Disclosure of Invention
Aiming at the problems existing in the prior art, the embodiment of the invention provides a method, a device, a medium and equipment for identifying a new user, which are used for solving the technical problem that in the prior art, the new user which is newly registered cannot be accurately identified in a live platform, so that the rights and interests of the live platform are damaged.
In a first aspect, the present invention provides a method of identifying a pull new user, the method comprising:
Acquiring equipment information registered by a pull-up user, wherein the equipment information comprises a plurality of attribute values;
For each attribute value, determining a first duty ratio of the number of normal registration devices corresponding to the attribute value in the total number of the normal registration devices in a preset time period;
determining a second duty ratio of the number of the new registered devices corresponding to the attribute value in the total number of the new registered devices;
determining a first anomaly suspicion value of the equipment information based on the first duty cycle and the second duty cycle;
Determining a second abnormal suspicion value corresponding to each attribute value based on the first duty ratio, the second duty ratio and the first abnormal suspicion value;
and identifying a pull-up user based on the second abnormal suspicion value.
In the above solution, the determining a first duty ratio of the number of normal registered devices corresponding to the attribute value in the total number of normal registered devices in the preset period of time includes:
according to the formulaDetermining a first duty ratio f (e) of the number of normal registered devices corresponding to the attribute value in the total number of the normal registered devices; wherein,
And e is any attribute value in the equipment information S, N (e) is the number of normal registered equipment corresponding to the attribute value, and N (S) is the total number of the normal registered equipment.
In the above solution, the determining the second duty ratio of the number of newly-registered devices corresponding to the attribute value in the total number of newly-registered devices includes:
according to the formulaDetermining a second duty ratio v (e) of the number of the new registered devices corresponding to the attribute value in the total number of the new registered devices; wherein,
And e is any attribute value in the equipment information S, M (e) is the number of the newly-pulled registered equipment corresponding to the attribute value, and M (S) is the total number of the newly-pulled registered equipment.
In the above solution, the determining the first abnormal suspicion value of the device information based on the first duty ratio and the second duty ratio includes:
Determining a device distribution difference value corresponding to each attribute value in the device information according to the first duty ratio and the second duty ratio;
and determining a first abnormal suspicion value of the equipment information based on the equipment distribution difference value corresponding to each attribute value.
In the above solution, the determining, according to the first duty ratio and the second duty ratio, a device distribution difference value corresponding to each attribute value in the device information includes:
according to the formulaDetermining a device distribution difference value aS (e) corresponding to each attribute value in the device information; wherein,
The f (e) is the first duty ratio of the number of the normal registered devices corresponding to the attribute value e in the total number of the normal registered devices, the v (e) is the second duty ratio of the number of the new registered devices corresponding to the attribute value e in the total number of the new registered devices, and the e is any attribute value in the device information S.
In the above solution, the determining the first abnormal suspicion value of the device information based on the device distribution difference value corresponding to each attribute value includes:
according to the formulaDetermining a first abnormal suspicion value gS of the equipment information; wherein,
The aS (e) is a device distribution difference value corresponding to each attribute value e in the device information S, the f (e) is a first duty ratio of the number of normal registered devices corresponding to the attribute value e in the total number of normal registered devices, and the v (e) is a second duty ratio of the number of new registered devices corresponding to the attribute value e in the total number of new registered devices.
In the above solution, the determining, based on the first duty ratio, the second duty ratio, and the first abnormal suspicion value, a second abnormal suspicion value corresponding to each attribute value includes:
according to the formulaDetermining a second abnormal suspicion value gS (e) corresponding to each attribute value; wherein,
GS is a first abnormal suspicion value of the device information S, aS (e) is a device distribution difference value corresponding to an attribute value e in the device information S, f (e) is a first duty ratio of the number of normal registered devices corresponding to the attribute value e in the total number of normal registered devices, and v (e) is a second duty ratio of the number of new registered devices corresponding to the attribute value e in the total number of new registered devices.
