CN112488754A - Anti-cheating system and method for advertisement clicking - Google Patents
Anti-cheating system and method for advertisement clicking Download PDFInfo
- Publication number
- CN112488754A CN112488754A CN202011369457.1A CN202011369457A CN112488754A CN 112488754 A CN112488754 A CN 112488754A CN 202011369457 A CN202011369457 A CN 202011369457A CN 112488754 A CN112488754 A CN 112488754A
- Authority
- CN
- China
- Prior art keywords
- request
- advertisement
- cheating
- information
- module
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000001914 filtration Methods 0.000 claims abstract description 35
- 238000009434 installation Methods 0.000 claims description 12
- 230000006399 behavior Effects 0.000 description 29
- 230000006872 improvement Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000008450 motivation Effects 0.000 description 2
- 241000209202 Bromus secalinus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0248—Avoiding fraud
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
An anti-cheating system for advertisement clicking comprises an acquisition module, an identification module, a filtering module and a recording module; the acquisition module is used for receiving and extracting the IP address, the ID information and the UA information in the advertisement request; the identification module is used for judging whether the advertisement request is a cheating request according to the IP address and UA information of the advertisement request; the filtering module is used for processing the cheating request identified by the identification module into an invalid request so as to filter the cheating request; and the recording module is used for adding the IP address, the ID and the UA information of the cheating request into a blacklist library. According to the method and the device, cheating advertisement clicks are identified through different dimensions, and the identification accuracy is improved.
Description
Technical Field
The invention relates to the technical field of internet advertisements, in particular to an anti-cheating system and method for advertisement clicking.
Background
With the wide application of the internet, the internet advertisement is increasingly favored by advertisers. Advertisers who pay for placement of advertisements can pay publishers (advertising platforms) to place their advertisements through web pages, search engines, browsers, or other online media, thereby promoting their products well. Currently, one of the mainstream advertisement charging methods is pay-Per-Click (abbreviated as CPC) advertisement.
In the CPC advertising mode, the advertiser only needs to pay for the behavior of the user clicking on the advertisement, and does not need to pay for the exposure of the advertisement, thereby avoiding the risk of exposing only and not clicking. Because advertisers pay publishers once each time a user clicks on an advertisement, advertisers expect that their paid ad clicks are valid clicks by real users rather than cheating clicks (also referred to as "malicious clicks"). In addition, the traffic owner, e.g., web site owner, public account with a certain amount of vermicelli, of the carrier providing the user traffic may participate in profit raising of the advertisement. Under the condition that the advertisement exposure is the same, the higher the click rate is, the higher the profit which is divided by the traffic owner is, therefore, the traffic owner has a strong cheating motivation to improve the advertisement click rate.
Therefore, how to verify whether the CPC advertisement user cheats is very important. Most of the prior art relies on the IP address of the advertisement request for judgment. When the advertisement request times of the same IP reach a certain value in a certain time period, the advertisement request is regarded as a cheating request, and the IP address is added into the blacklist library, so that all the advertisement requests of the IP are filtered in the follow-up process. The technology depends on single IP to judge cheating, and has the problems of high false killing rate and high omission factor.
Disclosure of Invention
The technical problem to be solved by the invention is to provide an anti-cheating system and method for advertisement clicking, which can identify cheating advertisement clicking through different dimensions and improve the accuracy of identification.
In the present invention, the false click means that after the user clicks, no subsequent actions such as watching, downloading, installing, etc. are performed, and is specifically determined according to the advertisement content. For example, the display type advertisement only needs to be watched by the corresponding user; the download class should then correspond to the download and install behavior. The advertisement request refers to an advertisement bidding request that the terminal initiates an advertisement bidding request to the server and obtains a final advertisement display opportunity.
In order to solve the technical problem, the invention provides an anti-cheating system for advertisement clicking, which comprises an acquisition module, an identification module, a filtering module and a recording module, wherein the acquisition module is used for acquiring advertisement information;
the acquisition module is used for receiving and extracting the IP address, the ID information and the UA information in the advertisement request;
the identification module is used for judging whether the advertisement request is a cheating request according to the IP address and UA information of the advertisement request;
the filtering module is used for processing the cheating request identified by the identification module into an invalid request so as to filter the cheating request;
and the recording module is used for adding the IP address, the ID and the UA information of the cheating request into a blacklist library.
In the above technical solution, the ID information refers to a device ID. Can be obtained by Telephony Manager service provided by the system, and has uniqueness. The User Agent is named as a User Agent UA for short, and is a special character string header, so that the server can identify an operating system and version, a CPU type, a browser and version, a browser rendering engine, a browser language, a browser plug-in and the like used by a client. Through the identification, the website visited by the user can display different typesetting so as to provide better experience for the user or perform information statistics. For example: when a User accesses a downloading website by using the Firefox, the website acquires the browser version of the User through a User Agent String, and if the content of the website is found to be difficult to be perfectly shown by the Firefox of the version, a personalized prompt can be given: "you can try on the latest version of Firefox, which can reveal the latest Web GL and HTML5 content". In addition, the website can also give out different CSS files according to the User Agent String so as to ensure that the best effect can be shown on different browsers. The recording module also sends the last advertisement request time of the cheating request to the blacklist library for recording. The information recorded in the blacklist library comprises an IP address, an ID, UA information and the last advertisement request time corresponding to the user.
