WO2016169193A1

WO2016169193A1 - Method and apparatus for detecting cheated clicks

Info

Publication number: WO2016169193A1
Application number: PCT/CN2015/089545
Authority: WO
Inventors: 庄馨; 田天; 朱军; 夏粉; 张潼
Original assignee: 百度在线网络技术（北京）有限公司
Priority date: 2015-04-24
Filing date: 2015-09-14
Publication date: 2016-10-27
Also published as: CN104765874B; CN104765874A

Abstract

A method and apparatus for detecting cheated clicks. The method comprises: determining, based on the number of clicks made on predetermined contents by a user within a predetermined time period, suspicious clicks (101); determining, according to the suspicious clicks, at least one suspicious user group suspected of cheating (102); determining, according to keywords of the predetermined contents clicked by each suspicious user group within the predetermined time period, non-cheating user groups to be eliminated (103); and eliminating the non-cheating user groups in the suspicious user groups so as to determine cheating user groups (104). Clicks on predetermined contents can be monitored, thereby improving the detection efficiency and detection accuracy of cheating clicks, and reducing the waste of time and resources.

Description

Method and device for detecting click cheating

Cross-reference to related applications

The application is filed on April 24, 2015, the application number is 201510202474.9, and the title of the invention is the priority of the Chinese Patent Application for "Method and Apparatus for Detecting Click Cheating", the entire contents of which are incorporated herein by reference. .

Technical field

The present application relates to the field of network technologies, and in particular, to a method and apparatus for detecting click cheating.

Background technique

With the rapid development of mobile Internet crowdsourcing technology, a type of cheating method that uses the crowdsourcing website to publish tasks, organizes netizens to manually click on specific advertisements, and gives a certain fee begins to rise. This kind of cheating is triggered by artificial reality and has strong concealment. It is difficult to detect by traditional methods.

At present, the existing methods for detecting cheats in advertising crowds include: 1 discovering suspicious clickers by establishing rules describing the characteristics of individual clickers, and then judging cheating behavior. The drawback of this technique is that because the source of crowdsourcing cheats is real user clicks rather than machines, the behavior is highly random and difficult to judge based on rules established by individual users or advertisers. 2 Determine whether there is a cheating behavior against it by observing the click traffic of an advertiser. The drawback of this technique is that since crowdsourcing cheats come from real users, when they feel that cheating is detected, they can quickly adjust their behavior, thus invalidating the previous rules. 3 to judge cheating by looking for a group of clickers with consistent behavior in the click log. The drawback of this technique is that it is not practical for the detection of artificial crowdsourcing cheating.

Summary of the invention

In order to solve the above problems, the present application provides a method and apparatus for detecting click cheating, which solves the technical problem of low detection efficiency and low detection precision for cheating clicks in the prior art.

In a first aspect, the present application provides a method for detecting a cheating of a click, the method comprising: determining a suspicious click based on a number of times the predetermined content is clicked by the user within a predetermined time period; determining at least one group based on the suspicious click a suspicious user group suspected of cheating; determining a non-cheating user group to be excluded according to a keyword of the suspicious content clicked by the suspicious user group in the predetermined time period; and excluding non-cheating in the suspicious user group User groups to identify groups of cheating users.

In some embodiments, the determining the suspicious click based on the number of times the predetermined content is clicked by the user within the predetermined time period comprises: obtaining the number of times each predetermined content is clicked by the user within the predetermined time period; determining each of the Whether the number of times the predetermined content is clicked satisfies the predetermined condition; the click corresponding to the predetermined content whose number of clicks satisfies the predetermined condition is determined as a suspicious click.

In some embodiments, determining whether the number of clicks satisfies a predetermined condition comprises: determining whether the number of clicks is greater than or equal to a first predetermined threshold, and less than or equal to a second predetermined threshold; if yes, determining the The number of times clicked satisfies the predetermined condition.

In some embodiments, the determining, according to the suspicious click, at least one group of suspicious users suspected of cheating comprises: obtaining related information of the suspicious clicks; determining at least one set of suspicious users based on the related information A group in which each group of suspicious user groups clicks on the same set of content during the same time period.

