KR20090063449A - Fraud click monitoring method using conversion information and apparatus for performing the method - Google Patents

Abstract

A method for monitoring fraud click by using conversion information and an apparatus for executing the method are provided to determine detection rules about four click considering conversion information per an advertisement, thereby effectively detecting fraud click. A device for monitoring fraud click sets and maintains detection rules for detecting four click per an advertisement based on conversion information of an advertisement(S101). If advertisement click is generated by a client, the device for monitoring fraud click applies detection rules per an advertisement. Fraud click of an advertisement in which the click occurs is detected by application. If the fraud click is detected, the device for monitoring fraud click records and maintains clients executing the fraud click in a fraud click list of the advertisement(S103).

Description

TECHNICAL FOR MONITORING CLICK FRAUD USING CONVERSION INFORMATION AND APPARATUS FOR EXECUTING THE METHOD}

The present invention relates to a fraudulent click monitor device of an advertisement providing system, and more particularly, to a fraudulent click monitoring method for preventing fraudulent clicks on an advertisement in an advertisement providing system having a billing form by a cost per click (CPC) method; To the device.

Today, with the rapid development of communication networks such as the Internet, information retrieval through communication networks is becoming very common. By using the Internet, Internet users (searchers) can easily obtain necessary information anytime, anywhere, and this information search has changed a lot in our lives.

Accordingly, various models have been developed for the form of payment of advertisement costs between the operator who supports the search operation service of the Internet user and the advertiser who obtains the advertisement effect by exposing advertisement information about his or her information site to the Internet user through the search operation. It is developed and presented.

Among these payment methods, a general method may be the exposure of advertiser information and the cost of advertising by cost per click (CPC) method. The CPC method calculates an advertisement cost by measuring the number of connection connections (valid connections) between the searcher and the advertiser as the searcher who makes a search request clicks on the advertisement information of a specific advertiser.

The order of information exposure in the CPC method is to display the advertisement information of the advertiser who has suggested the highest price-per-click (CPC) value that the advertiser can allow and displays the advertisement information of the advertiser at the top of a predetermined search screen that is easily recognized by the searcher. It is provided in the form of arranging the advertisement information of the advertiser who presented the low CPC value at the bottom of the search screen. Therefore, the CPC method sorts the search results according to the size of the CPC presented by the advertiser and provides them to the searcher.

The aspect of paying the advertisement cost by the CPC method has a problem in that it is not possible to guarantee that the advertiser's information is exposed to the desired exposure position. In other words, by comparing the CPC values presented by one or more advertisers and arranging them sequentially and exposing the advertiser's information on the search screen according to the sorting order, the information may be exposed to the exposure position that the advertiser does not want. Have

In addition, in the CPC method, it is well known that only advertisement information of an advertiser having a high CPC value is first extracted or preemptively positioned at a display point that may easily cause a click selection of a searcher. This causes an advertiser to provide the advertiser's advertisement information as a result of the search request acts as an increase factor of the bid price, which may result in a heavy advertising cost.

In particular, the conventional CPC method has an unreasonable problem that the advertiser does not enjoy the desired advertising effect when the user repeatedly clicks the advertisement of the advertiser for the purpose of damaging the advertiser, while the advertising cost increases.

Recently, various models for detecting such fraudulent clicks have been developed and presented. However, since the existing fraud detection method applies the same rules to all advertisements, it is impossible to expect a detection performance against fraudulent clicks.

The present invention provides a fraudulent click monitoring method and apparatus using conversion information for preventing fraudulent clicks on an advertisement by applying different detection rules for each advertisement.

The present invention provides a fraudulent click monitoring method and apparatus using the conversion information for effective fraud detection by determining a detection rule for fraudulent clicks in consideration of conversion information for each advertisement.

The present invention includes the steps of setting a detection rule for each advertisement based on the conversion information (conversion information) of the advertisement for each advertisement; And detecting a false click of the advertisement based on the detection rule for each advertisement when a click on the advertisement occurs.

