JP7354198B2 - Information processing device, information processing method, and information processing program - 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 become popular. As an example of such advertisement distribution, a technique has been proposed that maximizes advertising profit by controlling the bid amount for an advertisement space based on past bid results (see, for example, Patent Document 1). Regarding automatic bidding for such advertising spaces, the bid amount is determined, for example, by multiplying the target CPA (Cost Per Action) set by the advertiser by the conversion rate.

JP 2019-220052 Publication

However, the conventional technology does not take into consideration optimizing the conversion of advertising content when, for example, a target customer unit price is not set.

The present invention has been made in view of the above, and an object of the present invention is to provide an information processing device, an information processing method, and an information processing program that can optimize the conversion of advertising content.

In order to solve the above-mentioned problems and achieve the purpose, an information processing device according to the present invention sets a bid price that is an index of the customer acquisition unit price for the advertising content to be distributed from the distribution history of the advertising content. a reception unit that receives an advertising request corresponding to an advertising space in which the advertising content is displayed; and a bid amount for the advertising request accepted by the reception unit in accordance with the bid price set in the setting unit. and a determining unit that determines the.

According to the present invention, conversion of advertising content can be optimized.

FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. FIG. 2 is a block diagram illustrating a configuration example of an information processing apparatus according to an embodiment. FIG. 3 is a diagram illustrating an example of information stored in the advertisement information storage unit according to the embodiment. FIG. 4 is a diagram illustrating an example of information stored in the user vector storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of information stored in the distribution history storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of the relationship between the target budget and the actual budget according to the embodiment. FIG. 7 is a flowchart illustrating an example of the bid price setting process according to the embodiment. FIG. 8 is a flowchart illustrating an example of the bid amount determination process according to the embodiment. FIG. 9 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device according to the embodiment.

DESCRIPTION OF THE PREFERRED EMBODIMENTS An information processing apparatus, an information processing method, and an embodiment of an information processing program (hereinafter referred to as "embodiments") according to the present application will be described in detail below with reference to the drawings. Note that the information processing apparatus, information processing method, and information processing program according to the present application are not limited to this embodiment.

[Embodiment]
[1. Information processing〕
First, an example of information processing according to the embodiment will be described using FIG. 1. FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. Note that this information processing method is executed by, for example, the information processing apparatus 10 shown in FIG.

As shown in FIG. 1, the information processing apparatus 10 according to the embodiment, for example, when receiving an advertisement request for advertisement content from the user terminal 100, arranges between each advertiser T for the advertisement space displaying the advertisement content. This is an information processing device that operates an auction in which bids are made. Note that the information processing device 10 is realized by, for example, a server device, a cloud system, or the like.

The user terminal 100 is a terminal device owned by the user U, and uses data communication with the information processing device 10 to display advertisements set on a display medium (for example, a web page) distributed from the information processing device 10. This is the terminal that is displayed in the frame. Examples of the user terminal 100 include a smartphone, a tablet terminal, a personal computer, and a wearable terminal.

The advertiser terminal 200 is, for example, a so-called DSP (Demand-Side Platform) device, and is managed by the advertiser T or an advertising agency requested by the advertiser T. For example, the advertiser terminal 200 makes a bid in response to a bid request for an advertising space received from the information processing device 10. When a bidder wins an advertisement, a posting right, which is the right to post advertising content in an advertising space, is obtained, and the corresponding advertising content can be distributed to the user terminal 100 that made the advertisement request.

For example, the information processing device 10 distributes advertising content to an advertising space in accordance with a contract made with an advertiser T by a business operator of the information processing device 10 (hereinafter simply referred to as a business operator). For example, a business operator enters into a contract with an advertiser T regarding an advertising budget (for example, one day's advertising budget) regarding advertising content, distribution conditions, and the like. Then, the information processing device 10 accepts payment of advertising costs from the advertiser T when a billing event actually occurs for the distributed advertising content. Note that the billing event can take various embodiments such as an advertisement click, video playback, and impression (display). In the following description, a click on an advertisement will be explained as a billing event.

