CN105760455B - Anti-cheating method and device for advertisement clicking - Google Patents
Anti-cheating method and device for advertisement clicking Download PDFInfo
- Publication number
- CN105760455B CN105760455B CN201610079777.0A CN201610079777A CN105760455B CN 105760455 B CN105760455 B CN 105760455B CN 201610079777 A CN201610079777 A CN 201610079777A CN 105760455 B CN105760455 B CN 105760455B
- Authority
- CN
- China
- Prior art keywords
- user
- advertisement
- cheating
- click
- undetermined
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses an anti-cheating method and device for advertisement clicking, wherein the anti-cheating method comprises the following steps: selecting pending users from advertisement clicking users; acquiring an advertisement click record of a pending user in a first time period; selecting at least one advertisement from the advertisement click records, and sending the at least one advertisement to the pending user again; and under the condition that the number of times that the undetermined user clicks at least one advertisement which is sent again in a second time period after the first time period is larger than a first threshold value, the undetermined user is determined as a cheating user. According to the method and the device, the undetermined user can be judged whether to be a cheating user or not by sending one or more advertisements in the advertisement click record to the undetermined user again and accumulating the times of clicking the sent advertisements by the undetermined user again, so that the cheating user can be distinguished more accurately, and the false alarm rate of an anti-cheating system for advertisement click is reduced.
Description
Technical Field
The invention relates to the field of network advertisements, in particular to an anti-cheating method and device for advertisement clicking.
Background
Currently, with the development of networks and the widespread use of computers, the online advertising market is rapidly expanding. Advertisers who pay for placement of advertisements may pay publishers (advertising platforms) to place their advertisements through web pages, search engines, browsers, or other online media to promote 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 non-clicks. 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. In the prior art, various advertisement anti-cheating systems are provided to judge whether a user cheats, however, how to confirm that the false alarm rate and the missing report rate of the advertisement anti-cheating system are main pain points of all the anti-cheating systems, if the false alarm rate of the advertisement anti-cheating system is too high, a large number of actions of normal users for clicking advertisements can be mistakenly identified as cheating clicks, namely normal users are mistakenly identified as cheating users.
Disclosure of Invention
Technical problem
In view of the above, the technical problem to be solved by the present invention is to provide an advertisement clicking anti-cheating method and apparatus capable of reducing the false alarm rate of an anti-cheating system.
Solution scheme
In order to solve the above technical problem, in a first aspect, the present invention provides an anti-cheating method for advertisement clicking, including:
acquiring an advertisement click record of the undetermined user in a first time period;
selecting at least one advertisement from the advertisement click records, and sending the at least one advertisement to the pending user again; and
and when the number of times that the undetermined user clicks at least one advertisement which is sent again in a second time period is larger than a first threshold value, determining the undetermined user as a cheating user, wherein the second time period is after the first time period.
With reference to the first aspect, in a first possible implementation manner, the method further includes:
when the number of times that the pending user clicks at least one advertisement which is sent again in the second time period is smaller than or equal to the first threshold value, accumulating the verification number of times of the pending user; and
and when the verification times are larger than a second threshold value, verifying whether the undetermined user is a cheating user or not according to the advertisement click record of the undetermined user.
With reference to the first possible implementation manner of the first aspect, in a second possible implementation manner, the method further includes:
and when the verification times are less than or equal to the second threshold value, returning to execute the selection of at least one advertisement from the advertisement click record, and sending the at least one advertisement to the pending user again.
With reference to the first aspect, the first possible implementation manner of the first aspect, or the second possible implementation manner of the first aspect, in a third possible implementation manner, before a pending user is selected from advertisement click users, the anti-cheating method further includes:
judging whether each user is the pending user or not according to the advertisement click record of each user,
the advertisement click record comprises at least one of the click rate of each user to the advertisement, the time difference of each user clicking the same advertisement, the aggregation of the IP address distribution of each user, the aggregation of the number of the terminal equipment used by each user and the aggregation of the traffic owner of the advertisement clicked by each user.
In a second aspect, the present invention provides an anti-cheating device for advertisement clicking, comprising:
the selecting unit is used for selecting the pending user from the advertisement clicking users;
the acquisition unit is connected with the selection unit and used for acquiring the advertisement click record of the undetermined user in a first time period;
the sending unit is connected with the acquisition unit and used for selecting at least one advertisement from the advertisement click record and sending the at least one advertisement to the pending user again; and
and the verification unit is connected with the sending unit and used for judging the undetermined user as a cheating user under the condition that the frequency of clicking at least one advertisement which is sent again by the undetermined user in a second time period is greater than a first threshold value, wherein the second time period is after the first time period.
With reference to the second aspect, in a first possible implementation manner, the method further includes:
the accumulation unit is connected with the sending unit and used for accumulating the verification times of the user to be determined under the condition that the number of times that the user to be determined clicks at least one advertisement which is sent again in the second time period is smaller than or equal to the first threshold value; and
and the judging unit is connected with the accumulating unit and used for judging whether the undetermined user is a cheating user or not according to the advertisement click record of the undetermined user under the condition that the verification times is greater than a second threshold value.
With reference to the first possible implementation manner of the second aspect, in a second possible implementation manner, the method further includes:
and the returning unit is connected with the accumulating unit and the sending unit and used for returning and executing the selection of at least one advertisement from the advertisement click record and sending the at least one advertisement to the pending user again under the condition that the verification times is less than or equal to the second threshold value.
