JP5373003B2 - Advertisement processing apparatus and method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To promote a reserve of an advertisement whose commercial value is high. <P>SOLUTION: By calculating a keyword evaluation value from an evaluation value of an advertisement corresponding to the keyword so as to narrow down keywords at a selection stage, a distribution target is selected through a competition between advertisements whose evaluation value indicating a commercial value is high. Thus, a reserve of an advertisement having a high commercial value is promoted. Since a situation in which an advertisement with a high commercial value corresponding to another keyword is hampered due to an overestimation of a keyword evaluation value through influence of an evaluation value of an advertisement which cannot be practically reserved is avoided by removing an advertisement in a state in which its distribution cannot be done from a base of keyword evaluation value calculation, a reserve of an advertisement with a high commercial value can be further promoted. <P>COPYRIGHT: (C)2013,JPO&amp;INPIT

Description

  The present invention relates to an online advertisement.

  In economic activities, it is important to make the object to be treated have higher commercial value in order to generate more social value. It is important to target Internet advertisements to be displayed on web pages that attract more users' interests and that want to be sent even if the advertiser bears a higher advertising fee.

  As a type of Internet advertising along this line, the advertiser designates the keyword and bids the advertising unit price, and the degree of relevance with the keyword representing the characteristics of the content of the web page (also referred to as “content”), that is, content. Some display advertisements specifying high keywords (for example, see Non-Patent Document 1 and Patent Document 1), and words such as listing advertisements and keyword advertisements are often used.

  In this type of advertisement, selection of an advertisement to be inserted into a web page (also referred to as “allocation”) consists of two stages. The first stage is keyword acquisition, that is, a predetermined number of keywords having high relevance to the content and well-characterized by a language processing technique represented by tf-idf are selected. The second stage is the selection of advertisements. Specifically, for those related to a predetermined number of keywords selected in the first stage, only a predetermined number of bid advertisements with a high predetermined evaluation value are selected. Select as display target.

  Here, as the selection of the keyword, for example, a plurality of keywords may be selected in descending order of the degree of matching with the content, or several random numbers may be picked up from, for example, 50 acquired in order of the degree of matching. The evaluation value is an index representing the commercial value for each advertisement, and is typically eCPM (effective cost per mill) obtained by multiplying the bid amount and the click rate for each advertisement (see, for example, Patent Document 2). ).

Yahoo Japan Corporation, “Yahoo! Listing Ads”, [online], [Search March 2, 2011], Internet <URL: http://listing.yahoo.co.jp/>

JP 2007-286833 A Japanese Patent No. 4431058

  However, in the prior art as described above, in the first stage of acquiring a keyword, only the relevance to the content is the standard, and it is not considered whether there is an advertisement with a high evaluation value corresponding to the keyword . For this reason, even if a keyword has a high degree of relevance to the content, if the evaluation value of the corresponding advertisement is generally low, the second stage ad selection will be a competition between candidates with a low evaluation value. In the past, it was not always possible to select a keyword with a higher commercial value because other keywords specified in the higher- There was a problem that could not be allocated.

  In view of the above problems, an object of the present invention is to promote the allocation of advertisements with high commercial value.

  Based on the above object, according to one aspect (1) of the present invention, a keyword candidate corresponding to the content is acquired in an advertisement processing device that selects an advertisement to be distributed according to the content from an advertisement associated with the keyword. A keyword acquisition unit that calculates, for each of the acquired keyword candidates, a keyword evaluation unit that calculates a predetermined keyword evaluation value based on a bid evaluation value that is an evaluation value related to a bid for the corresponding advertisement. Based on keyword evaluation means for selecting a part of the keyword candidates as keywords based on the keyword evaluation value, and on the result evaluation value which is an evaluation value related to the display result of the advertisement from the advertisement corresponding to the selected keyword And advertisement allocation means for selecting an advertisement to be distributed.