Note that since a contract regarding advertising content is usually made on a campaign-by-campaign basis, advertising content regarding one contract will also be referred to as a campaign below. Furthermore, even if the advertising content is the same, if different contracts are concluded, they will be treated as separate campaigns.

By the way, in general, when bidding on advertising space, advertiser T sets a target cost per action (tCPA), which is the target cost per customer acquisition cost, and bids on advertising space with a bid amount according to tCPA. Set an upper limit cost per click (upper limit of bid amount). Note that tCPA is a target value of advertising cost/number of conversions, and, for example, a bid is made using a value obtained by multiplying tCPA by a conversion rate as the Bid amount.

However, for example, when distributing new advertising content, or for an advertiser T with a limited track record of distributing advertising content, it is not easy to set the tCPA appropriately. For example, if the tCPA is not set appropriately, there is a risk that the advertising budget will not be used up during the campaign period, or that the advertising budget will be used up during a part of the campaign period.

Therefore, in the information processing according to the embodiment, for example, in order to appropriately set the speed of spending the advertising budget, a bid price that is an index of the customer acquisition cost is set for each campaign, and then the bid amount is set according to the bid price. I decided to make a decision.

For example, the information processing device 10 sets a bid price based on the distribution history of the advertising content obtained by distributing the advertising content for a certain period of time (step S01). For example, the information processing device 10 collects actual measured values of the cost per click (hereinafter referred to as CPC) and conversion rate (CVR) for advertising requests from the most recent distribution history of advertising content, and The bid price is set based on the relationship with the campaign budget (hereinafter referred to as target spending budget).

Here, the bid price is a value that is an alternative to tCPA, and corresponds to the minimum value of tCPA suitable for consuming the target spending budget per unit time of the campaign. For example, the information processing device 10 sets a bid price that is most suitable for the target spending budget from among a plurality of preset bid prices based on the bid performance for the most recent advertisement request.

In more detail, for example, if the target spending budget is 80 yen, the bid amount for each ad request is determined by using the history of ad requests (Click #1 to Click #3... shown in the figure). A simulation is performed to determine whether or not there will be a successful bid, and the bid price that is closest to the target spending budget of 80 yen is set. That is, in this case, the bid price for the next cycle is set based on the most recent successful bid amount.

Subsequently, the information processing device 10 receives an advertisement request for an advertisement space from the user terminal 100 (step S02). For example, the advertisement request includes attribute information of the user U linked to the user terminal 100, information regarding the display medium that displays the advertisement space, information regarding the display position of the advertisement space on the display medium, and the like.

Subsequently, the information processing device 10 performs a process of predicting the CVR of the advertisement request received in step S02 (step S03). For example, the information processing device 10 assumes that an advertisement request that occurred in the past and an advertisement request that will occur in the future are requests of the same quality, and performs processing to predict the CVR of the advertisement request. That is, if the advertisement request is similar to a past advertisement request, the CVR of the current advertisement request is predicted, assuming that the CVRs of both are almost the same, and the predicted CVR is set as pCVR.

Subsequently, the information processing device 10 determines the bid amount for the advertisement request according to the bid price and pCVR (step S04). For example, the information processing device 10 determines the value obtained by multiplying the bid price by pCVR as the bid amount.

For example, bid price x pCVR can be expressed as "(target spending budget/number of conversions) x (number of conversions/number of clicks)" and is considered to be the upper limit of the cost per click per user U's click on advertising content. be able to.

That is, the higher the bid price, the higher the bid amount, and the lower the bid price, the lower the bid price. Therefore, by setting the bid price according to the target spending budget, it is possible to optimize the budget spending pace for each campaign.

Further, when the pCVR value for the advertisement request is high, the bid amount is higher than when the pCVR value is low. Therefore, a high bid amount is determined for an ad request that is expected to have a high conversion rate, making it easier to win the bid.

