KR102192580B1 - Apparatus and method for providing advertisements - Google Patents

Abstract

As an advertisement providing device that provides advertisements to users, an advertisement management unit that manages a plurality of advertisements and the exposure and performance history of each advertisement, and calculates the probability distribution of performance indicators for each advertisement based on the exposure and performance history of each advertisement. Receives an advertisement request from the advertisement performance index management unit and the user terminal, extracts the performance index value of each advertisement based on the probability distribution of the performance index for each advertisement, and provides it to the user terminal based on the performance index value of each advertisement. It includes an advertisement providing unit for selecting an advertisement.

Description

Advertisement providing apparatus and method {APPARATUS AND METHOD FOR PROVIDING ADVERTISEMENTS}

The present invention relates to an advertisement providing apparatus and method.

The user inputs a search word reflecting an interest in a portal site, etc., and receives search results related to the search word. At this time, a business operator operating a portal site or the like exposes an advertisement requested by an advertiser through an advertisement providing device in the search result. In addition, business operators and advertisers select advertisements, execute advertisements, and determine prices according to reaction information such as click through rate (CTR) per impression.

Until now, business operators have executed advertisements based on performance indicators calculated based on advertisement execution information. Accordingly, until the advertisement execution information is updated and the performance index is calculated again, the advertisement is executed based on the determined performance index. In addition, since the performance index so far is calculated as a ratio equal to the click rate per impression regardless of the number of advertisement exposures, there is a problem that the number of advertisement exposures is not reflected in advertisement execution. Therefore, since the new advertisement has a small number of impressions or clicks, it is difficult to evaluate the performance of the corresponding advertisement only with statistically calculated performance indicators. In this case, performance indicators of other advertisements are used to predict performance indicators, but this is only a temporary measure and is difficult to regard as a performance indicator of new advertisements.

The problem to be solved by the present invention is to provide an apparatus and method for variably extracting an advertisement performance index based on a probability distribution reflecting the number of advertisement exposures, and providing an advertisement based on the extracted performance index.

An advertisement providing device that provides advertisements to a user according to an embodiment of the present invention, comprising a plurality of advertisements, and an advertisement management unit that manages the exposure and performance history of each advertisement, based on the exposure and performance history of each advertisement, The advertisement performance indicator management unit that calculates the probability distribution of the performance indicators for each, receives an advertisement request from the user terminal, extracts the performance indicator value of each advertisement based on the probability distribution of the performance indicators for each advertisement, and calculates the performance indicator value of each advertisement. It includes an advertisement providing unit for selecting an advertisement to be provided to the user terminal on the basis of.

The advertisement performance indicator management unit calculates the average and standard deviation related to the performance index of each advertisement, based on the exposure and performance history related to the performance index of each advertisement, and based on the average and the standard deviation of each advertisement, each advertisement You can calculate the probability distribution of the performance indicators of

When the exposure and performance history of a random advertisement among the plurality of advertisements is updated, the advertisement performance indicator management unit may update a probability distribution of a performance index corresponding to the random advertisement.

When receiving the first advertisement request, the advertisement providing unit extracts a first performance index value from the probability distribution of the performance index corresponding to the first advertisement, and when receiving the second advertisement request, the probability of the performance index corresponding to the first advertisement The second performance indicator value can be extracted from the distribution.

The performance indicator may include at least one of a click rate per exposure and a response rate per exposure.

The probability distribution may include at least one of a normal distribution, a beta distribution, and a Poisson distribution.

An advertisement providing apparatus according to another embodiment of the present invention is a method of providing advertisements to a user, managing the exposure and performance history of each of a plurality of advertisements, based on the exposure and performance history of each of the plurality of advertisements, an advertisement Calculating the probability distribution of the performance indicators for each advertisement, extracting the performance indicator values of each advertisement based on the probability distribution of the performance indicators for each advertisement, and selecting an advertisement to be provided to the user terminal based on the performance indicator values of each advertisement. It includes the step of.

