Target user determination method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a target user determination method and device, electronic equipment and a storage medium. The method can be used in artificial intelligence field. The method comprises the steps of obtaining preprocessed data of a plurality of users, performing triple screening processing on the plurality of users according to the data of the plurality of users based on a pre-trained extreme gradient lifting model to obtain a first white list comprising the users meeting a target screening condition, the target screening condition is determined according to different financial data and / or user attribute information, the users which are not in the first white list but conform to the target screening condition are scooped back to obtain a second white list, and the users in the second white list are determined target users. According to the method, the intelligent degree and efficiency of determining the target user are improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, electronic device and storage medium for determining a target user. Background Art

[0002] In the financial field, in order to improve the quality of customer service, business services that are adapted to the target users are usually provided. Artificial intelligence technology can be used to accurately identify the target users, thereby improving service efficiency.

[0003] In the related art, when determining target users from a large number of users, business personnel are required to formulate screening rules based on their own experience and manually screen out target users based on the business data of each user.

[0004] However, the above method of determining target users has a low level of intelligence and poor screening efficiency. Summary of the invention

[0005] The embodiments of the present application provide a method, device, electronic device and storage medium for determining a target user, so as to achieve the technical effect of improving the intelligence and efficiency of the method for determining a target user.

[0006] In a first aspect, an embodiment of the present application provides a method for determining a target user, including:

[0007] Acquire pre-processed data of multiple users, the data including user attribute information and financial data;

[0008] Based on the pre-trained extreme gradient boosting model, the multiple users are triple-screened according to the data of the multiple users to obtain a first whitelist including users meeting a target screening condition, wherein the target screening condition is determined according to different financial data and / or user attribute information;

[0009] Users who are not in the first whitelist but meet the target screening condition are retrieved to obtain a second whitelist, and the users in the second whitelist are the determined target users.

[0010] In a possible implementation, the pre-trained extreme gradient boosting model performs triple screening on the multiple users according to the data of the multiple users to obtain a first whitelist including users meeting the target screening conditions, including:

[0011] performing a first screening process on the multiple users according to the data of the multiple users, and screening out a first user that meets a first target screening condition from the multiple users, where the first target screening condition is determined according to the first financial data and / or the first user attribute information;

[0012] Based on a preset scoring algorithm, a second screening process is performed on the first user to screen out a second user who meets a second target screening condition from the first user, where the second target screening condition is determined according to the second financial data and / or the second user attribute information;

[0013] Performing a third screening process on the second users, screening out third users that meet a third target screening condition from the second users, where the third target screening condition is determined based on third financial data and / or third user attribute information;

[0014] The first whitelist is generated and obtained according to the third user.

[0015] In a possible implementation, performing a second screening process on the first users based on a preset scoring algorithm to screen out second users meeting a second target screening condition from the first users includes:

[0016] Based on a preset first scoring algorithm and according to the data of the first user, calculating a first score of the first user on a preset first object feature;

[0017] Based on a preset second scoring algorithm, and according to the data of the first user, calculating a second score of the first user on a preset second object feature;

[0018] Based on a preset third scoring algorithm, and according to the data of the first user, calculating a third score of the first user on a preset third object feature;

[0019] A first user whose first score satisfies a preset first score threshold, whose second score satisfies a preset second score threshold, and whose third score satisfies a preset third score threshold is determined as the second user.

[0020] In a possible implementation, retrieving users who are not in the first whitelist but meet the target screening condition to obtain the second whitelist includes:

[0021] Acquire third users who meet the target screening condition within a preset time period;

[0022] Determining, according to the user attribute information of the third user, whether the third user is in the first whitelist;

[0023] If the third user is not in the first whitelist, the third user is added to the first whitelist to obtain the second whitelist.

[0024] In a possible implementation manner, after obtaining the second whitelist, the method further includes:

[0025] Get display permission;

[0026] According to the display permission, data of the target users in the second whitelist are displayed, and the data is data that is allowed to be displayed by the display permission.