In some embodiments, the information related to the suspicious click includes at least one of the following: identification information of the user corresponding to the suspicious click; identification information of the content corresponding to the suspicious click; and corresponding to the suspicious click time.

In some embodiments, the determining the at least one set of suspicious user groups based on the related information comprises: clustering the suspicious clicks based on the related information, so that a user group corresponding to each cluster center is The same group of content is clicked in the same time period; the user group corresponding to each cluster center is determined as a group of suspicious users.

In some embodiments, the determining a non-cheating user group to be excluded according to a keyword of the suspicious content clicked by the group of the suspicious user within the predetermined time period, The method includes: acquiring a keyword of the suspicious content clicked by the suspicious user group in the predetermined time period; determining, according to the keyword, whether the suspicious content is a similar content; if yes, corresponding to the suspicious content The suspicious user community is identified as a non-cheating user group to be excluded.

In some embodiments, the determining whether the suspicious content is a similar content based on the keyword comprises: determining whether a proportion of a similar keyword in the keyword is greater than or equal to a predetermined ratio; if yes, determining the Suspicious content is similar content.

In a second aspect, the present application provides an apparatus for detecting a cheating of a click, the apparatus comprising: a first determining unit, configured to determine a suspicious click based on a number of times the predetermined content is clicked by the user within a predetermined time period; a unit, configured to determine, according to the suspicious click, at least one group of suspicious users suspected of cheating; and a third determining unit, configured to: according to the suspicious content clicked by each group of the suspicious user group in the predetermined time period The keyword determines a non-cheating user group to be excluded; and a fourth determining unit, configured to exclude the non-cheating user group in the suspicious user group to determine a cheating user group.

In some embodiments, the first determining unit includes: an obtaining subunit, configured to acquire a number of times each predetermined content is clicked by the user in the predetermined time period; and a determining subunit, configured to determine each of the predetermined Whether the number of times the content is clicked satisfies a predetermined condition; the determining subunit is configured to determine a click corresponding to the predetermined content whose number of clicks meets the predetermined condition as a suspicious click.

In some embodiments, the determining subunit is configured to: determine whether the number of clicks is greater than or equal to a first predetermined threshold, and less than or equal to a second predetermined threshold; if yes, determine that the number of clicks is satisfied Predetermined conditions.

In some embodiments, the second determining unit includes: an information acquiring subunit, configured to acquire related information of the suspicious click; and a user group determining subunit, configured to determine at least one set of suspicious based on the related information A group of users, in which each group of suspicious users clicks on the same set of content during the same time period.

In some embodiments, the user group determining subunit configuration is configured to: The related information clusters the suspicious clicks, so that the user groups corresponding to each cluster center click the same group of content in the same time period; the user groups corresponding to each cluster center are determined as a group of suspicious Client.

In some embodiments, the third determining unit includes: a keyword obtaining subunit, configured to acquire a keyword of the suspicious content clicked by the group of the suspicious user within the predetermined time period; the category judging a unit, configured to determine, according to the keyword, whether the suspicious content is a similar content; the group determining sub-unit to be excluded, configured to determine, in response to the suspicious content as a similar content, the suspicious user group corresponding to the suspicious content as being to be excluded Non-cheating user groups.

In some embodiments, the category determining subunit is configured to: determine whether a proportion of the same type of keywords in the keyword is greater than or equal to a predetermined ratio; if yes, determine that the suspicious content is a similar content.

The method and device for detecting click cheating provided by the present application determine the suspicious user group suspected of cheating by narrowing the detection range, and the non-cheating user in the suspicious user group according to the keyword of the suspicious content clicked by the suspicious user group Group exclusion, which enables monitoring of clicks on scheduled content, improves the efficiency and detection accuracy of detecting cheating clicks, and reduces waste of time and resources.

DRAWINGS

Other features, objects, and advantages of the present application will become more apparent from the detailed description of the accompanying drawings.

1 is a flowchart of an embodiment of a method for detecting click cheating provided by an embodiment of the present application;

2 is a flowchart of an embodiment of a method for determining a suspicious click provided by an embodiment of the present application;

FIG. 3 is a flowchart of an embodiment of a method for determining at least one suspicious user group suspected of cheating according to a suspicious click according to an embodiment of the present application; FIG.

