A method, device, medium and equipment for identifying new users

Through the abnormal suspicious value of the computing device information, the problem of live broadcast platforms being difficult to identify abnormal new users is solved, and accurate identification of new users is achieved, and the platform's rights and interests are protected.

CN114155017BActive Publication Date: 2024-11-15武汉斗鱼鱼乐网络科技有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111264415.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-10-28
Publication Date
2024-11-15
Estimated Expiration
2041-10-28

AI Technical Summary

Technical Problem

It is difficult for live broadcast platforms to accurately identify newly registered abnormal new users, resulting in damage to the platform's rights and interests.

Method used

By obtaining the device information of new users to register, calculate the proportion of normal registered devices and the proportion of new registered devices for each attribute value within the preset time period, determine the abnormal suspicion value of device information, and then identify the abnormal user .

Benefits of technology

It improves the accuracy of accurate identification of abnormal new users, ensures the objectivity and accuracy of identification, and prevents platform losses.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114155017B_ABST
    Figure CN114155017B_ABST
Patent Text Reader

Abstract

The present invention provides a method, device, medium and equipment for identifying new users, and the method includes: obtaining device information registered by the new user; determining a first proportion of the number of normally registered devices corresponding to the device information attribute value in the total number of normally registered devices within a preset time period; determining a second proportion of the number of newly registered devices corresponding to the attribute value in the total number of newly registered devices; determining a first abnormal suspicion value of the device information based on the first proportion and the second proportion; determining a second abnormal suspicion value corresponding to each attribute value based on the first proportion, the second proportion and the first abnormal suspicion value; identifying the new user based on the second abnormal suspicion value; in this way, even if the new user does not generate a behavioral event after registration, the second abnormal suspicion value can be determined based on the difference between the device information used for registration and the normally registered device information, and whether the new user is an abnormal user can be accurately identified based on the second suspicion value to ensure the accuracy of identification.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of risk identification of live broadcast platforms, and in particular relates to a method, device, medium and equipment for identifying new users. Background Art

[0002] In order to attract more new users to register on the platform, the platform often carries out some activities to attract new users through sharing. Old users on the platform attract new users through other platforms by sharing, and both new and old users can get certain rewards after the new users complete the registration.

[0003] Since there is a certain reward for each new user, the black industry uses a large number of cheap or counterfeit devices to register and grab the platform's rewards. Such behavior will cause great losses to the platform, and it is necessary to effectively identify such new registered users.

[0004] However, since old black market users who participate in sharing activities will choose some accounts with normal behavior to share, and abnormal new users will no longer have any behavior after registration, the traditional non-risk identification method based on account identification is difficult to accurately identify abnormal new users. Summary of the invention

[0005] In response to the problems existing in the prior art, the embodiments of the present invention provide a method, device, medium and equipment for identifying new users, which are used to solve the technical problem in the prior art that newly registered abnormal new users cannot be accurately identified on the live broadcast platform, resulting in damage to the rights and interests of the live broadcast platform.

[0006] In a first aspect, the present invention provides a method for identifying new users, the method comprising:

[0007] Obtain device information for new user registration, where the device information includes multiple attribute values;

[0008] For each attribute value, determining a first proportion of the number of normally registered devices corresponding to the attribute value in the total number of normally registered devices within a preset time period;

[0009] Determine a second proportion of the number of newly registered devices corresponding to the attribute value in the total number of newly registered devices;

[0010] Determining a first abnormality suspicion value of the device information based on the first proportion and the second proportion;

[0011] Determine a second abnormality suspicion value corresponding to each of the attribute values ​​based on the first proportion, the second proportion, and the first abnormality suspicion value;

[0012] Identify new users based on the second abnormal suspicion value.

[0013] In the above solution, the determining of a first proportion of the number of normally registered devices corresponding to the attribute value in the total number of normally registered devices within the preset time period includes:

[0014] According to the formula Determine a first proportion f(e) of the number of normally registered devices corresponding to the attribute value in the total number of normally registered devices; wherein,

[0015] The e is any attribute value in the device information S, the N(e) is the number of normally registered devices corresponding to the attribute value, and the N(S) is the total number of normally registered devices.

[0016] In the above solution, determining the second proportion of the number of newly registered devices corresponding to the attribute value in the total number of newly registered devices includes:

[0017] According to the formula Determine a second proportion v(e) of the number of newly registered devices corresponding to the attribute value in the total number of newly registered devices; wherein,

[0018] The e is any attribute value in the device information S, the M(e) is the number of newly registered devices corresponding to the attribute value, and the M(S) is the total number of newly registered devices.