  Another aspect (4) of the present invention is an advertisement processing method in which the above aspect is captured by a method category, and a computer selects an advertisement to be distributed in accordance with content from advertisements associated with a keyword. , A keyword acquisition process for acquiring keyword candidates corresponding to the content, and for each of the acquired keyword candidates, a predetermined keyword evaluation value is calculated based on a bid evaluation value that is an evaluation value related to a bid for the corresponding advertisement A keyword evaluation process for selecting a keyword candidate part as a keyword based on the calculated keyword evaluation value, and an advertisement display result from the advertisement corresponding to the selected keyword. An ad allocation process for selecting an advertisement to be distributed based on a result evaluation value that is an evaluation value; And wherein the Mukoto.

  In this way, the keyword evaluation value that reflects the bid status of the advertisement corresponding to each keyword is calculated, and the keywords are narrowed down at the selection stage. Since the target is selected, the allocation of advertisements with high commercial value can be promoted.

  According to another aspect (2) of the present invention, in any one of the aspects described above, a means for receiving an instruction to stop distribution for the advertisement, a means for performing a process including an update for a budget balance of a preset advertisement fee, And the keyword evaluation means excludes at least one of the advertisement instructed to stop the distribution and the advertisement whose budget of the advertising fee is exhausted from the basis of the calculation of the keyword evaluation value. And

  In this way, by removing undeliverable ads from the basis of the keyword evaluation value calculation, the keyword evaluation value is overestimated due to the evaluation value of the advertisement that is not actually allocated, and the commercial value corresponding to other keywords is Since it is possible to avoid a situation in which the allocation of a high advertisement is hindered, the allocation of an advertisement having a high commercial value can be promoted more reliably.

  According to another aspect (3) of the present invention, in any one of the aspects described above, there is provided means for accepting a setting of a distribution condition for limiting a distribution opportunity and reflecting it in selection of an advertisement. The bid evaluation value of the advertisement for which is set is used for calculating the keyword evaluation value based on the ratio related to the limitation.

  In this way, with regard to bid evaluation values of advertisements that are distributed only under limited conditions such as the attributes of distribution target persons such as gender and age, and distribution time zones, specifically based on the ratio related to the limitation, By multiplying such a ratio and reflecting it in the keyword evaluation value, it is possible to avoid a situation in which the bid evaluation value of an advertisement that may not be delivered even if it is allocated is excessively reflected in the keyword evaluation value. That is, since the bid evaluation value of the advertisement with the limited condition also affects the keyword evaluation value within the range of the actual average expected value, the selection of the keyword based on the keyword evaluation value becomes high accuracy.

  It should be noted that categories different from the above-described aspects (methods for apparatuses, programs for methods, etc.) and more specific aspects described below are also included in the present invention. For categories different from the above-described aspects, “means” is appropriately read as “processing” or “step”. Further, the order of execution of processes and steps is not limited to the above, and can be changed as appropriate or can be processed collectively. Furthermore, in the category of methods and programs, “computers” that execute individual processes may be common or may be different for each process.

  According to the present invention, it is possible to promote the allocation of an advertisement having a high commercial value.

The functional block diagram which shows the structure of embodiment of this invention. The figure which illustrates the data (information) in embodiment of this invention. The flowchart which shows the process sequence in embodiment of this invention. The figure which shows the example of a screen display of a listing advertisement.

  Next, as an example of the present invention, a mode for carrying out the present invention (referred to as “embodiment”) will be described with reference to the drawings. It should be noted that assumptions common to those already described in the background art and problems are omitted as appropriate.

[1. Constitution〕
The present embodiment relates to the advertisement processing apparatus 1 (also referred to as “this apparatus” or “this apparatus 1”) shown in FIG. 1 (configuration diagram), and this apparatus 1 converts an advertisement associated with a keyword into content. The advertisement to be distributed is selected. In the present embodiment, the advertisement distribution function to the terminal T1 of the end user is provided. As shown in FIG. 1, the present apparatus 1 includes at least an arithmetic control unit 6 such as a CPU, a storage device 7 such as a main memory and an auxiliary storage device, and a communication network N (for example, the Internet). Communication means 8 (communication gateway device, communication circuit with mobile phone network or PHS network, wireless LAN adapter, etc.).

