JP6921922B2 - Information processing equipment, information processing methods, and information processing programs - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and an information processing program.

In recent years, with the rapid spread of the Internet, advertisement distribution via the Internet has been actively carried out. For example, an advertisement content such as a company or a product is displayed in an advertisement space set as an advertisement medium (web page), and when such advertisement content is clicked, an advertisement is delivered that transitions to the advertiser's web page. ing.

In such advertisement distribution, a bid unit price (CPC: Cost Per Click), which is a charge amount charged to the advertiser, may be used as a consideration for posting the advertisement content. In addition, instead of the bid unit price, the target value of the conversion unit price (CPA: Cost Per Action), which is the cost related to acquiring one profitable result such as product purchase or membership registration from the predetermined advertising content, is the target value. A technology (called conversion optimization) has been proposed in which the advertiser is allowed to set the conversion unit price, and the bid unit price set for the advertising content is calculated based on the target conversion unit price.

Here, the index value relating to the second content to which the first content is transitioned is predicted, and the index value relating to the degree of interest indicated by the user to be distributed of the first content is predicted, and the index value is based on the predicted index value. A technique for correcting the conversion rate (CVR) of one content has been proposed (see Patent Document 1).

JP-A-2017-167736

However, in the above-mentioned prior art, when correcting the conversion rate, the height (difficulty) of the hurdle that the user must overcome before the conversion is reached is not taken into consideration. Conversion means that the user who browses the advertisement content takes the action expected by the advertiser (implementation of a predetermined action). In Internet advertising, it is expected that the difficulty level of a user's conversion will affect the result of whether or not the user will convert. For example, the conversions set for advertisements are diverse depending on the settings of the advertiser, such as clicks on advertisements, staying on landing pages, requesting materials, answering questionnaires, requesting quotations, requesting sales, and purchasing products (contract conclusion). The height of the hurdle is different for each set conversion, but if the prediction model is generated based on whether or not the user has converted, high prediction accuracy can be obtained because the height of the hurdle is not taken into consideration in the prediction model. I can't. Therefore, it is required to improve the prediction accuracy of the conversion rate in consideration of the height of the hurdle leading to the conversion due to various factors.

The present application has been made in view of the above, and includes an information processing device, an information processing method, and an information processing program capable of improving the prediction accuracy of the conversion rate in consideration of the height of the hurdle leading to conversion. The purpose is to provide.

The information processing device according to the present application has accessed the reception unit that receives the submission of the advertisement content and the setting of the target value of the unit price related to the execution of the predetermined action for the advertisement content from the advertiser terminal, and the advertisement content. includes an estimation unit for the user to estimate the difficulty of up to the implementation of the predetermined action, based on the difficulty for each advertising content, and a correcting unit for correcting the implementation rate of the predetermined action, the The estimation unit presumes that if the predetermined action does not involve the expenditure of the user or is easy to operate for implementation, the difficulty is low and it is easy to carry out the predetermined action, and the predetermined action is determined. When the action is accompanied by the expenditure of the user or it is difficult to perform an operation for carrying out the action, it is presumed that the difficulty is high and it is difficult to carry out the predetermined action.

According to one aspect of the embodiment, it is possible to improve the prediction accuracy of the conversion rate in consideration of the height of the hurdle leading to the conversion.

FIG. 1 is an explanatory diagram showing an outline of an information processing method according to an embodiment. FIG. 2 is a diagram showing a configuration example of an information processing system according to an embodiment. FIG. 3 is a diagram showing an example of a user information storage unit according to the embodiment. FIG. 4 is a diagram showing an example of the advertisement information storage unit according to the embodiment. FIG. 5 is a diagram showing an example of the history information storage unit according to the embodiment. FIG. 6 is a diagram showing an example of the prediction model storage unit according to the embodiment. FIG. 7 is a flowchart showing an information processing procedure by the information processing apparatus according to the embodiment. FIG. 8 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device.

Hereinafter, the information processing apparatus according to the present application, the information processing method, and a mode for carrying out the information processing program (hereinafter, referred to as “the embodiment”) will be described in detail with reference to the drawings. The information processing apparatus, information processing method, and information processing program according to the present application are not limited by this embodiment. Further, in the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

[1. Information processing method overview]
First, with reference to FIG. 1, an outline of an information processing method performed by the information processing apparatus according to the embodiment will be described. FIG. 1 is an explanatory diagram showing an outline of an information processing method according to an embodiment. In the example of FIG. 1, the information processing system 1 includes an advertiser terminal 10, a terminal device 20, an information providing device 30, and an information processing device 100. Then, the advertiser terminal 10, the terminal device 20, the information providing device 30, and the information processing device 100 are connected to each other via a network so as to be communicable by wire or wirelessly. The information processing system 1 shown in FIG. 1 includes a plurality of advertiser terminals 10, a plurality of terminal devices 20, a plurality of information providing devices 30, and a plurality of information processing devices 100. You may. Further, in the present embodiment, it is assumed that the information providing device 30 and the information processing device 100 are managed by the business operator T1.

The advertiser terminal 10 is a terminal device used by the advertiser. For example, the advertiser terminal 10 is a smart device such as a smartphone or tablet terminal, a PC (Personal Computer), a mobile phone, a PDA (Personal Digital Assistant), an OA device (office automation device), or the like. Further, the advertiser terminal 10 submits the advertisement content to the information processing device 100 according to the operation of the advertiser.

For example, the advertiser terminal 10 submits advertisement contents corresponding to still images, moving images, text data, and the like to the information processing device 100. Further, for example, the advertiser terminal 10 sends the advertisement content corresponding to the URL (Uniform Resource Locator) of the transition destination content to be transitioned to the information processing device 100 when the advertisement content is selected (for example, clicked or tapped). Upload. In the following, the selection operation will be described as clicking.

Further, the advertiser terminal 10 sets a target conversion unit price, which is a target value of the conversion unit price, which is a cost related to acquiring one profitable result such as product purchase or membership registration from the advertisement content according to the operation of the advertiser. The information processing device 100 is instructed to set the corresponding advertisement content.

It is predetermined that the target conversion unit price can be set only for the advertising content for which a predetermined number (for example, "10") or more of conversions have been obtained. Therefore, for example, when the advertiser has achieved conversions of a predetermined number or more of his / her own advertisement content that has already been submitted, the advertiser sets a target conversion unit price for such advertisement content.

The terminal device 20 is a terminal device used by the user. For example, the terminal device 20 is a smart device such as a smartphone or a tablet terminal, a PC, a mobile phone, a PDA, or the like. For example, the terminal device 20 acquires a web page from the information providing device 30 by accessing the information providing device 30, and displays the acquired web page on the display screen.

Further, when the web page includes an advertising space, the terminal device 20 acquires the advertising content from the information processing device 100 by accessing the information processing device 100, and the acquired advertising content is used in the advertising space. indicate.

The information providing device 30 is a content server that provides contents such as a web page to the terminal device 20. The information providing device 30 provides various web pages related to, for example, news sites, auction sites, weather forecast sites, shopping sites, finance (stock price) sites, route search sites, map providing sites, travel sites, gourmet sites, web blogs, and the like. do.

The information processing device 100 is a server device that delivers advertising content submitted from the advertiser terminal 10. As described above, the information processing device 100 delivers the advertisement content to the terminal device 20 when accessed from the terminal device 20.

Further, as described above, the information processing apparatus 100 according to the embodiment automatically sets the bid unit price on behalf of the advertiser by accepting the setting of the target conversion unit price from the advertiser. Specifically, when the information processing device 100 selects the advertisement content by multiplying the conversion rate of the advertisement content and the target conversion unit price set for the advertisement content for each advertisement content. Calculate the bid unit price, which is the amount to be charged to. Then, the information processing device 100 delivers the advertisement based on the calculated bid unit price.

Here, the conversion rate is an actual value calculated by dividing the number of conversions (conversions) from the advertising content by the number of clicks clicked on the advertising content so far. Therefore, it can be said that the accuracy of the conversion rate becomes statistically higher as the number of conversions and the number of clicks increases. In other words, if the number of conversions and clicks is small, the accuracy of the conversion rate is statistically low. The accuracy of the conversion rate referred to here corresponds to the reliability such as whether or not the conversion rate is statistically sufficient.