With reference to the second aspect, or the first possible implementation manner of the second aspect, or the second possible implementation manner of the second aspect, in a third possible implementation manner, the method further includes:
a judging unit connected with the selecting unit and used for judging whether each user is the undetermined user or not according to the advertisement click record of each user before the undetermined user is selected from the advertisement click users,
the advertisement click record comprises at least one of the click rate of each user to the advertisement, the time difference of each user clicking the same advertisement, the aggregation of the IP address distribution of each user, the aggregation of the number of the terminal equipment used by each user and the aggregation of the traffic owner of the advertisement clicked by each user.
Advantageous effects
According to the anti-cheating method and device for advertisement clicking provided by the embodiment of the invention, for the undetermined user, one or more advertisements in the advertisement clicking record of the undetermined user can be sent to the undetermined user again, and the times of the undetermined user clicking the sent advertisements again are accumulated, so that whether the undetermined user is a cheating user or not is judged, therefore, the cheating user can be distinguished more accurately, and the false alarm rate of an anti-cheating system for advertisement clicking is reduced.
Other features and aspects of the present invention will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features, and aspects of the invention and, together with the description, serve to explain the principles of the invention.
FIG. 1a illustrates an architecture 10 of a pay-per-click advertising system;
FIG. 1b illustrates another architecture 20 of a pay-per-click advertising system;
FIG. 1c illustrates a flow diagram of an alternative anti-cheating method of advertisement clicking according to an embodiment of the present invention;
FIG. 2a illustrates an application scenario of the anti-cheating method for advertisement clicking of the present invention;
FIG. 2b illustrates a flow diagram of an alternative anti-cheating method of advertisement clicking according to an embodiment of the present invention;
FIG. 3a is a block diagram of an alternative anti-cheating device for advertisement clicking according to an embodiment of the present invention;
FIG. 3b is a block diagram illustrating an alternative anti-cheating device on advertisement clicking according to an embodiment of the present invention; and
fig. 4 is a schematic system architecture diagram of an anti-cheating system for determining whether a user cheats by using an advertisement clicking anti-cheating device according to an embodiment of the present invention.
Detailed Description
Various exemplary embodiments, features and aspects of the present invention will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present invention. It will be understood by those skilled in the art that the present invention may be practiced without some of these specific details. In some instances, methods, procedures, components, and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present invention.
FIG. 1a shows an architecture 10 of a pay-per-click advertising system, and FIG. 1b shows another architecture 20 of a pay-per-click advertising system.
As shown in FIG. 1a, architecture 10 may generally include: a publisher 11, an advertiser 12, and a user client 13. Wherein advertisers 12 may place advertisements through publishers 11 (e.g., QQ space, WeChat), and users may access publishers 11 through user clients 13.
Specifically, the user may access the advertisement content provided by the publisher 11 through a user client 13, such as a Mobile phone, a Mobile Internet Device (MID), a Personal Digital Assistant (PDA), a notebook, a desktop computer, a smart tv, and the like. For example, a user may access advertisement content provided by the publisher 11 in a click-through manner through the user client 13.
The publisher 11 may nest (host) the advertisement content provided by the advertiser 12 on, for example, a web page, and may display the queried advertisement content to the user in response to an operation in which the user queries the advertisement content provided by the advertiser 12 through the user client 13. If the user clicks on the advertising content, advertiser 12 may be charged a fee (i.e., the advertisement is a pay-per-click advertisement). In addition, the publisher 11 creates an index to record the advertisement clicked by each user within a certain time period, i.e., an advertisement click record.
Of course, the architecture of the pay-per-click advertising system may also be as shown in FIG. 1b as architecture 20. As shown in FIG. 1b, another architecture 20 for a pay-per-click advertising system may include: a publisher 21, an advertising platform 22, an advertiser 23, and a user client 24.
Wherein the advertising platform 22 is a platform or intermediary that connects the publisher 21 and the advertiser 23. The ad platform 22 may contact the publisher 21 and the advertiser 23 to send the advertiser 23's ad to the publisher 21; the publisher 21 may then place the transmitted advertisement; the user may access the ad placed by publisher 21 through user client 24, and if the user clicks on the ad placed by publisher 21, publisher 21 and advertising platform 22 may charge advertiser 23 and share the charge.
FIG. 1c is a flowchart illustrating an alternative anti-cheating method of advertisement clicking according to an embodiment of the present invention. As shown in fig. 1c, the anti-cheating method may mainly include:
step S100, selecting users to be cheated (examples of the users to be cheated) from the advertisement clicking users.
And step S120, obtaining the advertisement click record of the user to be cheated in the first time period.
As described above, the publisher 11 or the publisher 21 may establish an index to record the advertisement click record of each user, wherein each user may include, for example, a normal user, a cheating user, and a user to be cheated, and thus, after selecting a user to be cheated from the advertisement click users, the recorded advertisement click record of the user to be cheated may be obtained from the publisher 11 or the publisher 21. Wherein the advertisement click record may include that the user pending cheating was within a first time period, such as 12 months, 10 days, 8 of 2015: 12 month 12 day 7 from 00 to 2015: 00 the advertisement clicked on in this time period.
In a possible implementation manner, before step S100, the anti-cheating method may further include a process of pre-determining the user to be cheated: for example, whether each user is a user to be cheated is judged according to the advertisement click record of each user. The advertisement click record may include at least one of a click rate of each user for an advertisement (e.g., pay-per-click advertisement), a time difference between clicks of the same pay-per-click advertisement by each user, an aggregation of IP address distributions of each user, an aggregation of terminal device numbers used by each user, and an aggregation of traffic owners of pay-per-click advertisements clicked by each user. The advertisement click record of the embodiment may further include other data, and the data included in the advertisement click record may be flexibly selected according to the actual application scenario and requirements.