The setting of the detection rule for detecting false clicks may include setting a maximum number of conversions for each advertisement, setting a maximum number of clicks for each of the advertisements based on the maximum number of conversions, and the advertisement. It may include the step of setting the maximum number of clicks to the detection rule,

The detecting of the illegal click of the advertisement based on the detection rule for each advertisement may include accumulating the number of advertisement clicks of the same client when an advertisement click occurs from the client, and the maximum number of clicks corresponding to the clicked advertisement. The method may include determining the number of illegal clicks when the number of advertisement clicks accumulated by the client during the predetermined time exceeds the maximum number of clicks.

In addition, the present invention includes a database for storing the advertisement of the advertiser in association with a predetermined detection rule for each advertisement; A detection rule setting unit configured to set a detection rule for each advertisement based on conversion information of the advertisement; And a fraud click determination unit that detects fraudulent clicks of the advertisement based on a detection rule of the corresponding advertisement when a click on the advertisement occurs.

According to the present invention, fraudulent clicks can be monitored from a detection rule to which more intuitive advertisement information is applied by reflecting actual conversion information of the advertisement in determining a detection rule for fraudulent click detection.

According to the present invention, by providing different detection rules for each advertisement to detect fraudulent clicks on the advertisement, a more reasonable detection model can be provided and the detection performance of fraudulent clicks can be improved.

Hereinafter, with reference to the accompanying drawings will be described a negative click monitor method and a system for performing the method according to the present invention.

The present invention relates to a fraudulent click monitor method and apparatus for applying different detection rules for each advertisement based on actual conversion information of the advertisement.

In particular, the present invention sets the maximum number of clicks per client for each advertisement based on a predetermined maximum number of conversions per client (user) for each advertisement, thereby monitoring fraudulent clicks of the advertisement by applying different detection rules for each advertisement. have.

1 is a view showing the entire process of the negative click monitor method based on the conversion information of the advertisement in the negative click monitor method of the present invention.

The negative click monitor device of the present invention presets the maximum number of conversions per client for each advertisement provided by the advertiser, and stores and maintains the advertisement in association with the predetermined maximum number of conversions per client.

In the present specification, 'conversion' refers to the actual behavior of the client (user) for the advertisement, such as purchase, login, sign-up, page view, download, various Means corresponding to communication or the like.

The number of conversions means the number of conversions of the client for the same advertisement, and the maximum number of conversions per client means the maximum number of times that the same client can perform the conversion for the corresponding advertisement.

The conversion and the maximum number of conversions per client may be defined by an advertiser.

The advertiser may calculate the maximum number of conversions per client in consideration of the maximum conversion cost to achieve the conversion when the conversion occurs for the advertisement posted by the advertiser.

For example, if an advertiser posts an ad to make a purchase, one client will consider the maximum amount of money they can pay for the purchase, and if you post an ad that encourages signing up, the maximum amount of money spent on attracting one client You can consider the cost.

For an ad that induces a "notebook" to buy, the "maximum number of conversions per client" for that ad is estimated if "the same client does not buy more than two million US laptops for a given set time." Can be set to '2'.

In step S101, the negative click monitor apparatus sets and maintains a detection rule for detecting false clicks for each advertisement based on the conversion information of the advertisement. The negative click monitor apparatus stores an advertisement of an advertiser in association with a predetermined maximum number of conversions per client, sets a detection rule for each advertisement based on the maximum number of conversions per client, and then stores the set detection rule for each advertisement. By storing in association with the advertisement detection rules can be maintained.

As described above, the step S101 of setting the detection rule for each advertisement will be described in more detail with reference to FIG. 2.

In operation S102, when an illegal click monitor apparatus generates an advertisement click from the client, the negative click monitor apparatus applies the set detection rule for each advertisement to detect the illegal click of the advertisement in which the click occurs. The fraud click monitor apparatus may monitor fraudulent clicks on the advertisement by determining a detection rule of an advertisement in which a click has occurred and then applying the detection rule.

As described above, the step (S102) of detecting the illegal click of the advertisement will be described in more detail with reference to FIG. 3.