As an example, the advertisement content i will be described. For example, when the number of clicks is "10" and the number of conversions is "1" for the advertisement content i, the conversion rate of the advertisement content i is "0.1". However, when the number of clicks is "1000", the conversion rate is not always "0.1" because the number of conversions is "100". For example, in reality, when the number of clicks is "1000", the number of conversions is "20", so that the conversion rate may be calculated as "0.02".

In this way, the conversion rate can be said to be an unstable value that changes according to the distribution information. In other words, the conversion rate once calculated is not always a reliable value. Originally, it is desirable to use a sufficient number of clicks that is reliable and the conversion rate calculated from the number of conversions, but there are many advertising contents that are difficult to click in the first place, and even if the advertising content is generally clicked. Very unlikely to lead to conversions. Therefore, it may be difficult to accurately predict what the conversion rate of all advertising content will be as a statistically reliable value.

For example, depending on (a) the appearance of the content and design of the image or moving image displayed as advertising content, (b) the type of product to be advertised, (c) the content of the action set as conversion, etc. The likelihood of a user converting will vary.

Further, for example, when the bid unit price is calculated using a conversion rate with low accuracy, the calculated bid unit price can also be said to be a value with low accuracy. Then, if the advertisement is delivered using the bid unit price with low accuracy, the target conversion unit price may be greatly exceeded.

Therefore, the information processing apparatus 100 according to the embodiment performs a process for improving the prediction accuracy of the conversion rate in consideration of the situation surrounding the conversion rate as described above. Specifically, the information processing device 100 predicts that the user will convert (execute a predetermined action) in the second content (transition destination content), which is the transition destination of the advertisement content, which is an example of the first content. Based on the height (difficulty) of the hurdle, the conversion rate based on the actual information is corrected.

Then, using the prediction information in this way to correct the conversion rate based on the actual information predicts what kind of value the conversion rate will be as a statistically reliable value. Equivalent to doing.

The transition destination content that is transitioned from the advertising content is generally called a landing page (LP) or the like. Therefore, in the following, the transition destination content may be referred to as "LP". Further, in the following, the target conversion unit price is set to "target CPA", the conversion rate before correction calculated from the actual information is simply "CVR", and the correction value of the conversion rate obtained by simply correcting "CVR" is "corrected CVR". , The bid unit price may be expressed as "CPC".

Here, the relationship between the height of the hurdle to conversion in LP and the conversion rate will be described. Specifically, it is recognized that the lower the hurdle to conversion, the easier it is to convert. For example, when a user makes a request for materials or purchases a product from LP, the hurdle is low and conversion is easy to occur because the request for materials does not involve expenditure, but it is considered that the hurdle is high and it is difficult to reach conversion because the purchase of product involves expenditure. .. Also, if the design of the conversion button etc. displayed in the transition destination content (color, size, arrangement, etc. for the background) is easy to select and operate, the hurdle is low and it is easy to reach conversion, but it is difficult to select and operate. If there is, the hurdle is high and it is difficult to reach conversion.

That is, when the user is interested in the contents of the LP, the lower the hurdle to conversion, the higher the possibility that the user will convert, and the easier it is to convert. This point will be described with an example.

For example, it is assumed that the user A has recently searched for information using the search query "notebook computer". At this time, it can be said that the user is currently interested in the "notebook computer". Then, in such a case, if the advertisement content x1 related to the "notebook computer" is displayed on the terminal device 20 of the user A, there is a high possibility that the user A clicks the advertisement content x1 and shifts to the corresponding LP LPx11. In addition, even if the conversion type is product purchase, there is a sense of value due to special price sales for a limited time, and if the purchase amount is the amount that can actually be paid, the psychological hurdle is low, so there is a high possibility that conversion will occur. ..

Further, it is assumed that in addition to the advertisement content x1, the advertisement content x2 related to the "apartment" is also displayed. In such a case, the user A is unlikely to click the advertisement content x2. In addition, even if the user A clicks to switch to the corresponding LP, LPx12, the actual purchase / sale has a high hurdle unless he / she is prepared to purchase / sell the condominium in advance, so the conversion is performed. It is extremely unlikely that it will occur, but if it is a request for materials or a request for quotation, the hurdle is low, so the possibility of conversion is high.

From the above, the lower the hurdle to conversion in LP, the higher the possibility that the user will reach conversion, and the easier it will be to convert, that is, the higher the possibility that the conversion rate will be improved. On the contrary, the higher the hurdle to conversion in LP, the lower the possibility that the user will reach conversion, and the less likely it is that conversion will be achieved, that is, the possibility that the conversion rate will be improved. For this reason, a correlation is established between the height of the hurdle leading to conversion and the conversion rate in LP. Therefore, it is considered that the prediction accuracy for predicting the correction value of the conversion rate can be improved by using the height of the hurdle leading to the conversion.

Therefore, the information processing device 100 according to the embodiment estimates the height of the hurdle to conversion in the LP, which is the transition destination of the advertisement content. Then, the information processing apparatus 100 corrects the conversion rate (CVR) of the advertisement content based on the estimated height of the hurdle, and calculates the correction value (corrected CVR) of the conversion rate.

Hereinafter, the information processing performed by the information processing apparatus 100 will be specifically described with reference to FIG. The information processing device 100 according to the embodiment uses a method of determining the advertisement content to be distributed by using the search query recently used by the user in the content operated by the business operator T1. Such a method is called search targeting or the like. Further, it is assumed that the advertising content provided by the information processing apparatus 100 is a pay-per-click type advertising content.

First, the advertiser terminal 10 submits the advertisement content to the information processing device 100 and instructs the information processing device 100 to set various information related to the advertisement content according to the operation of the advertiser (step S1). As a result, the information processing device 100 receives the submission of advertisement content and the setting of various information from the advertiser. Then, the information processing device 100 stores the received advertisement content and various information in the advertisement content storage unit.

Further, the advertiser terminal 10 instructs the information processing apparatus 100 to set a target CPA for the advertisement content submitted by the advertiser according to the operation of the advertiser (step S2). As a result, the information processing apparatus 100 receives the setting of the target CPA from the advertiser. Then, the information processing device 100 associates the received target CPA with the advertisement content and stores it in the advertisement content storage unit.

In the example of the advertisement content storage unit shown in FIG. 1, the information processing device 100 submits the advertisement content AD11 from the advertiser C1, the LP URL “aa11.com” transitioned from the advertisement content AD11, and the keyword “insurance”. An example of accepting the setting of "" is shown. The keyword is information used for targeting the user, and indicates what kind of content the advertising content is.

Further, in the example of the advertisement content storage unit shown in FIG. 1, an example in which the information processing device 100 receives the setting of the target CPA “15,000” for the advertisement content AD11 from the advertiser C1 is shown. Here, the advertiser C1 has been described as an example, but since the other advertisers are also as shown in FIG. 1, the description thereof will be omitted.

Here, it is assumed that the terminal device 20 transmits the acquisition request of the web page P1 to the information providing device 30 according to the operation of the user U1 (step S3). As a result, the information providing device 30 delivers the web page P1 to the terminal device 20 of the acquisition request transmission source (step S4).

As shown in FIG. 1, the web page P1 includes an advertising space F1 in which the advertising content is displayed. Therefore, the terminal device 20 transmits a request for acquiring the advertisement content to the information processing device 100 (step S5).

When the information processing device 100 receives the advertisement content acquisition request from the terminal device 20, the information processing device 100 first identifies the advertisement content of the distribution candidate (step S6). For example, the information processing apparatus 100 refers to the user information storage unit and identifies a search query recently used by the user U1 for information retrieval. As shown in FIG. 1, the user information storage unit stores historical information related to the search query used by the user. In the example of FIG. 1, the information processing apparatus 100 identifies the search query "insurance" with the latest date as the search query recently used by the user U1. From this, it is highly likely that user U1 is currently interested in "insurance".

Then, the information processing device 100 refers to the advertisement content storage unit, and identifies the advertisement contents AD11 and AD21 to which the keywords matching the search query "insurance" are associated as the advertisement contents of the distribution candidates.

Next, in the information processing device 100, when the terminal device 20 accesses to acquire the advertisement content, the access source user, that is, the distribution target user U1 who distributes the advertisement content is the distribution candidate of each advertisement content ( The height of the hurdle to be overcome before conversion is estimated for each of the LPs (LP11 and LP21) corresponding to each of AD11 and AD21) (step S7).

