A method, apparatus, and electronic device for screening users

Abstract

The present invention discloses a method, device, electronic device and computer-readable medium for screening users, including: obtaining user data and creating a user risk profile; dividing users into multiple customer groups according to the user risk profile; constructing risk rules and filtering users in the multiple customer groups according to the risk rules; splitting users in the filtered customer groups to form customer group blocks; and screening the customer group blocks according to the revenue and risk data of the customer group blocks to complete user screening. The present invention can divide customer groups through the user risk profile, and screen users in different customer groups by combining risk rules and user behavior scores, so as to achieve accurate risk control.

Description

Technical Field

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

[0002] In the prior art, when adjusting the quota by screening target customers, financial platforms often focus on the risk level of target customers and use a unified policy threshold for verification. The risk quality of the selected top customers in the prior art is indeed good, but the coverage rate compared to all customers is low, the promotion effect on the disbursement amount is relatively limited, and it is not conducive to the long-term optimization of the overall risk level and the promotion of business income after disbursement. Summary of the Invention

[0003] The technical problem to be solved by the present invention is how to optimize the overall risk and income while improving the passing rate of user screening.

[0004] One aspect of the present invention provides a method for screening users, which is characterized by including: obtaining user data and creating a user risk profile; dividing users into multiple customer groups according to the user risk profile; constructing risk rules and filtering users in the multiple customer groups according to the risk rules; splitting users in the filtered customer groups to form customer group blocks; screening the customer group blocks according to the income and risk data of the customer group blocks to complete user screening.

[0005] According to a preferred embodiment of the present invention, the obtaining user data and creating a user risk profile further includes: obtaining user data; dividing the user data into data of multiple dimensions; establishing different user tags for data of different dimensions; and creating a user risk profile based on the different user tags.

[0006] According to a preferred embodiment of the present invention, the multiple dimensions further include at least one of an attribute dimension, a behavior dimension, a risk dimension, and a model scoring dimension.

[0007] According to a preferred embodiment of the present invention, the dividing users into multiple customer groups according to the user risk profile further includes: selecting user tags; establishing a grouping rule based on the selected user tags; analyzing the user risk profile according to the grouping rule, and dividing users into multiple customer groups.

[0008] According to a preferred embodiment of the present invention, the constructing risk rules further includes: constructing strong risk rules for excluding users in the customer group.

[0009] According to a preferred embodiment of the present invention, it further includes: constructing weak risk rules for differentiating users in the customer group.

[0010] According to a preferred embodiment of the present invention, users in the segmented and filtered customer group form customer group blocks, and it further includes: obtaining user behavior scores, and segmenting users in the segmented and filtered customer group according to the user behavior scores to form customer group blocks.

[0011] According to a preferred embodiment of the present invention, segmenting users in the segmented and filtered customer group according to the user behavior scores to form customer group blocks further includes: sorting users in the filtered customer group according to the level of the user behavior scores; segmenting users in the filtered customer group according to the sorting result to form customer group blocks.

[0012] According to a preferred embodiment of the present invention, it further includes: obtaining the revenue and risk data of the customer group blocks; adjusting the user behavior scores to make the revenue and risk data of the customer group blocks conform to monotonicity.

[0013] A second aspect of the present invention provides a device for screening users, which is characterized in that it includes: a user data acquisition module for acquiring user data and creating a user risk profile; a customer group division module for dividing users into multiple customer groups according to the user risk profile; a risk rule construction and use module for constructing risk rules and filtering users in the multiple customer groups according to the risk rules; a customer group block generation module for segmenting users in the filtered customer group to form customer group blocks; a customer group block screening module for screening the customer group blocks according to the revenue and risk data of the customer group blocks to complete user screening.

[0014] According to a preferred embodiment of the present invention, the user data acquisition module further includes: a user data acquisition unit for acquiring user data; a user data division unit for dividing the user data into data of multiple dimensions; a user label establishment unit for establishing different user labels for data of different dimensions; a user risk profile creation unit for creating a user risk profile based on the different user labels.

[0015] According to a preferred embodiment of the present invention, the multiple dimensions further include at least one of an attribute dimension, a behavior dimension, a risk dimension, and a model score dimension.

