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

Abstract

To provide an information processing device capable of appropriately grasping an advertising effect by distribution of a specific advertisement, an information processing method, and an information processing program.SOLUTION: An information processing device comprises a determination unit which determines a first distribution candidate and a second distribution candidate, a decision unit which decides one distribution candidate among the first distribution candidate and the second distribution candidate as an object to be distributed, and a simulation unit which virtually decides one of the first distribution candidate and the second distribution candidate as the object to be distributed. When the advertisement request accepted by the acceptance unit is an advertisement request of a first user who does not distribute a specific advertisement, the determination unit determines that the distribution candidate who has replaced the specific advertisement with another advertisement as the first distribution candidate. The simulation unit virtually decides one distribution candidate among the first distribution candidate and the second distribution candidate where a specific advertisement has not been replaced with another advertisement as the object to be distributed.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). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2019-220052 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the above-described conventional technology, for example, when performing a process of narrowing down advertisements to be distributed in two stages, it may be difficult to appropriately grasp the advertising effectiveness of the distribution of a specific advertisement.

[0005] 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 enable appropriate understanding of the advertising effectiveness of the delivery of a specific advertisement. [Means for solving the problem]

[0006] The information processing device of the present disclosure includes a reception unit that receives an advertisement request, an estimation unit that estimates a revenue due to delivery for each of a plurality of advertisements in response to the advertisement request received by the reception unit, a determination unit that determines a first delivery candidate and a second delivery candidate, each of which includes one or more advertisements selected from the plurality of advertisements based on the revenue estimated by the estimation unit, a determination unit that determines one of the first delivery candidate and the second delivery candidate as a delivery target based on the revenue estimated by the estimation unit, a delivery unit that delivers the delivery target determined by the determination unit, and a simulation unit that virtually determines one of the first delivery candidate and the second delivery candidate as a delivery target based on the revenue estimated by the estimation unit. When the advertisement request received by the reception unit is an advertisement request of a first user among an advertisement request of a first user that does not deliver a specific advertisement and an advertisement request of a second user that delivers a specific advertisement, the determination unit determines a delivery candidate in which the specific advertisement is replaced with another advertisement as the first delivery candidate. The simulation unit virtually determines, as a delivery target, one of the first and second delivery candidates in which a specific advertisement has not been replaced with another advertisement. Effect of the Invention

[0007] According to one aspect of the embodiment, it is possible to appropriately grasp the advertising effectiveness of the delivery of a specific advertisement. [Brief description of the drawings]

[0008] [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 advertisement information table stored in the advertisement information storage unit of the information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of an advertisement delivery history table stored in the advertisement delivery history storage unit of the information processing device according to the embodiment. [Figure 7] FIG. 7 is a flowchart showing an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 8] FIG. 8 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

[0009] 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.

[0010] [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.

[0011] 1, the information processing device 1 receives an advertisement request from the terminal device 2 (step S1). For example, a web browser and a news application (hereinafter, may be referred to as a news app) are installed in the terminal device 2. A user U of the terminal device 2 can obtain content from an information providing device (not shown) by starting the web browser or the news app, and can cause the terminal device 2 to execute a process of displaying the obtained content.

[0012] The content provided by the information providing device has a plurality of advertisement spaces, and the terminal device 2 transmits an advertisement request for acquiring advertisements to be displayed in each advertisement space to the information processing device 1. Such advertisement request includes information of an identifier for identifying the user U, such as the user ID (identifier) ​​of the user U or an HTTP cookie (Hyper Text Transfer Protocol cookie).

[0013] Next, the information processing device 1 estimates the revenue from the delivery of the advertisement requests received in step S1 for each of the advertisements (step S2). The revenue estimated in step S2 is, for example, an expected revenue that is the revenue expected from the delivery of the advertisement requests, and is a value obtained by multiplying the predicted result of the index value of the advertising effectiveness by the index cost.

[0014] First, the prediction of the index value of the advertising effectiveness will be described. The information processing device 1 has a prediction model for predicting the index value of the advertising effectiveness based on information of the user U (for example, information on the attributes and behavior history of the user U), and predicts the index value of the advertising effectiveness using the prediction model.

[0015] The advertising effectiveness index value is a value of an advertising performance index, such as, but not limited to, a predicted search rate, a predicted click rate, a predicted conversion rate, etc. For example, the advertising effectiveness index value may be a predicted engagement rate or other predicted value.

[0016] A search is a search (e.g., a web search) in which information on the target of the advertisement (hereinafter sometimes referred to as the advertising target) is used as a search keyword. Information on the advertising target is, for example, information on a specific trading target (e.g., the name of the trading target) or information on a specific brand or company (e.g., a brand name or company name), but is not limited to such examples. When the advertising effectiveness index is search, the prediction model outputs a predicted value of the search rate as a predicted result of the advertising effectiveness index value.

[0017] A click refers to an advertisement or content targeted by the advertisement being selected (e.g., clicked or tapped) by a user U, and a click rate is the probability that the advertisement or content targeted by the advertisement is selected by a user U for one delivery of the advertisement, which is the so-called Click Through Rate (CTR). When the indicator of advertising effectiveness is clicks, the prediction model outputs the predicted value of the CTR as the predicted result of the index value of advertising effectiveness.

[0018] A conversion is an indicator of reaching a goal (e.g., a conversion goal), such as, but not limited to, a purchase of an advertised transaction object, use of an advertised transaction object, registration for an advertised membership service, or visit to an advertised site. The transaction object may be, for example, a product or service.

[0019] The conversion rate is the probability that a conversion occurs for one advertisement delivery, and is known as the CVR (Conversion Rate). When the advertising effectiveness indicator is conversion, the prediction model outputs the predicted value of CVR as the predicted result of the advertising effectiveness indicator value. In the following, the advertising effectiveness indicator value may be simply referred to as the indicator value.

[0020] Engagement is, for example, an index that indicates the degree to which a person is actively involved with an advertising target, and examples thereof include shares, likes, posts, etc. on SNS (Social Networking Service), but are not limited to such examples.

[0021] Next, the index unit cost will be described. When the index is a click, the index unit cost is, for example, a cost per click (CPC: Cost Per Click), and when the index is a search or a conversion, the index unit cost is, for example, a cost per acquisition (CPA: Cost Per Action), but is not limited to such examples.

[0022] For example, when the index is clicks, the information processing device 1 estimates the revenue by multiplying the predicted value of the click rate by the cost per click of the advertisement. Also, for example, when the index is search or conversion, the information processing device 1 estimates the revenue by multiplying the predicted value of the search rate or conversion rate by the cost per acquisition of the advertisement. Note that the estimation of revenue by the information processing device 1 is not limited to the above-mentioned example.

[0023] Next, the information processing device 1 determines a first distribution candidate and a second distribution candidate, each of which includes one or more advertisements, based on the revenue estimated in step S2 (step S3). The advertisement is, for example, a content for advertising a transaction target to be advertised, and is also called an advertisement content.

[0024] Examples of the ad format include text ads, image ads, video ads, animation ads, and ads that combine two or more of text, image, video, and animation, but are not limited to these examples.

[0025] The information processing device 1 determines a first delivery candidate and a second delivery candidate, each of which includes a plurality of advertisements, based on the revenue estimated in step S2, for example. Each of the first delivery candidate and the second delivery candidate includes advertisements having different advertisement formats, but is not limited to this example.

[0026] Here, a case will be described where a first distribution candidate and a second distribution candidate each including a plurality of advertisements are determined. In this case, the information processing device 1 determines a first distribution candidate including the top m advertisements (m is, for example, an integer of 2 or more) in descending order of revenues estimated in step S2 from among a plurality of advertisements in a first advertisement format. Also, the information processing device 1 determines a second distribution candidate including the top m advertisements in descending order of revenues estimated in step S2 from among a plurality of advertisements in a second advertisement format. The first advertisement format is, for example, an advertisement represented by text or an image, and the second advertisement format is, for example, an advertisement represented by a video.

