User screening strategy generation method, device and electronic device

Abstract

The present disclosure relates to a method, device, electronic device and computer-readable medium for generating a user screening strategy. The method comprises: determining a user screening target, wherein the user screening target comprises a project category and a screening parameter; extracting multiple target users from historical users based on the project category to generate a user sample set; inputting the user sample set and the screening parameter into a policy model for calculation to generate multiple user screening strategies; extracting a target user screening strategy from the multiple user screening strategies based on preset standards. The method, device, electronic device and computer-readable medium for generating a user screening strategy involved in the present disclosure can quickly and accurately generate a user screening strategy according to the goals set by the administrator, thereby reducing labor costs, improving the accuracy of strategy screening, accelerating the time to launch a strategy, and timely identifying risky users to ensure resource security.

Description

Technical Field

[0001] The present disclosure relates to the field of computer information processing, and in particular to a method, device, electronic device and computer-readable medium for generating a user screening strategy. Background Art

[0002] With the development of the economy, in order to meet the needs of their own development, individual users or corporate users often borrow money from financial service institutions. For financial service institutions, users' borrowing activities are likely to bring risks to financial service companies. Before the repayment period expires, major adverse changes in the financial and business conditions of the borrower (credit user) are likely to affect its ability to perform its obligations, thereby causing risks such as bad debts and bad debts. Therefore, in order to reduce the probability of such risks, financial service institutions need to conduct risk assessments on borrowers and then formulate corresponding user strategies. User strategies are used to determine the amount of money that can be borrowed, the repayment period, the loan interest rate, etc. for the user.

[0003] In the formulation of user policies, the existing technology is to formulate user policies based on the experience and knowledge of experts, and then analyze based on historical user basic information combined with personal behavior data. If the guidelines of the user policy are updated, such as the user screening ratio is increased or the user rejection rate is increased, after these guidelines are changed, the policy makers still need to analyze again through this analysis method, which wastes a lot of time. Moreover, user policies with manual participation will inevitably introduce errors in the formulation process, which also brings security risks to the actual application of user policies.

[0004] Therefore, a new method, device, electronic device and computer-readable medium for generating a user screening strategy are needed.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] In view of this, the present disclosure provides a user screening policy generation method, device, electronic device and computer-readable medium, which can quickly and accurately generate user screening policies according to the goals set by the administrator, reduce labor costs, improve policy screening accuracy, speed up policy launch time, and timely identify risky users to ensure resource security.

[0007] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0008] According to one aspect of the present disclosure, a method for generating a user screening strategy is proposed, the method comprising: determining a user screening target, the user screening target comprising an item category and a screening parameter; extracting a plurality of target users from historical users based on the item category to generate a user sample set; inputting the user sample set and the screening parameter into a strategy model for calculation; generating a user screening strategy based on a path from a root node to a leaf node in the random forest model, wherein each path from the root node to a leaf node is a rule in the user screening strategy; screening a plurality of paths from a root node to a leaf node using the screening parameter to generate a plurality of user screening strategies; and extracting a target user screening strategy from the plurality of user screening strategies based on a preset standard.

[0009] Optionally, it also includes: receiving a resource quota application from a user; judging the resource quota application based on the target user screening strategy; generating a return notification for the resource quota application based on the judgment result, wherein the return notification includes approving the application or rejecting the application.

[0010] Optionally, judging the resource quota application based on the target user screening strategy includes: obtaining user information and application items from the credit application; and inputting the user information and application items into the target user screening strategy for judgment.

[0011] Optionally, extracting multiple target users from historical users based on the item category to generate a user sample set includes: determining a judgment criterion for sample labels based on the item category; extracting multiple target users from historical users based on the judgment criterion; and determining sample labels for the multiple target users to generate the user sample set.

[0012] Optionally, the user sample set and the screening parameters are input into a strategy model for calculation to generate multiple user screening strategies, including: inputting the user sample set into a random forest model for calculation; using the screening parameters to screen the calculation results of the random forest model; and generating multiple user screening strategies based on the screening results.

[0013] Optionally, the user sample set is input into a random forest model for calculation, including: inputting the user sample set into a random forest model; the random forest model performs calculations based on sample labels; and generating a user screening strategy based on a path from a root node to a leaf node in the random forest model, wherein each path from the root node to a leaf node is a rule in the user screening strategy.