4 is a flowchart of an embodiment of a method for determining a non-cheating user group to be excluded according to keywords of suspicious content clicked by each group of suspicious user groups in the predetermined time period according to an embodiment of the present application;

FIG. 5 is a schematic structural diagram of an embodiment of an apparatus for detecting click cheating provided by an embodiment of the present application; FIG.

FIG. 6 is a schematic structural diagram of a computer system suitable for implementing a terminal device or a server of an embodiment of the present application.

detailed description

The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the invention, rather than the invention. It is also to be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

It should be noted that the embodiments in the present application and the features in the embodiments may be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings.

Referring to Figure 1, a flow 100 of one embodiment of a method for detecting click cheating is shown.

As shown in FIG. 1, in step 101, a suspicious click is determined based on the number of times the predetermined content is clicked by the user within a predetermined time period.

In this embodiment, the predetermined content is content that may be involved in cheating clicks, such as content that can benefit from clicks (such as advertisements, voting, social networking sites, etc.), the greater the number of clicks on which the content is clicked, and The greater the benefits to its associated beneficiaries or units. In general, using crowdsourcing platforms for cheating, usually the beneficiaries associated with the scheduled content pass the task publisher, publish the task of clicking the scheduled content (such as advertising) on the crowdsourcing platform, and then the task publisher organizes a large number of netizens to receive the problem. Tasks, netizens complete tasks by clicking on the scheduled content, thereby obtaining rewards for completing the task.

It can be seen that the cheats click through the crowdsourcing platform, the click time is generally concentrated, usually occurs within a certain period of time after the release of the click task. Therefore, it is basically possible to exclude the possibility of cheating clicks in the time period in which the clicked content is not concentrated enough. Therefore, the predetermined period of time may select a period of time in which the predetermined content is clicked. Specifically, in an implementation manner, the distribution of the click corresponding to the predetermined content on the time axis may be acquired, and the distribution density is greater than a predetermined threshold. A period of time is taken as a predetermined period of time. In another In an implementation manner, the amount of clicks on the predetermined content at each time may also be acquired, and a period of time in which the amount of clicks each time is greater than a predetermined threshold is taken as the predetermined time period. It can be understood that there may be other implementation manners for selecting a predetermined time period, which is not limited in this application.

In this embodiment, in order to improve the efficiency of detecting cheating clicks and reduce the waste of time and resources, first, it is possible to first determine some clicks that may be related to cheating as suspicious clicks, and to exclude some clicks that are less likely to be cheated. Thereby reducing the range of detection. In the subsequent testing process, the detection is only performed in the range of suspicious clicks. Specifically, the suspicious click may be determined based on the number of times the predetermined content is clicked by the user within the predetermined time period.

Next, in step 102, at least one suspicious user group suspected of cheating is determined according to the suspicious click.

In general, a cheating task publisher may publish a click task containing multiple predetermined content to a crowdsourcing platform at a time, for example, publishing a click task containing 10 advertisements to the crowdsourcing platform. After the cheating clicker receives the cheat click task, it usually clicks on a set of scheduled contents in the task within a certain period of time. Therefore, the user group performing the task (clicking on a predetermined set of contents corresponding to the task) can be determined by analyzing related information of the suspicious click (such as click time, clicked content, etc.). A group of users who clicked on the same set of predetermined content was identified as a suspicious user group suspected of cheating.

Because, within a certain period of time, there may be multiple task publishers to publish the click task, so the above determined suspicious clicks may include multiple sets of predetermined content corresponding to different cheating click tasks. The predetermined content corresponding to the same cheating click task is a set of predetermined content. At the same time, each set of scheduled content can also correspond to a group of suspicious users suspected of cheating. Therefore, the suspicious click determined above corresponds to at least one group of suspicious users suspected of cheating.

Then, in step 103, the non-cheating user group to be excluded is determined according to the keyword of the suspicious content clicked by each group of suspicious user groups within a predetermined time period.