For example, the information processing apparatus 100 estimates the height of the hurdle to conversion in each LP by using crowdsourcing or a questionnaire. Alternatively, the information processing device 100 estimates the height of the hurdle from the past history information (log information) related to the advertisement distribution to the conversion in each LP.

At this time, the information processing device 100 asks "what kind of user" has "what kind of hurdle" before reaching "what kind of conversion" in the LP of "what kind of advertising content". By machine learning for each advertising content, the height of the hurdle to conversion is estimated for each LP.

Actually, the information processing apparatus 100 may use the score of the height of the hurdle acquired by the questionnaire or the like as it is. Further, the information processing device 100 has a high hurdle for the ratio of click "100", material request "10", product purchase "1", etc. from the history information of each group such as a certain advertiser or advertisement category. It may be reflected in the score.

Further, the information processing apparatus 100 may estimate the height of the hurdle from the user's behavior leading up to the conversion. Further, the information processing apparatus 100 may estimate the height of the hurdle from the number of operations performed until the conversion. For example, if a user views the same ad content many times and then converts, hesitates / crawls many times and then converts, although he / she was interested in the product or campaign to be advertised. It is presumed that it has arrived.

Further, the information processing apparatus 100 may estimate the height of the hurdle from the time elapsed from the display of the advertisement content to the execution of a predetermined action. For example, if a considerable amount of time has passed from the display of the advertisement content to the conversion by the user, it is presumed that the conversion was achieved after the user was lost for a long time.

Further, the information processing device 100 may estimate the height of the hurdle according to the advertisement target. For example, if the products targeted for advertising are "PC", "insurance", and "apartment", even if the conversion type is the same, it is presumed that the height of the hurdle for the user to convert is different. ..

Further, the information processing device 100 may estimate the height of the hurdle according to the appearance of the advertisement content. For example, it is presumed that the possibility that the user will be converted varies depending on whether or not the appearance such as the content and design of the image or moving image displayed as the advertisement content matches the user's sensibility. In addition, it is presumed that the possibility that the user will be converted varies even when the button displayed in the advertisement content is hidden in the background and difficult to see.

Here, it is assumed that the information processing apparatus 100 estimates the height of the hurdle in LP11 to be "2" and the height of the hurdle in LP21 to be "1". In the following, the height of the hurdle estimated in this way may be referred to as "estimated hurdle height".

Next, the information processing apparatus 100 corrects the conversion rate (CVR) of each of the advertising contents AD11 and AD21 using the hurdle height (estimated hurdle height) estimated in step S7, and corrects the conversion rate. (Correction CVR) is calculated (step S8). Here, the CVR of the advertising content AD11 is set to "0.05", and the CVR of the advertising content AD21 is set to "0.03".

In such a case, the information processing apparatus 100 multiplies the CVR "0.05" of the advertisement content AD11 by the weight value "2" corresponding to the estimated hurdle height in the LP11 to set the CVR of the advertisement content AD11 to "0. 1 ”is corrected. That is, the information processing apparatus 100 obtains "0.1" as the correction value of the conversion rate. Further, the information processing device 100 multiplies the CVR "0.03" of the advertisement content AD21 by the weight value "1" corresponding to the estimated hurdle height in the LP21 to obtain the CVR of the advertisement content AD21 "0.03". Is corrected to. That is, the information processing apparatus 100 obtains "0.03" as the correction value of the conversion rate.

As described above, the information processing apparatus 100 according to the embodiment corrects so that the higher the estimated hurdle, the higher the corrected CVR. The reason is that it is considered that the value per conversion is higher for the user to overcome the high hurdle and reach the conversion than to overcome the low hurdle and reach the conversion.

Next, the information processing apparatus 100 calculates the CPC by multiplying the corrected CVR calculated in step S8 and the target CPA set in step S2, and the calculated CPC and click through rate (CTR). The eCPM (effective cost per mille) is calculated by multiplying by (step S9).

In the example of the advertisement content storage unit shown in FIG. 1, the target CPA "15,000" is set in the advertisement content AD11, and the target CPA "20,000" is set in the advertisement content AD21.

Therefore, the information processing apparatus 100 multiplies the correction CVR "0.1" of the advertisement content AD11 by the target CPA "15,000" of the advertisement content AD11 to obtain the CPC "1,500" of the advertisement content AD11. calculate. Further, the information processing apparatus 100 calculates the CPC "600" of the advertisement content AD21 by multiplying the correction CVR of the advertisement content AD21 by "0.03" and the target CPA "20,000" of the advertisement content AD21. ..

Here, the CTR of the advertising content AD11 is set to "0.05", and the CTR of the advertising content AD21 is set to "0.03". In such a case, the information processing apparatus 100 calculates the eCPM "75" of the advertisement content AD11 by multiplying the CPC "1,500" of the advertisement content AD11 and the CTR "0.05" of the advertisement content AD11. Further, the information processing apparatus 100 calculates the eCPM "18" of the advertisement content AD21 by multiplying the CPC "600" of the advertisement content AD21 and the CTR "0.03" of the advertisement content AD21.

Next, the information processing device 100 generates a prediction model of a correction value of the conversion rate in consideration of the height of the hurdle leading to conversion for each advertisement content (step S10). At this time, the information processing apparatus 100 may generate a different prediction model for each type of conversion. Further, the information processing device 100 may generate a different prediction model for each advertisement content.

Here, an example of a conversion rate prediction method using a prediction model by the information processing apparatus 100 will be described. Specifically, the information processing apparatus 100 uses the "search query used by the user" obtained from the history information as the explanatory variable X1 as the user information corresponding to "what kind of user". Further, the information processing apparatus 100 uses the "keyword given to the advertising content displayed to the user" as the explanatory variable X2 as the advertising information corresponding to the "what kind of advertising content". Further, the information processing apparatus 100 sets the calculated "correction CVR" as the objective variable Y as the information corresponding to the "probability that the user reaches the conversion".

Then, the information processing apparatus 100 estimates the coefficient by combining the explanatory variables X1 and X2 and performing regression analysis on the objective variable Y. Then, the information processing apparatus 100 predicts the objective variable Y using the estimated coefficient. In the example of the prediction model storage unit shown in FIG. 1, an example in which the information processing device 100 generates the prediction model M11 as the prediction model for the advertisement content AD11 is shown. In addition, other advertising contents are also shown in the figure.

For example, the information processing apparatus 100 applies the search query "insurance" of the user U1 and the keyword "insurance" of the advertisement content AD 11 to the prediction model M11 corresponding to the advertisement content AD 11. Then, the information processing apparatus 100 predicts that the output corrected CVR is a correction value of the conversion rate in LP11.

Similarly, the information processing apparatus 100 applies the search query "insurance" of the user U1 and the keyword "insurance" of the advertisement content AD21 to the prediction model M21 corresponding to the advertisement content AD21. Then, the information processing apparatus 100 predicts that the output corrected CVR is a correction value of the conversion rate in LP21.

After the information processing apparatus 100 generates a prediction model of the conversion rate correction value, the information processing apparatus 100 predicts the conversion rate correction value in each LP by using this prediction model, thereby performing the above steps S7 and S8. The process can be omitted.

Actually, the information processing apparatus 100 may generate a prediction model of eCPM with the calculated "eCPM" as the objective variable Y. In this case, the above processes from step S7 to step S9 can be omitted.

Further, the information processing apparatus 100 may generate a prediction model using the user attributes and conversion types as explanatory variables X1 and X2. Any attribute such as demographic (demographic attribute) or psychographic (psychological attribute) can be adopted as the user attribute.

Next, the information processing device 100 extracts the advertisement content to be distributed from the advertisement content storage unit (step S11). For example, the information processing apparatus 100 uses the advertisement content AD11 for which the correction CVR having a large value is calculated among the correction values (correction CVR) of the conversion rate calculated in step S8 as the advertisement content to be distributed, and the advertisement content. Extract from the storage.

When the lower hurdle is emphasized, the information processing device 100 corresponds to the estimated hurdle height in LP21 rather than the advertising content AD11 in which the weight value corresponding to the estimated hurdle height in LP11 is "2". The advertisement content AD21 having a weight value of "1" is extracted from the advertisement content storage unit as the advertisement content to be distributed. Further, when the information processing apparatus 100 attaches importance to the larger eCPM, the information processing device 100 delivers the advertisement content AD11 in which the eCPM having the larger value is calculated out of the two eCPMs calculated in step S9 as described above. Extracted from the advertising content storage as advertising content.

