Information processing device, information processing method, and information processing program

Abstract

To provide an information processing device capable of supporting appropriate setting of budget for advertisement distribution, an information processing method, and an information processing program.SOLUTION: An information processing device comprises a first calculation unit, a second calculation unit, and a generation unit. The first calculation unit calculates a contribution degree to a specific object as an advertisement unit contribution degree for each of advertisements included in each of a plurality of advertisement groups. The second calculation unit calculates a contribution degree to a specific object of each of the plurality of advertisement groups as an advertisement group unit contribution degree on the basis of advertisement unit contribution degree per advertisement calculated by the first calculation unit. The generation unit generates characteristic information per advertisement group, the characteristic information being information indicative of the relationship between the advertisement group unit contribution degree of an advertisement group calculated by the second calculation unit and the amount of budget with respect to distribution of a plurality of advertisements included in the advertisement group.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] 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 technology has been proposed that maximizes advertising profits by controlling the bid amount for an advertisement space based on past bidding records (for example, see Patent Document 1).

[0003] In this type of automated bidding for ad slots, the bid amount is determined by multiplying the acquisition cost set by the advertiser, such as a threshold CPA (Cost Per Action), by a predicted CVR (Conversion Rate). Then, ads are delivered until the advertiser's budget is consumed. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2019-220052 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the conventional technology has room for improvement in terms of supporting the setting of the budget amount. For example, when an advertisement is distributed with a small budget, the performance of the advertisement (e.g., conversion, etc.) is evaluated, and the budget is set based on the evaluation result, it may be difficult to respond to the case where the performance of the advertisement changes depending on the budget amount.

[0006] The present application has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can provide assistance in appropriately setting a budget for advertising delivery. [Means for solving the problem]

[0007] The information processing device of the present disclosure includes a first calculation unit, a second calculation unit, and a generation unit. The first calculation unit calculates the contribution to a specific goal of each advertisement included in each of a plurality of advertisement groups as an ad unit contribution. The second calculation unit calculates the contribution to a specific goal of each of the plurality of advertisement groups as an ad group unit contribution based on the ad unit contribution of each advertisement calculated by the first calculation unit. The generation unit generates, for each advertisement group, characteristic information that is information indicating a relationship between the ad group unit contribution of the advertisement group calculated by the second calculation unit and the amount of a budget for delivery of a plurality of advertisements included in the advertisement group. Effect of the Invention

[0008] According to one aspect of the embodiment, it is possible to provide assistance for appropriately setting a budget for advertisement distribution. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a user information table stored in the user information storage unit of the information processing device according to the embodiment. [Diagram 5] FIG. 5 is a diagram illustrating an example of an advertiser information table stored in the advertiser information storage unit of the information processing device according to the embodiment. [Figure 6]FIG. 6 is a diagram illustrating an example of a campaign information table stored in the campaign information storage unit of the information processing device according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of an advertisement provision history table stored in the advertisement delivery history storage unit of the information processing device according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of a change in advertisement group unit contribution degree and the amount of a budget set by an advertiser according to the embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of characteristic information generated by the generating unit of the information processing device according to the embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of how the budget amount for each of a plurality of advertisement groups is determined by the determination unit of the information processing device according to the embodiment. [Figure 11] FIG. 11 is a diagram illustrating an example of a method for determining the amount of a budget for each of a plurality of advertisement groups by the determination unit of the information processing device according to the embodiment. [Figure 12] FIG. 12 is a diagram illustrating another example of a method for determining the amount of a budget for each of a plurality of advertisement groups by the determination unit of the information processing device according to the embodiment. [Figure 13] FIG. 13 is a flowchart illustrating an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 14] FIG. 14 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application (hereinafter, referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. In addition, each embodiment can be appropriately combined as long as the processing contents are not contradictory. In addition, the same parts in each of the following embodiments are given the same reference numerals, and duplicated explanations will be omitted.

[0011] [1. An example of information processing] First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment, which is executed by an information processing device 1.

[0012] The information processing device 1 calculates the contribution to a specific goal for each advertisement included in each of a plurality of advertisement groups set by the advertiser O as an advertisement unit contribution, and calculates the contribution to the specific goal of each of the plurality of advertisement groups as an advertisement group unit contribution based on the advertisement unit contribution for each advertisement. Then, the information processing device 1 generates, for each advertisement group, characteristic information that is information indicating the relationship between the advertisement group unit contribution of the advertisement group and the amount of the budget for delivery of the plurality of advertisements included in the advertisement group.

[0013] The advertisement group set by the advertiser O is an advertisement group included in an advertisement campaign set by the advertiser O, and includes, for example, a plurality of advertisements. Each advertisement is, for example, a content for advertising a transaction object to be advertised, and is also called an advertisement content.

[0014] The specific goal is, for example, a specific action by the user U of the terminal device 2, such as conversion or engagement by the user U. Conversion is an indicator of reaching a goal (for example, a conversion goal). The types of such conversions include, for example, purchasing a transaction object that is the subject of advertisement, using a transaction object that is the subject of advertisement, registering for a membership service that is the subject of advertisement, or visiting a site that is the subject of advertisement, but are not limited to such examples. The transaction object is, for example, a product or a service.

[0015] In addition, the type of conversion may be signing up for an advertised email distribution, registering an account for an advertised online service, requesting materials that are advertised, visiting a advertised physical store, etc., or it may be some other action.

[0016] Engagement is, for example, an indicator that indicates how actively a person is involved with the advertising target, and types of engagement include, for example, shares, likes, posts, etc. on SNS (Social Network Service) etc., but are not limited to such examples.

[0017] It is possible to arbitrarily set what kind of behavior of the user U is considered as conversion or engagement. For example, for each advertisement, what kind of behavior of the user U is considered as conversion or engagement is individually set by an administrator of the information processing device 1, an advertiser O, or the like. Note that conversion may be a concept including engagement.

[0018] First, the information processing device 1 receives the advertising campaign information transmitted from the terminal device 3, and accepts the received advertising campaign information (step S1).

[0019] The advertiser O can operate the terminal device 3 and input information about one or more advertising campaigns into the terminal device 3. The terminal device 3 transmits information including the information about the one or more advertising campaigns input by the advertiser O to the information processing device 1 as advertising campaign information.

[0020] 1, the advertising campaign information includes information on advertising campaign Camp1, information on advertising campaign Camp2, and information on advertising campaign Camp3. The information on advertising campaign Camp1 includes information on an advertisement group including advertisements A1, B1, and C1, the information on advertising campaign Camp2 includes information on an advertisement group including advertisements A2, B2, and C2, and the information on advertising campaign Camp3 includes information on an advertisement group including advertisements D, E, and F.

[0021] In the following, when advertising campaigns Camp1, Camp2, and Camp3 are referred to without distinction, they may be referred to as advertising campaign Camp. Also, when advertisements A1 and A2 are referred to without distinction, they may be referred to as advertisement A. When advertisements B1 and B2 are referred to without distinction, they may be referred to as advertisement B. When advertisements C1 and C2 are referred to without distinction, they may be referred to as advertisement C.

[0022] The information of the advertising campaign Camp includes, in addition to information on the group of advertisements, information on specific goals, information on the attributes of the target user U (e.g., age, gender, region, interests, consumption behavior, etc.), information indicating the amount of the budget for advertising delivery, information indicating the cost per acquisition of each advertisement, etc., but is not limited to these examples.

[0023] The information indicating the amount of the budget for advertisement delivery includes, but is not limited to, information indicating the amount of the budget for each predetermined period TB (for example, one day, three days, or one week, etc.) For example, the information indicating the amount of the budget for advertisement delivery may include information indicating the amount of the budget for each period set by the advertiser O, or may be information indicating periods for which the amount of the budget set by the advertiser O is different.

[0024] The cost per acquisition of the advertisement is, for example, a threshold CPA (Cost Per Acquisition) and is set by the advertiser O. Such cost per acquisition is used when determining the bid amount in automatic bidding for advertisement delivery. Note that the cost per acquisition of the advertisement may be determined by the information processing device 1 or the like based on the past advertisement delivery performance.

[0025] Advertisements A, B, and C are advertisements targeting product X1. Advertisements D, E, and F are advertisements targeting product X2. The number of advertisements included in each of the advertising campaigns Camp1, Camp2, and Camp3 is not limited to three, and may be two or less or four or more.

[0026] The delivery type of each of the advertisements A, B, C, D, E, and F is, for example, a broad delivery advertisement, an interest targeting advertisement, or a retargeting advertisement. For example, the ad delivery type of the advertisements A and D is a broad delivery advertisement, the ad delivery type of the advertisements B and E is an interest targeting advertisement, and the ad delivery type of the advertisements C and F is an interest targeting advertisement, but is not limited to such an example.

[0027] A broad distribution advertisement is, for example, an advertisement provided without narrowing down the interests and concerns of a user U. An interest targeting advertisement is, for example, an advertisement provided based on the interests and concerns of a user U. A retargeting advertisement is, for example, an advertisement provided to a user U who has visited a website or web page that is the subject of a transaction that is the subject of the advertisement. Note that providing an advertisement means, for example, presenting the advertisement to a user U, but may also include transitioning to a link destination of the advertisement by the user U selecting (for example, clicking) the advertisement.

[0028] In addition, the format type of each of the advertisements A, B, C, D, E, and F may be, for example, but is not limited to, a banner advertisement, a listing advertisement, a native advertisement, a social media advertisement, or a video advertisement. In addition, the delivery type of each of the advertisements A, B, C, D, E, and F is also not limited to the above-mentioned examples.

[0029] In the example shown in FIG. 1, the purchase of product X by user U of terminal device 2 is taken as an example of a conversion with a specific goal, and the information processing device 1 calculates the number of purchases of product X as the number of conversions, and calculates the advertisement unit contribution degree, which is the contribution degree of each advertisement, and the advertisement group unit contribution degree, which is the contribution degree of each advertisement group. Product X is a product of advertiser O, and in the case of advertising campaigns Camp1 and Camp2, it is product X1, and in the case of advertising campaign Camp3, it is product X2. Note that, hereinafter, user U who has achieved conversion may be referred to as the "relevant user."

[0030] Next, the information processing device 1 accepts an advertisement request transmitted from the terminal device 2 (step S2), and performs bidding processing for advertisement delivery (step S3). In step S3, the information processing device 1 calculates a predicted value of a specific goal achievement rate (e.g., a predicted CVR value or a predicted engagement rate value), which is a predicted value of a probability of reaching a specific goal, based on information of the user U of the terminal device 2 that transmitted the advertisement request (e.g., information on the attributes of the user U and information on the behavior history of the user U).