In general, some scheduled content may be more popular during a certain period of time, with a large amount of user clicks, or some users may be interested in a related batch of predetermined content within a certain period of time. For example, if a flu occurs in a certain area at a certain time, then there may be a large number of living in the area. People search online for anti-flu or flu-preventing drugs, and the ads or websites that these residents click on may overlap and are related to the flu. For another example, a certain season is more suitable for traveling to a certain area. In this season, a large number of users may search online and click on advertisements or websites related to travel to the area. The content clicked by these users may also partially overlap, and both Related to tourism in the area.

These predetermined content does not involve cheating clicks, and users who click on these predetermined content are not cheat user groups, but may be identified as cheating user groups suspected of cheating. Therefore, these non-cheating user groups need to be cheated. Find and exclude suspected suspicious user groups.

In this embodiment, the suspicious content is a predetermined content that the suspicious user group clicks within the predetermined time period. The non-cheating user group to be excluded may be determined according to the keywords of the suspicious content clicked by each group of suspicious user groups. If the keyword proximity of all suspicious content clicked by a certain group of suspicious users is high, it can be determined that the user group is a non-cheating user group.

Finally, in step 104, the non-cheating user population in the suspicious user population is excluded to determine the cheating user population.

In this embodiment, the non-cheating user group in the suspicious user group is excluded, and the remaining suspicious user groups are determined as the cheating user group.

The method provided by the foregoing embodiment of the present application determines a suspicious user group suspected of cheating by narrowing the detection range, and excludes the non-cheating user group in the suspicious user group according to the keyword of the suspicious content clicked by the suspicious user group, thereby The monitoring of the clicks of the predetermined content is realized, the efficiency of detecting cheating clicks and the detection precision are improved, and the waste of time and resources is reduced.

With further reference to FIG. 2, a flow 200 of one embodiment of a method of determining suspicious clicks is illustrated.

As shown in FIG. 2, in step 201, the number of times each predetermined content is clicked by the user within the predetermined time period is acquired.

In this embodiment, the number of times each predetermined content is clicked by the user in the predetermined time period can be obtained by the click log of the predetermined content. It can be understood that each predetermined content in the predetermined time period can be obtained by other means. The number of times the user clicked. Ben Shen Please do not limit this aspect.

Next, in step 202, it is determined whether the number of times each predetermined content is clicked satisfies a predetermined condition.

In general, if the number of times a predetermined content is clicked is too small, such as less than a predetermined threshold a, the likelihood that the predetermined content involves cheating is small. Because the purpose of cheating is to increase the amount of clicks, if the predetermined content involves cheating, the number of times it is clicked must not be too small.

If the number of times the predetermined content is clicked is too large for a period of time, for example, greater than a predetermined threshold b, then the probability that the predetermined content involves cheating will be small. Because cheating can increase the amount of clicks, the scale of organizational cheating is usually limited, and it is impossible to reach an excessive level. For example, suppose a cheating click can increase the number of clicks 1000, and if the number of times a predetermined content is clicked is 10,000, it can be judged that the predetermined content must not involve cheating. Because even if the predetermined content involves cheating, then the corresponding normal click volume is closer to an order of magnitude larger than the amount of clicks that can be increased by cheating clicks. Therefore, it is not meaningful to increase the amount of clicks by cheating.

In this embodiment, the predetermined condition is a condition that the predetermined content that may be involved in cheating is satisfied by the number of clicks, and firstly, it is determined whether the number of times the predetermined content is clicked within the predetermined time period is greater than or equal to a first predetermined threshold, and less than or equal to the second predetermined. Threshold. If the number of times is greater than or equal to the first predetermined threshold and less than or equal to the second predetermined threshold, it is determined that the number of times satisfies the predetermined condition.

Finally, in step 203, the click corresponding to the predetermined content whose number of clicks satisfies the predetermined condition is determined as a suspicious click.

In the present embodiment, if the number of times a predetermined content is clicked satisfies a predetermined condition, the predetermined content is likely to involve cheating, and the corresponding click is determined as a suspicious click. It should be noted that suspicious clicks do not necessarily mean cheating clicks, because even if a content involves cheating, the content will also be clicked normally by non-cheating users.

