0009]

[0010] In the above formula, x1 represents the customer's nature information, x2 represents the customer's basic information, and x3 represents the transaction behavior information; a1 represents the registration method, a2 represents the credit rating, a3 represents the star rating, a4 represents whether it is included in the restricted list, and η 0-4 represents the correlation coefficient of each variable in customer nature; b1 represents salary level, b2 represents salary type, b3 represents the completeness of contact information, b4 represents family relationship, κ 0-4 represents the correlation coefficient of each variable in the basic information of the customer; c1 represents the deposit amount, c2 represents the loan amount, c3 represents the financial management amount, c4 represents the daily consumption amount, λ 0-4 Represents the correlation coefficient of each variable in the transaction behavior information;

[0011] Get the first transfer transaction volume t of the customer whose limit is to be adjusted in the past N years (x) The correlation coefficient θ between customer nature information x1, customer basic information x2 and transaction behavior information x3 0-4 , we get the following personal transfer transaction prediction model:

[0012] t (x) =θ1x1+θ2x2+θ3x3+θ0.

[0013] As an embodiment of the present invention, obtaining the universal correlation coefficient between the transfer transaction amount and the limit value based on the second transfer transaction amount and the corresponding limit value includes: obtaining the universal correlation coefficient between the transfer transaction amount and the limit value based on the second transfer transaction amount and the corresponding limit value using the following correlation mathematical model:

[0014]

[0015] In the above formula, ρ is the universal correlation coefficient, t is the second transfer transaction volume of all customers in the past N years, z is the limit value corresponding to each customer, Cov(t,z) is the covariance of the two sets of data t and z, δ t δ z It is the product of the standard deviations of the two data sets t and z.

[0016] As an embodiment of the present invention, the above-mentioned obtaining the limit prediction model based on the universal correlation coefficient and the personal transfer transaction prediction model includes: substituting the universal correlation coefficient into the personal transfer transaction prediction model to obtain the following limit prediction model:

[0017] Z Q =β1X1+β2X2+β3X3+β0;

[0018] In the above formula, Z Q represents the limit of customer Q predicted by the limit prediction model, X1 represents the customer nature of customer Q, X2 represents the basic information of customer Q, X3 represents the transaction behavior of customer Q, β1=ρθ1, β2=ρθ2, β3=ρθ3, β0=ρθ0.

[0019] As an embodiment of the present invention, after obtaining the limit prediction model based on the universal correlation coefficient and the personal transfer transaction prediction model, the method further includes: obtaining policy parameters of the region where the customer whose limit is to be adjusted is located, and further improving the limit prediction model based on the policy parameters to obtain the following improved limit prediction model:

[0020]

[0021] The above formula summarizes, β Q X Q =β1X1+β2X2+β3X3, Represents the policy parameters of the region where customer Q is located.

[0022] According to a second aspect of the present invention, there is provided an automatic adjustment device for customer limits, the device comprising: a to-be-adjusted customer information acquisition unit, for acquiring the first transfer transaction volume and customer information of the to-be-adjusted customer in the past N years; a personal transaction model establishment unit, for establishing a customer personal transfer transaction prediction model based on the first transfer transaction volume and customer information; a regional customer information acquisition unit, for acquiring the second transfer transaction volume and corresponding limit values ​​of all customers within a specified region in the past N years; a universal correlation coefficient acquisition unit, for obtaining a universal correlation coefficient between transfer transaction volume and limit value based on the second transfer transaction volume and the corresponding limit value; a limit prediction model establishment unit, for obtaining a limit prediction model based on the universal correlation coefficient and the personal transfer transaction prediction model; a limit output unit, for outputting the transaction limit of the to-be-adjusted customer based on the limit prediction model.

[0023] As an embodiment of the present invention, the above-mentioned device also includes a model improvement unit, which is used to obtain and analyze the customer's subsequent active limit adjustment behavior, obtain the customer's transfer limit preference value, and input the transfer limit preference value into the limit prediction model to further improve the limit prediction model.

