JP7337887B2 - 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 been actively performed. In advertisement distribution, there is a listing advertisement that distributes an advertisement linked to the display screen of a terminal device.

As a technology related to listing advertisements, for example, there is a technology for controlling the budget consumption pace of advertisements by distributing advertisements according to a preset distribution plan (see, for example, Patent Document 1).

JP 2017-016320 A

However, in the prior art, for example, no consideration is given to ensuring the number of times each advertisement is delivered, and the delivery pace of each advertisement could not be controlled appropriately.

SUMMARY OF THE INVENTION It is an object of the present invention to provide an information processing apparatus, an information processing method, and an information processing program capable of appropriately controlling the delivery pace of each advertisement.

In order to solve the above-described problems and achieve the object, an information processing apparatus according to the present invention includes: a reception unit that receives an advertisement distribution request for an advertisement space; from the relative priority, which is a relative priority calculated in advance for each of the advertisements, for specifying a combination corresponding to the distribution request received by the reception unit, from among the combinations with the advertisements that become a calculation unit for calculating distribution priority, which is the priority of each of the advertisements included in the combination identified by the identification unit, with respect to the distribution request; and determining the advertisement according to the distribution priority calculated by the calculation unit. and a distribution unit for distribution.

According to the present invention, it is possible to appropriately control the delivery pace of each advertisement.

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 the information processing apparatus according to the embodiment; 3 is a diagram illustrating an example of information stored in an advertisement information storage unit according to the embodiment; FIG. FIG. 4 is a diagram illustrating an example of information stored in an inventory forecast information storage unit according to the embodiment; 5 is a diagram illustrating an example of information stored in a relative priority storage unit according to the embodiment; FIG. 6 is a diagram illustrating an example of processing by a generating unit according to the embodiment; FIG. FIG. 7 is a diagram showing the relationship between relative priority and distribution priority according to the embodiment. FIG. 8 is a schematic diagram illustrating an example of distribution priority according to the embodiment. FIG. 9 is a flowchart illustrating an example of relative priority calculation processing according to the embodiment. FIG. 10 is a flowchart illustrating an example of distribution processing according to the embodiment. FIG. 11 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus according to the embodiment.

Embodiments for implementing an information processing apparatus, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail below with reference to the drawings. The information processing apparatus, information processing method, and information processing program according to the present application are not limited to this embodiment.

[Embodiment]
[1-1. information processing]
First, an example of information processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. This information processing method is executed, for example, by the information processing apparatus 10 shown in FIG.

Further, the information processing method according to the embodiment can be applied not only to advertisement distribution but also to various types of inventory management. .

As shown in FIG. 1, the information processing apparatus 10 according to the embodiment receives, for example, an advertisement distribution request from a user terminal 50, selects an advertisement corresponding to the distribution conditions of the received distribution request, and then 50 is a processing device. In the following, the case where the distribution condition specifies the user attribute of the user to whom the advertisement is distributed will be described, but it is not limited to this. may be specified.

For example, the information processing device 10 distributes an advertisement to be displayed in the advertisement space 200 on the web page displayed on the user terminal 50 . Note that the information processing device 10 is realized by, for example, a server device, a cloud system, or the like.

The user terminal 50 is a terminal device owned by a user, and is a terminal that displays an advertisement distributed from the information processing device 10 in the advertising space 200 set on the web page by data communication with the information processing device 10. . Examples of user terminals 50 include smartphones, tablet terminals, personal computers, wearable terminals, and the like.

Here, for example, the operator of the information processing device 10 (hereinafter referred to simply as the operator) regards the advertising space generated in the future as inventory (hereinafter simply referred to as inventory), and trades the advertising space with the advertiser. contract. For example, an advertiser designates a distribution period, distribution conditions, and the number of times of distribution, and submits a purchase application for a future advertising space to a company.

On the other hand, if the advertising space presented by the purchase application is in stock, the business concludes a contract in response to the purchase application, and does not conclude a contract if the stock is insufficient. In addition, since a contract for an advertising space is normally made on a campaign-by-campaign basis, an advertisement relating to one contract is hereinafter also referred to as a campaign. Also, even for the same advertisement, when different contracts are concluded, it shall be treated as separate campaigns. In addition, regarding the relationship between demand and supply of ad spaces and campaigns, the ad space is the demand and the campaign is the supply.