With further reference to FIG. 3, a flow 300 of one embodiment of a method of determining at least one suspicious user population suspected of cheating based on suspicious clicks is illustrated.

As shown in FIG. 3, in step 301, information related to suspicious clicks is obtained.

In this embodiment, the related information of the suspicious click may include at least one of the following: The identification information of the user corresponding to the suspicious click; the identification information of the content corresponding to the suspicious click; and the time corresponding to the suspicious click.

Specifically, the identifier information of the user corresponding to the suspicious click may be the MAC address of the user who performs the suspicious click, or the IP address, or the serial number of the terminal device (such as a mobile phone, a computer, etc.), and the present application has suspicious clicks. The specific content and form of the corresponding user identification information are not limited. The content identification information corresponding to the suspicious click may be the name of the content clicked by the suspicious click, or the information such as the number used to identify or distinguish the content, and the specific content and form of the content identification information corresponding to the suspicious click in the present application. Not limited. The time corresponding to the suspicious click may be the time corresponding to the user performing the suspicious click described above. In this embodiment, information related to suspicious clicks can be obtained from the click log. It can be understood that the related information of the suspicious click can also be obtained by other means, and the manner in which the present application obtains the relevant information of the suspicious click is not limited.

Next, in step 302, at least one set of suspicious user groups is determined based on the related information, wherein each set of suspicious user groups clicks on the same set of content within the same time period.

In this embodiment, the suspicious user group may be determined based on the foregoing related information, wherein there may be one or more groups of suspicious user groups, and each group of suspicious user groups clicks the same group of content in the same time period.

In an implementation of this embodiment, a non-parametric clustering algorithm may be used to determine a suspicious user group. Specifically, first, all suspicious clicks are clustered based on the above related information, so that each cluster center The corresponding user group clicks on the same set of content in the same time period. The user group corresponding to each cluster center is then determined as a group of suspicious users.

Referring to FIG. 4, there is shown a flow 400 of one embodiment of a method for determining a non-cheating user population to be excluded based on keywords of suspicious content clicked by each set of suspicious user groups during the predetermined time period.

As shown in FIG. 4, in step 401, keywords of suspicious content clicked by each group of suspicious user groups within the predetermined time period are acquired.

In this embodiment, the suspicious content is a predetermined content that the suspicious user group clicks within the predetermined time period. It should be noted that users in the suspicious user group may also click other content that does not involve cheating within the above predetermined time period, but these do not involve cheating. The content is not related to suspicious clicks and therefore will not be judged as suspicious.

In this embodiment, the keyword of the suspicious content is a word that best reflects various characteristics of the suspicious content. For example, for an advertisement for a drug, the keyword may be a category of an advertisement product (drug), a name of a disease that the drug can treat, a name of a pharmaceutical factory that produces the drug, and the most important chemical component of the drug. Name and so on.

In an implementation of this embodiment, the content of the suspicious content may be parsed to obtain related keywords. In another implementation, the related keywords may also be obtained from the name or identification information of the above suspicious content. It can be understood that there may be other ways of obtaining keywords related to suspicious content, and the method for obtaining keywords related to suspicious content is not limited in the present application.

Next, in step 402, it is determined whether the suspicious content is the same content based on the keyword.

In this embodiment, different suspicious content may be determined according to keywords corresponding to different suspicious content. Specifically, firstly, among the keywords of a group of suspicious content clicked by each group of suspicious user groups in the predetermined time period, whether the proportion of the similar keywords is greater than or equal to a predetermined ratio. If the proportion of the similar keywords is greater than or equal to a predetermined ratio, it is determined that the suspicious content is the same content.

Finally, in step 403, the suspicious user group corresponding to the suspicious content is determined as a non-cheating user group to be excluded.

It should be noted that although the operations of the method of the present invention are described in a particular order in the drawings, this is not required or implied that such operations must be performed in that particular order, or that all illustrated operations must be performed to achieve the desired results. . Instead, the steps depicted in the flowcharts can change the order of execution. Additionally or alternatively, certain steps may be omitted, multiple steps being combined into one step, and/or one step being broken down into multiple steps.

With further reference to FIG. 5, a block diagram of one embodiment of an apparatus for detecting click cheating in accordance with the present application is shown.

