A user screening method, device, equipment and readable storage medium

Abstract

The application discloses a user screening method, relates to the field of anti-fraud, and comprises the following steps: acquiring user information; selecting anti-fraud features from the user information; setting associated screening conditions according to the anti-fraud features, and outputting target feature values satisfying the associated screening conditions; and determining target user numbers according to the target feature values. According to the application, the associated screening conditions are directly set according to the anti-fraud features, the feature values with fraud risks are screened out, and the user numbers are determined according to the feature values with fraud risks, so that the associated screening conditions can be set and the users can be screened in the case that the number of screening values is huge or the feature values of each user are basically different. The method can realize fuzzy definition, find the users with the same values under a certain feature, and realize wide-range searching of the users with high correlation degrees. In addition, the application further provides a user screening device, equipment and computer readable storage medium, which also have the beneficial effects.

Description

Technical Field

[0001] This invention relates to the field of anti-fraud, and in particular to a user screening method, apparatus, device, and computer-readable storage medium. Background Technology

[0002] Existing association tools first identify users based on relevant association filtering criteria, and then project their POIs (Points of Information) onto a map. The filtering methods are broadly divided into direct condition search and knowledge graph search. Direct condition search is only useful for feature values ​​with limited inherent attributes. When each user's feature data values ​​are largely different with only a few common values, direct filtering cannot identify the few identical users. Knowledge graph search requires finding users and other information associated with a specific data value, making it difficult to screen a large number of users with high correlation.

[0003] Currently, the filtering of users on the map is limited to a finite number of meaningful filtering values. If the number of filtering values ​​is huge or the characteristic data values ​​of each user are basically different, user filtering will become meaningless. Therefore, the existing filtering methods have limitations and are not universal. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a user screening method. This method filters out feature values ​​with fraud risk by directly setting associated screening conditions based on anti-fraud features, and determines the user number based on the feature values ​​with fraud risk. This method can be used to screen users when the number of screening values ​​is huge or the feature values ​​of each user are basically different. This method can achieve fuzzy definition and find users with the same value under a certain feature, so as to achieve a wide range of users with high correlation.

[0005] In addition, the present invention also provides a user screening device, apparatus, and computer-readable storage medium, which also have the above-mentioned beneficial effects.

[0006] To address the aforementioned technical problems, this invention provides a user screening method, comprising:

[0007] Obtain user information;

[0008] Select anti-fraud features from the user information;

[0009] Based on the anti-fraud features, set association filtering conditions and output the target feature values ​​that satisfy the association filtering conditions;

[0010] The target user ID is determined based on the target feature value.

[0011] Optionally, the step of setting association filtering conditions based on anti-fraud features and outputting target feature values ​​that satisfy the association filtering conditions includes:

[0012] Calculate the number of users associated with the feature values ​​in the anti-fraud features;

[0013] If the number of associated users is greater than a preset threshold, then the target feature value corresponding to the number of associated users is output.

[0014] Optionally, after calculating the number of associated users for the feature values ​​in the anti-fraud features, the method further includes:

[0015] Based on the size of the number of associated users, the feature values ​​corresponding to the number of associated users are sorted.

[0016] Accordingly, if the number of associated users is greater than a preset threshold, the target feature value corresponding to the number of associated users is output, including:

[0017] If the number of associated users of the sorted feature value is greater than a preset threshold, then the target feature value corresponding to the number of associated users is output.

[0018] Optionally, determining the target user ID based on the target feature value includes:

[0019] Determine whether the target feature value belongs to the same anti-fraud feature;

[0020] If it belongs to the target, then the target user number associated with the target feature value is determined as the target user number;

[0021] If it does not belong to the target, then the same target user number associated with the target feature value is determined as the target user number.

[0022] Optionally, after obtaining the user information, the method further includes:

[0023] Select anti-fraud feature information from the user information;

[0024] A data intermediate table is established based on the aforementioned anti-fraud feature information;

[0025] The intermediate data table uses the user ID as the primary key, and the anti-fraud feature information is associated with the corresponding user ID.

