Advertisement distribution device, determination device, advertisement distribution method, determination method, and program

Abstract

To provide an advertisement distribution device, a determination device, an advertisement distribution method, a determination method, and a program capable of appropriately distributing an advertisement matching a user's behavioral habit or preference.SOLUTION: Acquiring payment information of a user of an electronic payment service; performing machine learning on a learned model using a history of the payment information as an input to output a similarity with a specific user group; An advertisement distribution device comprising: a similarity determination unit configured to determine whether or not a settlement behavior of a user is similar to a settlement behavior of a specific group of users; and an advertisement content providing unit configured to provide advertisement content related to the settlement behavior of the specific group of users to a user terminal of the user when it is determined that the settlement behavior of the user is similar to the settlement behavior of the specific group of users.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an advertisement distribution device, a determination device, an advertisement distribution method, a determination method, and a program. [Background technology]

[0002] Conventionally, there is known a technique for analyzing a user's preferences for content and delivering advertisements that match the analyzed preferences. For example, Patent Document 1 discloses a technique for analyzing a user's preferences based on the user's attributes and access information related to content and delivering advertisements that match the analyzed preferences. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-71881 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology described in Patent Document 1 analyzes user preferences based on user access information to online content such as web pages. As described above, conventional technologies consider user behavior information online, but may not consider user behavior information in physical stores that sell goods or services. As a result, it may not be possible to appropriately deliver advertisements that match the user's behavioral habits and preferences.

[0005] The present invention has been made in consideration of these circumstances, and one of its objectives is to provide an advertising distribution device, a determination device, an advertising distribution method, a determination method, and a program that can appropriately distribute advertisements that match a user's behavioral habits and preferences. [Means for solving the problem]

[0006] One aspect of the present invention is an advertising distribution device comprising: a payment information acquisition unit that acquires payment information of a user of an electronic payment service; a similarity determination unit that uses a trained model that has been machine-learned to input a history of the payment information and output a similarity to a specific user group, and determines whether the payment behavior of the user is similar to the payment behavior of the specific user group; and an advertising content provision unit that, when it is determined that the payment behavior of the user is similar to the payment behavior of the specific user group, provides advertising content related to the payment behavior of the specific user group to a user terminal device of the user. [Effects of the Invention]

[0007] According to aspects of the present invention, it is possible to provide an advertising distribution device, a determination device, an advertising distribution method, a determination method, and a program that can appropriately distribute advertisements that match a user's behavioral habits and preferences. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration for realizing an electronic payment service. [Figure 2] FIG. 1 is a diagram illustrating an example of the general flow of electronic payment. [Figure 3] FIG. 10 is a diagram illustrating an example of a payment completion screen. [Figure 4] FIG. 10 is a diagram illustrating an example of an advertiser-only page. [Figure 5] FIG. 2 is a configuration diagram of a payment server 100. [Figure 6] FIG. 10 is a diagram showing an example of the contents of user information 172. [Figure 7] FIG. 10 is a diagram showing an example of the contents of store information 176. [Figure 8] FIG. 10 is a diagram showing an example of the contents of segment information 178. [Figure 9] FIG. 10 is a diagram showing an example of the contents of advertisement distribution conditions 180. [Figure 10] 10 is a diagram showing an example of advertising content delivered to a user who satisfies an advertisement delivery condition 180. FIG. [Figure 11]FIG. 10 is a diagram showing an example of the contents of segment information 178A. [Figure 12] FIG. 10 is a diagram showing an example of the contents of advertisement distribution conditions 180A. [Figure 13] FIG. 10 is a diagram showing an example of advertising content delivered to a user who satisfies an advertisement delivery condition 180A. [Figure 14] 10 is a flowchart showing an example of the flow of processing executed by the payment server 100. [Figure 15] FIG. 10 is a configuration diagram of a payment server 100A according to a modified example. [Figure 16] 10 is a diagram showing a screen IM1 which is an example of an interface screen provided to an advertiser terminal device 70. FIG. [Figure 17] FIG. 10 is a diagram showing an example of the contents of advertisement bidding information 184. [Figure 18] 10 is a flowchart showing an example of the flow of processing executed by the payment server 100. [Figure 19] FIG. 10 is a configuration diagram of a payment server 100B according to a second embodiment. [Figure 20] A figure showing an example of the contents of trained model 178B. [Figure 21] 10 is a diagram showing a screen IM2 which is an example of an interface screen provided to the advertiser terminal device 70. FIG. [Figure 22] FIG. 10 is a diagram showing an example of the contents of advertisement bidding information 184B. DETAILED DESCRIPTION OF THE INVENTION

[0009] [First embodiment] Hereinafter, with reference to the drawings, an embodiment of an advertisement distribution device, an advertisement distribution method, and a program according to a first embodiment of the present invention will be described. The advertisement distribution device is realized by one or more processors. The advertisement distribution device is a device that distributes advertisements in conjunction with an electronic payment service. The electronic payment service is a service that supports payments related to the purchase of goods and services at a store. The store is primarily a physical store (real store) that exists in the real world, as opposed to a virtual store related to e-commerce. Note that the mechanism of the present invention does not necessarily exclude the application of a virtual store related to e-commerce, but the stores targeted by the present invention include at least real stores.

