KR101129048B1 - Device and method for recommendation of keyword - Google Patents

Abstract

The keyword recommendation apparatus according to the present invention is a keyword recommendation apparatus for recommending a keyword to be purchased by a user terminal. An advertising cost calculation unit configured to calculate a price competitiveness compared to the third party based on the first advertising cost and the second advertising cost, and an index determination unit to determine a keyword recommendation index based on the price competitiveness And a keyword recommendation unit for recommending the keyword to the user terminal based on the keyword recommendation index.

Description

Keyword suggestion device and keyword suggestion {DEVICE AND METHOD FOR RECOMMENDATION OF KEYWORD}

The present invention relates to a keyword recommendation apparatus and a keyword recommendation method.

An internet user may search for a company of interest in a portal site or the like and receive information about the searched company. At this time, the user's search may be performed by inputting a keyword related to a company of interest. That is, the user may directly enter the name of the company or the name of the relevant region and the type of business of the relevant business, etc. The portal site may provide the user with a list of search results related to the keyword input by the user.

In connection with this, a search provider such as a portal site utilizes keyword advertising, which is an advertisement technique that allows advertisements of related companies to be exposed using keywords entered by a user.

Advertisers need to select and purchase appropriate keywords in order to effectively advertise their businesses and maintain revenue growth. Therefore, it is necessary to smoothly select keywords by recommending appropriate keywords to marketers who relay keyword purchases to advertisers or advertisers.

The technical problem to be achieved by the present invention is to recommend an appropriate keyword to the advertiser or the marketer for purchasing the keyword to the advertiser in consideration of the advertising cost and advertising effect.

The keyword recommendation apparatus according to an embodiment of the present invention is a keyword recommendation apparatus for recommending a keyword to be purchased by a user terminal, and includes a first advertisement cost previously generated for each of the plurality of keywords and a second advertisement of another company for each of the plurality of keywords An advertisement cost calculation unit that calculates a cost, a price competitiveness calculation unit that calculates a price competitiveness compared to the third party based on the first advertisement cost and the second advertisement cost, and determines a keyword recommendation index based on the price competitiveness An index determining unit and a keyword recommending unit recommending the keyword to the user terminal based on the keyword recommendation index.

The advertisement cost calculator may calculate the first advertisement cost according to a plurality of rankings arranged in a list of search results for each of the plurality of keywords.

The price competitiveness calculator may calculate a value obtained by subtracting a value obtained by dividing a value obtained by dividing the highest advertising cost among the first advertising costs by the highest advertising cost among the second advertising costs by one.

For each of the plurality of keywords, the standard deviation calculation unit for calculating a standard deviation between the advertising costs for the plurality of rankings may be further included.

The index determiner may further determine the keyword recommendation index in consideration of the standard deviation.

The apparatus may further include a past sales calculation unit for calculating past sales for each of the plurality of keywords.

The index determination unit may determine the keyword recommendation index further considering the past sales.

The index determination unit may determine a value obtained by multiplying the price competitiveness, the past sales, and the standard deviation as the keyword recommendation index.

The keyword recommendation apparatus according to another embodiment of the present invention is a keyword recommendation apparatus for recommending a keyword to be purchased by a user terminal. The keyword recommendation index is calculated based on past sales calculation for calculating past sales for each of a plurality of keywords and the past sales. An index determination unit for determining a, and a keyword recommendation unit for recommending the keyword to the user terminal based on the keyword recommendation index.

The method may further include an advertising cost calculation unit configured to calculate a first advertising cost previously generated for each of the plurality of keywords according to a plurality of rankings arranged in a search result list for each of the plurality of keywords.

For each of the plurality of keywords, the standard deviation calculation unit for calculating a standard deviation between the advertising costs for the plurality of rankings, the index determination unit may further determine the keyword recommendation index in consideration of the standard deviation.

The keyword recommendation apparatus according to another embodiment of the present invention is a keyword recommendation apparatus for recommending a keyword to be purchased by a user terminal. An advertising cost calculation unit that calculates the ranking according to the plurality arranged in the list, a standard deviation calculation unit that calculates a standard deviation between the advertising costs for the plurality of rankings for each of the plurality of keywords, and the keyword based on the standard deviation An index determining unit determines a recommendation index, and a keyword recommendation unit recommending the keyword to the user terminal based on the keyword recommendation index.