[0024] As an embodiment of the present invention, the above-mentioned customer information includes customer nature information, customer basic information and transaction behavior information. The customer nature information includes registration method, credit rating, star rating, and whether included in the restricted list; the customer basic information includes salary level, job type, completeness of contact information, and family relationships; the transaction behavior information includes deposit amount, loan amount, financial management amount, and daily consumption amount.

[0025] As an embodiment of the present invention, the above-mentioned personal transaction model building unit is specifically used to: obtain the following relationship between customer nature information, customer basic information and transaction behavior information and their variables respectively by using a multivariate linear regression method based on customer information:

[0026]

[0027] In the above formula, x1 represents the customer's nature information, x2 represents the customer's basic information, and x3 represents the transaction behavior information; a1 represents the registration method, a2 represents the credit rating, a3 represents the star rating, a4 represents whether it is included in the restricted list, and η 0-4 represents the correlation coefficient of each variable in customer nature; b1 represents salary level, b2 represents salary type, b3 represents the completeness of contact information, b4 represents family relationship, κ 0-4 represents the correlation coefficient of each variable in the basic information of the customer; c1 represents the deposit amount, c2 represents the loan amount, c3 represents the financial management amount, c4 represents the daily consumption amount, λ 0-4 Represents the correlation coefficient of each variable in the transaction behavior information;

[0028] Get the first transfer transaction volume t of the customer whose limit is to be adjusted in the past N years (x) The correlation coefficient θ between customer nature information x1, customer basic information x2 and transaction behavior information x3 0-4 , we get the following personal transfer transaction prediction model:

[0029] t (x) =θ1x1+θ2x2+θ3x3+θ0.

[0030] As an embodiment of the present invention, the universal correlation coefficient obtaining unit is specifically used to obtain the universal correlation coefficient between the transfer transaction amount and the limit value based on the second transfer transaction amount and the corresponding limit value by using the following correlation mathematical model:

[0031]

[0032] In the above formula, ρ is the universal correlation coefficient, t is the second transfer transaction volume of all customers in the past N years, z is the limit value corresponding to each customer, Cov(t,z) is the covariance of the two sets of data t and z, δt δ z It is the product of the standard deviations of the two data sets t and z.

[0033] As an embodiment of the present invention, the limit prediction model establishment unit is specifically used to: substitute the universal correlation coefficient into the personal transfer transaction prediction model to obtain the following limit prediction model:

[0034] Z Q =β1X1+β2X2+β3X3+β0;

[0035] In the above formula, Z Q represents the limit of customer Q predicted by the limit prediction model, X1 represents the customer nature of customer Q, X2 represents the basic information of customer Q, X3 represents the transaction behavior of customer Q, β1=ρθ1, β2=ρθ2, β3=ρθ3, β0=ρθ0.

[0036] As an embodiment of the present invention, the above-mentioned device further includes a policy parameter adjustment unit: used to obtain the policy parameters of the region where the customer whose quota is to be adjusted is located, and further improve the quota prediction model based on the policy parameters to obtain the following improved quota prediction model:

[0037]

[0038] The above formula summarizes, β Q X Q =β1X1+β2X2+β3X3, Represents the policy parameters of the region where customer Q is located.

[0039] According to a third aspect of the present invention, there is provided an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0040] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0041] It can be seen from the above technical solution that the method and device for automatically adjusting customer limits provided by the present invention, by establishing a personal transfer transaction prediction model for customers whose limits are to be adjusted, obtains the relationship between the transfer transaction volume of the customers whose limits are to be adjusted and the customer information variables, and then performs a correlation analysis on all samples in the specified area to obtain a universal correlation coefficient between the transaction volume and the limit, and obtains a limit prediction model based on the universal correlation coefficient and the personal transfer transaction prediction model, so that the limit value of the individual customer output by the limit prediction model is more in line with the customer's needs, and the whole process does not require manual intervention. At the bank level, this application frees up a large number of business personnel from manual operations, which is conducive to avoiding the occurrence of illegal transactions. At the customer level, this application meets the diverse transfer limit needs of customers, reduces unnecessary limit adjustment operations of customers, and protects the property safety of customers. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0043] Figure 1 It is a flowchart of a method for automatically adjusting customer quota provided in an embodiment of the present application;