In other words, by determining the bid amount based on the bid unit price and pCVR, the information processing device 10 can maximize conversion while optimizing the budget consumption pace for each campaign.

After that, the information processing device 10, for example, proposes the bid amount determined for each campaign to the corresponding advertiser T, and then receives bids for the advertisement request from each of the advertiser terminals 200 (step S05).

Then, the information processing device 10 selects the campaign with the highest bid amount among the bid amounts received from the advertiser T, and distributes an advertisement to the user terminal 100 (step S06). On the user terminal 100, the advertising content received from the information processing device 10 is displayed in an advertising space together with the display medium.

In this way, the information processing device 10 according to the embodiment sets a bid price that is an indicator of CPA based on the distribution record of advertising content. Thereby, according to the information processing device 10 according to the embodiment, conversion of advertising content can be optimized.

Furthermore, the information processing device 10 according to the embodiment maximizes the number of conversions while optimizing the budget consumption pace for each campaign by setting a bid price that is an indicator of CPA according to the target budget consumption. It becomes possible to do so.

[2. Configuration example of information processing device]
Next, a configuration example of the information processing device 10 will be described using FIG. 2. FIG. 2 is a block diagram showing a configuration example of the information processing device 10 according to the embodiment. As shown in FIG. 2, the information processing device 10 includes a communication section 110, a control section 120, and a storage section 130.

The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 connects networks such as various wireless communication networks such as 4G (Generation), 5G, LTE (Long Term Evolution), WiFi (registered trademark), or wireless LAN (Local Area Network), or various wired communication networks. Information is sent and received to and from external devices via the external device.

The storage unit 130 is realized by, for example, a semiconductor memory device such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 130 also includes an advertisement vector model storage unit 131, an advertisement information storage unit 132, a user vector model storage unit 133, and a distribution history storage unit 135.

Advertisement vector model storage section 131 stores advertisement vector models. The advertisement vector model is a learning model that converts information about advertisement content into advertisement vectors. For example, the ad vector model is a model that calculates a similarity score that indicates the similarity between ad contents.The higher the calculated similarity score, the higher the similarity of ad vectors. The model is trained to output vectors. Note that the advertisement vector model may be, for example, a model that outputs an advertisement vector including information regarding the advertiser T in addition to the advertisement content. For example, an advertisement vector may be output based on the type of business, scale, track record, etc. of advertiser T.

Advertisement information storage section 132 stores various information regarding advertisement content. FIG. 3 is a diagram illustrating an example of information stored in the advertisement information storage unit 132 according to the embodiment. In the example shown in FIG. 3, the advertising information storage unit 132 stores information on items such as "advertiser ID", "advertising vector", "campaign period", "advertising budget", "distribution conditions", etc. in association with each other. do.

"Advertiser ID" is an identifier for identifying the advertiser T of advertising content. "Advertisement vector" is an advertisement vector of the corresponding advertisement content. Note that although the example shown in FIG. 3 shows a case where the advertisement vector is two-dimensional, the advertisement vector may be one-dimensional or three-dimensional or more.

"Campaign period" indicates a distribution period during which advertising content is distributed, and "advertising budget" indicates advertising costs during the campaign period. For example, "advertising budget"/"campaign period" becomes the target spending budget per day.

“Distribution conditions” indicate conditions for distributing advertising content, in other words, conditions for specifying an advertising space in which advertising content is displayed. For example, the distribution conditions include information regarding the display medium of the display frame and user attributes regarding the user U to whom the advertising content is distributed. Note that the "campaign period", "advertisement budget", and "distribution conditions" are usually determined by a contract between the business operator and the advertiser T.

Returning to the explanation of FIG. 2, the user vector model storage unit 133 will be explained. The user vector model storage unit 133 stores user vector models. The user vector model is a learning model that converts user information regarding user U into a user vector.