Calculating the probability distribution of the performance indicators for each advertisement includes calculating an average and standard deviation related to the performance indicators of each advertisement, based on the exposure and performance history related to the performance indicators of each advertisement, and calculating the average and the standard deviation. As a basis, the probability distribution of performance indicators for each advertisement can be calculated.

The probability distribution may include at least one of a normal distribution, a beta distribution, and a Poisson distribution.

The performance indicator may include at least one of a click rate per exposure and a response rate per exposure.

In the step of extracting the performance index value of each advertisement, upon receiving an advertisement request from the user terminal, the performance index value of each advertisement may be extracted based on a probability distribution of the performance index for each advertisement.

In the step of extracting the performance index value of each advertisement, when a first advertisement request is received, a first performance index value is extracted from a probability distribution of a performance index corresponding to a first advertisement, and when a second advertisement request is received, the first advertisement The second performance index value may be extracted from the probability distribution of the performance index corresponding to the advertisement.

The advertisement providing method may further include updating a probability distribution of a performance index corresponding to the random advertisement when the exposure and performance history of the advertisement among the plurality of advertisements are updated.

According to an embodiment of the present invention, an advertisement performance index may be predicted based on the advertisement exposure and reaction information, and an advertisement may be executed based on the predicted performance index. Accordingly, according to an embodiment of the present invention, since exposure and reaction information of advertisements is reflected in a probability distribution of a performance index, and a performance index value is extracted from this probability distribution, a performance index value in a reliable section can be obtained.

According to an embodiment of the present invention, since the performance index is extracted according to the probability distribution of the performance index for each advertisement request, the performance index value is varied. Accordingly, according to an exemplary embodiment of the present invention, even if an advertisement having a small number of reactions such as exposure or click is given an opportunity to be executed, advertisement revenue and advertisement effect can be increased.

1 is a schematic diagram of an advertisement system according to an embodiment of the present invention.
2 to 4 are diagrams illustrating probability distributions of performance indicators according to an embodiment of the present invention.
5 is a flowchart of an advertisement providing method according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement the embodiments of the present invention. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and similar reference numerals are assigned to similar parts throughout the specification.

Throughout the specification, when a part "includes" a certain component, it means that other components may be further included rather than excluding other components unless otherwise stated. In addition, terms such as "... unit", "... group", and "module" described in the specification mean units that process at least one function or operation, which can be implemented by hardware or software or a combination of hardware and software. have.

1 is a schematic diagram of an advertisement system according to an embodiment of the present invention, and FIGS. 2 to 4 are diagrams illustrating probability distributions of performance indicators according to an embodiment of the present invention.

Referring to FIG. 1, the advertisement system 10 includes an advertisement providing device 100, an advertiser terminal 200, and a user terminal 300.

The advertisement providing device 100 provides the advertisement of the advertiser terminal 200 to the user terminal 300 according to the advertisement service request of the advertiser terminal 200.

The advertiser terminal 200 is a device through which an advertiser accesses and communicates with the advertisement providing device 100 through a network, for example, a computer, a personal digital assistant (PDA), a mobile communication terminal, and a television (television). TV) and other various communication devices can be used.

The user terminal 300 is a device for a user to access and communicate with the advertisement providing device 100 through a network. Like the advertiser terminal 200, various communication devices such as a computer, a personal portable information terminal, a mobile communication terminal, and a television can be used. I can.

The advertisement providing device 100 includes an advertisement management unit 110, an advertisement performance indicator management unit 130, and an advertisement providing unit 150.

The advertisement management unit 110 manages a plurality of advertisements, and the exposure and performance history of each advertisement. The exposure and performance history includes exposure information and various information related to performance after exposure. For example, the exposure and performance history includes the number of impressions, the number of clicks, and the number of reactions (actions). Here, the response includes a user's response to the advertisement in various forms, and may include, for example, a mouseover, a video playback, a video extension, and the like. For example, the advertisement management unit 110 manages the exposure and performance history of advertisements A and B as shown in Table 1.

Number of exposures Click count Number of reactions (actions) AD A 10000 8 20 AD B 1000 One 5

The advertisement performance indicator management unit 130 calculates a probability distribution of performance indicators for each advertisement based on the exposure and performance history of each advertisement. Performance indicators can be diverse, for example, click through rate (CTR) per impression, response rate per impression, etc.

)를 구한다. The probability distribution of a performance indicator can be calculated by various statistical methods. For example, the probability distribution can be expressed by various kinds of probability density functions. For example, the probability distribution may include various types of probability distributions, such as a normal distribution, a beta distribution, and a Poisson distribution calculated based on an average and a variance. For example, when the advertisement performance indicator management unit 130 calculates the probability distribution of the performance indicator using the normal distribution, the average (m) and the standard deviation (

).

)를 기초로 도 2와 같은 모양의 확률 분포를 구한다. 광고A와 광고B의 노출당 클릭률의 확률 분포는 표 2와 같은 평균과 표준 편차를 가지고, 도 2와 같은 확률 분포 모양을 가진다. 광고 성과 지표 관리부(130)는 노출당 반응률의 확률 분포를 구할 수 있고, 여기서는 노출당 클릭률(CTR)의 확률 분포를 기준으로 설명한다.The advertising performance indicator management unit 130 is the average (m) and standard deviation (

Based on ), the probability distribution of the shape shown in FIG. 2 is obtained. The probability distribution of the click-through rate per impression of advertisement A and advertisement B has the average and standard deviation shown in Table 2, and has the shape of the probability distribution shown in FIG. The advertisement performance indicator management unit 130 may obtain a probability distribution of a response rate per exposure, which will be described based on a probability distribution of a click rate per exposure (CTR).

Average Standard Deviation AD A 0.008 (0.08%) 0.00028 AD B 0.01(0.1%) 0.001

When the exposure and performance history of each advertisement is updated, the advertisement performance indicator management unit 130 also updates the probability distribution of the performance indicator. Referring to FIG. 3, the average may change as the advertisement is executed, and the probability density near the average gradually increases. Accordingly, as advertisements are executed, the width of the probability distribution becomes narrower and the probability density value increases. In other words, the probability that the performance index value will be extracted near the average increases.

The advertisement providing unit 150 receives an advertisement request from the user terminal 300. The advertisement providing unit 150 delivers at least one advertisement stored in the advertisement management unit 110 to the user terminal 300. In this case, the advertisement providing unit 150 determines which advertisement is to be executed among the plurality of advertisements stored in the advertisement management unit 110 based on the advertisement execution criteria. The advertisement execution criteria may vary not only in performance indicators but also in price, but it is assumed that advertisements are executed based on performance indicators.

범위 내, 또는 2

범위 내의 성과 지표값을 추출하도록 추출 범위를 설정할 수 있다.The advertisement providing unit 150 executes advertisements based on the performance indicators of each advertisement probabilistically extracted from the advertisement performance indicator management unit 130. That is, the advertisement providing unit 150 does not use a fixed performance index value, but uses the performance index value extracted from the probability distribution of the performance index. Therefore, the performance index value of each advertisement may vary each time a user requests an advertisement. The advertisement providing unit 150 may set an extraction range from a probability distribution. For example, the advertisement providing unit 150 is 1 in the probability distribution

Within range, or 2

The extraction range can be set to extract performance indicator values within the range.

For example, referring to FIG. 4, the average CTR (m_a) of advertisement A is lower than the average CTR (m_b) of advertisement B. Since the average CTR (m_b) of advertisement B has a small number of exposures, the average CTR (m_b) may not be a reliable value yet. Nevertheless, when an advertisement is executed only based on the average CTR, advertisement B having a high average CTR is always executed prior to advertisement A.

On the other hand, the advertisement providing unit 150 executes the advertisement in consideration of distribution by the number of exposures. The advertisement providing unit 150 extracts a random performance index value from the probability distribution of the performance index of each advertisement, compares the extracted performance index values, and executes the advertisement.

Ad A has a high probability density near the average CTR. Therefore, Ad A has a high probability that the performance index value of the click-through rate per impression will be extracted near the average CTR, and Ad B has a higher average CTR than Ad A but farther from the average CTR (e.g., There is also a probability that a value lower than the performance indicator value) will be extracted. If the performance index value m_a1 extracted from the probability distribution of advertisement A is larger than the performance index value m_b1 extracted from the probability distribution of advertisement B, the advertisement providing unit 150 may execute advertisement A first.

As described above, when the advertisement providing unit 150 uses a value extracted according to a probability distribution instead of using a fixed performance index value, the size of the performance index value may be changed. Accordingly, the advertisement providing unit 150 provides an opportunity to increase performance by executing advertisements having a low average performance index value.

5 is a flowchart of an advertisement providing method according to an embodiment of the present invention.

Referring to FIG. 5, the advertisement providing apparatus 100 calculates a probability distribution of a performance index for each advertisement based on the exposure and performance history of each advertisement (S110). For example, exposure and performance history includes the number of impressions, clicks, and reactions. Performance indicators may be click-through rate per impression (CTR), response rate per impression, and the like.

The advertisement providing device 100 receives an advertisement request from the user terminal 300 (S120).

The advertisement providing apparatus 100 extracts a performance index value for each advertisement from the probability distribution of the performance index of each advertisement (S130).

The advertisement providing apparatus 100 determines an advertisement to be provided to the user terminal 300 based on the performance index value for each advertisement (S140).

For example, if Ad C is 10000 impressions, 5 clicks, and an average CTR of 0.0005, Ad D is 10000 impressions, 6 clicks, and an average CTR of 0.0006. Ad D is always selected based on the difference between the dogs.

On the other hand, the advertisement providing apparatus 100 extracts the performance index value of each advertisement from the probability distribution of the performance index of each advertisement. Therefore, referring to Table 3, since the CTR is extracted to execute the advertisement, the CTR of each of the advertisement C and the advertisement D is changed. And, in some cases, the CTR of advertisement C may have a larger value than the CTR of advertisement D. For example, the advertisement providing device 100 may select advertisement C for the secondary advertisement request. As described above, when the advertisement providing device 100 extracts the performance index value of each advertisement from the probability distribution of the performance indicators of advertisement C and advertisement D for each advertisement request, and selects an advertisement based on the extracted performance index value, as a result, , Advertisement C and Advertisement D will be executed at a ratio of c:d. For example, c may be 39 and d may be 61. That is, the advertisement providing device 100 may execute the advertisement based on the performance index value extracted in real time when the advertisement is requested, not based on the advertisement execution ratio calculated in advance.

AD C AD D Selection result Primary 0.00043 0.00081 AD D Secondary 0.00078 0.00052 AD C 3rd 0.00042 0.00064 AD D 4th 0.00032 0.00061 AD D 5th 0.00079 0.00126 AD D

In this way, when the number of exposures, the number of clicks, and the number of reactions are insufficient, the advertisement providing apparatus 100 may reduce advertisement execution errors that occur using the fixed performance index value. In addition, the advertisement providing apparatus 100 extracts a performance index value from a probability distribution of a performance index generated based on the exposure and performance history of each advertisement, instead of randomly extracting a performance index value between 0 and 1. Accordingly, the advertisement providing apparatus 100 mainly extracts a value near the average based on the probability distribution, but also extracts a value away from the average, and adjusts the advertisement to be flexibly selected as a result.

When the number of impressions, number of clicks, and number of reactions is sufficient, the probability distribution of the performance indicator changes to a shape where the probability density of the average value is close to 1. In this case, the advertisement providing apparatus 100 may execute the advertisement based on the average performance index value.

The embodiments of the present invention described above are not implemented only through an apparatus and a method, but may be implemented through a program that realizes a function corresponding to the configuration of the embodiment of the present invention or a recording medium on which the program is recorded.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements by those skilled in the art using the basic concept of the present invention defined in the following claims are also provided. It belongs to the scope of rights.

Claims (13)

As an advertisement providing device that provides advertisements to users,
An advertisement management unit that manages multiple advertisements, and the exposure and performance history of each advertisement,
An advertisement performance indicator management unit that calculates a probability distribution of performance indicators for each advertisement based on the exposure and performance history of each advertisement, and
Receives an advertisement request from the user terminal, randomly extracts the performance index value of each advertisement from the specified extraction range of the probability distribution of the performance index for each advertisement, and selects the advertisement to be provided to the user terminal based on the performance index value of each advertisement. Includes an advertisement provider,
The extraction range is a range within a specified standard deviation from the average of the probability distribution. In claim 1,
The advertisement performance indicator management unit
Based on the exposure and performance history related to the performance indicators of each advertisement, the average and standard deviation related to the performance indicators of each advertisement are calculated, and the probability distribution of the performance indicators of each advertisement based on the average and the standard deviation of each advertisement Advertising providing device to calculate. In claim 1,
The advertisement performance indicator management unit
When the exposure and performance history of a random advertisement among the plurality of advertisements are updated, an advertisement providing device for updating a probability distribution of a performance index corresponding to the random advertisement. In claim 1,
The advertisement providing unit
Upon receiving the first advertisement request, the first performance index value is extracted from the probability distribution of the performance index corresponding to the first advertisement, and when the second advertisement request is received, the second advertisement is obtained from the probability distribution of the performance index corresponding to the first advertisement. An advertisement providing device that extracts performance index values. In claim 1,
The above performance indicators are
An advertisement providing device including at least one of a click-through rate per impression and a response rate per impression. In claim 1,
The advertisement providing apparatus including at least one of a normal distribution, a beta distribution, and a Poisson distribution. As a method for the advertisement providing device to provide advertisements to users,
Managing the exposure and performance history of each of the plurality of advertisements,
Calculating a probability distribution of performance indicators for each advertisement based on the exposure and performance history of each of the plurality of advertisements,
Extracting the performance index value of each advertisement based on the probability distribution of the performance index by advertisement, and
Including the step of selecting an advertisement to be provided to the user terminal based on the performance index value of each advertisement,
The step of extracting the performance index value of each advertisement
Upon receiving an advertisement request from the user terminal, the performance index value of each advertisement is randomly extracted from the specified extraction range of the probability distribution of the performance index for each advertisement,
The extraction range is a range within a specified standard deviation from the average of the probability distribution. In clause 7,
The step of calculating the probability distribution of the performance indicator for each advertisement
An advertisement that calculates the average and standard deviation related to the performance index of each advertisement based on the exposure and performance history related to the performance index of each advertisement, and calculates the probability distribution of the performance index for each advertisement based on the average and the standard deviation. Delivery method. In clause 7,
The probability distribution is an advertisement providing method including at least one of a normal distribution, a beta distribution, and a Poisson distribution. In clause 7,
The above performance indicators are
An advertisement providing method including at least one of a click-through rate per impression and a response rate per impression. delete In clause 7,
The step of extracting the performance index value of each advertisement
Upon receiving the first advertisement request, the first performance index value is extracted from the probability distribution of the performance index corresponding to the first advertisement, and when the second advertisement request is received, the second advertisement is obtained from the probability distribution of the performance index corresponding to the first advertisement. Ad serving method to extract performance indicator values. In clause 7,
If the exposure and performance history of a random advertisement among the plurality of advertisements is updated, updating a probability distribution of a performance index corresponding to the random advertisement
Advertising providing method further comprising.

Images