  The terminals T (T1 and T2) are electronic information devices such as stationary PCs, mobile PCs, tablet PCs, smartphones, and mobile phone terminals. An input / output unit using a display panel, a touch panel, a push button, or the like is included. Terminals T (T1 and T2) are schematically shown in a small number in FIG. 1, but a necessary number is used. In particular, a terminal T1 used by an end user such as a general website viewer assumes a large number according to the number of users. To do.

  Further, in the present apparatus 1, elements (20, 30, etc.) such as each means shown in FIG. 1 are realized by a predetermined computer program stored (installed) in the storage device 7 controlling the arithmetic control unit 6. . Among these elements, information storage means can be realized in any format such as various databases (also referred to as “DB”), files, arrays, variables such as various stacks, registers, system setting values in the storage device 7, Data used for processing by each means, processing results, etc., including those not shown or not specified, are stored.

  Among the storage means, the advertisement storage means 15 is means for storing information for each advertisement (referred to as “advertisement data”), and as the stored advertisement data, as illustrated in FIG. For each advertisement identified by the advertisement ID, a bid keyword that is a keyword specified at the time of ad submission and associated with the advertisement, distribution conditions that limit distribution opportunities, CTR (click-through rate: click rate), click There are a bid amount (that is, a bid price) that is a unit price of the advertisement fee charged when the advertisement is made, a budget balance of the advertisement fee, a stop flag indicating that the distribution is stopped, and the content of the advertisement. The content of the advertisement is arbitrary, such as a character string (referred to as “title” or “description”) displayed as a character string advertisement with a hyperlink, a jump destination URL of the hyperlink, and the like.

  Note that the arrows in the figure (for example, FIG. 1) supplementarily indicate the main direction of the flow of data, control, etc., and do not mean the limitation of the direction. For example, in order to acquire data in a certain direction, there is a data request transmission in the reverse direction in advance. In addition, each means other than the storage means is a processing means for realizing and executing the functions and operations of information processing as described below, but these are functional units arranged for explanation, and actual hardware It doesn't matter if it matches elements or software modules.

[2. Main actions and effects)
The operation procedure of the apparatus 1 in the present embodiment configured as described above is shown in the flowchart of FIG.
[2-1. Prerequisite mode of advertisement distribution]
As a premise of the flowchart of FIG. 3, in the present embodiment, the web server W that intends to distribute the web page to the user terminal T <b> 1 acquires the keyword of the apparatus 1 using the character string in the web page as content prior to the distribution. The web server W incorporates the advertisement transmitted to the means 20 and transmitted from the advertisement distribution means 70 of the apparatus 1 in response to the content into the web page of the content, and displays it on the user terminal T1.

[2-2. Acquisition of keyword candidates)
When distributing the advertisement as described above, in the present apparatus 1, as shown in the flowchart of FIG. 3, first, based on the content transmitted from the web server W, the keyword acquisition means 20 uses the keyword candidate corresponding to the content. Is acquired (step S3). Here, the keyword candidate is a keyword that is highly related to the content transmitted from the web server W, that is, a feature word that represents the feature, that is, a predetermined number selected by a language processing technique represented by tf-idf. Can be considered. However, it is not essential to transmit the content from the web server W to the apparatus 1, and the keyword candidate may be a feature word or the like previously associated with the content in the web server W or the apparatus 1.

[2-3. (Keyword evaluation value calculation)
Then, the keyword evaluation means 40 calculates a predetermined keyword evaluation value for each acquired keyword candidate based on a bid evaluation value that is an evaluation value related to a bid for the corresponding advertisement (step S4). The specific content of the bid evaluation value and the specific calculation method of the keyword evaluation value are free, but the bid evaluation value is an evaluation value that at least a part of elements is determined by bidding for one or more advertisements.

  As an example of the bid evaluation value, it may be counted as “1” when a certain advertisement is bid, or the bid amount of one advertisement, the number of bids of a group of advertisements, the average bid amount, etc. Further, it may be calculated by combining both of them and an evaluation value such as CTR related to the display result of the advertisement. The bid evaluation value can be used as the keyword evaluation value as it is.