As an improvement of the above solution, the identification module includes:
the comparison unit is used for comparing the IP address and the ID information with the IP address and the ID information in the blacklist library respectively; if the IP address or the ID information exists in a blacklist library, marking the advertisement request as a cheating request;
the IP filtering unit is used for marking the advertisement requests of which the clicking times exceed the threshold value in a period of time of the same IP as cheating requests;
and the UA filtering unit is used for comparing the request UA with the click UA and identifying the advertisement request with inconsistent proportion exceeding a threshold value as a cheating request.
In the above technical solution, the threshold value of the number of clicks is a fixed value specified by the system forenotice, and refers to a peak value of the click, rather than an average value over a long period of time. Comparing the request UA with the click UA can increase the dimensionality for identifying the cheating request, and the information such as UA installation is not adopted due to the continuity of user behaviors, namely the user does not always install the cheating request in real time after downloading is completed. The IP filtering unit can also filter anonymous IP and machine room IP, wherein the machine room IP refers to IP addresses of a certain machine room or other various public IP addresses. The scheme increases the identification accuracy and can filter out more cheating requests.
As an improvement of the above solution, the anti-cheating system for advertisement clicking further includes a tracking module, including:
a marking unit for adding a mark to the advertisement content; the advertisement content can be pictures, streaming media or videos;
the receiving unit is used for receiving the user behavior data returned by the mark and the corresponding link; the user behavior data comprises click, download and installation data of the user on the advertisement;
and the checking unit is used for checking the link received by the receiving unit with the advertisement request, marking the advertisement request with the false click ratio exceeding a threshold value as a cheating request, and simultaneously adding the IP address, the ID and the UA information of the cheating request into a blacklist library.
In the technical scheme, the tracking module realizes the monitoring of the authenticity of the advertisement display by tracking the advertisement display condition, and can effectively process the condition of counterfeit advertisement display in the advertisement cheating. The mark can be positioned in the picture or the video, covers the main form of the advertisement and has wide adaptability.
As an improvement of the above scheme, the mark added by the marking unit is one or several pixel points.
In the technical scheme, when the advertisement content is a picture, the advertisement content is marked as a pixel point. When the advertisement content is streaming media, the mark may be one pixel point or several pixel points. When the advertisement content is a video, the mark may be one pixel point or several pixel points. When the advertisement content is streaming media and video, the playing time of the streaming media and the video needs to be considered as a criterion for judgment. When the judgment criterion is one, only one pixel point can be marked. When there are multiple criteria, multiple pixels need to be marked. The scheme ensures that the mark has high flexibility, different mark forms can be selected according to different advertisement contents, and meanwhile, because the mark is a pixel point, the mark occupies less resources and does not influence the display of the advertisement.
As an improvement of the above scheme, the information checked by the checking unit is comparison between advertisement request times and subsequent user behavior times, including request times and display times, request times and download times, and request times and installation times.
In the scheme, the user clicks with obviously abnormal data can be identified according to the comparison between the user clicking times and the follow-up behavior times. Meanwhile, by comparing the comparison value of the two with the threshold value, the cheating requests can be filtered out, and the probability that normal advertisement clicks are judged mistakenly as the cheating requests can be reduced.
As an improvement of the above scheme, the anti-cheating system for advertisement clicking further comprises an updating module, which is used for removing the information that the advertisement is not requested again for a long time in the blacklist library from the blacklist library.
In the scheme, considering the misjudgment rate of any anti-cheating system, the information of the inactive advertisement request user in the blacklist library is removed through the updating module, so that the information misjudged as the cheating request is easier to remove from the blacklist library. Meanwhile, the information of the user requesting the non-active advertisement is removed from the blacklist library, so that the infinite expansion of the blacklist library is prevented, and the system delay is caused.
As an improvement of the above solution, the updating module calculates the longer period of time based on the last advertisement request time recorded by the recording module.
In the above scheme, the longer period of time is a fixed time specified by the system, and may be one of any fixed time periods such as 7 days, 14 days, 30 days, and the like. The updating module updates the blacklist library at a fixed frequency, so that the reading and writing frequency of information of the blacklist library can be reduced, and the running speed of the system is improved. According to the scheme, the dynamic updating of the blacklist library by the updating module is realized, so that the timeliness of updating the blacklist library is better.
Correspondingly, the invention also provides an anti-cheating method for advertisement clicking, which comprises the following steps.
A. And receiving and extracting the IP address, the ID information and the UA information in the advertisement request by using the acquisition module.
In this step, all the three pieces of information of the advertisement request are acquired as the main information of the subsequent step.
B. Comparing the IP address and the ID information with the IP address and the ID information in the blacklist library respectively by using the comparison unit; if the IP address or ID information exists in a blacklist repository, the advertisement request is marked as a cheating request.
