CN103577543A - Ranking fraud detection method and ranking fraud detection system of application program - Google Patents

Ranking fraud detection method and ranking fraud detection system of application program Download PDF

Info

Publication number
CN103577543A
CN103577543A CN201310469958.0A CN201310469958A CN103577543A CN 103577543 A CN103577543 A CN 103577543A CN 201310469958 A CN201310469958 A CN 201310469958A CN 103577543 A CN103577543 A CN 103577543A
Authority
CN
China
Prior art keywords
application program
credit worthiness
rank
active ues
swindle
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
Application number
CN201310469958.0A
Other languages
Chinese (zh)
Other versions
CN103577543B (en
Inventor
祝恒书
于魁飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Zhigu Ruituo Technology Services Co Ltd
Original Assignee
Beijing Zhigu Ruituo Technology Services Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Zhigu Ruituo Technology Services Co Ltd filed Critical Beijing Zhigu Ruituo Technology Services Co Ltd
Priority to CN201310469958.0A priority Critical patent/CN103577543B/en
Publication of CN103577543A publication Critical patent/CN103577543A/en
Application granted granted Critical
Publication of CN103577543B publication Critical patent/CN103577543B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/10—Protecting distributed programs or content, e.g. vending or licensing of copyrighted material ; Digital rights management [DRM]
    • G06F21/12—Protecting executable software
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2221/00—Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F2221/21—Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F2221/2127—Bluffing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2221/00—Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F2221/21—Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F2221/2135—Metering

Abstract

The invention provides a ranking fraud detection method and a ranking fraud detection system of an application program. The method comprises the following steps of detection of an active phase: detecting the active phase of an application program according to the historical ranking information; and detection of ranking fraud: detecting the active phase according to at least one evidence which is related to the creditworthiness of active users, and obtaining a ranking fraud detection result. By adopting the method and system, the ranking fraud behavior related to the application program can be automatically recognized, so that an application program user can obtain the real ranking information of the application program.