[0044] Figure 2 is a flow chart of a method for automatically adjusting customer quota limits provided by another embodiment of the present application;

[0045] Figure 3 It is a structural schematic diagram of a customer limit automatic adjustment device provided in an embodiment of the present application;

[0046] Figure 4 is a structural schematic diagram of a customer limit automatic adjustment device provided by another embodiment of the present application;

[0047] Figure 5 It is a schematic block diagram of the system structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0049] Due to the current limit setting method, in actual transactions, customers with large transaction volumes need to frequently contact the bank to review and increase their limits, while for customers with small transaction volumes, banks cannot effectively control sudden large transfers and suspicious frequent transactions. Therefore, the purpose of this application is to provide a method and device for automatically adjusting customer limits, which uses big data to collect customer behavior, and substitutes it into a model to calculate a limit value that meets customer behavior habits. High-quality customers who have a demand for high-frequency or large-value transactions will obtain more convenient limits without having to frequently go to outlets to increase their limits. For abnormal customers' large-value or high-frequency transactions, their limits will be controlled to protect account security and prevent illegal activities.

[0050] The acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of laws and regulations. The user information in the embodiments of this application is obtained through legal and compliant channels, and the acquisition, storage, use, and processing of user information are authorized and agreed by the customer.

[0051] like Figure 1 The figure is a flow chart of a method for automatically adjusting a customer limit provided by an embodiment of the present application, the method comprising the following steps:

[0052] Step S101: Obtain the first transfer transaction volume and customer information of the customer whose limit is to be adjusted in the past N years.

[0053] Step S102: establishing a customer personal transfer transaction prediction model based on the first transfer transaction volume and customer information.

[0054] Step S103: Obtain the second transfer transaction volume and corresponding limit value of all customers in the specified area in the past N years.

[0055] Step S104: obtaining a universal correlation coefficient between the transfer transaction amount and the limit value based on the second transfer transaction amount and the corresponding limit value.

[0056] Step S105: obtaining a limit prediction model based on the universal correlation coefficient and the personal transfer transaction prediction model.

[0057] Step S106: outputting the transaction limit of the customer whose limit is to be adjusted based on the limit prediction model.

[0058] From the above, it can be seen that the present application first establishes a personal transfer transaction prediction model for the customer whose limit is to be adjusted based on steps S101 and S102, and obtains the relationship between the transfer transaction volume of the customer whose limit is to be adjusted and the customer information variable. Due to the influence of various factors, the limit value of a certain customer in a certain area may not be able to derive its correlation with the transfer transaction volume. Therefore, the present application continues to perform correlation on all samples in the specified area through steps S103 and S104, and obtains a universal correlation coefficient between the transaction volume and the limit, and obtains the limit prediction model based on the universal correlation coefficient and the personal transfer transaction prediction model, so that the limit value of the individual customer output by the limit prediction model is more in line with the customer's needs, and the entire process does not require manual intervention.

[0059] like Figure 2 FIG. 1 is a flow chart of a method for automatically adjusting a customer limit provided by another embodiment of the present application, the method comprising the following steps:

[0060] Step S201: Obtain the first transfer transaction volume and customer information of the customer whose limit is to be adjusted in the past N years.

[0061] Preferably, the customer information in this embodiment includes customer nature information, customer basic information and transaction behavior information, wherein customer nature information includes registration method, credit rating, star rating, whether included in the restricted list; customer basic information includes salary level, job type, contact information completeness, family relationship; and transaction behavior information includes deposit amount, loan amount, financial management amount, daily consumption amount. These information will determine the size of the transfer transaction volume within a set time period (such as one month, one quarter or one year) to a certain extent.

[0062] Step S202: establishing a customer personal transfer transaction prediction model based on the first transfer transaction volume and customer information.