For example, the keyword evaluation value corresponding to the keyword candidate k is eCPM (k), the average bid of the advertisement corresponding to the keyword candidate k is AveBid (k), and the average CTR of the advertisement corresponding to the keyword candidate k is AveCTR (k). When representing

eCPM (k) = AveBid (k) x AveCTR (k) ... First example

It is possible to calculate as follows. In this example, an average bid price AveBid (k) that is a bid evaluation value is multiplied by AveCTR (k) that is an average CTR to obtain eCPM (k) that is a keyword evaluation value.

As another example, a predetermined selection index Selection (k) is used as a keyword evaluation value corresponding to the keyword candidate k, and an average bid is set to AveBid (k) in the same manner as described above, and bidding is performed corresponding to the keyword candidate k. When the number of ads being served is represented as Listingcount (k)

Selection (k) = AveBid (k) x Listingcount (k) ... Second example

It is possible to calculate as follows. In this example, selection (k), which is a keyword evaluation value, is obtained by multiplying the average bid unit price AveBid (k), each of which is a bid evaluation value, and the advertisement count Listingcount (k).

[2-4. (Keyword selection)
Next, the keyword selection means 50 selects some keyword candidates as keywords based on the keyword evaluation values calculated as described above (step S5).

のなかで占める割合の大きいものを優先して所定の選出数（例えば５０、２０など）までキーワードを選出してもよい。すなわち、

の割合に比例した確率で各キーワードｋを所定の選出数に達するまでキーワードとして選出すれば、キーワード評価値が相対的に小さいキーワード候補もキーワードとして選出されるチャンスが確保されるので、広告を取り巻く状況変化や広告の潜在的可能性にも対応する広告の引当てが実現できる。 In the case of the above first example, keywords can be selected from keyword candidates in descending order of the keyword evaluation value eCPM (k). Also, eCPM (k) as the keyword evaluation value of each keyword k is the sum of the keyword evaluation values of all keyword candidates (represented by capital letters “K”).

A keyword may be selected up to a predetermined selection number (for example, 50, 20, etc.) with priority given to those having a large proportion. That is,

If each keyword k is selected as a keyword with a probability that is proportional to the ratio until the number of selected keywords is reached, a keyword candidate with a relatively small keyword evaluation value is secured as a keyword, so the advertisement is surrounded. Provision of advertisements corresponding to situation changes and advertisement potential can be realized.

のなかで占める割合の大きいものを優先して所定の選出数までキーワードを選出してもよい。すなわち、

の割合に比例した確率で各キーワードｋを所定の選出数に達するまでキーワードとして選出すれば、キーワード評価値が相対的に小さいキーワード候補もキーワードとして選出されるチャンスが確保されるので、広告を取り巻く状況変化や広告の潜在的可能性にも対応する広告の引当てが実現できる。 In the case of the second example, keywords can be selected from keyword candidates in descending order of selection index Selection (k) that is a keyword evaluation value. The selection index Selection (k) for each keyword k is the sum of the keyword evaluation values of all keyword candidates.

The keywords may be selected up to a predetermined number of selections with priority given to those having a large proportion. That is,

If each keyword k is selected as a keyword with a probability that is proportional to the ratio until the number of selected keywords is reached, a keyword candidate with a relatively small keyword evaluation value is secured as a keyword, so the advertisement is surrounded. Provision of advertisements corresponding to situation changes and advertisement potential can be realized.

  When using the first example (Equation 1 (Equation 1) and Equation 2 (Equation 2)) using eCPM based on CTR as a keyword evaluation value used for selecting a keyword, a keyword having a high expected value of eCPM is selected. Therefore, it can be expected that the profit will be high. On the other hand, when the above second example using the number of bids (Formula 3 (Formula 3) or Formula 4 (Formula 4)) is used, it can be expected that many advertisements with high bids are distributed.

  From a short-term perspective, the selection based on the above-mentioned first example (Formula 1 and Formula 2) based on CTR is considered desirable. However, the frequency (advertising exposure frequency) increases and the same advertisement continues to appear. In the long term, the second example using the number of bids in the long run, considering the concerns such as a decline in the advertiser's disadvantage and a decrease in the total budget due to a decline in the number of advertisers' ads that are biased. It seems that it is more advantageous to put out many types of advertisements with high potential profits by selection based on (Formula 3 and Formula 4).

