JP7793435B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

This application relates to an information processing device, an information processing method, and an information processing program.

Advertising distribution via the Internet has traditionally been popular. For example, in traditional advertising distribution, advertising content such as still images, moving images, and text promoting companies, products, etc. are displayed in advertising spaces set up in designated locations on web pages. In traditional advertising distribution, when such advertising content is clicked, the user is redirected to a landing page, such as the advertiser's web page or content introducing the advertising target.

In addition, with conventional advertising delivery, targeted delivery may be used to selectively deliver advertisements that correspond to user information such as user preferences, gender, age, address, and occupation, in order to increase advertising effectiveness.

JP 2010-136332 A

However, in conventional ad delivery, there is room for improvement in the delivery method in order to achieve the desired results through advertising. For example, even if ads corresponding to user information are selectively delivered, if the ads themselves are weak, they often do not lead to access to landing pages, etc.

This application has been made in light of the above, and aims to provide an information processing device, information processing method, and information processing program that can increase the likelihood of achieving predetermined results through advertising.

The information processing device according to the present application has a selection unit, a generation unit, and a provision unit. The selection unit selects multiple advertisements as combination candidates from multiple advertisements corresponding to categories in which the user is interested. The generation unit calculates, for each combination of multiple advertisements selected by the selection unit, a combination evaluation score indicating the likelihood that each advertisement constituting the combination will be selected by the user based on the display mode of the combined advertisements and a predetermined index value indicating the advertising effectiveness of each advertisement, and generates a combination advertisement with the combination that maximizes the calculated combination evaluation score. The provision unit provides the combined advertisement generated by the generation unit to the user.

According to one aspect of the embodiment, it is possible to increase the likelihood that advertising will achieve a desired result.

FIG. 1 is a diagram showing an overview of a method for providing a combined advertisement according to an embodiment. FIG. 2 is a diagram showing an outline (part 1) of a modified example of the method for calculating a combination evaluation score according to the embodiment. FIG. 3 is a diagram showing an outline (part 2) of a modified example of the method for calculating a combination evaluation score according to the embodiment. FIG. 4 is a diagram showing an outline of a method for evaluating a combination effect according to an embodiment. FIG. 5 is a diagram showing an outline of a method for generating a combination effect evaluation model according to an embodiment. FIG. 6 is a diagram showing an outline of a method for determining a charge amount for a combined advertisement according to the embodiment. FIG. 7 is a diagram illustrating an example of the configuration of an information processing apparatus according to the embodiment. FIG. 8 is a diagram illustrating an example of advertisement information according to the embodiment. FIG. 9 is a diagram illustrating an example of bid information according to the embodiment. FIG. 10 is a diagram illustrating an example of information related to a combination evaluation model according to the embodiment. FIG. 11 is a diagram illustrating an example of information related to an interest level assessment model according to the embodiment. FIG. 12 is a diagram illustrating an example of information related to a combination effect evaluation model according to the embodiment. FIG. 13 is a flowchart illustrating an example of a procedure for providing a combined advertisement according to the embodiment. FIG. 14 is a flowchart illustrating an example of a procedure for evaluating a combination effect according to the embodiment. FIG. 15 is a flowchart illustrating an example of a procedure for determining a billing amount according to the embodiment. FIG. 16 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing apparatus according to the embodiment.

Below, detailed explanations are given of modes for implementing the information processing device, information processing method, and information processing program (hereinafter referred to as "embodiments") according to the present application, with reference to the drawings. Note that the information processing device, information processing method, and information processing program according to the present application are not limited to the multiple embodiments described below. Furthermore, the multiple embodiments described below can be combined as appropriate to the extent that the processing content is not contradictory. Furthermore, the same components in the multiple embodiments described below will be assigned the same reference numerals, and redundant explanations will be omitted.

[1. Overview of information processing]
(1-1. Method of providing combined advertisements)
An example of information processing according to an embodiment will be described with reference to FIG. 1. FIG. 1 is a diagram showing an overview of a method for providing a combined advertisement according to an embodiment. Note that FIG. 1 describes an example of information processing in the case where, when a web page related to a predetermined service is provided in response to a request from a user who is a service user, advertising content is displayed in an advertising space provided in a predetermined position on the web page. Note that the information processing according to the embodiment is not limited to the case where the advertising medium is a web page, but can also be applied to the case where the advertising medium is email.

In the example shown in FIG. 1, the information processing system SYS has a user terminal 10 and an information processing device 100. The user terminal 10 and the information processing device 100 are connected to a network N (see FIG. 7, for example) via a wired or wireless connection. The user terminal 10 and the information processing device 100 can communicate with each other via the network N. Note that the example shown in FIG. 1 is not particularly limited, and the information processing system SYS may include more user terminals 10 and information processing devices 100 than those shown in FIG. 1.

The user terminal 10 shown in FIG. 1 is an information processing terminal used by a user U, who is a user of various services provided by the information processing device 100. A typical example of the user terminal 10 is a smartphone, but it may also be implemented as a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), etc. In the example of FIG. 1, a smartphone is shown as the user terminal 10. Note that in the following description, the user terminal 10 may be referred to as the user U. In other words, the user U can be read as the user terminal 10. Note that in the following description, a user of various services provided by the information processing device 100 may be referred to simply as the "user."

The user terminal 10 also has a communication unit for connecting to the network N via a wireless communication network such as LTE (Long Term Evolution), 4G (4th Generation), or 5G (5th Generation: fifth generation mobile communication system), or via short-range wireless communication such as Bluetooth (registered trademark) or wireless LAN (Local Area Network). A user U operates the user terminal 10 having the communication unit to access the information processing device 100 and view information on various services.

The user terminal 10 can also display information for using various services provided by the information processing device 100 using a web browser or application. When the user terminal 10 receives control information from the information processing device 100 to realize information display processing using a web browser or application, the user terminal 10 realizes the display processing in accordance with the received control information.

The information processing device 100 shown in FIG. 1 is an information processing device that provides various services to a user U. The information processing device 100 is typically a server device, but may also be realized by a mainframe, workstation, or the like. When the information processing device 100 is realized by a server device, it may be realized by a single server, or may be realized by a cloud system in which multiple server devices and multiple storage devices operate in cooperation with each other.

The information processing device 100 may also function as a distribution device that distributes control information to user terminals 10 used by users of various services. Here, the control information is written in, for example, a script language such as JavaScript (registered trademark) or a style sheet language such as CSS (Cascading Style Sheets). The application itself distributed from the information processing device 100 may also be considered to be control information.

The various services provided by the information processing device 100 may also include API (Application Programming Interface) services corresponding to various applications, as well as various online services. The various online services may include Q&A services, Internet connections, search services, SNS (Social Networking Services), e-commerce services, electronic payment services, online games, online banking services, online trading services, hotel reservation services, ticket reservation services, video distribution services, music distribution services, news distribution services, map information services, route search services, route guidance services, line information services, operation information services, and weather information services.