[0026] Accordingly, selecting anti-fraud features from the user information includes:

[0027] The anti-fraud feature is selected from the anti-fraud feature information in the intermediate data table.

[0028] Optionally, after determining the target user ID based on the target feature value, the method further includes:

[0029] The map is associated with the user information;

[0030] Obtain the POI information corresponding to the target user ID;

[0031] The target user ID is marked on the map based on the POI information.

[0032] The present invention also provides a user screening device, comprising:

[0033] The first acquisition module is used to acquire user information;

[0034] The first selection module is used to select anti-fraud features from the user information;

[0035] The setting module is used to set association filtering conditions based on the anti-fraud features and output target feature values ​​that satisfy the association filtering conditions.

[0036] The determination module is used to determine the target user number based on the target feature value.

[0037] Optional, also includes:

[0038] The association module is used to establish an association between the map and the user information;

[0039] The second acquisition module is used to acquire the POI information corresponding to the target user number;

[0040] The annotation module is used to annotate the target user number on the map based on the POI information.

[0041] The present invention also provides a user screening device, comprising:

[0042] Memory, used to store computer programs;

[0043] A processor for implementing the user screening method described above when executing the computer program.

[0044] The present invention also provides a readable storage medium storing a computer program that, when executed by a processor, implements the user screening method described above.

[0045] As can be seen, this method filters out feature values ​​with fraud risk by directly setting association filtering conditions based on anti-fraud features, and determines the user number based on the feature values ​​with fraud risk. It can filter users by setting association filtering conditions when the number of filtering values ​​is huge or the feature values ​​of each user are basically different. This method can achieve fuzzy definition and find users with the same value under a certain feature, so as to achieve a large-scale search for users with high correlation.

[0046] In addition, the present invention also provides a user screening device, apparatus, and computer-readable storage medium, which also have the above-mentioned beneficial effects. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0048] Figure 1 Find example graphs for knowledge graphs;

[0049] Figure 2 A flowchart of a user screening method provided in an embodiment of the present invention;

[0050] Figure 3 A flowchart illustrating a user screening method provided in an embodiment of the present invention;

[0051] Figure 4 This is a schematic diagram of the structure of a user screening device provided in an embodiment of the present invention;

[0052] Figure 5 This is a schematic diagram of a user screening device provided in an embodiment of the present invention. Detailed Implementation

[0053] The purpose of this invention is to provide a user screening method, apparatus, device, and computer-readable storage medium. This method involves acquiring user information; selecting anti-fraud features from the user information; setting association screening conditions based on the anti-fraud features; outputting target feature values ​​that meet the association screening conditions; and determining the target user number based on the target feature values. This invention, by directly setting association screening conditions based on anti-fraud features, filters out feature values ​​with fraud risk and determines the user number based on these feature values. This allows for filtering users even when the number of screening values ​​is huge or the feature values ​​for each user are largely different. This method can also achieve fuzzy definition, finding users with the same value under a certain feature, enabling a wide-ranging search for users with high correlation.

[0054] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] There are two main types of existing filtering methods: one is direct condition search, and the other is knowledge graph search.

[0056] (1) Direct condition search is used to filter values ​​from a single feature or multiple features. See Table 1 for an example. Assume the relevant filtering conditions are: Apply for product X1; Application channel is APP; User level is new user. Direct condition search is only useful for feature values ​​with limited values ​​and self-attribute types, such as the features "Apply for product" and "Application channel" in Table 1. The user's data values ​​are limited and highly repetitive, making direct filtering possible. If each user's feature data values ​​are largely different, with only a few identical values, direct filtering cannot be implemented when it's necessary to identify the few identical users.