Specifically, the click rate may refer to a total number of times that the pay-per-click advertisement is clicked, and if the click rate of a certain user on the pay-per-click advertisement is greater than a predetermined threshold, the user may be determined as the user to be cheated. For example, assuming that the predetermined threshold is 5 and the paid click advertisement a is repeatedly clicked 8 times by a certain user, the click amount of the certain user on the paid click advertisement a is 8, and since the click amount is greater than the predetermined threshold 5, the user may be determined as a user to be cheated.
Specifically, the click rate may refer to a ratio of a click rate to an advertisement display amount, where the advertisement display amount may refer to a total number of displayed advertisements, and of course, the advertisement display amount may include repeated display. If the click rate of a certain user for clicking the paid advertisement is greater than a preset threshold value, the user can be judged as a user to be cheated. For example, assuming that the predetermined threshold is 1/3, ad A was presented 8 times, ad B was presented 2 times, and ad C was presented 1 time, and ad A was repeatedly clicked 8 times by a user, the click rate is 8/11. Since the click rate is greater than the predetermined threshold 1/3, the user may be determined to be a pending cheating user.
Specifically, if the time difference between the time when a certain user clicks the same pay-per-click advertisement is smaller than a predetermined threshold, the user may be determined as a user to be cheated. For example, assuming that the predetermined threshold is 2 minutes and a user clicks on pay-per-click advertisement a at 8 hours 45 minutes 30 seconds, 8 hours 45 minutes 50 seconds, 8 hours 46 minutes 01 seconds, and 8 hours 47 minutes 01 seconds of 12 days of 12 months in 2015, the time difference between the user clicking on pay-per-click advertisement a is 20 seconds, 11 seconds, and 1 minute, respectively. These three time differences are all less than the predetermined threshold for 2 minutes, so the user can be judged as a user to be cheated.
Specifically, if the aggregation degree of the IP address distribution of a certain user is greater than a predetermined threshold, the user may be determined as a user to be cheated. If the aggregation degree of the terminal equipment numbers used by a certain user is larger than a preset threshold value, the user can be judged as a user to be cheated. If the click rate of a certain user on a certain click-to-pay advertisement and the click rate of the user on the click-to-pay advertisement are larger than a certain threshold value, and the aggregation of the traffic owners of the click-to-pay advertisement clicked by the user is larger than a preset threshold value, the user can be judged as a user to be cheated.
Of course, the condition for determining whether the user is the user to be cheated may be appropriately relaxed, for example, the predetermined threshold of the click rate or the click rate may be appropriately reduced, or the predetermined threshold of the time difference may be appropriately increased, or the predetermined threshold of the IP address distribution, the number of the terminal device used by the user, or the aggregation of the traffic owners of the pay-per-click advertisements clicked by the user may be appropriately reduced, so that the omission of cheating users may be appropriately avoided, and the false dismissal rate of the anti-cheating system may be reduced.
It should be noted that, for the above-identified normal user, a normal pay-per-click advertisement may be sent to the normal user according to the user information of the normal user, such as the user' S gender, age, interest, etc., and for the above-identified pending cheating user, the operations in steps S100, S120, S140, S160, and S180 may be performed.
Step S140, selecting at least one advertisement from the advertisement click records, and sending the at least one advertisement to the user to be cheated again.
After the advertisement click record of the user to be cheated is acquired, one or more advertisements can be randomly extracted from the advertisement click record of the user to be cheated, and the extracted advertisements are sent to the user to be cheated again.
Step S160, judging whether the number of times that the user to be cheated clicks at least one advertisement which is sent again in a second time period is larger than a first threshold value, wherein the second time period is after the first time period. For example, the start time of the second time period is after the end time of the first time period, i.e., the second time period is a time period counted from the time when the at least one advertisement is transmitted again in step S160. In case that the number of times that the user to cheat on the schedule clicks the at least one advertisement to be sent again within the second time period is greater than the first threshold, step S180 may be performed.
And step S180, judging the user to be cheated as the cheating user.
Specifically, there may theoretically be a case where a normal user repeatedly clicks on a pay-per-click advertisement due to a particular interest in the pay-per-click advertisement. However, the number of such normal users is relatively small, and a normal user will typically only occasionally repeat clicking on a small number of pay-per-click ads of particular interest, and will not frequently repeat clicking on the same pay-per-click ads.
Based on this, if the user to cheat is waiting for a predetermined period of time, e.g., 2015, 12 month, 12 day 8: 12 month 12, 00 to 2015 14: 00, the number of times of clicking on the sent advertisement in the time period is greater than the first threshold, for example, 5 times, for example, the number of times of clicking on the sent advertisement a by the user to be cheated in the time period is 2 times, the number of times of clicking on the sent advertisement B is 2 times, the number of times of clicking on the sent advertisements C and D is 1 time, and the number of times of clicking on the sent advertisement E is 3 times, and for example, the number of times of clicking on the sent advertisement a by the user to be cheated in the time period is 3 times, and the number of times of clicking on the sent advertisement B is 4 times, the user to be cheated can be determined as the cheating user. The publisher 11 does not charge the advertiser 12 or the publisher 21 and the advertising platform 22 do not charge the advertiser 23 for the click behavior of the user to be cheated who is determined to be a cheating user.
The specific value of the first threshold may be obtained by performing training analysis on advertisement click records of each user recorded by the publisher 11 or 21, and may also be a preset empirical value, it should be noted that the specific value of the first threshold in the present application is not limited to the illustrated example, and a person skilled in the art may select the specific value of the first threshold according to an actual application scenario and an application requirement.
