CN106294508A - A kind of brush amount tool detection method and device - Google Patents
A kind of brush amount tool detection method and device Download PDFInfo
- Publication number
- CN106294508A CN106294508A CN201510317134.0A CN201510317134A CN106294508A CN 106294508 A CN106294508 A CN 106294508A CN 201510317134 A CN201510317134 A CN 201510317134A CN 106294508 A CN106294508 A CN 106294508A
- Authority
- CN
- China
- Prior art keywords
- user
- behavior characteristics
- users
- sorted group
- measured
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
Abstract
This application discloses a kind of brush amount tool detection method and device, method includes: obtain the behavioral data of at least one user corresponding with channel to be measured, the behavior characteristics of each user is generated according to the behavioral data of each user, the behavior characteristics utilizing each user calculates the behavior characteristics value of each user, with behavior characteristics value as class condition, user is classified, obtain several sorted group, when determining that in described sorted group, number of users meets preset decision plan, determine that described channel to be measured employs brush amount instrument.Owing to the behavior characteristics value of the user in each sorted group is similar or identical, if thus the number of users that comprises in one or more sorted group is the biggest, in then meaning this sorted group, most of user is fictitious users, namely may determine that channel to be measured employs brush amount instrument.The application method avoids existing distribution based on hardware access environment property parameters and detects the confinement problems that the method for brush amount instrument is latched in.
Description
Technical field
The application relates to networking technology area, more particularly, it relates to a kind of brush amount tool detection method and
Device.
Background technology
The intelligent terminal such as smart mobile phone popularize as various types of application APP (Application, application)
Provide carrier.Application provider, in order to promote oneself application, shows application by kinds of platform to user
And download function is provided, each platform is all considered as a channel of application.And as feedback,
After having new user to be have registered application account by certain channel, application provider needs to prop up to this channel
Pay certain development expenses.
In reality, some channel (platform), can profit in order to gain the development expenses of application provider by cheating
Generate false new user with brush amount instrument, process substantially: channel utilize brush amount instrument random or based on
Existing subscriber's data file, generates terminal unit IMEI (International Mobile Equipment
Identity, International Mobile Equipment Identity code), IMSI (International Mobile Subscriber
Identification Number, international mobile subscriber identity), MAC (Media Access Control,
Media interviews control) address, screen resolution, type, SIM number, cell-phone number, operator numbering or
The various parameters such as title, mobile phone operating system (OS) version, then using generate these parameters as newly
Customer parameter is registered.And for application vendor's end, typically merely by distinguishing that IMEI judges
Whether this user is new user, as long as namely unregistered mistake before the IMEI of current registration user, then it is assumed that
Current registration user is a new user, and then pays development expenses to corresponding channel.
In order to avoid the appearance of the problems referred to above, typically by detecting new registration under current channel in prior art
The IMSI of user, MAC Address, screen resolution, type, etc. hardware access environment property parameters point
Cloth is the most normal, differentiates and whether employs brush amount instrument under current channel.As a example by screen resolution,
If the screen resolution distribution of user has the biggest with all channel sub-screen resolution distribution under current channel
Difference, then mean that current channel may have been used brush amount instrument, citing is such as, new in next sky of channel 1
Registering the screen resolution of user and have 80% as screen resolution 1, remaining 20% is screen resolution 2 and screen
Curtain resolution 3, and under all channels, register the screen that the full screen resolution distribution situation of user is as 50%
The screen resolution 3 of resolution 2,30% and the screen resolution 1 of 20%.Obviously, the screen of channel 1 is differentiated
Rate distribution has the biggest difference with full screen resolution distribution, represents channel 1 and may have been used brush amount work
Tool.
But, existing distribution based on hardware access environment property parameters detects the method tool of brush amount instrument
There is certain limitation, the meeting when generating hardware and accessing environment property parameters of the brush amount instrument of some high-quality
Generate based on the distribution under each attribute truth, under the distribution situation of the most each parameter and normal channels
Each parameter distribution is consistent.For using the channel of this type of brush amount instrument, prior art will be unable to detect.
Summary of the invention
In view of this, this application provides a kind of brush amount tool detection method and device, be used for solving existing
There is circumscribed asking in the method that distribution based on hardware access environment property parameters detects brush amount instrument
Topic.
To achieve these goals, it is proposed that scheme as follows:
A kind of brush amount tool detection method, including:
Obtain the behavioral data of at least one user corresponding with channel to be measured；
According to the behavioral data of each user, generate the behavior characteristics of each user；
Utilize the behavior characteristics of each user, calculate the behavior characteristics value of each user；
With behavior characteristics value as class condition, each user is classified, obtain several sorted group；
When determining that in described sorted group, number of users meets preset decision plan, determine described channel to be measured
Employ brush amount instrument.
