Product management and control strategy control method and device, electronic equipment and computer medium

Abstract

The invention provides a product management and control strategy control method and device. According to the specific implementation scheme, historical management and control strategies of different management and control groups and credit products in a historical period are obtained; based on the management and control group and the historical management and control strategy, determining a corresponding relation set of the strategy and the group; determining at least two management and control objective functions for the credit product based on the management and control scene of the credit product; based on the management and control objective function and a multi-objective optimization algorithm, selecting a target corresponding relation from the corresponding relation set to obtain a target corresponding relation set comprising at least one target corresponding relation; and obtaining a target management and control strategy set comprising at least one target management and control strategy based on the target corresponding relation set. Through the implementation mode, the reliability of credit product risk management and control is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a product management and control strategy method and device, an electronic device, and a computer-readable medium. Background Art

[0002] Credit cards are gradually moving from an incremental era to a stock era, and refined operations in customer loans are becoming increasingly important. Traditional credit card management and control methods conduct multi-dimensional analysis of customer characteristics and select high-credit-risk customers for management and control.

[0003] However, in actual management and control, the current credit card control measures are not effective for all customers. Improper use of credit card control measures may cause customers to not continue to repay installment loans, causing the risk to spread. Summary of the invention

[0004] Provided are a product management and control policy control method and device, an electronic device, and a computer-readable storage medium.

[0005] According to a first aspect, a product management and control strategy control method is provided, the method comprising: obtaining historical management and control strategies of different management and control groups and credit products in historical periods; determining a correspondence set between strategies and groups based on the management and control groups and the historical management and control strategies; determining at least two management and control objective functions for credit products based on the management and control scenarios of credit products; selecting target correspondences from the correspondence set based on the management and control objective functions and a multi-objective optimization algorithm to obtain a target correspondence set including at least one target correspondence; and obtaining a target management and control strategy set including at least one target management and control strategy based on the target correspondence set.

[0006] According to a second aspect, a product management and control strategy control device is provided, the system comprising: an acquisition unit configured to acquire historical management and control strategies of different management and control groups and credit products in historical periods; a determination unit configured to determine a correspondence set between strategies and groups based on the management and control groups and the historical management and control strategies; a selection unit configured to determine at least two management and control objective functions for credit products based on the management and control scenarios of credit products; a relationship acquisition unit configured to select a target correspondence from the correspondence set based on the management and control objective function and a multi-objective optimization algorithm to obtain a target correspondence set including at least one target correspondence; a strategy acquisition unit configured to obtain a target management and control strategy set including at least one target management and control strategy based on the target correspondence set.

[0007] According to a third aspect, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any implementation manner of the first aspect.

[0008] According to a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method described in any implementation of the first aspect.

[0009] The product control strategy control method and device provided by the embodiment of the present disclosure first obtains the historical control strategies of different control groups and credit products in the historical period; secondly, based on the control groups and historical control strategies, determines the corresponding relationship set between strategies and groups; thirdly, based on the control scenario of credit products, determines at least two control objective functions for credit products; thirdly, based on the control objective function and the multi-objective optimization algorithm, selects the target corresponding relationship from the corresponding relationship set to obtain the target corresponding relationship set including at least one target corresponding relationship; finally, based on the target corresponding relationship set, obtains the target control strategy set including at least one target control strategy. Thus, the operations research method is used to summarize the historical credit product control strategies, and combined with the control groups of credit products, the optimal relationship between at least two control objective functions under different control strategies is quantified, and for different control groups, the appropriate target control strategy is matched, so as to balance the control objective function while reducing the credit product control risk and improving the reliability of credit product control.

[0010] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0012] Figure 1 is a flow chart of an embodiment of a product management and control strategy control method according to the present disclosure;

[0013] Figure 2 is a flow chart of another embodiment of the product management and control strategy control method according to the present disclosure;

[0014] Figure 3 is a schematic diagram of the structure of the Pareto front in an embodiment of the present disclosure;

[0015] Figure 4is a structural schematic diagram of an embodiment of a product management and control strategy control device according to the present disclosure;

[0016] Figure 5 It is a block diagram of an electronic device used to implement the product management policy control method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0017] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0018] In this embodiment, "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features.

[0019] During customer loan operations, in order to control the occurrence and spread of credit product risks, it is necessary to adopt loan management and control measures to ensure loan recovery and asset preservation and appreciation, and to ensure that credit asset risks are controllable.