Under such a contract, it is necessary to guarantee the frequency of advertisement distribution. Therefore, a method of calculating the distribution ratio to which each ad should be distributed is considered by setting the number of ad slots purchased for each campaign as the delivery target number and calculating the ratio of the inventory of the ad slots to the delivery target number. be done.

However, for example, if a distribution ratio is calculated for each received distribution request, the processing load is high, and there is a possibility that a delay may occur with respect to the distribution request, for example.

Therefore, in the information processing apparatus 10 according to the embodiment, the relative priority, which is the relative priority of each campaign, is calculated in advance. is calculated and the advertisement is distributed. That is, in the information processing apparatus 10 according to the embodiment, by calculating the relative priority in advance, the distribution priority corresponding to the above-described distribution probability is calculated by simple calculation.

For example, as shown in FIG. 1, first, the information processing apparatus 10 according to the embodiment acquires inventory forecast information from the web server 100 that provides web pages serving as display media for advertising spaces (step S01).

For example, the inventory forecast information is information about the advertising space 200 that will be generated in the future on the web page provided by the web server 100, for example, information about the advertising space 200 that will be generated per unit time. More specifically, for example, the inventory forecast information is information relating to a forecast value such as how many ad slots 200 for each attribute will be generated per unit time.

Subsequently, the information processing device 10 calculates the relative priority of each advertisement (step S02). The information processing device 10 calculates the relative priority of each campaign by mathematical programming using the first to third layers, for example.

Here, the relative priority is a relative numerical value of the distribution ratio of each campaign, such as which campaign should be distributed at what ratio in the entire campaign when a predetermined distribution request occurs. . The mathematical programming here includes various methods such as linear programming, nonlinear programming, dynamic programming, and discrete programming.

For example, the nodes (S1 to S3 . . . ) shown in the first layer correspond to the delivery conditions for each stock. For example, one node is generated for each delivery condition of inventory, such a node being, for example, a matrix corresponding to the number of inventory by date and time.

Nodes (D1 to D3 . . . ) shown in the third layer correspond to respective campaigns. For example, each addition of a campaign creates a new node, which is the matrix corresponding to the target number of deliveries for the entire campaign period.

Here, for example, it is also possible to calculate the relative priority by linear programming using the first layer and the third layer. However, in the linear programming method using the first and third layers, it is necessary to prepare a relative priority for each combination of campaigns that are candidates for advertisement distribution. The combination becomes huge. Therefore, in this case, it is necessary to store the relative priority corresponding to the number of combinations and incorporate a database into the distribution system that can be retrieved instantly, which is not preferable from the viewpoint of the scale of the distribution system.

Therefore, in the information processing apparatus 10 according to the embodiment, the second layer is set as an intermediate layer between the first layer and the third layer. For example, the nodes (P1 to P3 . That is, the second layer node is, for example, a matrix corresponding to the value obtained by dividing the target number of deliveries of each of the third layer nodes by the delivery period.

That is, by adding the second layer, the number of relative priorities to be prepared in advance can be reduced to the number of time periods×the number of campaigns. More specifically, in the third layer, for example, if N campaigns have overlapping delivery conditions, 2 (N-1) relative priorities corresponding to the number of combinations of campaigns are prepared in advance. By adding the second layer, it is sufficient to prepare N relative priorities corresponding to the number of campaigns for each time period, and the number of relative priorities prepared in advance can be reduced.

Then, in the information processing apparatus 10 according to the embodiment, for each unit time, nodes in the second layer that can be delivered under the delivery conditions of the nodes in the first layer are associated with each other, and mathematical programming is used. Calculate relative priority.

For example, the calculated relative priority is stored in the relative priority storage unit. Note that the relative priority may indicate a relative index for each campaign, and the method of calculating the relative priority is not limited to the example of step S02.

Thereafter, information processing device 10 receives, for example, an advertisement request to be displayed in advertisement space 200 from user terminal 50 (step S03). For example, the advertisement request includes information about the distribution conditions of the advertisement, and the information processing device 10 identifies the advertisement corresponding to the information about the distribution conditions and then distributes the advertisement.

At this time, in the information processing device 10, if there are a plurality of advertisements corresponding to the distribution conditions, the distribution priority, which is the priority for the advertisement request, is calculated from the relative priorities stored in the relative priority storage unit (step S04). ).