A kind of brush amount tool detection device, including:
Behavioral data acquiring unit, for obtaining the behavior number of at least one user corresponding with channel to be measured
According to；
Behavior characteristics signal generating unit, for the behavioral data according to each user, generates the row of each user
It is characterized；
Behavior characteristics value computing unit, for utilizing the behavior characteristics of each user, calculates each user's
Behavior characteristics value；
Classification processing unit, for behavior characteristics value as class condition, classifies to each user,
Obtain several sorted group；
Brush amount instrument determines unit, meets preset judgement plan for number of users in determining described sorted group
Time slightly, determine that described channel to be measured employs brush amount instrument.
From above-mentioned technical scheme it can be seen that the embodiment of the present application provide brush amount tool detection method,
Obtaining the behavioral data of at least one user corresponding with channel to be measured, behavioral data characterizes user and logs in
Various operations performed after application, and then each user can be generated according to the behavioral data of each user
Behavior characteristics, then utilize the behavior characteristics of each user to calculate the behavior characteristics value of each user, with
Behavior characteristics value is class condition, classifies user, obtains several sorted group, due to each point
The behavior characteristics value of the user in class group is similar or identical, if thus comprised in one or more sorted group
Number of users very big, then mean that major part user is fictitious users in this sorted group, namely permissible
Determine that channel to be measured employs brush amount instrument.Multiple fictitious users that the application utilizes brush amount instrument to produce exist
The principle of certain similarity is possessed in behavior, by calculating the behavior characteristics value of each user and the most right
User clusters, and then can judge whether channel to be measured uses brush amount instrument, keeps away according to predetermined policy
Exempt from existing to access the distribution of environment property parameters based on hardware and detect what the method for brush amount instrument was latched in
Confinement problems.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present application or technical scheme of the prior art, below will be to reality
Execute the required accompanying drawing used in example or description of the prior art to be briefly described, it should be apparent that below,
Accompanying drawing in description is only embodiments herein, for those of ordinary skill in the art, not
On the premise of paying creative work, it is also possible to obtain other accompanying drawing according to the accompanying drawing provided.
Fig. 1 is a kind of brush amount tool detection method flow diagram disclosed in the embodiment of the present application；
Fig. 2 is a kind of method flow determining channel to be measured use brush amount instrument disclosed in the embodiment of the present application
Figure；
Fig. 3 is the another kind of method stream determining channel to be measured use brush amount instrument disclosed in the embodiment of the present application
Cheng Tu；
Fig. 4 is a kind of brush amount tool detection apparatus structure schematic diagram disclosed in the embodiment of the present application；
Fig. 5 is that disclosed in the embodiment of the present application, a kind of brush amount instrument determines cellular construction schematic diagram；
Fig. 6 is that disclosed in the embodiment of the present application, another kind of brush amount instrument determines cellular construction schematic diagram；
Fig. 7 is a kind of behavior characteristics computing unit structural representation disclosed in the embodiment of the present application；
Fig. 8 is a kind of classification processing unit structural representation disclosed in the embodiment of the present application；
Fig. 9 is a kind of server hardware structural representation disclosed in the embodiment of the present application.
Detailed description of the invention
Before introducing the application scheme, first title or phrase to using in literary composition explains:
SimHash is a kind of dimensionality reduction technology, high dimension vector can be mapped to one-dimensional fingerprint, and it is the earliest
Proposed by Google, for removing duplicate webpages.The input of SimHash algorithm is a vector, and output is one
The fingerprint of individual f position.In order to state conveniently, it is assumed that input is the characteristic set of a user behavior, Mei Gete
Levying the weight of correspondence, SimHash algorithm is as follows:
1. the vectorial V of f dimension (f takes 64 herein) is initialized as 0, at the beginning of the binary number S of f position
Begin to turn to 0；
2. pair each feature: this feature produces the fingerprint b of a f position by traditional hash algorithm is right
I=1 to f, if the i-th bit of b is 1, then the i-th element of V (is weighed plus the weight of this feature herein
It is heavily 1)；Otherwise, the i-th element of V deducts the weight (weight is 1 herein) of this feature；
3. if the i-th element of V is more than 0, then the i-th bit of S is 1, is otherwise 0；
4. output fingerprint S.
Below in conjunction with the accompanying drawing in the embodiment of the present application, the technical scheme in the embodiment of the present application is carried out
Clearly and completely describe, it is clear that described embodiment is only some embodiments of the present application, and
It is not all, of embodiment.Based on the embodiment in the application, those of ordinary skill in the art are not doing
Go out the every other embodiment obtained under creative work premise, broadly fall into the scope of the application protection.
Seeing Fig. 1, Fig. 1 is a kind of brush amount tool detection method flow diagram disclosed in the embodiment of the present application.
As it is shown in figure 1, the method includes:
Step S100, obtain the behavioral data of at least one user corresponding with channel to be measured；
The user corresponding with channel to be measured refers to the user registered by channel to be measured.For this type of user,
Obtain it and log in the behavioral data produced after application.