[0014] Optionally, using the screening parameters to screen the calculation results of the random forest model includes: using the screening parameters to screen multiple paths from root nodes to leaf nodes.

[0015] Optionally, generating a plurality of user screening strategies according to the screening results includes: generating the plurality of user screening strategies through paths that satisfy the screening parameters.

[0016] Optionally, extracting a target user screening policy from the multiple user screening policies based on a preset standard includes: calculating the number of identical rules in the multiple user screening policies; and sorting the multiple user screening policies according to the number of identical rules to extract the target user screening policy.

[0017] Optionally, extracting a target user filtering policy from the multiple user filtering policies based on preset criteria includes: calculating the number of rules contained in each user filtering policy in the multiple user filtering policies; determining the complexity of the user filtering policies based on the number; and sorting the multiple user filtering policies from small to large based on the complexity to extract the target user filtering policy.

[0018] According to one aspect of the present disclosure, a user screening strategy generating device is proposed, which includes: a target module, used to determine a user screening target, wherein the user screening target includes a project category and a screening parameter; a sample module, used to extract multiple target users from historical users based on the project category to generate a user sample set; a calculation module, used to input the user sample set and the screening parameter into a policy model for calculation; a user screening strategy is generated based on the path from the root node to the leaf node in the random forest model, wherein each path from the root node to the leaf node is a rule in the user screening strategy; multiple paths from the root node to the leaf node are screened using the screening parameter to generate multiple user screening strategies; a strategy module, used to extract a target user screening strategy from the multiple user screening strategies based on a preset standard.

[0019] Optionally, it also includes: an application module for receiving resource quota applications from users; a judgment module for judging the resource quota applications based on the target user screening strategy; and a notification module for generating a return notification for the resource quota application based on the judgment result, wherein the return notification includes approval of the application or rejection of the application.

[0020] Optionally, the judgment module is further used to obtain user information and application items from the credit application; and input the user information and application items into the target user screening strategy for judgment.

[0021] Optionally, the sample module includes: a criterion unit, used to determine the judgment criterion of the sample label based on the project category; a user unit, used to extract multiple target users from historical users based on the judgment criterion; and a collection unit, used to determine sample labels for the multiple target users to generate the user sample set.

[0022] Optionally, the calculation module includes: a calculation unit, used to input the user sample set into the random forest model for calculation; a screening unit, used to use the screening parameters to screen the calculation results of the random forest model; and a result unit, used to generate multiple user screening strategies based on the screening results.

[0023] Optionally, the computing unit is also used to input the user sample set into a random forest model; the random forest model performs calculations based on sample labels; and a user screening strategy is generated based on a path from a root node to a leaf node in the random forest model, wherein each path from the root node to a leaf node is a rule in the user screening strategy.

[0024] Optionally, the screening unit is further used to screen multiple paths from root nodes to leaf nodes using the screening parameters.

[0025] Optionally, the result unit is further configured to generate the multiple user screening strategies through paths that satisfy the screening parameters.

[0026] Optionally, the policy module includes: a rule quantity unit, used to calculate the number of identical rules in the multiple user screening policies; and sort the multiple user screening policies according to the number of identical rules to extract the target user screening policy.

[0027] Optionally, the policy module includes: a complexity unit, used to calculate the number of rules contained in each user screening policy among the multiple user screening policies; determine the complexity of the user screening policy based on the number; and sort the multiple user screening policies from small to large based on the complexity to extract the target user screening policy.

[0028] According to one aspect of the present disclosure, an electronic device is proposed, which includes: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

[0029] According to one aspect of the present disclosure, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the method described above is implemented.

[0030] According to the user screening policy generation method, device, electronic device and computer-readable medium disclosed in the present invention, a user screening target is determined, and the user screening target includes a project category and a screening parameter; based on the project category, multiple target users are extracted from historical users to generate a user sample set; the user sample set and the screening parameters are input into a policy model for calculation to generate multiple user screening policies; based on preset standards, a target user screening policy is extracted from the multiple user screening policies. This can quickly and accurately generate user screening policies according to the goals set by the administrator, reduce labor costs, improve policy screening accuracy, speed up policy launch time, and timely identify risky users to ensure resource security.