[0019] In the above solution, determining the first abnormality suspicion value of the device information based on the first proportion and the second proportion includes:

[0020] Determine a device distribution difference value corresponding to each attribute value in the device information according to the first proportion and the second proportion;

[0021] A first abnormality suspicion value of the device information is determined based on the device distribution difference corresponding to each attribute value.

[0022] In the above solution, determining the device distribution difference value corresponding to each attribute value in the device information according to the first proportion and the second proportion includes:

[0023] According to the formula Determine the device distribution difference value a corresponding to each attribute value in the device information S (e) where:

[0024] The f(e) is the first proportion of the number of normally registered devices corresponding to the attribute value e in the total number of normally registered devices, the v(e) is the second proportion of the number of newly registered devices corresponding to the attribute value e in the total number of newly registered devices, and the e is any attribute value in the device information S.

[0025] In the above solution, the determining the first abnormality suspicion value of the device information based on the device distribution difference corresponding to each attribute value includes:

[0026] According to the formula Determine the first abnormality suspicion value g of the device information S ;in,

[0027] The a S (e) is the device distribution difference value corresponding to each attribute value e in the device information S, f(e) is the first proportion of the number of normally registered devices corresponding to the attribute value e in the total number of normally registered devices, and v(e) is the second proportion of the number of newly registered devices corresponding to the attribute value e in the total number of newly registered devices.

[0028] In the above solution, determining the second abnormality suspicion value corresponding to each attribute value based on the first proportion, the second proportion and the first abnormality suspicion value includes:

[0029] According to the formula Determine the second abnormal suspicion value g corresponding to each attribute value S (e) where:

[0030] The g S is the first abnormality suspicion value of the device information S, the a S (e) is the device distribution difference value corresponding to the attribute value e in the device information S, f(e) is the first proportion of the number of normally registered devices corresponding to the attribute value e in the total number of normally registered devices, and v(e) is the second proportion of the number of newly registered devices corresponding to the attribute value e in the total number of newly registered devices.

[0031] In a second aspect, the present invention provides a device for identifying new users, the device comprising:

[0032] An acquisition unit, used to acquire device information for registering a new user, wherein the device information includes a plurality of attribute values;

[0033] A first determining unit is used to determine, for each attribute value, a first proportion of the number of normally registered devices corresponding to the attribute value in the total number of normally registered devices within a preset time period; and determine a second proportion of the number of newly registered devices corresponding to the attribute value in the total number of newly registered devices;

[0034] A second determining unit, configured to determine a first abnormality suspicion value of the device information based on the first proportion and the second proportion;

[0035] A third determining unit, configured to determine a second abnormality suspicion value corresponding to each of the attribute values ​​based on the first proportion, the second proportion, and the first abnormality suspicion value;

[0036] An identification unit is used to identify new users based on the second abnormal suspicion value.

[0037] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the methods described in the first aspect.

[0038] In a fourth aspect, the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any one of the methods described in the first aspect when executing the program.

[0039] The present invention provides a method, device, medium and equipment for identifying newly-acquired users, the method comprising: obtaining device information of newly-acquired users registered, the device information comprising multiple attribute values; for each attribute value, determining a first proportion of the number of normally-registered devices corresponding to the attribute value in the total number of normally-registered devices within a preset time period; determining a second proportion of the number of newly-acquired devices corresponding to the attribute value in the total number of newly-acquired devices; determining a first abnormal suspicion value of the device information based on the first proportion and the second proportion; determining a second abnormal suspicion value corresponding to each attribute value based on the first proportion, the second proportion and the first abnormal suspicion value; identifying newly-acquired users based on the second abnormal suspicion value; in this way, even if the newly-acquired users registered do not generate any behavioral events after registering on the live broadcast platform, the second abnormal suspicion value can be determined based on the difference between the device information used for registration and the device information for normal registration, and whether the newly-acquired users are abnormal users can be accurately identified based on the second suspicion value, with strong objectivity, thereby ensuring the accuracy of identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0041] Figure 1 A schematic diagram of a flow chart of a method for identifying new users provided by an embodiment of the present invention;

[0042] Figure 2 A schematic diagram of the structure of a device for identifying new users provided by an embodiment of the present invention;

[0043] Figure 3 A schematic diagram of the structure of a computer device for identifying new users provided by an embodiment of the present invention;

[0044] Figure 4A schematic diagram of the structure of a computer-readable storage medium for identifying new users provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to solve the technical problem in the prior art that newly registered abnormal new users cannot be accurately identified on the live broadcast platform, resulting in damage to the rights and interests of the live broadcast platform, the present invention provides a method, device, medium and equipment for identifying new users.