Specifically, application server have recorded the behavioral data of each login user, takes in behavioral data
With channel mark, this channel mark shows active user by which channel is registered.
Behavioral data can comprise multiple, particular type need according to application type depending on, such as
For the application of the precious this kind of offer download function of application, its behavioral data can include off-the-shelf software scene
Amount of action, renewal that lower click is downloaded push to expose under behavior record quantity, fine work scene under scene and move
The quantity etc. made.
Certainly, for most of application, it generally individually can relate to following several behavioral data: uses
Family access record quantity, user's access duration time, the type that starts, login type, user participate in difference
The quantity of scene and the quantity etc. of user's click action.
It should be noted that we can obtain the behavior number of all users corresponding with channel to be measured
According to, only obtain the behavioral data of the new user registered in the same day or a period of time by channel to be measured.
Step S110, behavioral data according to each user, generate the behavior characteristics of each user；
Specifically, after obtaining the behavioral data of user, generate each user's according to preset method
Behavior characteristics.Behavior characteristics will behavioral data quantify after embodiment.User such as, is accessed by citing in advance
Record quantity is divided into multiple interval, and it is interval i.e. which the access record quantity of the user of acquisition specifically falls into
For a kind of behavior characteristics.
Step S120, utilize the behavior characteristics of each user, calculate the behavior characteristics value of each user；
The behavior characteristics of each user may comprise multiple, thus can use certain algorithm, based on
The behavior characteristics set of user, calculates the behavior characteristics value of user.
Ratio preferably, can use SimHash algorithm.
Step S130, with behavior characteristics value as class condition, each user is classified, obtains some
Individual sorted group；
Specifically, in each sorted group, the eigenvalue of user possesses certain similarity, namely represents same
In sorted group, the behavior of user is similar.
Step S140, when determining that in described sorted group, number of users meets preset decision plan, determine institute
State channel to be measured and employ brush amount instrument.
Specifically, preset decision plan can have multiple, referring particularly to hereafter relevant portion introduction.Due to
Multiple fictitious users produced by brush amount instrument possess certain similarity in behavior, are embodied in behavior characteristics
In value the most similar or identical, therefore by analyzing number of users in each sorted group, i.e. can determine that canal to be measured
Whether road employs brush amount instrument.
The brush amount tool detection method that the embodiment of the present application provides, obtains at least corresponding with channel to be measured
The behavioral data of individual user, behavioral data characterizes various operations performed after user logs in application, enters
And the behavior characteristics of each user can be generated according to the behavioral data of each user, then utilize each to use
The behavior characteristics at family calculates the behavior characteristics value of each user, with behavior characteristics value as class condition, to
Classifying in family, obtains several sorted group, due to the behavior characteristics value phase of the user in each sorted group
Like or identical, if thus the number of users comprised in one or more sorted group is very big, then mean
In this sorted group, major part user is fictitious users, namely may determine that channel to be measured employs brush amount instrument.
Multiple fictitious users that the application utilizes brush amount instrument to produce possess the principle of certain similarity in behavior,
By calculating the behavior characteristics value of each user, and accordingly user is clustered, and then can be according in advance
Fixed strategy judges whether channel to be measured uses brush amount instrument, it is to avoid existing access environment attribute based on hardware
The distribution of parameter detects the confinement problems that the method for brush amount instrument is latched in.
Optionally, with behavior characteristics value as class condition, when each user is classified, can be by
The user that behavior characteristics value is identical is divided into a class.It is, of course, also possible to classify according to Else Rule,
Such as when behavior characteristics value is binary system group number form formula, can be individual less than presetting by the number of different place values
The user that the behavior characteristics value of number is corresponding is divided into a class, as two behavior characteristics values are respectively 1011 Hes
1111, and predetermined number is 2, the most obvious two behavior characteristics values value of the 2nd the most from left to right is different, because of
Two users of behavior characteristics value 1011 and 1111 can be divided into a class by this.
In another embodiment of the application, disclose several different decision plan, to be measured to determine
Whether channel employs brush amount instrument.
See Fig. 2, Fig. 2 be disclosed in the embodiment of the present application a kind of determine channel to be measured use brush amount instrument
Method flow diagram.
As in figure 2 it is shown, the method includes:
Step S200, all sorted group filter out number of users exceed the sorted group of first threshold；
The total number of users amount that the sorted group that step S210, statistics filter out is comprised；
Each sorted group obtained for screening, is added the number of users in each sorted group, is used
Family total quantity.
Step S220, judge in described total number of users amount and all sorted group the ratio of total number of users amount whether
Exceed Second Threshold, the most then perform step S230；
Step S230, determine that described channel to be measured employs brush amount instrument.
In the present embodiment, from all users, filter out the user that similar behavior is higher, it is judged that this type of user
Whether the proportion accounting for total user number exceedes certain value, if then thinking that current channel to be measured employs brush amount
Instrument.