In a second aspect, the present invention provides an apparatus for identifying a pull new user, the apparatus comprising:
An obtaining unit, configured to obtain device information registered by a pull new user, where the device information includes a plurality of attribute values;
A first determining unit, configured to determine, for each attribute value, a first duty ratio of a number of normal registered devices corresponding to the attribute value in a total number of normal registered devices in a preset period; determining a second duty ratio of the number of the new registered devices corresponding to the attribute value in the total number of the new registered devices;
A second determining unit configured to determine a first abnormality suspicion value of the device information based on the first duty ratio and the second duty ratio;
A third determining unit, configured to determine a second anomaly suspicion value corresponding to each attribute value based on the first duty ratio, the second duty ratio, and the first anomaly suspicion value;
and the identification unit is used for identifying the new user based on the second abnormal suspicion value.
In a third aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the method of any of the first aspects.
In a fourth aspect, the present invention provides a computer apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of the first aspects when executing the program.
The invention provides a method, a device, a medium and equipment for identifying a new user, wherein the method comprises the following steps: acquiring equipment information registered by a pull-up user, wherein the equipment information comprises a plurality of attribute values; for each attribute value, determining a first duty ratio of the number of normal registration devices corresponding to the attribute value in the total number of the normal registration devices in a preset time period; determining a second duty ratio of the number of the new registered devices corresponding to the attribute value in the total number of the new registered devices; determining a first anomaly suspicion value of the equipment information based on the first duty cycle and the second duty cycle; determining a second abnormal suspicion value corresponding to each attribute value based on the first duty ratio, the second duty ratio and the first abnormal suspicion value; identifying a pull-up user based on the second abnormal suspicion; therefore, even if no behavior event is generated after the live platform registration of the user registered by the pull-up new, the second abnormal suspicion value can be determined based on the difference between the equipment information used by registration and the equipment information registered normally, whether the user registered by the pull-up new is an abnormal user or not can be accurately identified based on the second suspicion value, objectivity is high, and identification accuracy is further ensured.
Detailed Description
The invention provides a method, a device, a medium and equipment for identifying a new user, which are used for solving the technical problem that the rights and interests of a live broadcast platform are damaged because the new registered abnormal new user cannot be accurately identified in the live broadcast platform in the prior art.
In order to better understand the technical solutions described above, the technical solutions of the embodiments of the present specification are described in detail below through the accompanying drawings and the specific embodiments, and it should be understood that the specific features of the embodiments of the present specification and the specific features of the embodiments of the present specification are detailed descriptions of the technical solutions of the embodiments of the present specification, and not limit the technical solutions of the present specification, and the technical features of the embodiments of the present specification may be combined without conflict.
The present embodiment provides a method for identifying a pull new user, as shown in fig. 1, the method includes:
s110, acquiring equipment information registered by a pull-up user, wherein the equipment information comprises a plurality of attribute values;
Generally, when a black-out user shares the registration addresses of a plurality of new users, in order to reduce the cost of using a real machine, the black-out user can modify the relevant attribute of the equipment through a virtual machine and a simulator, falsify false equipment to perform the new registration, and then act as the new users. Therefore, the embodiment identifies the pull-new user based on the device information registered by the pull-new user, and ensures the accuracy of identification.
This step therefore requires obtaining device information registered by the pull-up user, the device information comprising a plurality of attribute values. Such as attribute values include: device brand, device model, resolution, CPU model, battery power, etc.
S111, for each attribute value, determining a first duty ratio of the number of normal registration devices corresponding to the attribute value in the total number of the normal registration devices in a preset time period; determining a second duty ratio of the number of the new registered devices corresponding to the attribute value in the total number of the new registered devices;
Because a black-out user may forge a certain attribute value of the device or forge a certain attribute value, for each attribute value, a first duty ratio of the number of normal registered devices corresponding to the attribute value in the total number of normal registered devices needs to be determined; and determining a second duty ratio of the number of the new registered devices corresponding to the attribute value in the total number of the new registered devices.
Normal registration may be understood as registration that occurs when inactive (e.g., newly active); the preset time period may be set according to practical situations, for example, may be 7 days, 15 days or 30 days.