[0063] After obtaining the above-mentioned first transfer transaction volume and customer information, the purpose of this application is to find the relationship between the first transfer transaction volume and various variables in the customer information, that is, to establish a personal transfer transaction prediction model for the customer. The personal transfer transaction prediction model can be established in the following way:

[0064] First, based on customer information, the multivariate linear regression method is used to obtain the following relationship between customer nature information, customer basic information, transaction behavior information and its variables:

[0065]

[0066] In the above formula, x1 represents the customer's nature information, x2 represents the customer's basic information, and x3 represents the transaction behavior information; a1 represents the registration method, a2 represents the credit rating, a3 represents the star rating, a4 represents whether it is included in the restricted list, and η 0-4 represents the correlation coefficient of each variable in customer nature; b1 represents salary level, b2 represents salary type, b3 represents the completeness of contact information, b4 represents family relationship, κ 0-4 represents the correlation coefficient of each variable in the basic information of the customer; c1 represents the deposit amount, c2 represents the loan amount, c3 represents the financial management amount, c4 represents the daily consumption amount, λ 0-4 Represents the correlation coefficient of each variable in the transaction behavior information.

[0067] Then, obtain the first transfer transaction volume t of the customer whose limit is to be adjusted in the past N years (x) The correlation coefficient θ between customer nature information x1, customer basic information x2, transaction behavior information x3 and other influencing variables 0-4 , and then we get the following personal transfer transaction prediction model:

[0068] t (x) =θ1x1+θ2x2+θ3x3+θ0

[0069] In the above formula, θ 1-3 are the correlation coefficients of customer nature information x1, customer basic information x2 and transaction behavior information x3, and θ0 is the coefficient of the variables other than the above customer nature information x1, customer basic information x2 and transaction behavior information x3.

[0070] Step S203: Obtain the second transfer transaction volume and corresponding limit value of all customers in the specified area in the past N years.

[0071] It should be pointed out that two sets of data are obtained here. One set of data is the second transfer transaction volume of all customers in the specified area in the past N years, and the other set of data is the limit value corresponding to all customers.

[0072] Step S204: obtaining a universal correlation coefficient between the transfer transaction amount and the limit value based on the second transfer transaction amount and the corresponding limit value.

[0073] Furthermore, this step may specifically include the following steps: based on the second transfer transaction volume and the corresponding limit value, using the following correlation mathematical model to obtain a universal correlation coefficient between the transfer transaction volume and the limit value:

[0074]

[0075] In the above formula, ρ is the universal correlation coefficient, t is the second transfer transaction volume of all customers in the past N years, z is the limit value corresponding to each customer, Cov(t,z) is the covariance of the two sets of data t and z, δ t δ z It is the product of the standard deviations of the two data sets t and z.

[0076] Step S205: obtaining a limit prediction model based on the universal correlation coefficient and the personal transfer transaction prediction model.

[0077] Furthermore, this step may specifically include the following steps: substituting the universal correlation coefficient into the personal transfer transaction prediction model to obtain the following limit prediction model:

[0078] Z Q =β1X1+β2X2+β3X3+β0;

[0079] In the above formula, Z Q represents the limit of customer Q predicted by the limit prediction model, X1 represents the customer nature of customer Q, X2 represents the basic information of customer Q, X3 represents the transaction behavior of customer Q, β1=ρθ1, β2=ρθ2, β3=ρθ3, β0=ρθ0.

[0080] Through this step, the construction of a model that is compatible with the limits of customers whose limits are to be adjusted and their customer information is preliminarily completed.

[0081] Step S206: Obtain policy parameters for the region where the customer whose quota is to be adjusted is located, and further improve the quota prediction model based on the policy parameters.

[0082] In this embodiment, due to the influence of policies in various regions, there will be a certain impact on customer limits. For example, some regions often encounter telecommunication fraud, so policies require customers in the region to transfer an amount to prevent telecommunication fraud, etc. Therefore, this embodiment adds the influence of normal parameters to the limit model obtained above, so that the limit model can be further improved.