Such as, corresponding with channel A to be measured has 200 users, through uniting mass data in citing
Meter, determines that first threshold is 20, and Second Threshold is 50%.6 sorted group have been obtained through classification, point
Not Wei sorted group 1-6, the number of users in each sorted group is followed successively by 100,80,10,5,3,2.Aobvious
So, the number in the 1st and the 2nd sorted group has exceeded first threshold, and in the two sorted group, number is total
With for 100+80=180, it is judged that 180/200=90% > 50%, it is thus determined that channel A to be measured employs brush
Amount instrument.
Seeing Fig. 3, Fig. 3 is that another kind disclosed in the embodiment of the present application determines that channel to be measured uses brush amount instrument
Method flow diagram.
As it is shown on figure 3, the method includes:
Step S300, by many orders the most at least, described sorted group is ranked up according to comprising number of users；
The total number of users amount that before in step S310, statistical series, n sorted group is comprised；
Here n value is preset constant, can be the constants that arbitrarily user sets such as 1,2, and certain n needs
Less than the total number of sorted group.
Step S320, judge in described total number of users amount and all sorted group the ratio of total number of users amount whether
More than the 3rd threshold value, the most then perform step S330；
Step S330, determine that described channel to be measured employs brush amount instrument.
Present embodiments provide another method determining that channel to be measured uses brush amount instrument, compared to upper
One embodiment, selects in this enforcement to comprise front n the sorted group that number of users is more, it is judged that this n point
Whether the proportion of class group total number of persons and all sorted group total numbers of persons is more than the 3rd threshold value, if then determining to be measured
Channel employs brush amount instrument.
Such as, corresponding with channel B to be measured has 200 users, through uniting mass data in citing
Meter, determines that n is 3, and the 3rd threshold value is 60%.6 sorted group, 6 sorted group have been obtained through classification
The number of users comprised is as shown in table 1 below:
Table 1
According to comprising number of users order from large to small, sorted group is ranked up: 1-3-4-6-5-2.Choosing
Take front 3 sorted group, i.e. sorted group 1, sorted group 3 and sorted group 4, ask for three sorted group numbers total
With for 120+50+15=185.Judge 185/200=92.5% > 60%, it is thus determined that channel B to be measured uses
Brush amount instrument.
It follows that in the present embodiment as a example by the precious software of application, whole scheme is introduced.
The behavioral data of each user corresponding with channel to be measured can be obtained by the precious software server of application,
Behavioral data includes the attribute shown in table 2 below:
Table 2
According to the behavioral data of each user, generate the behavior characteristics of each user, the attribute of behavior characteristics
It is described as follows table 3:
Table 3
Utilize SimHash algorithm, behavior characteristics set based on each user, calculate the row of each user
It is characterized value, and to gather to the user that behavior characteristics value is identical be a class, obtain several sorted group.Choose
Comprise the sorted group that number of users is most, by number of users in this sorted group divided by user in all sorted group
Total quantity, it is judged that whether result is more than preset value, if it is, think that current channel to be measured employs brush
Amount instrument.
The brush amount tool detection device provided the embodiment of the present application below is described, brush described below
Amount tool detection device can be mutually to should refer to above-described brush amount tool detection method.
Seeing Fig. 4, Fig. 4 is a kind of brush amount tool detection apparatus structure schematic diagram disclosed in the embodiment of the present application.
As shown in Figure 4, this device includes:
Behavioral data acquiring unit 41, for obtaining the behavior of at least one user corresponding with channel to be measured
Data；
Behavior characteristics signal generating unit 42, for the behavioral data according to each user, generates each user's
Behavior characteristics；
Behavior characteristics value computing unit 43, for utilizing the behavior characteristics of each user, calculates each user
Behavior characteristics value；
Classification processing unit 44, for behavior characteristics value as class condition, classifies to each user,
Obtain several sorted group；
Brush amount instrument determines unit 45, meets preset judgement for number of users in determining described sorted group
During strategy, determine that described channel to be measured employs brush amount instrument.
Optionally, Fig. 5 illustrates above-mentioned brush amount instrument and determines the optional structure of one of unit 45, such as Fig. 5 institute
Showing, brush amount instrument determines that unit 45 may include that
Sorted group screening unit 451, exceedes first threshold for filtering out number of users in all sorted group
Sorted group；
First user quantity statistics unit 452, for adding up the total number of users that the sorted group filtered out is comprised
Amount；
First ratio in judgement unit 453, is used for judging that described total number of users amount is total with user in all sorted group
Whether the ratio of quantity exceedes Second Threshold, if, it is determined that described channel to be measured employs brush amount instrument.
Optionally, Fig. 6 illustrates above-mentioned brush amount instrument and determines the optional structure of another kind of unit 45, such as Fig. 6
Shown in, brush amount instrument determines that unit 45 may include that
Sorted group sequencing unit 454, for according to comprising number of users by many orders at least to described classification
Group is ranked up；
Second number of users statistic unit 455, in statistical series before the user that comprised of n sorted group
Total quantity；
Second ratio in judgement unit 456, is used for judging that described total number of users amount is total with user in all sorted group
The ratio of quantity whether more than the 3rd threshold value, if, it is determined that described channel to be measured employs brush amount instrument.