[0020] Traditional credit card loan control selects high-credit risk customers for control through multi-dimensional analysis of customer characteristics, and achieves the goal of controlling risk by controlling the risk exposure of high-credit risk customers. Among them, the means of controlling risk exposure include restricting transactions, reducing repayment limits, and stopping payments. In actual operations, after selecting high-risk customers, a means will be used to control the risk exposure of the customer and control their non-performing loans. Different means of controlling risk exposure are often only effective for some high-risk customers. Improper control methods not only fail to control credit risks, but also further worsen the risks of high-risk customers.

[0021] Therefore, in actual management and control, the means of controlling risk exposure are not effective for all customers. Improper use of means will cause greater losses. For example, directly stopping payment for customers in installments may cause customers to stop repaying installment loans, thereby causing the spread of risks. Therefore, there is an urgent need for a scientific means to measure the impact of different management and control measures on different users, quantify the risks and benefits brought by management and control, and thus achieve scientific management and control of customers in loans.

[0022] Aiming at the problem that the control strategies adopted in traditional technologies have unbalanced control over credit products, the present disclosure provides a product control strategy control method, by: Figure 1A process 100 of an embodiment of a product management and control strategy control method according to the present disclosure is shown. The product management and control strategy control method comprises the following steps:

[0023] Step 101, obtaining historical control strategies for different control groups and credit products in historical periods.

[0024] In this embodiment, the execution subject on which the product management strategy control method of the present invention runs is located in different management scenarios, different management groups, and different credit products used by the management groups; for example, for loan management scenarios, high-risk groups are usually selected for management in history, and the management groups include: customers with overdue payments, customers with high credit overdue levels, and customers with multiple historical cycles; credit products can be actual products, such as credit cards, and credit products can also be virtual products. For example, credit products are different loan items, and historical management strategies for credit products include: repayment reduction, direct payment stop, and transaction restriction.

[0025] Step 102: Based on the control group and the historical control strategy, determine a corresponding relationship set between the strategy and the group.

[0026] In this embodiment, the execution entity on which the product control strategy control method runs can determine the correspondence between the strategy and the group based on the historical relationship between the control group and the historical control strategy, and the correspondence can be represented by a corresponding function in mathematical expression, that is, one correspondence is a function.

[0027] In mathematical expression, C can be used to represent the historical control strategy, and K can be used to represent the control group. Then, after strategy backtracking, the corresponding relationship R between the corresponding strategy and the group can be obtained, including the corresponding relationship set R of multiple corresponding relationships. i As shown in formula (1), in formula (1), i represents the number of corresponding relationship strategies.

[0028] R i =∑{C i →K i} (1)

[0029] In this embodiment, the above step 102 includes: determining the period of the control group and the historical control strategy, associating and representing the control group and the historical control strategy of the same period, and obtaining a corresponding relationship set between the strategy and the group.

[0030] In this embodiment, by looking back at the historical control strategies, the control groups and historical control strategies of each period are matched to each other, and the corresponding relationships between different groups in history are obtained. Multiple corresponding relationships form a corresponding relationship set as the basis of the multi-objective optimization algorithm. For example, from January to June 2020, the overdue group was selected for control, and the control method was repayment reduction. At the same time, from January to June 2020, the control method of restricting transactions was adopted for the group with a cycle of more than two months. By looking back at the historical control groups and methods, the past control strategies are sorted out as the basis for the multi-objective optimization algorithm to obtain the optimization strategy.

[0031] Step 103: Determine at least two control objective functions for the credit product based on the control scenario of the credit product.

[0032] In this embodiment, the control objective function is the goal achieved by the control algorithm (such as a multi-objective optimization algorithm). Mathematically, the control objective function is represented in the form of a function.

[0033] In this embodiment, different management and control scenarios may select different management and control objective functions. For example, for a credit card management and control scenario, the management and control objective function includes: minimizing the number of credit cards recovered and maximizing the number of bad credit cards recovered; for a credit card limit adjustment scenario, the management and control objective function includes: minimizing the number of credit cards with adjusted limits and maximizing the number of bad credit cards with adjusted limits.

[0034] Step 104 , based on the management and control objective function and the multi-objective optimization algorithm, select a target correspondence relationship from the correspondence relationship set to obtain a target correspondence relationship set including at least one target correspondence relationship.

[0035] In this embodiment, the multi-objective optimization algorithm is a main algorithm in operations research. Operations research is a discipline that improves decision-making by building mathematical models and using optimization algorithms to solve them. Its core is a series of optimization algorithms. According to the definition of the objectives and different constraints, the appropriate optimization algorithm can be selected to obtain the optimal solution for one or more objectives. The machine learning algorithm can be understood as an algorithm that automatically obtains rules from data and uses these rules to predict new samples.