[0027] In a possible implementation manner, obtaining pre-processed data of multiple users includes:

[0028] Acquiring original data of the multiple users;

[0029] For any user, the original data of the user is classified and preprocessed based on preset category features to obtain preprocessed data;

[0030] The preprocessed data of the multiple users is obtained.

[0031] In a second aspect, an embodiment of the present application provides a device for determining a target user, including:

[0032] An acquisition module, which acquires pre-processed data of multiple users, wherein the data includes user attribute information and financial data;

[0033] a processing module, configured to perform triple screening processing on the multiple users based on the pre-trained extreme gradient boosting model and the data of the multiple users, so as to obtain a first whitelist including users meeting a target screening condition, wherein the target screening condition is determined according to different financial data and / or user attribute information;

[0034] The processing module is further used to retrieve users who are not in the first whitelist but meet the target screening condition to obtain a second whitelist, and the users in the second whitelist are the determined target users.

[0035] In a possible implementation manner, the processing module is specifically configured to:

[0036] performing a first screening process on the multiple users according to the data of the multiple users, and screening out a first user that meets a first target screening condition from the multiple users, wherein the first target screening condition is determined according to the first financial data and / or the first user attribute information;

[0037] Based on a preset scoring algorithm, a second screening process is performed on the first user to screen out a second user who meets a second target screening condition from the first user, where the second target screening condition is determined according to the second financial data and / or the second user attribute information;

[0038] Performing a third screening process on the second users, screening out third users that meet a third target screening condition from the second users, where the third target screening condition is determined based on third financial data and / or third user attribute information;

[0039] The first whitelist is generated and obtained according to the third user.

[0040] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0041] The memory stores computer-executable instructions;

[0042] The processor executes the computer-executable instructions stored in the memory, so that the processor executes various possible implementations of the first aspect as described above.

[0043] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement various possible implementation methods of the first aspect above.

[0044] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements various possible implementation methods of the first aspect above.

[0045] The target user determination method, device, electronic device and storage medium provided in the embodiments of the present application obtain the data of multiple users after preprocessing, wherein the data includes user attribute information and financial data, and perform triple screening on multiple users based on the data of multiple users, based on the pre-trained extreme gradient boosting model, to obtain a first whitelist including users that meet the target screening conditions, wherein the target screening conditions are determined based on different financial data and / or user attribute information, and users who are not in the first whitelist but meet the target screening conditions are retrieved to obtain a second whitelist, wherein the users in the second whitelist are the determined target users. The method of the present application performs triple screening on users through the pre-trained extreme gradient boosting model to obtain a first whitelist, and retrieves the target users to obtain a more comprehensive target user in the second whitelist, which effectively improves the intelligence and efficiency of determining the target users. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0047] Figure 1 A flowchart of a method for determining a target user provided in an embodiment of the present application;

[0048] Figure 2 A flowchart of a method for obtaining a first whitelist provided in an embodiment of the present application;

[0049] Figure 3 A flowchart of a method for determining a second user provided in an embodiment of the present application;

[0050] Figure 4 A schematic diagram of the structure of a device for determining a target user provided in this application;

[0051] Figure 5 A schematic diagram of the structure of an electronic device provided in this application.

[0052] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0053] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0054] In the description of the embodiments of the present application, terms such as "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or component must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be understood as a limitation on the present application.

[0055] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, the terms "connected" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0056] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions, and corresponding operation entrances shall be provided for users to choose to authorize or refuse.

[0057] In order to improve the quality of service to customers in the financial field, it is necessary to identify a group of target users from a large number of users and provide them with appropriate business services.

[0058] At present, when determining target users, business personnel usually regularly export some users' business data from the data system, and then based on their personal work experience and with the help of some simple mathematical analysis models, according to the established screening rules, screen out target users that meet the business service requirements, obtain a whitelist containing the target users, and send the whitelist to the corresponding business service department.