[0010] [Electronic payment service] Figure 1 shows an example of a configuration for realizing an electronic payment service. The electronic payment service is realized mainly by a payment server 100. The payment server 100 communicates with, for example, one or more user terminal devices 10, one or more store terminal devices 50, and one or more advertiser terminal devices 70 via a network NW. The network NW includes, for example, the Internet, a LAN (Local Area Network), a wireless base station, a provider device, etc.

[0011] The user terminal device 10 is, for example, a portable terminal device such as a smartphone or tablet terminal. The user terminal device 10 is a computer device having at least an optical reading function, a communication function, a display function, an input acceptance function, and a program execution function. In the following description, the components for realizing these functions are referred to as a camera, a communication device, a touch panel, a CPU (Central Processing Unit), etc. In the user terminal device 10, a processor such as a CPU executes a payment application 20, which operates in cooperation with the payment server 100 to provide an electronic payment service to the user. The payment application 20 controls the camera, communication device, touch panel, etc.

[0012] The store terminal device 50 is installed, for example, in a store. The store terminal device 50 is a computer device having at least a product price acquisition function, an optical reading function, a program execution function, and a communication function. The store terminal device 50 may include a so-called POS (Point of Sale) device, and the product price acquisition function and the optical reading function may be realized by the POS device. The store code image 60 is placed in the store and is a code image such as a QR code (registered trademark) printed on a paper or plastic medium. The store code image 60 may also be displayed on a display placed in the store.

[0013] The advertiser terminal device 70 is a terminal device used by a person (advertiser) who intends to post an online advertisement (hereinafter simply referred to as an advertisement) that will be included in the payment completion screen described later. The advertiser terminal device 70 may be any computer device that can be connected to the network NW, such as a personal computer, a smartphone, or a tablet terminal.

[0014] The payment server 100 performs electronic payment based on payment information received from the user terminal device 10 or the store terminal device 50. The payment server 100 performs electronic payment, for example, by increasing or decreasing the balance information managed in association with the user ID (in other words, by depositing or withdrawing electronic money). Electronic payment may include methods such as revolving payment or credit payment that allow for purchases of a larger amount than the balance information at the time of purchase.

[0015] FIG. 2 is a diagram illustrating the general flow of electronic payment. There may be two patterns for electronic payment: Pattern 1 and Pattern 2. In Pattern 1, first, the payment app 20 is launched on the user terminal device 10, and a code image such as a QR code or barcode is displayed. The user holds (presents) the display surface of the user terminal device 10 over the store terminal device 50. The store terminal device 50 decodes the code image using its optical reading function and acquires information such as the user ID. The store terminal device 50 then generates payment information including the user ID, payment amount, store ID, etc., and transmits it to the payment server 100. The payment amount information has been acquired in advance by reading a barcode or manually entering it. The payment server 100 performs payment processing based on the received information.

[0016] In pattern 2, the user terminal device 10, with the payment app 20 running, decodes the store code image 60 using its optical reading function. The store code image 60 contains information such as the store name. The user enters the payment amount into the user terminal device 10 on the screen displaying the store name, etc. The user terminal device 10 then generates payment information including the user ID, payment amount, store ID, etc., and transmits it to the payment server 100. The payment server 100 performs payment processing based on the received information. Note that electronic payment may be performed using only one of the above patterns.

[0017] When the electronic payment is completed, a completion notice is sent from the payment server 100 to the user terminal device 10. The user terminal device 10 displays a payment completion screen in response to the received completion notice. The completion notice is, for example, in the form of a web page. FIG. 3 shows an example of the payment completion screen. The payment completion screen includes, for example, an area A1 displaying information about the store where the payment was made, an area A2 displaying the payment amount, etc., an area A3 displaying points (an example of a benefit) awarded to the user as a result of the payment, and an area A4 displaying advertisements by advertisers. The advertiser is primarily a business operator different from the operator of the payment server 100 (although the operator of the payment server 100 may also be the advertiser). This advertisement is selected using a technique such as second pricing based on the advertiser's bid amount (bid amount). The advertiser makes a bid using the advertiser terminal device 70. When the advertisement is posted and clicked (tapped) by a user, the advertiser pays an amount corresponding to the bid amount to the operator of the payment server 100. Details regarding advertisements will be described later. In this embodiment, the advertiser is a member store of the electronic payment service provided by the operator of the payment server 100, in other words, a store that allows users to make electronic payments using the electronic payment service.