Description

The rank fraud detection method of application program and rank fraud detection system
Technical field
The present invention relates to network field, relate in particular to a kind of rank fraud detection method and rank fraud detection system of application program.
Background technology
User application, the mobile applications development in recent years of especially installing and run on mobile terminal is rapid.In order to facilitate user to select and set up applications, a lot of application program websites or application program shop can intensively provide the services such as the inquiry, download, evaluation of application program, simultaneously also can be termly, for example every day, release application program ranking list (Application Leaderboard) is to embody some current application programs popular with users.In fact, this ranking list is one of most important means of sales promotion application program, and application program very high rank in ranking list can stimulate user to download in a large number this application program conventionally, and brings huge economic return for application developer.Therefore, application developer wishes that its application program occupies higher rank in ranking list very much.
The rank swindle (Ranking Fraud) of application program refers to that object is to improve the rank of application program in application program ranking list and the deceptive practices carried out.In fact, be different from the traditional market means of dependence and improve application program rank, application developer is by exaggerating its product sales volume or issue false product evaluation to implement the behavior of rank swindle more and more general, such as employing " waterborne troops (human water armies) " promote at short notice the download of application program and evaluate number of times etc.
Industry has been recognized and has been prevented that rank swindle is so that application user obtains the importance of real application program ranking information.In order to prevent the rank swindle of application program, existing way is the existence that the degree that rises according to application program rank in a day is inferred rank fraud, and occur when rank is swindled directly locking the rank of whole application program in judgement, this mode is too simple and crude, and the rank that is difficult to accurately judge rank fraud and injured normal application rises.Visible, this area is also very limited for understanding and the research of the rank fraud detection problem of application program, does not also have so far the correlation technique of the rank swindle of effective detection application program.
Summary of the invention
The object of the present invention is to provide a kind of detection technique of rank swindle of application program, thereby automatically effectively identify the rank fraud relevant with application program, so that application user obtains real application program ranking information.
For solving the problems of the technologies described above, according to an aspect of the present invention, provide a kind of rank fraud detection method of application program, described method comprises:
Active period detecting step, detects the active period of described application program based on historical ranking information;
Rank fraud detection step, verifies described active period based at least one evidence relevant to any active ues credit worthiness, obtains rank swindle the result.
According to another aspect of the present invention, also provide a kind of rank fraud detection system of application program, described system comprises:
Active period detecting unit, for detecting the active period of described application program based on historical ranking information;
Rank fraud detection unit, for described active period being verified based at least one evidence relevant to any active ues credit worthiness, obtains rank swindle the result.
According to another aspect of the present invention, also provide a kind of rank fraud detection method of application program, described method comprises:
Active period based at least one evidence application programs relevant to any active ues credit worthiness is verified, obtains rank swindle the result.
According to another aspect of the present invention, also provide a kind of rank fraud detection system of application program, described system comprises:
Rank fraud detection unit, verifies for the active period based at least one evidence application programs relevant to any active ues credit worthiness, obtains rank swindle the result.
Method and apparatus of the present invention can automatically effectively identify the rank fraud relevant with application program, thereby makes application user obtain real application program ranking information.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the active period detection method of application program in the specific embodiment of the invention;
Fig. 2 a is an example enlivening event in application program ranking list;
Fig. 2 b is an example of active period in application program ranking list;
Fig. 3 is the system construction drawing of the rank fraud detection system of application program in the specific embodiment of the invention;
Fig. 4 is the structural representation of the rank fraud detection system of application program in another embodiment of the present invention.
Embodiment
Below in conjunction with drawings and Examples, the specific embodiment of the present invention is described in further detail.Following examples are used for illustrating the present invention, but are not used for limiting the scope of the invention.
The present invention is directed to the technical matters relevant to application program rank studies, therefore those skilled in the art should be interpreted broadly " application program " in the present invention, it comprises various programs or the file that can be published on internet and can download, evaluate, carry out for user, comprise the legacy application running in PC, the mobile applications that runs on mobile terminal, also comprise multimedia files such as the picture that can download and play, audio frequency, video etc.
When the rank swindle that detects application program, there are several major issues that need solution.First, in the whole life cycle of application program, can't always there is rank swindle, therefore first need to detect the time that may occur rank swindle; The second, because number of applications is huge, be difficult to manually for each application program that occurs rank swindle, demarcate, therefore a kind of technology of automatic detection rank swindle need to be provided; The 3rd, in prior art and uncertain can be based on which kind of according to the existence that detect rank swindle.
Analysis and the research of globality has been carried out in the rank fraud of a specific embodiment of the present invention application programs, a kind of technology that detects the rank swindle of application program is provided, its can be by application programs the analysis of historical ranking information detect " active period " of application program, for user's prestige feature of application program in active period, the relevant evidence of any active ues credit worthiness based on to application program carries out the detection of rank swindle.
According to inventor's analysis, find, exist the application program of rank swindle can't in billboard, occupy for a long time very high rank, the situation that rank is higher is only to concentrate and occur in one relatively short period as some independent events, and this shows that rank fraud occurs in this period just.In the present invention, application program can be continued to " enlivening event (Leading Event) " that rank is called application program higher period, can be called to " active period (the Leading Session) " of application program the period of frequently enlivening event.Therefore, for the detection of rank swindle, first need to detect that each application program likely exists rank swindle that this enlivens event and this active period.
Application program shop operator place has the historical ranking information of application program, from application program shop, operator directly obtains, or analyze and process by the application program ranking list information of application programs shop operator lasting issue within one period of longer period of history, also can obtain the historical ranking information of application program.Because this history ranking information of application program has been recorded the historical information of relevant application program rank and the historical information of relevant application user credit worthiness, therefore in the specific embodiment of the invention, can carry out the event of enlivening of each application program and the detection of active period based on this history ranking information, and and then the detection of realization to rank swindle.User's credit worthiness by analysis application is found, than normal application program, exists the application program of rank swindle in enlivening event and active period, can be ready-made different user's prestige feature.Therefore, likely from the historical ranking information of application program, extract some evidences for judge rank swindle relevant to user's credit worthiness, and obtain these evidences, thereby realize the detection to rank swindle.
Correspondingly in the present invention, " any active ues " that the relative users that occurs user behavior (comprise purchase, download and use this application program or this application program is carried out grade evaluation or carried out the comment of character property) in active period in an application program is called to this application program, is called " any active ues credit worthiness " by the corresponding credit worthiness information of any active ues in active period.
As shown in Figure 1, provide a kind of rank fraud detection method of application program in a specific embodiment of the present invention, described method comprises:
Active period detecting step S10, detects the active period of described application program based on historical ranking information; Rank fraud detection step S20, detects described active period based at least one evidence relevant to any active ues credit worthiness, obtains rank fraud detection result.
Below, each steps flow chart and the function of above-mentioned rank fraud detection method in the specific embodiment of the invention are described by reference to the accompanying drawings.
Because historical ranking information is the data basis of detecting the rank swindle of application program in the present invention, therefore as a preferred embodiment of the present invention, this rank fraud detection method also can comprise a historical ranking information obtaining step, obtains the historical ranking information of described application program in application program ranking list.