[0016] According to a preferred embodiment of the present invention, the customer group division module further includes: a user tag selection unit for selecting user tags; a grouping rule establishment unit for establishing grouping rules based on the selected user tags; and a grouping rule usage unit for analyzing the user risk profile according to the grouping rules and dividing users into multiple customer groups.

[0017] According to a preferred embodiment of the present invention, the risk rule construction and usage module further includes: a strong risk rule construction unit for constructing strong risk rules, which are used to eliminate users in the customer group.

[0018] According to a preferred embodiment of the present invention, it further includes: a weak risk rule construction unit for constructing weak risk rules, which are used to perform differential processing on users in the customer group.

[0019] According to a preferred embodiment of the present invention, the customer group block generation module further includes: a customer group block generation unit for obtaining user behavior scores and segmenting users in the filtered customer group according to the user behavior scores to form customer group blocks.

[0020] According to a preferred embodiment of the present invention, the customer group block generation unit further includes: a user sorting subunit for sorting users in the filtered customer group according to the level of the user behavior scores; and a user segmentation subunit for segmenting users in the filtered customer group according to the sorting result to form customer group blocks.

[0021] According to a preferred embodiment of the present invention, it further includes: a revenue and risk data acquisition unit for acquiring the revenue and risk data of the customer group blocks; and a behavior score adjustment unit for adjusting the user behavior scores so that the revenue and risk data of the customer group blocks conform to monotonicity.

[0022] A third aspect of the present invention provides an electronic device, wherein the electronic device includes: a processor; and,

[0023] a memory storing computer-executable instructions, and the executable instructions, when executed, cause the processor to execute any one of the methods.

[0024] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, any one of the methods is implemented.

[0025] The technical solution of the present invention has the following beneficial effects:

[0026] The present invention groups users by creating user risk profiles, which is conducive to configuring differentiated screening strategies according to the characteristics of each customer group, so as to achieve the purpose of refined operation.

[0027] The present invention realizes differentiated screening strategies for the characteristics of each customer group by constructing strong risk rules and weak risk rules.

[0028] The present invention divides customer groups by using user behavior scores, making the risks and returns of the divided blocks show monotonicity, and then achieving the effect of optimizing the overall risks and returns. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to make the technical problems solved by the present invention, the technical means adopted and the technical effects obtained clearer, the specific embodiments of the present invention will be described in detail below with reference to the drawings. It should be noted that the drawings described below are only the drawings of the exemplary embodiments of the present invention, and those skilled in the art can obtain the drawings of other embodiments based on these drawings without creative efforts.

[0030] Figure 1 It is a schematic flowchart of a method for screening users according to the present invention;

[0031] Figure 2 It is a schematic flowchart of creating a user risk profile of a method for screening users according to the present invention;

[0032] Figure 3 It is a schematic diagram of a user risk profile of a method for screening users according to the present invention;

[0033] Figure 4 It is a schematic diagram of the module architecture of a device for screening users according to the present invention;

[0034] Figure 5 It is a schematic diagram of the architecture of a user data acquisition module of a device for screening users according to the present invention;

[0035] Figure 6 It is a schematic diagram of the structural framework of an electronic device for screening users according to the present invention;

[0036] Figure 7 It is a schematic diagram of a computer-readable storage medium according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. However, exemplary embodiments can be implemented in a variety of forms, and should not be construed as limiting the present invention to the embodiments set forth herein. On the contrary, providing these exemplary embodiments enables the present invention to be more comprehensive and complete, and is more convenient for fully conveying the inventive concept to those skilled in the art. The same reference numerals in the figures represent the same or similar elements, components or parts, and thus their repeated description will be omitted.

[0038] Under the premise of being consistent with the technical concept of the present invention, the features, structures, characteristics or other details described in a specific embodiment do not exclude that they can be combined in one or more other embodiments in a suitable manner.

[0039] In the description of specific embodiments, the features, structures, characteristics or other details described in the present invention are intended to enable those skilled in the art to fully understand the embodiments. However, it does not exclude that those skilled in the art can practice the technical solutions of the present invention without one or more of the specific features, structures, characteristics or other details.

[0040] 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.