[0031] The predicted value of the specific target achievement rate calculated in step S3 is, for example, a predicted value of a purchase probability of the product X by the user U of the terminal device 2 that has transmitted the advertisement request. The information processing device 1 determines, for example, a value obtained by multiplying the acquisition cost of each advertisement in the advertisement campaign Camp by the predicted value of the specific target achievement rate as a bid amount for each advertisement, and performs bidding processing for each advertisement using the determined bid amount for each advertisement.

[0032] The information processing device 1 determines an advertisement to be delivered to the terminal device 2 that sent the advertisement request through a bidding process, and delivers the determined advertisement to the terminal device 2 that sent the advertisement request (step S4). The processes of steps S2 to S4 are repeated to deliver each advertisement included in each advertisement campaign Camp.

[0033] In step S4 or the like, the information processing device 1 stores in an internal storage unit or the like information on the distribution history of advertisements to the user U. In addition, the information processing device 1 collects information on the purchase history of the product X by the user U from a shopping site that sells the product X or the like, and stores the collected information on the purchase history of the product X in an internal storage unit or the like.

[0034] Next, the information processing device 1 calculates the advertising unit contribution of each of the advertisements A1, B1, C1, A2, B2, C2, D, E, and F (step S5). The information processing device 1 calculates the advertising unit contribution of each of the advertisements A1, B1, C1, A2, B2, C2, D, E, and F, for example, for each predetermined period TB or for each period set by the advertiser O (for example, for each period with a different budget amount set by the advertiser O).

[0035] In step S5, the information processing device 1 acquires, for each conversion, from an internal storage unit or the like, advertisement information that includes information on an advertisement provided to the user U who has made a conversion.

[0036] For example, the information processing device 1 acquires advertisement information including information on one or more advertisements provided for each conversion from the time the user purchased the product X until a predetermined period of time TA. The predetermined period of time TA is, for example, one week, but is not limited to this example, and can be appropriately set depending on, for example, the attributes of the user U, the category of the product X, the content of the conversion, etc.

[0037] The information processing device 1 can also acquire provided advertisement information including information regarding conversion for each combination of advertisements provided from the time when the user purchased the product X until a predetermined period TA. Hereinafter, the combination of advertisements may be referred to as an advertisement combination.

[0038] The types of advertisement combinations are, in the case of purchasing product X1, a combination of one or more of six advertisements A1, A2, B1, B2, C1, and C2, and, in the case of purchasing product X2, a combination of one or more of three advertisements D, E, and F. In the following, advertisement combinations in the case of purchasing product X1 will be mainly described, but advertisement combinations in the case of purchasing product X2 are similar.

[0039] For example, the types of advertisement combinations include, but are not limited to, a combination of one advertisement among advertisements A1, A2, B1, B2, C1, and C2, a combination of two advertisements among advertisements A1, A2, B1, B2, C1, and C2, ..., a combination of advertisements A1, A2, B1, B2, C1, and C2, etc. For example, the advertisement combination may be a combination that includes the same advertisement.

[0040] Furthermore, the information processing device 1 can also acquire provided advertisement information including information regarding conversions for each order of advertisements provided from the time the user purchased the product X until a predetermined period TA before.

[0041] The information processing device 1 selects advertisement combinations AG1 to AG based on the above-mentioned provided advertisement information. n The number of conversions per ad is calculated. n is, for example, the same value as the total number of ad combinations.

[0042] For example, advertising combination AG m Assume that the combination of advertisements A1, B2, and C2 is a combination of advertisements A1, B2, and C2. In this case, the information processing device 1 calculates the number of conversions that occurred when advertisements A1, B2, and C2 were provided to the user from the time the user purchased product X until a predetermined period TA. m The number of conversions is calculated for each of the advertisement combinations AG1 to AG2. n When each of the above is referred to without distinguishing them individually, they may be referred to as advertising combination AG.

[0043] Then, for each advertisement combination AG, the information processing device 1 calculates the score of the advertisements included in the advertisement combination AG. For example, when the advertisement combination AG is a combination of only one advertisement, the information processing device 1 sets the score of the advertisements included in the advertisement combination AG to a value obtained by multiplying a reference value (for example, 1) by the number of conversions of the advertisement combination AG.

[0044] For example, assume that the advertisement combination AG is a combination of only one advertisement A1, and the number of conversions for the combination of only advertisement A1 is 100. In this case, the information processing device 1 calculates a value (e.g., 100) obtained by multiplying a reference value (e.g., 1) by 100 as the score of advertisement A1. In the case of a combination of only one advertisement A1, the scores of advertisements other than advertisement A1 are 0.

[0045] Furthermore, when the advertisement combination AG is a combination of two or more advertisements, the information processing device 1 sets the score of each advertisement included in the advertisement combination AG to a value obtained by multiplying a reference value by a weight and the number of conversions of the advertisement combination AG. The weight is the reciprocal of the number of advertisements, and for example, when there is a combination of two advertisements, it is 1 / 2, and when there is a combination of three advertisements, it is 1 / 3.

[0046] For example, assume that the advertisement combination AG includes two advertisements A1 and B1, and the number of conversions for the combination of the two advertisements A1 and B1 is 100. In this case, the information processing device 1 calculates a value (e.g., 50) obtained by multiplying a reference value (e.g., 1) by 1 / 2 and 100 as the score of each advertisement A1, B1. In the case of the combination of the two advertisements A1 and B1, the scores of advertisements other than advertisements A1 and B2 are 0.

[0047] The information processing device 1 calculates the advertisement unit contribution for each of the advertisements A1, B1, C1, A2, B2, and C2 by aggregating the scores of the advertisements A1, B1, C1, A2, B2, and C2 calculated for each advertisement combination AG. For example, when the score of the advertisement A1 calculated for each advertisement combination AG is scores SA11 to SA1 n In this case, the ad unit contribution of ad A is the score SA11 to SA1 n The sum of the above.

[0048] Furthermore, in the case of a combination of two or more advertisements, the information processing device 1 can weight the scores of the two advertisements included in the advertisement combination in accordance with the order of presenting the advertisements, instead of equally weighting the scores.

[0049] The advertisement presentation order is the order in which advertisements are presented to a user. For example, if advertisements X, Y, and Z are presented to the user in this order from the time the user purchases product X until a predetermined period TA, the advertisement presentation order is advertisement X, Y, and Z. The advertisements X, Y, and Z are, for example, different advertisements among advertisements A1, B1, C1, A2, B2, and C2, but some or all of advertisements X, Y, and Z may be the same advertisement.

[0050] Moreover, if one or more advertisements provided to the user in a predetermined period TA are in the order of advertisement X, advertisement Y, the advertisement presentation order is advertisement X, advertisement Y. Moreover, if one or more advertisements provided to the user in a predetermined period TA are only advertisement X (advertisement X is any one of advertisements A1, B1, C1, A2, B2, and C2), the advertisement presentation order is only advertisement X.

[0051] In this case, the information processing device 1 calculates the number of conversions for each advertisement presenting order based on the provided advertisement information. Then, the information processing device 1 calculates the score of the advertisement included in the advertisement presenting order for each advertisement presenting order.

[0052] For example, the advertisement presentation order is AO1~AO p If there is an advertisement providing order AO1 to AO p The number of conversions for each of the advertisement presentation orders AO1 to AO2 is calculated. p is, for example, the same value as the total number of advertisement presentation orders. p When referring to each of the above without distinguishing them individually, they may be referred to as advertisement presentation order AO.

[0053] The information processing device 1 can calculate, as the score of an advertisement, a value obtained by multiplying a value obtained by weighting an advertisement closer to the time when the advertisement is presented to the user in question, by the number of conversions.

[0054] In this case, the weights are set to, for example, a total of 1. For example, when the advertisement presentation order AO is advertisement A1, advertisement B1, and advertisement C2, the weight of advertisement A1 is, for example, 0.2, the weight of advertisement B1 is, for example, 0.3, and the weight of advertisement C2 is, for example, 0.5, but are not limited to such an example.

[0055] Advertisement Order AO m The order of advertisements is advertisement A1, advertisement B1, and advertisement C2, and the weights of advertisements A1, B1, and C2 are 0.15, 0.3, and 0.55, respectively. mAssume that the number of conversions is 100. In this case, the ad serving order AO m In the advertisement presentation order AO, the score of advertisement A1 is 15, the score of advertisement B1 is 30, and the score of advertisement C2 is 55. m In this example, the scores of all advertisements other than advertisements A2, B2, and C2 are 0.

[0056] Then, the information processing device 1 calculates the advertisement unit contribution degree for each of the advertisements A1, B1, C1, A2, B2, and C2 by aggregating the scores of the advertisements A1, B1, C1, A2, B2, and C2 calculated for each advertisement presenting order AO. For example, when the score of the advertisement A1 calculated for each advertisement presenting order AO is SA11 to SA12, the advertisement unit contribution degree for each of the advertisements A1, B1, C1, A2, B2, and C2 is calculated. p In this case, the ad unit contribution of ad A is the score SA11 to SA1 p The sum of the above.

[0057] The method of calculating the ad unit contribution of each advertisement is not limited to the above-mentioned calculation method. For example, the information processing device 1 can generate a prediction model that predicts the number of conversions according to the advertisement combination AG and the number of conversions according to the advertisement presentation order AO, and calculate the ad unit contribution of each advertisement using the generated prediction model.

[0058] The prediction model is expressed, for example, by the following formula (1). In the following formula (1), the feature amount is the information on the advertisement combination AG or the information on the advertisement presentation order AO, and pCV is the predicted number of conversions. Hereinafter, when the information on the advertisement combination AG and the information on the advertisement presentation order AO are shown without being individually distinguished from each other, they may be referred to as advertisement presentation related information. f(feature) = pCV (1)

[0059] The information processing device 1 calculates the number of conversions for each advertisement combination AG or for each advertisement presenting order AO, based on the provided advertisement information.

[0060] The information processing device 1 generates learning information including the advertisement provision related information and the information indicating the number of conversions for each combination of advertisements, and generates a prediction model using the learning information. The information processing device 1 calculates the advertisement unit contribution of each of the advertisements A1, B1, C1, A2, B2, and C2 using the generated prediction model.