As shown in FIG. 5, the apparatus 500 of this embodiment includes: a first determining unit 501, a second determining unit 502, a third determining unit 503, and a fourth determining unit 504. The first determining unit 501 is configured to determine, according to the number of times the predetermined content is clicked by the user within a predetermined time period. Suspicious clicks. The second determining unit 502 is configured to determine, according to the suspicious click, at least one group of suspicious users suspected of cheating. The third determining unit 503 is configured to determine, according to the keyword of the suspicious content clicked by the group of the suspicious user within the predetermined time period, the non-cheating user group to be excluded. The fourth determining unit 504 is configured to exclude the non-cheating user group in the suspicious user group to determine a cheating user group.

In some optional implementations, the first determining unit 501 includes an obtaining subunit, a determining subunit, and a determining subunit (not shown). The obtaining subunit is configured to acquire the number of times each predetermined content is clicked by the user in the predetermined time period. The judging subunit is configured to judge whether the number of times each of the predetermined contents is clicked satisfies a predetermined condition. The determining subunit is configured to determine a click corresponding to the predetermined content whose number of clicks meets the predetermined condition as a suspicious click.

In some optional implementations, the determining subunit is configured to: determine whether the number of clicks is greater than or equal to a first predetermined threshold, and less than or equal to a second predetermined threshold. If so, it is determined that the number of times the click is made satisfies a predetermined condition.

In some optional implementations, the second determining unit 502 includes an information acquisition subunit and a user population determination subunit (not shown). The information obtaining subunit is configured to acquire related information of the suspicious click. The user group determining subunit is configured to determine at least one set of suspicious user groups based on the related information, wherein each group of suspicious user groups clicks the same set of content within the same time period.

In some optional implementation manners, the information related to the suspicious click includes at least one of the following: identification information of the user corresponding to the suspicious click; identification information of the content corresponding to the suspicious click; and corresponding to the suspicious click Moment.

In some optional implementations, the user group determining subunit is configured to: cluster the suspicious clicks based on the related information, so that a user group corresponding to each cluster center clicks in the same time period The same group of content; the user group corresponding to each cluster center is determined as a group of suspicious users.

In some optional implementations, the third determining unit 503 includes a keyword acquisition subunit, a category determination subunit, and a to-be-excluded group determination subunit (not shown). The keyword acquisition subunit is configured to acquire keywords of the suspicious content clicked by the group of the suspicious user group within the predetermined time period. a category determining subunit for determining the ok based on the keyword Whether the content is similar. The to-be-excluded group determining sub-unit is configured to determine the suspicious user group corresponding to the suspicious content as the non-cheating user group to be excluded in response to the suspicious content being the same content.

In some optional implementations, the category determining subunit is configured to: determine whether a proportion of the same type of keywords in the keyword is greater than or equal to a predetermined ratio; if yes, determine that the suspicious content is a similar content.

It should be understood that the units or modules recited in apparatus 500 correspond to the various steps in the methods described with reference to Figures 1-4. Thus, the operations and features described above for the method are equally applicable to the apparatus 500 and the units contained therein, and are not described herein again. The device 500 may be preset in the server, or may be loaded into the server by downloading or the like. Corresponding units in device 500 can cooperate with units in the server to implement a scheme for detecting click cheating.

Referring now to Figure 6, a block diagram of a computer system 600 suitable for use in implementing a terminal device or server of an embodiment of the present application is shown.

As shown in FIG. 6, computer system 600 includes a central processing unit (CPU) 601 that can be loaded into a program in random access memory (RAM) 603 according to a program stored in read only memory (ROM) 602 or from storage portion 608. And perform various appropriate actions and processes. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also coupled to bus 604.

The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and a storage portion 608 including a hard disk or the like. And a communication portion 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the Internet. Driver 610 is also coupled to I/O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory or the like, is mounted on the drive 610 as needed so that a computer program read therefrom is installed into the storage portion 608 as needed.