[0041] 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.

[0042] It should be understood that although the terms "first", "second", "third", etc. may be used herein to describe various devices, elements, components or parts, this should not be limited by these terms. These terms are used to distinguish one from another. For example, a first device may also be called a second device without departing from the essential technical solution of the present invention.

[0043] The term "and / or" or "and / or" includes any one and all combinations of one or more of the associated listed items.

[0044] In the prior art, when screening target customers according to business characteristics, only variables in a single dimension are often emphasized. For example, when a financial platform adjusts the credit limit by screening target customers, it often only focuses on the risk level of the target customers, while ignoring variables in other dimensions, resulting in a waste of a large amount of data. Although the use of a single variable in the prior art results in relatively good risk quality for the selected top customers, the coverage rate compared to all customers is low, the promoting effect on the disbursement amount is relatively limited, and it is not conducive to long-term optimization of the overall risk level and the business income after promoting disbursement.

[0045] There is a problem of relatively coarse screening granularity in the prior art when screening target users.

[0046] The present invention obtains user data, divides the user data into data in multiple dimensions, and avoids using data in a single dimension.

[0047] In addition, the present invention further includes steps such as constructing a user risk profile, dividing the user risk profile into customer groups, and screening users in different customer groups by combining risk rules and user behavior scores, so as to achieve precise screening of target users, and further realize the control of risks and benefits.

[0048] Figure 1 It is a schematic flow chart of a method for screening users according to the present invention; as Figure 1 shown, the method of the present invention at least includes steps S101 to S105.

[0049] S101: Obtain user data and create a user risk profile.

[0050] As Figure 2 shown, Figure 2 It is a schematic flow chart of creating a user risk profile of a method for screening users according to the present invention. Among them, the obtaining of user data and creating a user risk profile further includes: obtaining user data; dividing the user data into data in multiple dimensions; establishing different user tags for data in different dimensions; and creating a user risk profile based on the different user tags.

[0051] Among them, the multiple dimensions further include at least one of an attribute dimension, a behavior dimension, a risk dimension, and a model scoring dimension.

[0052] As an example, user data is obtained from various data sources. Among them, data such as age, gender, education level, location, occupation, and income of users is obtained through a job hunting platform; data such as online shopping software login time, online shopping software login frequency, online shopping product type, online shopping product price, and monthly online shopping consumption amount is obtained through an online shopping platform; data such as the number of overdue times, overdue days, selected installment periods, platform loan frequency, and AI model score is obtained through a financial platform.

[0053] Divide the above - obtained data into dimensions such as attribute data, behavior data, risk data, and model scoring data.

[0054] Among them, the model scoring data at least includes: AI model scoring.

[0055] Establish different machine - learning models for attribute data, behavior data, and risk data, which are used to output scores for data of different dimensions, and obtain user labels according to the scores.

[0056] As an example, the attribute - type scoring model can be implemented through regression analysis, decision trees, artificial neural networks, support vector machines, K - Means, association rules, and / or time - series pattern algorithms. When inputting user attribute data, the probability of an attribute being yes or no can be obtained as the attribute - type score. For users with an attribute of yes, the user score is 1, and corresponding user labels are assigned; for users with an attribute of no, the user score is 0, and no corresponding user labels are assigned.

[0057] The construction processes of the behavior - type scoring model and the risk - type scoring model are similar to that of the attribute - type scoring model, and are not elaborated herein.

[0058] As an example, Figure 3 is a schematic diagram of a user risk profile for a method of screening users according to the present invention; as Figure 3 shown, the obtained user labels include attributes, behaviors, risks, AI model scoring, etc., and then a user risk profile is created according to the above - obtained labels.

[0059] S102: Divide users into multiple customer groups according to the user risk profile.

[0060] Among them, dividing users into multiple customer groups according to the user risk profile further includes: selecting user labels; establishing a grouping rule based on the selected user labels; analyzing the user risk profile according to the grouping rule, and dividing users into multiple customer groups.