In this step, the IP address, ID information, and information in the blacklist are compared in a traversal manner to identify information present in the blacklist repository. Because all the advertisement requests need to be traversed and compared, the information processing amount in the step is very large, and therefore higher necessary hardware needs to be equipped and the retrieval method needs to be optimized.
C. The advertisement requests with the same IP clicking times exceeding a threshold value in a period of time are marked as cheating requests by using the IP filtering unit.
In the step, the method is not triggered by normal users, so that the method has higher accuracy. And because the recording function exists for the cheating users, the cheating income of the single advertising cheating user is very limited.
D. And comparing the request UA with the click UA by using the UA filtering unit, and identifying the advertisement request with inconsistent proportion exceeding a threshold value as a cheating request.
In the step, UA is added as a judgment standard, so that cheating users can be more easily identified, and the problem of missed detection can be solved when IP is used as a single standard.
E. And processing the cheating request identified by the identification module into an invalid request by using the filtering module, so as to filter.
In this step, the benefit of the advertiser can be strongly secured by processing the cheating request.
F. And adding the IP address, the ID and the UA information of the cheating request into a blacklist library by using the recording module.
In the step, the information of the cheating request is recorded into the blacklist library, so that all the advertisement requests of the cheating users are directly filtered, the advertisement cheating benefits are small, and the benefits of advertisers are maximized.
As an improvement of the above scheme, the anti-cheating method for advertisement clicking further comprises the following steps.
G. Adding marks to the advertisement content by using the marking units; the advertisement content can be pictures, streaming media or videos.
In the step, the mark is added to the advertisement content, so that the advertisement display condition is accurately identified, and the false data of advertisement cheating can be effectively prevented.
H. Receiving the user behavior data returned by the mark and the corresponding link by using the receiving unit; wherein the user behavior data comprises user click, download and installation data of the advertisement.
In the step, the user behavior data and the corresponding link returned by the mark in the previous step are received, and the follow-up user behavior data is collected, so that whether the advertisement request is a cheating request can be analyzed and judged more comprehensively and accurately, and the judgment accuracy is improved.
I. And the link received by the receiving unit is checked with the advertisement request by using the checking unit, the advertisement request with the false click ratio exceeding a threshold value is marked as a cheating request, and the IP address, the ID and the UA information of the cheating request are added into a blacklist library.
In the step, the advertisement requests exceeding the threshold are screened out by checking the links and the times corresponding to clicking, downloading and installing, and are judged as cheating requests, and the user behavior habits are better met and the obtained conclusion is more accurate through the front-back sequence correlation comparison of the user behaviors.
As an improvement of the above scheme, the anti-cheating method for advertisement clicking further comprises the following steps.
J. And the information which does not require the advertisement again for a long time in the blacklist library is removed from the blacklist library by using the updating module.
In the step, a member exit mechanism in the blacklist library is added, and dynamic update of the blacklist library is realized, so that the method can realize better adaptability in a longer time.
The invention has the following beneficial effects.
The invention judges and identifies the cheating request through the IP address and the UA information together, so that the judgment on the advertising request is more three-dimensional and more accurate. The invention stores a plurality of information of the cheating requests in the blacklist library, so that the subsequent advertisement requests of the same cheating user are all marked as invalid requests, thereby leading the income of the advertisement cheating to be severely limited and fundamentally limiting the motivation of the cheating user.
Drawings
Fig. 1 is a schematic structural diagram of an anti-cheating system for advertisement clicking according to a first embodiment of the present invention.
Fig. 2 is a schematic structural diagram of an anti-cheating system for advertisement clicking according to a second embodiment of the present invention.
Fig. 3 is a schematic structural diagram of an anti-cheating system for advertisement clicking according to a third embodiment of the present invention.
FIG. 4 is a flowchart illustrating a method for anti-cheating on advertisement clicks according to a first embodiment of the present invention.
FIG. 5 is a flowchart illustrating a method for anti-cheating on advertisement clicks according to a second embodiment of the present invention.
FIG. 6 is a flowchart illustrating a third embodiment of an anti-cheating method for advertisement clicking according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings.
In a first embodiment of the present invention, as shown in fig. 1, an anti-cheating system for advertisement clicking is provided, which includes an obtaining module 100, an identifying module 200, a filtering module 300, and a recording module 400.
The obtaining module 100 is configured to receive and extract the IP address, the ID information, and the UA information in the advertisement request.
Specifically, the obtaining module 100 checks whether the information in the advertisement request includes all three information, i.e., the IP address, the ID information, and the UA information, after receiving the advertisement request, and transmits a request for obtaining information to the terminal that transmitted the advertisement request if the information in the advertisement request is missing. Since the information added to the advertisement request usually includes information other than the above three types of information, the acquisition module 100 needs to extract three types of information, i.e., the IP address, the ID information, and the UA information, from a plurality of types of information transmitted from the terminal. For example, the information accompanying the terminal when transmitting the advertisement information includes: the IP address, the MAC address, the longitude and latitude, the UA information, the deviceid, and the ID information, the obtaining module needs to extract the three information, i.e., the IP address, the ID information, and the UA information, from these information.