For example, the user vector model is a model that calculates a similarity score indicating the similarity between users U, and the user vector model is a model that calculates a similarity score indicating the similarity between users U. The model is trained to output vectors. Note that the user vector here is, for example, a vector related to similarity of user attributes or similarity of conversion by user U.

The user vector storage unit 134 stores a user vector for each user U. FIG. 4 is a diagram illustrating an example of information stored in the user vector storage unit 134 according to the embodiment. In the example shown in FIG. 4, the user vector storage unit 134 stores information on items such as "user ID" and "user vector" in association with each other.

“User ID” is an identifier for identifying user U. The "user vector" is a user vector regarding the corresponding user U. Note that although the example in FIG. 4 shows a case where the user vector is two-dimensional, it may be one-dimensional or three-dimensional or more.

Returning to the explanation of FIG. 2, the distribution history storage section 135 will be explained. The distribution history storage unit 135 stores information regarding the distribution history of each advertisement content. FIG. 5 is a diagram illustrating an example of information stored in the distribution history storage unit 135 according to the embodiment.

In the example shown in FIG. 5, the distribution history storage unit 135 associates information such as "advertisement ID", "display frame attribute", "user group attribute", "CVR", "CPC", etc. with each other. Remember.

"Advertising ID" is an identifier for identifying corresponding advertising content. "Display frame attribute" indicates an attribute related to the display frame of advertising content. For example, display frame attributes are classified according to the degree of similarity between advertising frames.

“User group attribute” indicates an attribute related to user U who is the delivery destination of the advertisement space. User group attributes are classified, for example, according to the degree of similarity of the user vectors described above. "CVR" indicates the conversion rate of advertising content. "CPC" indicates the cost per click of advertising content.

In the example of FIG. 5, when the advertising content with the advertising ID AD1 is displayed in the display frame with the display frame attribute P1 for the user U with the user group attribute U01, the CVR and CPC are "0.01" and "35", respectively. Indicates that

Returning to the explanation of FIG. 2, the control unit 120 will be explained. The control unit 120 is, for example, a controller, and various programs stored in a storage device inside the information processing device 10 use a RAM as a work area using a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. This is achieved by executing as .

As shown in FIG. 2, the control unit 120 includes an advertisement vector generation unit 121, a user vector generation unit 122, a setting unit 123, a reception unit 124, a prediction unit 125, a determination unit 126, and a distribution unit 127.

For example, the advertisement vector generation unit 121 inputs the advertisement content acquired from the advertiser T into an advertisement model vector model, and generates an advertisement vector. Advertisement vector generation section 121 stores the generated advertisement vector in advertisement information storage section 132.

The user vector generation unit 122 inputs, for example, user information regarding the user U obtained from the display medium of advertising content into the user vector model, and generates a user vector. The user vector generation unit 122 stores the generated user vector in the user vector storage unit 134.

The setting unit 123 sets a bid price that is an index of the customer acquisition unit price for the advertising content to be distributed based on the distribution history of the advertising content.

First, the setting unit 123 refers to the advertising information storage unit 132 and sets a distribution plan for each advertising content. For example, the distribution plan sets the consumption speed of the advertising budget. For example, the setting unit 123 sets the distribution plan so that the advertising budget is consumed evenly over the entire campaign period of the advertising content. The advertising budget per unit time set by the distribution plan becomes the target spending budget.

Note that the setting unit 123 may set the distribution plan based on, for example, a demand forecast for advertisement requests. For example, the setting unit 123 may configure the setting unit 123 for each time period according to the demand forecast for advertising requests so that a large amount of advertising budget is consumed during the period when there are many advertising requests, and a small advertising budget is consumed during the period when there are few advertising requests. The advertising budget may be weighted accordingly. Furthermore, the distribution plan set by the advertiser T may be used.

Subsequently, the setting unit 123 sets a bid price for each advertising content based on the distribution plan set for each advertising content. The setting unit 123 calculates, for example, an actual measurement value of the conversion rate (CVR) of the advertising content for each combination of the display frame attribute and the user group attribute, based on the distribution history of the advertising content.

The actual value of the conversion rate here is a value that is an indicator of the conversion rate that will occur in the future, and the setting unit 123 sets the bid price according to the conversion rate predicted from the distribution history of the advertising content. become.

Next, the setting unit 123 sets a bid price that is most suitable for the target spending budget from among the plurality of preset bid prices based on the bid results for the most recent advertisement request. The setting unit 123 uses the history of successful bids for advertisement requests to perform a simulation regarding the bid amount and the presence or absence of successful bids for each advertisement request for each bid price, and sets the bid price that is closest to the target spending budget.

At this time, the setting unit 123 may, for example, update the bid price according to the pace of consumption of the target budget. FIG. 6 is a diagram illustrating an example of the relationship between the target budget and the actual budget according to the embodiment.

As shown in FIG. 6, if the budget budget in cycle T11 is less than the target budget G, for example, in cycle T12, which is the next cycle after cycle T11, the budget budget for cycle T11 and the target budget G are different. Add the difference d1.

That is, in the cycle T12, the value obtained by adding the difference d1 to the target budget G becomes the target budget. Further, when the budget budget for the cycle T21 exceeds the target budget G, the difference d2 is subtracted from the target budget G for the next cycle T22, thereby setting the target budget budget for the cycle T22.

When updating the target spending budget, the setting unit 123 updates the bid price according to the updated target spending budget. That is, if the updated target spending budget is less than the target spending budget G, the bid price is lowered, and if the updated target spending budget is more than the target spending budget G, the bid price is set higher.

Thereby, it is possible to appropriately adjust the pace of spending the advertising budget in accordance with the updated target spending budget. Note that, for example, it is not necessary to spend all of the difference d1 in cycle T11 in the next cycle T12, and the target spending budget for each cycle may be set so that it is divided and spent in a plurality of cycles.

Further, the setting unit 123 may set the bid price, for example, according to the distribution history of bid prices set in the past. For example, in this case, the setting unit 123 stores the advertising budget spending pace for each set bid price, and sets the bid price so that the spending pace matches the current target spending budget. Even in this case, it is possible to appropriately control the consumption pace of the advertising budget in accordance with the distribution plan.

Returning to the explanation of FIG. 2, the reception unit 124 will be explained. The reception unit 124 receives an advertisement request corresponding to an advertisement space in which advertisement content is displayed. For example, the accepting unit 124 accepts an advertisement request from an advertisement content display medium or the user terminal 100.

For example, the receiving unit 124 receives various information regarding the advertising space and information identifying the user U of the user terminal 100 (for example, user ID) as an advertising request, and refers to the distribution conditions of each advertising content in the advertising information storage unit 132. , selects advertising content that can be delivered in response to an advertising request.

The reception unit 124 passes information regarding the advertisement request and information regarding advertisement content that can be distributed in response to the advertisement request to the prediction unit 125.

The prediction unit 125 predicts the conversion rate of each advertisement content for the advertisement request accepted by the reception unit 124.

For example, the prediction unit 125 predicts the conversion rate of each advertising content for the current advertising request from the actual value of the conversion rate of advertising content distributed for past advertising requests.

Specifically, if the advertising request is similar to a past advertising request from a statistical standpoint, the conversion rate of each advertising content for the current advertising request is predicted on the assumption that the CVRs of both are almost the same.

When the prediction unit 125 predicts the conversion rate of each advertisement content in response to the advertisement request, the prediction unit 125 passes information regarding the prediction result to the determination unit 126. At this time, the prediction unit 125 classifies the advertising requests (that is, user attributes and advertising space attributes) for each predetermined attribute, and predicts the pCVR for the current advertising request from the actual value of the conversion rate for each attribute. It's okay.

The determining unit 126 determines the bid amount for the advertisement request accepted by the receiving unit 124 according to the bid price set in the setting unit 123. For example, the determining unit 126 determines the product of the set bid price and the predicted conversion rate (pCVR) for the advertisement request as the bid amount for each advertisement content.