After an application program is published, any user can buy, downloads and use this application program or this application program is carried out grade evaluation or carried out the comment of character property.By to the collection of above-mentioned these user behaviors and analysis (such as the number of times of the application program of using institute to download or buy by mobile terminal counting user, frequency etc.), and in conjunction with other network behaviors of user (behavior such as user in social networks, user are in the behavior in other application program shop, user's rank fraud history once etc.), can grade to the prestige of each application user and (for example comprise from 1～5 these five grades, 5 representative of consumer prestige are the highest, 1 representative of consumer prestige is the poorest), the credit worthiness of usining as this user.Thereby, in this history ranking information, can comprise historical user's credit worthiness information, i.e. user's credit worthiness information of all application programs in certain application program or application program ranking list in historical each time period.
Application program ranking list can show the application program of K position before welcome rank conventionally, such as first 1000 etc.And application program ranking list is understood regular update conventionally, for example, upgrade every day.Therefore, have its historical ranking information for each application program a, this history ranking information can comprise and is expressed as a rank sequence corresponding with discrete-time series
Figure BDA0000393340860000061
interval between time point in this discrete-time series is fixed, i.e. the update cycle of application program ranking list.Wherein,
Figure BDA0000393340860000064
that this application program a is at time t itime rank,
Figure BDA0000393340860000062
+ ∞ represents the not row of K position before ranking list rank of application program a; N represents the corresponding time point sum of all historical ranking informations.For example, in ranking list every day more under news, t ijust represent the i days in this phase of history, be exactly total the corresponding number of days of the historical ranking information of n.Can find out,
Figure BDA0000393340860000063
value less, the application program a i days rank in ranking list is higher.
In this history ranking information obtaining step, can obtain in many ways this history ranking information.For example, can directly obtain this history ranking information from application program shop operator, the data that also can continue within one period of longer period of history from application program shop to issue, extract this history ranking information etc.
S10: active period detecting step, detects the active period of described application program based on historical ranking information.
Active period represents that application program rank in application program ranking list is higher, one higher period of user's attention rate namely, so the rank fraud that application programs market can affect greatly only there will be in these active period.So in the specific embodiment of the invention, first the detection of swindling for rank will detect the active period of application program from the historical ranking information of application program.
In a preferred embodiment of the invention, in this active period detecting step, can further comprise and enliven event detection step, based on this history ranking information, detect the event of enlivening of described application program.
Because application developer is all wished its application program occupy higher rank in ranking list, so application developer likely utilizes the means of rank swindle to make its application program rank among ranking list prostatitis.By analysis, find, application program can't always occupy very high rank in billboard, occur to continue rank and be " enlivening event " higher period, the example of the event of enlivening of application program has been shown in Fig. 2 a, in figure, transverse axis represents the time series that historical ranking information is corresponding (Date Index), the longitudinal axis represents the rank (Ranking) of application program, event 1(Event1 in figure) and event 2(Event2) represent to occur in this application program placement history two enliven event, its profile is formed by connecting by the rank point enlivening during event respectively.
In the specific embodiment of the invention, the application program standard that rank is higher in application program ranking list is that the rank of this application program is not more than a rank threshold k *.Due to the row of rank K* position before ranking list of application program, to be considered to rank higher, thereby the rank of application program continues can be considered to one in the time period of the row of front K* position and enlivens event, this enlivens event and should from this application program starts to enter ranking list, start by the row of K* position, lasts till that this application program falls the row end that K* position before ranking list.
Preferably, the method in embodiment of the present invention also can comprise that one arranges the step of this rank threshold k *, thereby determines application program higher standard of rank in application program ranking list.Because the application program total quantity K in ranking list is conventionally very large, such as being 1000 etc., therefore above-mentioned rank threshold k * is less than K value conventionally.According to the total quantity K of application program in application program ranking list and those skilled in the art's the factors such as analysis demand, this rank threshold k * can be in for example value between the integer between 1～500.The value that it will be understood by those skilled in the art that K* is less, and it is just higher that application program is considered to the standard that rank is higher.In Fig. 2 a, the value of this K* is 300.
According to the above-mentioned character express for enlivening event, the event of the enlivening e of application program a formulism statement as follows:
A given rank threshold k * is as the higher standard of rank, wherein K* ∈ [1, K]; The event of the enlivening e of application program a comprises the time range of time a to end time from the beginning
Figure BDA0000393340860000071
the rank of corresponding application program a meets
Figure BDA0000393340860000072
and r end a &le; K * < r end + 1 a , And &ForAll; t k &Element; ( t start e , t end e ) All meet r k a &le; K * 。
According to above-mentioned statement, can find out, the rank that detects application program for important being of the detection that enlivens event continued in start time and the end time of a period of time of the row of front K* position, and will be defined as enlivening event the period between a pair of start time and end time.Therefore,, in the specific embodiment of the invention, this enlivens event detection step and can further comprise the steps:
Start time identification step S101: in this step, identify the start time of the event of enlivening from historical ranking information.Particularly, in this start time identification step, application program rank in can sequential search historical ranking information on each time point, when the rank that is not more than rank threshold k * and a upper time point when the rank of current point in time is greater than rank threshold k *, identification current point in time is the start time of enlivening event.It will be understood by those skilled in the art that owing to may comprise a plurality of events of enlivening in application program placement history, therefore in this start time identification step, may identify a plurality of start time points.
End time identification step S102: in this step, identify the end time of the time of enlivening from historical ranking information.Particularly, in this end time identification step, application program rank in can sequential search historical ranking information on each time point, when the rank that is greater than rank threshold k * and a upper time point when the rank of current point in time is not more than rank threshold k *, identifying a upper time point is the end time of enlivening event.It will be understood by those skilled in the art that owing to may comprise a plurality of events of enlivening in application program placement history, therefore in this end time identification step, may identify a plurality of end time points.
Enliven event recognition step S103: in this step, the time period between each start time and its afterwards adjacent end time is identified as to the event of enlivening, has so just detected all the enliven events of application program in placement history.
What deserves to be explained is, as a kind of special circumstances, if on first time point of period of history of analyzing and processing, the first day in historical record for example, the rank of application program is the row of K* position before ranking list just, now, in described start time identification step S101, this first time point is defined as to a start time.Similarly, if on last time point of period of history of analyzing and processing, for example today, the rank of application program is the row of K* position before ranking list still, now in described end time identification step S102, this last time point are defined as to an end time.
Introduced above and detected the mode of enlivening event in application program, on this basis, in a preferred embodiment of the invention, can in this active period detecting step, merge the adjoining event of enlivening to form described active period.
By further research, find, can there is repeatedly continuously the near event of enlivening adjacent one another are in some application programs within one period, and be exactly " active period " of application program in the present invention this period.Visible, the adjoining event merge that enlivens is got up just to have formed active period.Particularly, can be less than to an interval threshold φ adjacent two time intervals of enlivening event as enlivening the standard of event merge in same active period by two, adjacent two time intervals of enlivening event refer to that adjacent two are enlivened last end time and rear one of enlivening event in event and enliven the interval between start time of event.
Preferably, the method in embodiment of the present invention also can comprise that one arranges the step of this interval threshold φ, thereby determines and enliven the standard of event merge in same active period by two.According to those skilled in the art's the factors such as analysis demand, the value of this interval threshold φ can be the round values in 2～10 times of update cycle of application program ranking list.The value that it will be understood by those skilled in the art that interval threshold φ is less, enlivens the standard of event merge in same active period just higher by two.