[0036] In this embodiment, the multi-objective optimization algorithm is an algorithm for a type of optimization problem in operations research. Generally, there are multiple objectives, and there are certain conflicts between the objectives. After solving the multi-objective optimization algorithm, a set of optimal solutions (Pareto frontier) can be obtained for decision makers to make reference and selection. The multi-objective optimization problem is actually a combinatorial optimization problem, and the solution space composed of different group combinations is efficiently heuristically searched and non-dominated sorted by the genetic algorithm, and finally the Pareto frontier is obtained.

[0037] In this embodiment, the target correspondence relationship is a correspondence relationship that simultaneously satisfies all the control objective functions in at least two control objective functions for credit products. The above step 104 includes: using a multi-objective optimization algorithm to analyze whether each correspondence in the relationship strategy set satisfies the effect of the control objective function, determining the target correspondence relationship that satisfies the control objective function, and combining the determined target correspondence relationships to obtain a target correspondence relationship set.

[0038] It should be noted that in order to analyze the correspondence relationship set using a multi-objective optimization algorithm, the correspondence relationship set can be represented by a mathematical function.

[0039] In this embodiment, the multi-objective optimization algorithm in operations research is used for the first time in the risk management scenario of credit products to summarize and quantify the effects of historical management strategies that have been used in history, thereby improving the reliability of the selection of product management strategies for credit products.

[0040] Optionally, the control scenario of the credit product is a loan control scenario, and the control objective function includes: a first objective function and a second objective function, the first objective function is to minimize the recovery of credit products; the second objective function is to maximize the recovery of non-performing credit products; the above step 104 includes: using a multi-objective optimization algorithm to select objectives corresponding to the first objective function and the second objective function from the correspondence relationship set, and obtain a target correspondence relationship set including at least one target correspondence relationship.

[0041] This optional implementation provides a method for calculating the stability value of stability, which uses operations research methods to summarize the historical credit card loan management effects, and combines segmented customer groups to quantify the optimal relationship between recovered loans and recovered non-performing loans under different management methods. For different high-risk customer groups, appropriate management methods are matched to achieve the loan management goal of balancing risks and returns.

[0042] Step 105: Based on the target correspondence set, a target management and control strategy set including at least one target management and control strategy is obtained.

[0043] In this embodiment, each target correspondence relationship represents the relationship between the control group and the historical control strategy. After determining the target correspondence relationship, the historical control strategy in the target correspondence relationship is extracted, and the historical control strategy is used as the target control strategy to obtain a target control strategy set including at least one target control strategy.

[0044] The product control strategy control method provided by the embodiment of the present disclosure first obtains the historical control strategies of different control groups and credit products in the historical period; secondly, based on the control groups and historical control strategies, determines the corresponding relationship set of strategies and groups; thirdly, based on the control scenario of the credit product, determines at least two control objective functions for the credit product; then, based on the control objective function and the multi-objective optimization algorithm, selects the target corresponding relationship from the corresponding relationship set to obtain the target corresponding relationship set including at least one target corresponding relationship; finally, based on the target corresponding relationship set, obtains the target control strategy set including at least one target control strategy. Thus, the operations research method is used to summarize the historical credit product control strategy, and combined with the control group of the credit product, the optimal relationship between at least two control objective functions under different control strategies is quantified, and for different control groups, the appropriate target control strategy is matched, so as to balance the control objective function while reducing the credit product control risk and improving the reliability of credit product control.

[0045] Figure 2 A process 200 of another embodiment of a product management and control strategy control method according to the present disclosure is shown. The product management and control strategy control method includes the following steps:

[0046] Step 201, obtaining historical control strategies for different control groups and credit products in historical periods.

[0047] Step 202: Based on the control group and the historical control strategy, determine a corresponding relationship set between the strategy and the group.

[0048] Step 203: Determine at least two control objective functions for the credit product based on the control scenario of the credit product.

[0049] Step 204 , based on the management and control objective function and the multi-objective optimization algorithm, select a target correspondence relationship from the correspondence relationship set to obtain a target correspondence relationship set including at least one target correspondence relationship.

[0050] Step 205: Based on the target correspondence set, a target management and control strategy set including at least one target management and control strategy is obtained.

[0051] It should be understood that the operations and features in the above steps 201 to 205 correspond to the operations and features in steps 101 to 105, respectively. Therefore, the above descriptions of the operations and features in steps 101 to 105 are also applicable to steps 201 to 205 and will not be repeated here.