[0059] However, the above method needs to rely heavily on manual operations of business personnel during the generation of the whitelist, has a low degree of intelligence, and is cumbersome, time-consuming, and inefficient.

[0060] Therefore, in view of the above technical problems in the prior art, the inventors found in the process of research that by using the extreme gradient boosting model (eXtreme Gradient Boosting, XGBoost), by setting the target screening conditions, and performing multiple screening on users according to the acquired user data, a first whitelist containing target users can be obtained more intelligently and quickly. In order to make the target users included in the first whitelist more comprehensive, the first whitelist can also be supplemented to obtain a second whitelist. Based on this, the present application proposes a method, device, electronic device and storage medium for determining target users.

[0061] It is understandable that the application scenario of this application can be the financial field, the enterprise service field, the educational service field, etc. This application does not limit the application field.

[0062] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0063] Figure 1The flowchart of a method for determining a target user provided in an embodiment of the present application is shown in FIG. The execution subject of the method may be an intelligent terminal with a target user determination function, for example, a personal computer, a laptop computer, a smart phone, a tablet computer, a portable wearable device, a server or a server cluster, etc. The method in this embodiment may be implemented by software, hardware, or a combination of software and hardware. Figure 1 As shown, the method may include the following steps:

[0064] S101. Acquire pre-processed data of multiple users, where the data includes user attribute information and financial data.

[0065] One possible implementation is:

[0066] The original data of multiple users are obtained. For any user, the original data of the user is classified and preprocessed based on preset category features to obtain preprocessed data, and then the preprocessed data of multiple users are obtained.

[0067] Optionally, the source of the original data can be obtained in two ways: direct acquisition and indirect acquisition.

[0068] Direct acquisition means that the forward system that stores the user data source directly sends the daily updated data in batches to the data lake, and then obtains the data required for the target user from the data lake. The data can exist in the form of a data table and is processed in the data warehouse. The processing includes data extraction, conversion, and loading, and finally the user's original data is obtained.

[0069] Indirect acquisition means that the forward system that stores the user data source provides an interface to the backward system in an online form. The backward system calls the user's real-time data through the interface and sends the data to the data lake. It then obtains the data required for the target user from the data lake and completes the data processing in the data warehouse to finally obtain the user's original data.

[0070] After obtaining the original data of multiple users, classification preprocessing is performed based on preset category features, such as basic information, pre-rules, first financial data, and second financial data, so as to obtain multiple categories of feature engineering information, i.e., preprocessed data.

[0071] S102. Based on the pre-trained extreme gradient boosting model, a triple screening process is performed on the multiple users according to the data of the multiple users to obtain a first whitelist including users that meet the target screening conditions, where the target screening conditions are determined according to different financial data and / or user attribute information.

[0072] The extreme gradient boosting model in this embodiment has been pre-trained, and its input is user data, which includes user attribute information and financial data, and its output is a whitelist containing users that meet the target screening conditions.

[0073] There may be multiple target screening conditions, and any target screening condition may be determined based only on user attribute information, or based only on financial data, or based on both user attribute information and financial data.

[0074] The triple screening process includes potential user screening process, model scoring screening process and post-decision screening process, which will be described in detail in the following embodiments. Please refer to the following embodiments for details.

[0075] S103: Retrieve users who are not in the first whitelist but meet the target screening condition to obtain a second whitelist, where the users in the second whitelist are the determined target users.

[0076] Optionally, a third user who meets the target screening conditions within a preset time period is obtained, and based on the user attribute information of the third user, it is determined whether the third user is in the first whitelist; if the third user is not in the first whitelist, the third user is added to the first whitelist to obtain a second whitelist.

[0077] The third user who meets the target screening conditions within the preset time period can be obtained by screening by business personnel, or can be obtained based on the above step S102. If obtained through the above steps, it should be noted that the time for determining the pre-processed user data obtained by the third user should be earlier.

[0078] Optionally, the third users meeting the target screening criteria within the preset time period may be directly merged with the first whitelist to obtain a second whitelist without determining whether they exist in the first whitelist, which will make the second whitelist more comprehensive.