[0057] Table 1. Examples of direct condition search

[0058] User ID Apply for product Application Channels User Level User 1 X1 app Existing users User 2 Y1 app New customers User 3 X1 WeChat New customers …… …… …… ……

[0059] (2) Knowledge graphs are a common tool in the current anti-fraud field. Given a certain characteristic value, they display the people associated with that value, as well as other information associated with those people. Specifically, for example... Figure 1 As shown, Figure 1 Example graph for knowledge graph lookup. Suppose that searching for phone number 1 reveals associated users 4 and 5. Expanding the depth of association allows finding users 1, 2, and 3 together. However, knowledge graphs require a specific data value to find associated users and other information; they cannot broadly search for users with high associations. For instance, finding users whose phone numbers are associated with more than 50 people is an abstract instruction that knowledge graphs cannot handle.

[0060] In view of this, embodiments of the present invention can employ a novel filtering method that can directly set fraudulent conditions (such as having the same characteristic rather than a specific numerical value) to filter users when the number of filtering values ​​is enormous or when the feature data values ​​of each user are basically different. Please refer to Figure 2 , Figure 2 A flowchart illustrating a user screening method provided in an embodiment of the present invention. The method may include:

[0061] S101, Obtain user information.

[0062] This embodiment does not limit the frequency of data acquisition. For example, it can acquire data once at a fixed time. This embodiment does not limit the specific content of the fixed time; for example, it can acquire data once every 24 hours, once every hour, or even in real time. This embodiment does not limit the specific content and quantity of user information. The information acquired is based on the content settings of the bank's form. For example, it can be name, ID number, home address, registered phone number; or it can be landline number, device fingerprint, business details, business time, branch address information, or IP address (Internet Protocol address).

[0063] To better store and process user information, the collected user information can be stored in an intermediate data table after a user submits an application. Furthermore, to save storage space in the intermediate data table, anti-fraud feature information and user ID can be selected from the user information. Then, using the user ID as the primary key, a data feature table can be created by associating the anti-fraud feature information with the user ID. This embodiment does not limit the anti-fraud feature information; based on anti-fraud experience, a portion of the collected user information can be used as anti-fraud feature information and associated with the corresponding user ID.

[0064] S102, Select anti-fraud features from user information.

[0065] Since the user information is not limited, this embodiment does not limit the specific content of the anti-fraud features. For example, it could be a pre-registered mobile phone number; or it could be a device fingerprint; or it could be an email address; or it could be an IP address. This embodiment does not limit the number of anti-fraud features. For example, it could be one anti-fraud feature; or it could be multiple anti-fraud features, set according to the actual situation.

[0066] S103, set association filtering conditions based on anti-fraud features, and output the target feature value that meets the association filtering conditions.

[0067] This embodiment does not limit specific association filtering conditions, as long as they can filter out the target feature value. This embodiment can calculate the number of users associated with each feature value in the anti-fraud features, and determine the target feature value based on the size of the number of associated users. This embodiment does not limit the filtering method; for example, the target feature value can be determined directly based on the number of users associated with each feature value in the anti-fraud features; or the feature values ​​can be sorted according to the number of users associated with each feature value in the anti-fraud features, and then the target feature value can be determined. This embodiment does not limit the specific determination method; for example, the feature value with the most associated users can be selected as the target feature value; or a preset threshold can be set, and feature values ​​greater than the preset threshold can be determined as the target feature value. This embodiment does not limit the specific preset threshold; users can set it according to their actual situation. Since the number of anti-fraud features is not limited, this embodiment does not limit the number of association filtering conditions. Once the number of anti-fraud features is determined, the same number of association filtering conditions are set, and corresponding association filtering conditions are set for each anti-fraud feature.

[0068] To improve screening efficiency, the feature values ​​corresponding to the number of associated users can be sorted according to the number of associated users. Then, the number of associated users for the sorted feature values ​​can be compared with a preset threshold, and the target feature value corresponding to the number of associated users greater than the preset threshold can be output. In order to make the target feature value of the screening meaningful and more reflective of the correlation, multiple anti-fraud features can be selected, and multiple correlation screening conditions can be set accordingly. The feature value that meets all the correlation screening conditions can be set as the target feature value.