[0052] Step 206: Select a target control strategy for each control group from the target control strategy set.

[0053] Before applying the target control strategy set, the stability of the target control strategy set needs to be verified. Therefore, after summarizing the rule set, it is necessary to arbitrarily select two other different time points to verify the stability of each target control strategy in the target control strategy set.

[0054] In this embodiment, the corresponding target control strategies are first traced back according to different groups, so that corresponding stability analysis is performed for each control group.

[0055] Step 207, calculating a stability value that characterizes the stability of the target control strategy of each control group.

[0056] In this embodiment, by analyzing the performance of the target control strategy of each control group on the control objective function, the stability of the target control strategy of each control group can be determined. Specifically, for each control group, the difference between any two control objective functions in the historical control strategies in the target control strategy under the control group can be calculated to determine the stability value of the target control strategy of each control group.

[0057] For example, in the loan control scenario of credit products, any two of the above control objective functions include: recovered loans and recovered non-performing loans. By calculating the relationship between recovered loans and recovered non-performing loans, the stable value of the target control strategy of the control group can be determined.

[0058] Step 208: In response to the stability value of a target control policy being greater than the stability threshold of the target control policy, the target control policy is deleted from the target control policy set to obtain an optimal control policy set.

[0059] In this embodiment, the stability threshold of the target control strategy can be determined based on the control requirements of the historical control strategy. When the stability value of the target control strategy is greater than the stability threshold of the target control strategy, it means that the historical control strategy corresponding to the target control strategy cannot balance all control objective functions at the same time when implementing various control objective functions, and the stability is poor. The target management strategy needs to be deleted from the target management strategy set.

[0060] In this embodiment, the optimal management and control strategies include at least one optimal management and control strategy, and each optimal management and control strategy can be applied to actual credit product management and control scenarios.

[0061] Optionally, in response to a stability value of a target control strategy being less than or equal to a stability threshold of the target control strategy, the target control strategy is used as an optimal control strategy in an optimal control strategy set.

[0062] The product control strategy control method provided by the embodiment of the present disclosure selects the target control strategy of each control group from the target control strategy set after obtaining the target control strategy set; calculates the stability value that characterizes the stability of the target control strategy of each control group; when the stability value of a target control strategy is greater than the stability threshold of the target control strategy, determines that the target control strategy has poor stability, deletes the target control strategy from the target control strategy set, and obtains a target control strategy with good stability effect, which provides a reasonable basis for the accuracy and rationality of credit product control.

[0063] Optionally, for the risk loan management scenario, the management objective function includes: a first objective function and a second objective function, the first objective function is to minimize the recovered credit products; the second objective function is to maximize the recovered non-performing credit products; first, the historical management groups and historical management strategies are traced back, and on the basis of the selected dimensions, a multi-objective optimization algorithm can be used to obtain the optimal relationship between the loans recovered by high-risk groups and the recovered non-performing loans under different historical management strategies, and the corresponding target management strategy set is summarized through the optimal relationship, and put into use after verifying the stability of the strategy set.

[0064] In some embodiments of the present disclosure, the above-mentioned management and control objective function includes: a first objective function and a second objective function; based on the management and control objective function and a multi-objective optimization algorithm, a target correspondence relationship is selected from a correspondence relationship set to obtain a target correspondence relationship set including at least one target correspondence relationship, including: determining at least one evaluation dimension of the correspondence relationship set; under each evaluation dimension of at least one evaluation dimension, determining the management and control effect function of each correspondence in the correspondence relationship set; based on the multi-objective optimization algorithm, the management and control effect function is solved to obtain the Pareto decision frontier of the first objective function and the second objective function; based on the Pareto decision frontier, a target correspondence relationship set including at least one target correspondence relationship is obtained.

[0065] In this embodiment, the Pareto decision frontier is the objective function value corresponding to the Pareto optimal solution, and the target corresponding relationship set is all the corresponding relationships corresponding to the Pareto decision frontier.

[0066] After determining the control objective function, it is necessary to make an overall evaluation of the corresponding relationship in other dimensions. For credit products, the dimensions of the selected evaluation effect can include the following two categories:

[0067] 1) Behavioral dimensions of users’ adoption of credit products: severely hungry customers, shared debt customers, revolving installment customers, regular high-usage customers, pure transaction customers, etc.

[0068] 2) Provisioning related dimensions: user CCF (Credit Conversion Factors) pool, B, user PD (Probability of Default) pool.