[0079] The obtained second whitelist can be used to provide business service references for business personnel, thereby improving service quality.

[0080] Optionally, after obtaining the second whitelist, a display permission may be obtained, and according to the display permission, data of the target user in the second whitelist may be displayed, wherein the data is data that is allowed to be displayed by the display permission.

[0081] The intelligent terminal only displays part of the target user's information in the second whitelist according to the authority restrictions of the business personnel, thereby protecting the target user's information.

[0082] In this embodiment, the data used by the XGBoost model in determining the target user and the monitoring indicators preset by the XGBoost model can also be displayed according to the authority restrictions of the business personnel, so that the business personnel can adjust the data or indicators required for the operation of the XGBoost model according to the target user finally obtained, thereby making the XGBoost model more accurate.

[0083] In the above-mentioned embodiment of the present application, by obtaining the data of multiple users after preprocessing, wherein the data includes user attribute information and financial data, based on the pre-trained extreme gradient boosting model, according to the data of multiple users, a triple screening process is performed on multiple users to obtain a first whitelist including users that meet the target screening conditions, the target screening conditions are determined according to different financial data and / or user attribute information, and users who are not in the first whitelist but meet the target screening conditions are retrieved to obtain a second whitelist, and the users in the second whitelist are the determined target users. The method of the present application performs a triple screening of users through a pre-trained extreme gradient boosting model to obtain a first whitelist, and by retrieving the target users, the target users in the second whitelist obtained are more comprehensive, which effectively improves the intelligence and efficiency of determining the target users.

[0084] Furthermore, based on the above embodiments, the following embodiments illustrate the process of performing triple screening on multiple users based on the pre-trained extreme gradient boosting model in step S102 according to the data of multiple users to obtain a first whitelist including users that meet the target screening conditions.

[0085] Figure 2 A flowchart of a method for obtaining a first whitelist provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the method comprises the following steps:

[0086] S201. Perform a first screening process on the multiple users based on data of the multiple users, and screen out a first user who meets a first target screening condition from the multiple users, where the first target screening condition is determined based on first financial data and / or first user attribute information.

[0087] Optionally, the first screening process may be a potential user screening process, the purpose of which is to screen out potential users who meet the requirements, namely, first users, from a large number of users.

[0088] For example,

[0089] The first target screening condition may be that the annual average daily financial data in the financial data is greater than 0, the status in the user attribute information is a normal state without deactivation, the qualification information is normal, and there is no abnormal behavior. The user who meets the above first target screening condition is determined as the first user.

[0090] It should be understood that the above examples are only used for illustration and do not limit the present application.

[0091] S202: Based on a preset scoring algorithm, perform a second screening process on the first user to screen out second users that meet a second target screening condition from the first users, where the second target screening condition is determined based on the second financial data and / or the second user attribute information.

[0092] Based on the first user screened out in step S201, a second screening process, namely, a model scoring screening process, is performed based on a preset scoring algorithm to obtain a second user.

[0093] In this application, three models are pre-deployed, namely the first object feature prediction model, the second object feature prediction model and the third object feature prediction model, and the scoring algorithm preset in each prediction model is used to score and calculate the data of each user, so as to obtain the score under different object features. Then, according to the size relationship between the score and the preset score threshold, it is judged whether the second target screening condition is met.

[0094] S203: Perform a third screening process on the second users to screen out third users that meet a third target screening condition from the second users, where the third target screening condition is determined based on the third financial data and / or the third user attribute information.

[0095] After the second user is obtained based on the above step S202, a third screening process, namely, a post-decision screening process, is performed on the second user.

[0096] For example,

[0097] The third target screening condition can be that the average daily financial data in the past six months is greater than or equal to T1. It can also be that the average daily financial data in the past six months is greater than or equal to T2 and less than T1 (T2 is less than T1), and the number of times the first preset target business service was performed in the early morning in the past six months is less than L1, and the financial data of the second preset target business service in the past six months is less than T3. Users who meet any of the above third target screening conditions are determined as third users.