In an alternative embodiment, determining the first ratio of the number of normal registered devices corresponding to the attribute value in the total number of normal registered devices in the preset time period includes:
according to the formulaDetermining a first duty ratio f (e) of the number of normal registered devices corresponding to the attribute value in the total number of the normal registered devices; wherein,
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.
In an alternative embodiment, determining the second duty ratio of the number of newly registered devices corresponding to the attribute value in the total number of newly registered devices includes:
according to the formulaDetermining a second duty ratio v (e) of the number of the new registered devices corresponding to the attribute value in the total number of the new registered devices; wherein,
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.
Thus, for each attribute value e, there is a corresponding first and second duty cycle.
The first duty ratio and the second duty ratio corresponding to each attribute value are determined, so that the distribution difference between the quantity generated in the new pulling process and the quantity generated in the normal registration process corresponding to each attribute value can be accurately analyzed in the subsequent process, and the identification precision is further improved.
S112, determining a first abnormality suspicion value of the equipment information based on the first duty ratio and the second duty ratio;
After the first duty ratio and the second duty ratio corresponding to each attribute value are determined, determining a first abnormal suspicion value of the equipment information based on the first duty ratio and the second duty ratio.
In an alternative embodiment, determining a first anomaly suspicion for the equipment information based on the first and second duty cycles includes:
determining a device distribution difference value corresponding to each attribute value in the device information according to the first duty ratio and the second duty ratio;
And determining a first abnormal suspicion value of the equipment information based on the equipment distribution difference value corresponding to each attribute value.
In an alternative embodiment, determining the device distribution difference value corresponding to each attribute value in the device information according to the first duty ratio and the second duty ratio includes:
according to the formulaDetermining a device distribution difference value aS (e) corresponding to each attribute value e in the device information S; wherein,
F (e) is the first duty ratio of the number of normal registered devices corresponding to the attribute value e in the total number of normal registered devices, v (e) is the second duty ratio of the number of new registered devices corresponding to the attribute value e in the total number of new registered devices, and e is any attribute value in the device information S.
The principle of the above formula is: if f (e) and v (e) have large differences, thenAndOne of which is relatively large; only when f (e) and v (e) are very close,AndWill be small and therefore the added value will be small. Thus, for the case of registering with a pull new activity and registering normally, the larger the user distribution difference of attribute e in the device information S, the larger aS (e) is. And the formula adoptsThe function of this form can take into account both the absolute influence of x and the degree to which x varies compared to y; that is, the present embodiment considers both the absolute influence of f (e) and v (e) on the device distribution difference value and the influence of the variation degree of f (e) on the device distribution difference value compared with v (e).
In an alternative embodiment, determining the first abnormal suspicion value of the device information based on the device distribution difference value corresponding to each attribute value includes:
according to the formulaDetermining a first abnormal suspicion value gS of the equipment information; wherein,
AS (e) is a device distribution difference value corresponding to each attribute value e in the device information S, f (e) is a first duty ratio of the number of normal registered devices corresponding to the attribute value e in the total number of normal registered devices, and v (e) is a second duty ratio of the number of new registered devices corresponding to the attribute value e in the total number of new registered devices.
The principle of the above formula is: anomalies in v (e) and f (e) are of concern when the first duty cycle v (e) increases significantly compared to the second duty cycle f (e). Therefore, when determining the abnormality suspicion value of the equipment information S, only the attribute value e having v (e) larger than f (e) is calculated, and the distribution difference values of these attributes are added to obtain the first abnormality suspicion value of the equipment information S. The larger the first abnormality suspicion value, the more likely the device information S is abnormal.
According to the method, the first abnormal suspicion value of the equipment information is determined according to the distribution difference value by determining the equipment distribution difference value corresponding to each attribute value, the equipment information with the abnormality is screened out first, and a data foundation is laid for the subsequent determination of the second abnormal suspicion value corresponding to each attribute value.