Therefore, in order to balance both of these according to the situation, as a new indicator

Extended_eCPM (k) = AveBid (k) x AveCTR (k) x Listingcount (k) ... Third example

It is also possible to select a keyword based on this calculation. In this way, keywords having a higher CTR and a higher number of bids are used preferentially, and therefore, it is possible to promote the allocation of advertisements having a high commercial value in terms of both CTR and the number of bids.

  Furthermore, if each term AveBid (k), AveCTR (k) and Listingcount (k) included in the third example is multiplied by an arbitrary coefficient, each of the average bid price, average CTR, and number of bid advertisements can be determined. Since it is possible to finely adjust the balance of whether or not the degree of importance is reflected in the keyword evaluation value, the application of the present invention suitable for the circumstances such as the purpose and situation can be realized.

[2-5. (Ad selection and delivery)
Then, the advertisement allocation unit 60 selects an advertisement to be distributed from advertisements corresponding to the selected keyword based on a result evaluation value that is an evaluation value related to an advertisement display result (step S6). The result evaluation value used for this selection can be arbitrarily selected, for example, eCPM, CPA (Cost Per Action), CPC (Cost Per Click), CR (Conversion Rate), etc. It may be calculated on the spot from the history, etc., or may be regularly prepared in the background or batch processing.

  For example, eCPM is the product of the CTR of the advertisement and the bid amount. In the example of the advertisement ID “A12” in FIG. 2, CTR: 0.08 is multiplied by the bid amount of ¥ 800 to be ¥ 64. Further, the means for calculating the bid evaluation value and the result evaluation value may be one means such as the advertisement evaluation means 30 or may be different means.

  The advertisement distribution means 70 such as a separate advertisement distribution server distributes the advertisement selected as described above to the user terminal T1 via the web server W, for example (step S7). FIG. 4 shows a state in which an advertisement AD, which is a character advertisement with a distributed hyperlink, is displayed in combination with the original content C. These advertisements AD are advertisements that use characteristic words such as “hybrid car” and “fuel economy” appearing in the title and text of the content C a plurality of times as bid keywords.

  Further, the CTR update unit 80 updates the CTR stored in the advertisement storage unit 15 depending on whether or not the distributed advertisement is clicked on the terminal T1 of the user who is the distribution destination (step S8). Although illustration is omitted, in practice, the actual number of distributions and the number of clicks are stored for each advertisement, and each time they are updated, a new CTR (FIG. 2) is calculated from them, Replace with CTR. The CTR updated in this way is used for calculation of the result evaluation value and the bid evaluation value. In addition to the CTR, a value used as the result evaluation value or the bid evaluation value (for example, AveCTR (k) which is an average CTR of keywords, A value corresponding to eCPM, CPA, CPC, CR, etc.) may be updated and stored.

  As described above, in this embodiment, an advertisement with a high evaluation value representing commercial value is calculated by calculating a keyword evaluation value reflecting the bid status of the advertisement corresponding to each keyword, and narrowing down the keyword at the selection stage. Since distribution targets are selected by competition between each other, it is possible to promote the allocation of advertisements with high commercial value.

[2-6. Example)
A simplified example of the above is shown. There are two keyword candidates for a certain content, “hybrid car” and “fuel economy”, but consider a case in which only one keyword is selected and only one advertisement is assigned and displayed. In this case, it is assumed that “fuel consumption” is superior in terms of fitness to content, but “hybrid car” is superior in keyword evaluation values such as average CTR of the corresponding advertisement. In such a case, in the prior art, “fuel consumption” that is superior in the degree of fitness for content is given priority, and only the corresponding advertisement is displayed. As a result, eCPM remains low, but in this embodiment, it is superior in keyword evaluation value. As a result of giving priority to the “hybrid car” and displaying only the corresponding advertisement, an excellent eCPM is realized.

[3. (Advertising excluded from calculation basis)
Further, in the present embodiment, in the calculation of the keyword evaluation value, the evaluation value of the advertisement whose distribution is stopped or the budget is exhausted is excluded from the calculation basis. In other words, the submission delivery control means 90 accepts an instruction to stop delivery of an advertisement from the advertiser terminal T2 used by a predetermined person such as an advertiser or from a predetermined electronic information processing organization, and is set in advance. Processes that include updating the budget balance of advertising fees.