[0098] It can be understood that the above examples are only used for illustration, and T1, T2, L1 and T3 can be adjusted according to actual application conditions, and this application does not limit them.

[0099] S204: Generate and obtain a first whitelist according to the third user.

[0100] Then, according to the third user, a first whitelist is generated according to a preset algorithm.

[0101] In the above-mentioned embodiment of the present application, a first screening process is performed on multiple users according to their data, a first user that meets the first target screening condition is screened out from the multiple users, and a second screening process is performed on the first user based on a preset scoring algorithm, a second user that meets the second target screening condition is screened out from the first user, and then a third screening process is performed on the second user, a third user that meets the third target screening condition is screened out from the second user, and a first whitelist is generated and obtained based on the third user. The method of this embodiment improves the accuracy and intelligence of the first whitelist obtained by performing a triple screening on users, and further improves the screening efficiency.

[0102] Furthermore, based on the above embodiment, the following embodiment illustrates a process of performing a second screening process on the first user based on a preset scoring algorithm to screen out second users who meet the second target screening condition from the first users.

[0103] Figure 3 A flow chart of a method for determining a second user provided in an embodiment of the present application is shown as follows: Figure 3 As shown, the method comprises the following steps:

[0104] S301. Based on a preset first scoring algorithm and according to data of a first user, a first score of the first user on a preset first object feature is calculated.

[0105] A first object feature prediction model is pre-deployed in the present application. According to the first scoring algorithm preset in the first object feature prediction model and the data of each first user, a specific score within a preset score range can be automatically generated according to a preset period. The preset score range can be, for example, 1 to 5 points.

[0106] Optionally, the first object feature may be a feature used to characterize a degree of importance.

[0107] S302: Based on a preset second scoring algorithm and according to the data of the first user, a second score of the first user on a preset second object feature is calculated.

[0108] A second object feature prediction model is also pre-deployed in the present application. According to the second scoring algorithm preset in the second object feature prediction model and the data of each first user, a specific score within a preset score range can also be automatically generated according to a preset period. The preset score range can be, for example, 1 to 5 points.

[0109] Optionally, the second object feature may be a feature used to characterize a security level.

[0110] S303: Based on a preset third scoring algorithm and according to the data of the first user, calculate a third score of the first user on a preset third object feature.

[0111] A third object feature prediction model is also pre-deployed in the present application. According to the third scoring algorithm preset in the third object feature prediction model and the data of each first user, a specific score within a preset score range can also be automatically generated according to a preset period. The preset score range can be, for example, 1 to 5 points.

[0112] Alternatively, the third object feature may be a feature for characterizing a degree of responsiveness.

[0113] After the first score, the second score and the third score are obtained, they can be stored in a target database or a background system that can store the above scores according to a preset period.

[0114] S304: Determine a first user whose first score satisfies a preset first score threshold, whose second score satisfies a preset second score threshold, and whose third score satisfies a preset third score threshold as a second user.

[0115] For example, assuming that the preset first score threshold, second score threshold, and third score threshold are all 3 points, the first user whose first score is greater than 3 points, whose second score is greater than 3 points, and whose third score is greater than 3 points is determined as the second user. That is, assuming that the first score of the first object feature of user a is 4 points, the second score of the second object feature is 5 points, and the third score of the third object feature is 4 points, user a is screened as the second user.

[0116] It is understandable that the above thresholds are only used for illustration and can be flexibly adjusted according to actual application conditions, and are not limited in this application.

[0117] In the above embodiment of the present application, by calculating the first score of the first user on the preset first object feature based on the data of the first user based on the preset first scoring algorithm, calculating the second score of the first user on the preset second object feature based on the data of the first user based on the preset second scoring algorithm, and calculating the third score of the first user on the preset third object feature based on the data of the first user based on the preset third scoring algorithm, the first user whose first score meets the preset first score threshold, whose second score meets the preset second score threshold, and whose third score meets the preset third score threshold is determined as the second user. The method of this embodiment improves the accuracy of second user judgment by determining whether the user is the second user based on the scores of each first user on different object features.