According to another embodiment of the present invention, a keyword recommendation method is a method of recommending, by a keyword recommendation apparatus, a keyword to be purchased by a user terminal, calculating a first advertisement cost previously generated for each of a plurality of keywords, and each of the plurality of keywords. Calculating a second advertising cost of the third party for the third party; calculating a price competitiveness with respect to the third party based on the first advertising cost and the second advertising cost; and calculating a keyword recommendation index based on the price competitiveness. Determining, and recommending the keyword to the user terminal based on the keyword recommendation index.

The method may further include calculating past sales for each of the plurality of keywords, and determining the keyword recommendation index may be performed by further considering the past sales.

The calculating of the first advertising cost may be performed according to a plurality of ranks arranged in a list of search results for each of the plurality of keywords, and the keyword recommendation method may include the plurality of ranks for each of the plurality of keywords. The method may further include calculating a standard deviation between advertising costs for.

The determining of the keyword recommendation index may be performed by further considering the standard deviation.

According to the present invention, by recommending a keyword in consideration of an advertisement cost and an advertisement effect to an advertiser or a marketer who purchases a keyword to an advertiser, it is possible to promote keyword sales.

1 is a block diagram illustrating a keyword recommendation apparatus according to an embodiment of the present invention.
2 is a flowchart illustrating a method for recommending a keyword to a user terminal by a keyword recommendation apparatus according to an exemplary embodiment of the present invention.
3 is a schematic diagram of a keyword recommendation apparatus according to another embodiment of the present invention.

DETAILED DESCRIPTION Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art may easily implement the present invention. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and like reference numerals designate like parts throughout the specification.

Throughout the specification, when a part is said to "include" a certain component, it means that it can further include other components, without excluding other components unless specifically stated otherwise. In addition, the terms “… unit”, “… unit”, “module”, etc. described in the specification mean a unit that processes at least one function or operation, which may be implemented by hardware or software or a combination of hardware and software. have.

A keyword recommendation apparatus and a keyword recommendation method according to an embodiment of the present invention will be described in detail with reference to the drawings.

1 is a block diagram illustrating a keyword recommendation apparatus according to an embodiment of the present invention.

The keyword recommendation apparatus 100 according to an exemplary embodiment of the present invention is a server recommending a keyword to be purchased by a user to the user terminal 200, and includes an advertisement cost calculation unit 110, a price competitiveness calculation unit 120, and a previous sales calculation unit. 130, a standard deviation calculation unit 140, an index determination unit 150, and a keyword recommendation unit 160.

The user terminal 200 is a communication device that allows a marketer who relays keyword purchases to a user, for example, an advertiser or an advertiser, to access the keyword recommendation device 100 through a network. Various communication devices such as a telephone can be used.

The advertisement cost calculation unit 110 calculates an advertisement cost for each of the plurality of keywords according to the ranking arranged in the search result list for each keyword. At this point, advertising costs include pay per click (PPC) (cost per click (CPC)), pay per sale (PPS), pay per lead (PPL), behavior It can be estimated by several criteria, such as cost per action (CPA) and cost per thousand (CPM).

In addition, the advertisement cost calculation unit 110 calculates an advertisement cost from another company for each of the plurality of keywords. In this case, the third-party advertising costs may be based on the advertising costs of the search results arranged in the top position in the search result list for each keyword.