The identifying module 200 is configured to determine whether the advertisement request is a cheating request according to the IP address and the UA information of the advertisement request.
Specifically, the identification module 200 includes an alignment unit 201, an IP filtering unit 202, and a UA filtering unit 203. The comparison unit 201 compares the IP address and the ID information with the IP address and the ID information in the blacklist library, respectively. If the IP address or ID information is present in the blacklist repository, the advertisement request is marked as a cheating request. The IP filtering unit 202 is used for marking the advertisement requests of which the clicking times exceed the threshold value in a period of time of the same IP as cheating requests and recording the times of the requests in the period of time; and the IP filtering unit 202 will also filter out anonymity in the count library belonging to maxmnd and the IP of the machine room IP. The total record number of the advertisement requests of the terminal is represented by win _ all, click _ all represents the number of clicks sent by the terminal, and diff _ ua represents the difference value between the advertisement requests of the terminal and the total number of clicks, namely diff _ ua = win _ all-click _ all. The UA filtering unit 203 compares the request UA with the clicked UA, and identifies the advertisement request with the inconsistent ratio exceeding the threshold as a cheating request, that is, the advertisement request with the diff _ UA/win _ all value exceeding a certain value is judged as a cheating request.
A filtering module 300, configured to process the cheating request identified by the identifying module 200 as an invalid request, so as to perform filtering.
Specifically, the filtering module 300 terminates all the cheating requests, so that the cheating requests cannot be received by the advertisement bidding system, the advertisement sending system, and the like on the server, thereby realizing the invisibility of the cheating requests. The system is located before the normal advertisement request response system, and only the advertisement requests screened by the system are sent to the response system. The filtering module 300 is the only module of the system having the intercepting function. When the filtering module 300 intercepts an advertisement request, the advertisement request cannot be responded to; and when the filtering module 300 passes the ad request, the ad request is responded to.
A recording module 400, configured to add the IP address, the ID, and the UA information of the cheating request to the blacklist repository.
Specifically, the recording module 400 receives the cheating request information sent by the filtering module 300, and writes the cheating request information into the blacklist library after adding the current time information. And if the cheating request information is not in the blacklist database before, writing the IP address, the ID information, the UA information and the time information into the blacklist database. If the cheating request information is in the blacklist database before, writing the current time information into the blacklist database, and overwriting the previous time information.
The second embodiment of the present invention, as shown in fig. 2, is different from the first embodiment, and further includes a tracking module 500.
Specifically, the tracking module 500 tracks the normally served advertisements and identifies the cheating advertisement requests that were missed in the previous embodiment. The tracking module 500 comprises a marking unit 501, a receiving unit 502 and a collating unit 503. The advertisement content delivered in the advertisement delivery is usually one of a picture, streaming media and video. The picture is a single picture file, and both streaming media and video can be regarded as a new file format formed by arranging a plurality of pictures according to a time sequence. The marking unit 501 marks a pixel point on a picture. For a picture, the marking unit 501 only marks one pixel point, i.e. one marking point. For streaming media and video, the marking unit 501 selectively marks one or more pixel points on one or more of the pictures, wherein only one pixel point is marked on one picture. When only one mark is carried out on the streaming media or the video, only one pixel point is selected from the corresponding picture to carry out marking. When multiple marks need to be marked in the streaming media or videos, multiple corresponding pictures need to be selected from the streaming media or videos, and one pixel point is selected on each selected picture for marking. The selection of the pixel points is generally located close to the edge, so that the display of the advertisement content is not influenced. For example, when a video needs to be marked for the 5 th second, the marking unit 501 first obtains a picture played to the 5 th second in the video, and marks a specified pixel point on the picture. For another example, when the 5 th second and the 10 th second of a certain video need to be marked, the marking unit 501 first obtains the picture played to the 5 th second and the picture played to the 5 th second in the video, and marks a pixel point on each of the two pictures. Therefore, the judgment on the playing time of the streaming media or the video can be realized, and effective advertisement clicking users can be identified.
The receiving unit 502 receives subsequent behavior data of the advertisement in the presentation, i.e. marks the returned user behavior data and the corresponding link. The user behavior data includes user click, download and install data for the advertisement. In normal user click behaviors, the most ideal situation is that a user clicks an advertisement once, then performs a downloading operation once, and then performs an installation operation once, but there may be a case where multiple advertisement click behaviors correspond to one advertisement downloading operation, or after the advertisement downloading is completed, the installation operation is performed at a longer interval. However, in normal user behavior data, the number of advertisement clicks corresponding to one download is limited, and the number of downloads corresponding to one installation is also limited, and the normal range of the normal user behavior data can be analyzed through historical data analysis of the user behavior. Therefore, the checking unit 503 checks the link received by the receiving unit 502 with the advertisement request, and marks the advertisement request whose false click ratio exceeds the threshold as a cheat request, while adding the IP address, ID and UA information of the cheat request to the blacklist repository. When the checking unit 503 adds the cheating request information to the blacklist, the recording module 400 will automatically supplement the current time information for the written record and regard it as the last advertisement request time of the cheating request. The information checked by the checking unit 503 is comparison between the advertisement request times and the subsequent user behavior times, and includes request times and display times, request times and download times, and request times and installation times.