[0069] S104, Determine the target user number based on the target feature value.

[0070] After the target feature value is determined, the target user number is determined based on the user number associated with the target feature value. This embodiment does not limit the specific method of determining the target user number. For example, the target user number can be determined directly based on the target feature value; or it can first determine whether the target feature value belongs to the same anti-fraud feature. If it belongs to the same anti-fraud feature, the target user number associated with the target feature value is output; if it does not belong to the same anti-fraud feature, it first determines whether the target user numbers associated with the target feature value are the same. If they are the same, the user number with the same target user number is determined as the target user number.

[0071] To make the screening more accurate, specific, reliable, and precise, we can first determine whether the target feature value belongs to the same anti-fraud feature. If it does, we can directly determine the target user number associated with the target feature value; if it does not, we can determine the same target user number associated with the target feature value as the target user number.

[0072] The user screening method provided in this invention directly sets associated screening conditions based on anti-fraud features to filter out feature values ​​with fraud risk. User numbers are then determined based on these feature values. This method can be used to screen users even when the number of screening values ​​is huge or the feature values ​​of each user are largely different. It allows for fuzzy definition, finding users with the same value under a certain feature, enabling a wide-ranging search for users with high correlation. First, anti-fraud feature information is selected from user information, and an intermediate data table is established based on the anti-fraud information and user numbers, saving storage space and improving efficiency for subsequent screening. Target feature values ​​are filtered based on preset thresholds, and before determining the target user number, it is determined whether the target feature values ​​belong to the same anti-fraud feature, making the screening more accurate, specific, and reliable. Sorting feature values ​​based on the number of associated users further improves screening efficiency.

[0073] Based on the above embodiments, in the existing anti-fraud and risk control fields, user information that should have a single attribute but exhibits large-scale similarity is defined as a clear fraud signal. If user POIs cluster on a map, it will be defined as a fraud gang; the large-scale similarity of fraud characteristics and the concentration of POIs can be considered as explicit phenomena of fraud gangs. This application can associate user information with a map; obtain POI information corresponding to a target user number; and mark the target user number on the map according to the POI information. This embodiment does not limit the specific method of association; for example, it can obtain the user's location information based on the user's IP address and associate the user information with the map; or it can obtain the user's location information based on the user's mobile terminal location and associate the user information with the map; or it can obtain the location information based on the current address information filled in by the user and associate the user information with the map. This embodiment does not limit the frequency of obtaining POI information corresponding to the target user number; for example, it can obtain all target user numbers together after all target user numbers are determined; or it can obtain the information as soon as a single target user number is determined. This embodiment does not limit the specific method of marking. For example, the location can be clearly marked with a red circle; or the latitude and longitude information of the location can be displayed at the same time as marking with a red circle.

[0074] This method enables large-scale filtering of user relationships and maps users onto a map to check for clustering. For example, it identifies users who apply using the same mobile phone number. To prevent legitimate users from applying using friends' phones, a threshold is set for the number of people using that phone number. When the number exceeds the threshold, it is mapped onto the map. This method allows for rapid detection of whether users with fraudulent characteristics are geographically clustered, enabling quick discovery of fraud rings and their corresponding locations.

[0075] To facilitate understanding of the above embodiments, a specific embodiment is provided below to illustrate the detailed process of the user screening method described above. Please refer to... Figure 3 , Figure 3 This is a flowchart illustrating a user screening method provided by an embodiment of the present invention. Users fill out a form at a bank and submit an application. The bank collects and stores user information, using the user ID as the primary key of a data intermediate table. Anti-fraud feature information is extracted from the user information and associated with the user ID to establish the data intermediate table. This data intermediate table is then linked to a map, and users are filtered based on the anti-fraud features associated with them. Examples of association filtering conditions include: Filtering condition 1: The number of users associated with anti-fraud feature 1 is greater than a preset threshold 'a'; Filtering condition 2: The number of users associated with anti-fraud feature 2 is greater than a preset threshold 'b'; The number of users associated with anti-fraud feature 1 and anti-fraud feature 2 in the data intermediate table is calculated; Target feature value 1 and Target feature value 2 are filtered out based on filtering conditions 1 and 2; User IDs associated with Target feature value 1 are selected from the data intermediate table as Target User ID 1, and User IDs associated with Target feature value 1 are selected as Target User ID 2; User IDs with the same Target User ID 1 and Target User ID 2 are selected as Target User IDs, and the corresponding Points of Interest (POIs) are marked on the map.