[0118] Figure 4 A schematic diagram of a target user determination device provided in this application is shown in FIG. Figure 4 As shown, the target user determination device provided in this embodiment includes:

[0119] The acquisition module 401 acquires the pre-processed data of multiple users, the data including user attribute information and financial data.

[0120] Processing module 402 is used to perform triple screening on multiple users based on the pre-trained extreme gradient boosting model and the data of multiple users to obtain a first whitelist including users that meet the target screening conditions, where the target screening conditions are determined based on different financial data and / or user attribute information.

[0121] The processing module 402 is further used to retrieve users who are not in the first whitelist but meet the target screening condition to obtain a second whitelist. The users in the second whitelist are the determined target users.

[0122] In a possible implementation manner, the processing module 402 is specifically configured to:

[0123] Based on the data of the multiple users, a first screening process is performed on the multiple users to screen out a first user who meets a first target screening condition from the multiple users, where the first target screening condition is determined based on the first financial data and / or the first user attribute information.

[0124] Based on a preset scoring algorithm, a second screening process is performed on the first user to screen out second users who meet second target screening conditions from the first users, and the second target screening conditions are determined according to the second financial data and / or the second user attribute information.

[0125] A third screening process is performed on the second users to screen out third users that meet a third target screening condition from the second users, where the third target screening condition is determined based on the third financial data and / or the third user attribute information.

[0126] According to the third user, a first whitelist is generated and obtained.

[0127] In a possible implementation manner, the processing module 402 is specifically configured to:

[0128] Based on a preset first scoring algorithm and according to the data of the first user, a first score of the first user on a preset first object feature is calculated.

[0129] Based on a preset second scoring algorithm and according to the data of the first user, a second score of the first user on a preset second object feature is calculated.

[0130] Based on a preset third scoring algorithm and according to the data of the first user, a third score of the first user on a preset third object feature is calculated.

[0131] A first user whose first score satisfies a preset first score threshold, whose second score satisfies a preset second score threshold, and whose third score satisfies a preset third score threshold is determined as a second user.

[0132] In a possible implementation manner, the processing module 402 is specifically configured to:

[0133] Acquire third users who meet the target screening conditions within a preset time period.

[0134] It is determined whether the third user is in the first whitelist according to the user attribute information of the third user.

[0135] If the third user is not in the first whitelist, the third user is added to the first whitelist to obtain a second whitelist.

[0136] A possible implementation manner is to further include a display module 403. After obtaining the second whitelist, the display module 403 is further used to:

[0137] Get display permission.

[0138] According to the display permission, the data of the target user in the second whitelist is displayed, and the data is the data allowed to be displayed by the display permission.

[0139] One possible implementation is that the acquisition module 401 is specifically configured to:

[0140] Get raw data of multiple users.

[0141] For any user, the user's original data is classified and preprocessed based on preset category features to obtain preprocessed data.

[0142] Get the preprocessed data of multiple users.

[0143] The device for determining the target user provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, which will not be described in detail in this embodiment.

[0144] Figure 5 This is a schematic diagram of the structure of an electronic device provided in this application. Figure 5 As shown, the electronic device provided in this embodiment includes: at least one processor 501 and a memory 502. Optionally, the device 50 also includes a communication component 503. The processor 501, the memory 502 and the communication component 503 are connected via a bus 504.

[0145] In a specific implementation process, at least one processor 501 executes the computer-executable instructions stored in the memory 502, so that at least one processor 501 executes the above method.