[0083] Through this step, the improved limit model is as follows:

[0084]

[0085] The above formula summarizes, β Q X Q =β1X1+β2X2+β3X3, Represents the policy parameters of the region where customer Q is located.

[0086] Step S207: outputting the transaction limit of the customer whose limit is to be adjusted based on the limit prediction model.

[0087] Step S208: Acquire and analyze the customer's subsequent active limit adjustment behavior to obtain the customer's transfer limit preference value, and input the transfer limit preference value into the limit prediction model to further improve the limit prediction model.

[0088] In this embodiment, after using the limit model to output the transaction limit of the customer whose limit is to be adjusted, it is also possible to subsequently use machine learning to continuously analyze the customer's limit adjustment behavior to obtain the customer's transfer limit preference value, and input the preference value into the limit prediction model to continuously self-improve the customer's limit prediction model.

[0089] The above method is further described below through a specific embodiment: Customer Q is a counter registered customer, 5-star, high credit rating, and is not on the restricted list. At the same time, he is an employee of a state-owned enterprise with a monthly salary of 20,000. He has a large amount of regular deposits in the bank, has not purchased financial management, uses the bank system for more consumption, and transfers a large amount. The result is obtained according to the limit prediction model, and the result shows that a higher level of limit value can be assigned to customer Q. However, since the customer's region often encounters telecommunications fraud, the policy requires controlling the customer's transfer amount to prevent telecommunications fraud. Therefore, the integrated limit prediction model assigns the customer the corresponding limit value after the policy parameters are adjusted. After that, customer Q believes that he has a large transfer demand and a high security level, and requests to increase the electronic banking limit. After the bank staff adjusts the limit value for him. The adjustment behavior of customer Q is recorded by the model self-improvement module, and the parameters will be appropriately increased when the corresponding limit value of the customer is analyzed later.

[0090] As can be seen from the above, the method for automatically adjusting customer limits provided in the embodiment of the present application establishes a personal transfer transaction prediction model for customers whose limits are to be adjusted, obtains the relationship between the transfer transaction volume of the customers whose limits are to be adjusted and the customer information variables, and then performs a correlation analysis on all samples in the specified area to obtain a universal correlation coefficient between the transaction volume and the limit, and obtains a limit prediction model based on the universal correlation coefficient and the personal transfer transaction prediction model, so that the limit value of the individual customer output by the limit prediction model is more in line with the customer's needs, and the entire process does not require manual intervention. At the bank level, this application frees up a large number of business personnel from manual operations, and can respond to local regulatory policies in a timely manner, which is conducive to avoiding the occurrence of illegal transactions. At the customer level, this application meets the diverse transfer limit needs of customers, reduces unnecessary limit adjustment operations of customers, and protects the property safety of customers.

[0091] like Figure 3The figure shows a schematic diagram of the structure of a device for automatically adjusting customer limits provided in an embodiment of the present application, the device comprising: a customer information acquisition unit 310 to be adjusted, a personal transaction model establishment unit 320, a regional customer information acquisition unit 330, a universal correlation coefficient acquisition unit 340, a limit prediction model establishment unit 350 and a limit output unit 360, which are sequentially connected to each other.

[0092] The to-be-adjusted customer information acquisition unit 310 is used to acquire the first transfer transaction volume and customer information of the to-be-adjusted customer's limit in the past N years.

[0093] The personal transaction model building unit 320 is used to build a customer personal transfer transaction prediction model based on the first transfer transaction volume and customer information.

[0094] The regional customer information acquisition unit 330 is used to acquire the second transfer transaction volume and corresponding limit value of all customers in a specified region in the past N years.

[0095] The universal correlation coefficient obtaining unit 340 is used to obtain a universal correlation coefficient between the transfer transaction amount and the limit value based on the second transfer transaction amount and the corresponding limit value.

[0096] The limit prediction model establishing unit 350 is used to obtain a limit prediction model based on the universal correlation coefficient and the personal transfer transaction prediction model.