[0018] When a user taps on the advertisement shown in area A4 on the user terminal device 10, the payment server 100 transitions the screen to a dedicated page on the electronic payment service of the advertiser that placed the tapped advertisement. Through the dedicated page for the advertiser to which the user is transitioned, the user can acquire coupons (benefits) that can be used for discounts on electronic payments, etc.

[0019] FIG. 4 is a diagram showing an example of an advertiser-only page. The advertiser-only page includes an area A5 that displays overview information about the advertiser's store, an area A6 that displays detailed information about the advertiser's store using switchable tabs, and so on. As shown in FIG. 4, for example, if a user taps on "Coupon," one of the tabs included in area A6, coupons that the user can currently use for electronic payments at the store are displayed. The user can acquire the displayed coupon by, for example, further tapping on the displayed coupon. The payment server 100 stores content information of coupons acquired by the user in coupon grant information in the user information 172, which will be described later. Coupons acquired by a user for a certain store are automatically applied when making an electronic payment at the store, and processing such as a discount is executed.

[0020] 3 and 4, a case has been described as an example in which a user taps on advertising content displayed on the payment completion screen to transition to an advertiser-only page and acquire a coupon on the transitioned advertiser-only page. However, the present invention is not limited to such a configuration, and for example, the advertising content itself may be a coupon. In this case, the user acquires the coupon by tapping on the coupon displayed on the payment completion screen, and the payment server 100 stores content information of the coupon acquired by the user in coupon grant information of the user information 172, which will be described later. Alternatively, the payment server 100 may transition the screen of the user terminal device 10 to a dedicated page for acquiring the coupon by the user tapping on the coupon displayed on the payment completion screen.

[0021] [Payment server] FIG. 5 is a configuration diagram of the payment server 100. The payment server 100 includes, for example, a communication unit 110, a payment content providing unit 120, a payment processing unit 130, an advertisement distribution unit 150, and a storage unit 170. The advertisement distribution unit 150 includes, for example, a payment information acquisition unit 152, a segment information generation unit 154, and an advertisement content providing unit 156. Each of the payment information acquisition unit 152, the segment information generation unit 154, and the advertisement content providing unit 156 is realized by, for example, a hardware processor such as a CPU executing a program (software). Some or all of these components may be realized by hardware (including circuitry) such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a GPU (Graphics Processing Unit), or may be realized by a combination of software and hardware. The program may be stored in advance in a storage device such as an HDD (Hard Disk Drive) or flash memory (a storage device with a non-transitory storage medium), or may be stored in a removable storage medium (a non-transitory storage medium) such as a DVD or CD-ROM, and installed in the storage device by inserting the storage medium into a drive device.

[0022] The storage unit 170 is a HDD, a flash memory, a RAM (Random Access Memory), etc. The storage unit 170 may be a NAS (Network Attached Storage) device that the payment server 100 can access via a network. The storage unit 170 stores information such as user information 172, payment content information 174, store information 176, segment information 178, advertisement delivery conditions 180, and advertisement content information 182.

[0023] The communication unit 110 is a communication interface for connecting to the network NW, and is, for example, a network card.

[0024] The payment content providing unit 120 has, for example, a web server function, and provides the user terminal device 10 with information (content) for displaying various screens for the electronic payment service, including the above-mentioned payment completion screen, and grants the user a coupon that can be used for the electronic payment service in response to an operation such as a tap by the user. The payment content providing unit 120 reads out necessary content from the payment content information 174 as appropriate and provides it to the user terminal device 10. The user terminal device 10 accepts various inputs by the user while content is being played by the payment application 20, and transmits the above-mentioned payment information and the like to the payment server 100.

[0025] The payment processing unit 130 performs payment processing based on the payment information transmitted by the user terminal device 10 or the store terminal device 50. The payment processing unit 130 performs payment processing while referring to the user information 172.