[0027] In the example shown in Fig. 1, the first distribution candidates include advertisements Ad1, Ad2, Ad3, and Ad4, and the second distribution candidates include advertisements Ad11, Ad12, Ad13, and Ad14. Among advertisements Ad1, Ad2, Ad3, and Ad4, advertisement Ad1 has the highest rank, advertisement Ad2 has the second highest rank, advertisement Ad3 has the next highest rank, and advertisement Ad4 has the lowest rank. Note that the higher the revenue estimated in step S2, the higher the rank.

[0028] Similarly, among advertisements Ad11, Ad12, Ad13, and Ad14, advertisement Ad11 has the highest rank, advertisement Ad12 has the second highest rank, advertisement Ad13 has the next highest rank, and advertisement Ad14 has the lowest rank.

[0029] Each of the first and second distribution candidates may include one advertisement having the largest revenue estimated in step S2 among the multiple advertisements. In this case, the first distribution candidate includes one advertisement Ad1 having the largest revenue estimated in step S2 among the multiple advertisements in the first advertisement format, and the second distribution candidate includes one advertisement Ad11 having the largest revenue estimated in step S2 among the multiple advertisements in the second advertisement format.

[0030] Next, the information processing device 1 determines whether the advertisement request accepted in step S1 is an advertisement request of a first user who does not deliver a specific advertisement or an advertisement request of a second user who delivers a specific advertisement (step S4).

[0031] The first user to whom a specific advertisement is not delivered is a user U to whom the specific advertisement is not delivered by the information processing device 1, and can also be called a control user for whom control is exercised so that the specific advertisement is not delivered. The first user to whom a specific advertisement is delivered is a user U to whom the specific advertisement is delivered by the information processing device 1, and can also be called a treat user to whom the specific advertisement is delivered.

[0032] For example, the information processing device 1 determines whether the user U of the terminal device 2 that sent the advertisement request is a first user or a second user, based on the information of the user U of the terminal device 2 that sent the advertisement request accepted in step S1.

[0033] The information of user U is, for example, a user ID, which is an identifier uniquely assigned to user U, and the information processing device 1 determines a user U whose last digit of the user ID is 0 to 4 as a first user, and determines a user U whose last digit of the user ID is 5 to 9 as a second user.

[0034] The method of determining whether user U is the first user or the second user is not limited to this example, and may be determined, for example, by a digit other than the last digit of the user ID. In addition, the information processing device 1 can also determine whether the user U is the first user or the second user by a specific digit of the MAC (Media Access Control) address of the terminal device 2 that has transmitted the advertisement request accepted in step S1.

[0035] 1, the specific advertisement is the advertisement Ad1 included in the second distribution candidates, but is not limited to such an example. In the following, as an example, the specific advertisement will be mainly the advertisement Ad1.

[0036] Next, when the received advertisement request is an advertisement request from a first user among the first user and the second user described above, the information processing device 1 determines a delivery candidate in which the specific advertisement is replaced with another advertisement as a first delivery candidate (step S5).

[0037] In step S5, the information processing device 1 determines, as the first distribution candidate, a distribution candidate in which the specific advertisement in the first distribution candidate determined in step S4 has been replaced with another advertisement. For example, when the first distribution candidate includes advertisements Ad1, Ad2, Ad3, and Ad4, the information processing device 1 replaces the advertisement Ad5, which is the advertisement with the second highest revenue after advertisement Ad4, which is the advertisement with the smallest revenue among advertisements other than advertisement Ad1, which is the specific advertisement in the first distribution candidate, with the other advertisement. The revenue is the revenue estimated in step S2.

[0038] Furthermore, when the first distribution candidates include only the advertisement Ad1 that is a specific advertisement, the information processing device 1 replaces the advertisement Ad1 with the advertisement Ad2 that is the advertisement having the second largest profit after the advertisement Ad1 as another advertisement.

[0039] The information processing device 1 may also perform the process of step S3 after the process of step S4, in which case the process of step S5 is incorporated into the process of step S3. For example, when the advertisement Ad1 is within the top m advertisements among a plurality of advertisements in the first advertisement format, the information processing device 1 does not include the advertisement Ad1 in the first distribution candidates.

[0040] Next, the information processing device 1 performs a final round process to determine one of the first and second distribution candidates as a distribution target based on the revenue estimated in step S2 (step S6). For example, the information processing device 1 calculates the revenue estimated when the first distribution candidate is distributed as a distribution target and the revenue estimated when the second distribution candidate is distributed as a distribution target.

[0041] The estimated revenue when the first distribution candidate is distributed as a distribution target is the total revenue estimated in step S2 for multiple advertisements included in the first distribution candidate, and may be referred to as the first distribution candidate expected revenue below. For example, if the first distribution candidate includes advertisements Ad1, Ad2, Ad3, and Ad4, the first distribution candidate expected revenue is the total revenue of advertisements Ad1, Ad2, Ad3, and Ad4 estimated in step S2. Also, if the first distribution candidate includes advertisements Ad2, Ad3, Ad4, and Ad5, the first distribution candidate expected revenue is the total revenue of advertisements Ad2, Ad3, Ad4, and Ad5 estimated in step S2.

[0042] In addition, the estimated revenue when the second distribution candidate is distributed as the distribution target is the total revenue estimated in step S2 for the multiple advertisements included in the second distribution candidate, and may be referred to as the second distribution candidate expected revenue below. For example, if the second distribution candidate includes advertisements Ad11, Ad12, Ad13, and Ad14, the second distribution candidate expected revenue is the total revenue of advertisements Ad11, Ad12, Ad13, and Ad14 estimated in step S2.

[0043] The information processing device 1 compares the expected profit of the first distribution candidate with the expected profit of the second distribution candidate, and determines the distribution candidate corresponding to the larger expected profit of the first distribution candidate and the second distribution candidate as the distribution target. For example, when the expected profit of the first distribution candidate is larger than the expected profit of the second distribution candidate, the information processing device 1 determines the first distribution candidate as the distribution target, and when the expected profit of the second distribution candidate is larger than the expected profit of the first distribution candidate, the information processing device 1 determines the second distribution candidate as the distribution target.

[0044] Next, the information processing device 1 delivers the multiple advertisements included in the delivery candidates determined as delivery targets in step S4 to the delivery destination terminal device 2 (step S7). For example, when the delivery candidate determined as the delivery target in step S6 is the first delivery candidate, the information processing device 1 delivers the multiple advertisements included in the first delivery candidate to the delivery destination terminal device 2, and when the delivery candidate determined as the delivery target in step S6 is the second delivery candidate, the information processing device 1 delivers the multiple advertisements included in the second delivery candidate to the delivery destination terminal device 2.

[0045] The information processing device 1 stores a history of the distribution candidates that were determined to be distribution targets in the final round process in step S6 and were distributed as distribution targets in step S7. Note that in step S7, the distribution of advertisements included in the distribution candidates is not limited to the transmission of the advertisements themselves to the terminal device 2, and may be the transmission of an advertisement ID for acquiring the advertisement to the terminal device 2. In this case, the information processing device 1 transmits to the terminal device 2 an advertisement that corresponds to the advertisement ID transmitted from the terminal device 2.

[0046] Next, the information processing device 1 acquires the result of the advertising effectiveness of the multiple advertisements included in the distribution candidates that were determined to be the distribution targets and distributed (step S8). The information processing device 1 acquires the result of the advertising effectiveness of the multiple advertisements included in the distribution candidates that were distributed every time the multiple advertisements included in the distribution candidates are distributed to the terminal device 2 in step S8.