According to the anti-cheating method for advertisement clicking, disclosed by the embodiment of the invention, for the user to be cheated, one or more advertisements in the advertisement clicking record can be sent to the user to be cheated again, and the times of clicking the sent advertisements again by the user to be cheated are accumulated, so that whether the user to be cheated is the cheating user or not is judged, therefore, the cheating user can be more accurately distinguished, and the false alarm rate of an anti-cheating system for advertisement clicking is reduced. In addition, the number of the users to be cheated is usually small in proportion to all the users, for example, less than 5% of all the users, so that the technical scheme of the application has a small negative effect on the advertisement experience of normal users.
Fig. 2a shows an application scenario of the anti-cheating method for advertisement clicking of the present invention, that is, the anti-cheating method is applied to the WeChat advertisement anti-cheating system. The 'mr. week' as an advertiser can place the advertisement shown in fig. 2a through a certain public number as a WeChat of a publisher, the WeChat advertisement anti-cheating system can judge which one of a normal user (i.e., a non-cheating user), an undetermined cheating user (i.e., an undetermined user) and a cheating user the user clicking the advertisement shown in fig. 2a is, and if the user is the cheating user, the public number does not charge the advertisement fee to the 'mr. week'; if the user is a non-cheating user, the public number charges the 'Mr. Weeker' for an advertisement; if the user is the user to be cheated, the following anti-cheating method shown in fig. 2b may be performed to further determine whether the user to be cheated is a cheating user or a non-cheating user.
As an optional example, an optional anti-cheating method for advertisement clicking of the embodiment of the present invention may include: step S100, step S120, step S140, and step S180, that is, include: s100, selecting pending users from advertisement clicking users; step S120, obtaining an advertisement click record of the undetermined user in a first time period; step S140, selecting at least one advertisement from the advertisement click records, and sending the at least one advertisement to the pending user again; and step S180, when the number of times that the undetermined user clicks at least one advertisement which is sent again in a second time period is larger than a first threshold value, the undetermined user is judged as a cheating user, and the second time period is after the first time period.
FIG. 2b is a flowchart illustrating an alternative anti-cheating method of advertisement clicking according to an embodiment of the present invention. As shown in fig. 2b, the anti-cheating method may mainly include:
in step S101, the user triggers an action of pulling an advertisement when browsing a web page, and then step S102 is performed.
In step S102, for example, it may be determined whether the user is a user to be cheated based on the advertisement click record of the user acquired from the publisher 11 or 21, and if the user is a normal user, step S106 is executed, and if the user is a user to be cheated, step S103 is executed.
In step S103, the pay-per-click advertisement clicked by the user for the last time, such as the last week or month, is randomly issued again to the user, and then step S104 is performed.
In step S104, it is determined whether the user repeatedly clicks the transmitted advertisement, and if the user still clicks the transmitted advertisement, step S105 is performed.
In step S105, the behavior of the user repeatedly clicking on the transmitted advertisement is recorded, and then step S107 is performed.
In step S106, the advertisement engine issues a normal advertisement to the user according to the user profile (user information) of the user such as gender, age, interest, etc.
In step S107, it is determined whether the pending cheating user frequently clicks the transmitted advertisement (old advertisement clicked in history), that is, whether the number of times the pending cheating user repeatedly clicks the transmitted advertisement within a certain time period after the last period of time exceeds a certain threshold, if yes, step S108 is executed, otherwise, step S109 is executed.
There may theoretically be a case where a normal user is particularly interested in a certain advertisement and repeatedly clicks on the same advertisement, but the number of such users is relatively small, and a normal user generally repeatedly clicks on a small number of particularly interested advertisements occasionally without frequently repeatedly clicking on the same advertisement.
In step S108, the user to be cheated is determined as the cheating user, so that the cheating user can be attacked in the anti-cheating system with a high certainty.
In step S109, it is repeatedly tried to determine whether the user to be cheated repeatedly clicks the transmitted advertisement, if the user to be cheated does not repeatedly click the transmitted advertisement after repeated trials, the determined non-cheating user can be treated as a false report in combination with the advertisement click record (historical advertisement behavior) of the user to be cheated, and the user is whitewashed out from the anti-cheating system, if the user to be cheated is still the user to be cheated, the advertisement in the advertisement click record of the user to be cheated is continuously issued for continuous investigation until the user to be cheated is determined to be the cheating user or the non-cheating user.
According to the anti-cheating method for advertisement clicking, disclosed by the embodiment of the invention, for the user to be cheated, one or more advertisements in the advertisement clicking record can be sent to the user to be cheated again, and the times of clicking the sent advertisements again by the user to be cheated are accumulated, so that whether the user to be cheated is the cheating user or not is judged, therefore, the cheating user can be more accurately distinguished, and the false alarm rate of an anti-cheating system for advertisement clicking is reduced. In addition, for the user to be cheated who cannot be judged as the cheating user, the verification times of the user to be cheated are accumulated and the advertisement click record of the user to be cheated is combined, so that whether the user to be cheated is a non-cheating user is judged. In addition, the number of the users to be cheated is usually small in proportion to all the users, for example, less than 5% of all the users, so that the technical scheme of the application has a small negative effect on the advertisement experience of normal users.
Fig. 3a is a block diagram illustrating an alternative anti-cheating device for advertisement clicking according to an embodiment of the present invention. The anti-cheating device 300 for advertisement clicking provided in this embodiment is used for implementing the anti-cheating method for advertisement clicking shown in fig. 1 c. As shown in fig. 3a, the anti-cheating device 300 may mainly include:
a selecting unit 301, configured to select a user to be cheated (an example of the user to be cheated) from the advertisement click users.
The obtaining unit 310 is connected to the selecting unit 301, and is configured to obtain an advertisement click record of the user to be cheated in the first time period.