For example, the information processing apparatus 10 calculates distribution priority by using a normalization technique called L1-Ball Projection. For example, the information processing device 10 uses a value obtained by subtracting the same number from each relative priority as the distribution priority of each advertisement so that the sum of the distribution priorities of each of a plurality of advertisements competing with respect to the advertisement request becomes 1. calculate. For example, if the relative priorities of Advertisement A and Advertisement B are "0.8" and "0.6", the total is "1.4". At this time, the distribution priority is calculated as "0.8-0.2=0.6" and "0.6-0.2=0.4".

Then, the information processing device 10 distributes the advertisement in response to the distribution request according to the calculated distribution priority (step S05). That is, in the above example, advertisements are distributed such that advertisement A and advertisement B are distributed at a ratio of 0.6 to 0.4 for distribution requests with the same attribute. Note that, for example, when the sum of the relative priorities of advertisement A and advertisement B is less than 1, each relative priority becomes the distribution priority as it is.

As described above, in the information processing apparatus 10 according to the embodiment, when there are a plurality of advertisements that can be distributed for an advertisement request, the relative priority calculated in advance is used to calculate the distribution priority for the advertisement request.

Accordingly, the information processing apparatus 10 according to the embodiment can appropriately calculate the distribution priority, and thus can appropriately control the distribution pace of each advertisement. In addition, the information processing apparatus 10 according to the embodiment calculates the relative priority by a total of three layers of linear programming, that is, the first layer, the third layer, and the second layer. Accordingly, in the information processing apparatus 10 according to the embodiment, the processing load can be reduced compared to the case where the relative priority is calculated using a total of two layers of linear programming, the first layer and the third layer. .

[1-2. Calculation process]
Next, a specific procedure for calculating the relative priority will be explained. First, a case of calculating the relative priority from two layers, the first layer and the third layer, will be described. Assume that each node shown in the first layer is stock s_i and each node shown in the third layer is d_j, with relative priority x_tj and delivery priority p_ij. Note that i is an inventory index, and j is an item (campaign) index.

Let A be the set of projects j, Γ(j) be the set of inventory i belonging to project j, Γ(i) be the set of projects j belonging to inventory i, and S_j be the total inventory of project j. (p_ij/S_j) and the target delivery probability (d_j/S_j) can be calculated using the evaluation function shown in the following equation (1). The full-year scheduled delivery probability is, for example, the relative priority from the inventory side, and the target delivery probability shows the relative priority from the project side.

In the above equation (1), the evaluation function is multiplied by 1/2 in consideration of later differentiation. The distribution priority p_ij is calculated by calculating the relative priority for each campaign using the above formula (1) and normalizing the relative priority by L1-Ball Projection.

Specifically, when the time period t belonging to the inventory i is B(i), the adjustment term δ_i for deriving the distribution priority p_ij from the relative priority x_tj of each item is calculated by the following formula (2). will do. Note that d_j/S_j may be adopted as the initial value of the relative priority x_tj.

On the other hand, when the second layer is added to the first and third layers, the distribution priority p_ij is the relative priority x_tj of the item j in the time slot t and the adjustment term δ_i shown in the above equation (2). can be expressed by the following formula (3), and applying this to the optimization formula results in formula (4).

In order to eliminate the max function in equation (4), add x_tj>δ_i to the condition of element i and let it be L. Finally, expression (5) is used to optimize the relative priority x_tj.

Next, by alternately repeating the derivation of the adjustment term δ_i by the above formula (2) and the update of the relative priority x_tj of the case j in the time zone t using the above formula (5), Optimize the relative priority x_tj.

[2. Configuration example of information processing device]
Next, a configuration example of the information processing apparatus 10 will be described with reference to FIG. 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 has 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) or the like. The communication unit 110 uses 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 an external device via the network.

The storage unit 130 is realized by, for example, a semiconductor memory device such as a RAM or flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 130 also has an advertisement information storage unit 131 , an inventory forecast information storage unit 132 and a relative priority storage unit 133 .

The advertisement information storage unit 131 stores information about advertisements of campaigns for which advertisement spaces have been purchased. FIG. 3 is a diagram showing an example of information stored in the advertisement information storage unit 131 according to the embodiment. As shown in FIG. 3, the advertisement information storage unit 131 associates information items such as "campaign ID", "advertiser ID", "distribution conditions", "distribution period" and "distribution target number" with each other. memorize.

“Campaign ID” is the identifier of the campaign that purchased the ad space, in other words, the identifier of the advertisement to be distributed. “Advertiser ID” is the identifier of the advertiser who purchased the ad space. "Distribution conditions" indicate the conditions for distributing advertisements. It should be noted that the distribution condition may be read as targeting.