Optionally, Fig. 7 illustrates the optional structure of one of above-mentioned behavior characteristics value computing unit 43, such as Fig. 7
Shown in, behavior characteristics value computing unit 43 may include that
The first row is characterized value computation subunit 431, is used for using SimHash algorithm, uses based on each
The behavior characteristics set at family, calculates the behavior characteristics value of each user.
Optionally, Fig. 8 illustrates the optional structure of one of above-mentioned classification processing unit 44, as shown in Figure 8,
Classification processing unit 44 may include that
First classification processes subelement 441, for user identical for behavior characteristics value is divided into a class.
It is, of course, also possible to classify according to Else Rule, such as, it is binary system group number when behavior characteristics value
During form, user corresponding less than the behavior characteristics value of predetermined number for the number of different place values can be divided
Being a class, as two behavior characteristics values are respectively 1011 and 1111, and predetermined number is 2, the most obvious two
Behavior characteristics value only has the value difference of the 2nd the most from left to right, therefore can be by the two of behavior characteristics value 1011 and 1111
Individual user is divided into a class.
The brush amount tool detection device that the embodiment of the present application provides, obtains at least corresponding with channel to be measured
The behavioral data of individual user, behavioral data characterizes various operations performed after user logs in application, enters
And the behavior characteristics of each user can be generated according to the behavioral data of each user, then utilize each to use
The behavior characteristics at family calculates the behavior characteristics value of each user, with behavior characteristics value as class condition, to
Classifying in family, obtains several sorted group, due to the behavior characteristics value phase of the user in each sorted group
Like or identical, if thus the number of users comprised in one or more sorted group is very big, then mean
In this sorted group, major part user is fictitious users, namely may determine that channel to be measured employs brush amount instrument.
Multiple fictitious users that the application utilizes brush amount instrument to produce possess the principle of certain similarity in behavior,
By calculating the behavior characteristics value of each user, and accordingly user is clustered, and then can be according in advance
Fixed strategy judges whether channel to be measured uses brush amount instrument, it is to avoid existing access environment attribute based on hardware
The distribution of parameter detects the confinement problems that the method for brush amount instrument is latched in.
The embodiment of the present application also provides for a kind of server, and this server can include brush amount work described above
Tool detection device, the description for brush amount tool detection device can refer to corresponding part description above, herein
Repeat no more.
Below the hardware configuration of the server that the embodiment of the present application provides is described, relates in being described below
And the part of account management can refer to corresponding part above and describes.The service that Fig. 9 provides for the embodiment of the present application
The hardware architecture diagram of device, with reference to Fig. 9, this server may include that
Processor 1, communication interface 2, memorizer 3, communication bus 4, and display screen 5；
Wherein processor 1, communication interface 2, memorizer 3 and display screen 5 complete phase by communication bus 4
Communication between Hu；
Optionally, communication interface 2 can be the interface of communication module, such as the interface of gsm module；
Processor 1, is used for performing program；
Memorizer 3, is used for depositing program；
Program can include that program code, described program code include the operational order of processor.
Processor 1 is probably a central processor CPU, or specific integrated circuit ASIC
(Application Specific Integrated Circuit), or be configured to implement the embodiment of the present application
One or more integrated circuits.
Memorizer 3 may comprise high-speed RAM memorizer, it is also possible to also includes nonvolatile memory
(non-volatile memory), for example, at least one disk memory.
Wherein, program can be specifically for:
Obtain the behavioral data of at least one user corresponding with channel to be measured；
According to the behavioral data of each user, generate the behavior characteristics of each user；
Utilize the behavior characteristics of each user, calculate the behavior characteristics value of each user；
With behavior characteristics value as class condition, each user is classified, obtain several sorted group；
When determining that in described sorted group, number of users meets preset decision plan, determine described channel to be measured
Employ brush amount instrument.
Finally, in addition it is also necessary to explanation, in this article, the relational terms of such as first and second or the like
It is used merely to separate an entity or operation with another entity or operating space, and not necessarily requires
Or imply relation or the order that there is any this reality between these entities or operation.And, art
Language " includes ", " comprising " or its any other variant are intended to comprising of nonexcludability, thus
Make to include that the process of a series of key element, method, article or equipment not only include those key elements, and
Also include other key elements being not expressly set out, or also include for this process, method, article or
The key element that person's equipment is intrinsic.In the case of there is no more restriction, by statement " including ... "
The key element limited, it is not excluded that also deposit in including the process of described key element, method, article or equipment
In other identical element.
In this specification, each embodiment uses the mode gone forward one by one to describe, and each embodiment stresses
Being the difference with other embodiments, between each embodiment, identical similar portion sees mutually.