The example of the active period of application program has been shown in Fig. 2 b, in figure, transverse axis represents the time series that historical ranking information is corresponding (Date Index), the longitudinal axis represents the rank (Ranking) of application program, 1(Session1 during in figure) and during 2(Session2) represent two active period that occur in this application program placement history, each active period consists of a plurality of events of enlivening.
According to the above-mentioned character express for active period, the active period s of application program a formulism statement as follows:
The active period s of application program a comprises a time range
Figure BDA0000393340860000091
with n the adjacent event of enlivening { e 1..., e n, it meets
Figure BDA0000393340860000092
and do not exist other active period s* to make
Figure BDA0000393340860000093
.In addition,
Figure BDA0000393340860000094
have
Figure BDA0000393340860000095
, wherein φ be preset enliven interval of events threshold value, be for judging between the event of enlivening that adjacent degree is to include them in the criterion of same active period.
According to above-mentioned statement, can find out, for important being of the detection of active period, based on interval threshold φ, by adjoining in application program placement history, enliven event merge to form active period.Particularly, in the active period detecting step of the specific embodiment of the invention, initial time point from historical ranking information starts each detected event of enlivening of sequential search, when current, enliven event and upper one time interval of enlivening event while being less than this interval threshold φ, enliven event merge in same active period by these two, until searched for all detected events of enlivening to detect all active period of this application program in placement history.
What deserves to be explained is, as a kind of special circumstances, if one is enlivened event, to enliven event not adjoining with any other, and this enlivens event self also can be considered to form an active period.In this case, in this active period detecting step, enliven event and upper one time interval of enlivening event was not less than described interval threshold φ when one, and this enlivens event and next and enlivens the time interval of event while being not less than described interval threshold φ, detect this and enliven event from as an active period.
Just as mentioned before, detected above-mentioned active period represents that application program rank in application program ranking list is higher, namely be subject to one period that user welcomes, this detected active period can be used as the data basis that comprises the various application program service that detect rank swindle.Therefore, after detecting the active period of application program, as a preferred embodiment of the invention, the active period information of detected application program can also be sent to the terminal user of application developer, application program shop operator or application program.
For application developer, it can be according to the development trend of this active period information analysis correlative technology field or the demand of application user, thereby instructs exploitation and the operation of application program; For the operator of application program shop, it can further analyze according to this active period information rank fraud that utilizes fraudulent mean to obtain false high rank in ranking list etc., thus the operation in improvement application program shop; And for application terminal user, they can judge that application program exists the possibility of rank swindle or application program that selection meets self-demand etc. voluntarily according to this active period information.
In addition,, as detecting the event of enlivening of application program and a kind of specific implementation of active period, following algorithm 1 shows the example that detects a program code of active period in the historical ranking information of given application program a.
Figure BDA0000393340860000111
In above-mentioned algorithm 1, each is enlivened to event e and be defined as
Figure BDA0000393340860000112
active period s is defined as
Figure BDA0000393340860000113
, wherein Es enlivens the set of event in active period s.Especially, each that first extracts application program a from the start time of historical ranking information enlivens the step 2-5 event e(algorithm 1).The event of the enlivening e extracting for each, detects e and previously enlivens time interval between event e* to judge whether they belong to same active period.Particularly, if
Figure BDA0000393340860000114
, the event e of enlivening is considered to belong to a new active period (the step 7-13 in algorithm 1).The single pass of the historical ranking information that like this, above-mentioned algorithm 1 can be by application programs a is identified the event of enlivening and active period.
Rank fraud detection step S20, detects described active period based at least one evidence relevant to any active ues credit worthiness, obtains rank fraud detection result.
As the above introduction to historical ranking information, it comprises historical user's credit worthiness information, i.e. user's credit worthiness information of all application programs in certain application program or application program ranking list in historical each time period.Meanwhile, active period is the period that rank swindle likely occurs application program.Therefore, can application programs active period in user's prestige feature of historical ranking information analyze, extract some information relevant to any active ues credit worthiness as the evidence for detection of rank swindle.
Particularly, user's credit worthiness of application program can be classified as in a discrete credit worthiness hierarchical system, for example, comprise that 5 representative of consumer prestige are the highest from 1～5 these five grades, and 1 representative of consumer prestige is the poorest.If there is rank swindle in the active period s of application program, just must there is the poor user of some user's credit worthinesses to participate in frauds such as falseness download, false evaluation or comment, therefore the user's credit worthiness within the time period of active period s will have the off-note different from user's credit worthiness of other historical stages, and this feature can be used for building the evidence relevant to any active ues credit worthiness for detection of rank swindle.
As a preferred embodiment of the present invention, this rank fraud detection step can further comprise an evidence verification step, based at least one evidence relevant to any active ues credit worthiness, described active period is verified to and obtained a swindle parameter.Like this, after extracting the evidence relevant with any active ues credit worthiness, can calculate the swindle parameter corresponding with this evidence, this swindle parameter itself can be used as the rank fraud detection result of the rank fraud detection method in present embodiment.Comparatively complicated owing to affecting the factor of user's prestige feature of application program, only rely on one or more evidences relevant to any active ues credit worthiness possibly cannot accurately judge that whether an application program exists rank swindle but only obtain a detected value for reference (swindle parameter), judges that application program exists the possibility of rank swindle but those skilled in the art can swindle parameter according to this completely.
For normal application program, in the average credit worthiness of particular active any active ues in the phase, should be consistent with its historical all users' average credit worthiness.On the contrary, for the application program that has rank swindle, in its active period, the average credit worthiness of any active ues can significantly decrease by tool than its historical all users' average credit worthiness.As a preferred embodiment of the present invention, the average credit worthiness of any active ues that the evidence relevant to any active ues credit worthiness can be based on application program
Figure BDA0000393340860000131
the average credit worthiness of historical user with this application program
Figure BDA0000393340860000132
form, and this evidence based on formed calculates an evidence value as the swindle parameter for judging that rank is swindled.
For example intuitively, the average credit worthiness of historical user that can computing application program
Figure BDA0000393340860000133
the average credit worthiness of any active ues with this application program
Figure BDA0000393340860000134
between difference, or the average credit worthiness of historical user of application program
Figure BDA0000393340860000135
the average credit worthiness of any active ues with this application program between ratio, as this swindle parameter.
Therefore,, than the active period of other application programs in ranking list, if the active period s of an application program comprises obviously larger above-mentioned difference or ratio, just there is a strong possibility that property exists rank swindle for this application program.
For normal application program, in the average credit worthiness of particular active any active ues in the phase, should be consistent with the average credit worthiness of historical user of all application programs in application program ranking list.On the contrary, for the application program that has rank swindle, in its active period, the average credit worthiness of any active ues can significantly decrease by tool than the average credit worthiness of historical user of all application programs in application program ranking list.As a preferred embodiment of the present invention, the average credit worthiness of any active ues that the evidence relevant to any active ues credit worthiness can be based on application program
Figure BDA00003933408600001311
the average credit worthiness of historical user with all application programs in application program ranking list
Figure BDA00003933408600001312
form, and this evidence based on formed calculates an evidence value as the swindle parameter for judging that rank is swindled.
For example, in intuitively, can the computing application program ranking list average credit worthiness of historical user of all application programs the average credit worthiness of any active ues with application program
Figure BDA0000393340860000138
between difference, or the average credit worthiness of historical user of all application programs in application program ranking list
Figure BDA0000393340860000139
the average credit worthiness of any active ues with application program
Figure BDA00003933408600001310
between ratio, as this swindle parameter.
Therefore,, than the active period of other application programs in ranking list, if the active period s of an application program comprises obviously larger above-mentioned difference or ratio, just there is a strong possibility that property exists rank swindle for this application program.