[0061] As an example, select four labels: attribute yes, attribute no, high risk, and low risk; based on the four labels of good attribute, bad attribute, high risk, and low risk, establish a grouping rule. The grouping rule can be: users with an attribute of yes and high risk are classified into customer group A, users with an attribute of no and high risk are classified into customer group B, users with an attribute of yes and low risk are classified into customer group C, and users with an attribute of no and low risk are classified into customer group D. According to the established grouping rule, all users can be divided into four types: customer group A, customer group B, customer group C, and customer group D.

[0062] S103: Construct a risk rule and filter users in the multiple customer groups according to the risk rule.

[0063] Among them, constructing risk rules further includes: constructing strong risk rules, which are used to eliminate users in the customer group.

[0064] Among them, constructing weak risk rules, which are used to differentiate users in the customer group.

[0065] As an example, uniformly eliminate users who meet the strong risk rules from each customer group. The strong risk rules are those that are completely not passed, that is, the hard conditions of the user, indicating that the user has a great risk. For example, a user in customer group A has overdue 100 times, and the risk of the user is extremely high. Use the strong risk rules to eliminate this user from customer group A.

[0066] After applying the strong risk rules to each customer group, it is necessary to analyze the weak risk rules for each customer group separately. Since the attributes of each customer group are different, the weak risk rules do not show effective discrimination for each type of customer group. Only use the weak risk rules for individual customer groups to show the differential strategy of customer segmentation.

[0067] The weak risk rules do not eliminate customers and are only used as a differential adjustment strategy for customer groups. For example: for the rule of having or not having a degree, the corresponding risk values are 0.3% and 0.5%. Then, customers with a degree have a higher adjustment amplitude, and customers without a degree have a lower adjustment amplitude.

[0068] S104: Segment users in the filtered customer group to form customer group blocks.

[0069] Among them, segmenting users in the filtered customer group to form customer group blocks further includes:

[0070] Obtain the user behavior score, and segment users in the filtered customer group according to the user behavior score to form customer group blocks.

[0071] Further, segmenting users in the filtered customer group according to the user behavior score to form customer group blocks further includes: sorting users in the filtered customer group according to the level of the user behavior score; segmenting users in the filtered customer group according to the sorting result to form customer group blocks.

[0072] As an example, use the Behavior score card to obtain the user behavior score, sort users in the filtered customer group from high to low according to the user behavior score, and segment users in the filtered customer group according to the sorting result to form customer group blocks.

[0073] Since the user behavior score has the finest granularity among other strategies such as strong risk and weak risk rules, as the last fallback rule, it is beneficial to segment the customer group into small blocks.

[0074] Wherein, the method of the present invention further includes: obtaining the revenue and risk data of the customer group segmentation; and making the revenue and risk data of the customer group segmentation conform to monotonicity by adjusting the user behavior score.

[0075] S105: Screen the customer group segmentation according to the revenue and risk data of the customer group segmentation to complete user screening.

[0076] Evaluate the actual risk performance and actual cash flow performance corresponding to each customer group segmentation. Based on the stability after customer segmentation and the superiority of the behavior scoring model, each customer group segmentation divided from high to low according to the behavior score should present a monotonic trend of revenue and risk. Eliminate the small blocks with unqualified revenue or higher overall risk, or adjust the strategy to make the revenue and risk present monotonicity, and a customer group screening result based on break-even and optimized risk can be obtained.

[0077] Finally, according to the screening results obtained in steps S10S to 105, the strategy maker can balance scale, risk, and revenue based on their business goals (such as KPI goals) on this basis, so as to formulate multiple sets of risk control screening strategies based on different business goals.

[0078] By creating a user risk profile to segment users, the present invention is conducive to configuring differentiated screening strategies according to the characteristics of each customer group, so as to achieve the purpose of refined operation.

[0079] By constructing strong risk rules and weak risk rules, the present invention realizes differentiated screening strategies for the characteristics of each customer group.

[0080] By using the user behavior score to segment the customer group, the risk and revenue of the segmentation present monotonicity, thereby achieving the effect of optimizing the overall risk and revenue.

[0081] Those skilled in the art can understand that all or part of the steps of implementing the above embodiments are realized as a program (computer program) executed by a computer data processing device. When the computer program is executed, the above method provided by the present invention can be realized. Moreover, the computer program can be stored in a computer-readable storage medium, and the storage medium can be a readable storage medium such as a disk, an optical disc, a ROM, a RAM, or a storage array composed of multiple storage media, such as a disk or tape storage array. The storage medium is not limited to centralized storage, and it can also be distributed storage, such as cloud storage based on cloud computing.