[0069] In the scenario of customer management during loans, we first segment the different management groups corresponding to the corresponding relationship set based on the above two dimensions, then combine these segmented management groups, and evaluate and sort them on at least two management objective functions to finally obtain a set of optimal solutions considered by the algorithm, that is, the relationship between loans recovered and non-performing loans recovered by different customer groups under different corresponding relationships.

[0070] like Figure 3 As shown in the figure, the horizontal axis represents the change of the first objective function, the vertical axis represents the change of the second objective function, and the Pareto boundary represents the maximum value that the second objective function can reach when the value of the first objective function is constant. For the loan control scenario, the first objective function is to minimize the first recovery of loans, and the second objective function is to maximize the second recovery of non-performing loans. Figure 3 The horizontal and vertical axes refer to: the maximum value of recovered non-performing loans under a certain condition of recovered loans, or the minimum value of recovered loans under certain conditions of recovered non-performing loans. There are other solutions for target optimization, but they are all in the lower right of the Pareto frontier.

[0071] On the Pareto frontier, the growth rate of recovered loans and recovered non-performing loans is relatively fast. After the L1_scaler point is selected, the same amount of recovered loans and recoverable non-performing loans gradually decrease until the max point is selected. The recovered loans increase, but no more non-performing loans can be recovered. In the management and control business, the goal of recovering loans is to recover non-performing loans. The combination corresponding to the max point is the maximum value of non-performing loans that can be recovered after the management and control strategy controls the group. Therefore, the corresponding relationship combination corresponding to the max point is selected as the target corresponding relationship set.

[0072] By summarizing the corresponding relationship set for multiple times, we can get the target strategy set for controlling different groups using different historical control strategies. The mathematical expression is shown in formula (2). In formula (2), the target control strategy is A i , the target control strategy set is A:

[0073] A=∑{C i →K i :A i} (2)

[0074] The method for obtaining the target control strategy set provided by this optional implementation method determines at least one evaluation dimension of the corresponding relationship set; under each evaluation dimension, the control effect function is determined, and the control effect function is solved based on a multi-objective optimization algorithm to obtain the Pareto decision frontier. From the Pareto frontier, the target control strategy set is obtained, which provides a reliable implementation method for obtaining the target control strategy set.

[0075] In some optional implementations of the present embodiment, the above-mentioned determination of the control effect function of each corresponding relationship in the corresponding relationship set under each evaluation dimension of at least one evaluation dimension includes: determining the performance value of each corresponding relationship in the corresponding relationship set under each evaluation dimension of at least one evaluation dimension; determining the performance value of the comparison group of the corresponding relationship for each corresponding relationship; and obtaining the control effect function corresponding to each corresponding relationship based on the difference between the performance value of each corresponding relationship and the performance value of the corresponding comparison group.

[0076] In this optional implementation, when executing a control strategy, which may be a historical control strategy or a comparative relationship strategy, a corresponding comparison group that has not executed the control strategy will generally be left behind. When evaluating the control effect of the control strategy, the performance value of the control group minus the performance value of the comparison group is used as the impact of the control strategy, wherein the control group is the group that executes the control strategy, and the comparison group is the group that does not execute the control strategy.

[0077] In mathematical expression, as shown in formula (3), E is used to represent the effect of the control strategy, e do represents the performance value of the control group, e compare represents the performance value of the comparison group, then:

[0078] E=e do -e compare (3)

[0079] The control effect function of the corresponding relationship between different control groups and different historical control strategies is shown in formula (4):

[0080] ∑{C i →K i :E=e do -e compare} (4)

[0081] The method for determining the management and control effect function provided by the embodiments of the present disclosure determines the performance value of each corresponding relationship in the corresponding relationship set under each evaluation dimension of at least one evaluation dimension; determines the performance value of the comparison group of each corresponding relationship; obtains the management and control effect function corresponding to each corresponding relationship based on the difference between the performance value of each corresponding relationship and the performance value of the corresponding comparison group, determines the performance value of the corresponding relationship and the comparison group through the evaluation dimension, and determines the management and control effect function corresponding to the corresponding relationship through the difference between the two performance values, which provides a reliable evaluation standard for multi-objective optimization and improves the reliability of the target management and control strategy set.