In user's credit worthiness information of application program, each user's prestige can be classified as discrete user's degrees of comparison system | in L|, for example, comprise that it has represented the height of user's prestige from 1～5 these five grades.For a normal application program a, the credit worthiness grade l of its any active ues in active period s idistribution p (l i| Q s,a) should user credit worthiness distribution of grades p (l historical with it i| Q a) be consistent.As a preferred embodiment of the present invention, the evidence relevant to any active ues credit worthiness can be based on application program any active ues credit worthiness distribute and historical user's credit worthiness of this application program distributes and forms, and this evidence based on formed calculates an evidence value as for judging the swindle parameter of rank swindle.
For example, the difference between historical user's credit worthiness that can computing application program distributes and any active ues credit worthiness of application program distributes, as this swindle parameter.Particularly, first can pass through
Figure BDA0000393340860000142
calculate p (l i| Q s,a) value, wherein
Figure BDA0000393340860000143
s is that user's credit worthiness grade is l in active period iany active ues number, it is any active ues number total in active period s; Can calculate p (l by similar mode simultaneously i| Q a); Difference between historical user's credit worthiness distribution of then computing application program and any active ues credit worthiness of application program distribute.As a kind of specific implementation, can use p (l i| Q s,a) and p (l i| Q a) between cosine distance D (s) estimate the difference between them.By formulism, describe, this swindle parameter D (s) is as follows:
D ( s ) = &Sigma; i = 1 | L | p ( l i | Q s , a ) &times; p ( l i | Q a ) &Sigma; i = 1 | L | p ( l i | Q s , a ) 2 &times; &Sigma; i = 1 | L | p ( l i | Q a ) 2 - - - ( 1 )
Visible, than the active period of other application programs in ranking list, if the active period s of an application program comprises obviously larger D (s) value, just there is a strong possibility that property exists rank to swindle for this application program.
Meanwhile, for a normal application program a, the credit worthiness grade l of its any active ues in active period s idistribution p (l i| Q s,a) should with the distribution of grades p (l of historical user's credit worthiness of all application programs in application program ranking list i| be Q) consistent.As a preferred embodiment of the present invention, the evidence relevant to any active ues credit worthiness can be based on application program any active ues credit worthiness distribute and application program ranking list in historical user's credit worthiness of all application programs distribute and form, and this evidence based on formed calculates an evidence value as the swindle parameter for judging that rank is swindled.
For example, can computing application program ranking list in historical user's credit worthiness of all application programs distribute and any active ues credit worthiness of the application program difference between distributing, as this swindle parameter.Particularly, first can pass through
Figure BDA0000393340860000151
calculate p (l i| Q s,a) value, wherein that user's credit worthiness grade is l in active period iany active ues number,
Figure BDA0000393340860000153
it is any active ues number total in active period s; Can calculate p (l by similar mode simultaneously i| Q); Difference in historical user's credit worthiness distribution of then computing application program and application program ranking list between historical user's credit worthiness distribution of all application programs.As a kind of specific implementation, can use p (l i| Q s,a) and p (l i| the cosine distance D (s) Q) is estimated the difference between them.By formulism, describe, this swindle parameter D (s) is as follows:
D ( s ) = &Sigma; i = 1 | L | p ( l i | Q s , a ) &times; p ( l i | Q ) &Sigma; i = 1 | L | p ( l i | Q s , a ) 2 &times; &Sigma; i = 1 | L | p ( l i | Q ) 2 - - - ( 2 )
Visible, than the active period of other application programs in ranking list, if the active period s of an application program comprises obviously larger D (s) value, just there is a strong possibility that property exists rank to swindle for this application program.
Introduced the multiple evidence relevant to any active ues credit worthiness above, except carrying out rank fraud detection with one in them separately in above-mentioned each preferred implementation, in a preferred implementation of evidence verification step, can also consider a plurality of in the above-mentioned evidence relevant to any active ues credit worthiness, the correspondence swindle parameter obtaining based on these evidence checkings is weighted, thereby obtains a final swindle parameter.Consider that above-mentioned multiple evidence likely has different dimensions, those skilled in the art can according in actual analysis demand for the attention degree of each evidence, based on method for normalizing commonly known in the art and Weight Determination, determine the weighted value of respectively swindling parameter, do not repeat them here.
More than introduced the evidence verification step in rank fraud detection step, it can verify and obtain a swindle parameter based at least one evidence relevant to any active ues credit worthiness to described active period, this swindle parameter itself just can be used as the rank fraud detection result of rank fraud detection method.But in order to make those skilled in the art carry out more easily rank fraud detection, in a preferred implementation, rank fraud detection step can further include a swindle parameter determining step, the swindle parameter calculating according to evidence and a threshold value are compared, thereby judge intuitively, judge whether application program exists rank swindle.
It will be appreciated by those skilled in the art that, multiple relevant to any active ues credit worthiness evidence based on above introducing, those skilled in the art can arrange respectively corresponding threshold value according to the heterogeneity of evidence and detection demand, according to set threshold value, carry out the judgement whether application program exists rank swindle, and using the rank fraud detection result of net result rank fraud detection method in the specific embodiment of the invention of judgement.For example, for multiple relevant to any active ues credit worthiness evidence above introduced, when the swindle parameter calculating surpasses set threshold value, judge this application program and have rank swindle phenomenon.
In rank fraud detection step, obtain after rank fraud detection result, in a preferred embodiment of the invention, resulting rank fraud detection result can also be sent to the terminal user of application program shop operator or application program.For the operator of application program shop, it can be according to the operation in this rank fraud detection result improvement application program shop; And for application terminal user, they can select according to this rank fraud detection result application program meeting self-demand etc.
As shown in Figure 3, also provide a kind of rank fraud detection system 100 of application program in the specific embodiment of the invention, described system 100 comprises:
Active period detecting unit 110, for detecting the active period of described application program based on historical ranking information; Rank fraud detection unit 120, for based at least one evidence relevant to any active ues credit worthiness, described active period being detected, obtains rank fraud detection result.
Below, each Elementary Function of said detecting system is described by reference to the accompanying drawings.
Because historical ranking information is the data basis of detecting the rank swindle of application program in the present invention, therefore as a preferred embodiment of the present invention, this rank fraud detection system 100 also can comprise a historical ranking information acquiring unit, for obtaining the historical ranking information of described application program in application program ranking list.
This history ranking information acquiring unit can obtain this history ranking information in many ways.For example, can directly obtain this history ranking information from application program shop operator, the data that also can continue within one period of longer period of history from application program shop to issue, extract this history ranking information etc.
Active period detecting unit 110, for detecting the active period of described application program based on historical ranking information.
In a preferred embodiment of the invention, this active period detecting unit 110 can further comprise and enlivens event checking module, for detect the event of enlivening of described application program based on this history ranking information.
Preferably, the system in embodiment of the present invention also can comprise a rank threshold value setting unit, for the value of rank threshold k * is set, thereby determines application program higher standard of rank in application program ranking list.The value of this rank threshold k * can be the integer between 1～500.
In the specific embodiment of the invention, this enlivens event checking module and further comprises:
Start time identification module 111, for identifying the start time of the event of enlivening from historical ranking information.Particularly, application program rank in can the sequential search historical ranking information of this start time identification module on each time point, when the rank that is not more than rank threshold k * and a upper time point when the rank of current point in time is greater than rank threshold k *, identification current point in time is the start time of enlivening event.
End time identification module 112, for identifying the end time of the time of enlivening from historical ranking information.Particularly, application program rank in can the sequential search historical ranking information of this end time identification module on each time point, when the rank that is greater than rank threshold k * and a upper time point when the rank of current point in time is not more than rank threshold k *, identifying a upper time point is the end time of enlivening event.
Enliven event recognition module 113, for the time period between each start time and its afterwards adjacent end time is identified as to the event of enlivening, so just detected all the enliven events of application program in placement history.
What deserves to be explained is, as a kind of special circumstances, if on first time point of period of history of analyzing and processing, the first day in historical record for example, the rank of application program is the row of K* position before ranking list just, and now this start time identification module 111 is defined as a start time by this first time point.Similarly, if on last time point of period of history of analyzing and processing, for example today, the rank of application program is the row of K* position before ranking list still, and now this end time identification module 112 is defined as an end time by this last time point.