  Here, an example of an instruction to stop distribution is that a predetermined operator (hereinafter collectively referred to as “advertiser etc.”) such as an advertiser, an advertising agency, and an operator of the apparatus 1 has a predetermined setting screen (not shown). If you log in to and stop the distribution, the distribution will be stopped until the next operation to restart the distribution. It can be considered. In the example of FIG. 2, the stop flag is set to “1” when a delivery stop operation is performed, and the next restart of the delivery is reset to “0”, and the stop flag “1” advertisement is stopped from being delivered. Is done.

  Also, the budget balance of the advertising fee is set by the advertiser on the setting screen as described above for each advertisement or each advertisement group (called “campaign”, etc.), and is charged when the advertisement is clicked Every time it is reduced in real time or at a timing equivalent to it, if it runs out (such as becoming zero or negative, or less than a predetermined remaining amount), the distribution is stopped. Then, the keyword evaluation means 40 excludes at least one of the advertisement instructed to stop distribution as described above and the advertisement whose budget for the advertising fee is exhausted from the basis of the keyword evaluation value calculation.

  As described above, in this embodiment, by removing an advertisement that cannot be delivered from the basis of keyword evaluation value calculation, the keyword evaluation value is overestimated due to the influence of the evaluation value of the advertisement that is not actually allocated, and is assigned to other keywords. Since it is possible to avoid the situation in which the allocation of the corresponding high commercial value advertisement is prevented, the allocation of the high commercial value advertisement can be further promoted.

[4. (Consideration of delivery conditions)
Further, in the calculation of the keyword evaluation value, it is possible to consider the distribution conditions set for the advertisement. That is, the submission delivery control means 90 accepts the setting of delivery conditions that limit delivery opportunities and reflects them in the selection of advertisements. For example, when setting of distribution conditions is accepted, as shown in FIG. 2, the advertisement storage unit 15 stores the distribution conditions, and the advertisement allocation unit 60 reads out the distribution conditions and selects an advertisement. To reflect. On the other hand, the keyword evaluation unit 40 uses the evaluation value of the advertisement for which the distribution condition is set to calculate the keyword evaluation value based on the ratio related to the limitation, specifically by multiplying the ratio related to the limitation. .

  Distribution conditions include, for example, the gender of the distribution target (for example, limited to men, limited to women, etc.), attributes such as age, access source area, website browsing history such as website browsing, and time period for distribution ( For example, from 18:00 to 24:00), the day of the week, etc. is free. The ratio related to the limitation (shown as “the number of real bids” in FIG. 2) is, for example, 1/2 (that is, 50%) if the distribution condition is limited to men when the distribution ratio is substantially the same. The distribution condition for limiting the time zone from 10:00 to 18:00 is 8/24 (about 33%).

  For example, in the case of the second example already described, when calculating the keyword evaluation value, the bid evaluation value “1” is counted for each advertisement corresponding to the keyword, and the total number of advertisements Listingcount (k) 2 (advertisement ID: “A12”) is counted as 1/2 (0.5), and advertisement with “B53” is counted as 1/3 (about 0.33). Thus, the advertisement count Listingcount (k), which is the keyword evaluation value, is calculated.

  As described above, in the present embodiment, the bid evaluation value of an advertisement that is distributed only under limited conditions such as the attribute of the distribution target person such as gender and age and the distribution time zone is based on the ratio related to the limitation. Specifically, by multiplying the ratio according to the limitation and reflecting it in the keyword evaluation value, it is possible to avoid a situation in which the bid evaluation value of an advertisement that may not be delivered even if it is allocated is reflected excessively in the keyword evaluation value. That is, since the bid evaluation value of the advertisement with the limited condition also affects the keyword evaluation value within the range of the actual average expected value, the selection of the keyword based on the keyword evaluation value becomes high accuracy.

