KR101614954B1 - Advertisement system and advertisement method for controling exposure frequency and exposure interval of advertisement to manage inventory - Google Patents

Abstract

Disclosed are an advertisement system and a method for managing an inventory by controlling an exposure frequency and an exposure interval of an advertisement. In an advertisement product whose sales are determined based on the number of impressions of an advertisement, an advertisement system that manages an inventory of searchable search terms using search terms input during a past unit period, A probability calculation unit for calculating a probability of inclusion by using a search term input during a past unit period, and an inventory prediction unit for predicting an inventory of the requested search term using the calculated probability.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an advertisement system and an advertisement system for managing an inventory by controlling an exposure frequency and an exposure interval of an advertisement,

Embodiments of the present invention relate to an advertisement system and method for managing an inventory by controlling an exposure frequency and an exposure interval of an advertisement.

Users can enter search terms into a search engine to obtain desired information. The information that these users acquire often reflects the user's interests. This user's interest is the main information for the advertiser's advertisement to be effective.

Thus, when a user visits a specific site, the advertisement effect can be maximized when the user presents an advertisement related to the content that the user is interested in. Therefore, there is a need for a method of how to select content and advertisements that the user is interested in. Also, in order to encourage advertisers to register their ads, there is a need for a method that can provide an objective indicator of the user's interest.

However, if the advertiser unconditionally exposes the advertiser to a user who has shown the behavior of the advertiser without special constraints, the advertiser may be repeatedly exposed to the same advertiser. Therefore, there is a need for a method that exposes the advertisement reflecting the user's interest but can control the highly repeated exposure of the same advertisement.

There is provided an advertisement system and an advertisement method capable of maximizing an advertisement effect by providing an advertisement related to a user's interest based on a search word input by a user.

An advertisement system capable of predicting an inventory of searchable search terms by using a probability that a request word is included in search terms input by a user during a unit period in providing an advertisement related to a user's interest based on a search word input by a user, An advertising method is provided.

There is provided an advertisement system and an advertisement method capable of managing an inventory by providing an advertisement related to a user's interest based on a search word input by a user and controlling an exposure limit and an exposure interval.

An advertisement system capable of determining the number of predicted inputs of a specific search term by using a probability that a request word is included in a search term input by a user during a unit period in providing an advertisement related to a user's interest, And methods are provided.

An advertisement system for managing an inventory of searchable search terms using search terms input during a past unit period in an advertisement product whose sales are determined based on the number of impressions of advertisements, There is provided an advertisement system including a probability calculation unit for calculating a probability that a search word will be included using a search term entered during a past unit period, and an inventory prediction unit for predicting an inventory of the requested search word using the calculated probability.

According to one aspect, the probability calculator calculates a probability by using a ratio of the number of searches performed in the past unit period to the total number of searches occurring in the past unit period and the number of search words entered per user in the past unit period Can be calculated.

According to another aspect, the inventory forecasting unit can estimate the inventory of the requested query using the calculated probability and the number of search terms input per user for the past unit period.

According to another aspect, the inventory forecasting unit can estimate the inventory of the requested query using the calculated probability, the number of search terms input per user per unit period in the past, and the exposure limit. At this time, the exposure limit may include the number of times that the same advertisement is allowed to be repeatedly exposed to the user. Here, the exposure limit may be determined by a ratio of the PV (Page View) to UV (Unique Visit) and a predetermined value, whichever is smaller.

According to another aspect, the inventory forecasting unit can estimate the inventory of the requested query using the calculated probability, the number of search terms entered per user per unit period in the past, the exposure limit, and the depreciation coefficient. At this time, the amortization coefficient can be calculated by using the sum of the isoquency series for users who decrease with a certain probability as the number of times of exposure of the same advertisement increases.

According to another aspect, the advertisement system may further include a sellable inventory determining unit that determines a sellable inventory for the requested search word using the probability and the sales amount of the pre-sold search term. At this time, the sellable inventory determining unit determines the ratio of the number of searches made during the past unit period to the total number of searches occurring in the past unit period, the sales amount of the requested query and the pre-sold query, The salesable inventory for the requested search term can be determined using the proportion of the total number of searches that occurred during the past unit period of the number of searches that occurred during the past unit period and the sales volume of the requested search term.

An advertisement system for managing a search term using a search term input during a past unit period, the system comprising: a probability calculating unit that calculates a probability that a search term input by a user during a unit period includes a specific search term, And a predictive input number determination unit for determining the predictive input number of a specific search word using the calculation unit and the calculated probability.

An advertisement method for managing an inventory of searchable search terms using search terms input during a past unit period in an advertisement product whose sales are determined based on the number of impressions of advertisements, Calculating a probability that a search word will be included using a search term entered during a past unit period, and predicting a sellable inventory of the requested search term using the calculated probability.

A method of managing a search term using a search term input during a past unit period, the method comprising the steps of: calculating a probability that a search term input by a user during a unit period includes a specific search term, And determining a predicted input number of a specific search term using the calculated probability.

It is possible to maximize the advertisement effect by providing the advertisement related to the user's interest based on the search word inputted by the user.

In providing the advertisement related to the user's interest, based on the search word input by the user, the user can predict the inventory of the searchable search term using the probability that the requested search word is included in the search words input during the unit period.

The user can manage the inventory by controlling the exposure limit and the exposure interval while providing advertisements related to the user's interest based on the search word inputted by the user.

In providing the advertisement related to the user's interest based on the search word input by the user, the user can determine the number of predicted inputs of the specific search word by using the probability that the request word is included in the search words input during the unit period.

1 is a diagram schematically illustrating a relationship between an advertiser, an advertisement platform, a publisher, and a user in an embodiment of the present invention.
2 is a diagram showing an overview of an advertisement system in an embodiment of the present invention.
FIG. 3 is a diagram illustrating an example of estimating the number of search terms entered per user and the inventory through UV in one embodiment of the present invention.
4 is an example showing the amount of inventory as the length of an arrow in an embodiment of the present invention.
5 is a diagram illustrating an example of a keyword-based inventory and a full inventory in an embodiment of the present invention.
FIG. 6 is a graph illustrating the number of users who are repeatedly exposed to the same advertisement material according to an exemplary embodiment of the present invention.
7 is a block diagram for explaining an internal configuration of an advertisement system in an embodiment of the present invention.
8 is a flowchart illustrating an advertising method in an embodiment of the present invention.
9 is a block diagram for explaining an internal configuration of an advertisement system in another embodiment of the present invention.
10 is a flowchart illustrating an advertising method in another embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram schematically illustrating a relationship between an advertiser, an advertisement platform, a publisher, and a user in an embodiment of the present invention.

1 shows an advertiser 110, an advertising platform 120, a publisher 130, and a user 140. Herein, the advertiser 110 and the user 140 may substantially mean a terminal such as a PC (personal computer), a smart phone, etc. used by the advertiser 110 or the user 140. 1 may indicate that data can be transmitted and received between a terminal used by the advertiser 110, an advertisement platform 120, a publisher 130, and a terminal used by the user 140 using a wired / wireless network .

The advertisement platform 120 may perform a bid for an advertisement of the advertiser 110, a match between an advertisement and a search word, an alignment of an advertisement or an advertiser, an advertisement to the publisher 130, and a charge based on exposure of the advertisement. Descriptions of matters that can be understood with reference to the prior art, such as matters related to the general technical aspects of the advertisement platform 120, i.e., search advertisements and / or banner advertisement platforms transmitted over the Internet, will be omitted.

First, the term "publisher" in this specification may be used in place of the term "site ". However, the description using the term site does not exclude the possibility of implementation of the present invention in an environment other than a general PC web site connection, such as an application screen executed in a mobile terminal. Conversely, the term "site" may be used interchangeably with the term publishing site or the publisher referred to above. In other words, each site may correspond to an individual publisher appearing on the publisher 130. At this time, the term "site" may include any kind of web site that can be exposed to the advertisement and can be provided to the user through a wired or wireless network, and may include a single web page constituting the web site.

In addition, the "exposure" of an advertisement can be interpreted to include that promotional contents such as text, images, sound, video, hyperlink, etc., associated with the advertiser through a site (publisher) In addition, the "selection" of the exposed advertisements causes a situation where the advertiser is trying to achieve through the delivery of the promotional contents by causing the user (site visitor) to react to the promotional contents such as the text and the image provided by the mouse . ≪ / RTI > At this time, the situation induced by the advertiser may include, for example, exposing the page associated with the advertiser to the user who selected the advertisement.

The publisher 130 may provide the user 140 with his or her site and may provide the pages the site includes through the site or provide the user 140 with search results for the search term through the entered search term . At this time, the publisher 130 may receive the advertisement for exposing through the pages to the advertisement platform 120 and provide the advertisement to the user 140. The publisher 130 can also deliver the search term entered by the user 140 to the ad platform 120 and receive advertisements for the search term from the ad platform 120 and provide it to the user 140 as a search result. have.

The publisher 130 may provide a path (screen) where the user 140 is directly provided with the advertisement, and the advertisement may be provided through the website in a general online environment. Each of the plurality of individual advertisement platforms (first advertisement platform, second advertisement platform, ...) included in the advertisement platform 120 includes a plurality of individual publishers (the first publisher, The first publisher, the second publisher, ...). In addition, each of the plurality of individual publishers may provide the user 140 with at least one of a variety of services that can be provided through a wired or wireless network, such as integrated search, keyword search, blog service, etc., Can be provided.

That is, the user 140 can basically input a search word to the publisher 130 to perform a search. In this case, the publisher 130 may be a search engine that provides search results associated with a search term to the user 100, or may be a subject that displays a service providing page that receives search terms and provides search results.

2 is a diagram showing an overview of an advertisement system in an embodiment of the present invention. The advertisement system 200 according to the embodiments of the present invention collects search terms inputted by the user 140 through the publisher 130 described with reference to FIG. 1, and searches for advertisements Can be extracted. The advertisement system 200 may be a system included in the individual advertisement platform of the advertisement platform 120 or a separate system associated with the individual advertisement platform. 2, an advertisement system 200 included in a specific advertisement platform will be described.

At this time, the advertisement system 200 can predict the sellable inventory for each search word. Here, the inventory may refer to a sellable amount regarding the number of impressions of the advertisement. For example, the inventory is for providing a guide to the number of impressions that the advertiser 110 can purchase, and may mean the number of impressions that the advertiser 110 can purchase among the available sales amount. At this time, if the advertiser 110 purchases a specific number of impressions, the advertisement of the advertiser 110 may be exposed for the corresponding number of impressions in the advertisement exposure area through the site of the publisher 130. That is, the advertiser 110 can know the amount of the available advertisement by knowing the inventory of the search word selected by the advertiser 110 in advance. For example, the advertisement system 200 may provide the inventory as an expected impression for each query for the guarantee that the advertiser 110 has purchased. In addition, the advertisement system 200 may sell the advertisements within the predicted inventory for at least one query that the advertiser 110 requests.

At least one individual ad platform 210 or ad system 200 included in the ad platform 130 may be configured to provide an advertisement for the search term entered by the user 140 to provide an advertisement that reflects the interests of the user 140 The management table 211 can be created by associating the extracted advertisement with the identification information of the user 140.

The management table 211 may store identification information of the user 140, information on the search term input by the user 140, and information on the advertisement extracted through the search term input by the user 140 in association with each other . More specifically, the related search history and the advertisement exposure history may be stored in the management table 211 for each user. Here, the related keyword history is stored in at least one search word among the search word entered in the past from the user 140, the search word related to the product purchased by the user 140, and the search word related to the advertisement or the web page provided to the user 140 And at least one search term and information about when the user 140 is related. For example, the search term entered by the user 140, the extracted advertisement for the inputted search term, and the identification information of the user 140 can be managed and stored in association with each other. As another example, the search term related to the purchased product of the user 140, the advertisement related to the search term, and the identification information of the user 140 may be related to each other and stored in the management table. At this time, the information on the time when the search term is associated with the user 140 may include information on the time when the search term is input from the user 140 or the time when the user 140 purchased the product.

Table 1 below shows an example of the management table.

Table 1 shows the advertisement information exposed through the search word " automobile " entered by the user "abcd " and the search word " automobile ". At this time, in the example of the management table in Table 1, the point in time when the user "abcd" entered the search term "car" is indicated as year, month, day, hour, and minute. In this case, when the same user repeatedly inputs the same search word, the point in time of repeated input may be all stored in the management table, or only the point in time of the latest input may be stored in the management table. Information on this point can be used to determine the recency of the search term. Table 1 further includes information on the number of times each advertisement is exposed. That is, in the example of Table 1, the number of times of exposure to the user "abcd" through the search word "automobile" is shown.

Here, the identification information may include at least one of an ID for identifying the user 140 in the publisher 130 and a cookie information of the terminal used by the user 140 to access the site provided by the publisher 130. Further, the management table 211 may further store validity period information determined according to the passage of time from the time when the user 140 has input a search word in the past. This validity period information can be used to determine the recency of the search term.

At this time, the individual advertisement platform 210 can update the management table 211 every time the user 140 inputs a search word and when an advertisement matching the search word exists.

After the management table 211 has been created for the user 140, the individual advertisement platform 210 can be used by the user 140 when the user 140 visits the service page of the individual publishers included in the publisher 130, Can be extracted. At this time, the individual advertisement platform 210 can provide the extracted advertisement to the individual publishers in association with the service page visited by the user 140, and the individual publishers can expose the provided advertisement to the user 140.

At this time, a plurality of advertisements may be stored in the management table 211, and an individual advertisement platform 210 may determine which advertisement among the plurality of advertisements is to be provided to an individual publisher. For example, the individual advertisement platform 210 may provide an individual publisher with an advertisement that matches the most recently entered search term based on the above-described validity period information. As another example, the individual ad platform 210 may provide individual publishers with ads that match the entered search terms within a certain unit period. In this case, the individual publishers can randomly roll over the provided advertisements through the site for exposure.

At this time, since the interest of the user 140 is recorded in the management table 211 through the search word input by the user 140, even if the user 140 visits another individual publisher, the same individual publisher belongs to the publisher 130 An advertisement may be exposed to the user 140. That is, by creating the management table 211 for each user (substantially every user ID or cookie information stored in the terminal of the users), it is possible to provide an advertisement suitable for each user's interest.

That is, if the identification information of the user 140 is a cookie, the publisher 130 may expose different advertisements according to the terminal used by the user 140. For example, when a search word related to an animal is input in a computer X used by a user at home, and a search word related to an estate is input in a computer Y used in a company, even if the same user is a same user, 130 and the service page of the publisher 130 via the computer Y, different advertisements may be exposed, respectively.

In addition, if the identification information of the user 140 is the login ID for the publisher 130 of the user 140, the same advertisement can be exposed regardless of the terminal used by the user 140. For example, if the user 140 logs in with the same ID even though he / she inputs a search word related to the animal in the computer X used by the user at home and a search word related to the real estate in the computer Y used in the company, The same advertisement can be exposed.

In addition, in another embodiment, the individual ad platform 210 may include not only the search term entered by the user 140, but also the matched ad, as well as a search term associated with the item purchased by the user, an ad associated with the search term, The management table 211 may be generated using a related search word or the like. That is, a search term reflecting the user's interest can be obtained through all the methods that can extract the search term related to the activity of the user 140. In other words, the search term used to reflect the interests of the user 140 is not limited to the search term entered through the publisher 130.

On the other hand, the individual advertisement platform 210 can register the advertisement from the advertiser 110 before generating the management table 211. In one example, the individual ad platform 210 may provide a number of sellable ad inventory for the search terms entered by the users 140. The individual ad platform 210 may calculate information about an advertisement product that is sold to the advertiser 110 based on a usage log at the publisher 130 to which the user is connected. For example, with respect to a CPM (Cost Per Mill) fee-based product, the individual advertisement platform 210 can provide information such as the number of predicted impressions for each search word to an advertiser who purchases the advertisement.

At this time, the advertisement system 200 can predict the predicted number of impressions for each keyword as an inventory. In one embodiment, when n search terms are input per user, the advertisement system 200 can predict the maximum value of the inventory for a specific search term by using the probability (or ratio) that a specific search word is included in the input n search terms have. At this time, the probability that a specific search word is included may refer to a probability that the search word input from one user is the query word A requested by the advertiser B when the advertiser B requests (purchases) the search word A.

For example, the probability that the search word A is included in the input n search terms per user can be calculated as shown in Equation 1 below.

Here, "QC" may mean a query count indicating the number of searches. In other words, the "QC proportion of query word A" may be a weight of the total number of searches performed by users using the query word A for a predetermined unit period. In addition, "n" may mean the number of search terms input per user, that is, the number of search words to be entered per UV (Unique Visit), for a certain unit period. For example, "n" can be calculated as a ratio to the total number of UVs of the inputted search term for a certain unit period.

At this time, the advertisement system 200 can predict the inventory for each search term by using UV as well as the probability (or rate) of inclusion of a specific search term. Some of the variables used herein may be measured for all advertising units, but may be measured for specific advertising units. Here, the advertisement unit can be classified according to a service such as a blog, a cafe, a knowledge search, and the like. For example, the above-described UV or PV (page view) to be described later may use UV or PV generated in the entire advertisement unit, but it may be used to measure the inventory by advertisement unit have. That is, the UV used by the advertisement system 200 for predicting the inventory for each search word may also mean the UV of the corresponding advertisement unit among the UVs measured for each advertisement unit and for each advertisement unit to predict the inventory for each search word.

For example, the advertisement system 200 can predict the inventory of query A as shown in Equation 2 below.

That is, when n search terms per user are input, the probability (or ratio) that a specific search word is included in the input n search words and the number of times that the total user is expected to input the search word A through UV multiplication operation Inventory can be predicted.

FIG. 3 is a diagram illustrating an example of estimating the number of search terms entered per user and the inventory through UV in one embodiment of the present invention. The first arrow 310 may indicate the number of search terms input for a certain unit period per user. In the example of FIG. 3, it is assumed that 60 search words are inputted per user for 7 days. Also, the second arrow 320 may mean UV in a particular ad unit. In the example of FIG. 3, it is assumed that 11,158,929 UVs occurred in a specific advertisement unit.

In this case, the rectangles may each mean one search word, and the circles may mean one UV. Assuming that the average QC generated for the query A corresponding to the specific quadrilateral 330 is 637,484 and the total QC is 814,089,033, the QC proportion of the query A is 0.078% (0.0078 = (637,484 / 814,089,033) , Rounded to the fifth decimal place). In this case, when n search terms are inputted per one user, the probability (or the ratio) that the search word A is included in the inputted n search terms, in a different expression, and when the advertiser B requests (purchases) the search word A, The probability that the search term is the query term A requested by the advertiser B is 4.6% (Equation 1 = 0046 = 1 - the probability that the 60 query words of the corresponding UV are not the query word A = 1 - (1 - 0.078%) ⁶⁰ ) Can be calculated. Here, the corresponding UV may mean the UV of the specific circle 340 corresponding to the specific rectangle 330.

Further, the UV of the specific advertisement unit and the query of the query A can be calculated as 502,112 (11,158,929 * 4.6%) through the equation (2).

At this time, the predicted inventory according to Equation (2) includes the assumption that each user inputs one search word only once for a predetermined unit period. However, in reality, users may need to reflect this redundant input because they can enter a query multiple times during a certain period of time.

At this time, as described above, the advertisements are provided using the management table 211 in which the interests of the users are reflected. Accordingly, in the case of providing the advertisement considering only the interests of users without any limitation, some specific advertisements may be provided to the users excessively and repeatedly.

Accordingly, the advertisement system 200 may introduce a frequency cap to limit the number of times the targeted advertisement is exposed. Here, the exposure limit is to limit exposure of the same advertisement to each user N times or more. In addition, the advertisement system 200 may further introduce an interval cap to limit the period of time during which the targeted advertisement is repeatedly exposed. Here, the exposure interval is for controlling the interval between exposures of the same advertisement within the exposure limit.

First, the ratio of PV to UV can be considered to reflect the redundant input. Here, PV may mean the number of hits of users. That is, the ratio of PV to UV may mean the number of hits per user, which may mean an average value of the number of times that a user can repeatedly input a specific search word at the maximum. However, as described above, when the ratio of this PV to UV is directly reflected in Equation (2), there is a possibility that some specific advertisements will be provided to the users excessively repeatedly. For example, if the ratio of PV to UV is 5, and user 140 enters query A 5 times, then 5 identical advertisements may be exposed to user 140, depending on the situation.

Accordingly, the advertisement system 200 may introduce an exposure limit for limiting the number of times of exposure of the same advertisement to a predetermined number of times or less so that one user is not repeatedly exposed to the same advertisement material N times or more. For example, Equation 2 for calculating the inventory of query A can be modified as shown in Equation 3 below.

Referring again to FIG. 3, the ratio of PV to UV is 12.4 (138,571,753 / 11,158,929), assuming that the PV of the specific ad unit is 138,571,753 and the exposure limit is 3, The value according to the function is 3. Therefore, the inventory of the query A according to Equation (3) can be calculated as 1,506,336 (502,112 * 3).

4 is an example showing the amount of inventory as the length of an arrow in an embodiment of the present invention. The second arrow 320 may refer to the UV in the particular ad unit described with reference to FIG. In the example of FIG. 4, it is assumed that 11,158,929 UVs are generated in a specific advertisement unit as in FIG.

The third arrow 410 is a combination of three arrows of the same length as the second arrow 320, with a length corresponding to three times the length of the second arrow 320, Indicating that the inventory can be predicted. That is, the fourth arrow 420 may indicate the amount of inventory to which the exposure limit is applied for the entire search term with the same length as the third arrow 410. Herein, the entire search term may refer to search terms input for a predetermined unit period in the corresponding advertisement unit. In the example of FIG. 4, the inventory according to the fourth arrow 420 may have a value of 33,476,787 (UV * 3).

In addition, the fifth arrow 430 may indicate the PV of the corresponding advertisement unit. In the example of FIG. 4, the PV according to the fifth arrow 430 is assumed to be 138,571,753. That is, the above-described exposure limit 3, rather than the ratio of PV to UV according to the "min ()" function shown in Equation 3, can be used for inventory prediction with a ratio of PV to UV of 12.4 (138,571,753 / 11,158,929) .

The sixth arrow 440 may indicate the amount of inventory available to the advertiser B at 1,506,336 when the QC portion of the query A requested by the advertiser B is 0.012% and n is 60.

The seventh arrow 450 indicates that the amount of inventory available to the advertiser C is 815,632 ((1 - (1 - 0.042%) ⁶⁰ ) * UV when the QC portion of the query B requested by the advertiser C is 0.042% * 3).

However, the sixth arrow 440 and the seventh arrow 450 only indicate the amount of available inventory when different advertisers B and C request different search terms A and B, and each advertiser requests a plurality of search terms And search queries that request each other may be duplicated. Thus, if a particular advertiser first buys all or part of the inventory for a particular search term, then the amount of inventory available for sale to other advertisers may be limited.

In order to calculate the amount of inventory for a plurality of search terms (hereinafter referred to as 'request query') when the advertiser requests a plurality of search terms, Equation (3) may be expressed as Equation (4) below.

The value of "f _inventory (query word A) + f _inventory (query word B)" may be defined as the value of "f _inventory (query A) + f _inventory (query B) f _inventory "has a value greater than the value of which" (term a + query B) f _inventory (term a + query B) "case, due to the interference between search terms occur, where" Keywords a + queries B Quot; can be used to calculate the amount of inventory for the mathematical expressions A and B as "the QC proportion of the query term A + the QC proportion of the query term B" as the " Hereafter, for convenience of explanation, "f _inventory (query word A)" is described as "f _inventory (A)" and "f _inventory (query word A + query word B)" is indicated as "f _inventory .

In this case, the sixth arrow 440 indicates the amount of inventory that can be sold to the advertiser B, 1,506,336, when the QC portion of the requested query term requested by the advertiser B is 0.012% and n is 60, and the advertiser C represents the requested query word of the advertiser B The amount of inventory available to the advertiser C may be different from the amount of the inventory indicated by the seventh arrow 450. In this case, For example, an eighth arrow 461 in the dashed box 460 may indicate the amount of inventory 2,280,410 calculated using the QC portion of the requested query term of Advertiser B and the QC portion of the requested query term of Advertiser C .

That is, when the advertiser B purchases the full amount of the first available sales amount 1,506,336, the amount of inventory that can be sold to the advertiser C is determined by the length of the eighth arrow 461 and the length of the eighth arrow 440 ) Can be calculated as follows.

In this way, when calculating the amount of available sales to advertisers, it is possible to eliminate the influence of interference between the search terms by considering a search term (hereinafter referred to as 'pre-sold search term') already sold on the inventory.

2, the advertisement system 200 calculates the amount of inventory that can be sold to the advertiser 110 based on the QC portion and the sales amount of the query term of the advertiser 110, the QC portion of the sales term, . For example, the advertisement system 200 may calculate the amount of inventory available for sale for the requested query as shown in Equation (5) below.

Here, the "f _inventory ()" function has already been described by Equation (4). Hereinafter, for convenience of explanation, sales amounts of the search terms A, B, and C are expressed as a sales amount (ABC).

Tables 2 to 5 below illustrate an example of managing an inventory for a search term, and indicate search terms, available sales amount, sales amount, and remaining amount for each search word.

First, when the advertiser 'A' queries the amount of available sales of the search terms A and B at the time of initial booking, the advertisement system 200 calculates' f _inventory (AB) = 4400 (assumption, 4400 <1000 + 4000) To the advertiser 'A'. The sellable inventory should be calculated using Equation (5), but Equation (5) is the same as Equation (4) if there is no pre-sold search term.

Also, in the present specification, "bookkeeping" may mean a process of selling an inventory to an advertiser.

The advertisement system 200 can sell the inventory for each search term according to the remaining amount ratio of the search words when the advertiser A wants to purchase 3000 of the inventory 4400 of the search terms A and B. That is, according to the remaining amount ratio 1000: 4000 of the search words A and B shown in Table 1, it is possible to sell the inventory 600 of the keyword A and the inventory 2400 of the keyword B to the advertiser A. At this time, after some of the inventories of the search terms A and B are sold to the advertiser 'A', the remaining amounts of the search terms A and B may be 400 and 1600, respectively, as shown in Table 3.

At this time, if the advertiser '' is requested to add ',' advertiser ',' the amount of available inventory of the search terms B, C, and D is inquired, the advertisement system 200 calculates the available sales inventory and provides the advertiser ' .

That is, the advertisement system 200 can calculate the sellable inventory using Equation (5). Here, it is assumed that "f _inventory (ABCD) = 6400 (<1000 + 4000 + 1500 + 2000)" and "f _inventory (BCD) = 5500 (<4000 + 1500 + 2000)". The available inventory is "min (6400 - 3000, 5500 - 2400)" because "Sales volume (ABCD)" is 3000 (see sales volume of queries A and B) and "Sales volume (BCD)" is 2400 = min (3400, 3100) = 3100 &quot;.

At this time, assuming that the advertiser 'purchases' all the available inventory 3100, Table 3 can be modified as shown in Table 4. Even in this case, the sales volume ratio can be determined according to the remaining amount ratios of the respective search words.

If another additional booking occurs for the advertiser 'bottle' requesting the query E, the advertisement system 200 may use the equation (5) to provide the sellable inventory to the advertiser 'bottle'.

In other words, the advertisement system 200 calculates "f inventory (ABCDE) = 7500", "f inventory (E) = 3000", "sales volume (ABCDE) = 6100" Quot; min (7500 - 6100, 3000 - 0) = min (1400, 3000) = 1400 " At this time, assuming that the advertiser 'bottle' purchases all of the sellable inventory 1400, Table 4 can be modified as shown in Table 5 below.

FIG. 5 is a diagram illustrating an example of an inventory according to a search term and an entire inventory in an embodiment of the present invention. FIG. First, "KWD" and "INV" shown in FIG. At this time, inventory by search term can be predicted as "f Inventory (A)", "f Inventory (B)", "f Inventory (C)", ..., "f Inventory (Z)", Can be calculated as "f inventory (ABC ... Z) ". At this time, the total inventory has a smaller value than the sum of the inventory per search word because it takes into consideration the overlapping factor between the search terms.

Again, referring back to FIG. 2, the advertisement system 200 may further introduce an interval cap to limit the time period over which the targeted advertisement is repeatedly exposed, as described above. FIG. 6 is a graph illustrating the number of users who are repeatedly exposed to the same advertisement material according to an exemplary embodiment of the present invention. In the graph 600, the x-axis represents the number of times the same advertisement material is exposed repeatedly, and the y-axis represents the number of users. That is, as shown in the graph 600, the proportion of the users who are overlapped with N + 1 times of the users whose overlapping exposure of the same advertisement material is N times is represented as "about 80% ". Therefore, the effect of the depreciation of the inventory can be calculated, for example, as the sum of the equilibrium series as shown in Equation (6) below.

Here, 'S (n)' may be the sum of the isoquency series, 'r' may be the ratio of the users who are exposed repeatedly N + 1 times, and 'a' may be the value of the first term of the isometric sequence. For example, if you assign r = 0.8, n = 10 and a = 1, then S (n) can have a value of 4.46, conservatively equals 4, It can be used as a coefficient.

At this time, when such an amortization coefficient is considered, the above Equation (4) can be modified as shown in Equation (7) below.

For example, the quantity 1,506,336 (502,112 * 3) of the query term A according to the equation (3) described in conjunction with FIG. 3 can be estimated as 6,025,344 (502,112 * 3 * 4) according to equation (7).

7 is a block diagram for explaining an internal configuration of an advertisement system in an embodiment of the present invention. The advertisement system 700 according to the present embodiment manages an inventory of search terms that can be sold by using search terms input during a past unit period in an advertisement product whose sales are determined based on the number of impressions of the advertisement. 7, the advertisement system 700 may include a probability calculation unit 710, an inventory predicting unit 720, and a sellable inventory determination unit 730.

The probability calculation unit 710 calculates the probability that the request word is included in the query words input by the user during the unit period, using the query term input during the past unit period. At this time, the probability calculation unit 710 calculates a ratio of the number of search occurrences occurred during the past unit period to the total number of search occurrences in the past unit period, and the number of search words inputted per user during the past unit period, Probability can be calculated. For example, the probability calculator 710 may calculate the probability that the requested query will be included using Equation (1). Since a case where a plurality of request words are included is also explained using Equation (4), repetitive description will be omitted.

The inventory predicting unit 720 predicts the inventory of the requested query using the calculated probability. First, in a first embodiment, the inventory predicting unit 720 can predict the inventory of the requested search term using the calculated probability and the number of search terms input per user for the past unit period.

In a second embodiment, the inventory predicting unit 720 can predict the inventory of the requested search term using the calculated probability, the number of search terms input per user per unit period in the past, and the exposure limit. At this time, the exposure limit may include the number of times that the same advertisement is allowed to be repeatedly exposed to the user. For example, the exposure limit can be determined by the ratio of the PV to the UV and the predetermined value, whichever is smaller.

In the third embodiment, the inventory predicting unit 730 can predict the inventory of the requested search term using the calculated probability, the number of search terms input per user per unit period in the past, the exposure limit, and the depreciation coefficient. At this time, the amortization coefficient may be calculated using the sum of the isoquency series for the user who decreases with a certain probability as the number of exposures of the same advertisement material increases.

For a concrete method of predicting the inventory of the requested query according to each embodiment, the description of Equations (2) through (4) and (7) can be referred to.

The sellable inventory determining unit 730 can determine the sellable inventory for the requested query using the above-described probability and the sales volume of the pre-sold search term. For example, the sellable inventory determination unit 730 determines the ratio of the number of searches that occurred during the past unit period to the total number of searches that occurred during the past unit period, the request query, The salesable inventory for the requested search term can be determined using the sales amount of the search term, the proportion of the number of searches that occurred during the past unit period with respect to the requested search term, and the sales amount of the requested search term. Since the method of determining the sellable inventory is described in detail with reference to FIG. 5, repetitive description will be omitted.

8 is a flowchart illustrating an advertising method in an embodiment of the present invention. The advertisement method according to the present embodiment can be performed by the advertisement system 700 described with reference to FIG. 8, a description will be made of an advertising method according to an embodiment of the present invention by explaining a process in which each step is performed by the advertisement system 700. FIG.

In step 810, the advertisement system 700 calculates the probability that the request word is included in the search terms input by the user during the unit period, using the search term input during the past unit period. At this time, the advertisement system 700 uses the ratio of the number of searches made during the past unit period to the total number of searches occurring during the past unit period and the number of search words input per user during the past unit period, Can be calculated. For example, the advertisement system 700 may calculate the probability that the requested search word is included using Equation (1). Since a case where a plurality of request words are included is also explained using Equation (4), repetitive description will be omitted.

At step 820, the advertisement system 700 predicts the inventory of the requested query using the computed probability. First, in a first embodiment, the advertisement system 700 can predict the inventory of the requested query using the calculated probability and the number of search terms input per user for the past unit period.

In a second embodiment, the advertisement system 700 may estimate the inventory of the requested query using the calculated probability, the number of search terms entered per user per unit period in the past, and the exposure limit. At this time, the exposure limit may include the number of times that the same advertisement is allowed to be repeatedly exposed to the user. For example, the exposure limit can be determined by the ratio of the PV to the UV and the predetermined value, whichever is smaller.

In a third embodiment, the advertisement system 700 may estimate the inventory of the requested query using the calculated probability, the number of search terms entered per user per unit period in the past, the exposure limit, and the depreciation coefficient. At this time, the amortization coefficient may be calculated using the sum of the isoquency series for the user who decreases with a certain probability as the number of exposures of the same advertisement material increases.

For a concrete method of predicting the inventory of the requested query according to each embodiment, the description of Equations (2) through (4) and (7) can be referred to.

In step 830, the advertisement system 700 can determine the sellable inventory for the requested query using the above-described probability and the sales amount of the pre-sold search term. For example, the advertisement system 700 may calculate the ratio of the number of searches made during the past unit period to the total number of searches that occurred during the past unit period, the sales amount of the query term The salesable inventory for the requested search term can be determined using the proportion of the number of searches that occurred during the past unit period to the total number of searches that occurred during the past unit period and the sales volume of the requested query. Since the method of determining the sellable inventory is described in detail with reference to FIG. 5, repetitive description will be omitted.

9 is a block diagram for explaining an internal configuration of an advertisement system in another embodiment of the present invention. The advertisement system 900 according to the present embodiment can manage the search term using the input search term during the past unit period. That is, unlike the advertisement system 700 described with reference to FIG. 7, the advertisement system 900 can determine the number of predicted inputs rather than the inventory. Here, the number of predicted inputs may mean the number of times a specific search word is input during a unit period. That is, the advertisement system 900 can be used not only for an advertisement product whose sales are determined based on the number of impressions of the advertisement but also for determining the number of predicted inputs of a specific keyword even in a CPC (Cost Per Click) advertisement method. To this end, the advertisement system 900 includes a probability calculation unit 910 and a predicted input number determination unit 920 as shown in FIG.

The probability calculation unit 910 calculates the probability that the request word is included in the search terms input by the user during the unit period, using the search term input during the past unit period. At this time, the probability calculator 910 calculates the probability of the search query using the ratio of the number of searches made during the past unit period to the total number of searches occurring during the past unit period and the number of search words input per user during the past unit period Probability can be calculated. For example, the probability calculator 910 may calculate the probability that the requested search word is included using Equation (1). Since a case where a plurality of request words are included is also explained using Equation (4), repetitive description will be omitted.

The predictive input number determination unit 920 determines the predictive input number of a specific search term using the calculated probability. First, in the first embodiment, the predictive input number determination unit 920 can determine the predicted input number of a specific search term using the calculated probability and the number of search terms input per user for the past unit period. For example, the predictive input number determination unit 920 can determine the result calculated using Equation (2) as the predicted input number.

In the second embodiment, the predictive input number determiner 920 can determine the number of predicted inputs of a specific search term using the calculated probability, the number of search terms input per user per unit period in the past, and the exposure limit. At this time, the exposure limit may include the number of times that the same advertisement is allowed to be repeatedly exposed to the user. For example, the exposure limit can be determined by the ratio of the PV to the UV and the predetermined value, whichever is smaller. For example, the predictive input number determination unit 920 can determine the result calculated using Equation (3) or Equation (4) as the predicted input number.

In the third embodiment, the predictive input number determination unit 920 can determine the number of predicted inputs of a specific search term using the calculated probability, the number of search terms input per user per unit period in the past, the exposure limit, and the depreciation coefficient . At this time, the amortization coefficient may be calculated using the sum of the isoquency series for the user who decreases with a certain probability as the number of exposures of the same advertisement material increases. For example, the predictive input number determination unit 920 can determine a result calculated using Equation (7) as a predictive input number.

10 is a flowchart illustrating an advertising method in another embodiment of the present invention. The advertisement method according to the present embodiment can be performed through the advertisement system 900 described with reference to FIG. 10, a description will be made of an advertising method according to another embodiment of the present invention by explaining a process in which each step is performed through the advertisement system 900. FIG.

In step 1010, the advertisement system 900 calculates the probability that the request word is included in the search words input by the user during the unit period, using the search word input during the past unit period. At this time, the advertisement system 900 uses the ratio of the number of searches made during the past unit period to the total number of searches occurring during the past unit period and the number of search words input per user during the past unit period, Can be calculated. For example, the advertisement system 900 may calculate the probability that the requested query is included using Equation (1). Since a case where a plurality of request words are included is also explained using Equation (4), repetitive description will be omitted.

At step 1010, the advertising system 900 determines the number of predicted inputs of a particular search term using the computed probability. First, in a first embodiment, the advertisement system 900 can determine the number of predicted inputs of a specific search term using the calculated probability and the number of search terms input per user for the past unit period. For example, the advertisement system 900 can determine the result calculated using Equation (2) as the predicted input number.

In a second embodiment, the advertisement system 900 may determine the number of predicted inputs of a particular search term using the calculated probability, the number of search terms entered per user per unit period in the past, and the exposure limit. At this time, the exposure limit may include the number of times that the same advertisement is allowed to be repeatedly exposed to the user. For example, the exposure limit can be determined by the ratio of the PV to the UV and the predetermined value, whichever is smaller. For example, the advertisement system 900 can determine the result calculated using Equation (3) or Equation (4) as the predicted input number.

In a third embodiment, the advertisement system 900 may determine the number of predicted inputs of a particular search term using the calculated probability, the number of search terms entered per user per unit period in the past, the exposure limit, and the depreciation coefficient. At this time, the amortization coefficient may be calculated using the sum of the isoquency series for the user, which decreases with a certain probability as the number of exposures of the same advertisement material increases. For example, the advertisement system 900 can determine the result calculated using Equation (7) as a predicted input number.

As described above, according to the embodiments of the present invention, it is possible to maximize the advertisement effect by providing the advertisement related to the user's interest based on the search word input by the user, It is possible to predict an inventory of searchable search terms by using a probability that a request word is included in the search terms input by the user for a unit period. In addition, an advertisement related to a user's interest can be provided based on a search word input by a user, and an inventory can be managed by controlling an exposure limit and an exposure interval.

In addition, in providing the advertisement related to the user's interest based on the search word input by the user, the user can determine the number of predicted inputs of the specific search word by using the probability that the request word is included in the search words input during the unit period have.

The methods according to embodiments of the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software. Furthermore, the above-described file system can be recorded on a computer-readable recording medium.

While the invention has been shown and described with reference to certain preferred embodiments thereof, it will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. This is possible.

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

200: Advertising system
210: Individual ad platforms
211: Management table

Claims (16)

An advertisement system for managing an inventory of searchable search terms using search terms input during a past unit period in an advertisement product whose sales are determined based on the number of impressions of the advertisement,
A probability calculation unit for calculating a probability that a request term is included in a search term input by a user during a unit period using a search term input during the past unit period; And
An inventory prediction unit for predicting an inventory of the request query using the calculated probability,
Lt; / RTI &gt;
The inventory forecasting unit predicts,
Estimating an inventory of the requested search word using the calculated probability, the number of search terms entered per user per unit period and the exposure limit in the past unit period,
Wherein the exposure limit includes the number of times that the same creative is allowed to be over exposed to the user. The method according to claim 1,
The probability calculator calculates,
The probability is calculated using the ratio of the number of searches made during the past unit period to the total number of searches occurring during the past unit period and the number of search words input per user during the past unit period with respect to the request query , Advertising system. delete delete The method according to claim 1,
Wherein the exposure limit is determined by a ratio of the PV (Page View) to UV (Unique Visit) and a predetermined value, whichever is smaller. An advertisement system for managing an inventory of searchable search terms using search terms input during a past unit period in an advertisement product whose sales are determined based on the number of impressions of the advertisement,
A probability calculation unit for calculating a probability that a request term is included in a search term input by a user during a unit period using a search term input during the past unit period; And
An inventory prediction unit for predicting an inventory of the request query using the calculated probability,
Lt; / RTI &gt;
The inventory forecasting unit predicts,
Estimating an inventory of the requested query using the calculated probability, the number of search terms entered per user per unit period, the exposure limit, and the depreciation coefficient,
Wherein the amortization coefficient is calculated using a sum of isoquency series for users whose probability decreases as the number of exposures of the same advertisement material increases. An advertisement system for managing an inventory of searchable search terms using search terms input during a past unit period in an advertisement product whose sales are determined based on the number of impressions of the advertisement,
A probability calculation unit for calculating a probability that a request term is included in a search term input by a user during a unit period using a search term input during the past unit period;
An inventory predicting unit for predicting an inventory of the request term using the calculated probability; And
Determining a sellable inventory for the request term by using the probability and the sales amount of the term that has been sold,
The advertising system. 8. The method of claim 7,
Wherein the sellable inventory determination unit comprises:
A ratio of the number of searches made during the past unit period to the total number of searches that occurred during the past unit period, the sales amount of the requested query, the sales amount of the pre-sold query, Wherein the salesable inventory for the requested search term is determined using the proportion of the number of searches made during the past unit period to the total number of searches occurring during the past unit period and the sales volume of the requested query. An advertisement system for managing a search term using a search term input during a past unit period,
A probability calculation unit for calculating a probability that a specific search word is included in the search words input by the user during a unit period using a search word input during the past unit period; And
A predicted input number determining unit for determining a predicted input number of the specific search word using the calculated probability,
Lt; / RTI &gt;
Wherein the predictive input number determination unit comprises:
Determining the number of predicted inputs of the specific search term using the calculated probability, the number of search terms input per user per unit period and the exposure limit in the past unit period,
Wherein the exposure limit includes the number of times that the same creative is allowed to be over exposed to the user. 10. The method of claim 9,
The probability calculator calculates,
The probability is calculated using the ratio of the number of searches made during the past unit period to the total number of searches occurring during the past unit period and the number of search words entered per user during the past unit period with respect to the specific search term , Advertising system. delete delete An advertisement system for managing a search term using a search term input during a past unit period,
A probability calculation unit for calculating a probability that a specific search word is included in the search words input by the user during a unit period using a search word input during the past unit period; And
A predicted input number determining unit for determining a predicted input number of the specific search word using the calculated probability,
Lt; / RTI &gt;
Wherein the predictive input number determination unit comprises:
Determining the number of predicted inputs of the specific search term using the calculated probability, the number of search terms input per user per unit period, the exposure limit, and the depreciation coefficient,
Wherein the amortization coefficient is calculated using a sum of isoquency series for users whose probability decreases as the number of exposures of the same advertisement material increases. An advertisement method for managing an inventory of searchable search terms using search terms input during a past unit period in an advertisement product whose sales are determined based on the number of impressions of the advertisement,
Calculating a probability that a request word is included in a search term input by a user during a unit period using a search term input during the past unit period; And
Estimating a sellable inventory of the request term using the calculated probability
Lt; / RTI &gt;
Wherein the step of predicting the sellable inventory of the request query comprises:
Estimating an inventory of the requested search word using the calculated probability, the number of search terms entered per user per unit period and the exposure limit in the past unit period,
Wherein the exposure limit includes a number of times that the same advertisement material is allowed to be repeatedly exposed to the user. An advertisement method for managing a search term using a search term input during a past unit period,
Calculating a probability that a specific search word is included in the search terms input by the user during a unit period using a search word input during the past unit period; And
Determining the number of predicted inputs of the specific search term using the calculated probability
Lt; / RTI &gt;
Wherein the step of determining the number of predicted inputs of the specific search term comprises:
Determining the number of predicted inputs of the specific search term using the calculated probability, the number of search terms input per user per unit period and the exposure limit in the past unit period,
Wherein the exposure limit includes a number of times that the same advertisement material is allowed to be repeatedly exposed to the user. A computer-readable recording medium recording a program for performing the method of any one of claims 14 to 15.

Images