[0076] For a specific example, two anti-fraud features can be selected: anti-fraud feature 1, device fingerprint, and anti-fraud feature 2, email address, to establish a data intermediate table. Table 2 shows an example of a data intermediate table. Map information is accessed, and the data intermediate table is linked. The number of users associated with anti-fraud feature 1 (device fingerprint) in the data intermediate table is calculated. Linkage filtering condition 1 is set as follows: the number of users associated with anti-fraud feature 1 (device fingerprint) is greater than a preset threshold of 50. Linkage filtering condition 2 is set as follows: the number of users associated with anti-fraud feature 2 (email address) is greater than a preset threshold of 50. The number of users associated with each anti-fraud feature value is calculated and sorted. The filtering results according to linkage filtering condition 1 are shown in Table 3. Table 3 shows the number of users associated with anti-fraud feature 1. Taking number 1 as an example, it indicates that 153 users applied for this service through a mobile phone with the device fingerprint "aa5423677188". This device fingerprint is associated with 153 users. Numbers 1-8 meet linkage filtering condition 1, indicating that these device fingerprints... Each associated user has more than 50 users. Users associated with the feature value (device fingerprints numbered 1-8) are filtered in the intermediate data table, and their user IDs are output. The results are shown in Table 4, which is the user table corresponding to association filtering condition 1. The filtering results according to association filtering condition 2 are shown in Table 5, which is the table of the number of users associated with anti-fraud feature 2. Taking number 1 as an example, it shows that 123 users filled in the email address 5423677188@xx.com when applying for this service. Numbers 1-6 meet association filtering condition 2, indicating that each of these email addresses is associated with more than 50 users. Users associated with the feature value (email addresses numbered 1-6) are filtered in the intermediate data table, and their user IDs are output. The results are shown in Table 6, which is the user table corresponding to association filtering condition 2. Finally, the users of association filtering condition 1 and association filtering condition 2 are matched to find the intersection, i.e., the shared users, which are used as the target user IDs. The target users are then marked on the map based on the POI information corresponding to the target user IDs.

[0077] Table 2 is an example of an intermediate data table.

[0078] User ID POI Anti-fraud feature 1 Anti-fraud feature 2 User 1 g1 1a 2a User 2 g2 1a 2b User 3 g3 1c 2a User 4 ...... ...... ...... User 5 ...... ...... ...... ...... ...... ...... ......

[0079] Table 3. Number of users associated with anti-fraud feature 1

[0080]

[0081]

[0082] Table 4 shows the user table corresponding to the association filter condition 1.

[0083]

[0084] Table 5. Number of Associated Users for Anti-Fraud Feature 2

[0085]

[0086]

[0087] Table 6. User table corresponding to filter condition 2.

[0088]

[0089] The user filtering device provided in the embodiments of the present invention will be described below. The user filtering device described below can be referred to in correspondence with the user filtering method described above.

[0090] Please refer to Figure 4 , Figure 4 A schematic diagram of a user screening device provided in an embodiment of the present invention includes:

[0091] The first acquisition module 100 is used to acquire user information;

[0092] The first selection module 200 is used to select anti-fraud features from user information;

[0093] The setting module 300 is used to set association filtering conditions based on anti-fraud features and output target feature values ​​that meet the association filtering conditions.

[0094] The determination module 400 is used to determine the target user number based on the target feature value.