[0046] In order to better understand the above technical scheme, the technical scheme of the embodiments of this specification is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical scheme of the embodiments of this specification, rather than limitations on the technical scheme of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0047] This embodiment provides a method for identifying new users. Figure 1 As shown, the method includes:

[0048] S110, obtaining device information of a new user registration, wherein the device information includes a plurality of attribute values;

[0049] Generally speaking, when a black market user shares a registration address with multiple new users, in order to reduce the cost of using a real device, the black market user will modify the relevant properties of the device through a virtual machine and simulator, forge a fake device to register new users, and thus act as a new user. Therefore, this embodiment identifies the new user based on the device information registered by the new user to ensure the accuracy of the identification.

[0050] Therefore, this step needs to obtain the device information of the new user registration, which includes multiple attribute values. For example, the attribute values ​​include: device brand, device model, resolution, CPU model, battery power, etc.

[0051] S111, for each attribute value, determining a first proportion of the number of normally registered devices corresponding to the attribute value in the total number of normally registered devices within a preset time period; determining a second proportion of the number of newly registered devices corresponding to the attribute value in the total number of newly registered devices;

[0052] Because black market users may forge a certain attribute value of a device, or forge several attribute values, for each attribute value, it is necessary to determine the first proportion of the number of normally registered devices corresponding to the attribute value within the preset time period in the total number of normally registered devices; determine the second proportion of the number of newly registered devices corresponding to the attribute value in the total number of newly registered devices.

[0053] Among them, normal registration can be understood as registration performed during inactive times (such as new user acquisition activities); the preset time period can be set according to actual conditions, such as 7 days, 15 days or 30 days.

[0054] In an optional embodiment, determining a first proportion of the number of normally registered devices corresponding to the attribute value in the total number of normally registered devices within a preset time period includes:

[0055] According to the formula Determine the first proportion f(e) of the number of normally registered devices corresponding to the attribute value in the total number of normally registered devices; wherein,

[0056] e is any attribute value in the device information S, N(e) is the number of normal registered devices corresponding to the attribute value e, and N(S) is the total number of normal registered devices.

[0057] In an optional embodiment, determining a second proportion of the number of newly registered devices corresponding to the attribute value in the total number of newly registered devices includes:

[0058] According to the formula Determine the second proportion v(e) of the number of newly registered devices corresponding to the attribute value in the total number of newly registered devices; wherein,

[0059] e is any attribute value in the device information S, M(e) is the number of newly registered devices corresponding to the attribute value e, and M(S) is the total number of newly registered devices.

[0060] In this way, for each attribute value e, there is a corresponding first proportion and second proportion.

[0061] This step determines the first proportion and the second proportion corresponding to each attribute value, so that in the subsequent process, the distribution difference between the number of each attribute value generated in the new customer acquisition process and the number generated in the normal registration process can be accurately analyzed, thereby improving the recognition accuracy.

[0062] S112, determining a first abnormality suspicion value of the device information based on the first proportion and the second proportion;

[0063] After the first proportion and the second proportion corresponding to each attribute value are determined, a first abnormality suspicion value of the device information is determined based on the first proportion and the second proportion.

[0064] In an optional embodiment, determining a first abnormality suspicion value of the device information based on the first proportion and the second proportion includes:

[0065] Determine a device distribution difference value corresponding to each attribute value in the device information according to the first proportion and the second proportion;

[0066] A first abnormality suspicion value of the device information is determined based on the device distribution difference corresponding to each attribute value.

[0067] In an optional embodiment, determining the device distribution difference value corresponding to each attribute value in the device information according to the first proportion and the second proportion includes:

[0068] According to the formula Determine the device distribution difference value a corresponding to each attribute value e in the device information S S (e) where:

[0069] f(e) is the first proportion of the number of normally registered devices corresponding to the attribute value e in the total number of normally registered devices, v(e) is the second proportion of the number of newly registered devices corresponding to the attribute value e in the total number of newly registered devices, and e is any attribute value in the device information S.