In a preferred embodiment of the invention, this active period detecting unit 110 is for merging the adjoining event of enlivening to form the described active period of described application program.
Preferably, the rank fraud detection system 100 in embodiment of the present invention also can comprise an interval threshold setting unit, for the value of this interval threshold φ is set, thereby determines and enlivens the standard of event merge in same active period by two.The value of this interval threshold φ can be the round values in 2～10 times of update cycle of application program ranking list.
In the specific embodiment of the invention, the initial time point of active period detecting unit 110 from historical ranking information starts each detected event of enlivening of sequential search, when current, enliven event and upper one time interval of enlivening event while being less than this interval threshold φ, enliven event merge in same active period by these two, until searched for all detected events of enlivening to detect all active period of this application program in placement history.
What deserves to be explained is, as a kind of special circumstances, if one is enlivened event, to enliven event not adjoining with any other, and this enlivens event self also can be considered to form an active period.In this case, this active period detecting unit 110 is for enlivening event and upper one time interval of enlivening event was not less than described interval threshold φ when one, and this enlivens event and next and enlivens the time interval of event while being not less than described interval threshold φ, detect this and enliven event from as an active period.
As a preferred embodiment of the invention, rank fraud detection system 100 can also comprise an active period transmitting element, and the active period information of detected application program is sent to application developer, application program shop operator or application user.
Rank fraud detection unit 120, for based at least one evidence relevant to any active ues credit worthiness, described active period being detected, obtains rank fraud detection result.
As a preferred embodiment of the present invention, this rank fraud detection unit 120 can further comprise an evidence authentication module, for described active period being verified to and obtained a swindle parameter based at least one evidence relevant to any active ues credit worthiness.
In a preferred implementation, the average credit worthiness of any active ues that the evidence relevant to any active ues credit worthiness can be based on application program
Figure BDA0000393340860000191
the average credit worthiness of historical user with application program form, and this evidence based on formed calculates an evidence value as the swindle parameter for judging that rank is swindled.In another preferred implementation, the average credit worthiness of any active ues that the evidence relevant to any active ues credit worthiness can be based on application program
Figure BDA0000393340860000193
the average credit worthiness of historical user with all application programs in application program ranking list
Figure BDA0000393340860000194
form, and this evidence based on formed calculates an evidence value as the swindle parameter for judging that rank is swindled.In another preferred implementation, the evidence relevant to any active ues credit worthiness can be based on application program any active ues credit worthiness distribute and historical user's credit worthiness of this application program distributes to form, and this evidence based on formed calculates an evidence value as for judging the swindle parameter of rank swindle.In another preferred implementation, the evidence relevant to any active ues credit worthiness can be based on application program any active ues credit worthiness distribute and application program ranking list in historical user's credit worthiness of all application programs distribute and form, and this evidence based on formed calculates an evidence value as the swindle parameter for judging that rank is swindled.
Except carrying out rank fraud detection with one in them separately in above-mentioned each preferred implementation, evidence authentication module can also consider a plurality of in the above-mentioned evidence relevant to any active ues credit worthiness, the correspondence swindle parameter obtaining based on these evidence checkings is weighted, thereby obtains a final swindle parameter.
In order to make those skilled in the art carry out more easily rank fraud detection, in a preferred implementation, rank fraud detection unit 120 can further include a swindle parameter judge module, the swindle parameter calculating according to evidence and a threshold value are compared, thereby judge intuitively, judge whether application program exists rank swindle.
In rank fraud detection step, obtain after rank fraud detection result, in a preferred embodiment of the invention, rank fraud detection system 100 also comprises a rank fraud detection result transmitting element, resulting rank fraud detection result is sent to the terminal user of application program shop operator or application program.
It will be appreciated by those skilled in the art that, in the event of enlivening of application program and the situation of active period ten-four, those skilled in the art can be directly enliven event and active period information is implemented above-mentioned rank fraud detection step according to above-mentioned, thereby realize the detection of application program rank swindle.Therefore, a kind of rank fraud detection method of application program is also provided in another embodiment of the present invention, described method comprises: based at least one evidence relevant to any active ues credit worthiness, come the active period of application programs to detect, obtain rank fraud detection result.In the application program rank fraud detection method of this embodiment, the technology contents of implementing is identical with rank fraud detection step in embodiment before, repeats no more herein.
Accordingly simultaneously, a kind of rank fraud detection system of application program is also provided in another embodiment of the present invention, described system comprises: rank fraud detection unit, for described active period being detected based at least one evidence relevant to any active ues credit worthiness, obtain rank fraud detection result.In the application program rank fraud detection system of this embodiment, the technology contents of implementing is identical with rank fraud detection unit in embodiment before, repeats no more herein.
The structural representation of the rank fraud detection system 400 of a kind of application program that Fig. 4 provides for the embodiment of the present invention, the specific embodiment of the invention does not limit the specific implementation of rank fraud detection system 400.As shown in Figure 4, this rank fraud detection system 400 can comprise:
Processor (processor) 410, communication interface (Communications Interface) 420, storer (memory) 430 and communication bus 440.Wherein:
Processor 410, communication interface 420 and storer 430 complete mutual communication by communication bus 440.
Communication interface 420, for the net element communication with such as client etc.
Processor 410, for executive routine 432, specifically can realize described in above-mentioned Fig. 3 the correlation function of rank fraud detection system in embodiment.
Particularly, program 432 can comprise program code, and described program code comprises computer-managed instruction.
Processor 410 may be a central processor CPU, or specific integrated circuit ASIC(Application Specific Integrated Circuit), or be configured to implement one or more integrated circuit of the embodiment of the present invention.
Storer 430, for depositing program 432.Storer 430 may comprise high-speed RAM storer, also may also comprise nonvolatile memory (non-volatile memory), for example at least one magnetic disk memory.Program 432 specifically can comprise:
Active period detecting unit, for detecting the active period of described application program based on historical ranking information;
Rank fraud detection unit, for based at least one evidence relevant to any active ues credit worthiness, described active period being detected, obtains rank fraud detection result.
Program 432 specifically also can comprise:
Rank fraud detection unit, for based at least one evidence relevant to any active ues credit worthiness, active period being detected, obtains rank fraud detection result.
In program 432, the specific implementation of each unit can, referring to the corresponding units in embodiment above, be not repeated herein.
Those skilled in the art can be well understood to, and for convenience and simplicity of description, the specific works process of the equipment of foregoing description and module, can describe with reference to the correspondence in aforementioned means embodiment, does not repeat them here.
Those of ordinary skills can recognize, unit and the method step of each example of describing in conjunction with embodiment disclosed herein, can realize with the combination of electronic hardware or computer software and electronic hardware.These functions are carried out with hardware or software mode actually, depend on application-specific and the design constraint of technical scheme.Professional and technical personnel can specifically should be used for realizing described function with distinct methods to each, but this realization should not thought and exceeds scope of the present invention.
If described function usings that the form of SFU software functional unit realizes and during as production marketing independently or use, can be stored in a computer read/write memory medium.Understanding based on such, the part that technical scheme of the present invention contributes to original technology in essence in other words or the part of this technical scheme can embody with the form of software product, this computer software product is stored in a storage medium, comprise that some instructions are with so that a computer equipment (can be personal computer, server, or the network equipment etc.) carry out all or part of step of method described in each embodiment of the present invention.And aforesaid storage medium comprises: various media that can be program code stored such as USB flash disk, portable hard drive, ROM (read-only memory) (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CDs.
Above embodiment is only for illustrating the present invention; and be not limitation of the present invention; the those of ordinary skill in relevant technologies field; without departing from the spirit and scope of the present invention; can also make a variety of changes and modification; therefore all technical schemes that are equal to also belong to category of the present invention, and scope of patent protection of the present invention should be defined by the claims.