Described above to the disclosed embodiments, makes professional and technical personnel in the field be capable of or uses
The application.Multiple amendment to these embodiments will be aobvious and easy for those skilled in the art
See, generic principles defined herein can in the case of without departing from spirit herein or scope,
Realize in other embodiments.Therefore, the application is not intended to be limited to the embodiments shown herein,
And it is to fit to the widest scope consistent with principles disclosed herein and features of novelty.
Claims (10)
1. a brush amount tool detection method, it is characterised in that including:
Obtain the behavioral data of at least one user corresponding with channel to be measured；
According to the behavioral data of each user, generate the behavior characteristics of each user；
Utilize the behavior characteristics of each user, calculate the behavior characteristics value of each user；
With behavior characteristics value as class condition, each user is classified, obtain several sorted group；
When determining that in described sorted group, number of users meets preset decision plan, determine described channel to be measured
Employ brush amount instrument.
Method the most according to claim 1, it is characterised in that described in determining described sorted group
When number of users meets preset decision plan, determine that described channel to be measured employs the process bag of brush amount instrument
Include:
In all sorted group, filter out number of users exceed the sorted group of first threshold；
The total number of users amount that the sorted group that statistics filters out is comprised；
Judge that whether described total number of users amount and the ratio of total number of users amount in all sorted group are more than the second threshold
Value, if, it is determined that described channel to be measured employs brush amount instrument.
Method the most according to claim 1, it is characterised in that described in determining described sorted group
When number of users meets preset decision plan, determine that described channel to be measured employs the process bag of brush amount instrument
Include:
Described sorted group is ranked up by many orders at least according to comprising number of users；
The total number of users amount that before in statistical series, n sorted group is comprised；
Judge that whether described total number of users amount and the ratio of total number of users amount in all sorted group are more than the 3rd threshold
Value, if, it is determined that described channel to be measured employs brush amount instrument.
Method the most according to claim 1, it is characterised in that the behavior characteristics of each user is many
Individual, the described behavior characteristics utilizing each user, calculate the behavior characteristics value of each user, including:
Use SimHash algorithm, behavior characteristics set based on each user, calculate the row of each user
It is characterized value.
Method the most according to claim 1, it is characterised in that described with behavior characteristics value for classification
Condition, classifies to each user, including:
User identical for behavior characteristics value is divided into a class.
6. according to the method described in any one of claim 1-5, it is characterised in that described user behavior number
According to including that user accesses record quantity, user's access duration time, the type that starts, login type, user
Participate in the different quantity of scene and the quantity of user's click action is any one or more.
7. a brush amount tool detection device, it is characterised in that including:
Behavioral data acquiring unit, for obtaining the behavior number of at least one user corresponding with channel to be measured
According to；
Behavior characteristics signal generating unit, for the behavioral data according to each user, generates the row of each user
It is characterized；
Behavior characteristics value computing unit, for utilizing the behavior characteristics of each user, calculates each user's
Behavior characteristics value；
Classification processing unit, for behavior characteristics value as class condition, classifies to each user,
Obtain several sorted group；
Brush amount instrument determines unit, meets preset judgement plan for number of users in determining described sorted group
Time slightly, determine that described channel to be measured employs brush amount instrument.
Device the most according to claim 7, it is characterised in that described brush amount instrument determines unit bag
Include:
Sorted group screening unit, exceedes first threshold for filtering out number of users in all sorted group
Sorted group；
First user quantity statistics unit, for adding up the total number of users amount that the sorted group filtered out is comprised；
First ratio in judgement unit, is used for judging described total number of users amount and total number of users in all sorted group
Whether the ratio of amount exceedes Second Threshold, if, it is determined that described channel to be measured employs brush amount instrument.
Device the most according to claim 7, it is characterised in that described brush amount instrument determines unit bag
Include:
Sorted group sequencing unit, for according to comprising number of users by many orders at least to described sorted group
It is ranked up；
Second number of users statistic unit, in statistical series before the user that comprised of n sorted group total
Quantity；
Second ratio in judgement unit, is used for judging described total number of users amount and total number of users in all sorted group
Amount ratio whether more than the 3rd threshold value, if, it is determined that described channel to be measured employs brush amount instrument.