[0082] In some embodiments of the present disclosure, the management and control scenario of the above-mentioned credit products is a loan management scenario, the first objective function is to minimize the recovery of credit products; the second objective function is to maximize the recovery of non-performing credit products; calculating the stable value that characterizes the stability of the target management and control strategies of each management group includes: calculating the first recovery amount of credit products under the target management and control strategies of each management group, and the second recovery amount of non-performing credit products; subtracting the first recovery amount from the second recovery amount to obtain the stable value of each target management and control strategy.

[0083] In this optional implementation, the loan control scenario mainly achieves the goal of controlling risk by controlling the risk exposure of high credit risk customers. According to the definition of loan control, two target strategies are selected:

[0084] The first objective function: minimize the first recovery amount of the loan. The first objective function can ensure the growth of transactions.

[0085] The second objective function: maximize the second recovery amount L of non-performing loans. The first objective function can effectively control the expansion of risks.

[0086] Methods for controlling user risk exposure include repayment reduction, direct stop payment, etc. From the data, after controlling risk exposure, the customer's loan balance will change. Mathematically, compared with the comparison group, the loan balance is recovered. D represents the first recovery amount of the loan balance. The first objective function is shown in formula (5). In formula (5), D do is the recovery amount of the loan balance of the control strategy, D compare To compare the recovery amount of the loan balance of the group:

[0087] C i →K i :D=D do -D compare (5)

[0088] The ultimate goal of controlling risk exposure is to control risk, that is, to control the customer's non-performing loans. The data is expressed as, compared with the comparison group, the non-performing loans are recovered, and L represents the second recovery of non-performing loans. The second objective function is shown in formula (6). In formula (6), L do is the recovery amount of bad loans under the control strategy, D compare The recovery amount of NPLs for the comparison group is:

[0089] C i →K i :L=L do -L compare (6)

[0090] This optional implementation provides a method for calculating the stable value of the stability of the target management and control strategy, which calculates the first recovery amount of credit products under the target management and control strategy of each management group, and the second recovery amount of non-performing credit products; subtracts the first recovery amount from the second recovery amount to obtain the stable value of each target management and control strategy, and determines the stable value of the target management and control strategy through the recovery amounts of credit products and non-performing credit products corresponding to the first objective function and the second objective function, thereby providing a reliable implementation method for obtaining the stable value.

[0091] Optionally, the control scenario of the above-mentioned credit product is a credit card control scenario, and the first objective function is to minimize the number of recovered credit cards; the second objective function is to maximize the number of recovered bad credit cards; calculating the stable value that characterizes the stability of the target control strategy of each control group includes: calculating the third recovery amount of credit cards under the target control strategy of each control group, and the fourth recovery amount of bad credit cards; subtracting the third recovery amount from the fourth recovery amount to obtain the stable value of each target control strategy.

[0092] Optionally, the management and control scenario of the above-mentioned credit product is a credit card limit adjustment scenario, and the first objective function is to minimize the number of credit cards with limit adjustments; the second objective function is to maximize the number of non-performing credit cards with limit adjustments; calculating the stable value that characterizes the stability of the target management and control strategies of each management group includes: calculating the first limit adjustment number of credit cards under the target management and control strategies of each management group, and the second limit adjustment number of non-performing credit cards; subtracting the second limit adjustment number from the first limit adjustment number to obtain the stable value of each target management and control strategy.

[0093] Optionally, the control scenario of the above-mentioned credit product is a credit card installment access scenario, and the first objective function is to maximize the credit cards with installment access; the second objective function is to minimize the bad credit cards with installment access; calculating the stable value that represents the stability of the target control strategy of each control group includes: calculating the credit card issuance volume of credit cards and the credit card recovery volume of bad credit cards under the target control strategy of each control group; subtracting the credit card issuance volume from the credit card recovery volume to obtain the stable value of each target control strategy.

[0094] Further references Figure 4 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a product management and control strategy control device, and the device embodiment is Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0095] like Figure 4 As shown, the product control strategy control device 400 provided in this embodiment includes: an acquisition unit 401, a determination unit 402, a selection unit 403, a relationship acquisition unit 404, and a strategy acquisition unit 405. Among them, the acquisition unit 401 can be configured to acquire historical control strategies of different control groups and credit products in historical periods. The determination unit 402 can be configured to determine a corresponding relationship set between strategies and groups based on the control groups and historical control strategies. The selection unit 403 can be configured to determine at least two control objective functions for credit products based on the control scenario of credit products. The relationship acquisition unit 404 can be configured to select a target corresponding relationship from the corresponding relationship set based on the control objective function and the multi-objective optimization algorithm to obtain a target corresponding relationship set including at least one target corresponding relationship. The strategy acquisition unit 405 can be configured to obtain a target control strategy set including at least one target control strategy based on the target corresponding relationship set.

[0096] In this embodiment, in the product management strategy control device 400, the specific processing of the acquisition unit 401, the determination unit 402, the selection unit 403, the relationship acquisition unit 404, and the strategy acquisition unit 405 and the technical effects thereof can be referred to respectively. Figure 1 The relevant descriptions of step 101, step 102, step 103, step 104, and step 105 in the corresponding embodiments are not repeated here.

[0097] In some optional implementations of the present embodiment, the above-mentioned device further includes: a screening unit (not shown in the figure), a calculation unit (not shown in the figure), and a deletion unit (not shown in the figure), wherein the above-mentioned screening unit may be configured to select target control strategies for each control group from the target control strategy set. The above-mentioned calculation unit may be configured to calculate a stability value that characterizes the stability of the target control strategies for each control group. The above-mentioned deletion unit may be configured to delete the target control strategy from the target control strategy set in response to a stability value of a target control strategy being greater than a stability threshold of the target control strategy, so as to obtain an optimal control strategy set.

[0098] In some optional implementations of this embodiment, the above-mentioned management and control objective function includes: a first objective function and a second objective function; the above-mentioned relationship obtaining unit 404 is further configured to: determine at least one evaluation dimension of the corresponding relationship set; under each evaluation dimension of at least one evaluation dimension, determine the management and control effect function of each corresponding relationship in the corresponding relationship set; based on a multi-objective optimization algorithm, solve the management and control effect function to obtain the Pareto decision frontier of the first objective function and the second objective function; based on the Pareto decision frontier, obtain a target correspondence relationship set including at least one target correspondence relationship.

[0099] In some optional implementations of the present embodiment, the above-mentioned relationship obtaining unit 404 is further configured to: determine the performance value of each corresponding relationship in the corresponding relationship set under each evaluation dimension of at least one evaluation dimension; determine the performance value of the comparison group of each corresponding relationship for each corresponding relationship; and obtain the control effect function corresponding to each corresponding relationship based on the difference between the performance value of each corresponding relationship and the performance value of the corresponding comparison group.

[0100] In some optional implementations of this embodiment, the management and control scenario of the above-mentioned credit products is a loan management scenario, the first objective function is to minimize the recovery of credit products; the second objective function is to maximize the recovery of non-performing credit products; the above-mentioned calculation unit is further configured to: calculate the first recovery amount of credit products under the target management and control strategy of each management group, and the second recovery amount of non-performing credit products; subtract the first recovery amount from the second recovery amount to obtain the stable value of each target management and control strategy.

[0101] The product control strategy control device provided by the embodiment of the present disclosure, first, the acquisition unit 401 acquires the historical control strategies of different control groups and credit products in the historical period; secondly, the determination unit 402 determines the corresponding relationship set between the strategy and the group based on the control group and the historical control strategy; thirdly, the selection unit 403 determines at least two control objective functions for the credit product based on the control scenario of the credit product; then, the relationship acquisition unit 404 selects the target corresponding relationship from the corresponding relationship set based on the control objective function and the multi-objective optimization algorithm, and obtains the target corresponding relationship set including at least one target corresponding relationship; finally, the strategy acquisition unit 405 obtains the target control strategy set including at least one target control strategy based on the target corresponding relationship set. Therefore, the operations research method is used to summarize the historical credit product control strategy, and the optimal relationship between at least two control objective functions under different control strategies is quantified in combination with the control group of the credit product. For different control groups, the appropriate target control strategy is matched, so as to balance the control objective function while reducing the credit product control risk and improving the reliability of credit product control.

[0102] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0103] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0104] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0105] like Figure 5As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0106] A number of components in the device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0107] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as the product control policy control method. For example, in some embodiments, the product control policy control method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the product control policy control method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the product control policy control method in any other appropriate manner (e.g., by means of firmware).

[0108] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0109] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable product management and control strategy control device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0110] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0111] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0112] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0113] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0114] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0115] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A product management and control strategy control method, the method comprising: Obtain historical control strategies for different control groups and credit products in historical periods; Based on the control group and the historical control strategy, determine a set of corresponding relationships between strategies and groups; Based on the control scenario of the credit product, determining at least two control objective functions for the credit product; Based on the control objective function and the multi-objective optimization algorithm, a target correspondence relationship is selected from the correspondence relationship set to obtain a target correspondence relationship set including at least one target correspondence relationship; Based on the target correspondence set, a target management and control strategy set including at least one target management and control strategy is obtained.

2. The method according to claim 1, further comprising: Selecting a target control strategy for each control group from the target control strategy set; Calculate the stability value that characterizes the stability of the target control strategy for each control group; In response to a stability value of a target control strategy being greater than a stability threshold of the target control strategy, the target control strategy is deleted from the target control strategy set to obtain an optimal control strategy set.

3. The method according to claim 1 or 2, wherein: The control objective function includes: a first objective function and a second objective function; based on the control objective function and the multi-objective optimization algorithm, selecting a target correspondence relationship from the correspondence relationship set to obtain a target correspondence relationship set including at least one target correspondence relationship includes: Determining at least one evaluation dimension of the corresponding relationship set; Under each evaluation dimension of the at least one evaluation dimension, determining a control effect function of each corresponding relationship in the corresponding relationship set; Solving the control effect function based on a multi-objective optimization algorithm to obtain the Pareto decision frontiers of the first objective function and the second objective function; Based on the Pareto decision frontier, a target correspondence relationship set including at least one target correspondence relationship is obtained.

4. The method according to claim 3, wherein: Determining the control effect function of each corresponding relationship in the corresponding relationship set under each evaluation dimension of the at least one evaluation dimension includes: Under each evaluation dimension of the at least one evaluation dimension, determining a performance value of each corresponding relationship in the corresponding relationship set; For each corresponding relationship, determining a performance value of a comparison group of the corresponding relationship; Based on the difference between the performance value of each corresponding relationship and the performance value of the corresponding comparison group, the control effect function corresponding to each corresponding relationship is obtained.

5. The method according to claim 3, wherein: The control scenario of the credit product is a loan control scenario, the first objective function is to minimize the recovered credit products; the second objective function is to maximize the recovered bad credit products; The calculation of the stability value representing the stability of the target control strategy of each control group includes: Calculate the first recovery amount of credit products under the target control strategy of each control group, and the second recovery amount of non-performing credit products; Subtract the first recovery amount from the second recovery amount to obtain the stable value of each target control strategy.

6. A product management and control strategy control device, the device comprising: An acquisition unit, configured to acquire historical control strategies for different control groups and credit products in historical periods; a determining unit configured to determine a set of corresponding relationships between policies and groups based on the controlled group and the historical control policy; A selection unit is configured to determine at least two management and control objective functions for the credit product based on the management and control scenario of the credit product; a relationship obtaining unit, configured to select a target corresponding relationship from the corresponding relationship set based on the control objective function and the multi-objective optimization algorithm, and obtain a target corresponding relationship set including at least one target corresponding relationship; The strategy obtaining unit is configured to obtain a target management and control strategy set including at least one target management and control strategy based on the target correspondence set.

7. The device according to claim 6, further comprising: A screening unit is configured to select a target control strategy for each control group from the target control strategy set; A calculation unit is configured to calculate a stability value representing the stability of the target control strategy of each control group; The deleting unit is configured to delete the target control strategy from the target control strategy set in response to the stability value of the target control strategy being greater than the stability threshold of the target control strategy, so as to obtain the optimal control strategy set.

8. The device according to claim 6 or 7, wherein: The management and control objective function includes: a first objective function and a second objective function; the relationship obtaining unit is further configured to: determine at least one evaluation dimension of the corresponding relationship set; under each evaluation dimension of the at least one evaluation dimension, determine the management and control effect function of each corresponding relationship in the corresponding relationship set; based on a multi-objective optimization algorithm, solve the management and control effect function to obtain the Pareto decision frontier of the first objective function and the second objective function; based on the Pareto decision frontier, obtain a target correspondence relationship set including at least one target correspondence relationship.

9. The device according to claim 8, wherein: The relationship obtaining unit is further configured to: determine the performance value of each corresponding relationship in the corresponding relationship set under each evaluation dimension of the at least one evaluation dimension; determine the performance value of the comparison group of each corresponding relationship for each corresponding relationship; and obtain the control effect function corresponding to each corresponding relationship based on the difference between the performance value of each corresponding relationship and the performance value of the corresponding comparison group.

10. The device according to claim 8, wherein: The control scenario of the credit product is a loan control scenario, the first objective function is to minimize the recovery of credit products; the second objective function is to maximize the recovery of non-performing credit products; the calculation unit is further configured to: calculate the first recovery amount of credit products under the target control strategy of each control group, and the second recovery amount of non-performing credit products; subtract the first recovery amount from the second recovery amount to obtain the stable value of each target control strategy.

11. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 5.

Images