[0070] The principle of the above formula is: if f(e) and v(e) are significantly different, then and There will be a larger one in the equation; only when f(e) and v(e) are very close, and Therefore, for the cases of registration through new user acquisition activities and normal registration, the greater the difference in the distribution of users with attribute e in device information S, the greater the difference in a S (e) is larger. And this formula adopts This form of function can consider both the absolute impact of x and the degree of change of x compared to y; that is, this embodiment takes into account the absolute impact of f(e) and v(e) on the device distribution difference value, and also takes into account the impact of the degree of change of f(e) compared to v(e) on the device distribution difference value.

[0071] In an optional embodiment, determining the first abnormality suspicion value of the device information based on the device distribution difference value corresponding to each attribute value includes:

[0072] According to the formula Determine the first abnormality suspicion value g of the device information S ;in,

[0073] a S (e) is the device distribution difference value corresponding to each attribute value e in the device information S, f(e) is the first proportion of the number of normally registered devices corresponding to the attribute value e in the total number of normally registered devices, and v(e) is the second proportion of the number of newly registered devices corresponding to the attribute value e in the total number of newly registered devices.

[0074] The principle of the above formula is: when the first proportion v(e) increases significantly compared to the second proportion f(e), the anomalies of v(e) and f(e) need to be paid attention to. Therefore, when determining the abnormal suspicion value of device information S, only the attribute value e with v(e) greater than f(e) is calculated, and the distribution difference values ​​of these attributes are added to obtain the first abnormal suspicion value of device information S. The larger the first abnormal suspicion value, the more likely the device information S is abnormal.

[0075] This step determines the device distribution difference value corresponding to each attribute value, and then determines the first abnormal suspected value of the device information based on the distribution difference value. This first screens out the abnormal device information and lays a data foundation for the subsequent determination of the second abnormal suspected value corresponding to each attribute value.

[0076] S113, determining a second abnormality suspicion value corresponding to each of the attribute values ​​based on the first proportion, the second proportion, and the first abnormality suspicion value;

[0077] After the first abnormality suspicion value is determined, the second abnormality suspicion value corresponding to each attribute value is determined based on the first proportion, the second proportion and the first abnormality suspicion value.

[0078] Here, since each attribute value corresponds to a first proportion and a second proportion, a corresponding second abnormality suspicion value can be determined for each attribute value.

[0079] In an optional embodiment, determining the second abnormality suspicion value corresponding to each of the attribute values ​​based on the first proportion, the second proportion, and the first abnormality suspicion value includes:

[0080] According to the formula Determine the second abnormal suspicion value g corresponding to each attribute value S (e) where:

[0081] g S is the first abnormality suspicion value of the device information S, a S (e) is the device distribution difference value corresponding to the attribute value e in the device information S, f(e) is the first proportion of the number of normally registered devices corresponding to the attribute value e in the total number of normally registered devices, v(e) is the second proportion of the number of newly registered devices corresponding to the attribute value e in the total number of newly registered devices, and e is any attribute value in the device information S.

[0082] The principle of the above formula is: the influencing factors of the second abnormality suspicion value of the attribute value e include the following: the first abnormality suspicion value g of the device information S to which the attribute value e belongs S , the device distribution difference value a of attribute value e S (e), and the growth ratio of v(e) to f(e) The larger the value of each of these three values, the more suspicious the attribute value e is. Since f(e) may be 0, Rewrite In the form of, adding 1 to the logarithm ensures Greater than 1 to ensure that the logarithmic calculations make sense.

[0083] This step determines the three influencing factors of the second abnormality suspected value of the attribute value e, and determines the second abnormality suspected value corresponding to each attribute value according to the three influencing factors, thereby ensuring the accuracy of the second abnormality suspected value and improving the subsequent recognition accuracy.

[0084] S114: Identify new users based on the second abnormality suspicion value.

[0085] After the second abnormality suspicion value is determined, new users are identified based on the second abnormality suspicion value.

[0086] In an optional embodiment, identifying new users based on the second abnormal suspicion value includes:

[0087] If the second abnormal suspicion value corresponding to the attribute value is greater than the preset risk threshold, the registered device corresponding to the attribute value is determined to be an abnormal device, and the new user corresponding to the registered device is determined to be an abnormal user.

[0088] For example, suppose a certain attribute value is device brand A, and device brand A corresponds to f(e)=0.01, v(e)=0.1;

[0089]

[0090] g s (e) = 0.5

[0091] then:

[0092]

[0093] Assuming that the risk threshold is 0.4, and 0.54 is greater than 0.4, it is determined that the new users registered using brand A are abnormal users.