The information processing device 100 also functions as a device for distributing advertising content. The information processing device 100 manages advertising content submitted by advertisers and manages information related to advertising bids set by the advertisers. For example, the information processing device 100 displays advertising content submitted by advertisers in advertising spaces provided on web pages of various services provided in response to user requests.

Incidentally, a single piece of advertising content is displayed in an advertising space provided on a webpage. For this reason, even if an advertisement that is unlikely to be selected as a delivery target and has a weak impact on users increases the number of opportunities for exposure to the advertisement, users often do not become interested in the advertisement and do not achieve the desired result, such as access to a landing page. In light of this situation, the information processing device 100 according to the embodiment displays a combination advertisement that combines multiple advertisements in an advertising space, with the aim of increasing the likelihood that the advertisement will achieve the desired result. Below, the information processing according to the embodiment will be described in detail, following the flow that is expected when this information processing is carried out.

For example, the user terminal 10 sends an access request to a specified service to the information processing device 100 in accordance with the operation of the user U (step S1).

When the information processing device 100 receives a request to access a predetermined service from the user terminal 10, it selects multiple combination candidate advertisements from among the multiple advertisements submitted by the advertiser (step S2). For example, the information processing device 100 selects, as combination candidate advertisements, multiple advertisements corresponding to categories for which the interest score, which indicates the degree of interest of user U, who is the advertisement delivery destination (target), is equal to or greater than a predetermined value. For example, the information processing device 100 can obtain the interest score using an interest evaluation model. The interest evaluation model is generated in advance for each predetermined category that is predefined to classify the subjects in which each user, who may be a target, is interested. For example, the interest evaluation model is trained using machine learning to input information about the user (for example, search history (search query)) and output an interest score corresponding to the user.

The information processing device 100 also selects a combination evaluation model from among the multiple combination evaluation models that matches the attributes of the target user U (step S3). Figure 1 shows an example in which "Model MA" is selected as the combination evaluation model that matches the attributes of user U.

The combination evaluation model is a trained model that has learned the correspondence between a predetermined index value indicating the advertising effectiveness of each advertisement and a predetermined index value indicating the advertising effectiveness of a combination advertisement formed by combining each advertisement. The predetermined index value indicating advertising effectiveness can be any index such as CPA (Cost Per Acquisition), CPC (Cost Per Click), CTR (Click Through Rate), number of conversions, CVR (Conversion Rate), or PV (Page View).

For example, the information processing device 100 collects the results of providing combination advertisements for each attribute of the users to whom the advertisements are delivered, and prepares a learning data sample that associates predetermined index values indicating the advertising effectiveness of each advertisement that makes up the combination advertisement with each index value indicating the advertising effectiveness of the combination advertisement. The information processing device 100 then uses the learning data sample to learn a combination evaluation model that inputs, for example, predetermined index values indicating the advertising effectiveness of each advertisement to be delivered, and outputs information on predetermined index values indicating the advertising effectiveness of the combination advertisement resulting from the combination of each advertisement.

In the training process for the combination evaluation model, the information processing device 100 can train the combination evaluation model using any machine learning model, such as a neural network, as the training model. Furthermore, when a neural network is used as the training model, the information processing device 100 performs a training process that adjusts the values of weights (connection coefficients) that are taken into account when scores (values) are propagated between nodes in each layer that make up the neural network. For example, the information processing device 100 uses any method, such as backpropagation, to train the combination evaluation model by performing a process that corrects parameters (connection coefficients) so as to reduce the error between the output from the training model and the correct answer (correct data) corresponding to the input. Furthermore, when using the backpropagation method, the information processing device 100 can correct the parameters (connection coefficients) so as to reduce the error between the output from the training model and the correct answer (correct data) corresponding to the input by performing a training process that minimizes a predetermined loss function.

In addition, the information processing device 100 can learn a combination evaluation model for each user attribute by using learning data samples based on the results of providing combination advertisements for each user attribute. User attributes (user context) indicate attributes such as demographic attributes such as the age and gender of user U, and psychographic attributes such as the interests and preferences of user U.

After obtaining the trained model, the information processing device 100 obtains, for each combination of multiple advertisements selected in step S2, a combination evaluation score indicating the likelihood that the combined advertisement will be selected by user U (step S4). For example, the information processing device 100 inputs the combination of multiple advertisements selected in step S2 into the trained model (model MA) obtained in step S3, thereby obtaining a combination evaluation score output from the trained model.

After obtaining the combination evaluation score, the information processing device 100 generates a combination advertisement using the combination that maximizes the obtained combination evaluation score (step S5). For example, the information processing device 100 generates a combination advertisement by arbitrarily placing each advertisement that constitutes the combination that maximizes the combination evaluation score in a single advertisement space provided on a webpage that corresponds to a specific service requested by user U. Figure 1 shows combination advertisement AD_a, in which advertisement A, advertisement B, and advertisement C are placed in a single advertisement space. Note that the advertisements that make up the combination advertisement do not need to be completely separate, and may overlap at least partially.

After generating the combination advertisement, the information processing device 100 transmits a web page including the combination advertisement to the user terminal 10 and provides it to the user U (step S6).

In this way, by providing users with combination advertisements that combine multiple advertisements, the information processing device 100 can create advertisements with new influence through the combination of advertisements, thereby increasing the likelihood that the advertisement will achieve the desired results.

Furthermore, when selecting multiple advertisements to be combined, the information processing device 100 may select advertisements whose index value indicating advertising effectiveness is less than a predetermined value from multiple advertisements corresponding to categories of interest to the user (e.g., user U) to whom the advertisements are to be delivered. This makes it possible to provide the user with a combination advertisement that includes advertisements that are of interest to the user (target) to whom the advertisements are to be delivered but that are unlikely to be delivered, thereby broadening the scope of influence of the combination advertisement.

In addition, the information processing device 100 may determine any one of the size, position, and display color of the display area to be individually allocated to each advertisement constituting the combination advertisement, depending on the bid amount when a bid corresponding to the combination advertisement is received from an advertiser. For example, the information processing device 100 may change the size of the display area in proportion to the size of the bid amount. For example, the information processing device 100 may display an advertisement in monochrome if the bid amount for the advertisement is less than a certain amount, and may display the advertisement in color if the bid amount for the advertisement is equal to or greater than the certain amount. For example, the information processing device 100 may display, among the advertisements constituting the combination advertisement, an advertisement with a bid amount higher than the other advertisements and exceeding the certain amount in a position in the advertising space with the highest click performance (for example, the upper left when viewed from the front).

In addition, the information processing device 100 may determine the display position of each advertisement in a combined advertisement, taking into account the similarity of the categories corresponding to each advertisement. For example, the information processing device 100 may determine the display position of each advertisement so that advertisements of similar categories are adjacent to each other.

In this way, the information processing device 100 can vary the display mode of combination advertisements.

Furthermore, when a combination advertisement is selected (e.g., clicked or tapped), the information processing device 100 may hold a display lottery with a probability based on the interest score of the category corresponding to each advertisement that constitutes the combination advertisement, and provide a webpage corresponding to the winning advertisement. For example, when user U clicks on combination advertisement AD_a, the information processing device 100 holds a display lottery for advertisements A, B, and C that constitute combination advertisement AD_a. Then, if advertisement A wins the display lottery, the information processing device 100 provides user U with a landing page, content, etc. that is pre-linked to advertisement A.