[0047] For example, the results of the advertisement results acquired in step S8 include the presence or absence of searches corresponding to each of the multiple advertisements included in the delivery candidates to be delivered, the presence or absence of selections corresponding to each of the multiple advertisements included in the delivery candidates to be delivered, and the presence or absence of conversions corresponding to each of the multiple advertisements included in the delivery candidates to be delivered. The presence or absence of searches, selections, and conversions refers to, for example, the presence or absence of searches, selections, and conversions during a predetermined period after the delivery candidates are delivered, but is not limited to such an example.

[0048] A search corresponding to an advertisement is a search for information on the advertisement target that is the subject of the advertisement, for example, a search using information such as the name of the transaction target, brand name, or company name that is the subject of the advertisement as a search keyword. A selection corresponding to an advertisement is a selection of the advertisement or a selection of content aimed at by the advertisement (for example, web content of the transaction target), etc. A conversion corresponding to an advertisement is a conversion of the advertisement target that is the subject of the advertisement, for example, a product purchase, membership registration, site visit, etc.

[0049] Here, when a delivery candidate in which the specific advertisement is replaced with another advertisement is determined as the first delivery candidate in step S5, the probability of the first delivery candidate being a delivery target may be lower than that of the first delivery candidate including the specific advertisement. This point will be specifically described below.

[0050] When the advertisement request accepted in step S1 is an advertisement request from a first user who does not deliver a specific advertisement, and the delivery candidates determined in step S6 as delivery targets are first delivery candidates, the first delivery candidates do not include the advertisement Ad1.

[0051] Since the advertisement Ad1 is the advertisement with the largest revenue, the first delivery candidate expected revenue of the first delivery candidate that does not include the advertisement Ad1 is smaller than the first delivery candidate expected revenue of the first delivery candidate that includes the advertisement Ad1.

[0052] Therefore, the first delivery candidate that does not include the advertisement Ad1 has a higher probability of having the expected revenue of the first delivery candidate < the expected revenue of the second delivery candidate, compared to the first delivery candidate that includes the advertisement Ad1, and may have a lower probability of being a delivery target than the first delivery candidate that includes the advertisement Ad1.

[0053] In the above example, since the last digit of the user ID is 0-4 or 5-9 to determine whether the ad request is from the first user or the second user, the first delivery candidate that does not include the advertisement Ad1 and the first delivery candidate that does not include the advertisement Ad2 are determined with a substantially 1:1 probability.

[0054] However, the first distribution candidate that does not include the advertisement Ad1 has a lower probability of being a distribution target compared to the first distribution candidate that includes the advertisement Ad1, and the lower the probability, the more difficult it is to properly grasp the advertising effect of the distribution of a specific advertisement, the advertisement Ad1.

[0055] Therefore, it is also possible to compare the first delivery candidate in a state where the specific advertisement Ad1 is not excluded in the determination in step S6 with the second delivery candidate, and if the first delivery candidate is determined to be a delivery target, deliver a delivery candidate in which the specific advertisement in the first delivery candidate is replaced with another advertisement as the first delivery candidate. The first delivery candidate in a state where the specific advertisement Ad1 is not excluded is, for example, a delivery candidate in a state where advertisements Ad1, Ad2, Ad3, and Ad4 are included.

[0056] In this case, since the first distribution candidate includes the advertisement Ad1 at the time of the determination in step S6, the expected revenue of the first distribution candidate does not change between the advertisement request of the first user and the advertisement request of the second user. Therefore, the probability that the first distribution candidate will be distributed does not change between the advertisement request of the first user and the advertisement request of the second user.

[0057] However, in actual distribution, the first distribution candidate that does not include the advertisement Ad1 is distributed as the distribution target, and therefore the actual revenue obtained from such distribution falls short of the expected revenue of the first distribution candidate estimated in step S6, resulting in a loss of profit from the distribution of the distribution candidate.

[0058] Therefore, the information processing device 1 performs a finals simulation process to virtually determine one of the first and second distribution candidates as a distribution target based on the profits estimated in step S2 (step S9).

[0059] In the final simulation process, one of the first and second distribution candidates in which the specific advertisement has not been replaced with another advertisement is virtually determined as a distribution target. For example, when the specific advertisement is advertisement Ad1, the first distribution candidate in which the specific advertisement has not been replaced with another advertisement is a distribution candidate in which advertisements Ad1, Ad2, Ad3, and Ad4 are included.

[0060] In this case, the expected revenue of the first distribution candidate is the same between the first user's advertisement request and the second user's advertisement request. Therefore, the probability that the first distribution candidate is distributed is the same between the first user's advertisement request and the second user's advertisement request. The information processing device 1 stores the result of the final match simulation process as history information.

[0061] Next, the information processing device 1 calculates an index value for the advertising effectiveness of a specific advertisement based on the information of the delivery candidates determined to be delivery targets in step S6, the results of the advertising effectiveness obtained in step S8, and the results of the final match simulation processing in step S9 (step S10).

[0062] First, a case will be described in which the first distribution candidate is determined as a distribution target in the final round in response to the advertisement request of the second user, and a specific advertisement is distributed. When the advertisement request accepted in step S1 is an advertisement request of the second user, and the first distribution candidate is determined as a distribution target in step S7, the information processing device 1 extracts all results of the advertising effectiveness of the specific advertisement in the first distribution candidate from the results of the advertising effectiveness acquired in step S9.

[0063] Then, the information processing device 1 determines an index value related to the result of the advertising effectiveness of the specific advertisement based on the result of the advertising effectiveness of the specific advertisement in the first distribution candidate. Hereinafter, the index value related to the result of the advertising effectiveness of the specific advertisement may be referred to as a specific advertisement index value.

[0064] For example, the information processing device 1 calculates, as the specific advertisement indicator value, one or more of a search rate, a click rate (eg, CTR), a conversion rate (eg, CVR), etc., according to an indicator serving as a target of a specific advertisement.

[0065] Next, a case will be described in which the first distribution candidate is determined as a distribution target in the final match simulation in response to the first user's advertisement request, but the specific advertisement is not distributed. When the advertisement request accepted in step S1 is an advertisement request of the second user and the first distribution candidate is determined as a distribution target in step S9, the information processing device 1 extracts all results of advertising effectiveness by advertisements corresponding to the specific advertisement from the results of advertising effectiveness acquired in step S9. Hereinafter, an advertisement corresponding to a specific advertisement may be referred to as a corresponding advertisement.

[0066] A corresponding advertisement, which is an advertisement that corresponds to a specific advertisement, is an advertisement that has the same rank as the specific advertisement in the first distribution candidate when the first distribution candidate in which the specific advertisement has been replaced with another advertisement in step S5 is determined to be a distribution target in the final round in step S7, for example, in the example shown in FIG. 1, it is advertisement Ad2 with rank 1.

[0067] In addition, when the second distribution candidate is determined to be a distribution target in the final round of step S7, the corresponding advertisement is an advertisement in the second distribution candidate that has the same rank as the specific advertisement, for example, in the example shown in FIG. 1, it is advertisement Ad11 with rank 1.

[0068] Then, the information processing device 1 determines an index value related to the result of the advertising effectiveness of the corresponding advertisement based on the extracted result of the advertising effectiveness of the corresponding advertisement. Hereinafter, the index value related to the result of the advertising effectiveness of the corresponding advertisement may be referred to as a corresponding advertisement index value.

[0069] For example, the information processing device 1 calculates, as the corresponding advertisement indicator value, one or more of a search rate, a click rate (eg, CTR), a conversion rate (eg, CVR), etc., according to an indicator that is a target of a specific advertisement.

[0070] Then, the information processing device 1 calculates the lift of the specific advertisement based on the difference between the specific advertisement index value and the corresponding advertisement index value. For example, the information processing device 1 calculates the lift of the specific advertisement by subtracting the corresponding advertisement index value from the specific advertisement index value.

[0071] The lift of a specific ad is an index indicating how much the index value of a user U who has received a specific ad has increased from the index value of a user U who has not received the specific ad. The lift of a specific ad is an example of the advertising effect of a specific ad.

[0072] For example, when the specific advertisement indicator value and the corresponding advertisement indicator value are search rates, the information processing device 1 calculates the lift of the search rate by subtracting the corresponding advertisement indicator value from the specific advertisement indicator value as the lift of the specific advertisement.

[0073] Furthermore, when the specific advertisement indicator value and the corresponding advertisement indicator value are click rates, the information processing device 1 calculates the lift of the click rate by subtracting the corresponding advertisement indicator value from the specific advertisement indicator value as the lift of the specific advertisement.

[0074] Furthermore, when the specific advertisement indicator value and the corresponding advertisement indicator value are conversion rates, the information processing device 1 calculates the lift of the conversion rate by subtracting the corresponding advertisement indicator value from the specific advertisement indicator value as the lift of the specific advertisement.

[0075] In the above example, the search rate, click rate, conversion rate, etc. are used as index values, but the index values ​​are not limited to such examples, and the number of searches, the number of clicks, the number of conversions, etc. can also be used as index values.

[0076] In this way, when the received advertisement request is an advertisement request of a first user among an advertisement request of a first user who does not deliver a specific advertisement and an advertisement request of a second user who delivers a specific advertisement, the information processing device 1 determines a delivery candidate in which the specific advertisement is replaced with another advertisement as a first delivery candidate, and virtually determines one of the first delivery candidate and the second delivery candidate in which the specific advertisement is not replaced with another advertisement as a delivery target. In this way, the information processing device 1 can create a state in which the probability that the first delivery candidate is determined as a delivery target by simulation does not decrease while suppressing damage to profits, and therefore makes it possible to appropriately grasp the advertising effect of the delivery of the specific advertisement.

[0077] The configuration of an information processing system including the information processing device 1 and terminal device 2 that perform such processing will be described in detail below.

[0078] 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, an information processing system 100 according to an embodiment includes an information processing device 1 and a plurality of terminal devices 2.

[0079] The multiple terminal devices 2 are used by different users U. The terminal devices 2 are, 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, but is not limited to, smart glasses or a smart watch. The user U is a user who receives advertisements from the information processing device 1 or the like.

[0080] The information processing device 1 and the terminal device 2 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.

[0081] 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).

[0082] The terminal device 2 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.

[0083] 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.

[0084] [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 via the network N.

[0085] [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 advertisement information storage unit 21, and an advertisement delivery history storage unit 22.

[0086] 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.

[0087] 4, the user information table stored in the user information storage unit 20 includes information items such as "user ID," "attribute information," and "history information." The "user ID" is an identifier for identifying a user U, and is information assigned to each user U.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 3.2.2. Advertising information storage unit 21 The advertisement information storage unit 21 stores various pieces of information related to advertisements. Fig. 5 is a diagram showing an example of an advertisement information table stored in the advertisement information storage unit 21 of the information processing device 1 according to the embodiment.

[0093] 5, the advertisement information table stored in the advertisement information storage unit 21 includes information items such as "advertisement ID" and "advertisement." The "advertisement ID" is an identifier that identifies an advertisement, and is information attached to the advertisement.

[0094] An "advertisement" is an advertisement associated with an "advertising ID," and is, for example, a banner advertisement, a listing advertisement, a native advertisement, a social media advertisement, a video advertisement, etc., but is not limited to these examples.

[0095] 5, the advertisement information table also includes information associated with the "advertising ID," such as the advertising effect target of the advertisement (e.g., information on the index used to calculate the advertising effect), information on the advertisement distribution period, information on the index unit cost (e.g., CPA (Cost Per Action)), and information on the target attributes which are the attributes of the target user U. Furthermore, the advertisement information storage unit 21 is not limited to the above, and can store various kinds of information according to the purpose.

[0096] [3.2.3. Advertisement distribution history storage unit 22] The advertisement delivery history storage unit 22 stores various information related to the delivery history of advertisements. Fig. 6 is a diagram showing an example of an advertisement delivery history table stored in the advertisement delivery history storage unit 22 of the information processing device 1 according to the embodiment.

[0097] 6, the advertisement delivery history table stored in the advertisement delivery history storage unit 22 includes information items such as "user ID", "delivered advertisement", "index information", and "processing result". The "user ID" is the same as the user ID shown in FIG. 4, and is information on the identifier of the user U to whom the advertisement is delivered.

[0098] The "delivered advertisement" includes, for example, an advertisement delivered to a user U associated with the "user ID" and information indicating the delivery date and time of the advertisement to the user U. The "index information" is information on the above-mentioned indexes related to advertising effectiveness, for example, information on indexes related to searches, information on indexes related to clicks, information on indexes related to conversions, or information on indexes related to engagement.

[0099] The search-related index includes information indicating the content of a search performed by a user U associated with a "user ID" and information on the date and time of the search (search date and time) by the user U. The content of the search is, for example, information on search keywords related to the advertisement target.

[0100] The click-related index includes information indicating the content of the click performed by the user U associated with the "user ID" and information on the date and time (click date and time) of the click by the user U. The click content is, for example, information on the advertisement selected by the user U or the content targeted by the advertisement.

[0101] The conversion-related index 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 performed by the user U (conversion date and time).

[0102] 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.

[0103] Furthermore, for example, the index regarding engagement 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).

[0104] 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.

[0105] The "processing result" is the result of processing performed in response to an advertisement request from the terminal device 2 of user U associated with the "user ID", and includes information indicating the result of the final match processing by the processing unit 12 and information indicating the result of the final match simulation processing by the processing unit 12.

[0106] The advertisement delivery history storage unit 22 also stores attribute information and history information of the user U at the time the advertisement was delivered, as well as advertisement display environment information of the advertisement at the time it was delivered to the user U. As described above, the advertisement display environment information is information such as the category of the website to which the advertisement is delivered, the type of application of the terminal device 2 to which the advertisement is delivered, and the display position of the advertisement.

[0107] [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.

[0108] 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).

[0109] 3, the processing unit 12 has an acquisition unit 30, a reception unit 31, an estimation unit 32, a determination unit 33, a judgment unit 34, a distribution unit 35, a simulation unit 36, and a calculation unit 37, 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 any other configuration as long as it performs the information processing described below.

[0110] [3.3.1. Acquisition part 30] The acquisition unit 30 acquires various pieces of information from an external information processing device or a terminal device 2 via the communication unit 10, and stores the acquired information in the storage unit 11.

[0111] For example, the acquisition unit 30 acquires user information, which is information about the user U, from an external information processing device or terminal device 2 or the like via the communication unit 10, and adds the acquired user information to a user information table in the user information storage unit 20. In addition, the acquisition unit 30 acquires advertising information, which is information about advertisements, from an external information processing device or terminal device 2 or the like via the communication unit 10, and adds the acquired advertising information to an advertising information table in the advertising information storage unit 21.

[0112] In addition, the acquisition unit 30 acquires a result of the advertising effectiveness regarding the first distribution candidate, for example, from an external information providing device, etc., when the first distribution candidate is distributed by the distribution unit 35. In addition, the acquisition unit 30 acquires a result of the advertising effectiveness regarding the second distribution candidate, for example, from an external information providing device, etc., when the second distribution candidate is distributed by the distribution unit 35. The acquisition unit 30 stores the acquired information on the result of the advertising effectiveness in the advertising distribution history storage unit 22, for example, as index information, etc.

[0113] Each of the results of the advertising effectiveness for the first distribution candidate and the results of the advertising effectiveness for the second distribution candidate is information on an indicator of advertising effectiveness. The indicator of advertising effectiveness is, for example, a search, a click, or a conversion.

[0114] The information on the indicator of advertising effectiveness is, for example, information indicating the presence or absence of a search, or information indicating a search rate, etc., if the indicator of advertising effectiveness is a click, the information on the indicator of advertising effectiveness is, for example, information indicating the presence or absence of a click, or information indicating a click rate, etc., if the indicator of advertising effectiveness is a conversion, the information on the indicator of advertising effectiveness is, for example, information indicating the presence or absence of a conversion, or information indicating a conversion rate, etc.

[0115] 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 about 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. For example, the acquisition unit 30 acquires user information about the user U of the terminal device 2 that has transmitted the advertisement request.

[0116] Furthermore, the acquiring unit 30 acquires information relating to the distribution history of the advertisement from the advertisement distribution history storage unit 22, etc. The information relating to the distribution history of the advertisement is some or all of the information on the distributed advertisement, the index information, the processing result, and so on.

[0117] In addition, when the determination unit 34 determines that the second delivery target is the delivery target in response to the advertisement request from the first user and the simulation unit 36 ​​virtually selects the first delivery candidate as the delivery target, the acquisition unit 30 acquires the result of the advertising effectiveness regarding the second delivery candidate, and when this is not the case, the acquisition unit 30 may not acquire the result of the advertising effectiveness regarding the second delivery candidate.

[0118] [3.3.2. Reception Unit 31] The reception unit 31 receives various requests and information from the terminal device 2 via the communication unit 10.

[0119] For example, the request received by the reception unit 31 is an advertisement request transmitted from the terminal device 2, but is not limited to this example. Furthermore, when the reception unit 31 receives advertisement information from an advertiser's terminal device or the like, the reception unit 31 stores the received advertisement information in the advertisement information storage unit 21 or the like.

[0120] [3.3.3. Estimation part 32] The estimation unit 32 estimates the revenue from delivery for each of the multiple advertisements in response to the advertisement request received by the reception unit 31. The revenue estimated by the estimation unit 32 is, for example, an expected revenue that is the revenue expected from delivery in response to the advertisement request, and is a value obtained by multiplying the predicted result of the index value of the advertising effectiveness by the index cost. Hereinafter, the revenue estimated by the estimation unit 32 may be referred to as the expected revenue.

[0121] The estimation unit 32 has a prediction model for predicting an index value of the advertising effectiveness based on information of the user U of the terminal device 2 that has sent the advertisement request (e.g., information on the attributes and behavior history of the user U), and predicts the index value of the advertising effectiveness using the prediction model. For example, the estimation unit 32 predicts the index value of the advertising effectiveness based on the information of the user U acquired by the acquisition unit 30.

[0122] The advertising effectiveness index value is a value of an advertising performance index, such as, but not limited to, a predicted search rate, a predicted click rate, a predicted conversion rate, etc. For example, the advertising effectiveness index value may be a predicted engagement rate or other predicted value.

[0123] A search is a search (e.g., a web search) in which information on the target of the advertisement (hereinafter sometimes referred to as the advertising target) is used as a search keyword. Information on the advertising target is, for example, information on a specific trading target (e.g., the name of the trading target) or information on a specific brand or company (e.g., a brand name or company name), but is not limited to such examples. When the advertising effectiveness index is search, the prediction model outputs a predicted value of the search rate as a predicted result of the advertising effectiveness index value.

[0124] A click refers to an advertisement or content targeted by an advertisement being selected (e.g., clicked or tapped) by a user U, and a click-through rate is the probability that an advertisement is selected by a user U for one delivery of the advertisement, which is the so-called CTR. When the indicator of advertising effectiveness is clicks, the prediction model outputs the predicted value of the CTR as the predicted result of the index value of advertising effectiveness.

[0125] A conversion is an indicator of reaching a goal (e.g., a conversion goal), such as, but not limited to, a purchase of an advertised transaction object, use of an advertised transaction object, registration for an advertised membership service, or visit to an advertised site. The transaction object may be, for example, a product or service.

[0126] The conversion rate is the probability that a conversion occurs for one advertisement delivery, and is also known as CVR. When the indicator of advertising effectiveness is conversion, the prediction model outputs the predicted value of CVR as the predicted result of the index value of advertising effectiveness.

[0127] The cost per index is, for example, a cost per click when the index is a click, and is, for example, a cost per acquisition when the index is a search or a conversion, but is not limited to these examples.

[0128] For example, when the index is clicks, the estimation unit 32 estimates the revenue by multiplying the predicted value of the click rate by the cost per click of the advertisement. Also, when the index is search or conversion, the estimation unit 32 estimates the revenue by multiplying the predicted value of the search rate or conversion rate by the cost per acquisition of the advertisement. Note that the estimation of revenue by the estimation unit 32 is not limited to the above-mentioned example.

[0129] [3.3.4. Determination unit 33] The determination unit 33 determines a first delivery candidate and a second delivery candidate, each of which includes one or more advertisements selected from among the plurality of advertisements based on an expected profit, which is the profit estimated by the estimation unit 32. The first delivery candidate and the second delivery candidate include, for example, advertisements having different advertisement formats, but are not limited to this example.

[0130] For example, the determination unit 33 determines a first delivery candidate and a second delivery candidate, each of which includes a plurality of advertisements, based on expected profits. For example, the determination unit 33 determines a first delivery candidate that includes the top m advertisements (m is, for example, an integer equal to or greater than 2) in descending order of expected profits among a plurality of advertisements in a first advertisement format. In addition, the determination unit 33 determines a second delivery candidate that includes the top m advertisements in descending order of expected profits among a plurality of advertisements in a second advertisement format. The first advertisement format is, for example, an advertisement represented by text or an image, and the second advertisement format is, for example, an advertisement represented by a video.

[0131] For example, suppose that multiple advertisements in a first advertising format are arranged in descending order of expected profits as advertisements Ad1, Ad2, Ad3, Ad4, Ad5, etc. Furthermore, suppose that multiple advertisements in a second advertising format are arranged in descending order of expected profits as advertisements Ad11, Ad12, Ad13, Ad14, Ad15, etc. In this case, if m=4, the first distribution candidates include advertisements Ad1, Ad2, Ad3, and Ad4, and also advertisements Ad11, Ad12, Ad13, and Ad14.

[0132] Furthermore, the number of advertisements included in each of the first and second delivery candidates may be 1. The determination unit 33 determines the first and second delivery candidates, each of which includes one advertisement, based on the expected profit.

[0133] In this case, the determination unit 33 determines the advertisement Ad1 having the highest expected profit among the multiple advertisements Ad1, Ad2, Ad3, Ad4, Ad5, ... of the first advertising format as the first distribution candidate advertisement. Also, the determination unit 33 determines the advertisement Ad11 having the highest expected profit among the multiple advertisements Ad11, Ad12, Ad13, Ad14, Ad15, ... of the first advertising format as the second distribution candidate advertisement.

[0134] In addition, when the advertisement request received by the receiving unit 31 is an advertisement request from the first user, the determining unit 33 replaces the advertisement with the advertisement having the next largest expected profit after the advertisement having the smallest expected profit among advertisements other than the specific advertisement in the first distribution candidate as the other advertisement.

[0135] For example, when the first distribution candidates include advertisements Ad1, Ad2, Ad3, and Ad4, the determination unit 33 replaces advertisement Ad4, which is the advertisement with the smallest expected profit among advertisements other than advertisement Ad1, which is a specific advertisement in the first distribution candidates, with advertisement Ad5, which is the advertisement with the second largest expected profit, as the other advertisement.

[0136] Furthermore, when the first distribution candidate includes only the advertisement with the highest expected profit, the determination unit 33 replaces the advertisement with the second highest expected profit after the advertisement with the highest expected profit with another advertisement. For example, when the first distribution candidate includes only the advertisement Ad1, which is a specific advertisement, the determination unit 33 replaces the advertisement Ad2, which is the advertisement with the second highest profit after the advertisement Ad1, with another advertisement.

[0137] It should be noted that, when the advertisement request accepted by the accepting unit 31 is an advertisement request from a second user, the deciding unit 33 does not replace the specific advertisement with another advertisement as described above.

[0138] [3.3.5. Judgment unit 34] The determination unit 34 determines whether the advertisement request accepted by the acceptance unit 31 is an advertisement request of a first user or an advertisement request of a second user.

[0139] For example, based on information of the user U of the terminal device 2 that sent the advertisement request accepted by the receiving unit 31, the determination unit 34 determines whether the user U of the terminal device 2 that sent the advertisement request is a first user or a second user.

[0140] The information of user U is, for example, a user ID, which is an identifier uniquely assigned to user U, and the judgment unit 34 judges a user U whose last digit of the user ID is 0 to 4 to be a first user, and judges a user U whose last digit of the user ID is 5 to 9 to be a second user.

[0141] The method of determining whether the user U is the first user or the second user is not limited to the above example, and may be determined, for example, by a digit other than the last digit of the user ID. The determination unit 34 can also determine whether the user U is the first user or the second user by a specific digit of the MAC address of the terminal device 2 that has transmitted the advertisement request accepted by the acceptance unit 31.

[0142] In addition, the determination unit 34 performs a final round process to determine one of the first and second distribution candidates as a distribution target based on the expected profit estimated by the estimation unit 32.

[0143] For example, the determination unit 34 calculates an expected profit when the first distribution candidate is distributed by the distribution unit 35 as a distribution target, and an expected profit when the second distribution candidate is distributed by the distribution unit 35 as a distribution target.

[0144] The expected revenue when the first delivery candidate is delivered as a delivery target by the delivery unit 35 is the above-mentioned first delivery candidate expected revenue, which is, for example, the total revenue estimated by the estimation unit 32 for multiple advertisements included in the first delivery candidate. For example, if the first delivery candidate includes advertisements Ad1, Ad2, Ad3, and Ad4, the first delivery candidate expected revenue is the total revenue of advertisements Ad1, Ad2, Ad3, and Ad4 estimated by the estimation unit 32. In addition, if the first delivery candidate includes advertisements Ad2, Ad3, Ad4, and Ad5, the first delivery candidate expected revenue is the total revenue of advertisements Ad2, Ad3, Ad4, and Ad5 estimated in step S2.

[0145] In addition, the expected revenue when the second delivery candidate is delivered as a delivery target by the delivery unit 35 is the above-mentioned second delivery candidate expected revenue, which is, for example, the total revenue value estimated by the estimation unit 32 for multiple advertisements included in the second delivery candidate. For example, when the second delivery candidate includes advertisements Ad11, Ad12, Ad13, and Ad14, the second delivery candidate expected revenue is the total revenue value estimated by the estimation unit 32 for advertisements Ad11, Ad12, Ad13, and Ad14.

[0146] The determination unit 34 compares the expected profit of the first distribution candidate with the expected profit of the second distribution candidate, and determines the distribution candidate corresponding to the larger expected profit of the first distribution candidate and the second distribution candidate as the distribution candidate. For example, when the expected profit of the first distribution candidate is larger than the expected profit of the second distribution candidate, the determination unit 34 determines the first distribution candidate as the distribution candidate, and when the expected profit of the second distribution candidate is larger than the expected profit of the first distribution candidate, the determination unit 34 determines the second distribution candidate as the distribution candidate.

[0147] [3.3.6. Distribution Unit 35] The distribution unit 35 distributes the delivery target determined by the determination unit 34. For example, when the delivery candidate determined as the delivery target by the determination unit 34 is a first delivery candidate, the distribution unit 35 distributes a plurality of advertisements included in the first delivery candidate to the delivery destination terminal device 2 via the communication unit 10, and when the delivery candidate determined as the delivery target by the determination unit 34 is a second delivery candidate, the distribution unit 35 distributes a plurality of advertisements included in the second delivery candidate to the delivery destination terminal device 2 via the communication unit 10.

[0148] Note that the delivery of an advertisement included in the delivery candidates is not limited to the transmission of the advertisement itself to the terminal device 2, and may be the transmission of an advertisement ID for acquiring the advertisement to the terminal device 2. In this case, the delivery unit 35 transmits the advertisement corresponding to the advertisement ID transmitted from the terminal device 2 to the terminal device 2 via the communication unit 10.

[0149] [3.3.7. Simulation section 36] The simulation unit 36 ​​virtually determines one of the first and second distribution candidates as a distribution target based on the profits estimated by the estimation unit 32.

[0150] The simulation unit 36 ​​virtually determines, as a delivery target, one of the first delivery candidates and the second delivery candidates in which a specific advertisement has not been replaced with another advertisement, regardless of whether the advertisement request accepted by the accepting unit 31 is an advertisement request of a first user or an advertisement request of a second user, for example.

[0151] In addition, when the advertisement request accepted by the accepting unit 31 is an advertisement request from a first user and a first delivery candidate in which a specific advertisement has been replaced with another advertisement by the determining unit 33 has been delivered by the delivery unit 35, the simulation unit 36 ​​can virtually determine that one of the first delivery candidate and the second delivery candidate in which the specific advertisement has not been replaced with the other advertisement is to be delivered.

[0152] In this case, the simulation unit 36 ​​does not perform a virtual determination of the delivery target when the advertisement request accepted by the accepting unit 31 is an advertisement request of the first user and the second delivery candidate is delivered by the delivery unit 35. This enables the information processing device 1 to reduce the processing load of the simulation unit 36.

[0153] [3.3.8. Calculation unit 37] The calculation unit 37 calculates the advertising effectiveness of a specific advertisement based on the advertising effectiveness result for the first distribution candidate and the advertising effectiveness result for the second distribution candidate acquired by the acquisition unit 30.

[0154] For example, when the advertising request accepted by the accepting unit 31 is an advertising request from the second user and the determination unit 34 determines that the first distribution candidate is the distribution target, the calculation unit 37 extracts all results of the advertising effectiveness of a specific advertisement in the first distribution candidate from the results of the advertising effectiveness acquired by the acquisition unit 30.

[0155] Then, the information processing device 1 determines a specific advertisement indicator value, which is an indicator value related to the result of the advertising effectiveness of the specific advertisement, based on the extraction result of the advertising effectiveness of the specific advertisement in the first distribution candidate.

[0156] For example, the calculation unit 37 calculates, as the specific advertisement indicator value, one or more of a search rate, a click rate (eg, CTR), a conversion rate (eg, CVR), etc., according to an indicator that is a target of a specific advertisement.

[0157] In addition, when the advertising request accepted by the accepting unit 31 is an advertising request from the first user and the simulation unit 36 ​​determines that the first delivery candidate is the delivery target, the calculation unit 37 extracts all the results of the advertising effectiveness of the corresponding advertisement, which is an advertisement corresponding to a specific advertisement, from the results of the advertising effectiveness acquired by the acquisition unit 30.

[0158] When a first distribution candidate in which a specific advertisement has been replaced with another advertisement by the determination unit 33 is determined to be a distribution target in the final round processing by the determination unit 34, the corresponding advertisement is an advertisement that has the same rank as the specific advertisement in the first distribution candidate, for example, advertisement Ad2 with rank 1 in the example shown in FIG. 1.

[0159] In addition, when the second distribution candidate is determined to be a distribution target in the final round processing by the determination unit 34, the corresponding advertisement is an advertisement in the second distribution candidate that has the same rank as the specific advertisement, for example, in the example shown in Figure 1, it is advertisement Ad11 with rank 1.

[0160] Then, the calculation unit 37 determines a corresponding advertisement index value, which is an index value related to the result of the advertising effectiveness of the corresponding advertisement, based on the extraction result of the advertising effectiveness of the extracted corresponding advertisement.

[0161] For example, the calculation unit 37 calculates, as the corresponding advertisement indicator value, one or more of a search rate, a click rate (eg, CTR), a conversion rate (eg, CVR), etc., according to an indicator that is a target of a specific advertisement.

[0162] Then, the calculation unit 37 calculates the lift of the specific advertisement based on the difference between the specific advertisement indicator value and the corresponding advertisement indicator value. For example, the calculation unit 37 calculates the lift of the specific advertisement by subtracting the corresponding advertisement indicator value from the specific advertisement indicator value.

[0163] The lift of a specific ad is an index indicating how much the index value of a user U who has received a specific ad has increased from the index value of a user U who has not received the specific ad. The lift of a specific ad is an example of the advertising effect of a specific ad.

[0164] For example, when the specific advertisement indicator value and the corresponding advertisement indicator value are search rates, the calculation unit 37 calculates the lift of the search rate by subtracting the corresponding advertisement indicator value from the specific advertisement indicator value as the lift of the specific advertisement.

[0165] Furthermore, when the specific advertisement indicator value and the corresponding advertisement indicator value are click rates, the calculation unit 37 calculates the lift of the click rate by subtracting the corresponding advertisement indicator value from the specific advertisement indicator value as the lift of the specific advertisement.

[0166] Furthermore, when the specific advertisement indicator value and the corresponding advertisement indicator value are conversion rates, the calculation unit 37 calculates the lift of the conversion rate by subtracting the corresponding advertisement indicator value from the specific advertisement indicator value as the lift of the specific advertisement.

[0167] In the above example, the search rate, click rate, conversion rate, etc. are used as index values, but the index values ​​are not limited to such examples, and the number of searches, the number of clicks, the number of conversions, etc. can also be used as index values.

[0168] 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. 7 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

[0169] 12, the processing unit 12 of the information processing device 1 determines whether an advertisement request has been received (step S20). If the processing unit 12 determines that an advertisement request has been received (step S20: Yes), the processing unit 12 estimates revenues for multiple advertisements (step S21).

[0170] Then, the processing unit 12 determines a first distribution candidate and a second distribution candidate based on the revenue estimated in step S21 (step S22).Then, the processing unit 12 determines whether the advertisement request determined to have been received in step S20 is an advertisement request of the first user or an advertisement request of the second user (step S23).

[0171] When the processing of step S23 is completed or when it is determined that an advertisement request has not been accepted (step S20: No), the processing unit 12 determines whether the advertisement request that was judged to have been accepted in step S20 is an advertisement request from a second user (step S24).

[0172] When the processing unit 12 determines that the advertisement request determined to have been received in step S20 is an advertisement request from a second user (step S24: Yes), the processing unit 12 determines a delivery candidate in which a specific advertisement in the first delivery candidate is replaced with another advertisement as the first delivery candidate (step S25).

[0173] When the processing of step S25 is completed, or when the processing unit 12 determines that the advertisement request determined to have been received in step S20 is not an advertisement request from the second user (step S24: No), the processing unit 12 performs a final round process to determine one of the first and second delivery candidates as a delivery target based on the revenue estimated in step S21 (step S26).

[0174] Next, the processing unit 12 performs a distribution process to distribute the distribution target determined in step S26 (step S27). The processing unit 12 also performs a finals simulation process based on the profit estimated in step S21 (step S28). Then, the processing unit 12 calculates the lift of a specific advertisement (step S29).

[0175] When the process of step S29 is completed or when it is determined that an advertisement request has not been received (step S20: No), the processing unit 12 determines whether or not the operation end timing has arrived (step S30). 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.

[0176] If the processing unit 12 determines that the operation end time has not arrived (step S30: No), it transitions to step S20, and if the processing unit 12 determines that the operation end time has arrived (step S30: Yes), it terminates the processing shown in FIG. 7.

[0177] 5. Modifications The index values ​​such as the specific advertising index value and the corresponding advertising index value are not limited to the above-mentioned examples, and may be, for example, a brand recognition rate or a viewable impression (vimps) rate.

[0178] A viewable impression refers to an advertisement or content corresponding to the advertisement being displayed in a state in which it is actually viewable by user U (e.g., an advertisement being displayed on user U's terminal device 2 for a preset period of time (e.g., 2 seconds) or more), and a viewable impression rate is the probability that an advertisement or content corresponding to the advertisement is displayed in a state in which it is actually viewable by user U for one delivery of the advertisement.

[0179] Brand recognition is, for example, recognition by a user U of a transaction target that is the subject of advertising, and a brand recognition rate is the probability that a user U recognizes the transaction target that is the subject of advertising through the advertisement.

[0180] In the above example, the specific advertisement is the advertisement with the highest rank (for example, the above-mentioned advertisement Ad1), but is not limited to such an example. For example, when the distribution candidates include multiple advertisements, the specific advertisement may be an advertisement other than the highest-ranked advertisement among the multiple advertisements included in the distribution candidates (for example, the above-mentioned advertisement Ad2, advertisement Ad3, or advertisement Ad4).

[0181] In this case, the corresponding advertisement used in calculating the lift and corresponding to the specific advertisement is an advertisement having the same rank as the specific advertisement before it was replaced in the first distribution candidate in which the specific advertisement was replaced with another advertisement, an advertisement having the same rank as the specific advertisement in the second distribution candidate, etc. For example, when the specific advertisement is the above-mentioned Ad3, the corresponding advertisement is advertisement Ad4 or advertisement Ad13.

[0182] In addition, the corresponding advertisement used to calculate lift and corresponding to a specific advertisement is not limited to an advertisement having the same rank as the specific advertisement, but may be an advertisement having the same rank as the specific advertisement.

[0183] [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. 8. Fig. 8 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] [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.

[0190] 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.

[0191] 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.

[0192] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0193] 8. Effects As described above, the information processing device 1 according to the embodiment includes a reception unit 31 that receives an advertisement request, an estimation unit 32 that estimates a revenue by delivery for each of a plurality of advertisements in response to the advertisement request received by the reception unit 31, a determination unit 33 that determines a first delivery candidate and a second delivery candidate, each of which includes one or more advertisements selected from the plurality of advertisements based on the revenue estimated by the estimation unit 32, a determination unit 34 that determines one of the first delivery candidate and the second delivery candidate as a delivery target based on the revenue estimated by the estimation unit 32, a delivery unit 35 that delivers the delivery target determined by the determination unit 34, and a simulation unit 36 ​​that virtually determines one of the first delivery candidate and the second delivery candidate as a delivery target based on the revenue estimated by the estimation unit 32. When the advertisement request received by the reception unit 31 is an advertisement request of a first user among an advertisement request of a first user that does not deliver a specific advertisement and an advertisement request of a second user that delivers a specific advertisement, the determination unit 33 determines a delivery candidate in which a specific advertisement is replaced with another advertisement as a first delivery candidate. The simulation unit 36 ​​virtually determines, as a delivery target, one of the first and second delivery candidates in which the specific advertisement has not been replaced with another advertisement. This enables the information processing device 1 to appropriately grasp the advertising effect of the delivery of the specific advertisement.

[0194] Furthermore, each of the first and second delivery candidates includes a plurality of advertisements selected from the plurality of advertisements in descending order of revenue estimated by the estimation unit 32, and when the advertisement request accepted by the acceptance unit 31 is an advertisement request from the first user, the determination unit 33 replaces the advertisement with the next largest revenue among the advertisements other than the specific advertisement in the first delivery candidate as the other advertisement. This enables the information processing device 1 to appropriately measure advertising effectiveness.

[0195] Furthermore, each of the first delivery candidate and the second delivery candidate includes one advertisement having the largest revenue estimated by the estimation unit 32 among the multiple advertisements, and when the advertisement request accepted by the acceptance unit 31 is an advertisement request from the first user, the determination unit 33 replaces the advertisement having the second largest revenue after the specific advertisement in the second delivery candidate with another advertisement. This enables the information processing device 1 to appropriately grasp the advertising effect of the delivery of the specific advertisement.

[0196] The information processing device 1 also includes an acquisition unit 30 that acquires a result of advertising effectiveness regarding the first delivery candidate when the first delivery candidate is delivered by the delivery unit 35, and acquires a result of advertising effectiveness regarding the second delivery candidate when the second delivery candidate is delivered by the delivery unit 35, and a calculation unit 37 that calculates advertising effectiveness regarding a specific advertisement based on the result of advertising effectiveness regarding the first delivery candidate and the result of advertising effectiveness regarding the second delivery candidate acquired by the acquisition unit 30. This enables the information processing device 1 to appropriately grasp the advertising effectiveness of the delivery of the specific advertisement.

[0197] Furthermore, the acquisition unit 30 acquires a result of the advertising effectiveness related to the second delivery candidate when the determination unit 34 determines the second delivery candidate as a delivery target in response to the advertisement request of the first user and the simulation unit 36 ​​virtually selects the first delivery candidate as a delivery target, and the calculation unit 37 calculates the advertising effectiveness related to the specific advertisement using the result of the advertising effectiveness related to the second delivery candidate when the determination unit 34 determines the second delivery candidate as a delivery target in response to the advertisement request of the first user and the simulation unit 36 ​​virtually determines the first delivery candidate as a delivery target. This enables the information processing device 1 to appropriately grasp the advertising effectiveness of the delivery of the specific advertisement.

[0198] In addition, the first and second distribution candidates include advertisements having different advertisement formats, which enables the information processing device 1 to appropriately grasp the advertising effectiveness of the distribution of a specific advertisement.

[0199] Furthermore, when the first delivery candidate in which the specific advertisement has been replaced with another advertisement by the determination unit 33 is delivered by the delivery unit 35, the simulation unit 36 ​​virtually determines, as a delivery target, one of the first delivery candidate and the second delivery candidate in which the specific advertisement has not been replaced with another advertisement. This enables the information processing device 1 to appropriately grasp the advertising effect of the delivery of the specific advertisement.

[0200] 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.

[0201] 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]

[0202] 1. Information processing device 2 Terminal Equipment 10. Communications Department 11 Storage section 12 Processing section 20 User information storage unit 21 Advertising information storage unit 22 Advertisement delivery history memory unit 30 Acquisition Department 31 Reception 32 Estimation part 33 Decision Section 34 Judgment section 35 Distribution Department 36 Simulation Department 37 Calculation section 100 Information Processing Systems

Claims

1. A reception unit that receives an advertisement request; an estimation unit that estimates revenue generated by delivery of the advertisement requests received by the reception unit for each of a plurality of advertisements; a determination unit that determines a first distribution candidate and a second distribution candidate, each of which includes one or more advertisements selected from the plurality of advertisements based on the revenue estimated by the estimation unit; a determination unit that determines one of the first and second delivery candidates as a delivery target based on the revenue estimated by the estimation unit; and a distribution unit that distributes the distribution target determined by the determination unit; a simulation unit that virtually determines one of the first distribution candidate and the second distribution candidate as a distribution target based on the revenue estimated by the estimation unit, The determination unit is when the advertisement request accepted by the accepting unit is an advertisement request of the first user among an advertisement request of a first user that does not deliver a specific advertisement and an advertisement request of a second user that delivers the specific advertisement, determining, as the first delivery candidate, a delivery candidate in which the specific advertisement is replaced with another advertisement; The simulation unit is One of the first and second delivery candidates in which the specific advertisement has not been replaced with the other advertisement is virtually determined as the delivery target.

23. An information processing apparatus comprising:

2. Each of the first distribution candidate and the second distribution candidate is a plurality of advertisements selected from the plurality of advertisements in descending order of the revenues estimated by the estimation unit, The determination unit is When the advertisement request received by the reception unit is an advertisement request from the first user, the advertisement having the second largest profit after the advertisement having the smallest profit among advertisements other than the specific advertisement in the first distribution candidate is replaced as the other advertisement.

2. The information processing apparatus according to claim 1,

3. Each of the first distribution candidate and the second distribution candidate is Among the plurality of advertisements, one advertisement whose revenue estimated by the estimation unit is the largest is included, The determination unit is When the advertisement request received by the reception unit is an advertisement request from the first user, an advertisement in the second distribution candidate that has the second largest profit after the specific advertisement is replaced as the other advertisement.

2. The information processing apparatus according to claim 1,

4. an acquisition unit that acquires a result of advertising effectiveness regarding the first delivery candidate when the first delivery candidate is delivered by the delivery unit, and acquires a result of advertising effectiveness regarding the second delivery candidate when the second delivery candidate is delivered by the delivery unit; a calculation unit that calculates an advertising effectiveness for the specific advertisement based on the advertising effectiveness result for the first delivery candidate and the advertising effectiveness result for the second delivery candidate acquired by the acquisition unit.

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

5. The acquisition unit is When the determination unit determines that the second delivery candidate is a delivery target in response to the advertisement request of the first user and the simulation unit virtually determines that the first delivery candidate is a delivery target, acquires a result of advertising effectiveness regarding the second delivery candidate, The calculation unit is When the determination unit determines that the second delivery candidate is a delivery target in response to the advertisement request of the first user and the simulation unit virtually selects the first delivery candidate as a delivery target, the result of the advertising effectiveness regarding the second delivery candidate is used to calculate the advertising effectiveness regarding the specific advertisement.

5. The information processing apparatus according to claim 4.

6. The first distribution candidate and the second distribution candidate Contains ads with different ad formats 4. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

7. The simulation unit is When the first distribution candidate in which the specific advertisement has been replaced with the other advertisement by the determination unit is distributed by the distribution unit, one of the first distribution candidate in which the specific advertisement has not been replaced with the other advertisement and the second distribution candidate is virtually determined as the distribution target.

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

8. 1. A computer-implemented information processing method, comprising: an acceptance step for accepting an advertisement request; an estimation step of estimating revenues from delivery of the advertisement requests received by the receiving step for each of the plurality of advertisements; a determination step of determining a first delivery candidate and a second delivery candidate, each of which includes one or more advertisements selected from the plurality of advertisements based on the revenue estimated by the estimation step; a determination step of determining one of the first and second delivery candidates as a delivery target based on the revenue estimated in the estimation step; a distribution step of distributing the distribution target determined by the determination step; a simulation step of virtually determining one of the first distribution candidate and the second distribution candidate as a distribution target based on the revenue estimated by the estimation step, The determining step includes: determining, when the advertisement request accepted by the accepting step is an advertisement request of the first user among an advertisement request of a first user that does not deliver a specific advertisement and an advertisement request of a second user that delivers the specific advertisement, a delivery candidate in which the specific advertisement is replaced with another advertisement as the first delivery candidate; The simulation step includes: One of the first and second delivery candidates in which the specific advertisement has not been replaced with the other advertisement is virtually determined as the delivery target.

23. An information processing method comprising:

9. An acceptance procedure for accepting ad requests; an estimation step of estimating revenue generated by delivery of the advertisement request received by the receiving step for each of a plurality of advertisements; a determination step of determining a first delivery candidate and a second delivery candidate, each of which includes one or more advertisements selected from the plurality of advertisements based on the revenue estimated by the estimation step; a determination step of determining one of the first delivery candidate and the second delivery candidate as a delivery target based on the revenue estimated by the estimation step; a distribution procedure for distributing the distribution target determined by the determination procedure; a simulation step of virtually determining one of the first distribution candidate and the second distribution candidate as a distribution target based on the revenue estimated by the estimation step; The determination procedure includes: determining, when the advertisement request accepted by the accepting step is an advertisement request of the first user among an advertisement request of a first user that does not deliver a specific advertisement and an advertisement request of a second user that delivers the specific advertisement, a delivery candidate in which the specific advertisement is replaced with another advertisement as the first delivery candidate; The simulation procedure includes: One of the first and second delivery candidates in which the specific advertisement has not been replaced with the other advertisement is virtually determined as the delivery target.

2. An information processing program comprising:

Images