In particular, the processes described above with reference to the flowcharts may be implemented as a computer software program in accordance with an embodiment of the present disclosure. For example, an embodiment of the present disclosure includes a computer program A sequential product comprising a computer program tangibly embodied on a machine readable medium, the computer program comprising program code for executing the method illustrated in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via communication portion 609, and/or installed from removable media 611.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality and operation of possible implementations of systems, methods and computer program products in accordance with various embodiments of the invention. In this regard, each block of the flowchart or block diagrams can represent a module, a program segment, or a portion of code that includes one or more logic for implementing the specified. Functional executable instructions. It should also be noted that in some alternative implementations, the functions noted in the blocks may also occur in a different order than that illustrated in the drawings. For example, two successively represented blocks may in fact be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts, can be implemented in a dedicated hardware-based system that performs the specified function or operation. Or it can be implemented by a combination of dedicated hardware and computer instructions.

The unit modules described in the embodiments of the present application may be implemented by software or by hardware. The described unit modules may also be provided in the processor, for example, which may be described as a processor comprising an operation first determining unit, a second determining unit, a third determining unit and a fourth determining unit. Wherein, the names of the unit modules do not constitute a limitation on the unit modules themselves in some cases. For example, the first determining unit may also be described as “for determining the number of times the predetermined content is clicked by the user within a predetermined time period. Unit of suspicious clicks."

In another aspect, the present application further provides a computer readable storage medium, which may be a computer readable storage medium included in the apparatus described in the foregoing embodiment, or may exist separately, not A computer readable storage medium that is assembled into a terminal. The computer readable storage medium stores one or more programs that are used by one or more processors to perform the methods described herein for detecting click cheating.

The above description is only a preferred embodiment of the present application and a description of the principles of the applied technology. Those skilled in the art should understand that the scope of the invention referred to in the present application is not limited. The technical solutions of the specific combination of the above technical features are also included in other technical solutions formed by any combination of the above technical features or equivalent features thereof without departing from the inventive concept. For example, the above features are combined with the technical features disclosed in the present application, but are not limited to the technical features having similar functions.

Claims

A method for detecting click cheating, characterized in that the method comprises:

Determining a suspicious click based on the number of times the predetermined content is clicked by the user within a predetermined time period;

Determining at least one suspicious user group suspected of cheating according to the suspicious click;

Determining a non-cheating user group to be excluded according to a keyword of the suspicious content clicked by the group of the suspicious user within the predetermined time period; and

The non-cheating user group in the suspicious user group is excluded to determine the cheating user group.
The method of claim 1, wherein the determining the suspicious click based on the number of times the predetermined content is clicked by the user within the predetermined time period comprises:

Obtaining the number of times each predetermined content is clicked by the user within the predetermined time period;

Determining whether the number of times each of the predetermined contents is clicked satisfies a predetermined condition;

The click corresponding to the predetermined content whose number of clicks satisfies the predetermined condition is determined as a suspicious click.
The method according to claim 2, wherein determining whether the number of clicks satisfies a predetermined condition comprises:

Determining whether the number of times of being clicked is greater than or equal to a first predetermined threshold, and less than or equal to a second predetermined threshold;

If so, it is determined that the number of times the click is made satisfies a predetermined condition.
The method according to any one of claims 1 to 3, wherein the determining, according to the suspicious click, at least one group of suspicious users suspected of cheating, comprising:

Obtaining information about the suspicious click;

At least one set of suspicious user groups is determined based on the related information, wherein each set of suspicious user groups clicks on the same set of content within the same time period.
The method according to claim 4, wherein the information related to the suspicious click comprises at least one of the following:

The identification information of the user corresponding to the suspicious click;

Identification information of the content corresponding to the suspicious click;

The moment corresponding to the suspicious click.
The method according to any one of claims 4-5, wherein the determining at least one group of suspicious users based on the related information comprises:

And clustering the suspicious clicks based on the related information, so that a user group corresponding to each cluster center clicks the same group of content in the same time period;

The user group corresponding to each cluster center is determined as a group of suspicious users.
The method according to any one of claims 1-6, wherein the determining the non-cheating user to be excluded according to the keyword of the suspicious content clicked by the group of the suspicious user within the predetermined time period Groups, including:

Obtaining keywords of the suspicious content clicked by the group of the suspicious user within the predetermined time period;