In addition, when providing a web page for an advertisement that has won the display lottery, the information processing device 100 displays other advertisements that lost the display lottery in advertising spaces provided on the web page that has won the display lottery. Note that the information processing device 100 may dynamically change the size of the display area for each advertisement in the combination advertisement in response to changes in click-through rate.

In this way, the information processing device 100 can vary the manner in which combined advertisements are presented.

In addition, in the above example, an example of information processing has been described that assumes that the information processing device 100 generates a combination advertisement, but if certain conditions are met, the information processing device 100 may execute processing to generate a combination advertisement. For example, after determining a single advertisement to be displayed in an advertisement space, the information processing device 100 determines whether there are any combination candidates that can be expected to produce a higher combination effect when displayed in combination with other advertisements than when displayed alone. Then, the information processing device 100 generates a combination advertisement on the condition that there are any combination candidates that can be expected to produce a higher combination effect when displayed in combination with other advertisements.

(1-2. Modified Example of Calculation Method of Combination Evaluation Score)
Furthermore, the information processing device 100 may calculate, for each combination of multiple advertisements, a combination evaluation score indicating the likelihood that each advertisement constituting the combination will be selected by a user, based on the display mode of each advertisement when combined and a predetermined index value indicating the advertising effectiveness of each advertisement. Figure 2 is a diagram showing an overview (part 1) of a modified example of the method for calculating the combination evaluation score according to the embodiment. Note that, although Figure 2 shows an example in which three advertisements are combined, any number of advertisements may be combined.

The information processing device 100 determines the display mode for the ad space of advertisements A, B, and D that make up combined advertisement AD_a. The display mode for each advertisement that makes up combined advertisement AD_a includes the size of the display area (display area) that is individually allocated to each advertisement that makes up the combined advertisement within the area of the ad space. Figure 2 shows that the size of display area A-1 for advertisement A is area "A," the size of display area A-2 for advertisement B is area "B," and the size of display area A-3 for advertisement D is area "D."

The information processing device 100 also calculates a combination evaluation score based on the size of the display area individually allocated to each advertisement constituting the combination advertisement within the area of the advertising space and an index value indicating the advertising effectiveness of each advertisement. For example, the information processing device 100 calculates the combination evaluation score by multiplying the area indicating the size of the display area of each advertisement by an index value indicating the advertising effectiveness of each advertisement and adding up the multiplication results for each advertisement. Specifically, the information processing device 100 multiplies the "area A" of advertisement A by the "index value PA" corresponding to advertisement A to calculate a score SC_A corresponding to advertisement A. The information processing device 100 also multiplies the "area B" of advertisement B by the "index value PB" corresponding to advertisement B to calculate a score SC_B corresponding to advertisement B. The information processing device 100 also multiplies the "area D" of advertisement D by the "index value PD" corresponding to advertisement D to calculate a score SC_D corresponding to advertisement D. Then, the information processing device 100 calculates the combination evaluation score SC_(A+B+D) corresponding to the combined advertisement AD_a by adding up the score SC_A corresponding to advertisement A, the score SC_B corresponding to advertisement B, and the score SC_D corresponding to advertisement C.

In addition, when calculating the combination evaluation score, the information processing device 100 may reflect weights that are predefined in association with the position of the display area. Figure 3 is a diagram showing an overview (part 2) of a modified example of the method for calculating the combination evaluation score according to the embodiment.

For example, the display mode of each advertisement constituting the combined advertisement AD_a may include the display position of each advertisement when displayed in the advertisement space. A predefined weight may be associated with the display position of each advertisement. Figure 3 shows that, among the display areas of the advertisement space, a weight of "1.3" is associated with display area A-1, which is located on the far left as one looks into the image; a weight of "1.2" is associated with display area A-2, which is located in the center as one looks into the image; and a weight of "1.1" is associated with display area A-3, which is located on the far right as one looks into the image. The display positions may be predefined as advertisement layout patterns for displaying each advertisement in an area within the advertisement space. In this case, the positions of predefined display areas within the advertisement space (for example, display areas A-1 to A-3 shown in Figure 3) correspond to the display positions. Note that multiple advertisement layout patterns for the advertisement space may be prepared in advance.

When calculating the combination evaluation score, the information processing device 100 may also reflect weights that are predefined in association with the position of the display area. Specifically, the information processing device 100 multiplies the "area A" of advertisement A, the "index value PA" corresponding to advertisement A, and the weight "1.3" associated with display area A-1 to calculate the score SC_A corresponding to advertisement A. The information processing device 100 also multiplies the "area B" of advertisement B, the "index value PB" corresponding to advertisement B, and the weight "1.2" associated with display area A-2 to calculate the score SC_B corresponding to advertisement B. The information processing device 100 also multiplies the "area D" of advertisement D, the "index value PD" corresponding to advertisement D, and the weight "1.1" associated with display area A-3 to calculate the score SC_D corresponding to advertisement D. Then, the information processing device 100 calculates the combination evaluation score SC_(A+B+D) corresponding to the combined advertisement AD_a by adding up the score SC_A corresponding to advertisement A, the score SC_B corresponding to advertisement B, and the score SC_D corresponding to advertisement D.

In this way, the information processing device 100 can obtain a score indicating the likelihood that each advertisement constituting the combination will be selected by the user, depending on the display mode of the combination advertisement.

(1-3. Method for evaluating the combined effect)
Furthermore, the information processing device 100 may evaluate, based on the results of presenting each advertisement including the combination advertisement, whether a combination effect is recognized, in which the likelihood that each advertisement constituting the combination advertisement will be selected by a user is increased when the advertisement is presented as a combination advertisement rather than when each advertisement is presented individually. For example, the information processing device 100 evaluates whether a combination effect is recognized based on a result of comparing a predetermined index value indicating the advertising effectiveness of the combination advertisement with a predetermined index value indicating the advertising effectiveness of each advertisement constituting the combination advertisement.

The method for evaluating the combination effect executed by the information processing device 100 will be described below with reference to FIG. 4. FIG. 4 is a diagram showing an overview of the method for evaluating the combination effect according to the embodiment. FIG. 4 shows a case where the index value indicating the advertising effect of a combination advertisement and each advertisement constituting the combination advertisement is the click-through rate. FIG. 4 also shows advertisement A, advertisement B, advertisement C, advertisement D, combination advertisement A+B+C, and combination advertisement A+B+D as examples of advertisements for explaining the evaluation of the combination effect.

First, the information processing device 100 obtains the click rates of each of advertisements A, B, and C that make up the combination advertisement A+B+C, and adds up the obtained click rates to calculate an estimated click rate for the combination advertisement A+B+C. Figure 4 shows an example in which the estimated click rate for the combination advertisement A+B+C is 7%. Next, the information processing device 100 references the results of providing the combination advertisement A+B+C to obtain the actual click rate for the combination advertisement A+B+C. Figure 4 shows an example in which the actual click rate for the combination advertisement A+B+C is 10%. Furthermore, the information processing device 100 compares the actual click rate with the estimated click rate, and if the actual click rate exceeds the estimated click rate, determines that the combination is effective. The information processing device 100 then associates the value "3," which corresponds to the 3% difference between the actual click rate and the estimated click rate, with advertisements A, B, and C that make up the combination advertisement A+B+C, and registers this as an assist score indicating the combination's effectiveness.