Device the most according to claim 7, it is characterised in that the behavior characteristics of each user is
Multiple, described behavior characteristics value computing unit includes:
The first row is characterized value computation subunit, is used for using SimHash algorithm, based on each user
Behavior characteristics set, calculates the behavior characteristics value of each user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510317134.0A CN106294508B (en) | 2015-06-10 | 2015-06-10 | Brushing amount tool detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510317134.0A CN106294508B (en) | 2015-06-10 | 2015-06-10 | Brushing amount tool detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106294508A true CN106294508A (en) | 2017-01-04 |
| CN106294508B CN106294508B (en) | 2020-02-11 |
Family
ID=57659601
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510317134.0A Active CN106294508B (en) | 2015-06-10 | 2015-06-10 | Brushing amount tool detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106294508B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106844655A (en) * | 2017-01-23 | 2017-06-13 | 广东欧珀移动通信有限公司 | Information processing method, device and computer equipment |
| CN107124391A (en) * | 2016-09-22 | 2017-09-01 | 北京小度信息科技有限公司 | The recognition methods of abnormal behaviour and device |
| CN107193972A (en) * | 2017-05-25 | 2017-09-22 | 山东浪潮云服务信息科技有限公司 | A kind of sorted users method and device based on big data |
| CN107707642A (en) * | 2017-09-22 | 2018-02-16 | 广东欧珀移动通信有限公司 | Brush amount terminal determines method and device |
| CN109284380A (en) * | 2018-09-25 | 2019-01-29 | 平安科技（深圳）有限公司 | Illegal user's recognition methods and device, electronic equipment based on big data analysis |
| WO2019041200A1 (en) * | 2017-08-30 | 2019-03-07 | 深圳市云中飞网络科技有限公司 | Method and apparatus for determining resources for increasing downloading quantities |
| WO2019041199A1 (en) * | 2017-08-30 | 2019-03-07 | 深圳市云中飞网络科技有限公司 | Method and apparatus for determining downloading quantity increase terminal |
| CN110189165A (en) * | 2019-05-14 | 2019-08-30 | 微梦创科网络科技（中国）有限公司 | Channel abnormal user and abnormal channel recognition methods and device |
| CN110378112A (en) * | 2019-07-08 | 2019-10-25 | 北京达佳互联信息技术有限公司 | A kind of user identification method and device |
| CN111368169A (en) * | 2018-12-25 | 2020-07-03 | 卓望数码技术（深圳）有限公司 | Method, device, equipment and storage medium for detecting brushing amount behavior |
| CN111639681A (en) * | 2020-05-09 | 2020-09-08 | 同济大学 | Early warning method, system, medium and device based on education drive type fraud |
| CN113383362A (en) * | 2019-06-24 | 2021-09-10 | 深圳市欢太科技有限公司 | User identification method and related product |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521248A (en) * | 2011-11-14 | 2012-06-27 | 北京亿赞普网络技术有限公司 | Network user classification method and device |
| CN102769851A (en) * | 2011-05-06 | 2012-11-07 | 中国移动通信集团广东有限公司 | Method and system for monitoring service provider services |
| CN103793484A (en) * | 2014-01-17 | 2014-05-14 | 五八同城信息技术有限公司 | Fraudulent conduct identification system based on machine learning in classified information website |
| CN103853841A (en) * | 2014-03-19 | 2014-06-11 | 北京邮电大学 | Method for analyzing abnormal behavior of user in social networking site |
| CN103886068A (en) * | 2014-03-20 | 2014-06-25 | 北京国双科技有限公司 | Data processing method and device for Internet user behavior analysis |
| CN104281882A (en) * | 2014-09-16 | 2015-01-14 | 中国科学院信息工程研究所 | Method and system for predicting social network information popularity on basis of user characteristics |
| CN104298719A (en) * | 2014-09-23 | 2015-01-21 | 新浪网技术(中国)有限公司 | Method and system for conducting user category classification and advertisement putting based on social behavior |
| CN104424433A (en) * | 2013-08-22 | 2015-03-18 | 腾讯科技（深圳）有限公司 | Anti-cheating method and anti-cheating system of application program |
-
2015
- 2015-06-10 CN CN201510317134.0A patent/CN106294508B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102769851A (en) * | 2011-05-06 | 2012-11-07 | 中国移动通信集团广东有限公司 | Method and system for monitoring service provider services |
| CN102521248A (en) * | 2011-11-14 | 2012-06-27 | 北京亿赞普网络技术有限公司 | Network user classification method and device |
| CN104424433A (en) * | 2013-08-22 | 2015-03-18 | 腾讯科技（深圳）有限公司 | Anti-cheating method and anti-cheating system of application program |
| CN103793484A (en) * | 2014-01-17 | 2014-05-14 | 五八同城信息技术有限公司 | Fraudulent conduct identification system based on machine learning in classified information website |
| CN103853841A (en) * | 2014-03-19 | 2014-06-11 | 北京邮电大学 | Method for analyzing abnormal behavior of user in social networking site |
| CN103886068A (en) * | 2014-03-20 | 2014-06-25 | 北京国双科技有限公司 | Data processing method and device for Internet user behavior analysis |
| CN104281882A (en) * | 2014-09-16 | 2015-01-14 | 中国科学院信息工程研究所 | Method and system for predicting social network information popularity on basis of user characteristics |