Determining, based on the keyword, whether the suspicious content is a similar content;

If yes, the suspicious user group corresponding to the suspicious content is determined as a non-cheating user group to be excluded.
The method according to claim 7, wherein the determining whether the suspicious content is a similar content based on the keyword comprises:

Determining whether a proportion of the same type of keywords in the keyword is greater than or equal to a predetermined ratio;

If so, the suspicious content is determined to be the same content.
A device for detecting click cheating, characterized in that the device comprises:

a first determining unit, configured to determine a suspicious click based on a number of times the predetermined content is clicked by the user within a predetermined time period;

a second determining unit, configured to determine, according to the suspicious click, at least one group of suspicious users suspected of cheating;

a third determining unit, configured to: according to each group of the suspicious user group, at the predetermined time The keyword of the suspicious content clicked in the segment determines the non-cheating user group to be excluded;

The fourth determining unit is configured to exclude the non-cheating user group in the suspicious user group to determine a cheating user group.
The apparatus according to claim 9, wherein the first determining unit comprises:

Obtaining a subunit, configured to acquire the number of times each predetermined content is clicked by the user within the predetermined time period;

a determining subunit, configured to determine whether the number of times each of the predetermined content is clicked satisfies a predetermined condition;

The determining subunit is configured to determine a click corresponding to the predetermined content whose number of clicks meets the predetermined condition as a suspicious click.
The apparatus according to claim 10, wherein said determining subunit is configured to:

Determining whether the number of times of being clicked is greater than or equal to a first predetermined threshold, and less than or equal to a second predetermined threshold;

If so, it is determined that the number of times the click is made satisfies a predetermined condition.
The apparatus according to any one of claims 9-11, wherein the second determining unit comprises:

An information obtaining subunit, configured to acquire information about the suspicious click;

The user group determining subunit is configured to determine at least one group of suspicious users based on the related information, wherein each group of suspicious users clicks the same group of content in the same time period.
The apparatus according to claim 12, wherein the information related to the suspicious click comprises at least one of the following:

The identification information of the user corresponding to the suspicious click;

Identification information of the content corresponding to the suspicious click;

The moment corresponding to the suspicious click.
The apparatus according to any one of claims 12-13, wherein the user group determining subunit is configured to:

And clustering the suspicious clicks based on the related information, so that a user group corresponding to each cluster center clicks the same group of content in the same time period;

The user group corresponding to each cluster center is determined as a group of suspicious users.
The apparatus according to any one of claims 9-14, wherein the third determining unit comprises:

a keyword obtaining subunit, configured to acquire a keyword of the suspicious content clicked by the suspicious user group in the predetermined time period;

a category determining subunit, configured to determine, according to the keyword, whether the suspicious content is a similar content;

The group determining subunit to be excluded is configured to determine the suspicious user group corresponding to the suspicious content as the non-cheating user group to be excluded in response to the suspicious content being the same content.
The apparatus according to claim 15, wherein said class determination subunit is configured to:

Determining whether a proportion of the same type of keywords in the keyword is greater than or equal to a predetermined ratio;

If so, the suspicious content is determined to be the same content.
An apparatus, comprising:

One or more processors;

Memory

One or more programs, the one or more programs being stored in the memory, when executed by the one or more processors:

Determining a suspicious click based on the number of times the predetermined content is clicked by the user within a predetermined time period;

Determining at least one suspicious user group suspected of cheating according to the suspicious click;

Determining a non-cheating user group to be excluded according to a keyword of the suspicious content clicked by the group of the suspicious user within the predetermined time period; and

The non-cheating user group in the suspicious user group is excluded to determine the cheating user group.
A non-volatile computer storage medium storing one or more programs, when the one or more programs are executed by a device, causing the device to:

Determining a suspicious click based on the number of times the predetermined content is clicked by the user within a predetermined time period;

Determining at least one suspicious user group suspected of cheating according to the suspicious click;

Determining a non-cheating user group to be excluded according to a keyword of the suspicious content clicked by the group of the suspicious user within the predetermined time period; and

The non-cheating user group in the suspicious user group is excluded to determine the cheating user group.