Then, the information processing device 100 delivers the extracted advertisement content AD 11 to the terminal device 20 of the acquisition request transmission source (step S12). Then, the terminal device 20 displays the web page P1 in which the advertisement content AD11 is displayed in the advertisement space F1 on the display screen.

In this way, the information processing device 100 according to the embodiment estimates the height of the hurdle until the user to whom the advertisement content is distributed reaches the conversion in the LP which is the transition destination of the advertisement content. Then, the information processing apparatus 100 corrects the conversion rate (CVR) of the advertisement content based on the estimated height of the hurdle, and calculates the correction value (corrected CVR) of the conversion rate.

As described above, the CVR used in conversion optimization is an unstable value because it is calculated based on the number of conversions and the number of clicks for which it is difficult to obtain a statistically sufficient number of actual information. Therefore, it is possible to obtain a highly accurate corrected CVR by correcting the CVR by using the height of the hurdle leading to the conversion which is correlated with the conversion rate. That is, the information processing apparatus 100 can improve the prediction accuracy of predicting the corrected CVR from the CVR. Further, since the information processing apparatus 100 can improve the accuracy of the CPC by using the corrected corrected CVR, it is possible to make it easier to achieve the target CPA set by the advertiser.

[2. Information processing device configuration]
Next, the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram showing a configuration example of the information processing device 100 according to the embodiment. As shown in FIG. 2, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 110 is connected to the network by wire or wirelessly, and transmits / receives information to / from, for example, the terminal device 20 or the information providing device 30.

The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 includes a user information storage unit 121, an advertisement content storage unit 122, a history information storage unit 123, and a prediction model storage unit 124.

(About user information storage unit 121)
The user information storage unit 121 stores information regarding actions taken by the user with respect to the content. In the present embodiment, the user information storage unit 121 stores a search keyword or the like used by the user for information retrieval in a predetermined content (for example, a search site) as a search history. Here, FIG. 3 shows an example of the user information storage unit 121 according to the embodiment. In the example of FIG. 3, the user information storage unit 121 has items such as "user ID", "search keyword", and "search date and time". The user information storage unit 121 shown in FIG. 3 describes the user information storage unit shown in FIG. 1 in more detail.

The "user ID" indicates identification information for identifying the user or the terminal device 20 used by the user. The "search keyword" indicates a search keyword used by the user for information retrieval in a predetermined content. The "search date and time" indicates the date and time when the user searches for information by inputting the "search keyword" in the predetermined content.

That is, in the example of FIG. 3, the user identified by the user ID "U1" searches for information by inputting the search keyword "insurance" in the predetermined content at "15:30 on March 1, 2019". An example is shown. As shown in FIG. 1, a user ID may be used to distinguish between users. For example, the user identified by the user ID "U1" is referred to as the user U1. Similarly, the advertiser, the advertisement content, and the LP are described using the identification information.

Here, in the present embodiment, the predetermined content is provided by the information providing device 30. For example, the information providing device 30 distributes a search site or the like, which is predetermined content, to the terminal device 20 in response to an access from the terminal device 20 by a user operation. Therefore, the information providing device 30 stores the search history in a predetermined storage unit in the own device.

Therefore, for example, the information processing device 100 acquires the search history from the information providing device 30 by periodically accessing the information providing device 30, and stores the acquired search history in the user information storage unit 121. Not limited to this example, the information processing device 100 may acquire the search history from, for example, the terminal device 20. For example, each time the information search is performed by the user, the terminal device 20 associates the user ID, the search keyword, and the search date and time with each other and transmits the information to the information processing device 100. As a result, the information processing device 100 acquires the search history from the terminal device 20.

(About advertising content storage unit 122)
The advertisement content storage unit 122 stores various information related to the advertisement content submitted from the advertiser terminal 10 and the advertisement content set by the advertiser terminal 10. In addition, the advertisement content storage unit 122 stores performance information related to advertisement distribution. Here, FIG. 4 shows an example of the advertisement content storage unit 122 according to the embodiment. In the example of FIG. 4, the advertisement content storage unit 122 has "advertiser ID", "advertisement ID", "advertisement content", "LP-ID", "LP-URL", "target CPA", "keyword", It has items such as "clicks", "CTR", and "conversions". The advertisement content storage unit 122 shown in FIG. 4 describes the advertisement content storage unit shown in FIG. 1 in more detail.

The "advertiser ID" indicates identification information for identifying an advertiser or an advertiser terminal. The "advertisement ID" indicates identification information for identifying the advertisement content. The "advertising content" indicates the advertising content submitted from the advertiser terminal 10. FIG. 4 shows an example in which conceptual information is stored in the “advertising content”, but in reality, still images, moving images, text data, file path names indicating their storage locations, and the like are stored. NS.

The "LP-ID" indicates identification information for identifying the transition destination content (landing page) to be transitioned when the corresponding advertising content is selected. “LP-URL” indicates the URL of the transition destination content. The "LP-URL" is attached to the advertisement content, for example, and is distributed together with the advertisement content.

The "target CPA" indicates a result that leads to profits such as product purchase and membership registration from the corresponding advertising content, that is, a target value of the conversion unit price, which is the cost related to acquiring one conversion. The "target CPA" can be set only for the advertising content for which a predetermined number (for example, "10") or more of conversions have been obtained. The "keyword" is information used for targeting the user, and indicates what kind of content the advertising content is. The "keyword" may be freely set by the advertiser, or may be selected by the advertiser by presenting a keyword as a candidate for the information processing device 100.

"Clicks" indicates the number of times the advertising content has been clicked so far. "CTR" is a value obtained by dividing "the number of clicks" by the number of impressions of the advertisement content. The CTR of the advertising content that has never been delivered to the terminal device 20 includes a predetermined fixed value, an average value of the CTR in all the advertising content, and the same advertising category (for example, "car", "car", " The average value of CTR etc. in all the advertising contents belonging to "Travel") is stored. "Conversions" indicates the number of clicks and conversions of advertising content so far.

That is, in the example of FIG. 4, an example is shown in which the advertiser identified by the advertiser ID "C1" has submitted the data "XX11" of the advertisement content as the advertisement content identified by the advertisement ID "AD11". .. Further, the advertiser C1 specifies the URL "aa11.com" of the LP identified by the LP-ID "LP11" for the advertising content "AD11", and sets the target CPA "15,000" and the keyword. An example of setting "insurance" is shown.

(About history information storage unit 123)
The history information storage unit 123 stores the height of the hurdle until the user reaches the conversion in the LP of the advertisement content delivered to the user. Here, FIG. 5 shows an example of the history information storage unit 123 according to the embodiment. In the example of FIG. 5, the history information storage unit 123 has items such as "advertiser ID", "advertisement ID", "search query", "LP-ID", and "hurdle".

The "advertiser ID", "advertisement ID", and "LP-ID" are the same as those shown in FIG. 4, and thus the description thereof will be omitted here. Further, the "search query" here indicates a search query that is the target of the "keyword" associated with the advertisement content when the corresponding advertisement content is determined as the distribution target. “Hurdle” indicates the height of the hurdle for the user to convert in LP.

Here, the "row" at the top of the history information storage unit 123 indicates that the advertisement content AD11 is displayed to the user who has recently performed an information search using the search query "insurance". Further, it is shown that the height of the hurdle to conversion in LP11 corresponding to the advertisement content AD11 is "1". This is because such a user is interested in "insurance" at the present time, so that it is easy to convert in LP11 displayed by clicking the advertisement content AD11 related to "insurance".

On the other hand, the third "row" of the history information storage unit 123 indicates that the advertisement content AD11 is displayed to the user who has recently performed an information search using the search query "foreign capital". Depending on the distribution logic of the information processing device 100, the advertisement content AD11 may be distributed to a user who has a search query not included in the keyword associated with the advertisement content AD11 in this way. Further, it is shown that the height of the hurdle to conversion in LP11 corresponding to the advertisement content AD11 is "5". This is because the user is currently interested in "foreign capital" and not in the advertising content AD11 or LP11 related to "insurance", so it is unlikely that the user will click on the advertising content AD11 in the first place. This is because even if the transition is made, it is difficult to reach conversion in the LP11 displayed by clicking the advertisement content AD11 related to "insurance".