Similarly, the information processing device 100 obtains the click rates of each of advertisements A, B, and D that make up the combination advertisement A+B+D, and adds up the obtained click rates to calculate an estimated click rate for the combination advertisement A+B+D. Figure 4 shows an example in which the estimated click rate for the combination advertisement A+B+D is 9%. Next, the information processing device 100 references the results of providing the combination advertisement A+B+D to obtain the actual click rate for the combination advertisement A+B+D. Figure 4 shows an example in which the actual click rate for the combination advertisement A+B+D is 11%. Furthermore, the information processing device 100 compares the actual click rate with the estimated click rate, and if the actual click rate exceeds the estimated click rate, determines that the combination is effective. The information processing device 100 then associates the value "2," which corresponds to the 2% difference between the actual click rate and the estimated click rate, with advertisements A, B, and D that make up the combination advertisement A+B+D, and registers this as an assist score indicating the combination's effectiveness. The assist score can also be said to be a score that indicates the combined effectiveness of combined advertising.

The information processing device 100 may also identify assist advertisements that, when combined with other advertisements, increase the likelihood of selection by a user. For example, when a combination advertisement is recognized as having a combined effect, the information processing device 100 calculates an assist score indicating the combined effect by subtracting the sum of predetermined index values indicating the advertising effectiveness of each advertisement constituting the combination advertisement (e.g., estimated click rate) from a predetermined index value indicating the advertising effectiveness of the combination advertisement (e.g., actual click rate). The information processing device 100 calculates an assist score for each combination advertisement for which a combined effect is recognized. The evaluation unit 135 then identifies assist advertisements that, when combined with other advertisements, increase the likelihood of selection by a user based on a cumulative score obtained by associating each assist score calculated for each combination advertisement for which a combined effect is recognized with each advertisement constituting the combination advertisement. For example, an advertisement with a higher assist score than other advertisements can be determined to be an assist advertisement that is likely to increase the likelihood of selection by a user when combined with other advertisements. As shown in Figure 4, the evaluation of the combined effectiveness of the combined advertisements A+B+C and A+B+D shows that the assist scores of advertisements A and B are higher than those of other advertisements. In other words, by evaluating the combined effectiveness described above, it is possible to estimate an assist advertisement that, when combined with other advertisements, increases the likelihood that the other advertisements will be selected.

In this way, the information processing device 100 can evaluate the combined effectiveness of combining multiple advertisements from the difference between the estimated click rate of the combination advertisement and the actual click rate, and can propose one methodology for verifying the advertising effectiveness of a combination advertisement composed of multiple advertisements. Note that the information processing device 100 may change the display area of the corresponding advertisement or position it near the main advertisement depending on the magnitude of the above-mentioned assist score.

The information processing device 100 may also identify advertisements that, when combined with other advertisements, are not recognized as having a combined effect, for example, a lower click-through rate. In this case, the information processing device 100 may exclude advertisements that are not recognized as having a combined effect from those to be combined with other advertisements in advance, or may display them in a small size and as far away from other advertisements as possible. The information processing device 100 may also select advertisements to be combined based on the relationship between the likelihood of being selected by a user and the amount charged to the advertiser. For example, if advertisements X and Y are present as combination candidates, and advertisement X has a higher assist score but a lower amount charged than advertisement Y, the information processing device 100 may select advertisements to be combined in this manner if priority is given to the likelihood of being selected by a user, or if priority is given to the amount charged.

Furthermore, when calculating the assist score (estimated click rate), the information processing device 100 may adjust the assist score by multiplying it by a correction coefficient according to the frequency of appearance of the advertisement. This can eliminate the inconvenience of the assist score becoming higher depending on the frequency of appearance.

In addition, the information processing device 100 may obtain a score indicating the combination effect using a combination effect evaluation model, which is a trained model that has learned the correspondence between information about each advertisement that constitutes a combination advertisement and the assist score corresponding to the combination advertisement. Figure 5 is a diagram showing an overview of a method for generating a combination effect evaluation model according to an embodiment.

For example, as shown in FIG. 5, the information processing device 100 references advertising information that stores the results of presenting advertisements, including combination advertisements, and prepares a training data sample that associates information about each advertisement that constitutes the combination advertisement with an assist score that indicates the combined effectiveness of the combination advertisement. Note that the information about the advertisements can be any information, such as category information indicating the advertising target associated with the advertisement or information about the advertiser of the advertisement. The information processing device 100 then uses the training data sample to train a combination effect evaluation model MB-2, which outputs information indicating the combined effectiveness of the combination advertisement formed by the combination of each advertisement, using, for example, an arbitrary machine learning model such as a neural network as the training model MB-1, when information about each advertisement is input. The information processing device 100 inputs information about each advertisement that is a candidate for a combination that constitutes the combination advertisement into the combination effect evaluation model MB-2, and can obtain an assist score that indicates the combined effectiveness of the combination advertisement formed by the combination of each advertisement from the combination effect evaluation model MB-2.

(1-4. Method for determining the charge amount for combined advertising)
Furthermore, when providing a combination advertisement generated by combining a plurality of advertisements, the information processing device 100 may determine a charge amount to be charged to an advertiser associated with the combination advertisement to be delivered, based on a ratio of user interest to each advertisement constituting the combination advertisement. Fig. 6 is a diagram illustrating an overview of a method for determining a charge amount for a combination advertisement according to an embodiment.

As shown in Figure 6, the information processing device 100 derives the user's interest ratio for each advertisement that makes up the combination advertisement to be delivered using the impression estimation model MC, which is a trained model that has learned the correspondence between information about each advertisement that makes up the combination advertisement and the user's interest ratio for each advertisement.

For example, the information processing device 100 uses crowdsourcing or the like to acquire impression information indicating which advertising target, among the advertising targets of each advertisement constituting the combination advertisement, the impression the advertisement had of that target. The information processing device 100 also prepares a training data sample that associates information about the combination advertisement with impression information corresponding to the combination advertisement. Then, using the training data sample, the information processing device 100 inputs information about the combination advertisement into an arbitrary machine learning model such as a neural network as a training model, and trains an impression estimation model MC that outputs impression information corresponding to the combination advertisement.

The information processing device 100 then uses the impression estimation model MC to derive the ratio of user interest for each advertisement that constitutes the combination advertisement to be delivered. For example, the information processing device 100 inputs information about the combination advertisement A+B+C to be delivered into the impression estimation model MC, and treats the output obtained from the impression estimation model MC as the ratio of user interest. Figure 6 shows an example in which, by inputting information about the combination advertisement A+B+C into the impression estimation model MC, the output obtained from the impression estimation model MC is: the estimated ratio of having the impression that advertisement A is: "0.7", the estimated ratio of having the impression that advertisement B is: "0.2", and the estimated ratio of having the impression that advertisement C is: "0.1".