[0082] The device embodiments of the present invention are described below, and the device can be used to execute the method embodiments of the present invention. For the details described in the device embodiments of the present invention, they should be regarded as a supplement to the above method embodiments; for the details not disclosed in the device embodiments of the present invention, they can be implemented with reference to the above method embodiments.

[0083] Those skilled in the art can understand that each module in the above device embodiments can be distributed in the device as described, or can be correspondingly changed and distributed in one or more devices different from the above embodiments. The modules of the above embodiments can be combined into one module, or can be further split into multiple sub-modules.

[0084] Figure 4 is a schematic diagram of the module architecture of a device for screening users according to the present invention; as Figure 4 shown, the device 400 of the present invention includes a user data acquisition module 401, a customer group division module 402, a risk rule construction and use module 403, a customer group block generation module 404, and a customer group block screening module 405.

[0085] The user data acquisition module 401 is used to acquire user data and create a user risk profile.

[0086] The customer group division module 402 is used to divide users into multiple customer groups according to the user risk profile.

[0087] The risk rule construction and use module 403 is used to construct risk rules and filter users in the multiple customer groups according to the risk rules.

[0088] The customer group block generation module 404 is used to divide users in the filtered customer groups to form customer group blocks.

[0089] The customer group block screening module 405 is used to screen the customer group blocks according to the revenue and risk data of the customer group blocks to complete user screening.

[0090] Figure 5 is a schematic diagram of the architecture of the user data acquisition module of a device for screening users according to the present invention; as Figure 5 shown, the user data acquisition module 401 further includes: a user data acquisition unit 501, a user data division unit 502, a user label establishment unit 503, and a user risk profile creation unit 504.

[0091] The user data acquisition unit 501 is used to acquire user data.

[0092] The user data division unit 502 is used to divide the user data into data of multiple dimensions.

[0093] The user label establishment unit 503 is used to establish different user labels for data of different dimensions.

[0094] The user risk profile creation unit 504 is used to create a user risk profile based on the different user labels.

[0095] Among them, the multiple dimensions further include at least one of an attribute dimension, a behavior dimension, a risk dimension, and a model scoring dimension.

[0096] Among them, the customer group division module further includes: a user label selection unit for selecting user labels; a grouping rule establishment unit for establishing grouping rules based on the selected user labels; and a grouping rule use unit for analyzing the user risk profile according to the grouping rules and dividing users into multiple customer groups.

[0097] Among them, the risk rule construction and use module further includes: a strong risk rule construction unit for constructing strong risk rules, which are used to eliminate users in the customer group.

[0098] Among them, it further includes: a weak risk rule construction unit for constructing weak risk rules, which are used to perform differential processing on users in the customer group.

[0099] Among them, the customer group block generation module further includes: a customer group block generation unit for obtaining user behavior scores and dividing users in the filtered customer group according to the user behavior scores to form customer group blocks.

[0100] Among them, the customer group block generation unit further includes: a user sorting subunit for sorting users in the filtered customer group according to the level of the user behavior scores; and a user division subunit for dividing users in the filtered customer group according to the sorting result to form customer group blocks.

[0101] Among them, the device of the present invention further includes: a revenue and risk data acquisition unit for acquiring the revenue and risk data of the customer group blocks; and a behavior score adjustment unit for adjusting the user behavior scores to make the revenue and risk data of the customer group blocks conform to monotonicity.

[0102] An embodiment of an electronic device of the present invention is described below. This electronic device can be regarded as a specific physical implementation manner of the above method and device embodiments of the present invention. For the details described in the embodiment of the electronic device of the present invention, they should be regarded as a supplement to the above method or device embodiments; for the details not disclosed in the embodiment of the electronic device of the present invention, they can be implemented with reference to the above method or device embodiments.

[0103] Figure 6 It is a schematic structural framework diagram of an electronic device for screening users according to the present invention. The following refers to Figure 6 to describe the electronic device 600 according to this embodiment of the present invention. Figure 6 The electronic device 600 shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention.