As described above, the publisher 11 or the publisher 21 may establish an index to record the advertisement click record of each user, wherein each user may include, for example, a normal user, a cheating user, and a user to be cheated, and therefore, after the selecting unit 301 selects a user to be cheated from the advertisement click users, the obtaining unit 310 may obtain the recorded advertisement click record of the user to be cheated from the publisher 11 or the publisher 21. Wherein the advertisement click record may include that the user pending cheating was within a first time period, such as 12 months, 10 days, 8 of 2015: 12 month 12 day 7 from 00 to 2015: 00 the advertisement clicked on in this time period.
In a possible implementation manner, the anti-cheating device 300 may also determine a user to be cheated in advance, in other words, as shown in fig. 3b, the anti-cheating device 300 may further include: and the determining unit 370 is connected to the selecting unit 301, and is configured to determine whether each user is an undetermined cheating user according to the advertisement click record of each user before the selecting unit 301 selects an undetermined user from the advertisement click users. The advertisement click record may include at least one of a click rate of each user for an advertisement (e.g., pay-per-click advertisement), a time difference between clicks of the same pay-per-click advertisement by each user, an aggregation of IP address distributions of each user, an aggregation of terminal device numbers used by each user, and an aggregation of traffic owners of pay-per-click advertisements clicked by each user. The advertisement click record of the embodiment may further include other data, and the data included in the advertisement click record may be flexibly selected according to the actual application scenario and requirements.
Specifically, the click rate may refer to a total number of times that the pay-per-click advertisement is clicked, and if the click rate of a certain user on the pay-per-click advertisement is greater than a predetermined threshold, the determining unit 370 may determine that the user is a user to be cheated. For example, assuming that the predetermined threshold is 5 and the paid click advertisement a is repeatedly clicked 8 times by a certain user, the click amount of the certain user on the paid click advertisement a is 8, and since the click amount is greater than the predetermined threshold 5, the determining unit 370 may determine that the user is a user to be cheated.
Specifically, the click rate may refer to a ratio of a click rate to an advertisement display amount, where the advertisement display amount may refer to a total number of displayed advertisements, and of course, the advertisement display amount may include repeated display. If the click rate of a user for clicking on a paid advertisement is greater than a predetermined threshold, determining unit 370 may determine the user as a user to be cheated. For example, assuming that the predetermined threshold is 1/3, ad A was presented 8 times, ad B was presented 2 times, and ad C was presented 1 time, and ad A was repeatedly clicked 8 times by a user, the click rate is 8/11. Since the click rate is greater than predetermined threshold 1/3, determination unit 370 may determine the user as a user to be cheated.
Specifically, if the time difference between the time when a certain user clicks the same pay-per-click advertisement is smaller than a predetermined threshold, the determination unit 370 may determine that the user is a user to be cheated. For example, assuming that the predetermined threshold is 2 minutes and a user clicks on pay-per-click advertisement a at 8 hours 45 minutes 30 seconds, 8 hours 45 minutes 50 seconds, 8 hours 46 minutes 01 seconds, and 8 hours 47 minutes 01 seconds of 12 days of 12 months in 2015, the time difference between the user clicking on pay-per-click advertisement a is 20 seconds, 11 seconds, and 1 minute, respectively. These three time differences are all smaller than the predetermined threshold value of 2 minutes, so the determination unit 370 may determine that the user is a user to be cheated.
Specifically, if the aggregation degree of the IP address distribution of a certain user is greater than a predetermined threshold, the determination unit 370 may determine that the user is a user to be cheated. If the aggregation degree of the terminal device numbers used by a certain user is greater than a predetermined threshold, the determination unit 370 may determine that the user is a user to be cheated. If the amount of clicks on a pay-per-click advertisement by a user and the rate of clicks on the pay-per-click advertisement by the user are greater than a certain threshold and the aggregation of traffic owners of the pay-per-click advertisement clicked by the user is greater than a predetermined threshold, the determination unit 370 may determine that the user is a user to be cheated.
Of course, the determining unit 370 may appropriately relax the above-mentioned condition for determining whether the user is the user to be cheated, for example, the determining unit 370 may appropriately decrease the predetermined threshold of the click rate or the click rate, or, for example, the determining unit 370 may appropriately increase the predetermined threshold of the time difference, or, for example, the determining unit 370 may appropriately decrease the predetermined threshold of the IP address distribution, the number of the terminal device used by the user, or the aggregation of the traffic owners of the pay-per-click advertisements clicked by the user, so that the cheating users may be appropriately prevented from being missed, and the false dismissal rate of the anti-cheating system may be reduced.
It should be noted that the normal user determined by the determining unit 370 may send a normal pay-per-click advertisement to the normal user according to the user information of the normal user, such as the user's gender, age, interest, etc., and the pending cheating user determined by the determining unit 370 may perform corresponding operations through the selecting unit 301, the obtaining unit 310, the sending unit 330, and the verifying unit 350.
A sending unit 330, connected to the obtaining unit 310, configured to select at least one advertisement from the advertisement click record, and send the at least one advertisement to the user to be cheated again.
After the obtaining unit 310 obtains the advertisement click record of the pending cheating user, the sending unit 330 may randomly extract one or more advertisements from the advertisement click record of the pending cheating user and send the extracted advertisements to the pending cheating user again.
The verification unit 350 is connected to the sending unit 330, and is configured to determine the user to be cheated as the cheating user if the number of times that the user to be cheated clicks the at least one advertisement that is sent again within the second time period is greater than the first threshold. Wherein the second time period is after the first time period, for example, the start time of the second time period is after the end time of the first time period, that is, the second time period is a time period counted from the sending unit 330 after sending the at least one advertisement again.