[0146] The specific implementation process of the processor 501 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0147] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0148] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0149] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0150] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0151] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0152] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0153] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0154] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0155] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0156] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0157] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0158] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0159] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for determining a target user, characterized in that: include: Acquire pre-processed data of multiple users, the data including user attribute information and financial data; Based on the pre-trained extreme gradient boosting model, the multiple users are triple-screened according to the data of the multiple users to obtain a first whitelist including users meeting a target screening condition, wherein the target screening condition is determined according to different financial data and / or user attribute information; Users who are not in the first whitelist but meet the target screening condition are retrieved to obtain a second whitelist, and the users in the second whitelist are the determined target users.

2. The method according to claim 1, characterized in that The method of performing triple screening on the multiple users based on the pre-trained extreme gradient boosting model according to the data of the multiple users to obtain a first whitelist including users meeting the target screening conditions includes: performing a first screening process on the multiple users according to the data of the multiple users, and screening out a first user that meets a first target screening condition from the multiple users, where the first target screening condition is determined according to the first financial data and / or the first user attribute information; Based on a preset scoring algorithm, a second screening process is performed on the first user to screen out a second user who meets a second target screening condition from the first user, where the second target screening condition is determined according to the second financial data and / or the second user attribute information; Performing a third screening process on the second users, screening out third users that meet a third target screening condition from the second users, where the third target screening condition is determined based on third financial data and / or third user attribute information; The first whitelist is generated and obtained according to the third user.

3. The method according to claim 2, characterized in that The performing a second screening process on the first users based on a preset scoring algorithm to screen out second users meeting a second target screening condition from the first users includes: Based on a preset first scoring algorithm and according to the data of the first user, calculating a first score of the first user on a preset first object feature; Based on a preset second scoring algorithm, and according to the data of the first user, calculating a second score of the first user on a preset second object feature; Based on a preset third scoring algorithm, and according to the data of the first user, calculating a third score of the first user on a preset third object feature; A first user whose first score satisfies a preset first score threshold, whose second score satisfies a preset second score threshold, and whose third score satisfies a preset third score threshold is determined as the second user.

4. The method according to claim 3, characterized in that The retrieving of users who are not in the first whitelist but meet the target screening condition to obtain a second whitelist includes: Acquire third users who meet the target screening condition within a preset time period; Determining, according to the user attribute information of the third user, whether the third user is in the first whitelist; If the third user is not in the first whitelist, the third user is added to the first whitelist to obtain the second whitelist.

5. The method according to claim 4, characterized in that After obtaining the second whitelist, the method further includes: Get display permission; According to the display permission, data of the target users in the second whitelist are displayed, and the data is data that is allowed to be displayed by the display permission.

6. The method according to any one of claims 1 to 5, characterized in that: The obtaining of pre-processed data of multiple users includes: Acquiring original data of the multiple users; For any user, the original data of the user is classified and preprocessed based on preset category features to obtain preprocessed data; The preprocessed data of the multiple users is obtained.

7. A device for determining a target user, characterized in that: include: An acquisition module, which acquires pre-processed data of multiple users, wherein the data includes user attribute information and financial data; a processing module, configured to perform triple screening processing on the multiple users based on the pre-trained extreme gradient boosting model and the data of the multiple users, so as to obtain a first whitelist including users meeting a target screening condition, wherein the target screening condition is determined according to different financial data and / or user attribute information; The processing module is further used to retrieve users who are not in the first whitelist but meet the target screening condition to obtain a second whitelist, and the users in the second whitelist are the determined target users.

8. The device according to claim 7, characterized in that The processing module is specifically used for: performing a first screening process on the multiple users according to the data of the multiple users, and screening out a first user that meets a first target screening condition from the multiple users, wherein the first target screening condition is determined according to the first financial data and / or the first user attribute information; Based on a preset scoring algorithm, a second screening process is performed on the first user to screen out a second user who meets a second target screening condition from the first user, where the second target screening condition is determined according to the second financial data and / or the second user attribute information; Performing a third screening process on the second users, screening out third users that meet a third target screening condition from the second users, where the third target screening condition is determined based on third financial data and / or third user attribute information; The first whitelist is generated and obtained according to the third user.

9. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

Images