[0095] The user screening device provided in this embodiment of the invention can filter out feature values ​​with fraud risk by directly setting associated screening conditions based on anti-fraud features, and determine the user number based on the feature values ​​with fraud risk. It can set associated screening conditions to screen users when the number of screening values ​​is huge or the feature values ​​of each user are basically different. This device can realize fuzzy definition to find users with the same value under a certain feature, and realize a wide range of users with high correlation.

[0096] Based on the above embodiments, it may also include:

[0097] The first association module is used to establish an association between the map and user information;

[0098] The second acquisition module is used to acquire the POI information corresponding to the target user number;

[0099] The annotation module is used to annotate the target user ID on the map based on POI information;

[0100] The sorting module is used to sort the feature values ​​corresponding to the number of associated users based on the size of the number of associated users.

[0101] The output module is used to output the target feature value corresponding to the number of associated users if the number of associated users of the sorted feature value is greater than a preset threshold.

[0102] The second selection module is used to select anti-fraud feature information from user information;

[0103] The table creation module is used to create intermediate data tables based on anti-fraud feature information;

[0104] The second association module is used in which the data intermediate table uses the user number as the primary key and the anti-fraud feature information is associated with the corresponding user number.

[0105] The third selection module is used to select anti-fraud features from the anti-fraud feature information in the intermediate data table.

[0106] Based on the above embodiments, the setting module 300 may include:

[0107] The calculation unit is used to calculate the number of users associated with the feature values ​​in the anti-fraud features;

[0108] The first output unit is used to output the target feature value corresponding to the number of associated users if the number of associated users is greater than a preset threshold.

[0109] Based on the above embodiments, the determining module 400 may include:

[0110] The judgment unit is used to determine whether the target feature values ​​belong to the same anti-fraud feature;

[0111] The first determining unit is used to determine the target user number associated with the target feature value as the target user number if it belongs to the target feature value.

[0112] The second determining unit is used to determine the same target user number associated with the target feature value as the target user number if it does not belong to the target user number.

[0113] The first association module, second acquisition module, and annotation module provided in this embodiment of the invention can achieve large-scale user relationship filtering, and simultaneously map users onto a map to check for clustering, which is beneficial for finding fraud gangs. It can quickly identify users with fraudulent characteristics that are geographically clustered, and rapidly discover the geographical locations of fraud gangs and their corresponding hideouts. The table building module, second association module, sorting module, second selection module, output module, and third selection module help improve filtering speed, increase efficiency, and save resources. The first output unit and calculation unit can search a wide range of highly relevant and meaningful feature values. The judgment unit, first determination unit, and second determination unit help extract users with more valuable information and improve the accuracy of user filtering.

[0114] The user screening device provided in the embodiments of the present invention is described below. The user screening device described below can be referred to in correspondence with the user screening method described above. The device may include:

[0115] Memory, used to store computer programs;

[0116] A processor is used to execute computer programs to implement the user screening method described above.

[0117] like Figure 5 As shown, Figure 5 This is a schematic diagram of a user screening device, which may include: a processor 10, a memory 11, a communication interface 12, and a communication bus 13. The processor 10, memory 11, and communication interface 12 all communicate with each other through the communication bus 13.

[0118] In this embodiment, the processor 10 may be a central processing unit (CPU), an application-specific integrated circuit, a digital signal processor, a field-programmable gate array, or other programmable logic devices.

[0119] The processor 10 can call the program stored in the memory 11. Specifically, the processor 10 can execute the operations in the embodiment of the abnormal IP identification method.

[0120] The memory 11 is used to store one or more programs, which may include program code and computer operation instructions.

[0121] In one possible implementation, the memory 11 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; and the data storage area may store data created during use.

[0122] In addition, memory 11 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device or other volatile solid-state storage device.

[0123] Communication interface 12 can be an interface for the communication module, used to connect with other devices or systems.

[0124] Of course, it should be noted that, Figure 5 The structure of the user screening device shown does not constitute a limitation on the device in the embodiments of this application. In practical applications, the device may include more than Figure 5 More or fewer components as shown, or combinations of certain components.