[0097] The limit output unit 360 is used to output the transaction limit of the customer whose limit is to be adjusted based on the limit prediction model.

[0098] Preferably, Figure 4 As shown, the above-mentioned device also includes a model improvement unit 370, which is used to obtain and analyze the customer's subsequent active limit adjustment behavior, obtain the customer's transfer limit preference value, and input the transfer limit preference value into the limit prediction model to further improve the limit prediction model.

[0099] Preferably, the above-mentioned customer information includes customer nature information, customer basic information and transaction behavior information. The customer nature information includes registration method, credit rating, star rating, and whether included in the restricted list; the customer basic information includes salary level, job type, completeness of contact information, and family relationships; the transaction behavior information includes deposit amount, loan amount, financial management amount, and daily consumption amount.

[0100] Preferably, the above-mentioned personal transaction model building unit 320 is specifically used to: obtain the following relationship between customer nature information, customer basic information and transaction behavior information and their variables respectively by using a multivariate linear regression method based on customer information:

[0101]

[0102] In the above formula, x1 represents the customer's nature information, x2 represents the customer's basic information, and x3 represents the transaction behavior information; a1 represents the registration method, a2 represents the credit rating, a3 represents the star rating, a4 represents whether it is included in the restricted list, and η 0-4 represents the correlation coefficient of each variable in customer nature; b1 represents salary level, b2 represents salary type, b3 represents the completeness of contact information, b4 represents family relationship, κ 0-4 represents the correlation coefficient of each variable in the basic information of the customer; c1 represents the deposit amount, c2 represents the loan amount, c3 represents the financial management amount, c4 represents the daily consumption amount, λ 0-4 Represents the correlation coefficient of each variable in the transaction behavior information;

[0103] Get the first transfer transaction volume t of the customer whose limit is to be adjusted in the past N years (x) The correlation coefficient θ between customer nature information x1, customer basic information x2 and transaction behavior information x3 0-4 , we get the following personal transfer transaction prediction model:

[0104] t (x) =θ1x1+θ2x2+θ3x3+θ0.

[0105] Preferably, the general correlation coefficient obtaining unit 340 is specifically used to obtain the general correlation coefficient of the transfer transaction volume and the limit value based on the second transfer transaction volume and the corresponding limit value by using the following correlation mathematical model:

[0106]

[0107] In the above formula, ρ is the universal correlation coefficient, t is the second transfer transaction volume of all customers in the past N years, z is the limit value corresponding to each customer, Cov(t,z) is the covariance of the two sets of data t and z, δ t δ z It is the product of the standard deviations of the two data sets t and z.

[0108] Preferably, the limit prediction model establishing unit 350 is specifically used to: substitute the universal correlation coefficient into the personal transfer transaction prediction model to obtain the following limit prediction model:

[0109] Z Q =β1X1+β2X2+β3X3+β0;

[0110] In the above formula, Z Q represents the limit of customer Q predicted by the limit prediction model, X1 represents the customer nature of customer Q, X2 represents the basic information of customer Q, X3 represents the transaction behavior of customer Q, β1=ρθ1, β2=ρθ2, β3=ρθ3, β0=ρθ0.

[0111] Preferably, the above device further includes a policy parameter adjustment unit 380: which is used to obtain the policy parameters of the region where the customer whose quota is to be adjusted is located, and further improve the quota prediction model based on the policy parameters to obtain the following improved quota prediction model:

[0112]

[0113] The above formula summarizes, β Q X Q =β1X1+β2X2+β3X3, Represents the policy parameters of the region where customer Q is located.

[0114] For a detailed description of each of the above units, please refer to the corresponding description in the aforementioned method embodiment, which will not be further elaborated here.