Further, the determining unit 126 determines a bid amount for each advertising content, and notifies each of the bid amounts to the corresponding advertiser terminals 200. As a result, for example, each advertiser terminal 200 determines the final bid amount with reference to the bid amount determined by the determination unit 126, and notifies the information processing device 10 of information regarding the final bid amount, thereby allowing the display frame An auction will be held for. Note that an auction for the display frame may be held based on the bid amount determined by the determining unit 126. That is, it is not necessarily necessary to notify each advertiser terminal 200 of the determined bid amount.

The distribution unit 127 conducts an auction using the bid amount determined by the determination unit 126, and distributes the advertising content that wins the auction to the user terminal 100 that is the source of the advertisement request. In the auction, winning content is determined so that, for example, the profitability of the advertising business increases. As a result, the advertising content is displayed in the display frame on the user terminal 100 together with the display medium for the advertising content.

As a result, the advertising content that won the auction is displayed in the display frame of the user terminal 100 together with the display medium of the advertising content. Note that, for example, the distribution unit 127 may decide the advertising content to be distributed by auction so that the profitability of the advertiser 200 is increased.

Note that, if the bid amounts of a plurality of advertisement contents are the same, the distribution unit 127 may make adjustments so that the plurality of advertisement contents are sequentially distributed in a predetermined order.

[3. Processing flow]
Next, a processing procedure executed by the information processing apparatus 10 according to the embodiment will be described using FIGS. 8 and 9. FIG. 8 is a flowchart illustrating an example of the bid price setting process according to the embodiment. FIG. 9 is a flowchart illustrating an example of the bid amount determination process according to the embodiment.

As shown in FIG. 8, in the bid price setting process, the information processing device 10 first collects advertising content distribution history (step S101). Subsequently, the information processing device 10 calculates the actual value of the CVR of the advertising content based on the collected distribution history (step S102).

Subsequently, the information processing device 10 sets a bid price based on the calculated CVR (step S103), and ends the process.

Next, the bid amount determination process will be explained. As shown in FIG. 9, the information processing device 10 receives an advertisement request (step S201). Subsequently, the information processing device 10 predicts the CVR for the advertisement request (step S202).

Then, the information processing device 10 determines the bid amount based on the bid price set in step S103 of FIG. 8 and the CVR estimated in step S202 (step S203), and ends the process.

[4. Modified example]
Incidentally, in the above-described embodiment, for example, a case has been described in which one bid amount is determined for each advertisement content in response to an advertisement request, but the present invention is not limited to this. For example, advertising requests may be classified into segments according to attributes, and bid amounts for each segment may be determined for each advertising content.

Further, in this case, for each advertising content, the auction participation rate for each segment may be determined so as to match the target spending budget, for example. Specifically, for example, in this case, a target spending budget is assigned to each segment for each advertising content, and a bid price is set for each segment according to the target spending budget for each segment.

Then, a bid amount is determined from the bid price according to the segment to which the advertisement request belongs. In addition, for example, depending on the consumption rate of the target budget for each segment, for example, segments with a low consumption rate may participate in the auction in preference to segments with a high consumption rate. You may decide to decide the rate.

For example, by allocating an advertising budget to each segment, you can distribute advertising content to a diverse user base, and by determining the bid amount according to the bid price set for each segment, you can control the pace of distribution for each segment. Can be properly controlled.

[5. effect〕
The information processing device 10 according to the embodiment described above includes a setting unit 123 that sets a bid price that is an index of the customer acquisition unit price for advertising content to be distributed based on the distribution history of the advertising content, and an advertising space in which the advertising content is displayed. and a determining unit 126 that determines the bid amount for the advertisement request received by the reception unit 124 in accordance with the bid price set by the setting unit 123. Therefore, according to the information processing device 10 according to the embodiment, conversion of advertising content can be optimized.

Further, the setting unit 123 according to the above-described embodiment sets, in the distribution plan, the consumption pace of the advertising budget for the advertising content when using each bid price candidate as a bid price candidate, with respect to the distribution history. A bid price candidate close to the target consumption pace is set as the bid price. Therefore, according to the information processing device 10 according to the embodiment, it is possible to control the consumption pace of the advertising budget in accordance with the target consumption pace.

Further, the setting unit 123 according to the embodiment updates the bid price at a predetermined period so as to reach the target consumption pace in accordance with the distribution plan. Therefore, according to the information processing device 10 according to the embodiment, it is possible to optimize the conversion of advertising content according to the consumption speed according to the distribution plan.

Further, the determining unit 126 according to the embodiment determines the product of the conversion rate for the advertisement request predicted from the distribution history and the bid price as the bid amount. Therefore, according to the information processing device 10 according to the embodiment, it is possible to determine an appropriate bid amount according to the conversion rate and the bid price.

Furthermore, the information processing device 10 according to the embodiment includes a distribution unit 127 that distributes the advertisement content for which the right to display in the advertisement space has been successfully bid for at the bid amount determined by the determination unit 126 to the advertisement request source. Therefore, according to the information processing device 10 according to the embodiment, advertising content with an optimized conversion rate can be distributed.

Further, the setting unit 123 according to the embodiment described above updates the bid price according to the distribution history of advertising content at the bid price set in the past. Therefore, according to the information processing device 10 according to the embodiment, the bid price can be corrected according to the distribution history, so the bid price can be kept at an appropriate value.

Further, the information processing method according to the embodiment described above is an information processing method executed by a computer, and includes settings for setting a bid price that is an index of the customer acquisition unit price for advertising content to be distributed based on the distribution history of the advertising content. a reception step of accepting an advertisement request for an advertisement space in which advertisement content is displayed; and a determination step of determining a bid amount for the advertisement request accepted in the reception step according to the bid price set in the setting step. include. Therefore, according to the information processing method according to the embodiment, conversion of advertising content can be optimized.

Furthermore, the information processing program according to the embodiment described above includes a setting procedure for setting a bid price that is an index of the customer acquisition unit cost for advertising content to be distributed from the distribution history of advertising content, and an advertising space in which the advertising content is displayed. A computer is caused to execute a reception procedure for accepting an advertisement request, and a determination procedure for determining a bid amount for the advertisement request accepted in the reception procedure, according to a bid price set in the setting procedure. Therefore, according to the information processing program according to the embodiment, conversion of advertising content can be optimized.

[6. Hardware configuration]
Further, the information processing apparatus 10 according to the embodiments described above is realized by, for example, a computer 1000 having a configuration as shown in FIG. 10. FIG. 10 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device 10 according to the embodiment. Computer 1000 has CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I/F) 1500, input/output interface (I/F) 1600, and media interface (I/F) 1700.

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

The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. Communication interface 1500 receives data from other devices via network (communication network) N and sends it to CPU 1100, and sends data generated by CPU 1100 to other devices via network N.

The CPU 1100 connects output devices such as displays and printers, and input devices such as keyboards and mice (in FIG. 10, output devices and input devices are collectively referred to as "input/output devices") via an input/output interface 1600. ). CPU 1100 obtains data from an input device via input/output interface 1600. Further, CPU 1100 outputs the generated data to an output device via input/output interface 1600.

Media interface 1700 reads programs or data stored in recording medium 1800 and provides them to CPU 1100 via RAM 1200. CPU 1100 loads this program from recording medium 1800 onto RAM 1200 via 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 a 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. etc.

For example, when the computer 1000 functions as the information processing device 10 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control unit 120 by executing a program loaded onto the RAM 1200. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from another device via the network N.

Some of the embodiments of the present application have been described above in detail based on the drawings, but these are merely examples, and various modifications and variations may be made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure section of the invention. It is possible to carry out the invention in other forms with modifications.

[7. others〕
Furthermore, among the processes described in the above embodiments and modified examples, all or part of the processes described as being performed automatically can be performed manually, or may be described as being performed manually. All or part of this processing can also be performed automatically using known methods. In addition, information including the processing procedures, specific names, and various data and parameters shown in the above documents and drawings may be changed arbitrarily, unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Furthermore, each component of each device shown in the drawings is functionally conceptual, and does not necessarily need to be physically configured as shown in the drawings. In other words, the specific form of distributing and integrating each device is not limited to what is shown in the diagram, and all or part of the devices can be functionally or physically distributed or integrated in arbitrary units depending on various loads and usage conditions. Can be integrated and configured.

Furthermore, the above-described embodiments and modifications can be combined as appropriate within a range that does not conflict with the processing contents.

Further, the above-mentioned "section, module, unit" can be read as "means", "circuit", etc. For example, the advertisement vector generation section 121 can be read as an advertisement vector generation section means or an advertisement vector generation section circuit.

10 Information processing device 100 User terminal 110 Communication unit 120 Control unit 121 Advertisement vector generation unit 122 User vector generation unit 123 Setting unit 124 Reception unit 125 Prediction unit 126 Determination unit 127 Distribution unit 130 Storage unit 130 Control unit 131 Advertisement vector model storage unit 131 User information acquisition unit 132 Advertising information storage unit 133 User vector model storage unit 134 User vector storage unit 135 Distribution history storage unit 200 Advertiser terminal

Claims (7)

a setting unit that sets a bid price that is an index of a customer acquisition unit price for the advertising content to be distributed from the distribution history of the advertising content;
a reception unit that receives an advertisement request for an advertisement space in which the advertisement content is displayed;
a determining unit that determines a bid amount for the advertisement request accepted by the accepting unit, according to the bid price set in the setting unit ;
The setting section includes:
For the distribution history, select the bid price candidates whose consumption pace of the advertising budget for the advertising content when using each of the bid price candidates as the bid price candidates is close to the target consumption pace set in the distribution plan. Set as bid price
An information processing device characterized by: The setting section includes:
The information processing device according to claim 1 , wherein the bid price is updated at a predetermined period so as to match the target consumption pace in accordance with the distribution plan. The determining unit is
The information processing device according to claim 1 or 2, wherein the bid amount is determined as a product of a conversion rate for the advertisement request predicted from the distribution history and the bid price. Claim 1, 2, or 3, further comprising: a distribution unit that distributes the advertisement content for which the right to display in the advertisement space has been successfully bid for at the bid amount determined by the determination unit to the advertisement request source. information processing equipment. The setting section includes:
The information processing device according to any one of claims 1 to 4, wherein the bid price is updated according to a distribution history of the advertising content at the bid price set in the past. An information processing method performed by a computer, the method comprising:
a setting step of setting a bid price that is an index of the customer acquisition cost for the advertising content to be distributed from the distribution history of the advertising content;
a reception step of accepting an advertisement request for an advertisement space in which the advertisement content is displayed;
a determining step of determining a bid amount for the advertisement request accepted by the accepting step according to the bid price set in the setting step ;
The setting step includes:
For the distribution history, select the bid price candidates whose consumption pace of the advertising budget for the advertising content when using each of the bid price candidates as the bid price candidates is close to the target consumption pace set in the distribution plan. Set as bid price
An information processing method characterized by: a setting procedure for setting a bid price that is an index of the customer acquisition cost for the advertising content to be distributed from the distribution history of the advertising content;
a reception procedure for accepting an advertisement request for an advertisement space in which the advertisement content is displayed;
causing a computer to execute a determining step of determining a bid amount for the advertisement request accepted in the accepting step according to the bid price set in the setting step ;
The setting procedure is as follows:
For the distribution history, select the bid price candidates whose consumption pace of the advertising budget for the advertising content when using each of the bid price candidates as the bid price candidates is close to the target consumption pace set in the distribution plan. Set as bid price
An information processing program featuring:

Images