[0031] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and other objects, features and advantages of the present disclosure will become more apparent by describing in detail its exemplary embodiments with reference to the accompanying drawings. The accompanying drawings described below are only some embodiments of the present disclosure, and it is clear to a person skilled in the art that other accompanying drawings can be obtained from these accompanying drawings without creative work.

[0033] Figure 1 The present invention is a system block diagram showing a method and device for generating a user screening strategy according to an exemplary embodiment.

[0034] Figure 2 The figure is a flow chart of a method for generating a user screening strategy according to an exemplary embodiment.

[0035] Figure 3 The figure is a flowchart of a method for generating a user screening strategy according to another exemplary embodiment.

[0036] Figure 4 The figure is a flowchart of a method for generating a user screening strategy according to another exemplary embodiment.

[0037] Figure 5 The figure is a flowchart of a method for generating a user screening strategy according to another exemplary embodiment.

[0038] Figure 6 The figure is a block diagram of a device for generating a user screening strategy according to an exemplary embodiment.

[0039] Figure 7 is a block diagram of a device for generating a user screening strategy according to another exemplary embodiment.

[0040] Figure 8It is a block diagram of an electronic device according to an exemplary embodiment.

[0041] Fig. 9 It is a block diagram of a computer-readable medium according to an exemplary embodiment. DETAILED DESCRIPTION

[0042] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0043] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0044] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0045] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0046] It should be understood that although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another component. Therefore, the first component discussed below can be referred to as the second component without departing from the teachings of the disclosed concepts. As used herein, the term "and / or" includes any one of the associated listed items and all combinations of one or more.

[0047] Those skilled in the art will appreciate that the drawings are merely schematic diagrams of example embodiments, and the modules or processes in the drawings are not necessarily necessary for implementing the present disclosure, and therefore cannot be used to limit the protection scope of the present disclosure.

[0048] In the present invention, resources refer to any available material, information, time, and information resources include computing resources and various types of data resources. Data resources include various special data in various fields. The innovation of the present invention lies in how to use the information interaction technology between the server and the client to make the resource allocation process more automated, efficient and reduce labor costs. Therefore, in essence, the present invention can be applied to the allocation of various resources, including physical goods, water, electricity, and meaningful data. However, for convenience, the present invention takes financial data resources as an example to illustrate the implementation of resource allocation, but those skilled in the art should understand that the present invention can also be used for the allocation of other resources.

[0049] Figure 1 The present invention is a system block diagram showing a method and device for generating a user screening strategy according to an exemplary embodiment.

[0050] like Figure 1 As shown, the system architecture 10 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0051] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as financial service applications, shopping applications, web browser applications, instant messaging tools, email clients, social platform software, etc.

[0052] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0053] The server 105 may be a server that provides various services, such as a backend management server that provides support for the financial service websites browsed by the users using the terminal devices 101, 102, 103. The backend management server may analyze and process the received resource quota applications, and feedback the processing results (approval or rejection) to the administrator of the financial service website and / or the terminal devices 101, 102, 103.

[0054] The server 105 may, for example, receive a resource quota application from a user; the server 105 may, for example, judge the resource quota application based on the target user screening strategy; the server 105 may, for example, generate a return notification for the resource quota application based on the judgment result, and the return notification includes approving the application or rejecting the application.

[0055] The server 105 may, for example, determine a user screening target, wherein the user screening target includes an item category and a screening parameter; the server 105 may, for example, extract multiple target users from historical users based on the item category to generate a user sample set; the server 105 may, for example, input the user sample set and the screening parameters into a policy model for calculation to generate multiple user screening policies; the server 105 may, for example, extract a target user screening policy from the multiple user screening policies based on preset criteria.

[0056] The server 105 may be a physical server, or may be composed of multiple servers. It should be noted that the user screening policy generation method provided in the embodiment of the present disclosure may be executed by the server 105, and accordingly, the user screening policy generation device may be arranged in the server 105. The web page provided to the user for browsing the financial service platform is generally located in the terminal devices 101, 102, and 103.