Claims (55)

1. a rank fraud detection method for application program, is characterized in that, described method comprises:
Active period detecting step, detects the active period of described application program based on historical ranking information;
Rank fraud detection step, verifies described active period based at least one evidence relevant to any active ues credit worthiness, obtains rank swindle the result.
2. method according to claim 1, is characterized in that, described rank fraud detection step further comprises:
Evidence verification step, verifies and obtains a swindle parameter based at least one evidence relevant to any active ues credit worthiness to described active period.
3. method according to claim 2, is characterized in that, any active ues average credit worthiness of the described evidence relevant to any active ues credit worthiness based on described application program and the average credit worthiness formation of historical user of described application program.
4. method according to claim 3, is characterized in that,
Described swindle parameter is difference or the ratio of the average credit worthiness of historical user of described application program and the average credit worthiness of any active ues of described application program.
5. method according to claim 2, is characterized in that, in the average credit worthiness of any active ues of the described evidence relevant to any active ues credit worthiness based on described application program and application program ranking list, the average credit worthiness of the historical user of all application programs forms.
6. method according to claim 5, is characterized in that,
Described swindle parameter is difference or the ratio of the average credit worthiness of historical user of all application programs in application program ranking list and the average credit worthiness of any active ues of described application program.
7. method according to claim 2, is characterized in that,
Any active ues credit worthiness of the described evidence relevant to any active ues credit worthiness based on described application program distributes and historical user's credit worthiness distribution of described application program forms.
8. method according to claim 7, is characterized in that,
Described swindle parameter is the difference between historical user's credit worthiness distribution of described application program and any active ues credit worthiness of described application program distribute.
9. method according to claim 8, is characterized in that, by the cosine distance of calculating between historical user's credit worthiness distribution of described application program and any active ues credit worthiness distribution of described application program, calculates the difference between them.
10. method according to claim 2, is characterized in that,
Any active ues credit worthiness of the described evidence relevant to any active ues credit worthiness based on described application program distribute and application program ranking list in historical user's credit worthiness of all application programs formation that distributes.
11. methods according to claim 10, is characterized in that,
Described swindle parameter is the difference between historical user's credit worthiness distribution of all application programs in application program ranking list and any active ues credit worthiness of described application program distribute.
12. methods according to claim 11, it is characterized in that, the cosine distance between distributing by historical user's credit worthiness distribution of all application programs in computing application program ranking list and any active ues credit worthiness of described application program is calculated the difference between them.
13. methods according to claim 2, it is characterized in that, in described evidence verification step, consider described at least one evidence relevant to any active ues credit worthiness, the corresponding swindle parameter obtaining based on described at least one evidence relevant to any active ues credit worthiness checking is weighted, thereby obtains described swindle parameter.
14. according to the method described in any one in claim 2-13, it is characterized in that, described rank fraud detection step further comprises:
Swindle parameter determining step, compares described swindle parameter and a threshold value, thereby judges whether described application program exists rank swindle.
15. methods according to claim 1, is characterized in that, described method also comprises:
Historical ranking information obtaining step, obtains the described historical ranking information of described application program in application program ranking list.
16. methods according to claim 15, is characterized in that, in described historical ranking information obtaining step, from application program shop operator, obtain described historical ranking information, or extract described historical ranking information from the data of application program shop issue.
17. methods according to claim 1, is characterized in that, described historical ranking information comprises user's credit worthiness of application program described in historical each time period or user's credit worthiness of all application programs in application program ranking list in historical each time period.
18. methods according to claim 1, is characterized in that, described method also comprises: the described active period of detected described application program is sent to at least one in application developer, application program shop operator, application user.
19. methods according to claim 1, is characterized in that, described method also comprises: detected described rank fraud detection result is sent to at least one in application program shop operator, application user.
The rank fraud detection system of 20. 1 kinds of application programs, is characterized in that, described system comprises:
Active period detecting unit, for detecting the active period of described application program based on historical ranking information;
Rank fraud detection unit, for described active period being verified based at least one evidence relevant to any active ues credit worthiness, obtains rank swindle the result.
21. systems according to claim 20, is characterized in that, described rank fraud detection unit further comprises:
Evidence authentication module, for verifying and obtain a swindle parameter based at least one evidence relevant to any active ues credit worthiness to described active period.
22. systems according to claim 21, is characterized in that, any active ues average credit worthiness of the described evidence relevant to any active ues credit worthiness based on described application program and the average credit worthiness formation of historical user of described application program.
23. systems according to claim 21, it is characterized in that, in the average credit worthiness of any active ues of the described evidence relevant to any active ues credit worthiness based on described application program and application program ranking list, the average credit worthiness of the historical user of all application programs forms.
24. systems according to claim 21, is characterized in that, any active ues credit worthiness of the described evidence relevant to any active ues credit worthiness based on described application program distributes and historical user's credit worthiness distribution of described application program forms.
25. systems according to claim 21, it is characterized in that, any active ues credit worthiness of the described evidence relevant to any active ues credit worthiness based on described application program distribute and application program ranking list in historical user's credit worthiness of all application programs formation that distributes.
26. systems according to claim 21, it is characterized in that, described evidence authentication module, for considering described at least one evidence relevant to any active ues credit worthiness, the corresponding swindle parameter obtaining based on described at least one evidence relevant to any active ues credit worthiness checking is weighted, thereby obtains described swindle parameter.
27. according to the system described in any one in claim 21-26, it is characterized in that, described rank fraud detection unit further comprises:
Swindle parameter judge module, for described swindle parameter and a threshold value are compared, thereby judges whether described application program exists rank swindle.
28. systems according to claim 20, is characterized in that, described system also comprises:
Historical ranking information acquiring unit, for obtaining the described historical ranking information of described application program in application program ranking list.
29. systems according to claim 28, is characterized in that, described historical ranking information acquiring unit for obtaining described historical ranking information from application program shop operator, or extracts described historical ranking information from the data of application program shop issue.
30. systems according to claim 20, it is characterized in that, described system also comprises an active period transmitting element, for the described active period of detected described application program being sent to at least one of application developer, application program shop operator, application user.
31. systems according to claim 20, it is characterized in that, described system also comprises a rank fraud detection result transmitting element, for detected described rank fraud detection result being sent to at least one of application program shop operator, application user.
The rank fraud detection method of 32. 1 kinds of application programs, is characterized in that, described method comprises:
Active period based at least one evidence application programs relevant to any active ues credit worthiness is verified, obtains rank swindle the result.
33. methods according to claim 32, is characterized in that, described method further comprises:
Evidence verification step, verifies and obtains a swindle parameter based at least one evidence relevant to any active ues credit worthiness to described active period.
34. methods according to claim 33, is characterized in that, any active ues average credit worthiness of the described evidence relevant to any active ues credit worthiness based on described application program and the average credit worthiness formation of historical user of described application program.
35. methods according to claim 34, is characterized in that,
Described swindle parameter is difference or the ratio of the average credit worthiness of historical user of described application program and the average credit worthiness of any active ues of described application program.
36. methods according to claim 33, it is characterized in that, in the average credit worthiness of any active ues of the described evidence relevant to any active ues credit worthiness based on described application program and application program ranking list, the average credit worthiness of the historical user of all application programs forms.
37. methods according to claim 36, is characterized in that,
Described swindle parameter is difference or the ratio of the average credit worthiness of historical user of all application programs in application program ranking list and the average credit worthiness of any active ues of described application program.
38. methods according to claim 33, is characterized in that,
Any active ues credit worthiness of the described evidence relevant to any active ues credit worthiness based on described application program distributes and historical user's credit worthiness distribution of described application program forms.
39. according to the method described in claim 38, it is characterized in that,
Described swindle parameter is the difference between historical user's credit worthiness distribution of described application program and any active ues credit worthiness of described application program distribute.
40. according to the method described in claim 39, it is characterized in that, by the cosine distance of calculating between historical user's credit worthiness distribution of described application program and any active ues credit worthiness distribution of described application program, calculates the difference between them.
41. methods according to claim 33, is characterized in that,
Any active ues credit worthiness of the described evidence relevant to any active ues credit worthiness based on described application program distribute and application program ranking list in historical user's credit worthiness of all application programs formation that distributes.
42. according to the method described in claim 41, it is characterized in that,
Described swindle parameter is the difference between historical user's credit worthiness distribution of all application programs in application program ranking list and any active ues credit worthiness of described application program distribute.
43. according to the method described in claim 42, it is characterized in that, the cosine distance between distributing by historical user's credit worthiness distribution of all application programs in computing application program ranking list and any active ues credit worthiness of described application program is calculated the difference between them.
44. methods according to claim 33, it is characterized in that, in described evidence verification step, consider described at least one evidence relevant to any active ues credit worthiness, the corresponding swindle parameter obtaining based on described at least one evidence relevant to any active ues credit worthiness checking is weighted, thereby obtains described swindle parameter.
45. according to the method described in any one in claim 33-44, it is characterized in that, described rank fraud detection step further comprises:
Swindle parameter determining step, compares described swindle parameter and a threshold value, thereby judges whether described application program exists rank swindle.
46. methods according to claim 32, is characterized in that, described method also comprises: detected described rank fraud detection result is sent to at least one in application program shop operator, application user.
The rank fraud detection system of 47. 1 kinds of application programs, is characterized in that, described system comprises:
Rank fraud detection unit, verifies for the active period based at least one evidence application programs relevant to any active ues credit worthiness, obtains rank swindle the result.
48. according to the system described in claim 47, it is characterized in that, described rank fraud detection unit further comprises:
Evidence authentication module, for verifying and obtain a swindle parameter based at least one evidence relevant to any active ues credit worthiness to described active period.
49. according to the system described in claim 48, it is characterized in that, any active ues average credit worthiness of the described evidence relevant to any active ues credit worthiness based on described application program and the average credit worthiness formation of historical user of described application program.
50. according to the system described in claim 48, it is characterized in that, in the average credit worthiness of any active ues of the described evidence relevant to any active ues credit worthiness based on described application program and application program ranking list, the average credit worthiness of the historical user of all application programs forms.
51. according to the system described in claim 48, it is characterized in that, any active ues credit worthiness of the described evidence relevant to any active ues credit worthiness based on described application program distributes and historical user's credit worthiness distribution of described application program forms.
52. according to the system described in claim 48, it is characterized in that, any active ues credit worthiness of the described evidence relevant to any active ues credit worthiness based on described application program distribute and application program ranking list in historical user's credit worthiness of all application programs formation that distributes.
53. according to the system described in claim 48, it is characterized in that, described evidence authentication module, for considering described at least one evidence relevant to any active ues credit worthiness, the corresponding swindle parameter obtaining based on described at least one evidence relevant to any active ues credit worthiness checking is weighted, thereby obtains described swindle parameter.
54. according to the system described in any one in claim 48-53, it is characterized in that, described rank fraud detection unit further comprises:
Swindle parameter judge module, for described swindle parameter and a threshold value are compared, thereby judges whether described application program exists rank swindle.
55. according to the system described in claim 47, it is characterized in that, described system also comprises a rank fraud detection result transmitting element, for detected described rank fraud detection result being sent to at least one of application program shop operator, application user.
CN201310469958.0A 2013-10-10 2013-10-10 The ranking fraud detection method and ranking fraud detection system of application program Active CN103577543B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310469958.0A CN103577543B (en) 2013-10-10 2013-10-10 The ranking fraud detection method and ranking fraud detection system of application program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310469958.0A CN103577543B (en) 2013-10-10 2013-10-10 The ranking fraud detection method and ranking fraud detection system of application program