As such, the advertisement cost calculated by the advertisement cost calculation unit 110 may be as shown in Table 1 below. The units of the numbers shown in Table 1 are circles.

number keyword 1st priority 2nd rank 3 rank 4th rank 5th rank Third party One loan 11,020 11,020 11,010 11,010 10,870 17,460 2 used car 690 520 360 210 160 1,140 3 Herbalife 5,480 4,410 3,660 3,650 3,400 6,150 4 invitation 2,940 2,930 2,910 2,910 2,910 4,230 5 Flower delivery service 3,070 3,060 3,030 2,080 2,080 7,470 6 A stone offering 740 730 720 720 720 1,220 7 Auto insurance comparison 3,510 3,470 3,330 2,020 2,020 5,680 8 Jeju Island Travel 790 780 780 780 780 2,260 9 Flower delivery 3,110 3,110 3,100 2,600 2,020 6,050 10 Internet subscription 1,900 1,890 1,880 1,880 1,870 2,240 11 Where to get a loan 5,590 5,560 5,540 5,530 5,530 9,850 12 Auto insurance 3,910 3,030 3,020 3,020 3,020 3,380 13 Maternity 570 570 570 560 560 670 14 Promotional material 3,610 2,970 2,960 2,950 2,700 5,410 15 Credit loan 10,260 10,260 10,250 10,240 10,220 17,270 16 Insurance comparison site 8,400 8,020 5,010 4,070 4,060 9,460 17 Dolbok rental 1,170 1,160 1,150 1,120 1,120 1,040 18 uniform 1,060 1,020 1,010 940 930 2,170 19 Jeju Island Pension 780 760 750 750 740 1,380 20 Dolbok rental 1,220 1,210 1,210 1,120 1,120 1,230

As shown in Table 1, the advertising cost calculation unit 110 may calculate the advertising costs of each of the first to fifth rankings and the third-party advertising costs of each of the 20 keywords.

The price competitiveness calculation unit 120 calculates a price competitiveness (P) compared to other companies based on the advertising cost calculated by the advertising cost calculation unit 110. The operation of the price competitiveness calculation unit 120 may be performed according to Equation 1 below.

In Equation 1, Ca is the advertising cost of a specific ranking of each keyword, Cb is the same specific ranking advertising costs of other companies for each keyword. Here, the specific rank may be the first rank.

The past sales calculation unit 130 calculates the past sales S, for example, the previous month sales, for each keyword. At this time, the past sales (S) refers to the sales generated by the user terminal 200 before purchasing the keyword.

The standard deviation calculation unit 140 calculates a standard deviation D between next-order advertising costs among the plurality of ranking advertising costs for each keyword. The standard deviation D calculated by the standard deviation calculation unit 140 calculates the variance as, for example, the average of the advertising costs for all ranks and the square of the difference of each advertising cost for each keyword, and the calculated variance. The standard deviation can be calculated from the square root of the positive s, which represents the scatter plot of the advertising cost for each keyword. That is, the average advertising cost difference between the next ranking for each keyword is shown. .

The index determination unit 150 calculates the price competitiveness P calculated by the price competitiveness calculation unit 120, the past sales S calculated by the past sales calculation unit 130, and the standard deviation calculated by the standard deviation calculation unit 140. The keyword recommendation index is determined based on at least one of (D). For example, the index determination unit 150 may determine the keyword recommendation index I as shown in Equation 2 below.

Table 2 shows the keyword recommendation index determined in this way.

number keyword Price Competitiveness (P) Past Sales (S) Standard deviation (D) Keyword Referral Index (I) One loan 0.37 23.161874 65.03845 556 2 used car 0.39 12.777449 219.7043 1108 3 Herbalife 0.11 11.972846 849.2055 1108 4 invitation 0.30 10.882332 14.14214 47 5 Flower delivery service 0.59 10.723615 533.3198 3369 6 A stone offering 0.39 8.982162 8.944272 32 7 Auto insurance comparison 0.38 8.355923 778.8132 2486 8 Jeju Island Travel 0.65 8.215135 4.472136 24 9 Flower delivery 0.49 7.545097 482.1514 1768 10 Internet subscription 0.15 6.859558 11.40175 12 11 Where to get a loan 0.43 6.407561 25.4951 71 12 Auto insurance -0.16 5.768318 396.9257 -359 13 Maternity 0.15 5.587643 5.477226 5 14 Promotional material 0.33 5.208453 339.0723 588 15 Credit loan 0.41 5.173824 16.7332 35 16 Insurance comparison site 0.11 4.394245 2137.187 1052 17 Dolbok rental -0.13 4.131105 23.02173 -12 18 uniform 0.51 4.01606 55.40758 114 19 Jeju Island Pension 0.43 3.882754 15.16575 26 20 Dolbok rental 0.01 3.785058 51.28353 2

As shown in Table 2, the price competitiveness calculation unit 120 may calculate the price competitiveness (P) for each of the 20 keywords, and the past revenue calculation unit 130 calculates the past sales (S) for the 20 keywords. The standard deviation calculation unit 140 may calculate a standard deviation D for 20 keywords, and the index determination unit 150 may determine a keyword recommendation index based on the standard deviation D.