Further, although not shown, it is recognized that the lower the hurdle to conversion, the more likely the user is to convert. Therefore, as described above, a correlation is established between the height of the hurdle leading to conversion and the conversion rate.

Here, an example of an estimation method for estimating the height of the hurdle leading to conversion will be described. For example, the information processing device 100 estimates the height of the hurdle by analyzing cases that have reached conversion and cases that have not reached conversion from past history information (log information) by machine learning, data mining, or the like. do. Alternatively, the information processing device 100 estimates the height of the hurdle by using crowdsourcing or a questionnaire. For example, the information processing device 100 conducts a questionnaire to the user about the height of the hurdle to the conversion at the time when the advertisement content is clicked and the time when the conversion in the LP is performed. Obtain a hurdle height score as a result of the questionnaire. Then, the information processing device 100 performs machine learning on the score of the height of the hurdle collected from each user, and estimates the height of the hurdle. In reality, the information processing apparatus 100 may obtain the average value or the median value of the hurdle height scores collected from the information processing apparatus 100. In addition, the questionnaire about the height of the hurdle to conversion may be conducted not only to users but also to advertisers and experts. As a result, the information processing device 100 stores the estimated height of the hurdle in the history information storage unit 123 together with the search query that is the target when the advertisement content is determined as the distribution target.

(About the prediction model storage unit 124)
The prediction model storage unit 124 stores the prediction model. For example, the prediction model storage unit 124 stores the prediction model generated for each advertisement content by the generation unit 134 described later. Here, FIG. 6 shows an example of the prediction model storage unit 124 according to the embodiment. In the example of FIG. 6, the prediction model storage unit 124 has items such as “advertisement ID”, “LP-ID”, and “prediction model”.

The "advertisement ID" and "LP-ID" are as described above. That is, the example of FIG. 6 shows an example in which the prediction model M11 for estimating the height of the hurdle until the user reaches the conversion is generated by the generation unit 134 in the LP11 corresponding to the advertisement content AD11.

(About control unit 130)
Returning to FIG. 2, in the control unit 130, various programs stored in the storage device inside the information processing device 100 are executed by the CPU (Central Processing Unit), the MPU (Micro Processing Unit), or the like using the RAM as a work area. It is realized by. Further, the control unit 130 is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 2, the control unit 130 includes a reception unit 131, an estimation unit 132, a correction unit 133, a generation unit 134, a prediction unit 135, an extraction unit 136, and a distribution unit 137. Realize or execute the information processing functions and actions described below. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 2, and may be another configuration as long as it is a configuration for performing information processing described later. Further, the connection relationship of each processing unit included in the control unit 130 is not limited to the connection relationship shown in FIG. 2, and may be another connection relationship.

(About reception desk 131)
The reception unit 131 receives the submission of the advertisement content and the setting of various information related to the advertisement content from the advertiser terminal 10, and stores the received advertisement content and the setting information in the advertisement content storage unit 122. Specifically, the reception unit 131 accepts the submission of advertising content corresponding to still images, moving images, text data, etc., and the setting of LP-URL, target CPA, keywords, and the like.

Then, the reception unit 131 pays out the advertiser ID and the advertisement ID, and stores the received information as described above in the advertisement content storage unit 122 in association with the paid out advertiser ID and the advertisement ID. The target CPA can be set only for the advertising content for which a predetermined number (for example, "10") or more of conversions have been obtained.

In addition, the reception unit 131 receives an advertisement content acquisition request from the terminal device 20. For example, the reception unit 131 receives a web page acquisition request by an HTTP (Hypertext Transfer Protocol) request or the like.

(About estimation unit 132)
The estimation unit 132 is an index value regarding the transition destination content (an example of the second content) that is the transition destination of the advertisement content (an example of the first content), and is a distribution that delivers the advertisement content for each distribution candidate advertisement content. Estimate the height of the hurdle for the target user to convert. For example, in the estimation unit 132, when the reception unit 131 receives the advertisement content acquisition request, the distribution target user reaches the conversion for each transition destination content corresponding to each of the distribution candidate advertisement contents. Estimate the height of the hurdle.

Here, an example of the estimation process by the estimation unit 132 will be described. For example, it is assumed that the terminal device 20 transmits a request for acquiring the advertisement content to the information processing device 100 according to the operation of the user U1. Then, when the reception unit 131 receives the acquisition request, the estimation unit 132 first identifies the advertisement content of the distribution candidate. For example, the estimation unit 132 refers to the user information storage unit 121 and identifies the latest search query with a date as the search query recently used by the user U1. In the example of the user information storage unit 121 shown in FIG. 3, the estimation unit 132 specifies the search query "insurance" as the search query in which the user U1 has the latest date.

Next, the estimation unit 132 refers to the advertisement content storage unit 122, and identifies the advertisement content to which the keyword including the specified search query “insurance” is associated. In the example of the advertisement content storage unit 122 shown in FIG. 4, the estimation unit 132 specifies the advertisement contents AD11 and AD21 to which the keyword including the search query “insurance” is associated as the advertisement contents of the distribution candidates. From this, it is highly likely that user U1 is currently interested in "insurance".

Next, when the estimation unit 132 accesses LP11 and LP21 corresponding to the advertisement contents AD11 and AD21, respectively, the estimation unit 132 estimates the height of the hurdle leading to conversion in each LP. Specifically, the estimation unit 132 estimates the height of the hurdle to conversion in each LP by using crowdsourcing or a questionnaire. Alternatively, the estimation unit 132 estimates the height of the hurdle to conversion in each LP from the past history information (log information) related to the advertisement distribution.

Furthermore, when a user overcomes a high hurdle and reaches a conversion, it can be said that the degree of interest the user shows in the advertising content or the importance / effect of the advertising content to the user is high. That is, when conversion is reached, the height of the hurdle is the high degree of interest the user shows in the advertisement content, or the importance / effect of the advertisement content to the user. Therefore, the estimation unit 132 determines the degree of interest the user shows in the advertising content or the importance / effect of the advertising content to the user based on the height of the hurdle to the conversion of the user. presume.

(About correction unit 133)
The correction unit 133 corrects the conversion rate (CVR) of the advertising content based on the height of the hurdle leading to the conversion estimated by the estimation unit 132, and calculates the correction value (correction CVR) of the conversion rate. .. Specifically, the correction unit 133 sets a weight value corresponding to the height of the hurdle to the conversion estimated in the LP corresponding to the advertisement content of the distribution candidate with respect to the conversion rate of the advertisement content of the distribution candidate. Correct the conversion rate by multiplying.

An example of the correction process by the correction unit 133 will be described. As described above, it is assumed that the advertisement contents of the distribution candidates are the advertisement contents AD11 and AD21. Then, it is assumed that "2" and "1" are estimated by the estimation unit 132 as the height of the hurdle to conversion in LP11 and LP21 corresponding to the respective advertisement contents.

In such a case, first, the correction unit 133 calculates the CVR of each of the advertisement contents AD11 and AD21. For example, the correction unit 133 refers to the advertisement content storage unit 122, and calculates the CVR by dividing the number of conversions by the number of clicks for each of the advertisement contents AD11 and AD21.

In the example of the advertisement content storage unit 122 shown in FIG. 4, the correction unit 133 calculates the CVR “0.05” of the advertisement content AD 11 by dividing the conversion number “15” by the click number “300”. Further, the correction unit 133 calculates the CVR "0.03" of the advertisement content AD11 by dividing the conversion number "27" by the click number "900".

Here, the correction unit 133 considers, for example, the estimated hurdle height as a weight value. Specifically, the correction unit 133 sets the estimated hurdle height “2” in LP11 as the weight value “2”. Then, the correction unit 133 sets the value "0.1" calculated by multiplying the CVR "0.05" of the advertisement content AD11 by the weight value "2" as the correction CVR that corrects the CVR of the advertisement content AD11. do. That is, the correction unit 133 corrects the CVR "0.05" of the advertisement content AD11 to obtain the correction CVR "0.1" as the correction value of the advertisement content AD11.

Further, the correction unit 133 sets the estimated hurdle height “1” in LP21 as the weight value “1”. Then, the correction unit 133 sets the value "0.03" calculated by multiplying the CVR "0.03" of the advertisement content AD21 by the weight value "1" as the correction CVR corrected for the CVR of the advertisement content AD12. do.