[0026] FIG. 6 is a diagram showing an example of the contents of user information 172. User information 172 associates information such as balance information, contact information, credit information, coupon grant information, and payment history information with a user ID, for example. Balance information is information indicating the balance of electronic money set by the user by transferring funds from a bank deposit or the like to the electronic payment service in advance. Note that balance information may also be automatically added by auto-charge associated with payment processing. Contact information is information entered when the user subscribes to the electronic payment service. Credit information is information indicating whether or not a revolving payment or the like has been approved. Coupon grant information is information indicating the contents of coupons (benefits) acquired and granted by the user. Payment history information is information indicating the breakdown of payments made by the user (date and time, store ID of the store where the purchase was made, payment amount, etc.) for each payment.

[0027] Information about stores is managed as store information 176. FIG. 7 is a diagram showing an example of the contents of store information 176. Store information 176 associates, for example, store IDs with information such as store category, location, and payment pattern. Store category may be one-level information, or may have a hierarchical structure of two or more levels. For example, information such as "Japanese cuisine," "restaurant," or "eatery" may be assigned as a higher-level concept than "sushi" shown in the figure. Locations may be represented by hierarchical code information such as JIS code. Payment pattern is information indicating whether payment is possible using pattern 1 or pattern 2 described above.

[0028] [Advertising] The advertisement distribution unit 150 performs processing for displaying advertisement content on the user terminal device 10. The advertisement distribution unit 150 is an example of an "advertising distribution device." In this embodiment, the advertisement distribution unit 150 is a function of the payment server 100, but the advertisement distribution unit 150 (advertising distribution device) may be a device separate from the payment server 100.

[0029] The payment information acquisition unit 152 acquires payment information for the electronic payment service. As described in FIG. 2, payment information is information that is generated each time a payment is made at a physical store and transmitted to the payment server 100. The payment information is provided to the payment processing unit 130 and reflected in the user information 172, and at the same time, the payment information is provided to the payment information acquisition unit 152.

[0030] The segment information generation unit 154 aggregates and categorizes the payment history information included in the user information 172 of multiple users to generate segment information 178 indicating the payment behavior of a specific user group, and stores the segment information 178 in the storage unit 170. FIG. 8 is a diagram illustrating an example of the content of the segment information 178. The segment information 178 associates, for example, information such as store category, location, store ID, payment frequency, payment time zone, payment price range, and number of users with a segment ID. Each record in the segment information 178 is a count of the number of users who meet the set conditions of store category, location, store ID, payment frequency, payment time zone, and payment price range. For example, the record for segment ID "S001" indicates that there are 100 or more users who make payments of 1,000 to 2,000 yen at least once a week between 11:00 and 12:00 at three stores in Chiyoda Ward with store IDs "001," "007," and "010" and whose store category is "sushi." The segment information generation unit 154, for example, while changing the combination of store category, location, store ID, payment frequency, payment time period, and payment price range, counts the number of people corresponding to each combination based on the user information 172 of multiple users, and generates combinations for which the number of people corresponding to a threshold value (for example, 50 people) or more as records of the segment information 178. This makes it possible to obtain information about user groups that exhibit characteristic payment behavior.

[0031] When payment information is acquired by the payment information acquisition unit 152 and the payment information satisfies advertisement distribution conditions 180 set based on the segment information 178, the advertisement content providing unit 156 provides advertisement content related to the payment behavior of a specific user group corresponding to the segment information 178 to the user terminal device 10 used by the user associated with the payment information. FIG. 9 is a diagram showing an example of the advertisement distribution conditions 180. The advertisement distribution conditions 180, for example, associate information such as a segment ID, distribution conditions, and distribution content with a distribution condition ID. Each record of the advertisement distribution conditions 180 specifies, as a distribution condition, a payment behavior similar to the payment behavior of a user group in a segment corresponding to the segment ID, and specifies, as the distribution content, the content of the advertisement content to be distributed when the distribution condition is satisfied. For example, the record with the distribution condition ID "C001" specifies that, for a user who has made a payment at only two of the three stores IDs "001," "007," and "010," advertisement content for the third store should be distributed. In this way, by delivering advertising content related to the payment behavior of a user group in a segment to users whose payment behavior is similar to that of the user group, the effectiveness of advertising can be improved. The advertisement delivery conditions 180 are an example of "predetermined conditions." The advertising content providing unit 156 can also be described as functioning as a "similarity determination unit" that determines the similarity of payment behavior based on the segment information 178 and the advertisement delivery conditions 180.

[0032] In this embodiment, the delivery conditions and delivery content are set in advance by, for example, the operator of the payment server 100. However, the advertisement delivery conditions 180 may be automatically generated based on the segment information 178. For example, the segment information 178 includes items such as store category, location, store ID, payment frequency, payment time zone, and payment price range. The delivery conditions may be automatically set so that advertising content is delivered to users who have made a different payment in only one of these items. Furthermore, for example, the delivery conditions may be set so that information similar to the segment information 178 is generated for each user based on the payment history information included in the user information 172, the similarity between the generated information and the segment information 178 is calculated as the distance between vectors, and if the calculated distance is equal to or less than a threshold, advertising content is delivered to the user.