Publications (2)

Publication Number Publication Date
CN103577543A true CN103577543A (en) 2014-02-12
CN103577543B CN103577543B (en) 2017-06-16

Family

ID=50049319

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310469958.0A Active CN103577543B (en) 2013-10-10 2013-10-10 The ranking fraud detection method and ranking fraud detection system of application program

Country Status (1)

Country Link
CN (1) CN103577543B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015051752A1 (en) * 2013-10-10 2015-04-16 Beijing Zhigu Rui Tuo Tech Co., Ltd Ranking fraud detection for application
CN107070876A (en) * 2016-02-05 2017-08-18 索尼公司 Method, equipment and system
CN107346367A (en) * 2016-05-04 2017-11-14 阿里巴巴集团控股有限公司 A kind of segmentation method and device of the numerical value of business variable
US10606845B2 (en) 2013-10-10 2020-03-31 Beijing Zhigu Rui Tuo Tech Co., Ltd Detecting leading session of application

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102279786B (en) * 2011-08-25 2015-11-25 百度在线网络技术（北京）有限公司 A kind of method of monitoring and measuring application program effective access amount and device
CN103198161B (en) * 2013-04-28 2018-09-07 中国科学院计算技术研究所 Microblog water army recognition methods and equipment

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015051752A1 (en) * 2013-10-10 2015-04-16 Beijing Zhigu Rui Tuo Tech Co., Ltd Ranking fraud detection for application
US10606845B2 (en) 2013-10-10 2020-03-31 Beijing Zhigu Rui Tuo Tech Co., Ltd Detecting leading session of application
CN107070876A (en) * 2016-02-05 2017-08-18 索尼公司 Method, equipment and system
CN107346367A (en) * 2016-05-04 2017-11-14 阿里巴巴集团控股有限公司 A kind of segmentation method and device of the numerical value of business variable
CN107346367B (en) * 2016-05-04 2020-09-18 阿里巴巴集团控股有限公司 Method and device for segmenting numerical value of business variable

Also Published As

Publication number Publication date
CN103577543B (en) 2017-06-16

Similar Documents

Publication Publication Date Title
CN103559208A (en) Application ranking fraud detection method and system
CN110019074B (en) Access path analysis method, device, equipment and medium
CN110781433B (en) Data type determining method and device, storage medium and electronic device
Chen et al. Toward detecting collusive ranking manipulation attackers in mobile app markets
CN111210326A (en) Method and system for constructing user portrait
CN103530796A (en) Active period detection method and active period detection system of application program
CN108648000B (en) Method and device for evaluating user retention life cycle and electronic equipment
CN103577543A (en) Ranking fraud detection method and ranking fraud detection system of application program
CN103577542A (en) Ranking fraud detection method and ranking fraud detection system of application program
CN103577541A (en) Ranking fraud detection method and ranking fraud detection system of application program
CN109842858A (en) A kind of service exception order detection method and device
CN103559210A (en) Application ranking fraud detection method and system
CN102982048A (en) Method and device for assessing junk information mining rule
CN102118382A (en) System and method for detecting attack of collaborative recommender based on interest combination
CN108074122A (en) Product beta test recommends method, apparatus and server
CN110009012A (en) A kind of risk specimen discerning method, apparatus and electronic equipment
CN111784360B (en) Anti-fraud prediction method and system based on network link backtracking
CN103761668A (en) Method and system for detecting bad users in network transaction
CN114817518B (en) License handling method, system and medium based on big data archive identification
CN115686623A (en) Homologous detection method of closed-source software
CN112866295B (en) Big data crawler-prevention processing method and cloud platform system
CN114399314A (en) User detection method, device, equipment and medium
CN111160987B (en) Information display method, device and system
CN110213341B (en) Method and device for detecting downloading of application program
CN113434826A (en) Detection method and system for counterfeit mobile application and related products

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