The “delivery period” is the delivery period of the corresponding advertisement and indicates the campaign period of the advertisement. "Distribution target number" indicates the number of ad slots purchased in the campaign.

Returning to the description of FIG. 2, the stock prediction information storage unit 132 will be described. The inventory forecast information storage unit 132 stores information regarding the inventory of the advertising space 200 . Stores information that predicts the inventory quantity of the advertising space 200. - 特許庁For example, inventory prediction information is information predicted based on past performance values of accesses to display media for advertising spaces.

FIG. 4 is a diagram showing an example of information stored in the inventory forecast information storage unit 132 according to the embodiment. As shown in FIG. 4, the inventory forecast information storage unit 132 stores items of information such as "user attribute", "date and time", and "inventory quantity" in association with each other.

"User attribute" indicates, for example, the attribute of the user who makes the advertisement request. "Date and time" and "inventory quantity" indicate that the corresponding inventory quantity is generated at the corresponding date and time. That is, in the example of FIG. 4, it is shown that the inventory for the group of users with the user attribute "T1" at 13:00 is "3000". Note that the stock quantity here is a predicted value.

Returning to the description of FIG. 2, the relative priority storage unit 133 will be described. The relative priority storage unit 133 stores information on relative priority. FIG. 5 is a diagram showing an example of information stored in the relative priority storage unit 133 according to the embodiment.

As shown in FIG. 5, the relative priority storage unit 133 stores items of information such as "campaign ID", "date and time", and "relative priority" in association with each other. “Campaign ID” is the identifier of the campaign that purchased the ad space.

"Date and time" and "Relative priority" indicate the relative priority at the corresponding date and time. The relative priority is, for example, a relative numerical value of the delivery ratio of each campaign based on the relationship between inventory and the target number of deliveries for the entire campaign. For example, the larger the distribution target number of the campaign, the greater the relative priority value, and the greater the inventory (delivery request number) corresponding to the campaign, the greater the relative priority value.

Returning to the description of FIG. 2, the control unit 120 will be described. The control unit 120 is, for example, a controller, and a CPU (Central Processing Unit), MPU (Micro Processing Unit), or the like allows various programs stored in a storage device inside the information processing apparatus 10 to use the RAM as a work area. It is realized by executing as

As shown in FIG. 2 , the control unit 120 has an acquisition unit 121 , a generation unit 122 , a pre-calculation unit 123 , a reception unit 124 , a specification unit 125 , a calculation unit 126 and a distribution unit 127 .

Acquisition unit 121 acquires inventory forecast information and advertisement information. Acquisition unit 121, for example, acquires inventory forecast information from web server 100 and acquires advertisement information from a business operator.

The inventory forecast information acquired by the acquisition unit 121 is stored in the inventory forecast information storage unit 132 , and the advertisement information is stored in the advertisement information storage unit 131 . Note that the information processing apparatus 10 may independently calculate information corresponding to the inventory forecast information from the advertisement distribution history instead of acquiring the inventory forecast information.

The acquisition unit 121 also functions as an acquisition unit that acquires demand forecast information that predicts demand for resources for each supply condition and supply target information that relates to the supply target for each supply condition. An example of resources here corresponds to a campaign, and an example of demand forecast information corresponds to inventory forecast information. An example of supply target information corresponds to advertisement information.

The generating unit 122 generates evaluation functions (first layer, second layer and third layer) for calculating relative priority. FIG. 6 is a diagram illustrating an example of processing by the generation unit 122 according to the embodiment. For example, each node in the first layer shown in FIG. 6 corresponds to the delivery condition of each inventory and is a matrix relating to the number of inventory generated per unit time.

Also, each node in the third layer shown in FIG. 6 corresponds to each campaign and is a matrix relating to the distribution target number for the entire campaign period. For example, the generation unit 122 refers to the inventory forecast information storage unit 132 to create the first layer based on the inventory forecast information, and refers to the advertisement information storage unit 131 to create the third layer based on the advertisement information. .

Also, each node in the second layer corresponds to the campaign indicated by each node in the third layer, and converts the matrix regarding the target number of distributions for the entire campaign period indicated by each node in the third layer into the target number of distributions per unit time. It is a matrix that

After generating each node in the second layer, the generation unit 122 identifies a combination of each node in the second layer corresponding to each node in the first layer. For example, if advertisements for campaign A can be delivered under distribution conditions A, a combination of a first layer node corresponding to distribution condition A and a second layer node corresponding to campaign A is specified. and connect the corresponding nodes.

In addition, if advertisements of campaign A or campaign B can be delivered under delivery conditions A or B, the nodes of the first layer of delivery conditions A and the nodes of the second layer corresponding to campaign A and campaign B are combined. One combination is specified, and the corresponding nodes are connected.

By sequentially performing these processes, it is possible to associate combinations of inventory generated per unit time with campaigns that can be delivered to each inventory.

Note that, for example, the inventory quantity and the distribution target quantity change each time an advertisement is distributed to an advertising space, so the generation unit 122 updates the first to third layers each time an advertisement is distributed. This makes it possible to appropriately maintain the relationship between the inventory quantity and the delivery target quantity. Note that, for example, the inventory quantity and the delivery target quantity may be updated in a predetermined time cycle, or in a predetermined delivery number cycle.

Note that the generation unit 122 sets a combination of resource supply conditions and resources that can be supplied under each supply condition based on the demand forecast information and the supply target information, and It also functions as an identification unit that identifies the relationship between the predicted value of demand per predetermined unit and the target value of supply per predetermined unit corresponding to each combination.

For example, the generation unit 122 generates each node of the second layer as processing related to the setting unit here, and performs processing of connecting each node of the second layer and the corresponding nodes of the first and third layers. In addition, the generation unit 122 performs, for example, a process of converting a node of the third layer into a node of the second layer as the processing related to the specifying unit here.

Returning to the description of FIG. 2, the pre-calculation unit 123 will be described. The pre-calculation unit 123 calculates the relative priority by linear programming using the predicted number of acquisitions per unit time of distribution requests for each distribution condition and the target number of distributions per unit time of each advertisement.

That is, the pre-calculator 123 calculates relative priorities by linear programming using the first to third layers generated by the generator 122 . The relative priority calculated by the pre-calculator 123 is stored in the relative priority storage 133 .

The reception unit 124 receives an advertisement distribution request for the advertisement space 200 . For example, the receiving unit 124 receives from the user terminal 50 a delivery request linked with information about a user to whom an advertisement is to be delivered. The information about the user here may include a user ID that identifies the user, and various personal data such as age, gender, annual income, place of residence, occupation, and tastes and preferences.

Information about the distribution request received by the receiving unit 124 is passed to the identifying unit 125 . Note that the reception unit 124 accesses a user information storage unit that stores personal data for each user, and acquires information on user attributes of the corresponding user based on an identifier that identifies the user (for example, a user ID). can be

The identifying unit 125 identifies a combination corresponding to the distribution request accepted by the accepting unit 124, from among combinations of advertisement distribution conditions and advertisements to be distributed under the respective distribution conditions.

That is, the identifying unit 125 identifies a campaign that can be distributed in response to the distribution request. For example, the identifying unit 125 refers to the distribution conditions of each campaign and identifies a campaign that matches the user attribute of the distribution request.

The identifying unit 125 then passes information on the identified campaign to the calculating unit 126 . Note that, for example, if there is only one campaign that can be distributed in response to a distribution request, the distribution unit 127 distributes an advertisement corresponding to that campaign.

The calculation unit 126 calculates the distribution priority of each advertisement included in the combination identified by the identification unit 125 from the relative priority calculated in advance for each advertisement. That is, the calculation unit 126 calculates the distribution priority of each campaign identified as a distribution target by the identification unit 125 using the relative priority pre-calculated by the pre-calculation unit 123 . In other words, the calculator 126 also functions as a corrector that corrects the relative priority to the distribution priority for the distribution request.

Upon receiving the information about the campaign specified as the distribution target from the specifying unit 125, the calculating unit 126 refers to the relative priority storage unit 133 and acquires the information about the relative priority of each campaign.

Subsequently, the calculation unit 126 calculates distribution priority using the obtained relative priority of each campaign. The calculation unit 126 passes the calculated distribution priority information to the distribution unit 127 .

The distribution unit 127 distributes the advertisement in response to the distribution request according to the distribution priority calculated by the calculation unit 126 . For example, when there are a plurality of campaigns to be distributed in response to a distribution request, the distribution unit 127 distributes the campaigns to the user terminal 50 at a distribution ratio corresponding to the distribution priority.

Next, a specific example of relative priority will be described with reference to FIGS. 7 and 8. FIG. FIG. 7 is a diagram illustrating the relationship between relative priority and distribution priority according to the embodiment. FIG. 8 is a schematic diagram illustrating an example of distribution priority according to the embodiment.

For example, as shown on the left side of FIG. 7, campaigns A to D, . For example, it is assumed that the identification unit 125 narrows down campaigns that can be distributed in response to the distribution request (step S11), and as a result, campaigns A, B, and C are narrowed down to a total of three.

Subsequently, the calculation unit 126 calculates the delivery priority so that the sum is 1 by subtracting the same number from the respective relative priorities of the campaigns A, B, and C (step S12). For example, in this case, the sum of relative priorities of campaigns A, B, and C is "0.2+0.8+0.6=1.6".

Therefore, the calculation unit 126 calculates a value obtained by subtracting 0.2 from the relative priority of each of the campaigns A, B, and C as the distribution priority of each of the campaigns A, B, and C. That is, in this case, the distribution priorities of campaigns A, B, and C are 0, 0.6, and 0.4, respectively.

That is, in this case, as shown in FIG. 8, if campaign A is not distributed and campaigns B and C are distributed at a ratio of 0.6 to 0.4 for distribution requests with the same attribute, each campaign The pace of delivery can be well controlled.

In the above example, campaign A will not be distributed at all for a distribution request with the same attribute as the above distribution request. Therefore, the delivery pace for campaign A is also appropriately controlled.

That is, for example, when the delivery conditions of two or more campaigns are in an inclusive relationship, and a delivery request corresponding to a subset part is received, the delivery priority is set so that the delivery conditions of the subset are preferentially delivered. is calculated. In this case, when a distribution request corresponding to a non-subset is received, it is sufficient to distribute the other campaign, so the distribution pace of each campaign can be appropriately controlled.

To give a more specific example, for example, the delivery condition for campaign A is male, the delivery condition for campaign B is male, 30s, and the delivery condition for campaign C is male, living in Tokyo.

In this case, campaign A can maintain an appropriate delivery pace with respect to inventory by delivering in delivery requests that do not conflict with campaigns B and C in terms of delivery. That is, campaign A can be distributed to men other than men in their thirties living in Tokyo, and there is no need to distribute in this case.

[3. Processing flow]
Next, a processing procedure executed by the information processing apparatus 10 according to the embodiment will be described with reference to FIGS. 9 and 10. FIG. FIG. 9 is a flowchart illustrating an example of relative priority calculation processing according to the embodiment. FIG. 10 is a flowchart illustrating an example of distribution processing according to the embodiment.

As shown in FIG. 9, first, the information processing apparatus 10 acquires inventory forecast information (step S101) and advertisement information (step S102). Subsequently, the information processing apparatus 10 sets a combination of distribution conditions for inventory and advertisements (campaigns) that can be distributed for each distribution condition (step S103).

Subsequently, the information processing apparatus 10 identifies the relationship between the inventory quantity per unit time and the target number of deliveries for each combination (step S104). Note that each node of the first to third layers is generated by the processing up to step S104.

Subsequently, the information processing apparatus 10 calculates a relative priority for each campaign (step S105), and ends the relative priority calculation process.

As shown in FIG. 10, in the distribution process, the information processing apparatus 10 first receives a distribution request (step S201), and identifies campaigns that can be distributed in response to the distribution request (step S202).

Subsequently, the information processing apparatus 10 calculates a distribution priority from the relative priority of each distributable campaign (step S203), distributes the advertisement according to the distribution priority (step S204), and performs distribution processing. exit.

[4. Modification]
By the way, in the above-described embodiment, a case has been described in which the advertisement distribution pace is controlled based on the advertisement demand forecast and the distribution target, but the present invention is not limited to this. In other words, resources are not limited to advertisements, and may be, for example, resources related to product delivery, or the products themselves may be regarded as resources.

That is, the present invention may be applied to various inventory management. In this case, the present invention can be applied by replacing the above-described inventory forecast information with target demand forecast information and replacing the advertisement information with target supply target information.

Also, in the above-described embodiment, the case where the time units of the first layer and the third layer are aligned in the second layer has been described, but the present invention is not limited to this. That is, in the second layer, for example, arbitrary parameters other than time units may be aligned. As an example of this, for example, the parameters relating to the area of advertisement distribution may be aligned.

[5. effect〕
The information processing apparatus 10 according to the above-described embodiment includes a reception unit 124 that receives an advertisement distribution request for an advertisement space, an advertisement distribution condition, and a combination of advertisements to be distributed under each of the distribution conditions. The identification unit 125 that identifies the combination corresponding to the distribution request accepted by the identification unit 125, and the relative priority that is the relative priority that is calculated in advance for each advertisement. A calculation unit 126 that calculates a distribution priority, which is a priority for a distribution request, and a distribution unit 127 that distributes an advertisement in response to the distribution request according to the distribution priority calculated by the calculation unit 126 . Therefore, according to the information processing apparatus 10 according to the embodiment, it is possible to appropriately control the delivery pace of each advertisement.

Further, the receiving unit 124 according to the above-described embodiment receives a distribution request linked with information about the user, and the identifying unit 125 identifies a combination based on the information about the user. Therefore, according to the information processing apparatus 10 according to the embodiment, it is possible to appropriately control the delivery pace of listing advertisements related to user attributes.

In addition, the calculation unit 126 according to the above-described embodiment is calculated according to the estimated number of acquisitions per unit time (corresponding to inventory) of distribution requests for each distribution condition and the target number of distributions per unit time for each advertisement. Distribution priority is calculated from the obtained relative priority. Therefore, according to the information processing apparatus 10 according to the embodiment, since the distribution priority can be calculated based on the relative priority per unit time, it is possible to calculate the distribution priority to an appropriate value.

The information processing apparatus 10 according to the above-described embodiment also includes the pre-calculation unit 123 that calculates the relative priority by mathematical programming using the predicted number of acquisitions and the target number of distributions of each advertisement per unit time. Therefore, according to the information processing apparatus 10 according to the embodiment, it is possible to optimize the relative priority.

Further, the calculation unit 126 according to the above-described embodiment subtracts the same number from the relative priority of each of the advertisements included in the combination specified by the specifying unit 125, and sets the distribution priority so that the total becomes 1. Calculate Therefore, according to the information processing apparatus 10 according to the embodiment, it is possible to calculate the priority for the delivery request to an appropriate value.

Moreover, the distribution unit 127 according to the above-described embodiment distributes the advertisement according to the distribution priority when there are a plurality of advertisements to be distributed in response to the distribution request. Therefore, according to the information processing apparatus 10 according to the embodiment, it is possible to appropriately control the delivery pace of each of a plurality of requests even when a plurality of campaigns compete for a delivery request.

Further, the information processing method according to the above-described embodiment is an information processing method executed by a computer, and includes a receiving step of receiving an advertisement distribution request for an advertisement space, an advertisement distribution condition, and a distribution target according to each of the distribution conditions. A specifying step of specifying a combination corresponding to the delivery request received by the receiving step from among the combinations of the advertisements, and the specifying step from the relative priority, which is the relative priority calculated in advance for each advertisement. a calculation step of calculating a delivery priority, which is the priority for each delivery request of the advertisements included in the combination, and a delivery step of delivering the advertisement in response to the delivery request according to the delivery priority calculated by the calculation step. include. Therefore, according to the information processing method according to the embodiment, it is possible to appropriately control the delivery pace of each advertisement.

In addition, the information processing program according to the above-described embodiment includes a receiving procedure for receiving an advertisement distribution request for an advertising space, an advertisement distribution condition, and a combination of advertisements to be distributed under each of the distribution conditions. For each delivery request of the advertisement included in the combination specified by the specific procedure for identifying the combination corresponding to the received delivery request and the relative priority, which is the relative priority calculated in advance for each advertisement A computer is caused to execute a calculation procedure for calculating a distribution priority, which is a priority, and a distribution procedure for distributing an advertisement in response to a distribution request according to the distribution priority calculated by the calculation procedure. Therefore, according to the information processing program according to the embodiment, it is possible to appropriately control the delivery pace of each advertisement.

[6. Hardware configuration]
Further, the information processing apparatus 10 according to the embodiment described above is implemented by a computer 1000 configured as shown in FIG. 11, for example. FIG. 11 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus 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 .

The CPU 1100 operates based on programs stored in the 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 up, a program 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, sends the data to CPU 1100, and transmits data generated by CPU 1100 to other devices via network N. FIG.

Through an input/output interface 1600, the CPU 1100 connects an output device such as a display and a printer, and an input device such as a keyboard and a mouse (in FIG. 11, the output device and the input device are collectively referred to as "input/output device"). ). CPU 1100 acquires data from an input device via input/output interface 1600 . CPU 1100 also 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 such a 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 disc), 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 apparatus 10 according to the embodiment, the CPU 1100 of the computer 1000 implements the functions of the control unit 120 by executing programs loaded on 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 via the network N from another device.

As described above, some of the embodiments of the present application have been described in detail based on the drawings. It is possible to carry out the invention in other forms with modifications.

[7. others〕
Further, among the processes described in the above embodiments and modifications, all or part of the processes described as being performed automatically can be performed manually, or described as being performed manually. All or part of the processing can also be performed automatically by a known method. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

Also, each component of each device illustrated is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to the one shown in the figure, and all or part of them can be functionally or physically distributed and integrated in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

Also, the above-described embodiments and modifications can be appropriately combined within a range that does not contradict the processing contents.

Also, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the acquisition unit 121 can be read as acquisition means or a user information acquisition circuit.

10 information processing device 50 user terminal 100 web server 121 acquisition unit 122 generation unit 123 advance calculation unit 124 reception unit 125 identification unit 126 calculation unit 127 distribution unit 131 advertisement information storage unit 132 inventory forecast information storage unit 133 relative priority storage unit

Claims (7)

a reception unit that receives an advertisement delivery request for an advertising space;
an identifying unit that identifies a combination corresponding to the distribution request received by the receiving unit from among combinations of the distribution conditions of the advertisement and advertisements to be distributed under each of the distribution conditions;
Calculation for calculating the delivery priority, which is the priority relative to the delivery request, of each of the advertisements included in the combination specified by the specifying unit, from the relative priority, which is the relative priority pre-calculated for each of the advertisements Department and
a distribution unit that distributes the advertisement according to the distribution priority calculated by the calculation unit ;
The calculation unit
calculating the distribution priority from the relative priority calculated according to the predicted number of acquisitions per unit time of the distribution request for each of the distribution conditions and the target number of distributions per unit time of each of the advertisements;
An information processing device characterized by: The reception unit
Receiving the delivery request associated with information about the user,
The identification unit
The information processing apparatus according to claim 1, wherein the combination is specified based on information about the user. The pre-calculation unit that calculates the relative priority by mathematical programming using the predicted number of acquisitions and the target number of distributions per unit time of each of the advertisements. Information processing equipment. The calculation unit
The delivery priority is calculated so that the sum is 1 by subtracting the same number from the relative priority of each of the advertisements included in the combination specified by the specifying unit. 4. The information processing device according to any one of 1 to 3 . The distribution unit
The information processing according to any one of claims 1 to 4, wherein when there are a plurality of advertisements to be distributed in response to the distribution request, the advertisements are distributed according to the distribution priority. Device. A computer-executed information processing method comprising:
a receiving step of receiving a request for distributing an advertisement for an advertising space;
an identifying step of identifying a combination corresponding to the distribution request received by the receiving step, from among combinations of the distribution conditions of the advertisement and advertisements to be distributed under each of the distribution conditions;
Calculation for calculating a delivery priority, which is the priority of each of the advertisements included in the combination specified by the specifying step, relative to the delivery request, from the relative priority, which is the relative priority pre-calculated for each of the advertisements process and
a distribution step of distributing the advertisement according to the distribution priority calculated by the calculation step ;
The calculation step includes:
calculating the distribution priority from the relative priority calculated according to the predicted number of acquisitions per unit time of the distribution request for each of the distribution conditions and the target number of distributions per unit time of each of the advertisements;
An information processing method characterized by: a reception procedure for receiving a request for distributing an advertisement for an advertising space;
a specifying step of specifying a combination corresponding to the delivery request accepted by the accepting procedure, from among combinations of the delivery conditions of the advertisement and advertisements to be delivered under each of the delivery conditions;
Calculation for calculating the delivery priority, which is the priority relative to the delivery request, of each of the advertisements included in the combination specified by the specifying procedure, from the relative priority, which is the relative priority pre-calculated for each of the advertisements a procedure;
causing a computer to execute a distribution procedure for distributing the advertisement according to the distribution priority calculated by the calculation procedure ;
The calculation procedure is
calculating the distribution priority from the relative priority calculated according to the predicted number of acquisitions per unit time of the distribution request for each of the distribution conditions and the target number of distributions per unit time of each of the advertisements;
An information processing program characterized by:

Images