The keyword recommendation unit 160 recommends the keyword to the user terminal 200 based on the keyword recommendation index determined by the index determination unit 150 for each keyword. For example, the keyword recommendation unit 160 may recommend the “flower delivery service” and the “car insurance comparison score” having a high keyword recommendation index to the user terminal 200.

As described above, according to the present invention, since the price competitiveness is calculated based on the price ratio with other companies, the keyword recommendation index is determined based on the price competitiveness, thereby providing a user with an opportunity to purchase a keyword at a lower advertising cost than other companies. have. In addition, since the keyword recommendation index is determined based on the past sales, a relatively popular keyword can be recommended to the user by recommending a keyword that has been sold in the past. In addition, the keyword recommendation index is determined according to the standard deviation of the advertising cost, so that the user terminal 200 can preoccupy a high arrangement rank at a relatively low price.

Now, a keyword recommendation method according to another embodiment of the present invention will be described in detail with reference to FIG. 2.

2 is a flowchart illustrating a method for recommending a keyword to a user terminal by a keyword recommendation apparatus according to an exemplary embodiment of the present invention.

Referring to FIG. 2, the keyword recommendation apparatus 100 calculates an advertisement cost and an advertisement cost of a third party for each keyword according to a ranking arranged in a search result list for each of the plurality of keywords (S210). In this case, the advertising cost may be calculated according to various criteria.

Thereafter, the keyword recommendation apparatus 100 calculates a price competitiveness based on the calculated advertising cost (S220). Price competitiveness can be calculated based on first-rate advertising costs and third-party advertising costs.

The keyword recommendation apparatus 100 calculates past sales of each keyword (S230).

In operation S240, the keyword recommendation apparatus 100 calculates a standard deviation between advertisement costs for a plurality of rankings for each of the plurality of keywords.

Thereafter, the keyword recommendation apparatus 100 determines a keyword recommendation index based on at least one of price competitiveness, past sales, and standard deviation of advertisement cost (S250).

Next, the keyword recommendation apparatus 100 recommends a keyword to the user terminal 200 based on the keyword recommendation index (S260). In this case, the keyword recommendation apparatus 100 may recommend a keyword having a high keyword recommendation index to the user terminal 200.

Then, the user terminal 200 selects a keyword based on the keyword recommendation from the keyword recommendation apparatus 100 and purchases the selected keyword (S270).

At least some of the functions of the keyword recommendation apparatus and the keyword recommendation method according to the embodiment of the present invention described above may be implemented in hardware or software coupled to the hardware. Hereinafter, an embodiment in which an advertisement device is coupled to a computer system will be described in detail with reference to FIG. 3.

3 is a schematic diagram of a keyword recommendation apparatus 1000 according to another exemplary embodiment of the present invention, wherein the advertisement cost calculation unit 110, the price competitiveness calculation unit 120, the historical sales calculation unit 130, and standard deviation are described above. Represents a system that can be used to perform at least some of the functions of the calculation unit 140, the index determination unit 150, and the keyword recommendation unit 160.

Referring to FIG. 3, the keyword recommendation apparatus 1000 may include a processor 1110, a memory 1120, at least one storage device 1130, an input / output (I / O) interface 1140, and a network interface ( 1150).