[0057] Figure 2 FIG. 2 is a flow chart of a method for generating a user screening policy according to an exemplary embodiment. The method 20 for generating a user screening policy includes at least steps S202 to S208.

[0058] like Figure 2 As shown, in S202, a user screening target is determined, and the user screening target includes an item category and a screening parameter.

[0059] In one application scenario, when a user applies for resource quota, before performing risk analysis of the user using a machine learning model, it is desired to screen out users with a higher risk of default through user policies, and then reject the applications of these users. In this case, the screening target may be, for example, the default risk, and the screening parameters may be the default risk rate and sample coverage.

[0060] In a specific embodiment, the default risk rate can be selected as users with a default risk rate greater than 3 times the average risk, and the sample coverage rate can be 3%. More specifically, assuming that the average risk rate of all users is 2%, it is necessary to screen out users with a user risk greater than 6% as target users, and the number of screened users is approximately 3% of the total number of users.

[0061] Furthermore, the parameters may also include: coverage rate threshold, risk rate threshold, number of variable combination results, depth of tree model, complexity of generated rules, etc.

[0062] In S204, multiple target users are extracted from historical users based on the item category to generate a user sample set, including: determining a judgment criterion for sample labels based on the item category; extracting multiple target users from historical users based on the judgment criterion; and determining sample labels for the multiple target users to generate the user sample set.

[0063] When the screening target is default risk, the target user can be a user with a history of default, and further, the overdue time can be used as a sample label. When the screening target is arrears risk, the target user can be a user with a history of arrears, and further, the sample label can be a positive label and a negative label. A positive label means that the user repays the debt in a short time (within 7 days), and a negative label means that the user does not repay the resource in a longer period of time.

[0064] In S206, the user sample set and the screening parameters are input into the strategy model for calculation to generate multiple user screening strategies, including: inputting the user sample set into the random forest model for calculation; using the screening parameters to screen the calculation results of the random forest model; and generating multiple user screening strategies according to the screening results.

[0065] In S208, a target user screening strategy is extracted from the plurality of user screening strategies based on a preset standard. The screened user strategies can be evaluated from different perspectives, and the target user screening strategy is selected for online use.

[0066] For example, filtering may be performed based on the difficulty of the user's filtering strategy, or based on the coverage accuracy of the user's filtering strategy, and so on.

[0067] According to the user screening policy generation method disclosed in the present invention, a user screening target is determined, and the user screening target includes a project category and a screening parameter; based on the project category, multiple target users are extracted from historical users to generate a user sample set; the user sample set and the screening parameters are input into a policy model for calculation to generate multiple user screening policies; based on preset standards, a target user screening policy is extracted from the multiple user screening policies. This method can quickly and accurately generate user screening policies according to the goals set by the administrator, reduce labor costs, improve policy screening accuracy, speed up policy launch time, and timely identify risky users to ensure resource security.

[0068] It should be clearly understood that the present disclosure describes how to form and use specific examples, but the principles of the present disclosure are not limited to any details of these examples. On the contrary, based on the teachings of the contents disclosed in the present disclosure, these principles can be applied to many other embodiments.

[0069] Figure 3 The figure is a flowchart of a method for generating a user screening strategy according to another exemplary embodiment. Figure 3 The process 30 shown is for Figure 2 Supplementary description of the process shown.

[0070] like Figure 3 As shown, in S302, a resource quota application from a user is received. After registering for credit, the user needs to apply for a resource quota before obtaining a resource quota.

[0071] In S304, the resource quota application is judged based on the target user screening strategy, including: obtaining user information and application items from the credit application; and inputting the user information and application items into the target user screening strategy for judgment.

[0072] In S306, a return notification is generated for the resource quota application based on the judgment result, and the return notification includes approval or rejection of the application. According to the judgment result of the user screening strategy, the user's application is rejected or approved. Furthermore, after approving the user's application, a machine learning model of the user risk class can be called to further analyze the user's risk to determine the user's resource quota.

[0073] The combination of the user screening strategy and the user risk analysis model disclosed in the present invention can quickly eliminate some user resource quota applications that do not meet the requirements, reduce the calculation pressure of the machine learning model, and speed up the user application process.