[5. Other embodiments]
In addition, the said embodiment is only an illustration and this invention includes what is illustrated below and other embodiment other than that. For example, the configuration diagrams, data diagrams, flowcharts, and the like in the present application are merely examples, and the presence / absence of each element, the order of the arrangement and processing execution, and the specific contents can be changed as appropriate. As an example, in the above-described embodiment, the present apparatus 1 includes the advertisement distribution unit. However, the apparatus 1 may be configured to only allocate advertisements. The advertisement is not limited to a character advertisement but may be an advertisement of an image or a video such as a banner advertisement. Further, the advertisement may be directly delivered from the apparatus 1 to the terminal T1 based on an HTML description or the like interpreted and displayed on the user terminal T1 without passing through the web server W.

  In addition, a configuration in which the individual means shown in FIG. 1 and the like are realized by separate and independent facilities is also common, and depending on the function of the server or the terminal, an external platform or the like may be connected to an API (Application Program Interface). ) And network computing (so-called cloud etc.), and the configuration can be flexibly changed. For example, the present apparatus shown in FIG. 1 and the web server W may be appropriately integrated. Furthermore, each element such as means relating to the present invention may be realized by other information processing mechanisms such as a physical electronic circuit as well as a computer control unit.

DESCRIPTION OF SYMBOLS 1 Advertisement processing apparatus 6 Operation control part 7 Storage apparatus 8 Communication means 15 Advertisement storage means 20 Keyword acquisition means 30 Advertisement evaluation means 40 Keyword evaluation means 50 Keyword selection means 60 Advertisement allocation means 70 Advertisement distribution means 80 CTR update means 90 Distribution control means AD Advertising C Content LAN Wireless N Communication network T (T1, T2) Terminal W Web server

Claims (4)

In an advertisement processing apparatus that selects an advertisement to be distributed according to content from advertisements stored in storage means associated with a keyword,
Computer
Keyword acquisition means for acquiring keyword candidates corresponding to the content;
One or two or more bids of the advertisement from the information for each advertisement stored in the storage means, which is an evaluation value related to the advertisement bid stored in the corresponding storage means for each of the acquired keyword candidates A keyword evaluation unit that acquires a bid evaluation value in which at least a part of the elements is determined by calculating a predetermined keyword evaluation value based on the acquired bid evaluation value ;
Keyword selection means for selecting a part of the keyword candidates as keywords based on the calculated keyword evaluation value;
From the stored in the storage means corresponding to the elected the keyword the advertisement, Ri evaluation value der according to the display result of the ads, to calculate the result evaluation value from the information of each advertisement stored in the storage means, Based on the calculated result evaluation value , an advertisement allocation means for selecting an advertisement to be distributed;
An advertisement processing apparatus comprising: A means for accepting an instruction to stop distribution for the advertisement stored in the storage means, and a means for performing a process including an update on a budget balance of a preset advertising fee,
The keyword evaluation unit excludes at least one of the advertisement instructed to stop the distribution and the advertisement whose budget of the advertising fee is exhausted from the basis of the calculation of the keyword evaluation value. 1. The advertisement processing apparatus according to 1. A means of accepting settings for distribution conditions that limit distribution opportunities and reflecting them in the selection of advertisements,
The keyword evaluation unit uses the bid evaluation value of the advertisement for which the distribution condition is set to calculate the keyword evaluation value based on a ratio related to the limitation. The advertisement processing apparatus described. In an advertisement processing method in which a computer selects an advertisement to be distributed according to content from advertisements stored in storage means associated with a keyword,
The computer is
A keyword acquisition process for acquiring keyword candidates corresponding to the content;
One or two or more bids of the advertisement from the information for each advertisement stored in the storage means, which is an evaluation value related to the advertisement bid stored in the corresponding storage means for each of the acquired keyword candidates A keyword evaluation process that obtains a bid evaluation value that determines at least a part of the element according to, and calculates a predetermined keyword evaluation value based on the acquired bid evaluation value ;
A keyword selection process for selecting a part of the keyword candidates as keywords based on the calculated keyword evaluation value;
From the stored in the storage means corresponding to the elected the keyword the advertisement, Ri evaluation value der according to the display result of the ads, to calculate the result evaluation value from the information of each advertisement stored in the storage means, An ad allocation process for selecting an advertisement to be distributed based on the calculated result evaluation value ;
Advertisement processing method which is characterized that you run the.

Images