S113, determining a second abnormal suspicion value corresponding to each attribute value based on the first duty ratio, the second duty ratio and the first abnormal suspicion value;
After the first abnormal suspicion value is determined, a second abnormal suspicion value corresponding to each attribute value is determined based on the first duty ratio, the second duty ratio and the first abnormal suspicion value.
Here, since each attribute value corresponds to one of the first duty ratio and the second duty ratio, the corresponding second abnormal suspicion value can be determined for each attribute value.
In an alternative embodiment, determining a second exception suspicion value corresponding to each of the attribute values based on the first duty cycle, the second duty cycle, and the first exception suspicion value includes:
according to the formulaDetermining a second abnormal suspicion value gS (e) corresponding to each attribute value; wherein,
GS is a first abnormal suspicion value of the device information S, aS (e) is a device distribution difference value corresponding to an attribute value e in the device information S, f (e) is a first duty ratio of the number of normal registered devices corresponding to the attribute value e in the total number of normal registered devices, v (e) is a second duty ratio of the number of new registered devices corresponding to the attribute value e in the total number of new registered devices, and e is any attribute value in the device information S.
The principle of the above formula is: the second anomaly suspicion influencing factors of the attribute value e include the following: the first abnormality suspicion number gS of the device information S to which the attribute value e belongs, the device distribution difference value aS (e) of the attribute value e, and the growth ratio of v (e) to f (e)The larger each of these three values, the larger the suspicion of attribute value e. Since f (e) may be 0, it willIs rewritten intoIn the form of (2), 1 is added to the logarithm to ensureGreater than 1 to ensure that the logarithmic calculation is meaningful.
In the step, three influence factors of the second abnormal suspicion values of the attribute value e are determined, and the second abnormal suspicion value corresponding to each attribute value is determined according to the three influence factors, so that the accuracy of the second abnormal suspicion values is ensured, and the subsequent recognition accuracy is further improved.
S114, identifying a new user based on the second abnormal suspicion value.
And after the second abnormal suspicion value is determined, identifying the refreshing user based on the second abnormal suspicion value.
In an alternative embodiment, identifying a pull new user based on the second outlier suspicion includes:
if the second abnormal suspected value corresponding to the attribute value is larger than the preset risk threshold, determining that the registration equipment corresponding to the attribute value is abnormal, and determining that the pull-up user corresponding to the registration equipment is abnormal.
For example, assume that a certain attribute value is device brand a, f (e) =0.01 and v (e) =0.1 corresponding to device brand a;
gs(e)＝0.5
Then:
Assuming a risk threshold of 0.4, where 0.54 is greater than 0.4, then it is determined that the pull new user registered with brand A is an abnormal user.
Thus, the abnormal new pulling user of the new pulling activity can be effectively identified.
In this embodiment, after determining the abnormal refresh user, the method further includes:
and obtaining the sharing user corresponding to the abnormal refreshing user, marking a risk mark on the sharing user, and recovering the refreshing rewards of the abnormal users of the sharing user.
In the step, the abnormal new user is identified by comparing the second abnormal suspicion value with the risk threshold, and the objectivity is high, so that the identification precision of the abnormal new user can be improved.
Based on the same inventive concept, this embodiment further provides a device for identifying a new user, as shown in fig. 2, where the device includes:
An acquisition unit 21 for acquiring device information registered by a pull-up user, the device information including a plurality of attribute values;
A first determining unit 22, configured to determine, for each attribute value, a first duty ratio of a number of normal registered devices corresponding to the attribute value in a total number of normal registered devices in a preset period; determining a second duty ratio of the number of the new registered devices corresponding to the attribute value in the total number of the new registered devices;
A second determining unit 23 configured to determine a first abnormality suspicion value of the device information based on the first duty ratio and the second duty ratio;
a third determining unit 24, configured to determine a second anomaly suspicion value corresponding to each of the attribute values based on the first duty ratio, the second duty ratio, and the first anomaly suspicion value;
An identifying unit 25, configured to identify a pull-up user based on the second abnormal suspicion value.