[0061] For example, the prediction model is assumed to be a recurrent neural network (RNN) such as a long short-term memory (LSTM) or a gated recurrent unit (GRU). In this case, the information processing device 1 inputs advertisement provision related information to the prediction model, and calculates the score of the advertisement by multiplying the output value of a softmax function in the prediction model by, for example, the number of conversions.

[0062] The output value of the softmax function is obtained by applying the softmax function to the output of hierarchical attention, and is expressed as a probability distribution of advertisements A1, B1, C1, A2, B2, and C2. Hierarchical attention is an example of an attention mechanism.

[0063] Also, the prediction model is assumed to be a classification model such as a linear regression model or a GBDT (Gradient Boosting Decision Tree). In this case, the information processing device 1 inputs advertisement presentation related information to the prediction model and performs a process of acquiring pCV, which is a predicted number of conversions, from the prediction model for each advertisement combination AG or each advertisement presentation order AO.

[0064] Then, the information processing device 1 performs a process of calculating the scores of the advertisements A1, B1, C1, A2, B2, and C2 for each advertisement combination AG or each advertisement presentation order AO, using the pCV for each advertisement combination AG or each advertisement presentation order AO.

[0065] For example, the information processing device 1 calculates a score for each of multiple advertisements based on the number of conversions predicted by a prediction model when multiple advertisements are provided to user U and the number of conversions predicted by a prediction model when only a portion of the multiple advertisements are provided to user U.

[0066] Even when a prediction model is used, the information processing device 1 calculates the advertising unit contribution for each advertisement A1, B1, C1, A2, B2, C2 by aggregating the scores of each advertisement A1, B1, C1, A2, B2, C2 calculated for the advertising combination AG or the advertising presentation order AO for each advertisement A1, B1, C1, A2, B2, C2.

[0067] The information processing device 1 calculates the advertisement unit contribution degree for each of advertisements D, E, and F by a process similar to that for the advertisement unit contribution degree for each of advertisements A1, B1, C1, A2, B2, and C2. Note that, in the above-mentioned example, the advertisement combination in the case of purchasing product X1 is different from the advertisement combination in the case of purchasing product X2, but is not limited to such an example.

[0068] For example, when product X1 and product X2 are products having a specific relationship, the advertisement combination for the purchase of product X1 may be the same as the advertisement combination for the purchase of product X2. In other words, the purchase of product X1 and the purchase of product X2 can be regarded as the same purchase of product X. In this case, the type of advertisement combination is a combination of one or more advertisements from among advertisements A1, A2, B1, B2, C1, C2, D, E, and F. The specific relationship may be, for example, the same type of product, the same category of product, or products related in design, but is not limited to such examples.

[0069] In addition, in the advertising campaign Camp3, the product X may be the product X1, and the advertising campaign Camp3 may have an advertising group including advertisements A3, B3, and C3 targeting the product X1, instead of the advertising group including advertisements D, E, and F. In this case, the type of the advertising combination is a combination of one of advertisements A1, A2, A3, B1, B2, B3, C1, C2, and C3. Note that, in the above example, the calculation method of the ad unit contribution in conversion has been described, but the ad unit contribution in engagement can also be calculated in the same manner as the ad unit contribution in conversion.

[0070] Next, the information processing device 1 calculates the contribution of each of the multiple advertisement groups to the specific goal as an ad group unit contribution based on the ad unit contribution of each advertisement calculated in step S5 (step S6). The information processing device 1 calculates the ad group unit contribution of each of the multiple advertisement groups, for example, for each predetermined period TB or for each period set by the advertiser O (for example, for each period with a different budget amount set by the advertiser O).

[0071] For example, the information processing device 1 calculates the ad group unit contribution of the advertisement group including advertisements A1, B1, and C1 (ad group of advertisement campaign Camp1) by summing the ad unit contributions of advertisements A1, B1, and C1.

[0072] Furthermore, the information processing device 1 calculates the ad-group unit contribution of the ad group including the advertisements A2, B2, and C2 (the ad group of the advertisement campaign Camp2) by summing the ad-group contributions of the advertisements A2, B2, and C2.

[0073] Furthermore, the information processing device 1 calculates the ad-group unit contribution of the advertisement group including advertisements D, E, and F (the ad group of the advertisement campaign Camp3) by summing the ad-group contributions of advertisements D, E, and F.

[0074] Next, the information processing device 1 generates characteristic information for each advertisement group, which is information indicating the relationship between the advertisement group unit contribution degree of the advertisement group calculated in step S6 and the budget amount for the delivery of multiple advertisements included in the advertisement group (step S7).

[0075] The information processing device 1 can generate characteristic information by using, for example, a mathematical model or a machine learning model. For example, the information processing device 1 generates characteristic information by using the Vidale & Wolfe model, which is one of the mathematical models. The Vidale & Wolfe model is expressed by, for example, the following formula (2).

[0076]

number

[0077] In the above formula (2), "dS / dt" indicates the change in advertising group unit contribution over time, "A(t)" indicates the amount of the budget to be invested, "r" indicates the response coefficient, "rA(t)" indicates the effect of the budget to be invested, "MS / M" indicates the marginal effect, and "λS" is the natural decay effect (≒ delayed effect).

[0078] In this way, the Vidale & Wolfe model can express marginal utility and the delayed occurrence of ad group unit contribution, and can be differentiated. Marginal utility is an effect in which the increase in effect decreases as the budget amount increases. Because marginal utility can be expressed, it is possible to take into account the attenuation of the increase in ad group unit contribution. For example, it is possible to make the increase in ad group unit contribution when the budget is increased from 10,000 yen to 20,000 yen larger than the increase in ad group unit contribution when the budget is increased from 100,000 yen to 110,000 yen.

[0079] In addition, since it is possible to express the delayed occurrence of ad group unit contributions, the results of the delayed observed target behavior (conversion or engagement) are also taken into account, and the most recent performance can be used for learning. In particular, ad group unit contributions are a good fit because they take time to occur. In addition, the Vidale & Wolfe model has the advantage that it is easy to use for optimization, since the change in ad group unit contribution when the budget amount is changed can be analytically obtained.

[0080] The information processing device 1 estimates parameters such as "M", "λ", and "r" for each advertisement group using time-series history information including information on the advertisement group unit contribution degree calculated in step S6 and information on the budget amount for each period. For example, the information processing device 1 estimates parameters such as "M", "λ", and "r" for each advertisement group using a statistical method such as maximum likelihood estimation or least squares method. Note that the information on the budget amount included in the history information may be information on the amount consumed within the period or information on the amount consumed multiplied by or added to an adjustment value in cases where only a portion of the budget amount is consumed within a period.

[0081] The information processing device 1 uses the Vidale & Wolfe model with estimated parameters to generate characteristic information for each advertisement group that indicates the relationship between the advertisement group unit contribution and the budget amount. The characteristic information is information of a function graph that indicates the advertisement group unit contribution and the budget amount, but is not limited to such an example. For example, the information processing device 1 can obtain a predicted value of the change in the advertisement group unit contribution by changing the budget amount in the Vidale & Wolfe model with estimated parameters, thereby generating characteristic information. Hereinafter, the function graph that indicates the advertisement group unit contribution and the budget amount may be referred to as a function curve.

[0082] Furthermore, the information processing device 1 can perform learning and generate a machine learning model using time-series history information including the information on the advertisement group unit contribution degree calculated in step S6 and the information on the budget amount for each period as learning information. In this case, the information on the advertisement group unit contribution degree is used as label information, but is not limited to such an example. The machine learning model is, for example, an RNN such as LSTM or GRU, a classification model such as a linear regression model or GBDT, etc., but is not limited to such an example.

[0083] The information processing device 1 generates, for each advertisement group, characteristic information indicating a relationship between the advertisement group unit contribution degree and the budget amount, using the generated machine learning model. The characteristic information is information of a function graph indicating the advertisement group unit contribution degree and the budget amount, but is not limited to such an example.

[0084] The information processing device 1 can also generate a scatter diagram showing the advertisement group unit contribution degree and the budget amount as characteristic information for each advertisement group by using time-series history information including the advertisement group unit contribution degree information and the budget amount information calculated in step S6. The information processing device 1 can also derive a characteristic curve from the generated scatter diagram.

[0085] Next, the information processing device 1 transmits the characteristic information for each advertisement group generated in step S7 to the terminal device 3 of the advertiser O (step S8). The terminal device 3 receives the characteristic information for each advertisement group transmitted from the information processing device 1, and displays the received characteristic information for each advertisement group. This allows the advertiser O to understand how to set the budget amount for each advertisement group from the characteristic information for each advertisement group in order to efficiently set the advertising effect of each advertisement group.

[0086] When the advertiser O changes the budget amount of each advertising campaign Camp, the advertiser O inputs information indicating the changed budget amount of the advertising campaign Camp by operating the terminal device 3. In this case, the terminal device 3 transmits budget change information including information indicating the changed budget amount of the advertising campaign Camp from the terminal device 3 to the information processing device 1. Upon receiving the budget change information transmitted from the terminal device 3, the information processing device 1 changes the budget amount of the advertising campaign Camp based on the received budget change information.

[0087] The advertiser O can input total budget information including information indicating the amount of the total budget in the account of the advertiser O by operating the terminal device 3. In the example shown in Fig. 1, the total budget amount, which is the total amount of the budgets of three advertising campaigns Camp1, Camp2, and Camp3, is set within the total budget amount in the account of the advertiser O.

[0088] When the total budget information is input from the advertiser O, the terminal device 3 transmits the total budget information to the information processing device 1 (step S9). Note that the total budget information may be included in the advertising campaign information in step S1, and in this case, the process of step S9 may not be performed.

[0089] When the information processing device 1 receives the total budget information transmitted from the terminal device 3, it determines the budget amount for each of the multiple advertising groups based on the total budget amount indicated in the total budget information and the characteristic information for each advertising group generated in step S7 (step S10).

[0090] For example, the information processing device 1 determines the budget for each of the multiple ad groups such that the sum of the ad group unit contributions of the multiple ad groups in the characteristic information of each of the multiple ad groups within the total budget amount is maximum or within a range of a predetermined condition from the maximum. Hereinafter, the sum of the ad group unit contributions of the multiple ad groups may be referred to as a total contribution.

[0091] For example, the total budget amount is "Pmax", the total contribution level is "Aall", the budget amount of advertising campaign Camp1 is "P1", the budget amount of advertising campaign Camp2 is "P2", and the budget amount of advertising campaign Camp3 is "P3".