[0094] This can effectively identify abnormal new users in new user acquisition activities.

[0095] In this embodiment, after determining that an abnormal new user is attracted, the method further includes:

[0096] Get the sharing user corresponding to the abnormal new user, mark the sharing user as risk, and recover the sharing user's reward for attracting the abnormal user.

[0097] This step identifies abnormal new users by comparing the second abnormal suspicion value and the risk threshold, which is highly objective and can improve the accuracy of identifying abnormal new users.

[0098] Based on the same inventive concept, this embodiment also provides a device for identifying new users. Figure 2 As shown, the device comprises:

[0099] An acquisition unit 21 is used to acquire device information of a new user registration, wherein the device information includes a plurality of attribute values;

[0100] The first determining unit 22 is used to determine, for each attribute value, a first proportion of the number of normally registered devices corresponding to the attribute value in the total number of normally registered devices within a preset time period; and determine a second proportion of the number of newly registered devices corresponding to the attribute value in the total number of newly registered devices;

[0101] A second determining unit 23, configured to determine a first abnormality suspicion value of the device information based on the first proportion and the second proportion;

[0102] A third determining unit 24 is used to determine a second abnormality suspicion value corresponding to each of the attribute values ​​based on the first proportion, the second proportion and the first abnormality suspicion value;

[0103] The identification unit 25 is used to identify new users based on the second abnormality suspicion value.

[0104] The specific functions of the above units can be found in the corresponding descriptions in the above method embodiments, which will not be described in detail here. Since the device introduced in the embodiment of the present invention is a device used to implement the method of the embodiment of the present invention, based on the method introduced in the embodiment of the present invention, those skilled in the art can understand the specific structure and deformation of the device, so they will not be described in detail here. All devices used in the method of the embodiment of the present invention belong to the scope of protection of the present invention.

[0105] The method, device, medium and equipment for identifying new users provided by the present invention can bring at least the following beneficial effects:

[0106] The present invention provides a method, device, medium and equipment for identifying newly-acquired users, the method comprising: obtaining device information of newly-acquired users registered, the device information comprising multiple attribute values; for each attribute value, determining a first proportion of the number of normally-registered devices corresponding to the attribute value in the total number of normally-registered devices within a preset time period; determining a second proportion of the number of newly-acquired devices corresponding to the attribute value in the total number of newly-acquired devices; determining a first abnormal suspicion value of the device information based on the first proportion and the second proportion; determining a second abnormal suspicion value corresponding to each attribute value based on the first proportion, the second proportion and the first abnormal suspicion value; identifying newly-acquired users based on the second abnormal suspicion value; in this way, even if the newly-acquired users registered do not generate any behavioral events after registering on the live broadcast platform, the abnormal suspicion value can be determined based on the difference between the device information used for registration and the device information for normal registration, and then accurately identifying whether the newly-acquired users are abnormal users based on the suspicion value, with strong objectivity, thereby ensuring the accuracy of identification.

[0107] Based on the same inventive concept, this embodiment provides a computer device 300, such as Figure 3 As shown, it includes a memory 310, a processor 320, and a computer program 31 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, the following steps are implemented:

[0108] Obtain device information for new user registration, where the device information includes multiple attribute values;

[0109] For each attribute value, determining a first proportion of the number of normally registered devices corresponding to the attribute value in the total number of normally registered devices within a preset time period;

[0110] Determine a second proportion of the number of newly registered devices corresponding to the attribute value in the total number of newly registered devices;

[0111] Determining a first abnormality suspicion value of the device information based on the first proportion and the second proportion;

[0112] Determine a second abnormality suspicion value corresponding to each of the attribute values ​​based on the first proportion, the second proportion, and the first abnormality suspicion value;

[0113] Identify new users based on the second abnormal suspicion value.

[0114] In a specific implementation process, when the processor 320 executes the computer program 311, any implementation method in the foregoing embodiments can be implemented.

[0115] Since the computer device introduced in this embodiment is a device used to implement a method for identifying new users in an embodiment of the present application, based on the method introduced in the aforementioned embodiment of the present application, a person skilled in the art can understand the specific implementation of the computer device of the present embodiment and its various variations, so how the server implements the method in the embodiment of the present application is not described in detail here. As long as the device used by a person skilled in the art to implement the method in the embodiment of the present application is within the scope of protection of the present application.