In step S103, when the fraudulent click is detected, the fraudulent click monitor apparatus records and maintains the client who has made the fraudulent click in the fraudulent click list of the advertisement. The fraudulent click monitor apparatus may maintain a fraudulent click list of a corresponding advertisement by storing at least one of an IP address, identification information, and cookie information of a client who has made the fraudulent click.

2 is a diagram illustrating a process of setting different detection rules for each advertisement based on the conversion information of each advertisement.

In step S201, the negative click monitor apparatus presets a maximum number of conversions per client for each advertisement posted by the advertiser. The illegal click monitor apparatus may use the actual conversion information of the corresponding advertisement to detect the illegal click of the advertisement by setting the maximum number of conversions per client.

In step S202, the negative click monitor apparatus calculates the maximum number of clicks per client of each advertisement based on a predetermined maximum number of conversions per client for each advertisement. The negative click monitor apparatus sets the maximum number of clicks per client as a detection rule for each advertisement.

The negative click monitor apparatus calculates a conversion rate of the corresponding advertisement based on the total number of clicks and the total number of conversions of the advertisement, and then calculates the maximum number of clicks per client based on the calculated conversion rate and the maximum number of conversions per client of the corresponding advertisement. Can be calculated

The maximum number of clicks per client is

Max clicks per client = Max conversions per client / Conversion rate for this ad = Max conversions per client / (Total clicks / Total conversions)

The maximum number of clicks per client may be calculated for each advertisement according to the maximum number of conversions per client compared to the conversion rate of the corresponding advertisement.

That is, the negative click monitor apparatus calculates the maximum clicks per client for each advertisement based on a predetermined maximum number of conversions per client for each advertisement, and sets the maximum clicks per client as a detection rule of the corresponding advertisement to each other. Other detection rules can be prepared.

3 is a diagram illustrating a process of determining an illegal click of an advertisement based on a detection rule for each advertisement.

In step S301, the negative click monitor apparatus accumulates the number of advertisement clicks of the same client when an advertisement click occurs from any client. The fraudulent click monitor apparatus may determine the same client using the IP address, ID information, cookie information, etc. of the client that clicked the advertisement, and accumulate the number of clicks of the corresponding advertisement for each same client when a click on the advertisement occurs. Can be.

In step S302, the negative click monitor apparatus determines a negative click on the accumulated click count of the same client based on the maximum number of clicks per client, which is a detection rule of the advertisement in which the click has occurred. The fraudulent click monitor apparatus may determine the maximum number of clicks per client corresponding to the advertisement in which the click occurred from the detection rule set in step S101. The illegal click monitor apparatus may determine that an advertisement click of a corresponding client is a negative click when the number of advertisement clicks of the same client accumulated for a predetermined time exceeds the maximum number of clicks per client.

As described above, the negative click monitor apparatus of the present invention may set different detection rules for each advertisement by using the conversion information of the advertisement, and when the click of the advertisement occurs, apply the detection rule of the corresponding advertisement to monitor the illegal click of the advertisement. .

The following describes a fraudulent click monitor apparatus for performing the fraudulent click monitor method according to the present invention. 4 is a diagram illustrating a peripheral configuration associated with a negative click monitor apparatus of the present invention, and FIG. 5 is a diagram illustrating an internal configuration of a negative click monitor apparatus using conversion information of an advertisement according to the present invention.

The fraudulent click monitor device of the present invention is a means for monitoring fraudulent clicks on an advertisement, and it is preferable to interwork with an advertisement providing system in which search word advertisement exposure and advertisement cost are determined by a cost per click (CPC) method.

As shown in Fig. 4, the searcher 410 has a terminal means for maintaining contact with the advertisement providing system 430 through the communication network 420, and the advertisement providing system 430 through the terminal means. An Internet user (hereinafter referred to as a "client") for inputting a predetermined keyword.

The advertiser 440 may refer to a content provider (CP) that operates a web site on a network by a network address (eg, an IP address, a URL, a domain, etc.), and may advertise his or her own advertisement in the advertisement providing system 430. Post and pay a predetermined advertising cost in accordance with the posted advertisement exposure.

The advertisement providing system 430 may include a search engine for extracting a predetermined number of advertisement lists corresponding to the keyword and providing the advertisement list as a search result.

When the keyword is input from the searcher 410, the advertisement providing system 430 extracts a list of advertisements corresponding to the keyword, and then determines the rank index of the advertisement according to the size of the CPC and in descending order of the rank index. The advertisement may be exposed.

The monitor device 450 of the present invention serves as a monitor for detecting fraudulent clicks of the advertisement when the client clicks on the advertisement of the advertiser.

As shown in FIG. 5, the monitor apparatus 450 may include a database, a detection rule setting unit 520, and a fraud click determination unit 530.

The monitor device 450 may provide different detection rules for each advertisement based on the actual conversion information of the advertisement, and monitor the fraudulent click of the advertisement according to the detection rule of the corresponding advertisement when a click on the advertisement occurs.

The database is a storage device for storing and maintaining an advertisement of an advertiser in association with a predetermined detection rule for each advertisement. In addition, the database may store and maintain the fraudulent click list by recording the client information of the fraudulent click on the fraudulent click list of the corresponding advertisement when a fraudulent click is detected.

That is, the database may include a conversion information database 510 which stores a detection rule for each advertisement for determining a false click, and a negative list database 540 for storing a monitor result including a false click list.

The detection rule setting unit 520 sets a detection rule for each advertisement based on the actual conversion information of the advertisement. The detection rule setting unit 520 calculates the maximum number of clicks per client based on a predetermined maximum number of conversions per client for each advertisement, and sets the number of clicks per client as a detection rule of the corresponding advertisement. The maximum number of clicks per client may be calculated based on a conversion rate indicating a ratio of the total number of conversions to the total number of clicks of the advertisement, and the maximum number of conversions per client of the advertisement.

The fraud click determination unit 530 accumulates the number of advertisement clicks of the same client when an advertisement click occurs from the client and determines the maximum number of clicks per client, which is a detection rule of the corresponding advertisement. The fraud click determination unit 530 may determine that a fraud click occurs when the number of advertisement clicks of the same client accumulated during a preset time exceeds the maximum number of clicks per client, which is the detection rule.

The fraud click determination unit 530 may determine the same client using the IP address, ID information, cookie information, etc. of the client, and accumulate the number of times a specific advertisement is clicked by the same client during the set time.

The fraud click determination unit 530, when a fraudulent click exceeding the maximum number of clicks per client of each advertisement is detected, the fraudulent list database of information (IP address, ID information, cookie information, etc.) of the client who has made the fraud click By passing to 540, the client can be recorded and managed in a fraudulent click list.

The fraudulent click monitor apparatus of the present invention sets a detection rule for detecting fraudulent clicks for each advertisement based on the conversion information (maximum number of conversions per client) of the advertisement, and then applies different detection rules for each advertisement. The detection performance can be improved.

The fraudulent click monitor method using the conversion information according to the present invention may be implemented in the form of program instructions that can be executed by various computer means and recorded in a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the media may be those specially designed and constructed for the purposes of the present invention, or they may be of the kind well-known and available to those having skill in the computer software arts. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tape, optical media such as CD-ROMs, DVDs, and magnetic disks, such as floppy disks. Magneto-optical media, and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

As described above, the present invention has been described by way of limited embodiments and drawings, but the present invention is not limited to the above embodiments, and those skilled in the art to which the present invention pertains various modifications and variations from such descriptions. This is possible.

Therefore, the scope of the present invention should not be limited to the described embodiments, but should be determined not only by the claims below but also by the equivalents of the claims.

1 is a view showing the entire process of the negative click monitor method based on the conversion information of the advertisement in the negative click monitor method of the present invention.

2 is a diagram illustrating a process of setting different detection rules for each advertisement based on the conversion information of each advertisement.

3 is a diagram illustrating a process of determining an illegal click of an advertisement based on a detection rule for each advertisement.

4 is a diagram for explaining a peripheral configuration associated with the negative click monitor apparatus of the present invention.

5 is a diagram showing the internal configuration of the fraudulent click monitor apparatus using the conversion information of the advertisement according to the present invention.

<Explanation of symbols for the main parts of the drawings>

450: monitor device 510: switching information database

520: detection rule setting unit 530: fraud click determination unit

540: fraudulent list database

Claims (17)

Setting a detection rule for each advertisement based on conversion information of the advertisement for each advertisement; And, Detecting a fraudulent click of the advertisement based on the detection rule for each advertisement when a click on the advertisement occurs; Negative click monitor method comprising a. The method of claim 1, Setting the detection rule for detecting the false click, Setting maximum conversions for each ad, Setting a maximum number of clicks for each of the ads based on the maximum number of conversions; Setting the maximum click count for each advertisement as the detection rule Negative click monitor method comprising a. The method of claim 2, The maximum number of conversions, The maximum number of conversions that a client can perform on the ad, which is the maximum number of conversions per client. Negative click monitor method characterized in that. The method of claim 3, The maximum number of conversions per client is Estimating based on the maximum conversion cost that can be spent to achieve the conversion of the ad. Negative click monitor method characterized in that. The method of claim 4, wherein The conversion is Client behavior for the advertisement, which corresponds to at least one of purchase, login, sign-up, page view, download, and communication Search terms advertising method characterized in that. The method of claim 2, Setting the maximum number of clicks for each of the ads, Calculating a conversion rate of the ad based on total clicks and total conversions of the ad; Calculating the maximum clicks based on the calculated conversion rate and the predetermined maximum conversion number for the advertisement. Negative click monitor method comprising a. The method of claim 2, Detecting the illegal click of the advertisement based on the detection rule for each advertisement, Accumulating ad clicks from the same client when an ad click occurs from a client; Determining a maximum number of clicks corresponding to the clicked advertisement; Determining that a click is illegal when the number of advertisement clicks of the client accumulated for a predetermined time exceeds the maximum number of clicks Negative click monitor method comprising a. The method of claim 7, wherein Detecting the illegal click of the advertisement based on the detection rule for each advertisement, If the fraud click is determined, recording the corresponding client in the fraudulent click list of the advertisement; The negative click monitor method further comprising. The method of claim 7, wherein In the accumulating the number of clicks on the ads of the same client, Determining the same client using at least one of an IP address, identification information, and cookie information of the client when the client connects to the client for clicking the advertisement; Negative click monitor method characterized in that. A computer-readable recording medium in which a program for executing the method of any one of claims 1 to 9 is recorded. A database storing advertisements of an advertiser in association with a predetermined detection rule for each advertisement; And, When a click on the advertisement occurs, the fraud click determination unit detects a fraudulent click of the advertisement based on a detection rule of the corresponding advertisement. Negative click monitor device comprising a. The method of claim 11, Detection rule setting unit for setting the detection rule for each advertisement based on the conversion information of the advertisement (conversion information) The negative click monitor device further comprising. The method of claim 12, The detection rule setting unit, Calculating the maximum number of clicks per client based on a predetermined maximum number of conversions per client for each advertisement, and setting the calculated maximum number of clicks per client as the detection rule of the advertisement. Negative click monitor device characterized in that. The method of claim 13, The detection rule setting unit, Calculating a conversion rate of the advertisement based on the total clicks and the total number of conversions of the advertisement, and calculating the maximum number of clicks per client based on the calculated conversion rate and a predetermined maximum number of conversions for the advertisement. Negative click monitor device characterized in that. The method of claim 13, The fraud click determination unit, When the client clicks on an advertisement, the client accumulates the number of clicks on the same client and determines the maximum number of clicks per client corresponding to the advertisement. If the number of clicks of the client accumulated during the preset time exceeds the maximum number of clicks per client, it is determined to be a false click. Negative click monitor device characterized in that. The method of claim 15, The fraud click determination unit, Determining the same client using at least one of the client's IP address, ID information, and cookie information Negative click monitor device characterized in that. The method of claim 15, The database, Recording and storing the client in a predetermined fraudulent click list when the fraudulent click is determined Negative click monitor device characterized in that.

Images