[0115] From the above, it can be seen that the automatic adjustment device for customer limits provided in the embodiment of the present application establishes a personal transfer transaction prediction model for the customer whose limit is to be adjusted, obtains the relationship between the transfer transaction volume of the customer whose limit is to be adjusted and the customer information variable, and then performs a correlation analysis on the full amount of samples in the specified area to obtain a universal correlation coefficient between the transaction volume and the limit, and obtains a limit prediction model based on the universal correlation coefficient and the personal transfer transaction prediction model, so that the limit value of the individual customer output by the limit prediction model is more in line with the customer's needs, and the whole process does not require manual intervention. At the bank level, this application frees up a large number of business personnel from manual operations, and can respond to local regulatory policies in a timely manner, which is conducive to avoiding the occurrence of illegal transactions. At the customer level, this application meets the diverse transfer limit needs of customers, reduces unnecessary limit adjustment operations of customers, and protects the property safety of customers.

[0116] An embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the above method is implemented when the processor executes the program.

[0117] An embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program for executing the above method.

[0118] like Figure 5 As shown, the electronic device 600 may further include: a communication module 110, an input unit 120, an audio processor 130, a display 160, and a power supply 170. It is worth noting that the electronic device 600 does not necessarily have to include Figure 5 In addition, the electronic device 600 may also include Figure 5 For components not shown, reference may be made to the prior art.

[0119] like Figure 5 As shown, the central processor 100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor devices and / or logic devices. The central processor 100 receives inputs and controls the operations of various components of the electronic device 600 .

[0120] The memory 140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The above-mentioned information related to the failure may be stored, and a program for executing the relevant information may also be stored. The CPU 100 may execute the program stored in the memory 140 to implement information storage or processing.

[0121] The input unit 120 provides input to the CPU 100. The input unit 120 is, for example, a key or a touch input device. The power supply 170 is used to provide power to the electronic device 600. The display 160 is used to display display objects such as images and text. The display may be, for example, an LCD display, but is not limited thereto.

[0122] The memory 140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 140 may also be some other type of device. The memory 140 includes a buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application / function storage unit 142, which is used to store applications and function programs or processes for executing the operation of the electronic device 600 through the central processor 100.

[0123] The memory 140 may also include a data storage unit 143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 144 of the memory 140 may include various drivers for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0124] The communication module 110 is a transmitter / receiver 110 that transmits and receives signals via an antenna 111. The communication module (transmitter / receiver) 110 is coupled to the central processor 100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0125] Based on different communication technologies, multiple communication modules 110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless LAN module. The communication module (transmitter / receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide an audio output via the speaker 131 and receive an audio input from the microphone 132, thereby realizing a common telecommunication function. The audio processor 130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 130 is also coupled to the central processor 100, so that the sound can be recorded on the local machine through the microphone 132, and the sound stored on the local machine can be played through the speaker 131.

[0126] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0127] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0128] 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.

[0129] 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.

[0130] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for automatically adjusting customer quota, characterized in that: The method comprises: Obtain the first transfer transaction volume and customer information of the customer whose limit is to be adjusted in the past N years; Establishing a customer personal transfer transaction prediction model based on the first transfer transaction volume and customer information; Get the second transfer transaction volume and corresponding limit value of all customers in the specified area in the past N years; Obtaining a universal correlation coefficient between the transfer transaction amount and the limit value based on the second transfer transaction amount and the corresponding limit value; Obtaining a limit prediction model based on the universal correlation coefficient and the personal transfer transaction prediction model; The transaction limit of the customer whose limit is to be adjusted is output based on the limit prediction model.

2. The method for automatically adjusting customer quota as claimed in claim 1, characterized in that: The method also includes: acquiring and analyzing the customer's subsequent active limit adjustment behavior to obtain the customer's transfer limit preference value, and inputting the transfer limit preference value into the limit prediction model to further improve the limit prediction model.

3. The method for automatically adjusting customer quota as claimed in claim 1, characterized in that: The customer information includes customer nature information, customer basic information and transaction behavior information. The customer nature information includes registration method, credit rating, star rating, and whether included in the restricted list; the customer basic information includes salary level, job type, completeness of contact information, and family relationships; the transaction behavior information includes deposit amount, loan amount, financial management amount, and daily consumption amount.