The information processing device 100 also determines the amount to be charged to advertisers associated with a combination advertisement based on the ratio of user interest in each advertisement constituting the combination advertisement to be delivered. For example, using the example shown in FIG. 6 , the information processing device 100 determines the amount to be charged to advertiser A for advertisement A by adding together the set charge amount A for advertisement A, the set charge amount B for advertisement B, and the set charge amount C for advertisement C, and multiplying this total set charge amount A+B+C by 0.7, which is the ratio of the user's interest in advertisement A. Similarly, the information processing device 100 determines the amount to be charged to advertiser B for advertisement B by multiplying the set charge amount A+B+C by 0.2, which is the ratio of the user's interest in advertisement B. Similarly, the information processing device 100 determines the amount to be charged to advertiser C for advertisement C by multiplying the set charge amount A+B+C by 0.1, which is the ratio of the user's interest in advertisement C.

In this way, the information processing device 100 can realize billing based on the user's impressions of combined advertisements, and can propose one method of billing for combined advertisements.

The information processing device 100 may also adjust the amount charged to the advertiser based on the above-mentioned assist score. For example, the information processing device 100 may not charge the advertiser of the advertisement with the highest assist score among the advertisements that make up the combination advertisement. Alternatively, the information processing device 100 may charge the set amount only to the advertiser of the advertisement with the lowest assist score among the advertisements that make up the combination advertisement. In this way, the information processing device 100 can realize charging for combination advertisements that takes into account the combined effect, and can propose one method of charging for combination advertisements.

2. Configuration of information processing device
An information processing device 100 according to an embodiment will be described with reference to Fig. 7. Fig. 7 is a diagram showing an example of the configuration of the information processing device according to an embodiment. As shown in Fig. 7, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

(Regarding the communication unit 110)
The communication unit 110 is realized by, for example, a network interface card (NIC). The communication unit 110 is connected to a network N via a wired or wireless connection. The information processing device 100 transmits and receives information to and from the user terminal 10 via the network N.

(Regarding the storage unit 120)
The storage unit 120 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 120 has an advertisement information storage unit 121, a bid information storage unit 122, a combination evaluation model storage unit 123, an interest level evaluation model storage unit 124, and a combination effect evaluation model storage unit 125.

(Advertisement information storage unit 121)
The advertisement information storage unit 121 stores advertisement information related to advertisements. Fig. 8 is a diagram illustrating an example of advertisement information according to the embodiment.

Note that Figure 8 shows an example of advertising information according to an embodiment, and may include information other than that shown in Figure 8. Also, Figure 8 shows an example in which conceptual information is displayed for multiple items contained in the advertising information, but in reality, specific information such as numerical values or character strings is stored.

As shown in Figure 8, the advertising information stored in the advertising information storage unit 121 has multiple items, such as an "advertising ID" field, an "advertiser ID" field, an "advertising detail information" field, a "category information" field, and an "related keyword information" field. These items in the advertising information are associated with each other.

The "Advertising ID" field stores identification information (advertising ID) for identifying an advertisement. Note that even in the case of a combination advertisement, the "Advertising ID" field may store a single advertising ID assigned to the combination advertisement. Furthermore, in the case of a combination advertisement, the "Advertising ID" field may also store advertising IDs assigned to each advertisement that makes up the combination advertisement.

The "Advertiser ID" field stores identification information (advertiser ID) for identifying the advertiser who submitted the advertisement. In the case of a combination advertisement, the "Advertiser ID" field may also store the advertiser IDs of each advertisement that makes up the combination advertisement.

The "Detailed Advertisement Information" field stores detailed information about the content of the advertisement. Examples of detailed information include the title displayed as text related to the advertisement, a description summarizing the content of the advertising page (web page) on which the advertisement is displayed, and the URL (Uniform Resource Locator) of the link destination set in the displayed advertisement.

The "Category Information" field stores information indicating the category that represents the advertising target. A category indicates a division that groups identical or similar products or identical or similar services at a specified granularity.

The "Related Keyword Information" field stores information indicating related keywords associated with the advertisement. For example, for an advertisement about automobiles, related keywords would be words that tend to co-occur in search queries, such as "new car" and "sales."

According to Figure 8, the advertiser of the advertising information identified by the advertising ID: "Advertiser #01" is identified by "Advertiser #01." Also, according to Figure 8, information mutually associated with the advertising information identified by the advertising ID: "Advertiser #01" includes "Detailed advertising information EX01," "Category information EX01," and "Related keyword information EX01."

(Bidding information storage unit 122)
The bid information storage unit 122 stores bid information related to conditions for displaying an advertisement. Fig. 9 is a diagram illustrating an example of bid information according to the embodiment.

Note that Figure 9 shows an example of bid information according to an embodiment, and the bid information may include information other than that shown in Figure 9. For example, the bid information storage unit 122 may store identification information (advertiser ID) for identifying an advertiser. The bid information storage unit 122 may also store predetermined index values indicating advertising effectiveness, such as CPA (Cost Per Acquisition), CPC (Cost Per Click), CTR (Click Through Rate), number of conversions, CVR (Conversion Rate), and PV (Page View).

Also, while Figure 9 shows an example in which conceptual information is displayed for multiple items contained in the bid information, in reality, specific information such as numerical values or character strings corresponding to each item is stored.

As shown in FIG. 9, the bid information stored in the bid information storage unit 122 has multiple fields, such as a "bid ID," an "advertising ID," a "bid price," a "number of impressions," and a "number of clicks." These fields in the bid information are associated with each other.

The "Bid ID" field stores identification information (bid ID) for identifying a bid. In this embodiment, bidding is conducted for one advertising space that displays a combination of multiple advertisements. The "Advertising ID" field stores identification information (advertising ID) for identifying the advertisement that is the subject of the bid. The identification information (advertising ID) stored in the "Advertising ID" field of the bidding information may be the same information as the identification information (advertising ID) stored in the "Advertising ID" field of the advertising information shown in Figure 8.

The "bid price" field stores information indicating the bid amount that serves as the basis for the amount charged to the advertiser each time an advertisement (e.g., a banner advertisement) is clicked. The "number of impressions" field stores information indicating the number of times the advertisement is displayed (number of impressions). The "number of clicks" field stores information indicating the number of times the advertisement is clicked.

Figure 9 shows that the advertisement space was won by the advertisements identified by advertisement IDs "Ad #01," "Ad #11," and "Ad #21" through a bid identified by bid ID "Bid #01." Figure 9 also shows that the bid prices for the advertisements identified by advertisement IDs "Ad #01," "Ad #11," and "Ad #21" are "bid price EX01," "bid price EX11," and "bid price EX21," the number of impressions are "impressions EX01," "impressions EX11," and "impressions EX21," and the number of clicks are "clicks EX01," "clicks EX11," and "clicks EX21."