Here, an example is shown in which the correction unit 133 calculates the CVR using the number of conversions and the number of clicks obtained as actual results, but the one calculated from the actual values often lacks reliability. Therefore, the generation unit 134, which will be described later, may generate a CVR prediction model in advance by machine learning, so that the correction unit 133 may calculate the CVR using the CVR prediction model.

Although the correction unit 133 has shown an example in which the estimated hurdle height is used as it is as a weight value, the present invention is not limited to this. For example, the correction unit 133 may use a predetermined weight value according to the height of the hurdle leading to conversion. As an example, "hurdle height range: ~ 1" (weight value "1"), "hurdle height range: 2-3" (weight value "1.1"), "hurdle height range: 4 ~" A weight value may be set in advance for each hurdle height range, such as "5" (weight value "1.2"). In such a case, the correction unit 133 corrects the conversion rate (CVR) by using the weight value associated with the hurdle height range including the estimated hurdle height calculated by the estimation unit 132, and corrects the conversion rate. (Corrected CVR) is calculated.

(About the generator 134)
The generation unit 134 generates a prediction model for each advertisement content. Specifically, the generation unit 134 generates a prediction model for each advertisement content for the user to be distributed to predict the correction value of the conversion rate in each LP corresponding to the advertisement content. It is assumed that the conversion type is preset for each advertising content.

For example, the generation unit 134 makes an advertisement by machine learning "what kind of user" is "what kind of conversion rate" in the LP of "what kind of advertisement content" for each advertisement content. Generate a prediction model for each content. Then, the generation unit 134 uses the user information about the user and the advertisement information about the advertisement content as explanatory variables, and the correction value of the conversion rate (correction CVR) as the objective variable. Then, the generation unit 134 generates a prediction model, which is a model that fits between the explanatory variable and the objective variable.

More specifically, the generation unit 134 sets the explanatory variable X1 corresponding to the search query input to the user in the history information storage unit 123. Further, the generation unit 134 uses the explanatory variable X2 as the explanatory variable corresponding to the advertisement content delivered to the user. Then, the generation unit 134 estimates the coefficient by combining the explanatory variables X1 and X2 and performing regression analysis (for example, Poisson regression) on the objective variable Y corresponding to the correction value of the conversion rate. Then, the generation unit 134 generates a prediction model for predicting the objective variable Y using the estimated coefficient.

Hereinafter, an example of the prediction model generation process by the generation unit 134 will be described. Here, a case where the generation unit 134 generates the prediction model M11 corresponding to the advertisement content AD11 will be described.

For example, the generation unit 134 refers to the history information storage unit 123 shown in FIG. 5, and each user who displays the advertisement content AD11 associated with the keyword “insurance” acquires and acquires the recently used search query. Aggregate the number of users for each search query. Further, the generation unit 134 acquires a correction value (correction CVR) of the conversion rate from the correction unit 133 as a probability that each user displaying the advertisement content AD 11 will reach a conversion in the LP 11 corresponding to the advertisement content AD 11.

Then, the generation unit 134 machine-learns what kind of tendency the conversion rate in LP11 shows according to the search query used by the user, based on the acquired correction value of the conversion rate (correction CVR). Then, the generation unit 134 sets the search query used by the user as the explanatory variable X1, the keyword associated with the advertisement content AD11 as the explanatory variable X2, and the conversion rate correction value (corrected CVR) as the objective variable Y. Then, the generation unit 134 generates a prediction model M11 for predicting the objective variable Y by combining the explanatory variables X1 and X2 and performing regression analysis on the objective variable Y. Then, the generation unit 134 stores the generated prediction model M11 in the prediction model storage unit 124.

(About Prediction Unit 135)
The prediction unit 135 predicts the correction value of the conversion rate based on the prediction model of the correction value of the conversion rate generated by the generation unit 134. That is, the prediction unit 135 performs a process for obtaining the correction value (correction CVR) of the conversion rate by using the prediction model of the correction value of the conversion rate instead of the estimation unit 132 and the correction unit 133.

Here, an example of the prediction process by the prediction unit 135 will be described. For example, it is assumed that the terminal device 20 transmits a request for acquiring the advertisement content to the information processing device 100 according to the operation of the user U1. Then, when the reception unit 131 receives the acquisition request, the prediction unit 135 first identifies the advertisement content of the distribution candidate. For example, the prediction unit 135 refers to the user information storage unit 121 and identifies the latest search query with a date as the search query recently used by the user U1. In the example of the user information storage unit 121 shown in FIG. 3, the prediction unit 135 specifies the search query "insurance" as the search query in which the user U1 has the latest date.

Next, the prediction unit 135 refers to the advertisement content storage unit 122, and identifies the advertisement content to which the keyword including the specified search query “insurance” is associated. In the example of the advertisement content storage unit 122 shown in FIG. 4, the prediction unit 135 specifies the advertisement contents AD11 and AD21 to which the keyword including the search query “insurance” is associated as the advertisement contents of the distribution candidates. From this, it is highly likely that user U1 is currently interested in "insurance".

Next, when the prediction unit 135 accesses LP11 and LP21 corresponding to the advertisement contents AD11 and AD21, respectively, the prediction unit 135 predicts the correction value of the conversion rate in each LP. Specifically, the prediction unit 135 applies the search query "insurance" of the user U1 and the keyword "insurance" of the advertisement content AD11 to the prediction model M11 corresponding to the advertisement content AD11. Then, the prediction unit 135 predicts that the output correction value of the conversion rate (correction CVR) is the correction value of the conversion rate in LP11.

Similarly, the prediction unit 135 applies the search query "insurance" of the user U1 and the keyword "insurance" of the advertisement content AD21 to the prediction model M21 corresponding to the advertisement content AD21. Then, the information processing apparatus 100 predicts that the output correction value of the conversion rate (correction CVR) is the correction value of the conversion rate in the LP 21.

(About extraction unit 136)
The extraction unit 136 extracts the advertisement content to be distributed. Specifically, the extraction unit 136 extracts the advertisement content to be distributed based on the conversion rate obtained by the above processing. At this time, the extraction unit 136 calculates the CPC by multiplying the corrected CVR and the target CPA. Then, the extraction unit 136 calculates the eCPM by multiplying the calculated CPC and the CTR. The extraction unit 136 extracts the advertisement content to be distributed based on the calculated eCPM. Therefore, the extraction unit 136 is a processing unit corresponding to the calculation unit. The extraction unit 136 may extract the advertisement content to be distributed based on the correction CVR calculated by the correction unit 133.

In the example of the advertisement content storage unit 122 shown in FIG. 4, the target CPA “15,000” is set in the advertisement content AD11. In such a case, the extraction unit 136 multiplies the correction CVR “0.1” of the advertisement content AD11 and the target CPA “15,000” to calculate the CPC “1,500” of the advertisement content AD11. Further, in the example of the advertising content shown in FIG. 3, the CTR of the advertising content AD11 is “0.05”. Therefore, the extraction unit 136 multiplies the CPC "1,500" of the advertisement content AD11 and the CTR "0.05" to calculate the eCPM "75" of the advertisement content AD11.

Further, in the example of the advertisement content storage unit 122 shown in FIG. 4, the target CPA "20,000" is set in the advertisement content AD21. In such a case, the extraction unit 136 calculates the CPC “600” of the advertisement content AD21 by multiplying the correction CVR “0.03” of the advertisement content AD21 and the target CPA “20,000”. Further, in the example of the advertising content shown in FIG. 3, the CTR of the advertising content AD21 is “0.03”. Therefore, the extraction unit 136 multiplies the CPC “600” of the advertisement content AD21 and the CTR “0.03” to calculate the eCPM “18” of the advertisement content AD21.

Of the two correction CVRs calculated by the correction unit, the extraction unit 136 extracts the advertisement content AD21 for which the correction CVR having the larger value is calculated from the advertisement content storage unit 122 as the advertisement content to be distributed.

The extraction unit 136 may extract the advertisement content to be distributed from the advertisement content storage unit 122 based on the height of the hurdle estimated by the estimation unit 132. For example, the extraction unit 136 may extract the advertisement content AD11 with a low hurdle estimated by the estimation unit 132 from the advertisement content storage unit 122 as the advertisement content to be distributed. Further, the extraction unit 136 may extract the advertisement content AD21 for which the eCPM having the larger value is calculated out of the two eCPMs calculated as described above from the advertisement content storage unit 122 as the advertisement content to be distributed.