[0104] As Figure 6 shown, the electronic device 600 is presented in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0105] Among them, the storage unit stores program code, and the program code can be executed by the processing unit 610, so that the processing unit 610 executes the steps according to various exemplary embodiments of the present invention described in the above-mentioned electronic prescription transfer processing method part of this specification. For example, the processing unit 610 can execute as Figure 1 shown in the steps.

[0106] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 6201 and / or a cache storage unit 6202, and may further include a read-only storage unit (ROM) 6203.

[0107] The storage unit 620 may further include a program / utility 6204 having a set (at least one) of program modules 6205. Such program modules 6205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0108] The bus 630 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any bus structure in a variety of bus structures.

[0109] The electronic device 600 can also communicate with one or more external devices 700 (such as a keyboard, a pointing device, a Bluetooth device, etc.), and can also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication can be carried out through the input / output (I / O) interface 650. Moreover, the electronic device 600 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 660. The network adapter 660 can communicate with other modules of the electronic device 600 through the bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 600, 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 description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described in the present invention can be implemented by software, or can be implemented by the way of software combined with necessary hardware. Therefore, the technical solutions according to the embodiments of the present invention can be embodied in the form of a software product, and the software product can be stored in a computer-readable storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on the network, including several 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 present invention. When the computer program is executed by a data processing device, the computer-readable medium can implement the above method of the present invention, that is: obtain user data and create a user risk profile; divide users into multiple customer groups according to the user risk profile; construct risk rules and filter users in the multiple customer groups according to the risk rules; segment users in the filtered customer groups to form customer group blocks; screen the customer group blocks according to the revenue and risk data of the customer group blocks to complete user screening.

[0111] The computer program can be stored on one or more computer-readable media, such as Figure 7As shown. The computer-readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having 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 of the above.

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

[0113] The program code for performing the operations of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages - such as Java, C++, etc., and also including conventional procedural programming languages - such as the "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, executed as a stand-alone 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 can 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, it can be connected to an external computing device (for example, by using an Internet service provider to connect through the Internet).

[0114] In summary, the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that general-purpose data processing devices such as microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the embodiments of the present invention. The present invention can also be implemented as a device or device program (e.g., a computer program and a computer program product) for executing some or all of the methods described herein. Such a program for implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or in any other form.

[0115] The specific embodiments described above further elaborate on the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the present invention is not inherently related to any specific computer, virtual device, or electronic device, and various general-purpose devices can also implement the present invention. The above are only specific embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

[0116] Program code for performing the operations of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's 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 can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., by using an Internet service provider to connect through the Internet).

[0117] In summary, the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that general-purpose data processing devices such as microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing some or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or in any other form.

[0118] In the specific embodiments described above, the objectives, technical solutions and beneficial effects of the present invention have been further described in detail. It should be understood that the present invention is not inherently related to any specific computer, virtual device or electronic device, and various general-purpose devices can also implement the present invention. The above are only specific embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for screening users, characterized in that, including: Obtain user data and divide the user data into data of multiple dimensions; Establish different scoring models for data of different dimensions to output scores corresponding to data of different dimensions, determine different user labels corresponding to data of different dimensions according to the scores of data of different dimensions, and create a user risk profile according to different user labels; Divide users into multiple customer groups according to the user risk profile; Construct risk rules and filter users in the multiple customer groups according to the risk rules, including: constructing strong risk rules, which are rules that are completely not passed and are used to eliminate users in the customer group; and constructing weak risk rules. After uniformly using the strong risk rules to eliminate users who meet the strong risk rules in each customer group, then use the weak risk rules to analyze users in individual customer groups according to the different attributes of each customer group to only perform differential amplitude adjustment processing without eliminating users; Obtain user behavior scores using a Behavior score card, sort users in the filtered customer group according to the level of the user behavior scores with the finest granularity, and divide users in the filtered customer group according to the sorting result to form customer group blocks; Screen the customer group blocks according to the revenue and risk data of the customer group blocks to complete user screening.