Specifically, there may theoretically be a case where a normal user repeatedly clicks on a pay-per-click advertisement due to a particular interest in the pay-per-click advertisement. However, the number of such normal users is relatively small, and a normal user will typically only occasionally repeat clicking on a small number of pay-per-click ads of particular interest, and will not frequently repeat clicking on the same pay-per-click ads.
Based on this, if the user to cheat is waiting for a predetermined period of time, e.g., 2015, 12 month, 12 day 8: 12 month 12, 00 to 2015 14: 00, the number of times of clicking on the sent advertisement is greater than the first threshold, for example, 5 times, for example, the number of times of clicking on the sent advertisement a by the user to be cheated is 2 times, the number of times of clicking on the sent advertisement B is 2 times, the number of times of clicking on the sent advertisements C and D is 1 time, and the number of times of clicking on the sent advertisement E is 3 times, and if the number of times of clicking on the sent advertisement a by the user to be cheated is 3 times, and the number of times of clicking on the sent advertisement B by the user to be cheated is 4 times, the verification unit 350 may determine the user to be cheated as the cheating user. The publisher 11 does not charge the advertiser 12 or the publisher 21 and the advertising platform 22 do not charge the advertiser 23 for the click behavior of the user to be cheated who is determined to be a cheating user.
The specific value of the first threshold may be obtained by performing training analysis on the advertisement click records of each user recorded by the publisher 11 or 21. Of course, the value may be a predetermined empirical value. It should be noted that the specific value of the first threshold in the present application is not limited to the illustrated example, and those skilled in the art can select the specific value of the first threshold according to the actual application scenario and the application requirement.
The anti-cheating device for advertisement clicking of the embodiment of the invention can send one or more advertisements in the advertisement clicking record to the user to be cheated again and accumulate the times of clicking the sent advertisements again by the user to be cheated, thereby judging whether the user to be cheated is a cheating user. Therefore, the cheating users can be distinguished more accurately, and the false alarm rate of the anti-cheating system for clicking the advertisement is reduced. In addition, the number of the users to be cheated is usually small in proportion to all the users, for example, less than 5% of all the users, so that the technical scheme of the application has a small negative effect on the advertisement experience of normal users.
Fig. 4 is a schematic diagram illustrating a system architecture of an anti-cheating system 400 for determining whether a user cheats by using an advertisement clicking anti-cheating device according to an embodiment of the present invention.
As shown in fig. 4, the anti-cheating system 400 may generally include: a suspected malicious user caching module 32, an anti-cheating module 33, a deduction module 36 and an advertisement engine 37, wherein the advertisement engine 37 comprises a normal user advertisement library 35 and a historical online advertisement library 34 clicked by suspected malicious users.
The data of the suspected malicious user cache module 32 is synchronized by the anti-cheating module 33, and the anti-cheating module 33 can determine whether the user 31 cheats according to various behavior characteristics of the user 31 in fig. 4, such as pulling and exposure of the user 31, click rate of the user 31 on an advertisement (e.g., pay-per-click advertisement), click rate of the user 31 on the pay-per-click advertisement, time difference of the user 31 clicking the same pay-per-click advertisement, aggregation of IP address distribution of the user 31, aggregation of device numbers used by the user 31, whether the pay-per-click advertisement clicked by the user 31 is repeated, aggregation of traffic owners of the pay-per-click advertisement clicked by the user 31 (aggregation of traffic owners), and the like. The anti-cheating module 33 determines whether the user 31 cheats by the method of the above embodiment.
It should be noted that if the false dismissal rate of the anti-cheating module 33 is to be reduced, the anti-cheating module 33 only needs to be appropriately relaxed to determine whether the user 31 is a limitation condition of the user to be cheated, so as to increase the number of users to be cheated, i.e., to consider more users to be cheated (suspected malicious users), thereby automatically increasing the recall rate.
If the anti-cheating module 33 confirms that the user 31 is a cheating user, the anti-cheating system 400 can directly attack the cheating user. That is, the anti-cheating module 33 may perform step S108 in the above-described embodiment. If the anti-cheating module 33 confirms that the user 31 is an undetermined cheating user, the user can be synchronized into the suspected malicious user cache module 32 to investigate the undetermined cheating user, and if the user is confirmed to be a non-cheating user after multiple examinations, namely, the user is confirmed to be a false alarm, the anti-cheating module 33 can wash the user to be cheated. And if the user to be cheated is confirmed to be still the user to be cheated after the plurality of examinations, continuing to examine the user to be cheated until the user to be cheated is determined to be the cheating user or the non-cheating user. That is, the suspected malicious user caching module 32 may perform step S109 in the above embodiment.
The advertisement engine 37 issues an appropriate advertisement to the user 31 based on the user profile (user information) such as the age, sex, and interest of the user 31. If the user 31 is a normal user, i.e. a normal user, to pull the advertisement, the advertisement engine 37 will obtain the appropriate advertisement from the normal user advertisement library 35 and issue it to the normal user. If the user 31 is a user to be cheated, the advertisement engine 37 randomly obtains the historical advertisement clicked by the user to be cheated in the latest period of time, such as a week or a month, from the historical online advertisement library 34 clicked by the suspected malicious user, and sends the historical advertisement to the user to be cheated. It will be apparent that the advertisement engine 37 will build an index to record advertisements that the user 31 has clicked on over time. In addition, generally, the number of the users to be cheated is not less than 5% of the total number of the users, so that the technical scheme of the application has little negative influence on the advertisement experience of normal users.