[0125] The following describes the computer-readable storage medium provided in the embodiments of the present invention. The computer-readable storage medium described below can be referred to in correspondence with the user screening method described above.

[0126] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the user screening method described above.

[0127] The computer-readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0128] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0129] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0130] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0131] Finally, it should be noted that in this document, relationships such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0132] The user screening method, apparatus, device, and computer-readable storage medium provided by the present invention have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A user screening method, characterized by, include: Obtain user information; Select anti-fraud features from the user information; Based on the anti-fraud features, set association filtering conditions and output the target feature values ​​that satisfy the association filtering conditions; Determine the target user ID based on the target feature value; The step of setting association filtering conditions based on the anti-fraud features and outputting target feature values ​​that satisfy the association filtering conditions includes: Calculate the number of users associated with the feature values ​​in the anti-fraud features; If the number of associated users is greater than a preset threshold, then the target feature value corresponding to the number of associated users is output; Determining the target user ID based on the target feature value includes: Determine whether the target feature value belongs to the same anti-fraud feature; If it belongs to the target, then the target user number associated with the target feature value is determined as the target user number; If it does not belong to the target, then the same target user number associated with the target feature value is determined as the target user number; After obtaining the user information, the process also includes: Select anti-fraud feature information from the user information; A data intermediate table is established based on the aforementioned anti-fraud feature information; The intermediate data table uses the user ID as the primary key, and the anti-fraud feature information is associated with the corresponding user ID. Accordingly, selecting anti-fraud features from the user information includes: The anti-fraud feature is selected from the anti-fraud feature information in the intermediate data table.

2. The user screening method of claim 1, wherein, After calculating the number of associated users for the feature values ​​in the anti-fraud features, the method further includes: Based on the size of the number of associated users, the feature values ​​corresponding to the number of associated users are sorted. Accordingly, if the number of associated users is greater than a preset threshold, the target feature value corresponding to the number of associated users is output, including: If the number of associated users of the sorted feature value is greater than a preset threshold, then the target feature value corresponding to the number of associated users is output.

3. The user screening method of any one of claims 1 to 2, wherein, After determining the target user ID based on the target feature value, the method further includes: The map is associated with the user information; Obtain the POI information corresponding to the target user ID; The target user ID is marked on the map based on the POI information.

4. A user screening apparatus, characterized by, include: The first acquisition module is used to acquire user information; The first selection module is used to select anti-fraud features from the user information; The setting module is used to set association filtering conditions based on the anti-fraud features and output target feature values ​​that satisfy the association filtering conditions. The determination module is used to determine the target user ID based on the target feature value; The configuration module includes: The calculation unit is used to calculate the number of users associated with the feature values ​​in the anti-fraud features; The first output unit is used to output the target feature value corresponding to the number of associated users if the number of associated users is greater than a preset threshold. The module to be determined includes: The judgment unit is used to determine whether the target feature values ​​belong to the same anti-fraud feature; The first determining unit is used to determine the target user number associated with the target feature value as the target user number if it belongs to the target feature value. The second determining unit is used to determine the same target user number associated with the target feature value as the target user number if it does not belong to the target user number. Also includes: The second selection module is used to select anti-fraud feature information from user information; The table creation module is used to create intermediate data tables based on anti-fraud feature information; The second association module is used in which the data intermediate table uses the user number as the primary key and the anti-fraud feature information is associated with the corresponding user number. The third selection module is used to select anti-fraud features from the anti-fraud feature information in the intermediate data table.

5. The user screening device of claim 4, wherein, Also includes: The association module is used to establish an association between the map and the user information; The second acquisition module is used to acquire the POI information corresponding to the target user number; The annotation module is used to annotate the target user number on the map based on the POI information.

6. A user screening device, characterized by, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the user screening method as described in any one of claims 1 to 3.

7. A readable storage medium, characterized by, The readable storage medium stores a computer program that, when executed by a processor, implements the steps of the user screening method as described in any one of claims 1 to 3.

Images