The third embodiment of the present invention as shown in fig. 3 is different from the second embodiment, and further includes an updating module 600, configured to remove information that an advertisement is not requested again for a long time in the blacklist library from the blacklist library.
Specifically, if a user is hijacked, the IP and UA of the user may be used for advertising cheating against the user's will, and the behavior characteristics of the user may be restored to the behavior characteristics of a normal user after the hijacking is finished, especially after the vulnerability of the user to be hijacked is filled. It is therefore necessary to maintain a mechanism for recovering the identity of a normal user for users whose behavior is abnormal for a short period of time due to unexpected reasons. From the characteristic of the clicking behavior of the user, when the hijacked condition of the user disappears, the clicking rate of the user on the advertisement can be restored to a normal level. Since the click rate of the advertisement by the normal user is usually low, for example, within 5%, the normal user will not click on the advertisement for a long time. Based on the rule, the updating module 600 calculates the last advertisement request time recorded by the recording module 400 as a reference, and deletes the user information from the blacklist library when the user in the blacklist library has no advertisement request for a preset long period of time. The update module 600 only scans and determines the information in the blacklist library at regular time intervals in consideration of the bearing capacity of the server. However, since the advertisement request has the characteristic of periodic fluctuation, the updating module 600 is performed in a time period with a small number of advertisement requests.
Correspondingly, as shown in fig. 4, the invention further provides an anti-cheating method for advertisement clicking, which comprises the following steps.
S001, the IP address, the ID information and the UA information in the advertisement request are received and extracted by using the acquisition module.
In this step, three information, i.e., an IP address, ID information, and UA information, are received and extracted for each advertisement request received by the system. Normally, the advertisement request will carry the IP address, ID information and UA information, but there are also partial advertisement requests missing partial information. If the advertisement request lacks partial information, the terminal needs to be requested for the missing data. The information obtained in this step is the key data in the method, and each step in this embodiment needs to be processed accordingly.
And S002, comparing whether the IP address and the ID information exist in the blacklist library or not by using the comparison unit.
In the step, the new advertisement request is compared with the information in the blacklist library, and if the advertisement request is identified as a cheating request by the system, the cheating request can be identified in the shortest time, so that the subsequent calculation and judgment processes can be saved. On the other hand, compared with the condition that the cheating request can be judged after a certain number of clicks through IP filtering, the cheating request can be found out when the advertisement request is carried out for the first time through the method, and therefore cost for finding the cheating request is saved.
And S003, judging whether the number of clicks of the same IP in a period of time exceeds a threshold value by using the IP filtering unit.
In this step, since the number of clicks on the same advertisement by the same IP user in the same time period under normal conditions is limited, most of the cheating requests can be filtered out by this method. Since the method of clicking a lot through IP is the most common cheating method, the method can cope with most cheating requests.
And S004, comparing the request UA with the clicked UA by using the UA filtering unit, and judging whether the inconsistent proportion of the request UA and the clicked UA exceeds a threshold value.
In this step, the method is only effective for the case where the same user has multiple advertisement requests. Since the UA is based on the personalized information of the user and includes the characteristics of the browser, after a normal user clicks an advertisement, the browser may jump to a standby state, so that the UA information changes, and the ratio of the request UA to the clicked UA is used as the standard for judging the cheating request, but the cheating request is judged if the request UA is inconsistent with the clicked UA. For the cheating request, because the click and the download are false information, the request UA information and the download UA information are often inconsistent, namely, the inconsistency is very high, so the method can effectively judge the cheating request.
And S005, using the filtering module to process the cheating request identified by the identification module into an invalid request, thereby filtering.
In this step, the cheating request recognized in steps S003 and S004 is processed as an invalid request, and the cheating request is not transmitted to the system that transmitted the advertisement, and thus is not responded to the cheating request. When step S003 recognizes the advertisement request as the cheating request, it jumps directly to step S005. When the advertisement request is recognized as a normal request in step S003, step S004 is performed, and if it is determined as a cheat request, step S005 is performed. If the advertisement request is recognized as a normal request in step S004, the method is ended.
S006, adding the IP address, the ID and the UA information of the cheating request to a blacklist library by using the recording module.
In the step, the identified cheating request information is added into the blacklist library, so that the cheating requests from the user can be quickly processed into invalid requests, the cheating requests are quickly identified, and the operating pressure of the server is reduced.
As another embodiment of the above method, as shown in fig. 5, unlike the above method, the following steps are further included.
S007, adding marks to the advertisement content by using the marking units; the advertisement content can be pictures, streaming media or videos.
In this step, normal advertisement display is monitored, and the most real advertisement display effect can be obtained by marking the advertisement display content, so that credible display data can be obtained. Meanwhile, the needs of various advertisement displays are considered, and the uniform mark is used, so that different advertisement contents can be quickly marked.
S008, receiving the user behavior data returned by the mark and the corresponding link by using the receiving unit; wherein the user behavior data comprises user click, download and installation data of the advertisement.
In this step, the click, download and install data obtained by the marking in step S007 can be well used to judge the user behavior during the advertisement presentation.
S009, the link received by the receiving unit is checked with the advertisement request by using the checking unit, the advertisement request with the false click ratio exceeding a threshold value is marked as a cheating request, and meanwhile, the IP address, the ID and the UA information of the cheating request are added into a blacklist library.
In this step, the comparison data with the data of the advertisement request is obtained by analyzing the advertisement display effect, so that whether the advertisement is a cheating advertisement can be judged again. Since this step requires obtaining multiple advertisement requests and display data, it is also necessary to do so after the user has multiple clicks and downloads data.
As another embodiment of the above method, as shown in fig. 6, unlike the above method, the following steps are further included.
And S010, removing the information which does not request the advertisement again for a long time in the blacklist library from the blacklist library by using the updating module.
In the step, the data in the blacklist library is removed regularly, so that the data in the blacklist library are all active cheating users, a data release function in the blacklist library is realized, the users identified as cheating requests due to short-term interference factors can return to normal user groups, and the problems of overlong retrieval time, slow response speed and the like caused by infinite expansion of the blacklist library are solved.
While the invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not to be limited to the disclosed embodiment, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (10)
1. An anti-cheating system for advertisement clicking is characterized in that: the device comprises an acquisition module, an identification module, a filtering module and a recording module;
the acquisition module is used for receiving and extracting the IP address, the ID information and the UA information in the advertisement request;
the identification module is used for judging whether the advertisement request is a cheating request according to the IP address and UA information of the advertisement request;
the filtering module is used for processing the cheating request identified by the identification module into an invalid request so as to filter the cheating request;
and the recording module is used for adding the IP address, the ID and the UA information of the cheating request into a blacklist library.
2. The anti-cheating system of advertisement clicks of claim 1, wherein said identification module comprises:
the comparison unit is used for comparing the IP address and the ID information with the IP address and the ID information in the blacklist library respectively; if the IP address or the ID information exists in a blacklist library, marking the advertisement request as a cheating request;
the IP filtering unit is used for marking the advertisement requests of which the clicking times exceed the threshold value in a period of time of the same IP as cheating requests;
and the UA filtering unit is used for comparing the request UA with the click UA and identifying the advertisement request with inconsistent proportion exceeding a threshold value as a cheating request.
3. The anti-cheating system on advertisement clicks recited in claim 1, further comprising a tracking module comprising:
a marking unit for adding a mark to the advertisement content; the advertisement content can be pictures, streaming media or videos;
the receiving unit is used for receiving the user behavior data returned by the mark and the corresponding link; the user behavior data comprises click, download and installation data of the user on the advertisement;
and the checking unit is used for checking the link received by the receiving unit with the advertisement request, marking the advertisement request with the false click ratio exceeding a threshold value as a cheating request, and simultaneously adding the IP address, the ID and the UA information of the cheating request into a blacklist library.
4. The anti-cheating system of advertisement clicking of claim 3, wherein the mark added by said marking unit is one or several pixels.
5. The system of claim 3, wherein the information checked by the checking unit is a comparison between the number of advertisement requests and the number of subsequent user actions, including the number of requests and the number of presentations, the number of requests and the number of downloads, and the number of requests and the number of installations.
6. The system of claim 1, further comprising an update module for removing from the blacklist library information that an advertisement has not been requested again for a longer period of time.
7. The system of claim 6, wherein the updating module calculates the longer period of time based on a last advertisement request time recorded by the recording module.
8. An anti-cheating method for advertisement clicking is characterized by comprising the following steps:
A. receiving and extracting the IP address, the ID information and the UA information in the advertisement request using the acquisition module of any one of claims 1-7;
B. comparing the IP address, ID information with the IP address, ID information in the blacklist library, respectively, using the comparison unit of any one of claims 1-7; if the IP address or the ID information exists in a blacklist library, marking the advertisement request as a cheating request;
C. using the IP filtering unit of any of claims 1-7 to mark advertising requests for which the number of clicks of the same IP over a period of time exceeds a threshold as cheating requests;
D. comparing the request UA with the click UA using the UA filter unit of any one of claims 1-7, and identifying as a cheating request an advertisement request for which the ratio of disagreement between the request UA and the click UA exceeds a threshold;
E. filtering by processing the cheating requests identified by the identification module as invalid requests using the filtering module of any of claims 1-7;
F. adding the IP address, ID and UA information of the cheat request to a blacklist repository using the logging module of any of claims 1-7.
9. The anti-cheating method of advertisement clicking as claimed in claim 8, further comprising the steps of:
G. tagging of advertising content with a tagging unit according to any of claims 1-7; the advertisement content can be pictures, streaming media or videos;
H. receiving user behavior data returned by the tag and a corresponding link using the receiving unit of any of claims 1-7; the user behavior data comprises click, download and installation data of the user on the advertisement;
I. using the collating unit according to any one of claims 1-7 to collate the link received by the receiving unit with the advertisement request and to mark as a cheating request an advertisement request for which the false click ratio exceeds a threshold value, while adding the IP address, ID and UA information of the cheating request to the blacklist store.
10. The anti-cheating method of advertisement clicking as claimed in claim 9, further comprising the steps of:
J. the use of an update module as claimed in any of claims 1 to 7 to remove from the blacklist store information that an advertisement has not been requested again for a longer period of time in the blacklist store.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011369457.1A CN112488754A (en) | 2020-11-30 | 2020-11-30 | Anti-cheating system and method for advertisement clicking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011369457.1A CN112488754A (en) | 2020-11-30 | 2020-11-30 | Anti-cheating system and method for advertisement clicking |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112488754A true CN112488754A (en) | 2021-03-12 |
Family
ID=74936992
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011369457.1A Pending CN112488754A (en) | 2020-11-30 | 2020-11-30 | Anti-cheating system and method for advertisement clicking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112488754A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113225325A (en) * | 2021-04-23 | 2021-08-06 | 北京明略昭辉科技有限公司 | IP (Internet protocol) blacklist determining method, device, equipment and storage medium |
| CN114119037A (en) * | 2022-01-24 | 2022-03-01 | 深圳尚米网络技术有限公司 | Marketing anti-cheating system based on big data |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101296360A (en) * | 2007-04-24 | 2008-10-29 | 宋亚民 | Advertisement issuing and charging method and system |
| CN105677869A (en) * | 2016-01-06 | 2016-06-15 | 广州神马移动信息科技有限公司 | Multidimensional search log anti-cheating method, system and computing equipment |
| CN106603554A (en) * | 2016-12-29 | 2017-04-26 | 北京奇艺世纪科技有限公司 | Adaptive real-time video data anti-cheating method and apparatus |
| CN107343047A (en) * | 2017-07-06 | 2017-11-10 | 北京奇虎科技有限公司 | Application system and method |
| CN108109011A (en) * | 2017-12-28 | 2018-06-01 | 北京皮尔布莱尼软件有限公司 | A kind of anti-cheat method of advertisement and computing device |
| CN109003137A (en) * | 2018-07-23 | 2018-12-14 | 广州至真信息科技有限公司 | A kind of anti-method and device practised fraud of advertisement |
| CN109034906A (en) * | 2018-08-03 | 2018-12-18 | 北京木瓜移动科技股份有限公司 | Anti- cheat method, device, electronic equipment and the storage medium of advertising conversion |
| CN109101532A (en) * | 2018-06-25 | 2018-12-28 | 广州爱九游信息技术有限公司 | Detect cheat method, device and equipment |
| CN109146546A (en) * | 2018-07-23 | 2019-01-04 | 广州至真信息科技有限公司 | A kind of method and device of cheating detection |
| CN110097389A (en) * | 2018-01-31 | 2019-08-06 | 上海甚术网络科技有限公司 | A kind of anti-cheat method of ad traffic |
| CN110490657A (en) * | 2019-08-21 | 2019-11-22 | 江苏文旭信息技术股份有限公司 | A kind of more ad distribution platform cooperative systems calculated based on cloud with inter-library access |
| KR20190132598A (en) * | 2018-05-18 | 2019-11-28 | 주식회사 티앤케이팩토리 | Method and apparatus for detecting fraud click using user agent |
| CN110602184A (en) * | 2019-08-29 | 2019-12-20 | 微梦创科网络科技（中国）有限公司 | Method and device for monitoring and processing cheating behaviors in website |
| CN111435507A (en) * | 2019-01-11 | 2020-07-21 | 腾讯科技（北京）有限公司 | Advertisement anti-cheating method and device, electronic equipment and readable storage medium |
| CN111768251A (en) * | 2020-09-03 | 2020-10-13 | 北京悠易网际科技发展有限公司 | Advertisement putting method and device based on traffic information evaluation and electronic equipment |
| CN112950249A (en) * | 2019-12-16 | 2021-06-11 | 旺脉信息科技(上海)有限公司 | Method and system for processing advertisement flow data, electronic equipment and storage medium |
-
2020
- 2020-11-30 CN CN202011369457.1A patent/CN112488754A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101296360A (en) * | 2007-04-24 | 2008-10-29 | 宋亚民 | Advertisement issuing and charging method and system |
| CN105677869A (en) * | 2016-01-06 | 2016-06-15 | 广州神马移动信息科技有限公司 | Multidimensional search log anti-cheating method, system and computing equipment |
| CN106603554A (en) * | 2016-12-29 | 2017-04-26 | 北京奇艺世纪科技有限公司 | Adaptive real-time video data anti-cheating method and apparatus |
| CN107343047A (en) * | 2017-07-06 | 2017-11-10 | 北京奇虎科技有限公司 | Application system and method |
| CN108109011A (en) * | 2017-12-28 | 2018-06-01 | 北京皮尔布莱尼软件有限公司 | A kind of anti-cheat method of advertisement and computing device |
| CN110097389A (en) * | 2018-01-31 | 2019-08-06 | 上海甚术网络科技有限公司 | A kind of anti-cheat method of ad traffic |
| KR20190132598A (en) * | 2018-05-18 | 2019-11-28 | 주식회사 티앤케이팩토리 | Method and apparatus for detecting fraud click using user agent |
| CN109101532A (en) * | 2018-06-25 | 2018-12-28 | 广州爱九游信息技术有限公司 | Detect cheat method, device and equipment |
| CN109146546A (en) * | 2018-07-23 | 2019-01-04 | 广州至真信息科技有限公司 | A kind of method and device of cheating detection |
| CN109003137A (en) * | 2018-07-23 | 2018-12-14 | 广州至真信息科技有限公司 | A kind of anti-method and device practised fraud of advertisement |
| CN109034906A (en) * | 2018-08-03 | 2018-12-18 | 北京木瓜移动科技股份有限公司 | Anti- cheat method, device, electronic equipment and the storage medium of advertising conversion |
| CN111435507A (en) * | 2019-01-11 | 2020-07-21 | 腾讯科技（北京）有限公司 | Advertisement anti-cheating method and device, electronic equipment and readable storage medium |
| CN110490657A (en) * | 2019-08-21 | 2019-11-22 | 江苏文旭信息技术股份有限公司 | A kind of more ad distribution platform cooperative systems calculated based on cloud with inter-library access |
| CN110602184A (en) * | 2019-08-29 | 2019-12-20 | 微梦创科网络科技（中国）有限公司 | Method and device for monitoring and processing cheating behaviors in website |
| CN112950249A (en) * | 2019-12-16 | 2021-06-11 | 旺脉信息科技(上海)有限公司 | Method and system for processing advertisement flow data, electronic equipment and storage medium |
| CN111768251A (en) * | 2020-09-03 | 2020-10-13 | 北京悠易网际科技发展有限公司 | Advertisement putting method and device based on traffic information evaluation and electronic equipment |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113225325A (en) * | 2021-04-23 | 2021-08-06 | 北京明略昭辉科技有限公司 | IP (Internet protocol) blacklist determining method, device, equipment and storage medium |
| CN113225325B (en) * | 2021-04-23 | 2022-09-13 | 北京明略昭辉科技有限公司 | IP (Internet protocol) blacklist determining method, device, equipment and storage medium |
| CN114119037A (en) * | 2022-01-24 | 2022-03-01 | 深圳尚米网络技术有限公司 | Marketing anti-cheating system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7019744B2 (en) | Methods and equipment for collecting distributed user information for media impressions and search terms | |
| JP6870901B2 (en) | Methods and equipment for determining media impressions using distributed demographic information | |
| US11039178B2 (en) | Monitoring individual viewing of television events using tracking pixels and cookies | |
| CN106062801B (en) | Tracking pixels and COOKIE for television event viewing | |
| JP6062895B2 (en) | Content rendering control system and method | |
| CN106156363B (en) | The method and apparatus for determining media impression | |
| CN108335150B (en) | Apparatus and computer-readable storage medium for monitoring media presentation | |
| US8478862B2 (en) | Method and apparatus for internet traffic monitoring by third parties using monitoring implements | |
| US20150382075A1 (en) | Monitoring individual viewing of television events using tracking pixels and cookies | |
| US20030177488A1 (en) | Systems and methods for media audience measurement | |
| US20090083417A1 (en) | Method and apparatus for tracing users of online video web sites | |
| US20070208828A1 (en) | Systems and methods for data mining and interactive presentation of same | |
| CN104050178A (en) | Internet monitoring anti-spamming method and device | |
| KR20080109735A (en) | Systems and methods for data mining and interactive presentation of same | |
| US8838522B1 (en) | Identifying user segment assignments | |
| CN112488754A (en) | Anti-cheating system and method for advertisement clicking | |
| CN103268562B (en) | The monitoring method of a kind of Internet advertising audience demographics's attribute and system | |
| CN111859234A (en) | Illegal content identification method and device, electronic equipment and storage medium | |
| JP2018163663A (en) | Using messaging associated with adaptive bitrate streaming to perform media monitoring for mobile platforms | |
| KR20190083899A (en) | System and method for detecting block | |
| US20170345052A1 (en) | Method and system for identifying anomalous content requests | |
| US20180337844A1 (en) | Relaying internet census information | |
| CN113923190B (en) | Equipment identification jump identification method and device, server and storage medium | |
| CN112734502B (en) | Testing method and device for multimedia information directional delivery and electronic equipment | |
| CN112135199B (en) | Video playing method based on multiple types of video sources and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 313-319, 3rd floor, building 3, room 418-420, 4th floor, 283 Jianguo West Road, Xuhui District, Shanghai 200031 Applicant after: Shanghai kuliang Technology Co.,Ltd. Address before: Room 313-319, 3rd floor, building 3, room 418-420, 4th floor, 283 Jianguo West Road, Xuhui District, Shanghai 200031 Applicant before: Shanghai kuliang Information Technology Co., Ltd |