The specific functions of the above units may be referred to the corresponding descriptions in the above method embodiments, and are not repeated herein. Since the device described in the embodiments of the present invention is a device used for implementing the method of the embodiments of the present invention, based on the method described in the embodiments of the present invention, a person skilled in the art can understand the specific structure and the deformation of the device, and therefore, the description thereof is omitted herein. All devices used in the method of the embodiment of the invention are within the scope of the invention.
The method, the device, the medium and the equipment for identifying the new user provided by the invention have the beneficial effects that:
The invention provides a method, a device, a medium and equipment for identifying a new user, wherein the method comprises the following steps: acquiring equipment information registered by a pull-up user, wherein the equipment information comprises a plurality of attribute values; for each attribute value, determining a first duty ratio of the number of normal registration devices corresponding to the attribute value in the total number of the normal registration devices in a preset time period; determining a second duty ratio of the number of the new registered devices corresponding to the attribute value in the total number of the new registered devices; determining a first anomaly suspicion value of the equipment information based on the first duty cycle and the second duty cycle; determining a second abnormal suspicion value corresponding to each attribute value based on the first duty ratio, the second duty ratio and the first abnormal suspicion value; identifying a pull-up user based on the second abnormal suspicion; therefore, even if no behavior event is generated after the live platform registration of the user registered by pulling the new user, the abnormal suspicion value can be determined based on the difference between the equipment information used by registration and the equipment information registered normally, and further whether the user registered by pulling the new user is an abnormal user or not can be accurately identified based on the suspicion value, the objectivity is high, and the identification accuracy is ensured.
Based on the same inventive concept, this embodiment provides a computer device 300, as shown in fig. 3, including a memory 310, a processor 320, and a computer program 31 stored on the memory 310 and executable on the processor 320, wherein the processor 320 implements the following steps when executing the computer program 311:
Acquiring equipment information registered by a pull-up user, wherein the equipment information comprises a plurality of attribute values;
For each attribute value, determining a first duty ratio of the number of normal registration devices corresponding to the attribute value in the total number of the normal registration devices in a preset time period;
determining a second duty ratio of the number of the new registered devices corresponding to the attribute value in the total number of the new registered devices;
determining a first anomaly suspicion value of the equipment information based on the first duty cycle and the second duty cycle;
Determining a second abnormal suspicion value corresponding to each attribute value based on the first duty ratio, the second duty ratio and the first abnormal suspicion value;
and identifying a pull-up user based on the second abnormal suspicion value.
In a specific implementation, when the processor 320 executes the computer program 311, any of the foregoing embodiments may be implemented.
Since the computer device described in this embodiment is a device for implementing the method for identifying a new user in this embodiment of the present application, those skilled in the art will be able to understand the specific implementation of the computer device and various modifications thereof based on the method described in the foregoing embodiment of the present application, so how the method in this embodiment of the present application is implemented by the server will not be described in detail herein. The apparatus used to implement the methods of embodiments of the present application will be within the scope of the intended protection of the present application.
Based on the same inventive concept, the present embodiment provides a computer-readable storage medium 400, as shown in fig. 4, having stored thereon a computer program 411, which computer program 411, when executed by a processor, realizes the steps of:
Acquiring equipment information registered by a pull-up user, wherein the equipment information comprises a plurality of attribute values;
For each attribute value, determining a first duty ratio of the number of normal registration devices corresponding to the attribute value in the total number of the normal registration devices in a preset time period;
determining a second duty ratio of the number of the new registered devices corresponding to the attribute value in the total number of the new registered devices;
determining a first anomaly suspicion value of the equipment information based on the first duty cycle and the second duty cycle;
Determining a second abnormal suspicion value corresponding to each attribute value based on the first duty ratio, the second duty ratio and the first abnormal suspicion value;
and identifying a pull-up user based on the second abnormal suspicion value.
In a specific implementation, the computer program 411 may implement any of the foregoing embodiments when executed by a processor.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
The above description is not intended to limit the scope of the invention, but is intended to cover any modifications, equivalents, and improvements within the spirit and principles of the invention.