When the user 31 clicks the advertisement, the click data is reported to the fee deduction module 36, and the fee deduction module 36 will go to the anti-cheating module 33 to inquire whether the user 31 or the click of the user 31 is cheated. If the user 31 or the click of the user 31 is non-cheating (i.e., the anti-cheating module 33 confirms that the user 31 is a non-cheating user), the fee deduction module 36 deducts the advertising fee. If the user 31 or the click-to-cheat of the user 31 (i.e., the anti-cheating module 33 confirms that the user 31 is a cheating user), the fee deduction module 36 does not deduct the advertising fee. The deduction module 36 will also report the click data to the advertisement engine 37 to facilitate the advertisement engine 37 to record and store the relevant information.
The anti-cheating device for advertisement clicking can judge whether the user cheats, and can further judge whether the user to be cheated is a cheating user or a non-cheating user for the user to be cheated. Therefore, the cheating users can be distinguished more accurately, and the false alarm rate of the anti-cheating system for clicking the advertisement is reduced. In addition, the number of the users to be cheated is usually small in proportion to all the users, for example, less than 5% of all the users, so that the technical scheme of the application has a small negative effect on the advertisement experience of normal users.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (8)
1. An anti-cheating method for advertisement clicking is characterized by comprising the following steps:
selecting pending users from advertisement clicking users;
acquiring an advertisement click record of the undetermined user in a first time period;
selecting at least one advertisement from the advertisement click records, and sending the at least one advertisement to the pending user again; and
and when the number of times that the undetermined user clicks at least one advertisement which is sent again in a second time period is larger than a first threshold value, determining the undetermined user as a cheating user, wherein the second time period is after the first time period.
2. The anti-cheating method of claim 1, further comprising: when the number of times that the pending user clicks at least one advertisement which is sent again in the second time period is smaller than or equal to the first threshold value, accumulating the number of times of verification of the pending user, wherein the number of times of verification is used for representing the number of times that the pending user clicks the sent advertisement again; and
and when the verification times are larger than a second threshold value, verifying whether the undetermined user is a cheating user or not according to the advertisement click record of the undetermined user.
3. The anti-cheating method of claim 2, further comprising:
and when the verification times are less than or equal to the second threshold value, returning to execute the selection of at least one advertisement from the advertisement click record, and sending the at least one advertisement to the pending user again.
4. The anti-cheating method of any of claims 1-3, wherein prior to selecting a pending user from among advertisement click users, the anti-cheating method further comprises:
judging whether each user is the pending user or not according to the advertisement click record of each user,
the advertisement click record comprises at least one of the click rate of each user to the advertisement, the time difference of each user clicking the same advertisement, the aggregation of the IP address distribution of each user, the aggregation of the number of the terminal equipment used by each user and the aggregation of the traffic owner of the advertisement clicked by each user.
5. An anti-cheating device of advertisement clicking, comprising:
the selecting unit is used for selecting the pending user from the advertisement clicking users;
the acquisition unit is connected with the selection unit and used for acquiring the advertisement click record of the undetermined user in a first time period;
the sending unit is connected with the acquisition unit and used for selecting at least one advertisement from the advertisement click record and sending the at least one advertisement to the pending user again; and
and the verification unit is connected with the sending unit and used for judging the undetermined user as a cheating user under the condition that the frequency of clicking at least one advertisement which is sent again by the undetermined user in a second time period is greater than a first threshold value, wherein the second time period is after the first time period.
6. The anti-cheating device of claim 5, further comprising:
the accumulation unit is connected with the sending unit and used for accumulating the verification times of the undetermined user under the condition that the number of times that the undetermined user clicks at least one advertisement which is sent again in the second time period is smaller than or equal to the first threshold, wherein the verification times are used for representing the number of times that the undetermined user clicks the sent advertisement again; and
and the judging unit is connected with the accumulating unit and used for judging whether the undetermined user is a cheating user or not according to the advertisement click record of the undetermined user under the condition that the verification times is greater than a second threshold value.
7. The anti-cheating device of claim 6, further comprising:
and the returning unit is connected with the accumulating unit and the sending unit and used for returning and executing the selection of at least one advertisement from the advertisement click record and sending the at least one advertisement to the pending user again under the condition that the verification times is less than or equal to the second threshold value.
8. Anti-cheating device according to any of claims 5 to 7, further comprising:
a judging unit connected with the selecting unit and used for judging whether each user is the undetermined user or not according to the advertisement click record of each user before the undetermined user is selected from the advertisement click users,
the advertisement click record comprises at least one of the click rate of each user to the advertisement, the time difference of each user clicking the same advertisement, the aggregation of the IP address distribution of each user, the aggregation of the number of the terminal equipment used by each user and the aggregation of the traffic owner of the advertisement clicked by each user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610079777.0A CN105760455B (en) | 2016-02-04 | 2016-02-04 | Anti-cheating method and device for advertisement clicking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610079777.0A CN105760455B (en) | 2016-02-04 | 2016-02-04 | Anti-cheating method and device for advertisement clicking |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105760455A CN105760455A (en) | 2016-07-13 |
| CN105760455B true CN105760455B (en) | 2021-05-14 |
Family
ID=56330613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610079777.0A Active CN105760455B (en) | 2016-02-04 | 2016-02-04 | Anti-cheating method and device for advertisement clicking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105760455B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651423A (en) * | 2016-09-28 | 2017-05-10 | 华南理工大学 | Quality scoring method for mobile application advertisement putting |
| CN107566897B (en) * | 2017-07-19 | 2019-10-15 | 北京奇艺世纪科技有限公司 | A kind of discrimination method, device and the electronic equipment of video brush amount |
| CN107590693A (en) * | 2017-09-12 | 2018-01-16 | 浙江华信区块链科技服务有限公司 | A kind of anti-cheating method and system of the intelligent digital media information push based on Quick Response Code |
| CN107742265A (en) * | 2017-10-27 | 2018-02-27 | 合肥亚慕信息科技有限公司 | One kind is based on big data analysis online testing invigilator's system |
| CN108009844B (en) * | 2017-11-20 | 2021-06-29 | 北京智钥科技有限公司 | Method and device for determining advertisement cheating behaviors and cloud server |
| CN108109011B (en) * | 2017-12-28 | 2021-07-09 | 北京皮尔布莱尼软件有限公司 | Advertisement anti-cheating method and computing equipment |
| 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 |
| CN110213209B (en) * | 2018-05-11 | 2022-01-07 | 腾讯科技（深圳）有限公司 | Cheating detection method and device for push information click and storage medium |
| CN108900909B (en) * | 2018-06-06 | 2020-07-17 | 武汉斗鱼网络科技有限公司 | Method for judging cheating user, related storage medium and electronic equipment |
| CN111489184A (en) * | 2019-01-29 | 2020-08-04 | 北京京东尚科信息技术有限公司 | Method, device, server, client and medium for verifying click behavior |
| CN109905738B (en) * | 2019-03-26 | 2022-03-08 | 湖南快乐阳光互动娱乐传媒有限公司 | Video advertisement abnormal display monitoring method and device, storage medium and electronic equipment |
| CN111127070B (en) * | 2019-11-08 | 2023-08-11 | 广州坚和网络科技有限公司 | Method for finding channel cheating |
| CN111353814A (en) * | 2020-02-24 | 2020-06-30 | 上海佳投互联网技术集团有限公司 | Method and system for identifying invalid advertisement users |
| CN111798281B (en) * | 2020-09-08 | 2020-12-11 | 腾讯科技（深圳）有限公司 | Method and device for judging cheating operation, computer readable storage medium and equipment |
| CN112258221A (en) * | 2020-10-12 | 2021-01-22 | 上海酷量信息技术有限公司 | System and method for identifying cheating terminal |
| CN117217830B (en) * | 2023-11-07 | 2024-02-27 | 深圳市豪斯莱科技有限公司 | Advertisement bill monitoring and identifying method, system and readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101132311A (en) * | 2007-09-25 | 2008-02-27 | 腾讯科技（深圳）有限公司 | Method and system for preventing network advertisement from being viciously clicked |
| CN103077172A (en) * | 2011-10-26 | 2013-05-01 | 腾讯科技（深圳）有限公司 | Method and device for mining cheating user |
| CN104715395A (en) * | 2015-02-13 | 2015-06-17 | 北京集奥聚合科技有限公司 | Method and system for filtering cheat clicks |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101696009B1 (en) * | 2013-02-27 | 2017-01-12 | 한국전자통신연구원 | Game characteristics detection apparatus and method for illegal user detection using game characteristics |
-
2016
- 2016-02-04 CN CN201610079777.0A patent/CN105760455B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101132311A (en) * | 2007-09-25 | 2008-02-27 | 腾讯科技（深圳）有限公司 | Method and system for preventing network advertisement from being viciously clicked |
| CN103077172A (en) * | 2011-10-26 | 2013-05-01 | 腾讯科技（深圳）有限公司 | Method and device for mining cheating user |
| CN104715395A (en) * | 2015-02-13 | 2015-06-17 | 北京集奥聚合科技有限公司 | Method and system for filtering cheat clicks |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105760455A (en) | 2016-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105760455B (en) | Anti-cheating method and device for advertisement clicking | |
| CN105447724B (en) | Content item recommendation method and device | |
| KR100754525B1 (en) | Method for setting the bidding rank about internet keyword advertisement of auto bidding | |
| CA2843056C (en) | User-initiated boosting of social networking objects | |
| KR101597247B1 (en) | System and method for exposuring advertisement based keyword in real-time | |
| US7870024B2 (en) | Systems and methods for electronic marketing | |
| US20100198655A1 (en) | Advertising triggers based on internet trends | |
| US8195512B2 (en) | System and method for serving relevant question-based advertisements | |
| CN110232597A (en) | Appraisal procedure, device, equipment and the storage medium of advertising channel | |
| KR100588109B1 (en) | System and method for bidding automatically about internet keyword advertisement and computer readable medium processing the method | |
| US20140229273A1 (en) | Initiating real-time bidding based on expected revenue from bids | |
| US11288710B2 (en) | Analyzing the advertisement bidding-chain | |
| US8484082B2 (en) | Systems and methods for electronic marketing | |
| CN107330718B (en) | Media anti-cheating method and device, storage medium and terminal | |
| JP2010541047A (en) | Method and apparatus for monitoring the effectiveness of online advertising | |
| CN106204121A (en) | Advertisement placement method based on browser and system | |
| US20150227963A1 (en) | Systems, methods, and apparatus for budget allocation | |
| KR20070027851A (en) | Method for preventing invalid clicks on the internet keyword advertisement | |
| US20130191209A1 (en) | Reducing invitational content serving exposure to cap limited campaigns | |
| US20160275571A1 (en) | Pacing the serving of a content item | |
| JP5113274B2 (en) | Advertisement delivery apparatus and method | |
| CN113011912B (en) | Media information processing method, device, electronic equipment and storage medium | |
| KR20100032585A (en) | Method, system and computer-readable recording medium for performing auction and charging for search advertisement | |
| CN114897562A (en) | Advertisement putting method and device, electronic equipment and storage medium | |
| US20100042492A1 (en) | Methods and apparatus for determining advertisement relevance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |