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

Abstract

To provide an information processing device, information processing method, and information processing program, capable of obtaining an appropriate advertisement effect in a plurality of phases in a funnel.SOLUTION: An information processing device comprises an acquisition unit, a selection unit, and a distribution unit. The acquisition unit acquires selection condition information of a plurality of indexes on an advertisement effect obtained by distribution of advertisements included in an advertisement group. The selection unit selects an index to be optimized from among the plurality of indexes on the basis of the selection condition information acquired by the acquisition unit. The distribution unit distributes an advertisement using the index selected by the selection unit.SELECTED DRAWING: Figure 3

Description

[Technical field]

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

[0002] In recent years, with the rapid spread of the Internet, advertisement distribution via the Internet has become popular. As an example of such advertisement distribution, a technology has been proposed that maximizes advertising profits by controlling the bid amount for an advertisement space based on past bidding records (for example, see Patent Document 1).

[0003] In automated bidding for this type of advertising space, the bid amount is determined by multiplying the acquisition cost set by the advertiser, such as a threshold CPA (Cost Per Action), by a predicted CVR (Conversion Rate). [Prior art documents] [Patent documents]

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

[0005] However, the above-mentioned conventional techniques have room for improvement in terms of obtaining appropriate advertising effectiveness in multiple phases in the funnel from when a user becomes aware of an advertised product or service to when he or she purchases it.

[0006] The present application has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that are capable of obtaining appropriate advertising effectiveness in multiple phases in a funnel. [Means for solving the problem]

[0007] The information processing device of the present disclosure includes an acquisition unit, a selection unit, and a distribution unit. The acquisition unit acquires information on selection conditions of a plurality of indices related to advertising effectiveness by distribution of advertisements included in an advertisement group. The selection unit selects an index to be optimized from the plurality of indices based on the information on the selection conditions acquired by the acquisition unit. The distribution unit distributes advertisements using the index selected by the selection unit. Effect of the Invention

[0008] According to one aspect of the embodiment, it is possible to obtain an appropriate advertising effect in multiple phases in the funnel. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a user information table stored in the user information storage unit of the information processing device according to the embodiment. [Diagram 5] FIG. 5 is a diagram illustrating an example of an advertiser information table stored in the advertiser information storage unit of the information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a campaign information table stored in the campaign information storage unit of the information processing device according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of an advertisement provision history table stored in the advertisement provision history storage unit of the information processing device according to the embodiment. [Figure 8] FIG. 8 is a diagram for explaining an example of a method for selecting an index based on information on the selection order by the selection unit of the information processing device according to the embodiment. [Figure 9]FIG. 9 is a diagram for explaining an example of a method for selecting an index based on information of a user's condition by the selection unit of the information processing device according to the embodiment. [Figure 10] FIG. 10 is a diagram for explaining another example of a method for selecting an index based on information on the selection order by the selection unit of the information processing device according to the embodiment. [Figure 11] FIG. 11 is a diagram for explaining yet another example of a method for selecting an index based on information on the selection order by the selection unit of the information processing device according to the embodiment. [Figure 12] FIG. 12 is a flowchart illustrating an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 13] FIG. 13 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

[0012] The information processing device 1 selects an index to be optimized from among multiple indexes based on information on selection conditions for multiple indexes related to the advertising effectiveness of the delivery of advertisements included in the advertisement group, and delivers the advertisements included in the advertisement group using the selected index.

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

[0014] The format type of each advertisement may be, for example, but is not limited to, a banner advertisement, a listing advertisement, a native advertisement, a social media advertisement, or a video advertisement. The delivery type of each advertisement may be, for example, but is not limited to, a broad delivery advertisement, an interest targeting advertisement, or a retargeting advertisement.

[0015] Types of indicators related to advertising effectiveness include, for example, conversion indicators and engagement indicators. Conversion is an indicator related to reaching a goal (e.g., a conversion goal). Such types of conversion include, for example, purchasing an advertised transaction object, using an advertised transaction object, registering for an advertised membership service, or visiting an advertised site, but are not limited to these examples. An example of an object of transaction is a product or service.

[0016] In addition, the type of conversion may be signing up for an advertised email distribution, registering an account for an advertised online service, requesting materials that are advertised, visiting a advertised physical store, etc., or it may be some other action.

[0017] Engagement is an indicator of how actively a person is involved with the advertising target, and types of engagement include, for example, shares, likes, posts, etc. on SNS (Social Network Service), but are not limited to such examples.

[0018] What kind of user behavior is considered as conversion or engagement can be set arbitrarily. For example, what kind of user behavior is considered as conversion or engagement for each advertisement is set individually by an administrator of the information processing device 1, an advertiser O, or the like. Note that conversion may be a concept including engagement.

[0019] First, the information processing device 1 receives the advertising campaign information transmitted from the terminal device 3, and accepts the received advertising campaign information (step S1).

[0020] The advertiser O can operate the terminal device 3 and input information about one or more advertising campaigns into the terminal device 3. The terminal device 3 transmits information including the information about the one or more advertising campaigns input by the advertiser O to the information processing device 1 as advertising campaign information.

[0021] In the example shown in FIG. 1, the advertising campaign information includes information on the account of the advertiser O, information on the advertising campaign Camp1, information on the advertising campaign Camp2, cost-per-acquisition information, and selection condition information.

[0022] The information on advertising campaign Camp1 includes information on a group of advertisements including advertisements A, B, and C, and the information on advertising campaign Camp2 includes information on a group of advertisements including advertisements D, E, and F. In the following, when advertising campaigns Camp1 and Camp2 are referred to without being individually distinguished, they may be referred to as advertising campaign Camp.

[0023] The information of the advertising campaign Camp includes, in addition to information about the group of advertisements, information about the attributes of the target users (e.g., age, gender, region, interests, consumption behavior, etc.), information indicating the amount of the budget for advertising delivery, information about the delivery period, etc., but is not limited to these examples.

[0024] The information indicating the amount of the budget for advertisement delivery includes, for example, information indicating the amount of the budget for each predetermined period TB (e.g., one day, three days, or one week), but is not limited to such an example and may include, for example, information indicating the amount of the budget for each period set by advertiser O.

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

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

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

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

[0029] The acquisition cost information includes information indicating the acquisition cost for each index. The acquisition cost for each index is, for example, a threshold CPA (Cost Per Acquisition) and is set by the advertiser O. Such an acquisition cost is used when determining a bid amount in automatic bidding for advertisement delivery. Note that the acquisition cost of an advertisement may be determined by the information processing device 1 or the like based on the past advertisement delivery performance.

[0030] The selection condition information includes information on selection conditions of a plurality of indicators related to the advertising effectiveness of the advertisements included in the advertisements of the advertising campaign Camp indicated by the advertising campaign information. The information on the selection conditions of the plurality of indicators may be, but is not limited to, information on the selection order of the plurality of indicators or information on the conditions of the user U who is the selection target of each of the plurality of indicators.

[0031] First, a case will be described where the information on the selection conditions for the multiple indices is information on the selection order of the multiple indices. The information on the selection order of the multiple indices is, for example, information on the indices selected for each predetermined period, and for example, different indices are set for each of three predetermined periods: an early distribution period, a distribution growth period, and a distribution maturity period.

[0032] In the example shown in Fig. 1, the multiple indicators for which selection conditions are set are site visits, membership registration, and product purchases. In addition, the indicator in the early distribution stage is site visits, the indicator in the distribution growth stage is membership registration, and the indicator in the distribution maturity stage is product purchases.

[0033] A site visit is, for example, a visit to a specific site by the user U, a membership registration is, for example, a membership registration for a specific service by the user U, and a product purchase is, for example, a purchase of a specific product by the user U. Each of a site visit, a membership registration, and a product purchase is an example of a conversion.

[0034] When the indicator is site visits, the advertising effectiveness is expressed by the number of site visits, which is the number of users U who visited a specific site, or the number of times a specific site was visited by users U. When the indicator is membership registrations, the advertising effectiveness is expressed by the number of membership registrations, which is the number of membership registrations for a specific service by users U. When the indicator is product purchases, the advertising effectiveness is expressed by the number of product purchases, which is the number of purchases of a specific product by users U.

[0035] In the example shown in Fig. 1, the selection conditions for a plurality of indices are shown as a selection order for a plurality of indices, which is the order of site visit, membership registration, and product purchase. The selection condition information also includes information indicating a condition for changing the indices to be selected.

[0036] The information indicating the conditions for changing the indicator to be selected is, for example, a condition that the number of site visits is greater than or equal to a threshold value as a condition for changing the indicator from site visit to member registration, and a condition that the number of member registrations is greater than or equal to a threshold value as a condition for changing the indicator from member registration to product purchase, but is not limited to such examples.

[0037] The information indicating the condition for changing the index to be selected is information indicating the condition for selecting the index to be selected, and the information indicating the condition for selecting the index to be selected is not limited to the above-mentioned example. For example, in the information indicating the condition for selecting the index to be selected, if the number of site visits is less than a threshold, the index to be selected may be site visits, if the number of site visits is equal to or greater than the threshold and the number of registered members is less than a threshold, the index to be selected may be member registrations, and if the number of site visits is equal to or greater than the threshold and the number of registered members is equal to or greater than the threshold, the index to be selected may be product purchases.

[0038] Next, a case will be described where the information on the selection conditions of the multiple indices is information on the conditions of a user U who is a selection target of each of the multiple indices. The information on the user who is a selection target of each of the multiple indices is, for example, information on a phase in a funnel, and such phases are, for example, a latent layer for the advertising target, a semi-latent layer for the advertising target, an active layer for the advertising target, etc., but are not limited to such examples.

[0039] The latent layer is, for example, users U who are not aware of the advertising target. The semi-latent layer is, for example, users U who have an interest or concern in the advertising target but are not at the stage of considering purchasing the advertising target. The latent layer is, for example, users U who are at the stage of considering purchasing the advertising target.

[0040] The phases are not limited to the above examples, and for example, a part of the quasi-latent layer may be included in the latent layer and the rest of the quasi-latent layer may be included in the latent layer without providing a quasi-latent layer. Also, the funnel may have four or more phases.

[0041] Next, the information processing device 1 accepts an advertisement request transmitted from the terminal device 2 (step S2) and performs bidding processing for advertisement delivery (step S3). In step S3, the information processing device 1 calculates a predicted value of a specific behavior probability based on information of the user U of the terminal device 2 that transmitted the advertisement request (e.g., information on the attributes of the user U and information on the behavior history of the user U). The specific behavior is, for example, conversion or engagement. In the following, the user U of the terminal device 2 that transmitted the advertisement request may be referred to as an advertisement delivery target user.

[0042] When the indicator for which the selection condition is set is an indicator related to conversion, the specific behavior probability is, for example, a conversion rate, and the predicted value of the specific behavior probability is, for example, a CVR predicted value. When the indicator for which the selection condition is set is an indicator related to engagement, the specific behavior probability is, for example, an engagement rate, and the predicted value of the specific behavior probability is, for example, an engagement rate predicted value.

[0043] The information processing device 1, for example, determines the value obtained by multiplying the cost per acquisition indicated in the advertising campaign information by the predicted value of the specific behavior probability as the bid amount for each advertisement, and performs bidding processing for each advertisement using the determined bid amount for each advertisement.

[0044] The information processing apparatus 1 determines an advertisement to be distributed to the terminal device 2 that has sent an advertisement request through a bidding process, and distributes the determined advertisement to the terminal device 2 that has sent the advertisement request (step S4). The processes in steps S2 to S4 are repeatedly performed, and each advertisement included in each advertising campaign Camp is distributed.

[0045] In step S4 and the like, the information processing apparatus 1 stores the advertisement distribution history to the user U in an internal storage unit or the like. Further, the information processing apparatus 1 collects information on the history of specific actions performed by the user U, and stores the collected information on the history of specific actions in an internal storage unit or the like.

[0046] Here, the selection of a plurality of indicators will be specifically described. The information processing apparatus 1 selects an indicator to be optimized from among a plurality of indicators based on the selection condition information included in the selection condition information included in the advertising campaign information (step S5).

[0047] For example, assume that a plurality of indicators whose selection order is defined in the selection condition information are site visit, membership registration, and product purchase, and the selection order of the plurality of indicators indicated in the selection condition information is in the order of site visit, membership registration, and product purchase. Also, assume that the indicator change conditions indicated in the selection condition information include a first change condition for changing the indicator from site visit to membership registration and a second change condition for changing the indicator from membership registration to product purchase.

[0048] The first change condition is, for example, a condition that the number of site visits is equal to or greater than a first threshold Th1, or a condition that after the increase rate of the number of site visits per a predetermined period becomes equal to or greater than a second threshold Th2 and then becomes equal to or less than a third threshold Th3 (<Th2). These thresholds Th1, Th2, and Th3 are set by the advertiser O, but may be set or changed by the information processing apparatus 1 based on advertising campaign information (for example, information on the amount of the budget, information on the distribution period, etc.).

[0049] Further, the second change condition is, for example, a condition that the number of member registrations has reached or exceeded a fourth threshold Th4, or a condition that the growth rate of the number of member registrations per predetermined period has reached or exceeded a fifth threshold Th5 and then has become equal to or less than a sixth threshold Th6 (<Th5). These thresholds Th4, Th5, and Th6 are set by the advertiser O, but may be set or changed by the information processing apparatus 1 based on advertising campaign information (such as information on the amount of the budget and information on the distribution period).

[0050] For example, as shown in FIG. 1(a), the information processing apparatus 1 selects site visits as an optimization target index at the initial stage of distribution until the first change condition is satisfied. In this case, the information processing apparatus 1 performs a bidding process for advertisement distribution in step S3 using a predicted value of the site visit probability, which is the probability of site visits.

[0051] For example, the information processing apparatus 1 calculates a predicted value of the site visit probability for each advertisement using a prediction model or the like based on information such as information on advertisement distribution target users. The information processing apparatus 1 performs a process of determining the bid amount for each advertisement based on the calculated predicted value of the site visit probability and the acquisition unit price set for the advertisement. For example, for an advertisement with an acquisition unit price of 10 yen for site visits and a site visit probability of 0.05, the bid amount is 0.5 yen.

[0052] Then, the information processing apparatus 1 performs a bidding process using the determined bid amount for each advertisement, and if there is an advertisement that becomes a distribution target by the bidding process among the plurality of advertisements included in the advertising campaigns Camp1 and Camp2, the information processing apparatus 1 distributes such an advertisement.

[0053] Since the information processing apparatus 1 performs the bidding process so that site visits are optimized at the initial stage of distribution until the first change condition is satisfied, for example, the recognition of the product targeted by the advertisement can be enhanced.

[0054] For example, when the first change condition is satisfied, the information processing device 1 determines that the distribution has transitioned to a distribution growth period, which is the next phase after the initial distribution phase, and selects member registration as an optimization target index, as shown in (b) of Fig. 1. In this case, the information processing device 1 performs bidding processing for advertisement distribution in step S3 using a predicted value of the member registration probability, which is the probability of member registration.

[0055] For example, the information processing device 1 calculates a predicted value of the membership registration probability for each advertisement using a prediction model or the like based on information on users to whom advertisements are delivered. The information processing device 1 performs a process of determining the bid amount for each advertisement based on the calculated predicted value of the membership registration probability and the acquisition cost set for the advertisement. For example, if the acquisition cost for membership registration is 100 yen for an advertisement and the membership registration probability is 0.02, the bid amount is 2 yen.

[0056] Then, the information processing device 1 performs bidding processing using the determined bid amount for each advertisement, and if any advertisement among the multiple advertisements included in the advertisement campaigns Camp1 and Camp2 becomes a distribution target through the bidding processing, distributes the advertisement.

[0057] During the distribution growth period after the first change condition is satisfied, the information processing device 1 performs bidding processing to optimize member registrations, thereby, for example, increasing the user U's interest in the product that is the subject of advertisement.

[0058] For example, when the second change condition is satisfied after the transition to the delivery growth period, the information processing device 1 determines that the transition has been made to the delivery maturity period, which is the next phase of the delivery growth period, and selects product purchase as the optimization target index, as shown in (c) of Fig. 1. In this case, the information processing device 1 performs bidding processing for advertisement delivery in step S3 using a predicted value of the product purchase probability, which is the probability of product purchase.

[0059] For example, the information processing device 1 calculates a predicted value of the product purchase probability for each advertisement using a prediction model or the like based on information on the advertisement delivery target users. The information processing device 1 performs a process of determining the bid amount for each advertisement based on the calculated predicted value of the product purchase probability and the acquisition cost set for the advertisement. For example, if the advertisement has a product purchase cost of 500 yen and the product purchase probability is 0.01, the bid amount is 5 yen.

[0060] Then, the information processing device 1 performs bidding processing using the determined bid amount for each advertisement, and if any advertisement among the multiple advertisements included in the advertisement campaigns Camp1 and Camp2 becomes a distribution target through the bidding processing, distributes the advertisement.

[0061] In the mature delivery period after the second change condition is satisfied, the information processing device 1 performs bidding processing so as to optimize product purchases, and can thereby promote purchases of the advertised product by the user U.

[0062] In this way, the information processing device 1 can deliver advertisements using indicators that are optimized according to the overall funnel phase of the user U who is the advertising target, thereby achieving appropriate advertising effectiveness at multiple phases in the funnel.

[0063] In addition, the multiple indicators for which the conditions of user U are specified in the selection condition information are site visits, membership registration, and product purchases, and the conditions of user U indicated in the selection condition information are a latent layer for site visits, a semi-latent layer for membership registration, and an active layer for product purchases.

[0064] In this case, the information processing device 1 determines whether the advertisement delivery target user, who is the user U to whom the advertisement is delivered, is a latent layer, a quasi-latent layer, or an apparent layer. For example, the information processing device 1 determines whether the advertisement delivery target user is a latent layer, a quasi-latent layer, or an apparent layer based on the advertisement delivery target user, using an estimation model that uses information of the user U (e.g., attributes of the user U and information on the behavior history of the user U, etc.) as a feature (input) and estimates whether the user U is a latent layer, a quasi-latent layer, or an apparent layer. The estimation model is generated, for example, using learning information that includes information of the user U and information indicating whether the user U is a latent layer, a quasi-latent layer, or an apparent layer for each user U.

[0065] Then, when the target users for advertisement delivery are in the latent demographic, the information processing device 1 performs bidding processing for advertisement delivery in step S3 using a predicted value of site visit probability, which is the probability of site visit. Also, when the target users for advertisement delivery are in the quasi-latent demographic, the information processing device 1 performs bidding processing for advertisement delivery in step S3 using a predicted value of member registration probability, which is the probability of member registration. Also, when the target users for advertisement delivery are in the latent demographic, the information processing device 1 performs bidding processing for advertisement delivery in step S3 using a predicted value of product purchase probability, which is the probability of product purchase.

[0066] In this way, the information processing device 1 can deliver advertisements using indicators that are optimized according to the phase of each user in the funnel related to the advertising target, thereby making it possible to obtain appropriate advertising effectiveness at multiple phases in the funnel.

[0067] Furthermore, the information processing device 1 can calculate a predicted value of the specific behavior probability by using information on an index other than the index selected as the index to be optimized among the multiple indexes as a feature amount of the prediction model.

[0068] For example, assume that the multiple indicators indicated in the selection condition information are site visits, membership registration, and product purchases, and the indicator selected as the target indicator for optimization is product purchases. In this case, the information processing device 1 calculates a predicted value of the product purchase probability using a prediction model that uses one or more pieces of information on site visits and membership registrations, and information on users to whom advertisements are delivered as features.

[0069] The site visit information is, for example, information on the time elapsed since the site visit of the ad delivery target user, and the member registration probability information is, for example, information on the time elapsed since the member registration of the ad delivery target user. The information processing device 1 performs bidding processing for ad delivery in step S3 using the calculated predicted value of the product purchase probability.

[0070] In addition, the advertiser O can include in the advertising campaign information selection condition information that is set to exclude some of the multiple indicators from the indicators that are candidates for optimization. For example, when the multiple indicators indicated in the selection condition information are site visits, membership registrations, and product purchases, the advertiser O can set the candidate indicators for optimization to site visits and product purchases, and exclude membership registrations from the candidate indicators for optimization.

[0071] In this case, when product purchase is selected as the target of optimization, the information processing device 1 calculates a predicted value of the product purchase probability using a prediction model whose features are one or more of site visit information and member registration information, and information of the ad delivery target user, etc. The information processing device 1 performs bidding processing for ad delivery in step S3 using the calculated predicted value of the product purchase probability.

[0072] In this way, since membership registration can be excluded from the candidate indicators to be optimized, advertiser O can obtain appropriate advertising effectiveness at multiple phases in the funnel, even if, for example, there is a site where a product can be purchased without membership registration in addition to or instead of a site where a product can be purchased with membership registration.

[0073] Note that the above-mentioned site visits are not limited to visits to one site, and the information processing device 1 can increment the number of site visits, for example, when the user U visits any of two or more sites.

[0074] In this way, the information processing device 1 selects an index to be optimized from among multiple indexes based on information on selection conditions for multiple indexes related to the advertising effectiveness of the advertisements delivered in the advertisement group, and delivers the advertisements using the selected index. This allows the information processing device 1 to obtain appropriate advertising effectiveness in multiple phases in the funnel.

[0075] The configuration of an information processing system including an information processing device 1 that performs such processing, a plurality of terminal devices 2, and a terminal device 3 will be described in detail below.

[0076] 2. Configuration of the Information Processing System 2 is a diagram showing an example of a configuration of an information processing system according to an embodiment. As shown in FIG. 2, the information processing system 100 according to the embodiment includes an information processing device 1, a plurality of terminal devices 2, and a plurality of terminal devices 3.

[0077] The multiple terminal devices 2 are used by different users U. The multiple terminal devices 3 are used by different advertisers O. Each of the terminal devices 2 and 3 is, for example, a notebook PC (Personal Computer), a desktop PC, a smartphone, a tablet PC, or a wearable device. The wearable device is, for example, smart glasses or a smart watch, but is not limited to such examples. The user U is a user who receives advertisements provided from an information processing device 1 or the like.

[0078] The information processing device 1, the terminal device 2, and the terminal device 3 are connected to each other so as to be able to communicate with each other by wire or wirelessly via a network N. Note that the information processing system 100 shown in FIG. 2 may include a plurality of information processing devices 1 and the like.

[0079] 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).

[0080] The terminal device 2 and the terminal device 3 can connect to the network N via short-range wireless communication such as a mobile communication network, Bluetooth (registered trademark), or a wireless LAN (Local Area Network), and communicate with the information processing device 1.

[0081] 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.

[0082] [3.1. Communication unit 10] The communication unit 10 is realized by, for example, a communication module or a NIC (Network Interface Card). The communication unit 10 is connected to a network N by wire or wirelessly, and transmits and receives information to and from various other devices. For example, the communication unit 10 transmits and receives information to and from the terminal device 2 and the terminal device 3 via the network N.

[0083] [3.2. Storage section 11] The storage unit 11 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 11 has a user information storage unit 20, an advertiser information storage unit 21, a campaign information storage unit 22, and an advertisement provision history storage unit 23.

[0084] 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.

[0085] 4, the user information table stored in the user information storage unit 20 includes information items such as "User ID (Identifier)," "Attribute Information," and "History Information." The "User ID" is an identifier for identifying a user U, and is information assigned to each user U.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] [3.2.2. Advertiser information storage unit 21] The advertiser information storage unit 21 stores various information related to the advertiser O. Fig. 5 is a diagram showing an example of an advertiser information table stored in the advertiser information storage unit 21 of the information processing device 1 according to the embodiment.

[0091] 5, the advertiser information table stored in the advertiser information storage unit 21 includes information items such as "advertiser ID," "account," "campaign ID," "index information," and "selection condition information." The "advertiser ID" is an identifier that identifies the advertiser O, and is information assigned to each advertiser O.

[0092] "Account" is information on the account of the advertiser O associated with the "Advertiser ID", and is assigned to each advertiser O. Note that two or more accounts may be assigned to each advertiser O.

[0093] The "Campaign ID" is an identifier for identifying an advertising campaign Camp associated with an "Account" and is information assigned to each advertising campaign Camp. The advertiser information storage unit 21 is not limited to the above and can store various information according to the purpose.

[0094] The "index information" is information on a plurality of indexes related to the advertising effectiveness of the delivery of the advertisements included in the group of advertisements of the advertising campaign Camp associated with the account, information on the acquisition cost of the index, etc. The acquisition cost information is, for example, information on the threshold CPA, but is not limited to such an example.

[0095] "Selection condition information" is selection condition information associated with an "advertiser ID" or an "account." The selection condition information includes, for example, information on selection conditions of a plurality of indicators related to the advertising effectiveness of delivery of advertisements included in an advertisement group of one or more advertising campaigns Camp associated with an account. The information on the selection conditions of the plurality of indicators is, for example, information on the selection order of the plurality of indicators, or information on the conditions of a user U who is the selection target for each of the plurality of indicators, but is not limited to such examples.

[0096] 3.2.3. Campaign information storage unit 22 The campaign information storage unit 22 stores various information related to the advertising campaign Camp received from the terminal device 3. Fig. 6 is a diagram showing an example of a campaign information table stored in the campaign information storage unit 22 of the information processing device 1 according to the embodiment.

[0097] In the example shown in Fig. 6, the campaign information table stored in the campaign information storage unit 22 includes information items such as "Campaign ID" and "Advertisement". The "Campaign ID", like the campaign ID shown in Fig. 5, is an identifier for identifying an advertising campaign Camp, and is information assigned to each advertising campaign Camp.

[0098] An "advertisement" is an advertisement included in an advertising campaign Camp associated with a "campaign ID", and may be, for example, a banner advertisement, a listing advertisement, a native advertisement, a social media advertisement, a video advertisement, etc., but is not limited to such examples.

[0099] 6, the campaign information table also includes information on the distribution period of advertisements included in the advertising campaign Camp associated with the "campaign ID," and information on target attributes that are attributes of the target user U. In addition, the campaign information storage unit 22 is not limited to the above, and can store various types of information according to the purpose.

[0100] [3.2.4. Advertisement provision history storage unit 23] The advertisement provision history storage unit 23 stores various information related to the distribution history of advertisements. Fig. 7 is a diagram showing an example of an advertisement provision history table stored in the advertisement provision history storage unit 23 of the information processing device 1 according to the embodiment.

[0101] 7, the advertisement provision history table stored in the advertisement provision history storage unit 23 includes information items such as "user ID", "provided advertisement", and "index information". The "user ID" is the same as the user ID shown in FIG. 4, and is information of the identifier of the user U to whom the advertisement is provided.

[0102] The "provided advertisement" includes, for example, the advertising ID of the advertisement provided (delivered) to the user U associated with the "user ID", and information indicating the date and time the advertisement was provided 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 conversion or information on indexes related to engagement. The indexes related to conversion include information indicating the content of the conversion performed by the user U associated with the "user ID", and information on the date and time of the conversion by the user U (conversion date and time).

[0103] 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.

[0104] 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).

[0105] 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.

[0106] The advertisement provision history storage unit 23 also stores attribute information and history information of the user U at the time the advertisement was provided, as well as advertisement display environment information of the advertisement when it was provided to the user U. As described above, the advertisement display environment information is information such as the category of the website on which the advertisement is provided, the type of application of the terminal device 2 on which the advertisement is provided, and the display position of the advertisement.

[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, a selection unit 32, a delivery unit 33, a determination unit 34, and a provision unit 35, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 3, and may be other configurations as long as they perform the information processing described below.

[0110] [3.3.1. Acquisition part 30] The acquisition unit 30 acquires various pieces of information from an external information processing device, the terminal device 2, the terminal device 3, or the like via the communication unit 10, and stores the acquired information in the storage unit 11.

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

[0112] Furthermore, the acquisition unit 30 acquires various types of information from the storage unit 11. For example, the acquisition unit 30 acquires user information, which is information on the user U, from the user information storage unit 20 or the like. The user information acquired by the acquisition unit 30 includes, for example, a part or all of at least one of the above-mentioned attribute information and history information.

[0113] In addition, the acquisition unit 30 acquires advertiser information, which is information about the advertiser O, from the advertiser information storage unit 21 or the like, and acquires information about the advertising campaign Camp from the campaign information storage unit 22.

[0114] For example, the acquisition unit 30 acquires, as part of the advertiser information, selection condition information that is information on selection conditions of a plurality of indexes related to the advertising effectiveness of the delivery of advertisements included in the advertisement group. The selection condition information acquired by the acquisition unit 30 is information on selection conditions the settings of which are accepted by the acceptance unit 31 described later, but may also be information on selection conditions determined by the determination unit 34 described later.

[0115] The information on the selection conditions of the multiple indices is information on the selection order of the multiple indices, or information on the conditions of a user U who is to be selected for each of the multiple indices. For example, the acquisition unit 30 acquires information on the selection order of the multiple indices as the selection condition information. Also, the acquisition unit 30 acquires information on a user who is to be selected for each of the multiple indices as the selection condition information. As described above, each of the multiple indices is, for example, an index related to conversion or an index related to engagement.

[0116] Furthermore, the acquisition unit 30 acquires information on the advertisement provision history from the advertisement provision history storage unit 23. The information on the advertisement provision history acquired by the acquisition unit 30 includes, for example, the above-mentioned information on the provided advertisements and index information.

[0117] [3.3.2. Reception Unit 31] The reception unit 31 receives various requests and information from the terminal device 2 and the terminal device 3 via the communication unit 10 .

[0118] For example, the request accepted by the accepting unit 31 is an advertisement request transmitted from the terminal device 2, but is not limited to such an example. In addition, the accepting unit 31 accepts advertisement campaign information transmitted from the terminal device 3 to the information processing device 1.

[0119] The advertising campaign information includes selection condition information, and the reception unit 31 receives the advertising campaign information to receive the setting of the above-mentioned selection condition from the advertiser O of the advertisement group. The reception unit 31 can also receive the setting of the above-mentioned selection condition from the operator of the information processing device 1, etc.

[0120] When the receiving unit 31 receives advertiser-related information, it stores the received advertiser-related information in the advertiser information storage unit 21, etc. When the receiving unit 31 receives advertising campaign information, it stores information included in the received advertising campaign information in the advertiser information storage unit 21, the campaign information storage unit 22, etc. Note that the selection condition information may be included in the advertiser-related information instead of the advertising campaign information.

[0121] [3.3.3. Selection unit 32] The selection unit 32 performs various selections. For example, the selection unit 32 selects an index to be optimized from among a plurality of indexes based on selection condition information, which is information on the selection conditions acquired by the acquisition unit 30. The selection condition information is information on the selection order of the plurality of indexes, information on the conditions of the user U to be selected for each of the plurality of indexes, and the like.

[0122] When the selection condition information includes information on the selection order of multiple indicators, the selection unit 32 can select an optimization target from among the multiple indicators based on the selection order information included in the selection condition information acquired by the acquisition unit 30.

[0123] The information on the selection order includes, for example, information indicating conditions for changing the index to be selected or information indicating conditions for the selection period of each index. First, the information indicating the conditions for changing the index to be selected will be described. FIG. 8 is a diagram for explaining an example of a method for selecting an index based on the selection order information by the selection unit 32 of the information processing apparatus 1 according to the embodiment.

[0124] In the example shown in FIG. 8, the plurality of indexes are site visit, membership registration, and product purchase, and the selection order of these indexes is in the order of site visit, membership registration, and product purchase. In this case, the conditions for changing the index to be selected include, for example, a first change condition for changing the index from site visit to membership registration and a second change condition for changing the index from membership registration to product purchase.

[0125] The first change condition is, for example, a condition that the number of site visits is equal to or greater than a first threshold Th1, or a condition that the increase rate of the number of site visits per a predetermined period becomes equal to or greater than a second threshold Th2 and then becomes equal to or less than a third threshold Th3 (<Th2). These thresholds Th1, Th2, Th3 are set by the advertiser O, but may be set or changed by the information processing apparatus 1 based on advertising campaign information (for example, information on the amount of budget, information on the distribution period, etc.).

[0126] Also, the second change condition is, for example, a condition that the number of membership registrations is equal to or greater than a fourth threshold Th4, or a condition that the increase rate of the number of membership registrations per a predetermined period becomes equal to or greater than a fifth threshold Th5 and then becomes equal to or less than a sixth threshold Th6 (<Th5). These thresholds Th4, Th5, Th6 are set by the advertiser O, but may be set or changed by the information processing apparatus 1 based on advertising campaign information (for example, information on the amount of budget, information on the distribution period, etc.).

[0127] The selection unit 32 determines the number of site visits, the number of member registrations, the number of product purchases, etc., based on the information on the advertisement provision history acquired by the acquisition unit 30. Then, the selection unit 32 selects site visits as an optimization target index in the initial stage of distribution until the first change condition is satisfied. As a result, in the initial stage of distribution until the first change condition is satisfied, the bidding process is performed in the distribution unit 33 so as to optimize site visits, thereby increasing awareness of the product that is the target of advertising.

[0128] Furthermore, when the first change condition is satisfied, the selection unit 32 determines that the distribution has transitioned to a distribution growth period, which is the next phase after the initial distribution phase, and selects member registration as an optimization target index. As a result, in the distribution growth period in which the first change condition is satisfied, the distribution unit 33 performs bidding processing so as to optimize member registration, and therefore, for example, it is possible to increase the interest of the user U in the product that is the target of advertising.

[0129] Furthermore, when the second change condition is satisfied after the transition to the delivery growth period, the selection unit 32 determines that the transition has been made to the delivery maturity period, which is the next phase of the delivery growth period, and selects product purchase as the optimization target index. As a result, in the delivery maturity period in which the second change condition is satisfied, the bidding process is performed in the delivery unit 33 so that product purchase is optimized, and it is possible to promote, for example, purchases by the user U of the product that is the target of advertisement.

[0130] In this way, the selection unit 32 can change the index to be selected as the index to be optimized from among multiple indexes based on the selection order information acquired by the acquisition unit 30 and information on the history of advertising effectiveness due to the delivery of advertisements included in the group of advertisements indicated in the advertising campaign information.

[0131] Note that the information indicating the conditions for changing the target indicator is the information indicating the conditions for selecting the target indicator, and the information indicating the conditions for selecting the target indicator is not limited to the above-described example. For example, in the information indicating the conditions for selecting the target indicator, if the number of site visits is less than the threshold value, the target indicator is site visit; if the number of site visits is greater than or equal to the threshold value and the number of member registrations is less than the threshold value, the target indicator is member registration; and if the number of site visits is greater than or equal to the threshold value and the number of member registrations is greater than or equal to the threshold value, the target indicator may be product purchase.

[0132] Next, an explanation will be given regarding the condition for applying the selected indicator being the condition for the selection period of each indicator. The condition for the selection period of each indicator is, for example, the condition for the period based on the time point t0 when the distribution of the advertisement indicated by the advertisement campaign information starts. When a plurality of indicators are site visit, member registration, and product purchase, for example, the first period T1 (t0 ≤ t < t1) is set as the selection period for site visit, the second period T2 (t1 ≤ t < t2) is set as the selection period for member registration, and the third period T3 (t2 ≤ t < t3) is set as the selection period for product purchase. Note that t0 < t1 < t2 < t3.

[0133] Next, an explanation will be given regarding the case where the selection condition information includes information on the conditions of the user U for each of the plurality of indicators to be selected. In this case, the selection unit 32 selects the indicator to be optimized from among the plurality of indicators based on the information on the conditions of the user U included in the selection condition information acquired by the acquisition unit 30.

[0134] FIG. 9 is a diagram for explaining an example of a method for selecting an indicator based on information on the conditions of the user U by the selection unit 32 of the information processing apparatus 1 according to the embodiment. In the example shown in FIG. 9, the plurality of indicators in which the conditions of the user U are defined in the selection condition information are site visit, member registration, and product purchase, and the conditions of the user U indicated by the selection condition information are the potential layer for site visit, the semi-potential layer for member registration, and the actual layer for product purchase.

[0135] In this case, the selection unit 32 determines whether the advertisement delivery target user, who is the user U to whom the advertisement is delivered, is a latent layer, a quasi-latent layer, or an apparent layer. For example, the selection unit 32 determines whether the advertisement delivery target user is a latent layer, a quasi-latent layer, or an apparent layer based on the advertisement delivery target user, using an estimation model that uses information of the user U (e.g., attributes of the user U and information on the behavior history of the user U, etc.) as a feature (input) and estimates whether the user U is a latent layer, a quasi-latent layer, or an apparent layer. The estimation model is generated, for example, using learning information that includes information of the user U and information indicating whether the user U is a latent layer, a quasi-latent layer, or an apparent layer for each user U.

[0136] If the target users of the advertisement delivery are in the latent demographic, the selection unit 32 selects site visits as the index to be optimized. If the target users of the advertisement delivery are in the semi-latent demographic, the selection unit 32 selects membership registration as the index to be optimized. If the target users of the advertisement delivery are in the active demographic, the selection unit 32 selects product purchase as the index to be optimized. In this way, the selection unit 32 can select the index to be optimized according to the phase of each user in the funnel of the advertisement target.

[0137] In this way, the selection unit 32 can select an index to be optimized from among multiple indexes based on the information on the selection conditions acquired by the acquisition unit 30 and the information on the user U to whom the advertisement is to be provided. This allows the information processing device 1 to use an index to be optimized according to the phase of each user U in the funnel related to the advertising target.

[0138] In the example shown in Fig. 9, the conditions of user U indicated by the selection condition information are latent for site visits, semi-latent for membership registration, and explicit for product purchases, but are not limited to such an example. For example, user U may be divided into two layers (for example, latent and explicit) instead of three layers, or user U may be divided into four layers.

[0139] The above-mentioned site visit may be a visit to one of a plurality of sites. Fig. 10 is a diagram for explaining another example of a method for selecting an index based on information on the selection order by the selection unit 32 of the information processing device 1 according to the embodiment. In the example shown in Fig. 10, either a visit to site A or a visit to site B is treated as a site visit.

[0140] As described above, the advertiser O can also include in the advertising campaign information selection condition information in which a setting is made to exclude some of the multiple indexes from the indexes that are candidates for optimization. Fig. 11 is a diagram for explaining yet another example of the method for selecting indexes based on information on the selection order by the selection unit 32 of the information processing device 1 according to the embodiment.

[0141] 11, when the multiple indices indicated in the selection condition information are site visits, membership registration, and product purchases, the advertiser O can select site visits and product purchases as candidates for the indices to be optimized, and can exclude membership registration from the candidates for the indices to be optimized. In this case, when product purchases are selected as the target for optimization, the selection unit 32 selects either site visits or product purchases as the indices to be optimized, and does not select membership registration as the indices to be optimized.

[0142] The advertisements included in the multiple advertising campaigns included in the advertising campaign information are set to start delivery at the same timing, but are not limited to this example. For example, the selection unit 32 can select an advertisement or an advertising campaign to be delivered from among the multiple advertisements included in the multiple advertising campaigns included in the advertising campaign information, based on selection condition information including information indicating the conditions for delivery.

[0143] The conditions for the target of delivery are, for example, conditions that associate the index to be optimized with the advertising campaign or advertisement to be delivered. For example, the conditions for the target of delivery are a condition that the target of delivery is advertising campaign Camp1 (see FIG. 6) when the index to be optimized is site visits, and a condition that the target of delivery is advertising campaign Camp2 (see FIG. 6) when the index to be optimized is membership registration or product purchases.

[0144] In this case, when the selection unit 32 selects site visits as an indicator to be optimized, it selects advertisements A, B, and C included in the advertisement group of advertising campaign Camp1 as targets for delivery, and does not select advertisements E, F, and G included in the advertisement group of advertising campaign Camp2 as targets for delivery.

[0145] In addition, when the selection unit 32 selects membership registration or product purchase as the indicator to be optimized, it does not select advertisements A, B, and C included in the advertisement group of advertising campaign Camp1 as the delivery target, but selects advertisements E, F, and G included in the advertisement group of advertising campaign Camp2 as the delivery target.

[0146] The selection unit 32 can also select the delivery target for each advertisement instead of for each advertising campaign Camp. In this case, the conditions for the delivery target are, for example, a condition that the delivery target is advertisements A and D (see FIG. 6) when the index to be optimized is site visits, a condition that the delivery target is advertisements B and E (see FIG. 6) when the index to be optimized is membership registration, and a condition that the delivery target is advertisements C and F (see FIG. 6) when the index to be optimized is product purchases.

[0147] In this case, when the selection unit 32 selects site visits as the index to be optimized, it selects advertisements A and D as the delivery targets, and does not select advertisements B, C, E, and F as the delivery targets. When the selection unit 32 selects member registration as the index to be optimized, it selects advertisements B and E as the delivery targets, and does not select advertisements A, C, D, and F as the delivery targets. When the selection unit 32 selects product purchases as the index to be optimized, it selects advertisements C and F as the delivery targets, and does not select advertisements A, B, E, and F as the delivery targets.

[0148] [3.3.4. Distribution Unit 33] The distribution unit 33 distributes an advertisement when an advertisement request transmitted from the terminal device 2 is accepted by the acceptance unit 31. For example, when an advertisement request transmitted from the terminal device 2 is accepted by the acceptance unit 31, the distribution unit 33 performs a bidding process and distributes an advertisement selected by the bidding process to the terminal device 2 that is the advertisement request source.

[0149] The distribution unit 33 distributes advertisements using, for example, an index selected as an optimization target index, which is an index to be optimized, by the selection unit 32. For example, the distribution unit 33 calculates a predicted value of a specific behavior probability corresponding to the index selected as the optimization target index by the selection unit 32, based on information (for example, attribute information, behavior history information, etc.) of an advertisement distribution target user who is a user U of the terminal device 2 that has transmitted an advertisement request.

[0150] For example, when the index selected as the optimization target index by the selection unit 32 is a site visit, the specific behavior probability corresponding to the index selected as the optimization target index is the site visit probability. In this case, the delivery unit 33 calculates the predicted value of the site visit probability as the predicted value of the specific behavior probability, for example, by using a prediction model that predicts the site visit probability.

[0151] Furthermore, when the index selected as the optimization target index by the selection unit 32 is member registration, the specific behavior probability corresponding to the index selected as the optimization target index is the member registration probability. In this case, the distribution unit 33 calculates the predicted value of the member registration probability as the predicted value of the specific behavior probability, for example, by using a prediction model that predicts the member registration probability.

[0152] Furthermore, when the index selected as the optimization target index by the selection unit 32 is a product purchase, the specific behavior probability corresponding to the index selected as the optimization target index is a product purchase probability. In this case, the delivery unit 33 calculates a predicted value of the product purchase probability as a predicted value of the product purchase probability, for example, by using a prediction model that predicts the product purchase probability.

[0153] The distribution unit 33, for example, determines a value obtained by multiplying the cost per acquisition indicated in the advertising campaign information by the predicted value of the specific behavior probability as the bid amount for each advertisement, and performs bidding processing for each advertisement using the determined bid amount for each advertisement. The distribution unit 33 determines an advertisement to be distributed to the terminal device 2 that transmitted the advertisement request through the bidding processing, and distributes the determined advertisement to the terminal device 2 that transmitted the advertisement request.

[0154] The cost per acquisition indicated in the advertising campaign information is, for example, the cost per acquisition set for site visits when the index selected as the optimization target index is site visits, the cost per acquisition set for membership registration when the index selected as the optimization target index is membership registration, and the cost per acquisition indicated in the advertising campaign information is the cost per acquisition set for product purchases when the index selected as the optimization target index is product purchases.

[0155] In addition, the distribution unit 33 can also use information on indices other than the indices selected by the selection unit 32 as features in a prediction model that calculates predicted values ​​for the indices selected by the selection unit 32 as optimization target indices.

[0156] For example, assume that the multiple indicators indicated by the selection condition information are site visits, membership registration, and product purchases, and the indicator selected as the target indicator for optimization is product purchases. In this case, the distribution unit 33 calculates a predicted value of the product purchase probability using a prediction model that uses one or more pieces of information on site visits and membership registrations, and information on users to whom advertisements are distributed as features.

[0157] The site visit information is, for example, information on the time elapsed since the site visit of the ad delivery target user, and the member registration probability information is, for example, information on the time elapsed since the member registration of the ad delivery target user. The delivery unit 33 performs bidding processing for ad delivery using the calculated predicted value of the product purchase probability.

[0158] In this way, since membership registration can be excluded from the candidate indicators to be optimized, advertiser O can obtain appropriate advertising effectiveness at multiple phases in the funnel, even if, for example, there is a site where a product can be purchased without membership registration in addition to or instead of a site where a product can be purchased with membership registration.

[0159] In addition, the prediction model inputs information such as information on user U and information on target attributes as features and outputs a CVR predicted value, but is not limited to this example and may be, for example, a prediction model of a target attribute.

[0160] In addition, the bidding process may be an automatic bidding process called a first price auction, in which the highest bidder wins, or an automatic bidding process called a second price action, in which the second highest bidder wins. In addition, the bidding process may be an automatic bidding process other than a second price action or first price auction.

[0161] [3.3.5. Decision Unit 34] The determination unit 34 makes various decisions. For example, the determination unit 34 determines the selection conditions for a plurality of indexes. For example, the determination unit 34 can determine the selection conditions for a plurality of indexes based on the track record of the number of specific actions or the probability of specific actions for each index since the start of distribution of the advertisement indicated in the advertising campaign information. The number of specific actions is, for example, the number of site visits, the number of member registrations, the number of product purchases, etc.

[0162] For example, the determination unit 34 can input the actual number of specific behaviors or the probability of a specific behavior for each indicator as a feature, and determine the selection conditions for multiple indicators using a prediction model that outputs the selection conditions for multiple indicators.

[0163] Furthermore, the determination unit 34 can determine the selection conditions for the multiple indicators based on the content (e.g., format type, delivery type, etc.) of each advertisement indicated in the advertising campaign information. For example, the determination unit 34 can input the content (e.g., format type, delivery type, etc.) of each advertisement indicated in the advertising campaign information as a feature amount, and determine the selection conditions for the multiple indicators using a prediction model that outputs the selection conditions for the multiple indicators.

[0164] [3.3.6.Providing Department 35] The providing unit 35 provides various information to the user U and the advertiser O. For example, the providing unit 35 transmits information indicating the selection conditions of the multiple indexes determined by the determining unit 34 to the terminal device 3, thereby providing the information indicating the selection conditions of the multiple indexes to the advertiser O.

[0165] 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. 12 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

[0166] 12, the processing unit 12 of the information processing device 1 determines whether or not the advertising campaign information has been received (Step S20). If the processing unit 12 determines that the advertising campaign information has been received (Step S20: Yes), the processing unit 12 stores the received advertising campaign information (Step S21).

[0167] When the processing of step S21 is completed, or when it is determined that the advertising campaign information has not been accepted (step S20: No), the processing unit 12 determines whether the advertisement distribution period for the advertising campaign that was determined to have been accepted in step S20 has started (step S22).

[0168] If the processing unit 12 determines that the advertisement distribution period has started (step S22: Yes), it acquires selection condition information, etc. from the memory unit 11 (step S23), and selects an index to be optimized based on the acquired selection condition information, etc. (step S24).

[0169] When the processing of step S24 is completed or when it is determined that the advertisement distribution period has not started (step S22: No), the processing unit 12 determines whether or not an advertisement request has been accepted (step S25). When it is determined that an advertisement request has been accepted (step S25: Yes), the processing unit 12 performs distribution processing based on bidding processing using the index selected in step S24 (step S26).

[0170] When the process of step S26 is completed or when it is determined that the advertisement request has not been received (step S25: No), the processing unit 12 determines whether or not the operation end timing has arrived (step S27). 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.

[0171] If the processing unit 12 determines that the operation end time has not arrived (step S27: No), it transitions to step S20, and if it determines that the operation end time has arrived (step S27: Yes), it terminates the processing shown in FIG. 12.

[0172] 5. Modifications In the above example, the cost per acquisition is set for each index, but the cost per acquisition may be set for each advertisement. In addition, when the advertising campaign information includes information on a correction value for each advertisement, the selection unit 32 can correct the cost per acquisition for each index with the correction value.

[0173] In addition, the condition for changing the indicator indicated in the selection condition information is not limited to the number of specific behaviors, but may be, for example, a condition on the cost required for advertisement delivery, or a combination of the number of specific behaviors and the cost required for advertisement delivery.

[0174] Also, in the above example, the conditions for user U are conditions for user U's phase in the funnel, but the classification of user U is not limited to such an example and may be, for example, classified using multiple classification methods, in which case user U's conditions are classified using multiple classification methods.

[0175] In the above example, one index is selected at the same time as an index to be optimized, but the present invention is not limited to this example, and two or more indexes may be selected at the same time as an index to be optimized. In this case, the advertising campaign information includes information indicating a selection ratio for each period, and the selection unit 32 can select an index based on the selection ratio. For example, when the multiple indexes are site visits, membership registration, and product purchases, the selection ratio is represented by the selection probability of site visits, the selection probability of membership registration, and the selection probability of product purchases.

[0176] In this case, the selection ratio may be, for example, in the early stage of distribution, the selection probability of visiting the site > the selection probability of registering as a member > the selection probability of purchasing a product; in the growth stage of distribution, the selection probability of visiting the site < the selection probability of registering as a member > the selection probability of purchasing a product; and in the mature stage of distribution, the selection probability of visiting the site < the selection probability of registering as a member < the selection probability of purchasing a product, but is not limited to these examples.

[0177] [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. 13, for example. Fig. 13 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, an 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] [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.

[0184] 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.

[0185] 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.

[0186] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0187] 8. Effects As described above, the information processing device 1 according to the embodiment includes an acquisition unit 30, a selection unit 32, and a distribution unit 33. The acquisition unit 30 acquires information on selection conditions for a plurality of indices related to the advertising effectiveness of the distribution of advertisements included in an advertisement group. The selection unit 32 selects an index to be optimized from the plurality of indices based on the information on the selection conditions acquired by the acquisition unit 30. The distribution unit 33 distributes advertisements using the index selected by the selection unit 32. This allows the information processing device 1 to obtain appropriate advertising effectiveness in a plurality of phases in the funnel.

[0188] Moreover, the information processing device 1 includes a reception unit 31 that receives settings of selection conditions, and the acquisition unit 30 acquires information on the selection conditions whose settings are received by the reception unit 31. This enables the information processing device 1 to obtain appropriate advertising effects in multiple phases in the funnel.

[0189] Furthermore, the receiving unit 31 receives settings of selection conditions from the advertiser O of the advertisement group. This enables the information processing device 1 to easily support obtaining appropriate advertising effects in a plurality of phases in the funnel.

[0190] Moreover, the acquiring unit 30 acquires information on the selection order of a plurality of indexes as information on the selection condition, which enables the information processing device 1 to obtain an appropriate advertising effect in a plurality of phases in the funnel.

[0191] Furthermore, the selection unit 32 changes the index to be selected as an index to be optimized from among the multiple indexes based on the information on the selection order acquired by the acquisition unit 30 and the information on the history of the advertising effectiveness due to the delivery of the advertisements included in the advertisement group. This enables the information processing device 1 to obtain appropriate advertising effectiveness in multiple phases in the funnel.

[0192] Furthermore, the acquisition unit 30 acquires information on the user U who is to be selected for each of the multiple indices as information on selection conditions, and the selection unit 32 selects an index to be optimized from the multiple indices based on the information on the selection conditions acquired by the acquisition unit 30 and the information on the user U to whom the advertisement is to be provided. This enables the information processing device 1 to obtain appropriate advertising effects in multiple phases in the funnel.

[0193] Furthermore, the distribution unit 33 uses, as a feature, information on an index other than the index selected by the selection unit 32 in a prediction model that calculates a predicted value for the index selected by the selection unit 32. This enables the information processing device 1 to obtain an appropriate advertising effect in multiple phases in the funnel.

[0194] Each of the multiple indices is an index related to conversion or an index related to engagement. This allows the information processing device 1 to obtain appropriate advertising effectiveness in multiple phases in the funnel.

[0195] 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.

[0196] 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]

[0197] 1. Information processing device 2,3 Terminal Equipment 10. Communications Department 11 Storage section 12 Processing section 20 User information storage unit 21 Advertiser information storage unit 22 Campaign information storage unit 23 Ad serving history memory unit 30 Acquisition Department 31 Reception 32 Selection section 33 Distribution Department 34 Decision Section 35 Providing Department 100 Information Processing Systems N Network

Claims

1. an acquisition unit that acquires information on selection conditions for a plurality of indexes related to advertising effectiveness by delivery of advertisements included in the advertisement group; a selection unit that selects an index to be optimized from among the plurality of indexes based on the information on the selection condition acquired by the acquisition unit; a distribution unit that distributes the advertisement using the index selected by the selection unit.

23. An information processing apparatus comprising:

2. a reception unit for receiving a setting of the selection condition, The acquisition unit is Acquire information on the selection conditions that have been set and accepted by the acceptance unit.

2. The information processing apparatus according to claim 1,

3. The reception unit is Accepting settings of the selection conditions from the advertisers of the advertisement group 3. The information processing apparatus according to claim 2.

4. The acquisition unit is Information on the selection order of the plurality of indices is obtained as information on the selection condition.

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

5. The selection unit is The index to be selected as the index to be optimized is changed from among the plurality of indexes based on the information on the selection order acquired by the acquisition unit and information on a history of advertising effectiveness due to the delivery of the advertisements included in the advertisement group.

5. The information processing apparatus according to claim 4.

6. The acquisition unit is acquiring information on users who are to be selected for each of the plurality of indexes as information on the selection conditions; The selection unit is An index to be optimized is selected from the plurality of indexes based on the information on the selection condition acquired by the acquisition unit and information on a user to which the advertisement is to be provided.

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

7. The distribution unit is In a prediction model for calculating a predicted value for an index selected by the selection unit, information on an index other than the index selected by the selection unit is used as a feature.

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

8. Each of the plurality of indexes is It is a conversion or engagement metric.

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

9. 1. A computer-implemented information processing method, comprising: An acquisition step of acquiring information on selection conditions for a plurality of indexes related to advertising effectiveness due to delivery of advertisements included in the group of advertisements; a selection step of selecting an index to be optimized from among the plurality of indexes based on the information on the selection condition acquired by the acquisition step; a delivery step of delivering the advertisement using the index selected by the selection step.

23. An information processing method comprising:

10. An acquisition step of acquiring information on selection conditions for a plurality of indexes related to advertising effectiveness due to delivery of advertisements included in the group of advertisements; a selection step of selecting an index to be optimized from among the plurality of indexes based on the information on the selection condition acquired by the acquisition step; a delivery step of delivering the advertisement using the index selected by the selection step.

2. An information processing program comprising:

Images