The processor 1110 may be implemented with a central processing unit (CPU), other chipsets, microprocessors, or the like. The memory 1120 may be a medium such as RAM, such as dynamic random access memory (DRAM), rambus DRAM (RDRAM), synchronous DRAM (SDRAM), static RAM (SRAM), or the like. It can be implemented as. The storage device 1130 may include a hard disk, a compact disk read only memory (CD-ROM), a CD rewritable (CD-RW), a digital video disk ROM (DVD-ROM), a DVD-RAM, and a DVD-RW disk. The optical disk may be implemented as a permanent or volatile storage device such as an optical disk such as a blu-ray disk, a flash memory, or various types of RAM. The I / O interface 1140 also allows the processor 1110 and / or the memory 1120 to access the storage device 1130. The network interface 1150 allows the processor 1110 and / or the memory 1120 to access the network.

In this case, the processor 1110 may include an advertising cost calculation unit 110, a price competitiveness calculation unit 120, a historical sales calculation unit 130, a standard deviation calculation unit 140, an index determination unit 150, and a keyword recommendation unit ( Program instructions for implementing at least some of the functions of 160 are loaded into the memory 1120, and the advertisement cost calculation unit 110, the price competitiveness calculation unit 120, the past sales calculation unit 130, the standard deviation calculation unit 140, the functions of the index determiner 150 and the keyword recommender 160 may be located in the storage device 1130 to control the operations described with reference to FIGS. 1 and 2.

The processor 1110, the memory 1120, the storage device 1130, the I / O interface 1140, and the network interface 1150 illustrated in FIG. 3 may be implemented in one computer or distributed in a plurality of computers. It may be implemented.

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

Claims (16)

A keyword recommendation apparatus for recommending keywords to be purchased by a user terminal.
An advertising cost calculation unit that calculates a first advertising cost previously generated for each of the plurality of keywords and a second advertising cost of another company for each of the plurality of keywords,
A price competitiveness calculation unit calculating a price competitiveness of the third party based on the first advertisement cost and the second advertisement cost;
Index determination unit for determining a keyword recommendation index based on the price competitiveness, and
A keyword recommending unit recommending the keyword to the user terminal based on the keyword recommendation index
Keyword recommendation device comprising a. In claim 1,
The advertising cost calculation,
Calculating the first advertising cost according to a plurality of rankings arranged in a search result list for each of the plurality of keywords;
Keyword recommender. In claim 2,
The price competitiveness calculation unit,
And a value obtained by subtracting a value obtained by dividing a value obtained by dividing an advertisement cost of the highest rank among the first advertisement costs by an advertisement cost of the highest rank among the second advertisement costs by 1 as the price competitiveness. In claim 2,
And a standard deviation calculation unit for calculating a standard deviation between advertisement costs for the plurality of rankings for each of the plurality of keywords. In claim 4,
The index determination unit determines the keyword recommendation index further considering the standard deviation.
Keyword recommender. In claim 5,
Further comprising a past sales calculation unit for calculating the past sales for each of the plurality of keywords
Keyword recommender. In claim 6,
The index determination unit may further determine the keyword recommendation index in consideration of the past sales.
Keyword recommender. In claim 7,
And the index determination unit determines the keyword recommendation index as a value obtained by multiplying the price competitiveness, the past sales, and the standard deviation. delete delete delete delete As a method for recommending a keyword for a user terminal to purchase a keyword,
Calculating first advertising costs previously incurred for each of the plurality of keywords,
Calculating second advertising costs of third parties for each of the plurality of keywords;
Calculating a price competitiveness of the third party based on the first advertising cost and the second advertising cost;
Determining a keyword recommendation index based on the price competitiveness, and
Recommending the keyword to the user terminal based on the keyword recommendation index.
Keyword recommendation method comprising a. In claim 13,
Calculating past sales for each of the plurality of keywords
Further comprising:
Determining the keyword recommendation index is performed in consideration of the past sales further keyword recommendation method. The method of claim 13 or 14,
The step of calculating the first advertising cost,
In accordance with a plurality of ranks arranged in a list of search results for each of the plurality of keywords,
The keyword recommendation method is
Calculating, for each of the plurality of keywords, a standard deviation between advertising costs for the plurality of rankings. The method of claim 15,
The determining of the keyword recommendation index is performed by further considering the standard deviation.

Images