(Combination evaluation model storage unit 123)
The combination evaluation model storage unit 123 stores information about a combination evaluation model that receives a predetermined index value indicating the advertising effectiveness of each advertisement to be distributed and outputs information about the predetermined index value indicating the advertising effectiveness of a combined advertisement resulting from a combination of advertisements. Fig. 10 is a diagram showing an example of information about the combination evaluation model according to the embodiment.

Note that Figure 10 shows an example of information relating to a combination evaluation model according to an embodiment, and may include information other than that shown in Figure 10. Also, Figure 10 shows an example in which conceptual information is displayed for multiple items contained in the information relating to the combination evaluation model, but in reality, specific information such as numerical values or character strings corresponding to each item is stored.

As shown in FIG. 10, the information about the combination evaluation model stored in the combination evaluation model storage unit 123 has multiple items, such as a "model ID" field, a "corresponding attribute" field, and a "model information" field. These items in the information about the combination evaluation model are associated with each other.

The "Model ID" item stores identification information (model ID) for identifying the model.

The "Corresponding Attributes" field stores information indicating the attributes associated with the combination evaluation model.

The "Model Information" item stores information about the combinatorial evaluation model. For example, the "Model Information" item stores various pieces of information that make up the model, such as information about the model's configuration (network configuration) and parameters. In other words, the various pieces of information that make up the model include information about the nodes in each layer of the network, the functions used by each node, the connection relationships between the nodes, and the connection coefficients set for the connections between the nodes.

(Interest Level Evaluation Model Storage Unit 124)
The interest evaluation model storage unit 124 receives information about a user and stores information about an interest evaluation model that has been trained by machine learning so as to output an interest score corresponding to the user. Fig. 11 is a diagram illustrating an example of information about the interest evaluation model according to the embodiment.

Note that Figure 11 shows an example of information relating to the interest assessment model according to the embodiment, and may include information other than that shown in Figure 11. Also, Figure 11 shows an example in which conceptual information is displayed for multiple items contained in the information relating to the interest assessment model, but in reality, specific information such as numerical values or character strings corresponding to each item is stored.

As shown in FIG. 11, the information about the interest assessment model stored in the interest assessment model storage unit 124 has multiple items, such as a "model ID" field, a "model information" field, and a "category" field. These items in the information about the interest assessment model are associated with each other.

The "Model ID" item stores identification information (model ID) for identifying the model.

The "Model Information" item stores information about the interest assessment model. For example, the "Model Information" item stores various pieces of information that make up the model, such as information about the model's configuration (network configuration) and parameters. In other words, the various pieces of information that make up the model include information about the nodes in each layer of the network, the functions used by each node, the connection relationships between the nodes, and the connection coefficients set for the connections between the nodes.

The "Category" item stores information indicating the category corresponding to the interest assessment model. The category information is predefined to categorize the subjects of interest for each potential target user. Subjects can be a wide variety of information, including information indicating products and services, as well as hobbies and lifestyles.

(Combination Effect Evaluation Model Storage Unit 125)
The combination effect evaluation model storage unit 125 stores information about each advertisement constituting a combination advertisement and information about the combination effect evaluation model, which is a trained model that has learned the correspondence between information about each advertisement constituting a combination advertisement and an assist score corresponding to the combination advertisement. Fig. 12 is a diagram illustrating an example of information about the combination effect evaluation model according to the embodiment.

As shown in FIG. 12, the information about the combination effect evaluation model stored in the combination effect evaluation model storage unit 125 has multiple items, such as a "model ID" item and a "model information" item. These items in the information about the combination effect evaluation model are associated with each other.

The "Model ID" item stores identification information (model ID) for identifying the model.

The "Model Information" item stores information about the combination effect evaluation model. For example, the "Model Information" item stores various pieces of information that make up the model, such as information about the model's configuration (network configuration) and parameters. In other words, the various pieces of information that make up the model include information about the nodes in each layer of the network, the functions used by each node, the connection relationships between the nodes, and the connection coefficients set for the connections between the nodes.

(Regarding the control unit 130)
The control unit 130 is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like executing various programs stored in a storage device inside the information processing device 100 using RAM as a work area. The control unit 130 is also realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 7, the control unit 130 has a selection unit 131, a generation unit 132, a provision unit 133, a derivation unit 134, an evaluation unit 135, and a determination unit 136, and realizes or executes the information processing functions and actions described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 7, and may be other configurations that perform the information processing described below. Furthermore, the connection relationships between the processing units in the control unit 130 are not limited to the connection relationships shown in FIG. 7, and may be other connection relationships.

(Selection unit 131)
The selection unit 131 selects a plurality of advertisements to be combination candidates from a plurality of advertisements corresponding to categories in which the user is interested. For example, the selection unit 131 selects a plurality of advertisements corresponding to categories in which the interest score, which indicates the degree to which the user U, who is the advertisement delivery destination (target), is interested, is equal to or greater than a predetermined value, as combination candidates. For example, the selection unit 131 can acquire the interest score using an interest evaluation model. The interest evaluation model is generated in advance for each predetermined category that is predefined to classify the objects in which each user, who may be a target, is interested. The interest evaluation model is trained by machine learning so as to input information about the user (for example, search history (search query)) and output an interest score corresponding to the user.

The selection unit 131 may also select at least one advertisement whose index value indicating advertising effectiveness is less than a predetermined value from among multiple advertisements corresponding to categories in which the user U, who is the advertisement delivery destination (target), is interested.

(Generation unit 132)
The generation unit 132 generates a combination advertisement by combining the plurality of advertisements selected by the selection unit 131. For example, the generation unit 132 uses a combination evaluation model to obtain a combination evaluation score indicating the possibility that the combination advertisement resulting from the combination will be selected by a user for each combination of the plurality of advertisements selected by the selection unit 131, and generates a combination advertisement resulting from the combination that maximizes the obtained combination evaluation score.

When generating a combination advertisement, the generation unit 132 can arbitrarily determine the display layout, such as the size and display position of the display area when combining multiple advertisements. For example, the generation unit 132 may determine the size of the display area to be individually allocated to each advertisement that constitutes the combination advertisement, depending on the bid amount when a bid corresponding to the combination advertisement is received from an advertiser. The generation unit 132 may also determine the display position of each advertisement in the combination advertisement, taking into account the similarity of the categories corresponding to each advertisement that constitutes the combination advertisement. The generation unit 132 may also generate a combination advertisement by selecting a layout pattern for a pre-prepared advertisement space and arranging multiple advertisements in the selected layout pattern.

Furthermore, for each combination of multiple advertisements selected by the selection unit 131, the generation unit 132 may calculate a combination evaluation score indicating the likelihood that each advertisement constituting the combination will be selected by a user based on the display mode of each advertisement when combined and a predetermined index value indicating the advertising effectiveness of each advertisement, and generate a combination advertisement based on the combination that maximizes the calculated combination evaluation score. In this case, the generation unit 132 calculates the combination evaluation score based on the size of the display area individually allocated to each advertisement constituting the combination advertisement within the area of the advertising space in which the combination advertisement is displayed, and a predetermined index value indicating the advertising effectiveness of each advertisement. Furthermore, when calculating the combination evaluation score, the generation unit 132 may reflect weights that are predefined in association with the position of the display area.

(Providing unit 133)
The providing unit 133 provides the user with the combined advertisement generated by the generating unit 132. For example, the providing unit 133 provides the user U with the combined advertisement by transmitting a web page including the combined advertisement to the user terminal 10 via the communication unit 110.

Furthermore, when a combination advertisement is selected, the providing unit 133 may hold a display lottery for each advertisement that constitutes the combination advertisement with a probability based on the interest score for the category corresponding to each advertisement that constitutes the combination advertisement, and provide a webpage corresponding to the winning advertisement. Furthermore, when providing a webpage that has won the display lottery, the providing unit 133 may display other advertisements that have lost the display lottery in advertising spaces provided on the webpage.

(Derivation unit 134)
When providing a combination advertisement generated by combining a plurality of advertisements, the derivation unit 134 derives a ratio of user interest in each advertisement constituting the combination advertisement. For example, the derivation unit 134 derives a ratio of user interest in each advertisement constituting the combination advertisement to be delivered using a trained model that has trained a correspondence relationship between information about each advertisement constituting the combination advertisement and a ratio of user interest in each advertisement.

(Evaluation unit 135)
The evaluation unit 135 evaluates, based on the results of providing each advertisement including the combination advertisement, whether or not a combination effect is recognized that increases the possibility of each advertisement being viewed by a user when provided as a combination advertisement rather than when each advertisement constituting the combination advertisement is provided individually.

For example, the evaluation unit 135 evaluates whether the combined advertisement is effective based on the comparison result between a predetermined index value indicating the advertising effectiveness of the combined advertisement and predetermined index values indicating the advertising effectiveness of each advertisement that makes up the combined advertisement. Specifically, the evaluation unit 135 determines that the combined advertisement is effective if the actual click rate of the combined advertisement exceeds the estimated click rate of the combined advertisement.

The evaluation unit 135 may also identify assist advertisements that improve the likelihood of being selected by a user when combined with other advertisements. For example, when a combination effect is recognized, the evaluation unit 135 calculates an assist score indicating the combination effect by subtracting the sum of predetermined index values indicating the advertising effectiveness of each advertisement that constitutes the combination advertisement from a predetermined index value indicating the advertising effectiveness of the combination advertisement. The evaluation unit 135 calculates an assist score for each combination advertisement that improves the combination effect. The evaluation unit 135 then identifies assist advertisements that improve the likelihood of being selected by a user when combined with other advertisements based on a cumulative score that is obtained by associating each assist score calculated for each combination advertisement that improves the combination effect with each advertisement that constitutes the combination advertisement. For example, it can be determined that an advertisement with a higher assist score than other advertisements is highly likely to be an assist advertisement that improves the likelihood of being selected by a user when combined with other advertisements.

The evaluation unit 135 may also obtain a score indicating the combination effect using a combination effect evaluation model that has learned the correspondence between information about each advertisement that constitutes the combination advertisement and an assist score that indicates the combination effect corresponding to the combination advertisement.

(Determination unit 136)
The determination unit 135 determines the amount to be charged to the advertiser associated with the combination advertisement to be distributed, based on the ratio derived by the derivation unit 134. Furthermore, the determination unit 135 may adjust the amount to be charged, based on a score indicating the combination effect corresponding to the combination advertisement.

3. Processing Procedure
(3-1. Procedure for providing combined advertisements)
Hereinafter, an example of an information processing procedure executed by the information processing device 100 according to the embodiment will be described with reference to the drawings. Hereinafter, an example of a procedure for providing a combined advertisement according to the embodiment will be described with reference to FIG. 13. FIG. 13 is a flowchart showing an example of a procedure for providing a combined advertisement according to the embodiment. The processing procedure shown in FIG. 13 is executed by the control unit 130 of the information processing device 100. The processing procedure shown in FIG. 13 is repeatedly executed while the information processing device 100 is operating.

As shown in FIG. 13, the selection unit 131 selects multiple advertisements that are candidates for combination from multiple advertisements that correspond to categories in which the user is interested (step S101).

In addition, the generation unit 132 obtains, for each combination of multiple advertisements selected by the selection unit 131, a combination evaluation score indicating the likelihood that the combined advertisement will be selected by a user (step S102).

The generation unit 132 also generates a combination advertisement using the combination that maximizes the acquired combination evaluation score (step S103).

The providing unit 133 also provides the combined advertisement generated by the generating unit 132 to the user (step S104), and ends the processing procedure shown in FIG. 13.

(3-2. Procedure for evaluating the combined effect)
An example of a procedure for evaluating a combined effect according to the embodiment will be described below with reference to Fig. 14. Fig. 14 is a flowchart showing an example of a procedure for evaluating a combined effect according to the embodiment. The processing procedure shown in Fig. 14 is executed by the control unit 130 of the information processing device 100. The processing procedure shown in Fig. 14 is repeatedly executed while the information processing device 100 is in operation.

As shown in FIG. 14, the evaluation unit 135 obtains the results of providing each advertisement, including the combination advertisement (step S201).

The evaluation unit 135 also compares a predetermined index value indicating the advertising effectiveness of the combined advertisement with a predetermined index value indicating the advertising effectiveness of each advertisement that constitutes the combined advertisement (step S202).

Then, based on the comparison results of step S202, the evaluation unit 135 evaluates whether the combined advertisements have a combination effect (step S203), and ends the processing procedure shown in Figure 14.

(3-3. Procedure for determining the amount of charges)
An example of a procedure for determining a charge amount according to the embodiment will be described below with reference to Fig. 15. Fig. 15 is a flowchart showing an example of a procedure for determining a charge amount according to the embodiment. The processing procedure shown in Fig. 15 is executed by the control unit 130 of the information processing device 100. The processing procedure shown in Fig. 15 is repeatedly executed while the information processing device 100 is in operation.

As shown in FIG. 15, the derivation unit 134 derives the ratio of the user's interest in each advertisement that constitutes the combined advertisement (step S301).

Next, the determination unit 136 determines the amount to be charged to the advertiser associated with the combination advertisement to be distributed based on the derived ratio (step S302), and ends the processing procedure shown in Figure 15.

4. Modifications
The information processing device 100 according to the embodiment described above may be implemented in various different forms other than the embodiment described above. Therefore, other embodiments of the information processing device 100 will be described below.

(4-1. Ad selection specialized for user context)
In the above embodiment, the information processing device 100 may select advertisements specialized for a specific user when generating a combination advertisement. For example, the information processing device 100 creates a user list indicating a list of users who may select each advertisement to be delivered, based on user context. Next, the information processing device 100 compares the user lists with each other to determine the user overlap rate between the user lists. Then, the information processing device 100 selects multiple advertisements with a high user overlap rate as combination candidates for the combination advertisement. For example, when selecting three advertisements when generating a combination advertisement, the information processing device 100 can select the advertisements with the top three overlap rates. This makes it possible to generate a combination advertisement specialized for the user context of the user list.