[0074] Figure 4 The figure is a flowchart of a method for generating a user screening strategy according to another exemplary embodiment. Figure 4 The process 40 shown is for Figure 2 The process shown in FIG. 1 is a detailed description of S206 “inputting the user sample set and the screening parameters into a policy model for calculation to generate a plurality of user screening policies”.

[0075] like Figure 4 As shown, in S402, the user sample set is input into the random forest model for calculation. It includes: inputting the user sample set into the random forest model; the random forest model performs calculation based on the sample label; generating a user screening strategy based on the path from the root node to the leaf node in the random forest model, wherein each path from the root node to the leaf node is a rule in the user screening strategy. The path from the root node to the leaf node constitutes a rule, and a rule set is generated (for example, a rule set of a single variable, a combination of two variables, or a combination of three or more variables).

[0076] In S404, the random forest model calculation results are screened using the screening parameters, including: using the screening parameters to screen multiple paths from root nodes to leaf nodes. The screening parameter may be rule complexity, and rules with greater complexity may be deleted, for example.

[0077] In S406, a plurality of user screening strategies are generated according to the screening results, including: generating the plurality of user screening strategies through paths that meet the screening parameters.

[0078] In the prior art, only several parameters of the user strategy can be combined manually to generate a user screening strategy. The user screening strategy generated by the random forest decision tree can introduce more variables, thereby performing a more comprehensive analysis.

[0079] Figure 5 The figure is a flowchart of a method for generating a user screening strategy according to another exemplary embodiment. Figure 5 The process 50 shown is for Figure 2 The process shown is a detailed description of S208 "Extracting a target user screening policy from the multiple user screening policies based on a preset standard".

[0080] like Figure 5 As shown, in S502, the number of identical rules in the multiple user screening policies is calculated.

[0081] In S504, the plurality of user screening policies are sorted according to the number of identical rules. It can be considered that if a rule is used the most, then this rule can be used by as many users as possible, and can screen users better. Each user policy contains a plurality of rules, and the number of identical rules is extracted. The user screening policies can be sorted according to the number of identical rules they contain.

[0082] In S506, the number of rules included in each of the multiple user screening policies is calculated.

[0083] In S508, the complexity of the user screening strategy is determined according to the number. It can be considered that the user screening strategy containing the most rules has many corresponding operations and complex logic, which may cause other system problems. It can be considered that the simpler the user screening strategy, the more it meets the requirements.

[0084] In S510, the plurality of user screening strategies are sorted from small to large based on the complexity.

[0085] In S512, a target user screening strategy is extracted according to the ranking.

[0086] In one embodiment, the number of repetitions of each rule is n, the coverage and risk level are multiples of the input standard p, the complexity of the rule is c,

[0087] p=(coverage threshold / (coverage threshold+risk rate threshold) / risk rate threshold / 2;

[0088] r = n*p / c can be used to represent the evaluation value of the user screening strategy. The higher the value, the more applicable the user screening strategy is to more users.

[0089] Those skilled in the art will appreciate that all or part of the steps for implementing the above embodiments are implemented as a computer program executed by a CPU. When the computer program is executed by the CPU, the above functions defined by the above method provided by the present disclosure are performed. The program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0090] In addition, it should be noted that the above figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0091] The following are embodiments of the device disclosed herein, which can be used to execute the method embodiments disclosed herein. For details not disclosed in the device embodiments disclosed herein, please refer to the method embodiments disclosed herein.

[0092] Figure 6 FIG. 1 is a block diagram of a user screening strategy generating device according to an exemplary embodiment. Figure 6 As shown, the user screening strategy generating device 60 includes: a target module 602 , a sample module 604 , a calculation module 606 , and a strategy module 608 .

[0093] The target module 602 is used to determine the user screening target, which includes the project category and the screening parameter;

[0094] The sample module 604 is used to extract multiple target users from historical users based on the project category to generate a user sample set; the sample module 604 includes: a criterion unit, used to determine the judgment criterion of the sample label based on the project category; a user unit, used to extract multiple target users from historical users based on the judgment criterion; and a collection unit, used to determine sample labels for the multiple target users to generate the user sample set.