2. The method according to claim 1, characterized in that, Establish different scoring models for data of different dimensions to output scores corresponding to data of different dimensions, and determine user labels corresponding to data of different dimensions according to the scores of data of different dimensions, including: For attribute data, establish an attribute class scoring model to output the score of the attribute data; For behavior data, establish a behavior class scoring model to output the score of the behavior data; For risk data, establish a risk class scoring model to output the score of the risk data; The model scoring data includes AI model scores; Each of the different scoring models is a machine learning model; Determine the label of the user through the scores of attribute data, behavior data, risk data, and AI model scores.

3. The method according to claim 1, wherein The dividing users into multiple customer groups according to the user risk profile includes: Select user labels; Based on the selected user labels, establish grouping rules; Analyze the user risk profile according to the grouping rules and divide users into multiple customer groups.

4. The method according to claim 1, characterized in that It also includes: The granularity of the user behavior score is the finest compared to the strong risk rules and the weak risk rules.

5. The method according to claim 1, characterized in that, It also includes: Obtain the revenue and risk data of the customer group blocks; Adjust the user behavior scores to make the revenue and risk data of the customer group blocks conform to monotonicity.

6. A device for screening users, characterized in that, including: A user data acquisition module, including: A user data acquisition unit that acquires user data; A user data division unit that divides user data into data of multiple dimensions; A user label establishment unit that establishes different scoring models for data of different dimensions to output scores corresponding to data of different dimensions, and determines different user labels corresponding to data of different dimensions according to the scores of data of different dimensions; A user risk profile creation unit that creates a user risk profile according to different user labels; A customer group division module, configured to divide users into multiple customer groups according to the user risk profiles; A risk rule construction and usage module, configured to construct risk rules and filter users in the multiple customer groups according to the risk rules, including: A strong risk rule construction unit, which constructs strong risk rules. The strong risk rules are rules that are completely not passed and are used to eliminate users in the customer groups; A weak risk rule construction unit, which constructs weak risk rules. After using the strong risk rules to eliminate users who meet the strong risk rules in each customer group uniformly, the weak risk rules are used to analyze users in individual customer groups according to the different attributes of each customer group for differential amplitude adjustment processing without eliminating users; A customer group block generation module, including: a customer group block generation unit, configured to obtain user behavior scores using a Behavior score card; a user sorting sub-unit, configured to sort users in the filtered customer group according to the level of the most detailed user behavior scores; a user splitting sub-unit, configured to split users in the filtered customer group according to the sorting result to form customer group blocks; A customer group block screening module, configured to screen the customer group blocks according to the revenue and risk data of the customer group blocks to complete user screening.

7. The device according to claim 6, characterized in that, A user label establishment unit, specifically further including: Establishing an attribute class scoring model for attribute data to output scores of the attribute data; Establishing a behavior class scoring model for behavior data to output scores of the behavior data; Establishing a risk class scoring model for risk data to output scores of the risk data; The model scoring data includes AI model scores; Each of the different scoring models is a machine learning model; Determining the label of the user through the scores of the attribute data, the scores of the behavior data, the scores of the risk data, and the AI model scores.

8. The device according to claim 6, characterized in that, The customer group division module, Specifically includes: A user label selection unit, configured to select user labels; A grouping rule establishment unit, configured to establish grouping rules based on the selected user labels; A grouping rule usage unit, configured to analyze the user risk profiles according to the grouping rules and divide users into multiple customer groups.

9. The device according to claim 6, characterized in that The customer group block generation unit specifically further includes: The granularity of the user behavior scores is the most detailed compared to the strong risk rules and the weak risk rules.

10. The device according to claim 6, characterized in that, It further includes: A revenue and risk data acquisition unit, configured to acquire the revenue and risk data of the customer group blocks; A behavior score adjustment unit, configured to make the revenue and risk data of the customer group blocks conform to monotonicity by adjusting the user behavior scores.

11. An electronic device, wherein, The electronic device includes: A processor; and, A memory storing computer-executable instructions, where the executable instructions, when executed, cause the processor to execute the method according to any one of claims 1-5.

12. A computer-readable storage medium, wherein, The computer-readable storage medium stores one or more programs, and when the one or more programs are executed by the processor, the method according to any one of claims 1-5 is implemented.

Images