When generating a generalized combination advertisement that is universal to all users, rather than specialized for a specific user, the information processing device 100 may select multiple advertisements with a low user overlap rate as combination candidates for the combination advertisement. For example, when generating a combination advertisement, if the information processing device 100 selects three advertisements, it can select the advertisements with the lowest overlap rates, from the top three. This makes it possible to generate a generalized combination advertisement that is not specialized to the user context of the user list.

(4-2. Combination Rejection Based on User Response)
In the above embodiment, the information processing device 100 may conduct a questionnaire survey of users to whom the combination advertisement is to be delivered, and generate the combination advertisement by eliminating combinations of advertisements in the combination advertisement that have low ratings.

(4-3. Deriving an assist score corresponding to a combination of advertising targets)
In the above embodiment, the information processing device 100 may regard the index values indicating the advertising effectiveness of each advertisement that constitutes a combination advertisement as index values of the products or services that the advertisements advertise, and may derive an assist score for each combination of advertising targets using the method described in the above embodiment.

5. Hardware Configuration
The information processing device 100 according to the embodiment described above is realized, for example, by a computer 1000 having a configuration as shown in Fig. 16. Fig. 16 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment.

The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected via a bus 1090.

The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and secondary storage device 1050, and programs read from the input device 1020, and executes various processes. The primary storage device 1040 is a memory device, such as RAM, that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used by the arithmetic device 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), HDD, flash memory, etc.

The output IF 1060 is an interface for transmitting information to be output to an output device 1010, such as a monitor or printer, which outputs various types of information. It is implemented, for example, by a connector conforming to a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (High Definition Multimedia Interface). The input IF 1070 is an interface for receiving information from various input devices 1020, such as a mouse, keyboard, and scanner, and is implemented, for example, by USB.

The input device 1020 may be a device that reads information from optical recording media such as a CD (Compact Disc), DVD (Digital Versatile Disc), or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. The input device 1020 may also be an external storage medium such as a USB memory.

Network IF 1080 receives data from other devices via network N and sends it to the computing device 1030, and also transmits data generated by the computing device 1030 to other devices via network N.

The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

For example, when the computer 1000 functions as the information processing device 100 according to the above embodiment, the arithmetic unit 1030 of the computer 1000 executes a program (e.g., an information processing program) loaded onto the primary storage device 1040, thereby realizing functions similar to those of the control unit 130. In other words, the arithmetic unit 1030 works in cooperation with the program (e.g., an information processing program) loaded onto the primary storage device 1040 to realize the processing performed by the information processing device 100 according to the above embodiment.

[6. Other]
Of 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 using 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 as desired unless otherwise specified.

Furthermore, the components of each device shown in the figure are functional concepts and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

Furthermore, the above-described embodiments can be combined as appropriate to the extent that the processing content is not contradictory.

7. Effects
The information processing device 100 according to the embodiment includes a selection unit 131, a generation unit 132, and a provision unit 133. The selection unit 131 selects a plurality of advertisements to be combination candidates from a plurality of advertisements corresponding to categories in which the user is interested. The generation unit 132 calculates, for each combination of the plurality of advertisements selected by the selection unit 131, a combination evaluation score indicating the likelihood that each advertisement constituting the combination will be selected by the user, based on the display mode of the advertisements when combined and a predetermined index value indicating the advertising effectiveness of each advertisement, and generates a combination advertisement based on the combination with the highest calculated combination evaluation score. The provision unit 133 provides the combination advertisement generated by the generation unit 132 to the user.

In addition, in the information processing device 100 according to the embodiment, the generation unit 132 calculates a combination evaluation score based on the size of the display area individually allocated to each advertisement constituting the combination advertisement within the area of the advertising space in which the combination advertisement is displayed, and a predetermined index value.

In addition, in the information processing device 100 according to the embodiment, the generation unit 132 reflects a weight that is predefined in association with the position of the display area when calculating the combination evaluation score.

By using the processes performed by the above-mentioned units, or any combination of the units, the information processing device 100 according to the embodiment can create a new, influential advertisement based on the display mode of multiple advertisements, further increasing the likelihood that the advertisement will achieve the desired results.

The above describes in detail the embodiments of the present application based on several drawings, but these are merely examples, and the present invention can be implemented in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the Disclosure of the Invention section.

In addition, the above-mentioned "section, module, unit" can be interpreted as "means" or "circuit." For example, a control unit can be interpreted as a control means or a control circuit.

REFERENCE SIGNS LIST 10 User terminal 100 Information processing device 110 Communication unit 120 Storage unit 121 Advertising information storage unit 122 Bidding information storage unit 123 Combination evaluation model storage unit 124 Interest level evaluation model storage unit 125 Combination effect evaluation model storage unit 130 Control unit 131 Selection unit 132 Generation unit 133 Provision unit 134 Derivation unit 135 Evaluation unit 136 Determination unit

Claims (5)

a selection unit that selects, from among a plurality of advertisements corresponding to a category in which a user is interested , a plurality of advertisements having an index value indicating advertising effectiveness that is less than a predetermined value, as advertisements to be combination candidates;
a generation unit that calculates, for each combination of a plurality of advertisements selected by the selection unit, a combination evaluation score that indicates the likelihood that each advertisement constituting the combination will be selected by the user, based on a display mode when each advertisement is combined and a predetermined index value that indicates the advertising effectiveness of each advertisement, and generates a combination advertisement using the combination that maximizes the calculated combination evaluation score;
a providing unit that provides the combined advertisement generated by the generating unit to the user. The generation unit
The information processing device according to claim 1, characterized in that the combination evaluation score is calculated based on the size of a display area individually allocated to each advertisement constituting the combination advertisement within an area of an advertising frame in which the combination advertisement is displayed, and the predetermined index value. The generation unit
The information processing device according to claim 2 , wherein a weight that is predefined in association with a position of the display area is reflected when calculating the combination evaluation score. 1. A computer-implemented information processing method, comprising:
a selection step of selecting, from among a plurality of advertisements corresponding to a category in which the user is interested , a plurality of advertisements having an index value indicating advertising effectiveness that is less than a predetermined value as advertisements to be combination candidates;
a generating step of calculating, for each combination of a plurality of advertisements selected in the selecting step, a combination evaluation score indicating the likelihood that each advertisement constituting the combination will be selected by the user, based on the display mode of each advertisement when combined and a predetermined index value indicating the advertising effectiveness of each advertisement, and generating a combined advertisement using the combination that maximizes the calculated combination evaluation score;
a providing step of providing the combined advertisement generated in the generating step to the user. On the computer,
a selection step of selecting, from among a plurality of advertisements corresponding to a category in which the user is interested , a plurality of advertisements having an index value indicating advertising effectiveness that is less than a predetermined value as advertisements to be combined;
a generation step of calculating, for each combination of a plurality of advertisements selected by the selection step, a combination evaluation score indicating the likelihood that each advertisement constituting the combination will be selected by the user, based on the display mode of each advertisement when combined and a predetermined index value indicating the advertising effectiveness of each advertisement, and generating a combination advertisement based on the combination that maximizes the calculated combination evaluation score;
and a providing step of providing the combined advertisement generated by the generating step to the user.