[0095] The calculation module 606 is used to input the user sample set and the screening parameters into the policy model for calculation, and generate multiple user screening policies. The calculation module 606 includes: a calculation unit, which is used to input the user sample set into the random forest model for calculation; the calculation unit is also used to input the user sample set into the random forest model; the random forest model performs calculations based on sample labels; the user screening policy is generated based on the path from the root node to the leaf node in the random forest model, wherein each path from the root node to the leaf node is a rule in the user screening policy; a screening unit, which is used to filter the calculation results of the random forest model using the screening parameters; the screening unit is also used to filter multiple paths from the root node to the leaf node using the screening parameters; a result unit, which is used to generate multiple user screening policies according to the screening results. The result unit is also used to generate the multiple user screening policies through the paths that meet the screening parameters.

[0096] The policy module 608 is used to extract the target user screening policy from the multiple user screening policies based on a preset standard. The policy module 608 includes: a rule quantity unit, used to calculate the number of identical rules in the multiple user screening policies; sort the multiple user screening policies according to the number of identical rules to extract the target user screening policy. A complexity unit, used to calculate the number of rules contained in each user screening policy in the multiple user screening policies; determine the complexity of the user screening policy according to the number; sort the multiple user screening policies from small to large based on the complexity to extract the target user screening policy.

[0097] Figure 7 FIG. 1 is a block diagram of a user screening strategy generating device according to another exemplary embodiment. Figure 7 As shown, the user screening strategy generating device 70 includes: an application module 702 , a judgment module 704 , and a notification module 706 .

[0098] The application module 702 is used to receive resource quota applications from users;

[0099] The judgment module 704 is used to judge the resource quota application based on the target user screening strategy; the judgment module 704 is also used to obtain user information and application items from the credit application; and input the user information and application items into the target user screening strategy for judgment.

[0100] The notification module 706 is used to generate a return notification for the resource quota application based on the judgment result, and the return notification includes application approval or application rejection.

[0101] According to the user screening policy generating device disclosed in the present invention, a user screening target is determined, and the user screening target includes a project category and a screening parameter; based on the project category, multiple target users are extracted from historical users to generate a user sample set; the user sample set and the screening parameters are input into a policy model for calculation to generate multiple user screening policies; based on preset standards, a target user screening policy is extracted from the multiple user screening policies. This method can quickly and accurately generate user screening policies according to the goals set by the administrator, reduce labor costs, improve policy screening accuracy, speed up policy launch time, and timely identify risky users to ensure resource security.

[0102] Figure 8 It is a block diagram of an electronic device according to an exemplary embodiment.

[0103] Refer to the following Figure 8 The electronic device 800 according to this embodiment of the present disclosure is described. Figure 8 The electronic device 800 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0104] like Figure 8 As shown, the electronic device 800 is in the form of a general computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810), a display unit 840, etc.

[0105] The storage unit stores a program code, which can be executed by the processing unit 810, so that the processing unit 810 performs the steps in this specification according to various exemplary embodiments of the present disclosure. For example, the processing unit 810 can perform the following steps: Figure 2 , Figure 3 , Figure 4 , Figure 5 Follow the steps shown in .

[0106] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 8201 and / or a cache memory unit 8202 , and may further include a read-only memory unit (ROM) 8203 .

[0107] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0108] Bus 830 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0109] The electronic device 800 may also communicate with one or more external devices 800' (e.g., keyboards, pointing devices, Bluetooth devices, etc.) so that a user can communicate with the device that interacts with the electronic device 800, and / or the electronic device 800 can communicate with any device (e.g., routers, modems, etc.) that communicates with one or more other computing devices. Such communication may be performed through an input / output (I / O) interface 850. In addition, the electronic device 800 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter 860. The network adapter 860 may communicate with other modules of the electronic device 800 through a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0110] Through the above description of the implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by combining software with necessary hardware. Fig. 9 As shown, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the above method according to the embodiment of the present disclosure.

[0111] The software product may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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 thereof.

[0112] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0113] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0114] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by a device, the computer-readable medium implements the following functions: determining a user screening target, wherein the user screening target includes an item category and a screening parameter; extracting multiple target users from historical users based on the item category to generate a user sample set; inputting the user sample set and the screening parameters into a strategy model for calculation to generate multiple user screening strategies; and extracting a target user screening strategy from the multiple user screening strategies based on preset criteria.

[0115] Those skilled in the art will appreciate that the above modules can be distributed in the device according to the description of the embodiment, or can be changed accordingly and only used in one or more devices different from the embodiment. The modules of the above embodiments can be combined into one module, or further divided into multiple sub-modules.

[0116] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiment of the present disclosure.

[0117] The exemplary embodiments of the present disclosure are specifically shown and described above. It should be understood that the present disclosure is not limited to the detailed structures, configurations or implementations described herein; on the contrary, the present disclosure is intended to cover various modifications and equivalent configurations included in the spirit and scope of the appended claims.

Claims

1. A method for generating a user screening strategy, characterized in that: include: Determine the user screening target, the user screening target includes project category and screening parameters, the screening parameters include: default risk rate, sample coverage rate, coverage rate threshold, risk rate threshold, number of variable combination results, depth of tree model, and rule complexity of generated rules; Determine a criterion for sample labels based on the item category; Extracting multiple target users from historical users based on the judgment criteria; Determining sample labels for the multiple target users to generate a user sample set; Inputting the user sample set into a random forest model; The random forest model is calculated based on sample labels; Generate a user screening strategy based on the path from the root node to the leaf node in the random forest model, wherein each segment of the path from the root node to the leaf node is a rule in the user screening strategy; Filtering multiple paths from root nodes to leaf nodes using the filtering parameters, and deleting paths that do not meet the range specified by the filtering parameters; generating a plurality of user screening strategies according to the screening results; Calculating the number of identical rules in the plurality of user screening policies; sorting the plurality of user screening strategies according to the number of identical rules; Calculating the number of rules included in each of the plurality of user screening policies; The complexity of the user screening strategy is determined according to the number; wherein the number of repetitions of each rule is n, the coverage and risk level are multiples of the input standard p, the complexity of the rule is c, p=coverage threshold / (coverage threshold+risk rate threshold) / risk rate threshold / 2; r = n*p / c; r is the evaluation value of the user screening strategy; Sort the plurality of user screening strategies in ascending order based on the complexity; Extract target user filtering strategies based on sorting.

2. The method according to claim 1, characterized in that Also includes: Receive resource quota applications from users; Judging the resource quota application based on the target user screening strategy; A return notification is generated for the resource quota application based on the judgment result, and the return notification includes approval or rejection of the application.

3. The method according to claim 2, characterized in that The resource quota application is judged based on the target user screening strategy, including: Obtain user information and application items from the credit application; The user information and the application items are input into the target user screening strategy for determination.

4. A user screening strategy generating device, characterized in that: include: The target module is used to determine the user screening target, which includes the project category and screening parameters. The screening parameters include: default risk rate, sample coverage rate, coverage rate threshold, risk rate threshold, number of variable combination results, depth of tree model, and complexity of generated rules; A sample module is used to determine a judgment criterion for sample labels based on the item category; extract multiple target users from historical users based on the judgment criterion; determine sample labels for the multiple target users to generate a user sample set; A calculation module is used to input the user sample set into a random forest model; the random forest model performs calculations based on sample labels; a user screening strategy is generated based on the path from the root node to the leaf node in the random forest model, wherein each path from the root node to the leaf node is a rule in the user screening strategy; multiple paths from the root node to the leaf node are screened using the screening parameters, and paths that do not meet the specified range of the screening parameters are deleted; and multiple user screening strategies are generated according to the screening results; A policy module is used to calculate the number of identical rules in the multiple user screening policies; sort the multiple user screening policies according to the number of identical rules; calculate the number of rules contained in each of the multiple user screening policies; determine the complexity of the user screening policies according to the number; wherein the number of repetitions of each rule is n, the coverage rate and the risk level are multiples p of the input standard, the complexity of the rule is c, p=coverage rate threshold / (coverage rate threshold+risk rate threshold) / risk rate threshold / 2; r=n*p / c; r is the evaluation value of the user screening policy; sort the multiple user screening policies from small to large based on the complexity; and extract the target user screening policy according to the sorting.

5. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 3.

6. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images