[0116] Based on the same inventive concept, this embodiment provides a computer-readable storage medium 400, such as Figure 4 As shown, a computer program 411 is stored thereon, and when the computer program 411 is executed by a processor, the following steps are implemented:

[0117] Obtain device information for new user registration, where the device information includes multiple attribute values;

[0118] For each attribute value, determining a first proportion of the number of normally registered devices corresponding to the attribute value in the total number of normally registered devices within a preset time period;

[0119] Determine a second proportion of the number of newly registered devices corresponding to the attribute value in the total number of newly registered devices;

[0120] Determining a first abnormality suspicion value of the device information based on the first proportion and the second proportion;

[0121] Determine a second abnormality suspicion value corresponding to each of the attribute values ​​based on the first proportion, the second proportion, and the first abnormality suspicion value;

[0122] Identify new users based on the second abnormal suspicion value.

[0123] In the specific implementation process, when the computer program 411 is executed by a processor, any implementation method in the aforementioned embodiments can be implemented.

[0124] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0125] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0126] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0127] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0128] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0129] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for identifying new users, characterized in that: The method comprises: Obtain device information for new user registration, where the device information includes multiple attribute values; For each attribute value, determining a first proportion of the number of normally registered devices corresponding to the attribute value in the total number of normally registered devices within a preset time period; Determine a second proportion of the number of newly registered devices corresponding to the attribute value in the total number of newly registered devices; Determining a first abnormality suspicion value of the device information based on the first proportion and the second proportion; Determine a second abnormality suspicion value corresponding to each of the attribute values ​​based on the first proportion, the second proportion, and the first abnormality suspicion value; Identifying a new user based on the second abnormal suspicion value, wherein the identifying a new user based on the second abnormal suspicion value includes: if the second abnormal suspicion value corresponding to the attribute value is greater than a preset risk threshold, determining that the registered device corresponding to the attribute value is an abnormal device, and determining that the new user corresponding to the registered device is an abnormal user; The determining a first proportion of the number of normally registered devices corresponding to the attribute value in the total number of normally registered devices within the preset time period includes: According to the formula Determine a first proportion f(e) of the number of normally registered devices corresponding to the attribute value in the total number of normally registered devices; wherein, The e is any attribute value in the device information S, the N(e) is the number of normal registered devices corresponding to the attribute value, and the N(S) is the total number of normal registered devices; The determining a second proportion of the number of newly registered devices corresponding to the attribute value in the total number of newly registered devices includes: According to the formula Determine a second proportion v(e) of the number of newly registered devices corresponding to the attribute value in the total number of newly registered devices; wherein, The e is any attribute value in the device information S, the M(e) is the number of newly registered devices corresponding to the attribute value, and the M(S) is the total number of newly registered devices; The determining a first abnormality suspicion value of the device information based on the first proportion and the second proportion includes: Determine a device distribution difference value corresponding to each attribute value in the device information according to the first proportion and the second proportion; Determine a first abnormality suspicion value of the device information based on a device distribution difference corresponding to each attribute value; The determining, according to the first proportion and the second proportion, a device distribution difference value corresponding to each attribute value in the device information includes: According to the formula Determine the device distribution difference value a corresponding to each attribute value in the device information S (e) where: f(e) is a first proportion of the number of normally registered devices corresponding to the attribute value e in the total number of normally registered devices, v(e) is a second proportion of the number of newly registered devices corresponding to the attribute value e in the total number of newly registered devices, and e is any attribute value in the device information S; The determining the first abnormality suspicion value of the device information based on the device distribution difference corresponding to each attribute value includes: According to the formula Determine the first abnormality suspicion value g of the device information S ;in, The a S (e) is the device distribution difference value corresponding to each attribute value e in the device information S, f(e) is the first proportion of the number of normally registered devices corresponding to the attribute value e in the total number of normally registered devices, and v(e) is the second proportion of the number of newly registered devices corresponding to the attribute value e in the total number of newly registered devices; The determining, based on the first proportion, the second proportion, and the first abnormality suspected value, a second abnormality suspected value corresponding to each of the attribute values ​​includes: According to the formula Determine the second abnormal suspicion value g corresponding to each attribute value S (e) where: The g S is the first abnormality suspicion value of the device information S, the a S (e) is the device distribution difference value corresponding to the attribute value e in the device information S, f(e) is the first proportion of the number of normally registered devices corresponding to the attribute value e in the total number of normally registered devices, and v(e) is the second proportion of the number of newly registered devices corresponding to the attribute value e in the total number of newly registered devices.

2. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method described in claim 1 is implemented.

3. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to claim 1 is implemented.