4. The method for automatically adjusting customer quota as claimed in claim 3, characterized in that: The establishing of a customer personal transfer transaction prediction model based on the first transfer transaction volume and customer information comprises: Based on customer information, the multivariate linear regression method is used to obtain the following relationship between customer nature information, customer basic information, transaction behavior information and its variables: In the above formula, x1 represents the customer's nature information, x2 represents the customer's basic information, and x3 represents the transaction behavior information; a1 represents the registration method, a2 represents the credit rating, a3 represents the star rating, a4 represents whether it is included in the restricted list, and η 0-4 represents the correlation coefficient of each variable in customer nature; b1 represents salary level, b2 represents salary type, b3 represents the completeness of contact information, b4 represents family relationship, κ 0-4 represents the correlation coefficient of each variable in the basic information of the customer; c1 represents the deposit amount, c2 represents the loan amount, c3 represents the financial management amount, c4 represents the daily consumption amount, λ 0-4 Represents the correlation coefficient of each variable in the transaction behavior information; Get the first transfer transaction volume t of the customer whose limit is to be adjusted in the past N years (x) The correlation coefficient θ between customer nature information x1, customer basic information x2 and transaction behavior information x3 0-4 , we get the following personal transfer transaction prediction model: t (x) =θ1x1+θ2x2+θ3x3+θ0.

5. The method for automatically adjusting customer quota as claimed in claim 4, characterized in that: The general correlation coefficient of the transfer transaction amount and the limit value obtained based on the second transfer transaction amount and the corresponding limit value includes: Based on the second transfer transaction volume and the corresponding limit value, the general correlation coefficient of the transfer transaction volume and the limit value is obtained using the following correlation mathematical model: In the above formula, ρ is the universal correlation coefficient, t is the second transfer transaction volume of all customers in the past N years, z is the limit value corresponding to each customer, Cov(t,z) is the covariance of the two sets of data t and z, δ t δ z It is the product of the standard deviations of the two data sets t and z.

6. The method for automatically adjusting customer quota as claimed in claim 5, characterized in that: The obtaining of the limit prediction model based on the universal correlation coefficient and the personal transfer transaction prediction model comprises: Substituting the universal correlation coefficient into the personal transfer transaction prediction model, the following limit prediction model is obtained: Z Q =β1X1+β2X2+β3X3+β0; In the above formula, Z Q represents the limit of customer Q predicted by the limit prediction model, X1 represents the customer nature of customer Q, X2 represents the basic information of customer Q, X3 represents the transaction behavior of customer Q, β1=ρθ1, β2=ρθ2, β3=ρθ3, β0=ρθ0.

7. The method for automatically adjusting customer quota as claimed in claim 6, characterized in that: After obtaining the limit prediction model based on the universal correlation coefficient and the personal transfer transaction prediction model, the method further includes: obtaining policy parameters of the region where the customer whose limit is to be adjusted is located, and further improving the limit prediction model based on the policy parameters to obtain the following improved limit prediction model: The above formula is summarized, β Q X Q =β1X1+β2X2+β3X3, Represents the policy parameters of the region where customer Q is located.

8. A customer limit automatic adjustment device, characterized in that: The device comprises: A unit for acquiring information of customers to be adjusted, used for acquiring the first transfer transaction volume and customer information of the customers whose quotas are to be adjusted in the past N years; A personal transaction model building unit, used to build a customer personal transfer transaction prediction model based on the first transfer transaction volume and customer information; A regional customer information acquisition unit, used to acquire the second transfer transaction volume and corresponding limit value of all customers in a specified region in the past N years; A universal correlation coefficient obtaining unit, configured to obtain a universal correlation coefficient between a transfer transaction amount and a limit value based on the second transfer transaction amount and the corresponding limit value; A quota prediction model establishing unit, used to obtain a quota prediction model based on the universal correlation coefficient and the personal transfer transaction prediction model; A quota output unit is used to output the transaction limit of the customer whose limit is to be adjusted based on the quota prediction model.

9. An electronic 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 steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images