| CN104298719A (en) * | 2014-09-23 | 2015-01-21 | 新浪网技术(中国)有限公司 | Method and system for conducting user category classification and advertisement putting based on social behavior |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107124391A (en) * | 2016-09-22 | 2017-09-01 | 北京小度信息科技有限公司 | The recognition methods of abnormal behaviour and device |
| CN107124391B (en) * | 2016-09-22 | 2021-11-16 | 北京星选科技有限公司 | Abnormal behavior identification method and device |
| CN106844655A (en) * | 2017-01-23 | 2017-06-13 | 广东欧珀移动通信有限公司 | Information processing method, device and computer equipment |
| CN107193972A (en) * | 2017-05-25 | 2017-09-22 | 山东浪潮云服务信息科技有限公司 | A kind of sorted users method and device based on big data |
| WO2019041200A1 (en) * | 2017-08-30 | 2019-03-07 | 深圳市云中飞网络科技有限公司 | Method and apparatus for determining resources for increasing downloading quantities |
| WO2019041199A1 (en) * | 2017-08-30 | 2019-03-07 | 深圳市云中飞网络科技有限公司 | Method and apparatus for determining downloading quantity increase terminal |
| CN107707642A (en) * | 2017-09-22 | 2018-02-16 | 广东欧珀移动通信有限公司 | Brush amount terminal determines method and device |
| CN109284380A (en) * | 2018-09-25 | 2019-01-29 | 平安科技（深圳）有限公司 | Illegal user's recognition methods and device, electronic equipment based on big data analysis |
| CN109284380B (en) * | 2018-09-25 | 2023-04-25 | 平安科技（深圳）有限公司 | Illegal user identification method and device based on big data analysis and electronic equipment |
| WO2020062690A1 (en) * | 2018-09-25 | 2020-04-02 | 平安科技（深圳）有限公司 | Method and apparatus for illegal user identification based on big data analysis, and electronic device |
| CN111368169B (en) * | 2018-12-25 | 2023-08-01 | 卓望数码技术（深圳）有限公司 | Method, device, equipment and storage medium for detecting brushing amount behavior |
| CN111368169A (en) * | 2018-12-25 | 2020-07-03 | 卓望数码技术（深圳）有限公司 | Method, device, equipment and storage medium for detecting brushing amount behavior |
| CN110189165B (en) * | 2019-05-14 | 2021-07-23 | 微梦创科网络科技（中国）有限公司 | Channel abnormal user and abnormal channel identification method and device |
| CN110189165A (en) * | 2019-05-14 | 2019-08-30 | 微梦创科网络科技（中国）有限公司 | Channel abnormal user and abnormal channel recognition methods and device |
| CN113383362A (en) * | 2019-06-24 | 2021-09-10 | 深圳市欢太科技有限公司 | User identification method and related product |
| CN113383362B (en) * | 2019-06-24 | 2022-05-13 | 深圳市欢太科技有限公司 | User identification method and related product |
| CN110378112A (en) * | 2019-07-08 | 2019-10-25 | 北京达佳互联信息技术有限公司 | A kind of user identification method and device |
| CN111639681A (en) * | 2020-05-09 | 2020-09-08 | 同济大学 | Early warning method, system, medium and device based on education drive type fraud |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106294508B (en) | 2020-02-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106294508A (en) | A kind of brush amount tool detection method and device | |
| CN107579956B (en) | User behavior detection method and device | |
| CN102724219B (en) | A network data computer processing method and a system thereof | |
| CN106560811A (en) | Direct broadcasting room recommending method and system based on broadcaster style | |
| CN107368856B (en) | Malicious software clustering method and device, computer device and readable storage medium | |
| CN104836781A (en) | Method distinguishing identities of access users, and device | |
| CN104391979A (en) | Malicious web crawler recognition method and device | |
| CN108038130A (en) | Automatic cleaning method, device, equipment and the storage medium of fictitious users | |
| CN107222511B (en) | Malicious software detection method and device, computer device and readable storage medium | |
| CN108243191A (en) | Risk behavior recognition methods, storage medium, equipment and system | |
| CN110209551B (en) | Abnormal equipment identification method and device, electronic equipment and storage medium | |
| CN106375975A (en) | Policy conflict detection method and apparatus | |
| CN110516752A (en) | Clustering cluster method for evaluating quality, device, equipment and storage medium | |
| CN106936778A (en) | The abnormal detection method of website traffic and device | |
| CN112488716A (en) | Abnormal event detection system | |
| CN108171570A (en) | A kind of data screening method, apparatus and terminal | |
| CN110222790A (en) | Method for identifying ID, device and server | |
| CN107948257B (en) | The method for pushing and computer readable storage medium of APP | |
| CN113609409A (en) | Method and system for recommending browsing information, electronic device and storage medium | |
| EP2621156B1 (en) | Subscriber portfolio management system | |
| CN107623696A (en) | A kind of user ID authentication method and device based on user behavior feature | |
| CN105989019B (en) | A kind of method and device for cleaning data | |
| CN104767739B (en) | The method that unknown multi-protocols blended data frame is separated into single protocol data frame | |
| KR101568800B1 (en) | Real-time issue search word sorting method and system | |
| CN108259363A (en) | A kind of method and device of staged service traffics control |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |