KR100666202B1 - Method for providing a search service and system for executing the method - Google Patents

Abstract

A method for offering a search service and a search system for executing the same are provided to guarantee a quality of the search result offered to each keyword AD(ADvertisement) service by selecting the search result based on a bidding price and an ACR(Average Click Rate) of the search result. A database manager(303) maintains a search result database(301) storing a keyword, the search result associated with the keyword, and the bidding price, a total click number, the ACR, and an advertiser ID associated with the search result. An exposure index calculator(302) calculates the ACR of each past period based on a current time point of each search result, and calculates an exposure index for each search result based on the ACR and the bidding price. The database manager updates the calculated exposure index to the search result database. A search result selector(305) selects the specific number of search results having high ranked ACR among the search results associated with the keyword in case that a search request including the keyword is received from a user through a user input part(304).

Description

Method for Providing A Search Service And System For Executing The Method}

1 is a diagram illustrating a network connection of a search system according to the present invention.

2 is a flowchart illustrating a search service providing method according to an embodiment of the present invention.

3 is a block diagram illustrating a search system according to another exemplary embodiment of the present invention.

4 is a diagram illustrating a process of constructing a search result database according to one embodiment of the present invention.

5 is a diagram illustrating an example of a data structure included in a search result database adopted according to an embodiment of the present invention.

FIG. 6 is a table illustrating a click rate for a predetermined search result on a daily basis with respect to a search result associated with the predetermined search word.

FIG. 7 is a diagram showing an example of an exposure index, a bid, an advertisement execution amount, and a registration time of a search result for a predetermined search result to explain the present invention.

8 is a diagram illustrating a table used to explain a process of calculating a unit advertisement cost associated with a selected search result according to one embodiment of the present invention.

9 is an internal block diagram of a general purpose computer device that may be employed to perform a method of providing a search service according to the present invention.

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

300: search system

301: search result database 302: exposure index calculator

303: database management unit 304: user input unit

305: search result selection unit 306: search result list providing unit

307: billing

The present invention relates to a method of providing a search service and a search system for performing the method, and more particularly, to select a search result based on an impression index reflecting an average clickthrough rate (CTR) and a bid of each search result, The present invention relates to a method of calculating the unit advertisement cost of each search result using the lowest exposure index among the exposure index, and a search system for performing the method.

A search system that provides a recent search service does not merely provide search results in response to a user's search request, but in return for providing the search results to the user, or in return for selecting the provided search results, The so-called "keyword advertising service" for charging a predetermined advertising fee is simultaneously provided to the advertiser who registered the search results.

However, in order to generate a predetermined advertising effect by exposing a search result of an advertiser to a user, the user recognizes the search result or selects the search result and links to a web page related to the advertiser. The search results may be arranged in a position and a form that can be easily recognized by the user in a search result page.

As the type of information searchable on the Internet is enormous, the number of search results provided in response to a user's search request increases. Accordingly, only a list of search results according to the search request, which is several to tens of pages on the web page, can be found. Cases also occur frequently. Thus, the advertiser wants his search results to be provided in a more distinctive form, above the list of search results. Hereinafter, the list of search results provided above or in a characteristic form according to the keyword advertisement service is referred to as a "search result list".

However, when a plurality of search results registered for a keyword advertisement exist for a predetermined search word, it is impossible or inappropriate to arrange the plurality of search results all at the top or provide a characteristic form. Therefore, the search system must perform a process of selecting a search result included in a search result list by the keyword advertisement service among search results registered for the search word.

The search system disclosed in Korean Laid-Open Patent Publication No. 2002-0019042 discloses a configuration in which, when providing a keyword advertising service, the search results are sorted according to a bid registered by an advertiser and provided to a user with a search request. That is, the search system is provided to the user in the form that the search results with a high bid is located above the other search results. That is, according to the related art, a search system providing a keyword advertisement service selects search results included in a search result list based on a bid.

On the other hand, in a search system that does not provide a keyword advertising service, a configuration that selects and provides a search word requested by a user and a search result to be provided corresponding to the search request in order of relevance or preference.

Various methods are known for measuring the relevance or preference between a search term and a search result or information provided in connection with the search result, and one of them is how many times a user selects a given search result according to a search request. How to measure depending on whether or not. That is, the search results that are frequently selected by the users may be regarded as having high relevance or preference with respect to the search word.

However, such relevance or preference is a factor that is difficult to be introduced in a keyword advertising service that charges an advertisement fee to an advertiser in return for being included in a search result list and provided to a user. Accordingly, the search system according to the related art is a keyword advertising service. In the case of providing the search result, the search result included in the search result list provided according to the keyword advertising service was inevitably selected depending on the bid.

However, when a search result provided in a search result list included in the search result does not correspond to information desired by the user or does not provide sufficient information, the user may search for a search system that provides a search service. There is a risk of their credibility being lowered.

Accordingly, NHN Co., Ltd., which is the applicant of the present invention and provides a search service including a keyword advertisement service on a web page naver (www.naver.com), selects a search result as well as a bid, that is, a predetermined A method of selecting a search result included in a search result list is further considered in consideration of the "click rate" which is the ratio of the number of times a search result is provided to users and the number of times the user selects the provided search result.

However, as a result of an applicant using an extensive database accumulated in the process of providing a keyword advertising service on the web page, if the click rate is used as it is in the process of selecting a search result, the search result included in the search result list is very high. It has been found that severe fluctuations can occur.

That is, since the clickthrough rate is determined by the user's choice, the volatility is greater by time of day, time of year, social issue, or for no specific reason, compared to the bid, and some search results are selected during this cycle. Unlike the prior art in which only bids are considered, such as not selected in the next cycle, it is difficult to predict which search results are included in the search result list.

If you don't solve this problem, advertisers can't predict how their search results will be selected by adjusting their bids, making it difficult for them to decide how much they should bid, and users will receive different results each time they search. It will be difficult to find the search results again.

Accordingly, in order to select a search result included in a search result list, the applicant of the present invention combines a click rate to provide users with a bid corresponding to the purpose of the keyword advertising service and a search result recognized as being related to the search word. Reflecting the above, it has been developed a search service providing method and a search system for performing the method that can solve the problem that the search results included in the search result list is severely changed according to the change in the click rate.

Meanwhile, the method of providing a keyword advertisement service according to the related art does not involve at all about whether the search result registered by the advertiser includes faithful content corresponding to the corresponding search request, or the administrator manually sets the content of the search result. I was staying at the degree to check. Accordingly, the applicant of the present invention has attempted to develop a search system that can automatically induce the advertiser to improve the quality of the search results provided by the keyword advertising service.

The present invention has been made to improve the prior art as described above, and provides a search service providing method and a search system that can select a search result in consideration of the bid associated with the search results, the average click rate calculated for the search results together It aims to provide.

In addition, the present invention is to provide a search service providing method and a search system that can ensure the quality of the search results provided by the keyword advertising service by selecting the search results based on the bid and the average click rate for another object do.

In particular, the present invention calculates the unit advertising cost in inverse proportion to the average clickthrough rate associated with each search result, so that advertisers who provide good search results are charged a lower unit advertising cost, so that the advertisers themselves can improve the quality of their search results. It is another object of the present invention to provide a search service providing method and a search system that can be induced to improve.

In addition, another object of the present invention is to provide a search service providing method and a search system that allow an advertiser to predict which search results may be selected by selecting a search result using an average click rate having a smaller variation than a click rate. It is done.

In addition, the present invention can be difficult to treat the average clickthrough rate as valid data because the search results are not sufficiently provided to the user during the current time from the registration time when the advertiser registers a predetermined search result, or the period from the time of registration to the current time Another object of the present invention is to provide a search service providing method and a search system for providing a criterion for determining whether to provide the search result to a user even when the average click rate is difficult to treat as valid data. .

In addition, the present invention determines the M value according to the number of inputs of the search word in order to calculate the average click rate, and calculates the average click rate by reflecting only the click rate during a unit period having the number of impressions (the number of times the search results are provided) equal to or greater than the M value. It is another object of the present invention to provide a search service providing method and a search system that can further ensure that the fluctuation range is small.

In order to achieve the above object and solve the above-mentioned problems of the prior art, the search service providing method according to the present invention, a search word, a search result associated with the search word, a bid associated with the search result, an exposure associated with the search result Maintaining a search results database including an index or an identifier of an advertiser associated with the search result, and calculating an average clickthrough rate, which is the average of clickthrough rates per unit period over a period of time, based on a current time point, for each of the search results (The clickthrough rate for each unit period is the number of times calculated for each unit period as the ratio of the number of impressions that are the number of times the search result is provided to the user and the number of clicks that are the number of times the user selects the provided search result.) Calculate impression indexes based on clickthrough rates and bids, Recording and updating in association with the search result in a base; selecting a predetermined number of search results among search results associated with the search word when receiving a search request including a predetermined search word from a user; Generating and providing a search result list including the search results of the search results to the user, selecting an exposure index having the smallest value among the exposure indices associated with the selected search result as the basic exposure index, the basic exposure index, Calculating a unit advertisement cost of each of the selected search results based on a ratio of the average clickthrough rate associated with the selected search result.

According to one aspect of the present invention, when the user selects any one of the search results included in the provided search result list, the step of charging the advertiser associated with the search results unit advertising costs associated with the selected search results It further includes.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram illustrating a network connection of a search system according to the present invention.

The search system 100 maintains a search result for each search term in a predetermined search result database, and when a search request for a search term is input from the user terminal 110, the search system 100 includes a search result list including search results corresponding to the search term. Transmit to terminal 110.

The user may input a search request to the search system 100 using the user terminal 110 and receive a list of search results in response to the search request. The user terminal 110 may include a code division multiplexing access (CDMA) module, a Bluetooth module, an infrared communication module (IrDA), a wired / wireless device such as a personal digital assistant (PDA), a smart phone, a handheld PC, a mobile phone, and the like. By providing a predetermined communication module such as a LAN card, a communication terminal capable of connecting to the search system 100 through a wired or wireless internet network is collectively referred to.

According to the present invention, the search system 100 searches for a plurality of searches corresponding to the search term according to an impression index calculated based on 1) a bid suggested by an advertiser for each search result of the search term, and 2) an average clickthrough rate. It decides which search results from among the results are provided or whether the search results are placed on the first screen of the search results web page. That is, the search result included in the search result list provided to the user is selected based on the bid and the average click rate.

In addition, the search system 100 according to the present invention has a predetermined number of times that the search result is less than a predetermined period from the time of registration to the present time, or the number of times the search result has been provided to users from the time of registration to the present time is a predetermined number of times. If less, the default click rate is used instead of the average click rate. That is, the search system 100 may determine whether to include the search result in the search result list according to the impression index calculated based on 1) the bid and 2) the basic clickthrough rate.

The bid means the maximum cost that the advertiser is willing to pay as an advertisement fee when the advertiser's search result is provided to the user in association with a predetermined search word and the user selects the search result. The specific meanings of the average click rate and the basic click rate will be described later in each embodiment.

In addition, the search system 100 according to the present invention, when the user provided with the search result list selects any one of the search results included in the search result list by a mouse click, the advertiser is registered with the selected search results. A certain advertising fee is charged. Hereinafter, the term "selection" used when the search system 100 selects a search result included in a search result list and a user who is provided with the search result list is included in the search result list. In order to distinguish the term "selection" used in selecting a result, in the latter case the term "click" may also be used. However, the division of these terms is purely for convenience of explanation, and the use of the term "click" is not limited to the case where the search results are selected by clicking on a search result.

In addition, the search system 100 according to the present invention employs a method of charging a predetermined unit advertising fee to the advertiser each time the search result is clicked. As described above, if the advertiser refers to the maximum cost that the advertiser can pay for one click, the unit advertisement cost means the cost actually paid by the advertiser when the search result is clicked once.

In addition, the search system 100 may allow the advertiser to deposit a predetermined advertising cost, and may adopt a method of deducting the advertising cost in real time or periodically whenever a click on the search result occurs. In particular, the search system 100 according to the present invention dynamically determines the unit advertisement cost associated with the selected search result every time a search result list is generated. A detailed configuration for determining a unit advertisement cost for a search result included in the search result list every time a search result list is generated will be described later.

Hereinafter, a search service providing method according to an embodiment of the present invention will be described with reference to FIG. 2. In addition, the search service providing method may be performed by the search system 300 shown in FIG. 3.

The search system 300 may include a search result database 301, an exposure index calculator 302, a database manager 303, a user input unit 304, a search result selector 305, a search result list provider 306, and The charging unit 307 is included.

In step 201 the search system 300 is associated with a search term, a search result associated with the search term, a bid associated with the search result, a total number of impressions associated with the search result, an impression index associated with the search result, or an associated search result. Maintain a search results database 301 that includes an advertiser identifier.

Referring to FIG. 4, the process of maintaining the search result database 301 will be described in more detail.

In operation 401, when the advertiser requests registration of a search result for a predetermined search word, the database manager 303 records the search result in the search result database 301 in association with the search word. In addition, the database manager 303 further records an advertiser identifier for identifying the advertiser and a bid provided by the advertiser in association with the search result in the search result database 301.

In operation 402, the exposure index calculator 302 calculates the total number of impressions from the registration time point to the current time point for each search result.

In the present specification, the term 'impressions' means a number of times a predetermined search result is provided to a user according to a keyword advertising service.

Generally, when the advertiser requests registration of a search result to be exposed to a predetermined search term in order to use the keyword advertisement service, the registration time is recorded by registering the search result in the search result database 301 according to the registration request. It means the time point. However, the timing of registration of the search result is not strictly determined, and the time point when the administrator who manages the search system 300 records in the search result database 301 from the time point at which the registration is requested by policy and actually becomes a target of the keyword advertising service. It may be determined at any point in between.

In addition, the search system 300 may calculate the total number of impressions in real time by increasing the total number of impressions by one each time the search result is exposed.

In addition, the search system 300 may periodically calculate the total number of impressions by adding the number of impressions increased for a predetermined period to the total number of impressions.

In operation 403, the database manager 303 records the calculated total impressions in the search result database 301 in association with the search result.

In step 404, the exposure index calculator 302 determines whether the calculated total impressions is greater than or equal to a predetermined number of confidence impressions.

As will be described later, the present invention calculates an exposure index for each search result, and determines whether to include the search result in the search result list based on the exposure index. For example, the search system 300 may generate a search result list including only a predetermined number of search results whose exposure index is higher.

In the present invention, the confidence impressions is a criterion for determining how to calculate an exposure index associated with the search result. That is, if the total number of impressions is greater than or equal to the confidence impressions, an exposure index for the search result is calculated by the first exposure index calculation method as described later, and if the total number of impressions is less than the confidence impressions, the second impression as described later An exposure index calculation method calculates an exposure index for the search result.

According to an embodiment of the present invention, the trusted impressions are determined differently for each search word. For example, the confidence impressions is determined as 100 for search results registered in connection with the search term "flower delivery", and the confidence impressions as 30 in search results registered in connection with the search term "patent". You can decide. As will be described later, since the trusted impressions play a role of a threshold value, the impressions are adaptively determined for each search word to calculate a more suitable exposure index. The impression index calculator 302 may compare the number of confidence impressions specified for the search word associated with the search result and the total number of impressions of the search result for each search result.

In addition, according to another embodiment of the present invention, the trusted impressions may be designated as an average of the number of inputs per unit period of the search word for a predetermined period based on the current time. For example, the predetermined period may be set to "last 30 days" and the unit period may be set to "1 day" based on the current time. The exposure index calculator 302 may calculate the average number of inputs per day for the last 30 days for each search word, and determine the calculated value as the number of confidence impressions. The number of inputs of a search word refers to the number of times a user inputs a search request including the search word to the search system 300.

If the total number of impressions is greater than or equal to the confidence exposure index, in operation 405, the exposure index calculator 302 calculates an exposure index associated with the search result according to the first exposure index calculation method.

In addition, when the total number of impressions is less than the confidence exposure index, in step 406, the exposure index calculator 302 calculates an exposure index associated with the search result according to the second exposure index calculation method. A detailed description of the first exposure index calculation method and the second exposure index calculation method will be described later.

In operation 407, the exposure index calculator 302 records the calculated exposure index in the search result database 301 in association with the search result.

In addition, the exposure index calculator 302 may recalculate and update the exposure index whenever the reason for the change of the exposure index occurs, or periodically calculate and update the exposure index again.

FIG. 5 shows an example of data recorded in the search result database 301 constructed by performing steps 401 to 407 as described above. The search result recorded in the search result database 301 is information provided to a user according to a search request, and may be used as information for providing a link to the web page including link information to a predetermined web page. have.

Hereinafter, a process of calculating an exposure index according to the first exposure index calculation method and a process of calculating an exposure index according to the second exposure index calculation method will be described in detail.

(1) When calculating the exposure index according to the first exposure index calculation method

The impression index calculator 302 calculates an average click rate for each of the search results when the total number of impressions of the search result is equal to or more than the trusted impressions. The average clickthrough rate is an average of clickthrough rates per unit period for a certain period in the past based on the current time. Hereinafter, a case in which the unit period is selected as one day will be described as an example. However, this is merely exemplary, and the unit period may be arbitrarily selected by the operator of the search system 300 in various manners such as 1 hour, 10 hours, 2 days, and so on.

CTR can be calculated by dividing clicks by impressions. The number of impressions means the number of times a predetermined search result is provided to the user according to the keyword advertisement search, and the number of clicks means the number of times the provided search result is selected by the user.

The average clickthrough rate may be calculated differently depending on how the predetermined period is selected. A process of calculating the average clickthrough rate will now be described with reference to FIG. 6.

1) When calculating the average clickthrough rate according to the first method

Table 1 of FIG. 6A illustrates a click rate of a predetermined search result on a daily basis, for a search result associated with a predetermined search word. For example, Table 1 calculates the daily clickthrough rate for the search result 501 in association with the search term "flower delivery."

The first method selects a continuous period of time in the past from the present time point as the above-mentioned constant period. Referring to Table 1, if the current point in time is October 10, 2004 at 10 o'clock, several consecutive days before the current point in time, for example, five days from 0 o'clock October 5, 2004 to 24 o'clock October 9, 2004 Consecutive periods of time can be determined as said constant period.

Therefore, from October 5, 2004 to October 9, 2004, the average click-through rate can be calculated by adding up the daily click-through rates and dividing by 5 days. Referring to Table 1, the average clickthrough rate for the search result 501 is as follows.

2) When the average clickthrough rate is calculated according to the second method

The second method selects the sum of predetermined N unit periods as the predetermined period. The N unit periods, that is, N days, may not be continuous unlike in the first method. According to the second method, the exposure index calculator 302 identifies N, for example, five, in a close order, based on the current time point, only on a unit period, i.e., the number of impressions for one day or more.

If the M value is 20, the days on which 20 or more impressions are input are indicated by hatching in Table 2 of FIG. 6B, respectively. For example, October 8, 2004, where 80 impressions were entered.

The exposure index calculator 302 may identify five past days in which 20 or more impressions have been input in the reverse order of the time flow, based on the current time point (10 October 31, 2004). The impression index calculator 302 may calculate the average click rate by adding up the click rates of the identified days and dividing by five. Referring to Table 2, the average clickthrough rate of the search result 501 is as follows.

Meanwhile, in the present embodiment, for the convenience of description, the average clickthrough rate for 5 days, which is a relatively short period, was calculated. However, the search system 300 determines how long the average clickthrough rate is to be calculated, that is, to select the predetermined period. ) Can be determined using empirical and statistical methods. For example, the exposure index calculator 302 may calculate the average clickthrough rate for the last 30 days based on the current time.

Further, according to another embodiment of the present invention, the M may be determined differently for each search word by reflecting the number of times the search word is input. The number of times the user inputs the search word, which is the number of times the user inputs the search word, may reflect the popularity of the search word. For example, the search system 300 calculates an average for each unit period of input times (that is, the number of times a search request is made while entering the search word), which is the number of times the search word has been input in the past based on a current time point. The M value may be selected in proportion to the average of each unit period. In order to distinguish between the predetermined period selected for calculating the average click rate and the predetermined period selected for calculating the average for each unit period of the number of inputs of the search word, the latter is referred to as a “second period”. The second period may be selected by an operator of the search system 300, and may be selected in consideration of the predetermined period (N days) selected to calculate the average clickthrough rate.

30 = 100으로 산출된다. For example, if the second period is set to 30 days, if the search term "flower delivery" has been input from the user in the last 30 days, a total of 3000 times, the average of the input period of the search term "flower delivery" per unit period (day) Silver 3000

Calculated as 30 = 100.

The exposure index calculator 302 may calculate the M value for each keyword in proportion to the daily average for 30 days of the number of times the keyword “flower delivery” is input. For example, M may be calculated as follows.

M = associated with the term "flower delivery"

5% of the daily average of the number of entries in 30 days for the query "flower delivery" =

100 × 20% = 20

That is, the exposure index calculator 302 may calculate the average clickthrough rate only on the days of 20 or more impressions per day for the search result associated with the search word “flower delivery”.

Meanwhile, in the above embodiment, 20% of the daily average is selected as the M, but how much of the daily average of the unit period during the predetermined period of each search term is reflected in the M value, such as 10% of the daily average is selected as M. Whether or not, the operator of the search system 300 can be determined statistically and empirically.

The average clickthrough rate calculated according to the first method or the second method is a factor used to calculate an exposure index of the search result as described below, and the exposure index includes the search result in a search result list to allow a user to It is used as a criterion to decide whether or not to provide it. In addition, as described above, the average clickthrough rate is set to "the number of impressions that are the number of times a user is provided with a search result in connection with a predetermined search term and the click rate that is the ratio of the number of clicks that the user clicks on a predetermined search result". As calculated on the basis of the results, the average clickthrough rate reflects the preferences of the users or the relevance between the search term and the search result. In addition, since the average clickthrough rate has a characteristic of a moving average of clickthrough rates for the last few days from the current time point, the average clickthrough rate calculated every time according to a predetermined search result has a smaller variation than the daily clickthrough rate.

Taking Table 2 of FIG. 6B as an example, if the number of impressions on October 10 for the search result 501 is 70 and the clickthrough rate is 12, the average clickthrough rate for the last N days (ie 5 days) on October 11 If calculated according to the second method, the newly calculated average clickthrough rate is as follows.

Thus, compared to the previously calculated average clickthrough rate of 15.3, the difference from the newly calculated average clickthrough rate is only -1. On the other hand, if you look at the number of clicks per day, compared to 15 times on October 9, two days ago, the click rate on October 10, the day before, is 12, the difference is three.

Therefore, when selecting the search result by reflecting the average click rate, the possibility of variation of the selected search result is lower than that of simply selecting the search result by reflecting the click rate during the unit period such as the daily click rate.

Meanwhile, the exposure index calculator 302 may periodically calculate the average click rate, such as calculating the average click rate at 2 am every day.

The impression index calculator 302 calculates an impression index for each search result based on the average click rate calculated for the search result and the bid associated with the search result as described above.

According to one embodiment of the invention, the exposure index is calculated as follows.

Impression index = average clickthrough rate × bid

In addition, according to another embodiment of the present invention, the exposure index is calculated as follows.

Impression index = weighted average clickthrough rate × weighted bid

          = (Average clickthrough rate + a) × (bid + b)

A and b are respectively a first weighted value added to the average clickthrough rate and a second weighted value added to the bid. Depending on how the first weight value and the second weight value are selected, the operator of the search system 300 may determine whether to further reflect preference or relevance or to further reflect the bid. The operator of the retrieval system 300 may appropriately select a and b according to statistical or empirical methods.

The exposure index calculated according to the first exposure index calculation method is calculated based on the i) the average clickthrough rate and the bid, i) for each search result in relation to i) a predetermined search word. If the average clickthrough rate of the search result 501 associated with the search term "flower delivery" is 15.3, the bid amount suggested by the advertiser who registered the search result 501 is $ 950, so the search result associated with the search term "flower delivery" ( 501) is calculated as 15.3 × 950 = 14535 from the average clickthrough rate × bid.

Therefore, those skilled in the art can recognize that the impression index is changed when the advertiser registers by changing the bid or when the average clickthrough rate is changed. That is, since the impression index is calculated based on the average click rate, the impression index reflects how much users prefer the search result 501.

In addition, since the advertiser may register the same search result 501 for each of the search terms "flower delivery", "garland", and the like, the exposure index is preferably calculated for each search word and for each search result.

In addition, the search system 300 may update the impression index in real time whenever the bid is changed or whenever the average click rate is changed for a predetermined search result associated with a predetermined search word. In addition, the search system 300 may periodically calculate the exposure index in consideration of the system load.

(2) When calculating the exposure index by the second exposure index calculation method

The impression index calculator 302 calculates an impression index based on a bid associated with the search result and a predetermined default click rate when the total number of impressions of the search result is less than the trusted impressions.

When the total number of impressions is less than the number of trusted impressions, it is difficult to see that the clickthrough rate for the search result reflects the preference of users. For example, the click rate is 20% when the first search result exposed 100 times is selected 20 times by the users, and the click rate is calculated as 20% even when the second search result exposed 5 times is selected once by the user. .

Thus, if the total number of impressions themselves is too small, it is difficult to see that enough data has been accumulated to reflect the user's preference. Therefore, when the total number of impressions itself is small, the impression index calculation unit 302 determines that it is not appropriate to use the average click rate, which is the moving average for a certain period of click rate, and uses the default click rate. That is, in the present invention, the confidence exposure number has a characteristic of a threshold value.

The default clickthrough rate may be selected empirically or experimentally by the operator of the search system 300. In addition, according to another embodiment of the present invention, the exposure index calculator 302 may select the basic click rate for each search word associated with the search result. In the case of a popular search word, since the user is more likely to select a search result provided according to a search request to the search word, the default click rate may be larger as the popular search word. On the other hand, the higher the frequency of input of the search word may determine that the search word is more popular.

That is, the impression index calculator 302 may calculate an impression index using a bid associated with the search result and a basic click rate selected for the search word associated with the search result.

According to one embodiment of the invention, the exposure index is calculated as follows.

Impression index = default clickthrough rate × bid

In addition, according to another embodiment of the present invention, the exposure index is calculated as follows.

Impression index = weighted default clickthrough rate × weighted bid

          = (Default clickthrough rate + c) × (bid + d)

C and d are each a first weighted value added to an average clickthrough rate and a second weighted value added to a bid.

Again, the search service providing method according to the present embodiment will be described with reference to FIG.

In operation 202, when the user transmits a search request for a predetermined search word to the search system 300, the user input unit 304 of the search system 300 receives the search request. For example, the search term is "flower delivery."

In operation 203, the search result selector 305 calculates a predetermined number of search results associated with the search word by referring to the search result database 301 according to the search request. According to an embodiment of the present invention, the search result selector 305 selects a predetermined number of search results having a high exposure index among search results associated with the search word.

For example, the search result selector 305 may select five search results having a high exposure index. On the other hand, if the number of search results associated with the search word is less than five, only a corresponding number of search results are selected.

For example, if the exposure index of the search results associated with the search term "flower delivery" is high, respectively, 19000, 18000, 17000, 16500, 16200 (for search result 502), 14535 (search result 501). ), 14000,... , Then select five search results with an exposure index of 19000, 18000, 17000, 16000, 16200. Therefore, the search result 501 having the sixth highest exposure index as 14535 is not included in the five search results.

In addition, according to another embodiment of the present invention, when the search result selection unit 305 cannot select the top five because there is a search result having the same exposure index, the search result is given five priorities each time as follows. Only can be selected. Table 3 of FIG. 5 is a table showing an example of an impression index, a bid, an advertisement execution amount, and a registration time of the search result, for each search result associated with the search word "flower delivery". Table 3 shows a case where the search results are sorted according to the exposure index.

Because of the search results 4 through 7 of the current exposure index 16500, it is not easy for the search system 300 to select only the top five search results. Therefore, the search system 300 according to the present embodiment gives priority to search results having a high bid when the impression index is the same.

Referring to Table 3, search result 7 has a smaller bid than search results 4 to 6 having the same exposure index. Therefore, the search system 300 does not select the search result 7.

On the other hand, it is not easy for the search system 300 to select only five search results this time because the search results 4 to 6 have the same priority even after the impression index is further considered. Therefore, according to another exemplary embodiment of the present invention, the search system 300 selects a search result by further considering an advertisement execution amount for a search result having the same impression index and a bid.

As described above, the bid may mean a maximum advertising cost that the advertiser can pay, and the actual advertising fee charged to the advertiser may be different from the bid. In this specification, an advertisement fee charged to the advertiser when users select a search result is called an advertisement execution cost. For example, the search system 300 may determine the bid as the advertisement execution amount as it is, or may determine the amount of the advertisement cost by adding a predetermined amount to the bid of the search result corresponding to the next rank of the search result.

In addition, according to another embodiment of the present invention, if five search results cannot be selected even though the impression index, the bid amount, and the advertisement execution amount are considered, the search result registered first may be selected by further considering the registration date of the search results. .

Accordingly, the search system 300 may include i) an impression index, ii) a bid for search results with the same impression index, iii) an ad execution cost for a search result with the same impression index and bid, iv) an impression index, a bid, and an ad flight. For search results having the same cost, a predetermined number of search results may be selected in consideration of the search result registration time.

Referring to Table 3 of FIG. 7, for search results 4 to 7 having the same impression index, only the search results 4 to 6 are selected in consideration of the bid, and for the search results 4 to 6 having the same impression index and the bid, the ad execution amount Consider further, and select the search results 4 and 5. In consideration of the advertisement execution amount, since all five search results are selected, such as search results 1 to 5, in the case of Table 3, the search system 300 does not need to further consider the registration time of the search results.

The search result list providing unit 306 generates a search result list including the selected five search results in step 204, and transmits the generated search result list to the user terminal 110 in step 205. To the user.

5, if the average clickthrough rates of the search result 501 and the search result 502 are 15.3 and 18.0, respectively, the exposure index of the search result 501 is 14535 by 15.3 × 950, and the search result The exposure index of 502 becomes 16200 by 18.0 x 900. Thus, a search result 502 with a lower bid but a larger average clickthrough rate is selected as a search result included in the search result list, rather than a search result 501 that suggests a higher bid. Thus, according to the present embodiment, an advertiser may, i) raise a bid, ii) present a bid to some extent in order for his or her search result to be included in a search result list and be provided to users. It is possible to adopt a method that allows users to choose a lot by organizing in a form and content that they may prefer. Since the bid is used as a criterion for calculating an advertisement execution cost, which is an advertisement fee charged to the advertiser when each search result is clicked by a user, it is difficult for the advertiser to raise the bid without risk.

Accordingly, according to the present invention, i) by reflecting the click-through rate for the search results when selecting the search results, so that the user's preferred search results can be provided to users more, ii) not the click-through rate for the search results itself, By using the average value of the clickthrough rate (CTR) per unit period over the past period of time, we ensure that the search results provided each time a search request does not fluctuate heavily, and iii) the advertiser wants to increase the likelihood that their search The quality of the results is also taken into account. Therefore, according to the present invention, the quality of the search results provided by the search system 300 is increased, thereby increasing the user's preference for the search service itself provided by the search system 300. That is, users prefer a search service provided by the search system 300 to other search services.

In addition, advertisers who find that their search results are not preferred by their users, in terms of average clickthrough rates, can still raise their bids by lower average clickthrough rates to ensure that their search results are still included in the search results list. Therefore, it is possible to increase the rate of return in the search system (300). In particular, since the variation in the average clickthrough rate is small according to the present invention, the advertiser can roughly predict the degree to which his or her search results can be selected.

In addition, the search result list providing unit 306 may generate the search result list to arrange five search results included in the search result list in the order of exposure. In addition, the search result list providing unit 306 may generate the search result list to arrange five search results according to a bid. In addition, whenever the search system 300 provides the user with a list of search results, the search system 300 may allow the five search results to be newly sorted in a random rolling or order rolling manner. The random rolling method allows the five search results to be sorted in any order each time the list of search results is provided to the user. In addition, the order rolling method is a method in which the five search results are arranged such that their positions are changed in a predetermined order whenever the search result list is provided to the user. For example, according to the order rolling method, the search result of any one of the five search results is the first position when provided this time, the second position when provided next, and the third position when provided next, … The position may be changed sequentially, such as.

However, the present invention relates to a method of selecting a predetermined number of search results included in a search result list, and the scope of the present invention is provided in which order, or in what form, the selected search results are provided in a sorted order. Not limited by

Further, in step 206, the charging unit 307 determines the exposure index having the smallest value among the exposure indices associated with the selected search result as the “base exposure index”. That is, in the present specification, the basic exposure index means an exposure index having the smallest value among the predetermined number of exposure indices associated with the predetermined number of search results selected by the search result selection unit 305. Therefore, the basic exposure index is a value determined for the selected search results after a predetermined number of search results are selected by the search result selection unit 305. Therefore, the basic exposure index is dynamically determined for each search result list.

As described below, the basic impression index is used to calculate unit advertising costs associated with the selected search results.

For example, assuming that five search results associated with the search term "flower delivery" have been selected, the bids, average clickthrough rates, and impression indices associated with the five search results are shown in Table 4 shown in FIG. 8, respectively. In step 307, the process of calculating the unit advertisement cost will be described in more detail. In FIG. 8, a method of calculating an impression index according to "exposure index = bid x average click rate" is taken as an example.

Referring to FIG. 8, in step 206, the charging unit 307 identifies that the exposure index of the search result 5 is the smallest among the selected five search results and selects 16000 which is the exposure index of the search result 5 as “the selected index”. Default exposure index for five search results ".

Next, in step 207, the charging unit 307 calculates the unit advertisement cost of the selected search result based on the ratio of the basic exposure index and the average clickthrough rate respectively associated with the selected search result.

Unit cost of each search result =

Default impression index ÷ average clickthrough rate (CTR) for each search result

In addition, according to another embodiment of the present invention, the charging unit 307 may remove the value calculated by the basic impression index and the average clickthrough rate of each search result, and the value within the unit amount may be removed using rounding, rounding, or rounding. It may be.

19 = 842.105263…"과 같으나 십원 단위 미만의 값에 대해서는 내림을 적용하여 840원을 검색 결과 1의 단위 광고비로 결정할 수 있다.For example, since search result 1 of FIG. 8 has an average clickthrough rate of 19%, the unit advertising cost of search result 1 is “16000.

19 = 842.105263. ", But for the value less than 10 won unit can be applied to the 840 won to determine the unit advertising cost of the search result 1.

19 -> 840", 검색 결과 2의 단위 광고비는 "16000

20 -> 800", … 이 된다. 검색 결과 5는 자신의 노출 지수를 자신의 평균 클릭률로 나누는 결과가 되기 때문에, 광고주가 제시한 입찰가가 그대로 단위 광고비가 된다.The unit advertisement cost calculated in the above manner is as indicated by the reference numeral 801 of FIG. 8. For example, the unit cost for Search Result 1 is "16000.

19-> 840 ", resulting in a unit ad cost of" 16000 "

20-> 800 ",…. Since the search result 5 divides its impression index by its average clickthrough rate, the bid suggested by the advertiser becomes the unit advertising cost.

In operation 208, the user who has received the search result list may select one of the five search results included in the list by clicking the search results. In response, the search system 300 performs a predetermined operation such as linking the user to a web page of a URL address included in (or associated with) the clicked search result. For example, the web page may be a sales page where the advertiser sells a predetermined product.

In this way, when the user clicks on the search result, in response to the predetermined advertisement being made in association with the search result, the charging unit 307 instructs the advertiser to charge the calculated unit advertisement fee in step 209. To control. For example, if the clicked search result is search result 1, the charging unit 307 refers to the search result database 301 and identifies the advertiser who registered the search result 1, and the unit calculated as described above to the advertiser Advertisement costs 840 won

For example, the accounting unit 307 may calculate the remaining advertising cost by subtracting 840 won from the advertising fee prepaid by the advertiser each time the search result 1 of the advertiser is clicked.

As described above, the present invention adopts a method in which an advertisement fee equal to the unit advertisement cost is charged to the advertiser each time one click occurs.

As such, according to the present invention, it can be seen that the advertising fee charged to each advertiser is inversely proportional to the average clickthrough rate of the search result registered by the advertiser. In other words, an advertiser who registers a search result having a high user preference, that is, a quality search result that faithfully responds to a user's search request, reduces the actual advertising cost.

For example, as indicated by reference numeral 801 of FIG. 8, the unit advertisement fee charged to an advertiser who registers a search result 4 having a high average clickthrough rate, that is, a user's preference is only 500 won. Compared to other search results included in the same search result list, the advertiser of search result 4 obtains the same or similar advertising effect at a relatively very low cost.

Accordingly, according to the present invention, in order to reduce the advertising cost burden, the advertisers make an effort to improve the quality of the search results (and / or web pages provided by clicking the search results). This develops into a preference for a search service that provides the above search results, thereby indirectly increasing the number of users visiting web pages that provide such a search service.

In addition, as shown by reference numeral 801 of FIG. 8, an advertiser who registers a search result 5 having a low average clickthrough rate because the user's preference is not high pays a relatively high advertising cost of 1,000 won each time the search result 5 is clicked. In addition, a low average clickthrough rate should not be excluded from the search result list 5 of its search results. That is, since the search result included in the search result list is selected based on the impression index, and the impression index is determined by reflecting the average clickthrough rate as described above, the advertiser of the search result 5 having a small average clickthrough rate is the own search. The bid increase method is still used as a method of increasing the exposure index in a short time so that the result 5 is not excluded from the search result list. Therefore, the profit of the search service provider using the search service providing method according to the present invention can also be guaranteed.

In addition, even when the unit advertising cost is determined based on the division of the basic impression index by the average click rate associated with each search result, since the change in the average click rate is not large, the change in the unit advertising cost is not large. You'll be able to predict some of the cost per unit of search results.

Meanwhile, in the above-described embodiment, when a search request is input from the user in step 202, steps 203 to 207 are described as being performed, but this is merely exemplary and steps 203 to Step 207 may be performed independently of the search request. For example, the search result selector 305 may pre-select the top five search results having a large exposure index for each search term in real time or periodically, and provide the five preselected search results when a user requests a search. You may. In addition, the charging unit 307 may calculate the unit advertisement cost for the selected five search results irrespective of the user's search request. Of course, the process may be performed in real time or periodically whenever a predetermined renewal reason occurs, such as a change in the average clickthrough rate according to the user's preference ward or the advertiser changes the bid.

In addition, according to another embodiment of the present invention, the charging unit 307 may determine a value of the lowest bid among the search results included in the search result list as the unit advertisement cost of the search result. According to the present embodiment, the unit advertisement cost of the search results included in the search result list becomes the lowest bid.

In addition, embodiments of the present invention include computer-readable media containing program instructions for performing various computer-implemented operations. The program recorded on the computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. The media may be those specially designed and constructed for the purposes of the present invention, or they may be of the kind well-known and available to those having skill in the computer software arts.

9 is an internal block diagram of a general purpose computer device that may be employed to perform a method of providing a search service according to the present invention.

Computer device 900 includes one or more processors 910 coupled with a main memory device including random access memory (RAM) 920 and read only memory (ROM) 930. The processor 910 is also called a central processing unit (CPU). As is well known in the art, the ROM 930 serves to transfer data and instructions to the CPU unidirectionally, and the RAM 920 typically transfers data and instructions bidirectionally. Used to. RAM 920 and ROM 930 may include any suitable form of computer readable media. Mass storage 940 is bidirectionally coupled to processor 910 to provide additional data storage capability and may be any of the computer readable recording media described above. The mass storage device 940 is used to store programs, data, and the like, and is a secondary memory device such as a hard disk which is generally slower than the main memory device. Certain mass storage devices such as CD ROM 960 may be used. The processor 910 may include one or more input / output interfaces, such as video monitors, trackballs, mice, keyboards, microphones, touchscreen displays, card readers, magnetic or paper tape readers, voice or handwriting readers, joysticks, or other known computer input / output devices. 950. Finally, the processor 910 may be connected to a wired or wireless communication network through the network interface 970. Through this network connection, the procedure of the method described above can be performed. The apparatus and tools described above are well known to those skilled in the computer hardware and software arts.

The hardware device described above may be configured to operate as one or more software modules to perform the operations of the present invention.

While specific embodiments of the present invention have been described so far, various modifications are possible without departing from the scope of the present invention.

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

As described above, the present invention has been described by way of limited embodiments and drawings, but the present invention is not limited to the above-described embodiments, which can be variously modified and modified by those skilled in the art to which the present invention pertains. Modifications are possible.

Accordingly, the spirit of the present invention should be understood only by the claims set forth below, and all equivalent or equivalent modifications thereof will belong to the scope of the present invention.

According to the present invention, a method and a search service providing method for selecting a search result in consideration of a bid associated with a search result and an average click rate calculated for the search result, which are devised to improve the conventional technology as described above. A system is provided.

In addition, according to the present invention, by selecting a search result based on the bid and the average click rate, there is provided a search service providing method and a search system that can ensure the quality of the search results provided according to the keyword advertising service.                     

In addition, according to the present invention, the unit advertising cost is calculated in inverse proportion to the average clickthrough rate associated with each search result, so that an advertiser who provides a high quality search result is charged a smaller unit advertising cost, so that the advertiser decides Provided are a search service providing method and a search system that can lead to improved quality.

In addition, according to the present invention, there is provided a search service providing method and a search system that allow an advertiser to predict which search results can be selected by selecting a search result using an average click rate whose variation is smaller than the click rate.

Further, according to the present invention, if the search result is not sufficiently provided to the user during the present time from the registration time when the advertiser registers the predetermined search result, and it is difficult to treat the average click rate as valid data, or from the registration time to the present time A search service providing method and a search system are provided that provide a criterion for determining whether to provide the search result to a user even when the period of time is short and it is difficult to treat the average click rate as valid data.

In addition, according to the present invention, in order to calculate the average clickthrough rate, the M value is determined according to the number of inputs of the search word, and the average clickthrough rate is reflected only by the clickthrough rate during the unit period having the number of impressions or more (the number of times the search result is provided). There is provided a search service providing method and a search system that can further ensure that the variation is small by calculating.

Claims (14)

delete delete delete delete delete delete In the search service providing method in a search system, The search system includes a search result database, an exposure index calculator, a database manager, a search result selector, a search result list providing unit, and a billing unit, Maintaining, by the database manager, the search result database including a search term, a search result associated with the search term, a bid associated with the search result, an impression index associated with the search result, or an advertiser identifier associated with the search result; Wherein the impression index calculation unit calculates an average clickthrough rate, which is an average of clickthrough rates per unit period for a certain period in the past, for each of the search results based on a current time point, wherein the clickthrough rate for each unit period is provided to the user A number of times calculated for each unit period as a ratio of the number of impressions that are the number of times and the number of clicks that are the number of times the user selects the provided search result; Calculating, by the impression index calculator, an impression index based on an average clickthrough rate and a bid for each search result; Recording and updating the calculated exposure index in association with the search result in the search result database by the database manager; Selecting, by the search result selector, a predetermined number of search results among search results associated with the search word when a search request including a predetermined search word is received from a user; Generating, by the search result list providing unit, a search result list including the selected predetermined number of search results to the user; Selecting, by the charging unit, an exposure index having the smallest value among the exposure indices associated with the selected search result as a basic exposure index; And Calculating the unit advertising costs of the selected search results based on the ratio of the basic impression index and the average clickthrough rate associated with the selected search result, respectively; Including, The step of calculating the impression index based on the average clickthrough rate and bid for each of the search index calculation unit, (1) the exposure index calculating unit calculating a total number of impressions, the number of times a predetermined search result is provided to a user from a registration time point to a current time point, wherein the registration time point is a time point at which the search result is recorded in the search result database- ; (2) the impression index calculating unit calculating the average clickthrough rate for each search result when the total number of impressions of the search result is greater than or equal to a predetermined confidence impression number; (3) the impression index calculator calculating an impression index for the search result based on the calculated average clickthrough rate and the bid associated with the search result; (4) the impression index calculator calculating an impression index for the search result based on a bid associated with the search result and a predetermined default click rate when the total number of impressions of the search result is less than the confidence impression number; And (5) the exposure index calculator recording the total number of impressions and the calculated exposure index in association with the search result in the search result database Search service providing method comprising a. The method of claim 7, wherein The confidence impressions is, Calculating, by the exposure index calculator, an input number for each unit period, which is a number of times a search word associated with the search result is input for each unit period; Calculating, by the exposure index calculator, an average input value, which is an average value of the number of inputs per unit period for a second past period, based on a current time point, for the search word; Specifying, by the exposure index calculator, the average input value as the number of confidence impressions for the search result Is determined by (2) step, And determining, by the exposure index calculator, whether the total number of impressions of the search result is greater than or equal to the number of reliable impressions associated with the search result. The method of claim 7, wherein The basic clickthrough rate is set for each search term associated with the search result. In the search service providing method in a search system, The search system includes a search result database, an exposure index calculator, a database manager, a search result selector, a search result list providing unit, and a billing unit, Maintaining, by the database manager, the search result database including a search term, a search result associated with the search term, a bid associated with the search result, an impression index associated with the search result, or an advertiser identifier associated with the search result; Wherein the impression index calculation unit calculates an average clickthrough rate, which is an average of clickthrough rates per unit period for a certain period in the past, for each of the search results based on a current time point, wherein the clickthrough rate for each unit period is provided to the user A number of times calculated for each unit period as a ratio of the number of impressions that are the number of times and the number of clicks that are the number of times the user selects the provided search result; Calculating, by the impression index calculator, an impression index based on an average clickthrough rate and a bid for each search result; Recording and updating the calculated exposure index in association with the search result in the search result database by the database manager; Selecting, by the search result selector, a predetermined number of search results among search results associated with the search word when a search request including a predetermined search word is received from a user; Generating, by the search result list providing unit, a search result list including the selected predetermined number of search results to the user; Selecting, by the charging unit, an exposure index having the smallest value among the exposure indices associated with the selected search result as a basic exposure index; And Calculating the unit advertising costs of the selected search results based on the ratio of the basic impression index and the average clickthrough rate associated with the selected search result, respectively; Including, The period is determined by the sum of the N unit periods, Wherein the step of calculating the impression index calculation average clickthrough rate for a predetermined period from the current time point for each of the search results, Identifying, by the exposure index calculator, N unit periods in which the number of impressions during the unit period is M or more for each of the search results in an order close to the current time; The impression index calculation unit summing click-through rates for each of the identified N unit periods, respectively, for each unit period; And Calculating an average clickthrough rate (CTR) for the predetermined period by dividing the sum of the click rates by the predetermined period by the impression index calculator; Search service method comprising a. The method of claim 10, Wherein the step of the exposure index calculation unit for each of the search results for identifying each of the N unit periods of the number of impressions during the unit period of M or more in the order in close order from the current time point, Calculating, by the exposure index calculator, an average for each unit time period of input times, the number of times a search word associated with the search result is input from a user during a second period; Determining, by the exposure index calculator, the M value to be proportional to the calculated average for each unit period Search service method comprising a. delete A computer-readable recording medium having recorded thereon a program for performing the method of any one of claims 7 to 11. delete

Images