As described above, in the present embodiment, the estimation unit 132 performs the estimation process every time the request for acquisition of the advertisement content is received from the terminal device 20. After the generation unit 134 generates the prediction model, the prediction unit 135 may perform the prediction process every time the request for acquisition of the advertisement content is received from the terminal device 20. Then, the extraction unit 136 also calculates the CPC each time the request for acquisition of the advertisement content is received from the terminal device 20 according to the estimation process by the estimation unit 132 or the prediction process by the prediction unit 135. Therefore, even if the content is the same, the CPC may differ depending on the time of distribution. Therefore, the information processing apparatus 100 may be configured so that once the CPC is calculated, the CPC is not calculated for a certain period of time.

(About distribution unit 137)
The distribution unit 137 distributes the advertisement content extracted by the extraction unit 136 to the terminal device 20. For example, the distribution unit 137 associates predetermined information with the advertisement content extracted by the extraction unit 136 and distributes it to the terminal device 20.

Explaining using an example in which the advertisement content AD21 is extracted by the extraction unit 136, the distribution unit 137 attaches the URL of the LP21 to the advertisement content AD21. In the example of the advertisement content storage unit 122 shown in FIG. 4, the distribution unit 137 attaches the URL “bb21.com” of the LP21 to the advertisement content AD21. The distribution unit 137 includes information indicating the CPC calculated by the extraction unit 136 in the advertisement content AD21. Then, the distribution unit 137 distributes the advertisement content AD 21 to the terminal device 20.

In addition, the distribution unit 137 may receive information that the advertisement content has been clicked from the terminal device 20. For example, the distribution unit 137 updates the corresponding number of clicks in the advertisement content storage unit 122 every time the information that the advertisement content is clicked is received from the terminal device 20.

In addition, the distribution unit 137 may receive information from the terminal device 20 that the conversion has been obtained. For example, each time the distribution unit 137 receives information regarding conversion acquisition from the terminal device 20, the distribution unit 137 updates the corresponding number of conversions in the storage in the advertisement content storage unit 122.

[3. Processing procedure]
Next, the procedure of information processing executed by the information processing apparatus 100 according to the embodiment will be described with reference to FIG. 7. FIG. 7 is a flowchart showing an information processing procedure by the information processing apparatus 100 according to the embodiment.

First, the reception unit 131 of the information processing device 100 determines whether or not the request for acquisition of the advertisement content has been accepted (step S101). If the reception unit 131 has not received the acquisition request (step S101; No), the reception unit 131 waits until the acquisition request is received.

On the other hand, when the acquisition request is received by the reception unit 131 (step S101; Yes), the estimation unit 132 identifies the advertisement content of the distribution candidate (step S102). Next, the estimation unit 132 selects one unprocessed advertisement content for which eCPM has not been calculated from the specified distribution candidate advertisement contents (step S103).

Then, the estimation unit 132 has a high hurdle that the distribution target user (user of the acquisition request transmission source) must overcome before the conversion in the LP corresponding to the selected distribution candidate advertisement content (advertisement content i). Is estimated (step S104).

Next, the correction unit 133 corrects the conversion rate (CVR) of the advertisement content i using the estimated hurdle height estimated in step S104, and calculates the correction value (correction CVR) of the conversion rate (step). S105).

Although not shown, after calculating the conversion rate correction value (correction CVR), the generation unit 134 generates a prediction model of the conversion rate correction value (correction CVR) for each advertisement content. The prediction unit 135 predicts the correction value of the conversion rate based on the prediction model generated by the generation unit 134. That is, after the prediction model is generated, the prediction unit 135 obtains the correction value (correction CVR) of the conversion rate by using the prediction model instead of the estimation unit 132 and the correction unit 133 in the above steps S104 and S105. Perform the processing for.

Next, the extraction unit 136 calculates the eCPM of the advertisement content i (step S106). Specifically, the extraction unit 136 calculates the CPC by multiplying the corrected CVR calculated in step S105 and the target CPA of the advertisement content i, and also multiplies the calculated CPV and the CTR of the advertisement content i to eCPM. Is calculated.

Here, the extraction unit 136 determines whether or not there is unprocessed advertising content for which eCPM has not been calculated among the distribution candidate products specified in step S102 (step S107). Then, when the unprocessed product exists (step S107; Yes), the extraction unit 136 repeats the processing from step S103.

On the other hand, when the extraction unit 136 determines that there is no unprocessed advertisement content (step S107; No), the extraction unit 136 delivers the content based on the height of the hurdle estimated in step S106 or the eCPM calculated in step S106. Extract the target advertising content (step S108). Then, the distribution unit 137 distributes the advertisement content extracted in step S107 to the terminal device 20 (step S109).

[4. Modification example]
The information processing apparatus 100 according to the above embodiment may be implemented in various different forms other than the above embodiment. Therefore, another embodiment of the information processing apparatus 100 will be described below.

In the above embodiment, the information processing apparatus 100 may update the prediction model every time / periodically / every predetermined number of cases even after the prediction model of the correction value of the conversion rate is generated. As the number of ad servings and conversions increases, so does the conversion rate. Therefore, it is preferable that the information processing apparatus 100 updates the prediction model as appropriate. The procedure for updating the prediction model may be the same as the procedure for generating the prediction model. In this case, the information processing apparatus 100 overwrites the existing prediction model with the newly generated prediction model.

Further, in the above embodiment, for example, regarding the weight value corresponding to the estimated hurdle height, the advertisement click has a weight value of "1", the landing page stay has a weight value of "2", the material request has a weight value of "3", and the questionnaire response. May have a weight value of "4", and product purchase (contract establishment) may have a weight value of "5".

Further, in the above embodiment, the height of the hurdle leading to conversion in LP is represented by one element (item), but in reality, it may be represented by a plurality of elements. Further, the weight value corresponding to the estimated hurdle height may be any of the total value, the average value, or the median value of the weight values of the plurality of elements. For example, regarding the height of the hurdle to reach a certain conversion, "user is not interested in the content of the advertisement" (weight value "5"), "request for materials" (weight value "3"), "button size" When represented by a plurality of elements such as (weight value "1"), the weight value corresponding to the estimated hurdle height may be either the total value "9", the average value "3", or the median value "3". good.

Further, in the above embodiment, the height of the hurdle leading to conversion is predicted each time in LP, but in reality, a list may be created in advance for each hurdle leading to conversion.

Further, in the above embodiment, the advertising content may be a mini game or the like. For example, when the advertising content is a treasure hunt game, the height of the hurdle for the user to convert may be estimated by using hints, finding and acquiring items, clearing a predetermined number of stages, and the like as conversions.

Further, in the above embodiment, the machine learning performed by the information processing apparatus 100 may be, for example, deep learning (deep learning) using a deep neural network or the like. Further, the information processing apparatus 100 may use data mining or other machine learning algorithms.

[5. Hardware configuration]
The information processing apparatus 100 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. Hereinafter, the information processing apparatus 100 will be described as an example. FIG. 8 is a hardware configuration diagram showing an example of a computer 1000 that realizes the functions of the information processing device 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F). ) Has 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program depending on the hardware of the computer 1000, and the like.

The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 receives data from another device via the communication network 50 (corresponding to the network N shown in FIG. 2) and sends the data to the CPU 1100, and the data generated by the CPU 1100 is transmitted to the other device via the communication network 50. Send to the device.

The CPU 1100 controls an output device such as a display or a printer, and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the data generated via the input / output interface 1600 to the output device.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. And so on.

For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the RAM 1200. Further, the data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via the communication network 50.

[6. effect〕
As described above, the information processing device 100 according to the present application estimates the height (difficulty) of hurdles that a user (user) who has accessed the advertisement content must overcome before conversion (implementation of a predetermined action). The estimation unit 132 is provided, and the correction unit 133 that corrects the conversion rate (execution rate of a predetermined action) based on the height of the hurdle for each advertisement content. As a result, the accuracy of predicting the conversion rate can be improved in consideration of the height of the hurdle leading to conversion.

The estimation unit 132 estimates the degree of interest the user shows in the advertising content based on the height of the hurdle. As a result, when the user overcomes a high hurdle and reaches a conversion, it can be estimated that the degree of interest the user shows in the advertising content is high.

In addition, the estimation unit 132 estimates the height of the hurdle using at least one of crowdsourcing and the questionnaire. This makes it possible to generate a prediction model that takes into account the height of the hurdle to conversion based on the results of crowdsourcing or questionnaires to users, advertisers, and the like.

In addition, the estimation unit 132 estimates the height of the hurdle from the past history information of the user who has accessed the advertisement content. This makes it possible to estimate the height of the hurdle leading to conversion based on past log information.

In addition, the estimation unit 132 estimates the height of the hurdle from the user's behavior leading up to the conversion. As a result, the height of the hurdle to conversion can be estimated based on the behavior of the user other than the conversion.

Further, the estimation unit 132 estimates the height of the hurdle from the number of operations performed until the conversion. This makes it possible to estimate the height of the hurdle to conversion based on the number of operations performed by the user before conversion.

In addition, the estimation unit 132 estimates the height of the hurdle from the time elapsed from the display of the advertisement content to the execution of a predetermined action. This makes it possible to estimate the height of the hurdle to conversion based on the actions taken by the user before conversion.

In addition, the estimation unit 132 estimates the height of the hurdle according to the advertisement target. This makes it possible to estimate the height of the hurdle to conversion based on the target product of the advertisement.

In addition, the estimation unit 132 estimates the height of the hurdle according to the appearance of the advertisement content. This makes it possible to estimate the height of the hurdle to conversion based on the appearance of the advertising content.

Further, the information processing apparatus 100 according to the present application further includes a generation unit that generates a prediction model for predicting a correction value of the conversion rate. This makes it possible to predict the correction value of the conversion rate using the prediction model.

In addition, the generation unit 134 generates a different prediction model for each type of predetermined action. This makes it possible to generate different prediction models for each type of conversion.

In addition, the generation unit 134 generates a different prediction model for each advertisement content. This makes it possible to generate a different prediction model for each advertising content.

The information processing apparatus 100 according to the present application further includes a prediction unit that predicts a correction value of the conversion rate by using a prediction model. As a result, the correction value of the conversion rate can be predicted.

Further, the information processing apparatus 100 according to the present application further includes an extraction unit 136 that extracts the advertisement content to be distributed based on the correction value of the conversion rate from the candidates for the advertisement content. As a result, it is possible to select the advertisement content to be distributed from the candidates for the advertisement content based on the correction value of the conversion rate.

[7. others〕
Although the embodiments of the present application have been described above, the present invention is not limited to the contents of these embodiments. Further, the above-mentioned components include those that can be easily assumed by those skilled in the art, those that are substantially the same, that is, those having a so-called equal range. Furthermore, the components described above can be combined as appropriate. Further, various omissions, replacements or changes of the components can be made without departing from the gist of the above-described embodiment.

Further, among the processes described in the above-described embodiment, all or a part of the processes described as being automatically performed can be manually performed, or the processes described as being manually performed can be performed. All or part of it can be done automatically by a known method. In addition, the processing procedure, specific name, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of the device is functionally or physically dispersed / physically distributed in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

For example, the information processing device 100 described above may be realized by a plurality of server computers, or may be realized by calling an external platform or the like by API (Application Programming Interface), network computing, or the like depending on the function. Can be changed flexibly.

Further, the above-described embodiments and modifications can be appropriately combined as long as the processing contents do not contradict each other.

Further, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the reception unit can be read as a reception means or a reception circuit.

1 Information processing system 10 Advertiser terminal 20 Terminal device 30 Information providing device 100 Information processing device 121 User information storage unit 122 Advertising content storage unit 123 History information storage unit 124 Prediction model storage unit 130 Control unit 131 Reception unit 132 Estimating unit 133 Correction Part 134 Generation part 135 Prediction part 136 Extraction part 137 Distribution part

Claims (17)

A reception unit that accepts the submission of advertising content from the advertiser terminal and the setting of the target value of the unit price related to the execution of a predetermined action for the advertising content.
An estimation unit which the user who has accessed the advertisement content to estimate the difficulty of up to the implementation of the predetermined action,
Each advertising content is provided with a correction unit that corrects the execution rate of the predetermined action based on the difficulty .
The estimation unit presumes that if the predetermined action does not involve the expenditure of the user or is easy to operate for implementation, the difficulty is low and the predetermined action is likely to be carried out. An information processing apparatus characterized in that when the action is accompanied by expenditure of the user or it is difficult to perform an operation for carrying out the action, it is presumed that the difficulty is high and it is difficult to carry out the predetermined action. By multiplying the execution rate of the predetermined action and the target value of the unit price related to the execution of the predetermined action, the bid unit price, which is the amount to be charged to the advertiser terminal when the advertisement content is selected, is calculated. Calculation part and
Based on the calculated bid unit price, the distribution unit that distributes the advertisement content and
The information processing apparatus according to claim 1, further comprising. The information processing device according to claim 1 or 2 , wherein the estimation unit estimates the degree of interest the user shows in the advertising content based on the difficulty. The information processing apparatus according to any one of claims 1 to 3, wherein the estimation unit estimates the difficulty using at least one of crowdsourcing and a questionnaire. The information processing device according to any one of claims 1 to 4 , wherein the estimation unit estimates the difficulty from the past history information of a user who has accessed the advertisement content. The information processing device according to any one of claims 1 to 5 , wherein the estimation unit estimates the difficulty from the behavior of the user who has performed the predetermined behavior. The information processing apparatus according to any one of claims 1 to 6 , wherein the estimation unit estimates the difficulty from the number of operations performed until the predetermined action is performed. The information according to any one of claims 1 to 7 , wherein the estimation unit estimates the difficulty from the time elapsed from the display of the advertisement content to the performance of the predetermined action. Processing equipment. The information processing device according to any one of claims 1 to 8 , wherein the estimation unit estimates the difficulty according to an advertisement target. The information processing device according to any one of claims 1 to 9 , wherein the estimation unit estimates the difficulty according to the appearance of the advertisement content. The information processing apparatus according to any one of claims 1 to 10 , further comprising a generation unit that generates a prediction model for predicting a correction value of the execution rate of the predetermined action. The information processing device according to claim 11 , wherein the generation unit generates different prediction models for each type of predetermined action. The information processing device according to claim 11 or 12 , wherein the generation unit generates a different prediction model for each advertisement content. The information processing apparatus according to any one of claims 11 to 13 , further comprising a prediction unit that predicts a correction value of an execution rate of the predetermined action by using the prediction model. The invention according to any one of claims 1 to 14 , further comprising an extraction unit that extracts the advertisement content to be distributed based on the correction value of the implementation rate of the predetermined action from the candidates for the advertisement content. Information processing equipment. It is an information processing method executed by an information processing device.
A reception process that accepts the submission of advertising content from the advertiser terminal and the setting of the target value of the unit price related to the implementation of the predetermined action for the advertising content.
An estimation step of the user who has accessed the advertisement content to estimate the difficulty of up to the implementation of the predetermined action,
Based on the difficulty for each advertising content viewed contains a correction step of correcting the implementation rate of the predetermined action,
In the estimation step, when the predetermined action does not involve the expenditure of the user or the operation for implementation is easy, it is estimated that the difficulty is low and the predetermined action is likely to be carried out. An information processing method, characterized in that, when the behavior of the user is accompanied by expenditure of the user or it is difficult to perform an operation for carrying out the behavior, it is presumed that the difficulty is high and it is difficult to carry out the predetermined behavior. The reception procedure for accepting the submission of the advertisement content and the setting of the target value of the unit price related to the execution of the predetermined action for the advertisement content from the advertiser terminal.
And estimation procedure that the user who has accessed the advertisement content to estimate the difficulty of up to the implementation of the predetermined action,
Based on the difficulty for each advertising content, the computer is made to execute a correction procedure for correcting the execution rate of the predetermined action .
In the estimation procedure, when the predetermined action does not involve the expenditure of the user or the operation for implementation is easy, it is estimated that the difficulty is low and the predetermined action is likely to be carried out. An information processing program characterized in that when the behavior of the user is accompanied by expenditure of the user or it is difficult to perform an operation for implementation, it is presumed that the difficulty is high and it is difficult to carry out the predetermined behavior.

Images