[0092] In the example shown in Fig. 1, the total contribution Aall is expressed by the following formula (3): In the following formula (3), "AT1" is the ad-group unit contribution of the ad group of the ad campaign Camp1, "AT2" is the ad-group unit contribution of the ad group of the ad campaign Camp2, and "AT3" is the ad-group unit contribution of the ad group of the ad campaign Camp3. Aall = AT1 + AT2 + AT3 (3)

[0093] In this case, the information processing device 1 calculates advertisement group unit contributions AT1, AT2, AT3 that are the maximum total contribution Aall or advertisement group unit contributions AT1, AT2, AT3 that are within a range of a predetermined condition from the maximum total contribution Aall under the constraint condition of the following formula (4). The range of the predetermined condition is, for example, a range from 90% to 100% of the total contribution Aall, but can be set arbitrarily by the advertiser O. Pmax ≧ P1 + P2 + P3 (4)

[0094] The information processing device 1 determines a budget amount P1 corresponding to the calculated ad group unit contribution degree AT1 from the characteristic information of the ad group of the advertising campaign Camp1. The information processing device 1 also determines a budget amount P2 corresponding to the calculated ad group unit contribution degree AT2 from the characteristic information of the ad group of the advertising campaign Camp2. The information processing device 1 also determines a budget amount P3 corresponding to the calculated ad group unit contribution degree AT3 from the characteristic information of the ad group of the advertising campaign Camp3.

[0095] In addition, the information processing device 1 can determine the budget amount of each of multiple advertisement groups within the total budget amount based on the change in advertisement group unit contribution (e.g., the amount of change or the rate of change) when the budget amounts P1, P2, and P3 of each advertisement group are increased or decreased.

[0096] For example, the information processing device 1 determines the budget amounts P1, P2, and P3 for each of the multiple advertisement groups within the total budget amount using the following formula (5). b(t)=P Q {b(t-1)+η∇g(b(t-1))} ···(5)

[0097] In the above formula (5), “b(t)” is the budget amount for the current period for the advertising group, “b(t-1)” is the budget amount for the previous period for the advertising group, and “P Q " is the projection onto the constraint of the total budget amount for the ad group, and "η" is the update range. "∇g(b(t-1))" is the slope of the function graph (characteristic curve) for the budget amount for the previous period for the ad group, and is an example of a change in ad group unit contribution when the budget amount for the ad group is increased or decreased. The period here is a predetermined period TB or a period set by the advertiser O (for example, each period in which the budget amount set by the advertiser O is different), but is not limited to such examples.

[0098] The information processing device 1 can use the change in the advertisement group unit contribution when the budget amount for each advertisement group is increased or decreased, thereby making it possible to stably update the budget amount without being easily affected by probabilistic variations.

[0099] In this way, the information processing device 1 calculates the contribution to a specific goal for each advertisement included in each of the multiple advertisement groups set by the advertiser O as an advertisement unit contribution, and calculates the contribution to a specific goal for each of the multiple advertisement groups as an ad group unit contribution based on the advertisement unit contribution for each advertisement. Then, the information processing device 1 generates characteristic information for each advertisement group, which is information indicating the relationship between the ad group unit contribution of the advertisement group and the amount of the budget for the delivery of the multiple advertisements included in the advertisement group. This allows the information processing device 1 to provide support for appropriately setting a budget for the delivery of advertisements.

[0100] The configuration of an information processing system including an information processing device 1 that performs such processing, a plurality of terminal devices 2, and a terminal device 3 will be described in detail below.

[0101] 2. Configuration of the Information Processing System 2 is a diagram showing an example of a configuration of an information processing system according to an embodiment. As shown in FIG. 2, the information processing system 100 according to the embodiment includes an information processing device 1, a plurality of terminal devices 2, and a plurality of terminal devices 3.

[0102] The multiple terminal devices 2 are used by different users U. The multiple terminal devices 3 are used by different advertisers O. Each of the terminal devices 2 and 3 is, for example, a notebook PC (Personal Computer), a desktop PC, a smartphone, a tablet PC, or a wearable device. The wearable device is, for example, smart glasses or a smart watch, but is not limited to such examples. The user U is a user who receives advertisements provided from an information processing device 1 or the like.

[0103] The information processing device 1, the terminal device 2, and the terminal device 3 are connected to each other so as to be able to communicate with each other by wire or wirelessly via a network N. Note that the information processing system 100 shown in FIG. 2 may include a plurality of information processing devices 1 and the like.

[0104] The network N includes, for example, a Wide Area Network (WAN) such as the Internet and mobile communication networks such as Long Term Evolution (LTE), 4th Generation (4G), and 5th Generation (5G: fifth generation mobile communication system).

[0105] The terminal device 2 and the terminal device 3 can connect to the network N via short-range wireless communication such as a mobile communication network, Bluetooth (registered trademark), or a wireless LAN (Local Area Network), and communicate with the information processing device 1.

[0106] 3. Configuration of information processing device 1 3 is a diagram showing an example of the configuration of the information processing device 1 according to the embodiment. As shown in FIG. 3, the information processing device 1 includes a communication unit 10, a storage unit 11, and a processing unit 12.

[0107] [3.1. Communication unit 10] The communication unit 10 is realized by, for example, a communication module or a NIC (Network Interface Card). The communication unit 10 is connected to a network N by wire or wirelessly, and transmits and receives information to and from various other devices. For example, the communication unit 10 transmits and receives information to and from the terminal device 2 and the terminal device 3 via the network N.

[0108] [3.2. Storage section 11] The storage unit 11 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 11 has a user information storage unit 20, an advertiser information storage unit 21, a campaign information storage unit 22, and an advertisement delivery history storage unit 23.

[0109] 3.2.1. User information storage unit 20 The user information storage unit 20 stores various pieces of information related to the user U. Fig. 4 is a diagram showing an example of a user information table stored in the user information storage unit 20 of the information processing device 1 according to the embodiment.

[0110] 4, the user information table stored in the user information storage unit 20 includes information items such as "User ID (Identifier)," "Attribute Information," and "History Information." The "User ID" is an identifier for identifying a user U, and is information assigned to each user U.

[0111] The "attribute information" is attribute information indicating attributes of the user U associated with the "user ID." The attributes of the user U are, for example, demographic attributes, psychographic attributes, etc. The demographic attributes are demographic attributes, and include a plurality of attribute items such as age, sex, occupation, place of residence, annual income, and family structure.

[0112] The psychographic attributes are psychological attributes, and include, for example, a plurality of attribute items related to lifestyle, values, interests, etc. For example, each of the plurality of attribute items in the psychographic attributes is an object of interest of the user U, such as a car, clothes, travel, games, camping, motorcycle, train, home appliance, or computer.

[0113] The "history information" includes information on the behavior history of the user U associated with the "user ID." The behavior history of the user U includes, for example, information on the behavior history of the user U in the online service. The behavior history information of the user U in the online service includes, for example, search history information, browsing history information, delivery history information, and transaction history information in the online service of the user U.

[0114] The search history information of the user U includes, for example, information on the search history by the user U in a web search service. The browsing history information of the user U includes, for example, information on the browsing history of content by the user U in an online service. The distribution history information includes information on the distribution history of content distributed to the terminal device 2 of the user U. The transaction history information includes information on the transaction history of products by the user U in an online service.

[0115] [3.2.2. Advertiser information storage unit 21] The advertiser information storage unit 21 stores various information related to the advertiser O. Fig. 5 is a diagram showing an example of an advertiser information table stored in the advertiser information storage unit 21 of the information processing device 1 according to the embodiment.

[0116] 5, the advertiser information table stored in the advertiser information storage unit 21 includes information items such as “advertiser ID”, “account”, “budget amount”, and “campaign ID”. The “advertiser ID” is an identifier for identifying the advertiser O, and is information assigned to each advertiser O.

[0117] "Account" is information about the account of the advertiser O associated with the "Advertiser ID" and is assigned to each advertiser O. Note that two or more accounts may be assigned to each advertiser O. "Budget amount" is the budget amount assigned to the account, which is the total budget amount described above. Such a total budget amount is, for example, the total budget amount for each predetermined period TB or the total budget amount for each period set by the advertiser O (for example, for each period in which the budget amount set by the advertiser O is different), but is not limited to such examples.

[0118] The "Campaign ID" is an identifier for identifying an advertising campaign Camp associated with an "Account" and is information assigned to each advertising campaign Camp. The advertiser information storage unit 21 is not limited to the above and can store various information according to the purpose.

[0119] 3.2.3. Campaign information storage unit 22 The campaign information storage unit 22 stores various information related to the advertising campaign Camp received from the terminal device 3. Fig. 6 is a diagram showing an example of a campaign information table stored in the campaign information storage unit 22 of the information processing device 1 according to the embodiment.

[0120] In the example shown in Fig. 6, the campaign information table stored in the campaign information storage unit 22 includes information on items such as "Campaign ID", "Advertisement", "Cost per acquisition", and "Budget amount". The "Campaign ID", like the campaign ID shown in Fig. 5, is an identifier that identifies an advertising campaign Camp, and is information that is assigned to each advertising campaign Camp.

[0121] An "advertisement" is an advertisement included in an advertising campaign Camp associated with a "campaign ID", and may be, for example, a banner advertisement, a listing advertisement, a native advertisement, a social media advertisement, a video advertisement, etc., but is not limited to such examples.

[0122] The "cost per acquisition" is information on the cost per acquisition corresponding to the advertisement included in the advertisement campaign Camp associated with the "campaign ID", for example, threshold CPA information, but is not limited to such an example.

[0123] The "budget amount" is information on the amount of the budget corresponding to each advertisement included in the advertising campaign Camp associated with the "campaign ID", and is, for example, the total budget amount for a predetermined period TB or the budget amount for each period set by the advertiser O, but is not limited to such examples. For example, the "budget amount" may be information on the amount of the budget corresponding to the advertising campaign Camp associated with the "campaign ID".

[0124] 6, the campaign information table includes information on the distribution period of advertisements included in the advertising campaign Camp associated with the "campaign ID," information on specific goals, and information on target attributes that are attributes of the target user U. The campaign information storage unit 22 is not limited to the above, and can store various types of information according to the purpose.

[0125] [3.2.4. Advertisement distribution history storage unit 23] The advertisement delivery history storage unit 23 stores various information related to the delivery history of advertisements. Fig. 7 is a diagram showing an example of an advertisement provision history table stored in the advertisement delivery history storage unit 23 of the information processing device 1 according to the embodiment.

[0126] In the example shown in Fig. 7, the advertisement delivery history table stored in the advertisement delivery history storage unit 23 includes information items such as "user ID", "presented advertisement", and "specific target information". The "user ID" is the same as the user ID shown in Fig. 4, and is information of the identifier of the user U to whom the advertisement is to be provided.

[0127] The "provided advertisement" includes, for example, an advertisement ID of an advertisement provided (distributed) to a user U associated with the "user ID", and information indicating the date and time of providing the advertisement to the user U. The "specific goal information" is information regarding a specific goal that is the goal of the provided advertisement, and, for example, if the specific goal is a conversion, includes information indicating the content of the conversion performed by the user U associated with the "user ID", and information on the date and time of the conversion by the user U (conversion date and time).

[0128] The content of the conversion may be, for example, but is not limited to, the purchase of a transaction object, the use of an advertised transaction object, the registration as a member of an advertised site, or the viewing (display) of an advertised site. The transaction object may be, for example, a product or a service.

[0129] In addition, if the specific goal is engagement, the "specific goal information" includes information indicating the content of the engagement performed by the user U associated with the "user ID" and information on the date and time of the engagement by the user U (engagement date and time).

[0130] Engagement is, for example, an indicator of how actively a person is involved with the advertising target, and examples include shares, likes, posts, etc. on social media, but are not limited to such examples.

[0131] In addition, the advertising delivery history memory unit 23 can also store advertisements provided to a user U for a specified period TA in association with the user U who has achieved a specific goal (e.g., a specific action such as conversion or engagement) for a certain transaction object.

[0132] For example, the advertisement delivery history memory unit 23 associates with a user U who has achieved a specific goal (e.g., a specific behavior such as conversion or engagement) corresponding to the advertising target, and stores, among the advertisements provided to the user U during a specified period TA, advertisements corresponding to the advertising target, in association with the combination or presentation order of the advertisements.

[0133] For example, the advertisement delivery history storage unit 23 stores, for a product X, one or more advertisements that advertise the product X among the advertisements provided during a predetermined period TA (such as the most recent week) prior to the date and time when the user U purchased the product X, in association with the product X and in association with the combination or order of provision thereof.

[0134] The advertisement delivery history storage unit 23 also stores, for example, attribute information and history information of the user U at the time the advertisement was provided, and advertisement display environment information of the advertisement at the time it was provided to the user U. As described above, the advertisement display environment information is information such as the category of the website on which the advertisement is provided, the type of application of the terminal device 2 on which the advertisement is provided, and the display position of the advertisement.

[0135] [3.3. Processing section 12] The processing unit 12 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the information processing device 1 using a RAM as a working area.

[0136] The processing unit 12 may be partially or entirely realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

[0137] 3, the processing unit 12 has an acquisition unit 30, a reception unit 31, a distribution unit 32, a calculation unit 33, a generation unit 34, a determination unit 35, and a provision unit 36, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 3, and may be other configurations as long as they perform the information processing described below.

[0138] [3.3.1. Acquisition part 30] The acquisition unit 30 acquires various pieces of information from an external information processing device, the terminal device 2, the terminal device 3, or the like via the communication unit 10, and stores the acquired information in the storage unit 11.

[0139] For example, the acquisition unit 30 acquires user information, which is information about the user U, from an external information processing device or the terminal device 2 via the communication unit 10, and adds the acquired user information to a user information table in the user information storage unit 20.

[0140] Furthermore, the acquisition unit 30 acquires various types of information from the storage unit 11. For example, the acquisition unit 30 acquires user information, which is information on the user U, from the user information storage unit 20 or the like. The user information acquired by the acquisition unit 30 includes, for example, a part or all of at least one of the above-mentioned attribute information and history information.

[0141] In addition, the acquisition unit 30 acquires advertiser information, which is information on the advertiser O, from the advertiser information storage unit 21 or the like, and acquires information on the advertising campaign Camp from the campaign information storage unit 22. In addition, the acquisition unit 30 acquires information on the advertisement provision history from the advertisement delivery history storage unit 23.

[0142] For example, the acquisition unit 30 acquires, from the storage unit 11, advertisement information including information on advertisements provided to a user U who has reached a specific goal (a specific behavior such as conversion or engagement) for each specific goal. For example, the acquisition unit 30 acquires advertisement information including information on one or more advertisements provided from the time when the user U reaches the specific goal (for example, the time when the user purchases product X) until a predetermined period TA before the specific goal is reached.

[0143] The predetermined period TA is, for example, a period such as one week, but is not limited to this example, and can be set appropriately depending on, for example, the attributes of the user U, the category of the product X, the contents of the specific goal, and the like.

[0144] In addition, the acquisition unit 30 can, for example, aggregate information stored in the memory unit 11 and acquire provided advertisement information including information regarding the specific goal for each combination of advertisements provided to the user from the time the user reaches the specific goal until a predetermined period TA before the time.

[0145] For example, in the example shown in FIG. 1, the types of advertisement combinations are, in the case of the purchase of product X1, a combination of one or more of six advertisements A1, A2, B1, B2, C1, and C2, and in the case of the purchase of product X2, a combination of one or more of three advertisements D, E, and F.

[0146] In addition, the acquisition unit 30 can also, for example, aggregate information stored in the memory unit 11 and acquire provided advertisement information including information regarding the specific goal for each advertisement provision order provided from the time the specific goal is reached by the user up to a predetermined period TA before the time the specific goal is reached.

[0147] [3.3.2. Reception Unit 31] The reception unit 31 receives various requests and information from the terminal device 2 and the terminal device 3 via the communication unit 10.

[0148] For example, the request accepted by the accepting unit 31 is, but is not limited to, an advertisement request transmitted from the terminal device 2. In addition, the accepting unit 31 accepts advertiser information, advertising campaign information, budget change information, or total budget information transmitted from the terminal device 3 to the information processing device 1.

[0149] When the reception unit 31 receives advertiser information, it stores the received advertiser information in the advertiser information storage unit 21. When the reception unit 31 receives advertising campaign information, it stores information included in the received advertising campaign information in the advertiser information storage unit 21, the campaign information storage unit 22, etc.

[0150] [3.3.3. Distribution Unit 32] When the reception unit 31 receives an advertisement request transmitted from the terminal device 2, the distribution unit 32 performs a bidding process and distributes an advertisement selected by the bidding process to the terminal device 2 that is the advertisement request source.

[0151] For example, when an advertisement request transmitted from the terminal device 2 is received by the receiving unit 31, the distribution unit 32 performs bidding processing for advertisement distribution. The distribution unit 32 calculates a predicted value of a specific goal achievement rate (for example, a predicted CVR value or a predicted engagement rate value), which is a predicted value of a probability of reaching a specific goal, based on information of the user U of the terminal device 2 that transmitted the advertisement request received by the receiving unit 31 (for example, information on the attributes of the user U and information on the behavior history of the user U).

[0152] The distribution unit 32 has, for example, a prediction model that calculates a predicted value of a specific target achievement rate, and calculates a predicted value of the specific target achievement rate using the prediction model. The prediction model inputs, for example, information on the user U and information on the target attribute as feature quantities, and outputs a predicted value of the specific target achievement rate, but is not limited to such an example and may be, for example, a prediction model of the target attribute.

[0153] The predicted value of the specific target achievement rate calculated by the distribution unit 32 is, for example, a predicted value of the probability of the user U of the terminal device 2 that has transmitted the advertisement request purchasing the product X. For example, the distribution unit 32 determines a value obtained by multiplying the acquisition cost of each advertisement in the advertisement campaign Camp by the predicted value of the specific target achievement rate as the bid amount for each advertisement, and performs bidding processing for each advertisement using the determined bid amount for each advertisement.

[0154] When the distribution unit 32 determines the terminal device 2 that transmitted the advertisement request accepted by the reception unit 31 as the destination of the advertisement through the bidding process, the distribution unit 32 distributes the advertisement to the terminal device 2 that transmitted the advertisement request accepted by the reception unit 31.

[0155] In the bidding process, an automatic bidding called a first price auction is conducted in which the highest bidder wins, but an automatic bidding called a second price action is also conducted in which the second highest bidder wins. Also, in the bidding process, automatic bidding other than second price action and first price auction may be conducted.

[0156] 3.3.4. Calculation unit 33 The calculation unit 33 calculates various pieces of information. For example, the calculation unit 33 calculates the ad unit contribution of each advertisement, the ad group unit contribution of each advertisement group, etc. The calculation unit 33 includes a first calculation unit 40 and a second calculation unit 41.

[0157] 3.3.4.1. First Calculation Unit 40 The first calculation unit 40 calculates the contribution to a specific goal for each advertisement included in each of a plurality of advertisement groups set by the advertiser O as an advertisement unit contribution. The specific goal is, for example, conversion or engagement. In the following, the case where the specific goal is conversion will be mainly described.

[0158] The first calculation unit 40, for example, calculates the advertising unit contribution for each predetermined period TB, or calculates the advertising unit contribution for each period set by the advertiser O (for example, for each period in which the budget amount set by the advertiser O is different).

[0159] The first calculation unit 40 calculates the number of conversions for each of the above-mentioned advertisement combinations AG based on the provided advertisement information acquired by the acquisition unit 30. For example, m Assume that a combination of advertisements X, Y, and Z is a combination of advertisements X, Y, and Z. Each of advertisements X, Y, and Z is, for example, one of the above-mentioned advertisements A1, A2, B1, B2, C1, C2, D, E, and F, but is not limited to such an example. Each of advertisements X, Y, and Z is, for example, a different advertisement from each other, but advertisements X, Y, and Z may be partly or entirely the same advertisement.

[0160] In this case, the first calculation unit 40 calculates the number of conversions that occurred when the advertisements X, Y, and Z were provided to the user from the time of conversion of the user (for example, the time when the user purchased the product X) until a predetermined period TA, thereby calculating the advertisement combination AG. m Calculate the number of conversions.

[0161] Then, for each advertisement combination AG, the first calculation unit 40 calculates the score of the advertisements included in the advertisement combination AG. For example, when the advertisement combination AG is a combination of only one advertisement, the first calculation unit 40 sets the score of the advertisements included in the advertisement combination AG to a value obtained by multiplying a reference value (for example, 1) by the number of conversions of the advertisement combination AG.

[0162] For example, assume that the advertisement combination AG is a combination of only one advertisement X, and the number of conversions for the combination of only advertisement X is 100. In this case, the first calculation unit 40 calculates a value (e.g., 100) obtained by multiplying a reference value (e.g., 1) by 100 as the score of advertisement X. In the case of a combination of only one advertisement X, the scores of advertisements other than advertisement X are 0.

[0163] Furthermore, when the advertisement combination AG is a combination of two or more advertisements, the first calculation unit 40 multiplies the score of each advertisement included in the advertisement combination AG by a reference value, the weight, and the number of conversions of the advertisement combination AG. The weight is the reciprocal of the number of advertisements, and is, for example, 1 / 2 when there is a combination of two advertisements, and 1 / 3 when there is a combination of three advertisements.

[0164] For example, assume that the advertisement combination AG includes two advertisements X and Y, and the number of conversions for the combination of the two advertisements X and Y is 100. In this case, the first calculation unit 40 calculates a value (e.g., 50) obtained by multiplying a reference value (e.g., 1) by 1 / 2 and 100 as the score of each advertisement X and Y. In the case of the combination of two advertisements X and Y, the scores of advertisements other than advertisements X and Y are 0.

[0165] The first calculation unit 40 calculates the advertisement unit contribution degree for each advertisement by tallying up the advertisement scores calculated for each advertisement combination AG for each advertisement. For example, the score of advertisement X calculated for each advertisement combination AG is scores SX1 to SX n In this case, the ad unit contribution of ad X is the score SX1 to SX n The sum of the above.

[0166] Furthermore, in the case of a combination of two or more advertisements, the first calculation unit 40 may weight the scores of the two advertisements included in the advertisement combination in accordance with the advertisement presenting order AO instead of equally weighting the scores.

[0167] The advertisement presentation order AO is the order in which advertisements are presented to a corresponding user. For example, if advertisements X, Y, and Z are presented to the corresponding user in this order from the time of conversion of the corresponding user (e.g., the time when the corresponding user purchases product X) until a predetermined period TA, the advertisement presentation order AO is advertisement X, advertisement Y, and advertisement Z. Advertisements X, Y, and Z are, for example, different advertisements from each other, but some or all of advertisements X, Y, and Z may be the same advertisement.

[0168] Moreover, when one or more advertisements provided to a corresponding user in a predetermined period TA are in the order of advertisement X, advertisement Y, the advertisement presentation order AO is advertisement X, advertisement Y. Moreover, when one or more advertisements provided to a corresponding user in a predetermined period TA are only advertisement X, the advertisement presentation order AO is only advertisement X.

[0169] In this case, the first calculation unit 40 calculates the number of conversions for each advertisement presenting order AO based on the provided advertisement information. Then, the first calculation unit 40 calculates the score of the advertisement included in the advertisement presenting order AO for each advertisement presenting order AO. For example, when the advertisement presenting orders are AO1 to AO, p , the first calculation unit 40 calculates the advertisement presentation order AO1 to AO p Calculate the number of conversions for each.

[0170] The first calculation unit 40 can calculate the score of the advertisement by multiplying a value obtained by weighting the advertisement closer to the time of conversion of the user (for example, the time when the user purchased product X) by the number of conversions.

[0171] In this case, the weights are set to, for example, a total of 1. For example, when the advertisement presentation order AO is advertisement X, advertisement Y, and advertisement Z, the weight of advertisement X is, for example, 0.2, the weight of advertisement Y is, for example, 0.3, and the weight of advertisement Z is, for example, 0.5, but are not limited to such an example.

[0172] Advertisement Order AO m The order is Ad X, Ad Y, Ad Z, and the weights of Ad X, Ad Y, and Ad Z are 0.15, 0.3, and 0.55, respectively. m Assume that the number of conversions is 100. In this case, the ad serving order AO m In the above, the score of advertisement X is 15, the score of advertisement Y is 30, and the score of advertisement Z is 55. m In this example, the score of ads other than ads X, Y, and Z is 0.

[0173] Then, the first calculation unit 40 calculates the advertisement unit contribution degree for each advertisement by tallying up the advertisement scores calculated for each advertisement presentation order AO for each advertisement. For example, if the score of advertisement X calculated for each advertisement presentation order AO is SX11 to SX1 p In this case, the ad unit contribution of ad X is the score SX1 to SX p The sum of the above.

[0174] The method of calculating the ad unit contribution of each advertisement is not limited to the above-mentioned calculation method. For example, the first calculation unit 40 can generate a prediction model that predicts the number of conversions according to the advertisement combination AG and the number of conversions according to the advertisement presentation order AO, and calculate the ad unit contribution of each advertisement using the generated prediction model.

[0175] The prediction model is expressed by, for example, the above formula (1). In the above formula (1), the feature amount is advertisement presentation related information (for example, information on advertisement combination AG or information on advertisement presentation order AO), and pCV is the predicted number of conversions.

[0176] The first calculation unit 40 calculates the number of conversions for each advertisement combination AG or for each advertisement presentation order AO based on the provided advertisement information. The first calculation unit 40 then generates learning information including advertisement presentation related information and information indicating the number of conversions for each advertisement combination, and generates a prediction model using the learning information. The first calculation unit 40 calculates the ad unit contribution of each advertisement using the generated prediction model.

[0177] For example, the prediction model is an RNN such as LSTM or GRU. In this case, the information processing device 1 inputs advertisement provision related information to the prediction model, and calculates the score of the advertisement by multiplying the output value of a softmax function in the prediction model at this time by, for example, the number of conversions. The output value of the softmax function is obtained by applying the softmax function to the output of hierarchical attention, and is expressed as a probability distribution of each advertisement. Hierarchical attention is an example of an attention mechanism.

[0178] Also, it is assumed that the prediction model is a classification model such as a linear regression model or GBDT. In this case, the first calculation unit 40 inputs the advertisement presentation related information into the prediction model and performs a process of acquiring pCV, which is a predicted number of conversions, from the prediction model for each advertisement combination AG or each advertisement presentation order AO.

[0179] Then, the information processing device 1 performs a process of calculating the score of each advertisement for each advertisement combination AG or each advertisement presentation order AO, using the pCV for each advertisement combination AG or each advertisement presentation order AO.

[0180] For example, the first calculation unit 40 calculates a score for each of the multiple advertisements based on the number of conversions predicted by the prediction model when the multiple advertisements are provided to the user U and the number of conversions predicted by the prediction model when only a portion of the multiple advertisements are provided to the user U.

[0181] For example, assume that the advertisement combination is a combination of advertisements X, Y, and Z. In this case, the first calculation unit 40 performs the calculations of the following formulas (6) to (8). Sc(X) is the score of advertisement X, Sc(Y) is the score of advertisement Y, and Sc(Z) is the score of advertisement Z. Sc(X)={f(φ)+(f(X)-f(φ)) ···(6) Sc(Y)={f(φ)+(f(X,Y)-f(X)) ···(7) Sc(Z)={f(φ)+(f(X,Y,Z)-f(X,Y)) ···(8)

[0182] In the above formulas (6) to (8), f(φ) is the pCV when none of advertisements X, Y, and Z are provided to user U, and f(X) is the pCV when only advertisement X is provided to user U. In the above formulas (7) and (8), f(X,Y) is the pCV when advertisements X and Y are provided to user U. In the above formula (8), f(X,Y,Z) is the pCV when advertisements X, Y, and Z are provided to user U. Note that "φ" in f(φ) means an empty set.

[0183] In this way, the scores Sc(X), Sc(Y), and Sc(Z) are expressed in a form that includes an equation that subtracts the pCV of an advertising combination that does not include one ad from the pCV of an advertising combination in which one ad is added to an advertising combination that does not include one ad.

[0184] The first calculation unit 40 similarly calculates each advertisement score for advertisement combinations other than the combination of advertisements X, Y, and Z. Then, the first calculation unit 40 calculates the advertisement unit contribution degree for each advertisement by tallying up the scores of each advertisement for each advertisement.

[0185] In the above-mentioned example of processing in the first calculation unit 40, the calculation of the advertising unit contribution for each advertisement when the specific goal is conversion was explained, but the first calculation unit 40 can also calculate the advertising unit contribution for each advertisement by similar processing when the specific goal is engagement.

[0186] In addition to the information on the type of advertisement provision, the feature of the prediction model may include attribute information of the user U. In this case, the attribute information of the user U is information on the attributes of the user, such as the age and sex of the user, but is not limited to such an example and may include, for example, occupation, place of residence, and annual income.

[0187] [3.3.4.2. Second Calculation Unit 41] The second calculation unit 41 calculates the contribution of each of the multiple ad groups to a specific goal as an ad group unit contribution, based on the ad unit contribution for each advertisement calculated by the first calculation unit 40. As described above, the specific goal is, for example, conversion or engagement.

[0188] 8 is a diagram illustrating an example of a change in the ad group unit contribution degree and the amount of the budget set by the advertiser O according to the embodiment. In the example illustrated in FIG. 8, as the amount of the budget set by the advertiser O increases, the ad group unit contribution degree increases.

[0189] The second calculation unit 41, for example, calculates the advertising unit group contribution degree for each predetermined period TB, or calculates the advertising unit group contribution degree for each period set by the advertiser O (for example, for each period in which the budget amount set by the advertiser O is different).

[0190] For example, it is assumed that the advertising campaign information received by the receiving unit 31 includes information on the above-mentioned advertising campaigns Camp1, Camp2, and Camp3. In this case, the second calculation unit 41 calculates the ad group unit contribution of the advertisement group including advertisements A1, B1, and C1 (the ad group of the advertising campaign Camp1) by summing the ad unit contributions of advertisements A1, B1, and C1.

[0191] Moreover, the second calculation unit 41 calculates the ad group unit contribution of the ad group including advertisements A2, B2, and C2 (ad group of advertising campaign Camp2) by summing the ad unit contributions of advertisements A2, B2, and C2. Moreover, the second calculation unit 41 calculates the ad group unit contribution of the ad group including advertisements D, E, and F (ad group of advertising campaign Camp3) by summing the ad unit contributions of advertisements D, E, and F.

[0192] [3.3.5. Generation unit 34] The generation unit 34 generates, for each advertisement group, characteristic information that is information indicating a relationship between the advertisement group unit contribution degree of the advertisement group calculated by the second calculation unit 41 and the amount of the budget for delivery of multiple advertisements included in the advertisement group (budget amount for the advertisement group). The characteristic information includes, for example, information obtained using a mathematical model or a machine learning model.

[0193] Fig. 9 is a diagram showing an example of characteristic information generated by the generation unit 34 of the information processing device 1 according to the embodiment. In the example shown in Fig. 9, when the budget amount of the ad group is small, the increase rate of the ad group unit contribution of the ad group is large relative to the increase rate of the budget amount of the ad group, but when the budget amount of the ad group is large, the increase rate of the ad group unit contribution of the ad group is small relative to the increase rate of the budget amount of the ad group. Therefore, simply increasing the budget amount of the ad group may not provide an ad group unit contribution that matches the budget amount of the ad group.

[0194] The generating unit 34 generates the characteristic information based on, for example, the advertisement group unit contribution degree for each predetermined period TB and the amount of the budget for each predetermined period TB. The generating unit 34 can also generate the characteristic information based on, for example, the advertisement group unit contribution degree for each amount of the budget.

[0195] The generating unit 34 can generate the characteristic information by using, for example, a mathematical model or a machine learning model. For example, the generating unit 34 generates the characteristic information by using the Vidale & Wolfe model, which is one of the mathematical models. The Vidale & Wolfe model is expressed by, for example, the above formula (2).

[0196] In this way, the Vidale & Wolfe model can express marginal utility and the delayed occurrence of ad group unit contribution, and can be differentiated. Marginal utility is an effect in which the increase in effect decreases as the budget amount increases. Because marginal utility can be expressed, it is possible to take into account the attenuation of the increase in ad group unit contribution. For example, it is possible to make the increase in ad group unit contribution when the budget is increased from 10,000 yen to 20,000 yen larger than the increase in ad group unit contribution when the budget is increased from 100,000 yen to 110,000 yen.

[0197] In addition, since it is possible to express the delayed occurrence of ad group unit contributions, the results of the delayed observed target behavior (conversion or engagement) are also taken into account, and the most recent performance can be used for learning. In particular, ad group unit contributions are a good fit because they take time to occur. In addition, the Vidale & Wolfe model has the advantage that it is easy to use for optimization, since the change in ad group unit contribution when the budget amount is changed can be analytically obtained.

[0198] The generation unit 34 estimates parameters such as "M", "λ", and "r" for each advertisement group using time-series history information including information on the advertisement group unit contribution degree calculated by the calculation unit 33 and information on the budget amount for each period. For example, the information processing device 1 estimates parameters such as "M", "λ", and "r" for each advertisement group using a statistical method such as maximum likelihood estimation or least squares method. Note that the information on the budget amount included in the history information may be information on the amount consumed within the period or information on the amount obtained by multiplying or adding an adjustment value to the consumed amount in a case where only a part of the budget amount is consumed within the period.

[0199] The generation unit 34 uses the Vidale & Wolfe model with estimated parameters to generate characteristic information indicating the relationship between the ad-group unit contribution and the budget amount for each ad group. The characteristic information is information of a function graph indicating the ad-group unit contribution and the budget amount, but is not limited to such an example. For example, the generation unit 34 can obtain a predicted value of the change in the ad-group unit contribution by changing the budget amount in the Vidale & Wolfe model with estimated parameters, thereby generating characteristic information.

[0200] Furthermore, the generation unit 34 can perform learning and generate a machine learning model using time-series history information including the information on the advertisement group unit contribution degree calculated by the calculation unit 33 and the information on the budget amount for each period as learning information. In this case, the information on the advertisement group unit contribution degree is used as label information, but is not limited to such an example. The machine learning model is, for example, an RNN such as LSTM or GRU, a classification model such as a linear regression model or GBDT, or the like, but is not limited to such an example.

[0201] The generation unit 34 generates, for each advertisement group, characteristic information indicating a relationship between the advertisement group unit contribution degree and the budget amount, using the generated machine learning model. The characteristic information is information of a function graph indicating the advertisement group unit contribution degree and the budget amount, but is not limited to such an example.

[0202] The generation unit 34 can also generate a scatter diagram showing the advertisement-group-unit contribution degree and the budget amount as characteristic information for each advertisement group, using time-series history information including, for each period, information on the advertisement-group-unit contribution degree and information on the budget amount calculated by the calculation unit 33. The generation unit 34 can also derive a characteristic curve from the generated scatter diagram.

[0203] [3.3.6. Decision Unit 35] The determination unit 35 performs various determinations. For example, the determination unit 35 determines the amount of the budget for each of the plurality of advertisement groups based on the amount of the budget for the plurality of advertisement groups (total budget amount) set by the advertiser O and the characteristic information of each of the plurality of advertisement groups generated by the generation unit 34.

[0204] Fig. 10 is a diagram showing an example of how the determination unit 35 of the information processing device 1 according to the embodiment determines the amount of the budget for each of a plurality of advertisement groups. In the example shown in Fig. 10, the advertisement campaign information included in the advertisement campaign information received by the reception unit 31 is the information on the above-mentioned advertisement campaigns Camp1, Camp2, and Camp3. As shown in Fig. 10, the determination unit 35 determines the amount of the budget for each of the plurality of advertisement groups so that, for example, the total contribution degree Aall is maximized.

[0205] For example, the determination unit 35 determines the budget for each of multiple ad groups such that the total contribution Aall, which is the sum of the ad group unit contributions of multiple ad groups in the characteristic information of each of the multiple ad groups, within the total budget amount Pamx, which is the amount of the budget for multiple ad groups, is maximum or within a range of a predetermined condition from the maximum.

[0206] Fig. 11 is a diagram showing an example of a method for determining the budget amount of each of a plurality of advertisement groups by the determination unit 35 of the information processing device 1 according to the embodiment. In the example shown in Fig. 11, the budget amount of the advertisement campaign Camp1 is set to "P1", the budget amount of the advertisement campaign Camp2 is set to "P2", and the budget amount of the advertisement campaign Camp3 is set to "P3". In this case, the total contribution degree Aall is expressed by the above formula (3).

[0207] The determination unit 35 calculates the advertisement group unit contributions AT1, AT2, AT3 that are the maximum total contribution Aall or the advertisement group unit contributions AT1, AT2, AT3 that are within a range of a predetermined condition from the maximum total contribution Aall under the constraint condition of the above formula (4). The range of the predetermined condition is, for example, a range from 90% to 100% of the total contribution Aall, but can be set arbitrarily. Then, the determination unit 35 determines the determined budget amount Ps1, which is the budget amount P1 corresponding to the calculated advertisement group unit contribution AT1, from the characteristic information of the advertisement group in the advertising campaign Camp1.

[0208] The determination unit 35 also determines a determined budget amount Ps2, which is the budget amount P2 corresponding to the calculated advertisement group unit contribution level AT2, from the characteristic information of the advertisement group in the advertisement campaign Camp2. The determination unit 35 also determines a determined budget amount Ps3, which is the budget amount P3 corresponding to the calculated advertisement group unit contribution level AT3, from the characteristic information of the advertisement group in the advertisement campaign Camp3.

[0209] In addition, the determination unit 35 can also determine the budget amount of each of multiple advertisement groups within the total budget amount Pamx, which is the budget amount for multiple advertisement groups, based on the change in advertisement group-based contribution when the budget amount of the advertisement group is increased or decreased.

[0210] 12 is a diagram showing another example of a method for determining the budget amount of each of a plurality of advertisement groups by the determination unit 35 of the information processing device 1 according to the embodiment. As shown in FIG. 12, the determination unit 35 can determine the budget amount of each of a plurality of advertisement groups within the total budget amount Pmax by using the above formula (5).

[0211] In this way, the determination unit 35 can use the change in the advertisement group unit contribution when the budget amount for each advertisement group is increased or decreased, thereby making it possible to update the budget amount stably without being affected by probabilistic variations.

[0212] For example, if the change in ad group unit contribution is large when the amount of the budget for an advertisement group is changed, the change in ad group unit contribution can be made larger even if the increase in the budget amount is small, compared to when the change in ad group unit contribution is small. Also, if the change in ad group unit contribution is small when the amount of the budget for an advertisement group is increased, the change in ad group unit contribution can be made smaller even if the decrease in the budget amount is large, compared to when the change in ad group unit contribution is large. Therefore, the budget amount can be updated stably without being affected by stochastic variations.

[0213] [3.3.7.Providing Department 36] The providing unit 36 ​​provides various types of information to the user U and the advertiser O via the communication unit 10. For example, the providing unit 36 ​​transmits information on the advertisement unit contribution degree of each advertisement and information on the advertisement group unit contribution degree of each advertisement group calculated by the calculation unit 33 to the terminal device 3 of the advertiser O, thereby providing the advertiser O with information on the advertisement unit contribution degree of each advertisement and information on the advertisement group unit contribution degree of each advertisement group.

[0214] In addition, the providing unit 36 ​​can provide the advertiser O with the specific information for each advertisement group, by transmitting the specific information for each advertisement group generated by the generating unit 34 to the terminal device 3 of the advertiser O, for example.

[0215] In addition, the providing unit 36 ​​can provide the determined budget information to the advertiser O by transmitting the determined budget information including information on the budget amount of each of the multiple advertising groups determined by the determining unit 35 to the terminal device 3 of the advertiser O.

[0216] 4. Processing Procedure Next, a procedure of information processing by the processing unit 12 of the information processing device 1 according to the embodiment will be described. Fig. 13 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

[0217] 13, the processing unit 12 of the information processing device 1 determines whether or not the advertising campaign information has been received (Step S20). If the processing unit 12 determines that the advertising campaign information has been received (Step S20: Yes), the processing unit 12 stores the received advertising campaign information (Step S21).

[0218] When the processing of step S21 is completed or when it is determined that the advertising campaign information has not been accepted (step S20: No), the processing unit 12 determines whether or not it is time to generate characteristic information (step S22). The timing to generate characteristic information is, but is not limited to, a timing that arrives at a predetermined cycle, a timing that a predetermined period has elapsed since the start of distribution of the advertisement indicated in the advertising campaign information, or a timing that is requested by the advertiser O.

[0219] When the processing unit 12 determines that it is time to generate characteristic information (step S22: Yes), it calculates the advertisement unit contribution of each advertisement included in each advertisement group (step S23), and calculates the advertisement group unit contribution of each advertisement group based on the advertisement unit contribution of each advertisement (step S24).Then, the processing unit 12 generates characteristic information for each advertisement group based on the information on the advertisement group unit contribution of the advertisement group and the information on the budget amount for the advertisement group (step S25), and provides the generated characteristic information for each advertisement group to the advertiser O (step S26).

[0220] When the processing of step S26 is completed or when it is determined that the timing for generating characteristic information has not come (step S22: No), the processing unit 12 determines whether or not the total budget information has been received (step S27). When it is determined that the total budget information has been received (step S27: Yes), the processing unit 12 determines the amount of the budget for each advertisement group (step S28). When the process of step S27 is completed or when it is determined that the total budget information has not been received (step S27: No), the processing unit 12 determines whether or not the operation end timing has arrived (step S29). The processing unit 12 determines that the operation end timing has arrived when, for example, the power supply of the information processing device 1 is turned off.

[0221] If the processing unit 12 determines that the operation end time has not arrived (step S29: No), it transitions to step S20, and if it determines that the operation end time has arrived (step S29: Yes), it terminates the processing shown in FIG. 13.

[0222] 5. Modifications In the above example, the specific goal of advertising campaigns Camp1 and Camp2 (purchasing product X1) is different from the specific goal of advertising campaign Camp3 (purchasing product X2), but the specific goals of advertising campaigns Camp1, Camp2, and Camp3 may be the same as each other.

[0223] In addition, in the above example, before the budget amount of each advertisement group is determined based on the specific information, the budget amount of each advertisement group is changed by the advertiser O, but the budget amount of each advertisement group may also be changed by the determination unit 35.

[0224] For example, the determination unit 35 can change the total budget amount Pmax randomly or according to a predetermined rule before determining the amount of the budget for each advertisement group based on the specific information. This allows the processing unit 12 to generate characteristic information even if the advertiser O does not change the budget amount for the advertisement group.

[0225] The processing unit 12 can also generate characteristic information for various conditions such as for each day of the week, for each time period, for each season, for each specific event, and can determine the amount of the budget for each advertisement group. The processing unit 12 can also generate characteristic information according to a combination of two or more of the day of the week, the time period, the season, and the specific event, and can determine the amount of the budget for each advertisement group.

[0226] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by a computer 80 having a configuration as shown in Fig. 14, for example. Fig. 14 is a hardware configuration diagram showing an example of the computer 80 that realizes the functions of the information processing device 1 according to the embodiment. The computer 80 has a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, a HDD (Hard Disk Drive) 84, a communication interface (I / F) 85, an input / output interface (I / F) 86, and a media interface (I / F) 87.

[0227] The CPU 81 operates and controls each part based on a program stored in the ROM 83 or the HDD 84. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 is started up, and programs that depend on the hardware of the computer 80.

[0228] The HDD 84 stores programs executed by the CPU 81, data used by such programs, etc. The communication interface 85 receives data from other devices via the network N (see FIG. 2) and sends it to the CPU 81, and transmits data generated by the CPU 81 to other devices via the network N.

[0229] The CPU 81 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 86. The CPU 81 acquires data from the input devices via the input / output interface 86. The CPU 81 also outputs data generated via the input / output interface 86 to the output devices.

[0230] The media interface 87 reads a program or data stored in a recording medium 88 and provides it to the CPU 81 via the RAM 82. The CPU 81 loads the program from the recording medium 88 onto the RAM 82 via the media interface 87 and executes the loaded program. The recording medium 88 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.

[0231] For example, when the computer 80 functions as the information processing device 1 according to the embodiment, the CPU 81 of the computer 80 executes a program loaded onto the RAM 82 to realize the function of the processing unit 12. In addition, the HDD 84 stores data in the storage unit 11. The CPU 81 of the computer 80 reads and executes these programs from a recording medium 88, but as another example, these programs may be obtained from another device via the network N.

[0232] [7. Other] In addition, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0233] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0234] For example, the above-mentioned information processing device 1 may be realized by a terminal device and a server computer, or may be realized by multiple server computers. Also, depending on the functions, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

[0235] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0236] 8. Effects As described above, the information processing device 1 according to the embodiment includes a first calculation unit 40, a second calculation unit 41, and a generation unit 34. The first calculation unit 40 calculates the contribution to a specific goal for each advertisement included in each of a plurality of advertisement groups set by the advertiser O as an advertisement unit contribution. The second calculation unit 41 calculates the contribution to a specific goal for each of the plurality of advertisement groups as an advertisement group unit contribution based on the advertisement unit contribution for each advertisement calculated by the first calculation unit 40. The generation unit 34 generates, for each advertisement group, characteristic information that is information indicating a relationship between the advertisement group unit contribution of the advertisement group calculated by the second calculation unit 41 and the amount of a budget for the delivery of a plurality of advertisements included in the advertisement group. This allows the information processing device 1 to provide support for appropriately setting a budget for the delivery of advertisements.

[0237] Furthermore, the first calculation unit 40 calculates the advertisement unit contribution for each predetermined period, the second calculation unit 41 calculates the advertisement group unit contribution AT1 for each predetermined period, and the generation unit 34 generates characteristic information based on the advertisement group unit contribution for each predetermined period and the budget amount for each predetermined period. This allows the information processing device 1 to generate characteristic information with high accuracy.

[0238] Furthermore, the first calculation unit 40 calculates the advertisement unit contribution for each budget amount, the second calculation unit 41 calculates the advertisement group unit contribution for each budget amount, and the generation unit 34 generates characteristic information based on the advertisement group unit contribution for each budget amount. This allows the information processing device 1 to provide support for appropriately setting a budget for advertisement delivery. This allows the information processing device 1 to generate characteristic information with high accuracy.

[0239] Furthermore, the characteristic information includes information obtained using a mathematical model or a machine learning model, which allows the information processing device 1 to generate the characteristic information with high accuracy.

[0240] The information processing device 1 also includes a determination unit 35 that determines the amount of the budget for each of the plurality of advertisement groups, based on the amount of the budget for the plurality of advertisement groups set by the advertiser O and the characteristic information of each of the plurality of advertisement groups generated by the generation unit 34. This allows the information processing device 1 to provide support for appropriately setting the budget for advertisement distribution.

[0241] Furthermore, the determination unit 35 determines the budget for each of the plurality of ad groups such that the sum of the ad group unit contribution degrees AT1 of the plurality of ad groups in the characteristic information of each of the plurality of ad groups is maximum or within a range of a predetermined condition from the maximum within the amount of the budget for the plurality of ad groups. This enables the information processing device 1 to provide support for appropriately setting the budget for delivering advertisements.

[0242] Furthermore, the determination unit 35 determines the budget amount for each of the plurality of advertisement groups within the budget amount for the plurality of advertisement groups, based on the change in the advertisement group unit contribution degree AT1 when the budget amount for the advertisement group is increased or decreased. This enables the information processing device 1 to provide support for appropriately setting the budget for advertisement delivery.

[0243] Moreover, the specific goal is conversion or engagement. This allows the information processing device 1 to provide support for appropriately setting a budget for advertisement delivery.

[0244] The above describes the embodiment of the present application in detail based on the drawings, but this is merely an example, and the present invention can be implemented in other forms that include various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the Disclosure of the Invention section.

[0245] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, an acquisition section can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0246] 1. Information processing device 2,3 Terminal Equipment 10. Communications Department 11 Storage section 12 Processing section 20 User information storage unit 21 Advertiser information storage unit 22 Campaign information storage unit 23 Advertisement delivery history memory unit 30 Acquisition Department 31 Reception 32 Distribution Department 33 Calculation section 34 Generation part 35 Decision Section 36 Providing Department 40 First Calculation Section 41 Second Calculation Section 100 Information Processing Systems N Network

Claims

1. a first calculation unit that calculates a contribution to a specific goal for each advertisement included in each of a plurality of advertisement groups as an advertisement unit contribution; a second calculation unit that calculates a contribution of each of the plurality of advertisement groups to the specific goal as an ad group unit contribution based on the ad unit contribution for each of the advertisements calculated by the first calculation unit; a generation unit that generates, for each of the advertisement groups, characteristic information that is information indicating a relationship between the advertisement group unit contribution degree of the advertisement group calculated by the second calculation unit and an amount of a budget for delivery of a plurality of advertisements included in the advertisement group.

23. An information processing apparatus comprising:

2. The first calculation unit is Calculating the advertising unit contribution for each predetermined period; The second calculation unit is Calculating the advertisement group unit contribution degree for each of the predetermined periods; The generation unit is The characteristic information is generated based on the advertisement group unit contribution degree for each of the predetermined periods and the amount of the budget for each of the predetermined periods.

2. The information processing apparatus according to claim 1,

3. The first calculation unit is Calculating the advertising unit contribution for each amount of the budget; The second calculation unit is Calculating the advertisement group unit contribution for each amount of the budget; The generation unit is The characteristic information is generated based on the advertisement group unit contribution degree for each budget amount.

2. The information processing apparatus according to claim 1,

4. The characteristic information is Includes information obtained using mathematical or machine learning models 4. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

5. A determination unit that determines a budget amount for each of the plurality of advertisement groups based on a budget amount for the plurality of advertisement groups set by an advertiser and the characteristic information for each of the plurality of advertisement groups generated by the generation unit.

4. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

6. The determination unit is A budget for each of the plurality of ad groups is determined such that a sum of the ad group unit contribution degrees of the plurality of ad groups in the characteristic information of each of the plurality of ad groups is maximized or falls within a range of a predetermined condition from the maximum within the amount of the budget for the plurality of ad groups.

6. The information processing apparatus according to claim 5,

7. The determination unit is Based on a change in the advertisement group unit contribution degree when the amount of the budget for the advertisement group is increased or decreased, a budget amount for each of the plurality of advertisement groups is determined within the budget amount for the plurality of advertisement groups.

6. The information processing apparatus according to claim 5,

8. The specific goal is: Conversion or engagement 4. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

9. 1. A computer-implemented information processing method, comprising: a first calculation step of calculating a contribution to a specific goal for each advertisement included in each of a plurality of advertisement groups as an advertisement unit contribution; a second calculation step of calculating a contribution of each of the plurality of advertisement groups to the specific goal as an advertisement group unit contribution based on the advertisement unit contribution of each of the advertisements calculated in the first calculation step; and generating, for each of the advertisement groups, characteristic information indicating a relationship between the advertisement group unit contribution degree of the advertisement group calculated in the second calculation step and a budget amount for delivery of a plurality of advertisements included in the advertisement group.

23. An information processing method comprising:

10. a first calculation step of calculating a contribution to a specific goal for each advertisement included in each of a plurality of advertisement groups as an advertisement unit contribution; a second calculation step of calculating a contribution of each of the plurality of advertisement groups to the specific goal as an advertisement group unit contribution based on the advertisement unit contribution for each of the advertisements calculated by the first calculation step; a generating step of generating, for each of the advertisement groups, characteristic information indicating a relationship between the advertisement group unit contribution degree of the advertisement group calculated by the second calculating step and a budget amount for delivery of a plurality of advertisements included in the advertisement group.

23. An information processing program comprising:

Images