[0033] FIG. 10 is a diagram illustrating an example of advertising content delivered to a user who satisfies the advertisement delivery condition 180. FIG. 10 illustrates an example of advertising content delivered to a user who satisfies the delivery condition ID "C001" illustrated in FIG. 9. That is, the user has payment history information for only two of the three sushi restaurants in Chiyoda Ward indicated by the segment with segment ID "S001," but does not have a payment history for the remaining restaurant. Therefore, the advertising content providing unit 156 displays advertising content A4 related to the remaining restaurant on the user terminal device 10 of the user. The displayed advertising content A4 is determined in advance to be displayed to users who have visited the two sushi restaurants in Chiyoda Ward. Therefore, for example, the creator of the advertising content A4 can enhance the advertising effectiveness of the advertisement by creating appealing content related to services not offered at these two sushi restaurants (e.g., "one free piece of bluefin tuna") in advance. Note that the advertising content providing unit 156 may display the user's current location and the location of the advertised restaurant on a map, as shown in the lower part of FIG. 10.

[0034] In addition to the segment information 178 shown in FIG. 8 , the segment information generation unit 154 may generate segment information 178A indicating transitions in payment behavior of a specific user group by aggregating and categorizing transitions in payment history information included in the user information 172 of multiple users, and store the segment information 178A in the storage unit 170. FIG. 11 is a diagram showing an example of the content of the segment information 178A. For example, the segment information 178A associates information such as a pre-transition store ID, a post-transition store ID, payment frequency, payment time zone, payment price range, and number of relevant users with a segment ID. Each record in the segment information 178A is a count of the number of relevant users who made a payment at a store indicated by a pre-transition store ID and then made a payment at a store indicated by a post-transition store ID, and who met the set conditions of payment frequency, payment time zone, and payment price range. For example, the record for segment ID "S010" indicates that there are 50 or more users who make a payment at the store indicated by pre-transition store ID "001" and then make a payment at the store indicated by post-transition store ID "002," and who make payments of 2,000 to 3,000 yen at least once a week between 11:00 and 16:00. The segment information generation unit 154, for example, changes the combination of pre-transition store ID, post-transition store ID, payment frequency, payment time period, and payment price range, and tallies the number of people corresponding to each combination based on the payment history information included in the user information 172 of multiple users, and generates combinations for which the number of people corresponding to a threshold value (for example, 50 people) or more as records of segment information 178.

[0035] When payment information is acquired by the payment information acquisition unit 152, if the payment information satisfies advertisement delivery conditions 180A set based on the segment information 178A, the advertisement content providing unit 156 may provide advertisement content related to the payment behavior of a specific user group corresponding to the segment information 178A to the user terminal device 10 used by the user associated with the payment information. FIG. 12 is a diagram showing an example of the contents of the advertisement delivery conditions 180A. For example, the advertisement delivery conditions 180A associate information such as a segment ID, delivery conditions, and delivery content with a delivery condition ID. Each record of the advertisement delivery conditions 180A specifies, as a delivery condition, payment behavior similar to the payment behavior of a user group in a segment corresponding to the segment ID, and specifies, as the delivery content, the content of the advertisement content to be delivered when the delivery conditions are satisfied. For example, the record with distribution condition ID "C010" specifies that, of two stores with store IDs "001" and "002," advertising content for the store with store ID "002" be delivered to a user who has no history of making a payment at the store with store ID "002" and has made a payment at the store with store ID "001." In this way, by delivering advertising content related to a transition to users whose payment behavior is similar to that of a user group in a segment representing a transition between certain stores, the promotional effectiveness of the advertisement can be improved.

[0036] 12 illustrates an example in which advertising content for a store after a transition is delivered to a user who has made a payment at a store before a transition in segment information 178A and has no history of making a payment at the store after the transition, but the present invention is not limited to such a configuration. For example, advertising content for the store before a transition may be delivered to a user who has made a payment at a store after a transition and has no history of making a payment at the store before the transition.

[0037] FIG. 13 is a diagram illustrating an example of advertising content delivered to a user who satisfies the advertisement delivery condition 180A. FIG. 13 illustrates an example of advertising content delivered to a user who satisfies the delivery condition ID "C010" illustrated in FIG. 12. That is, the user has made a payment at a store with a pre-transition store ID "001" indicated by the segment with the segment ID "S010," but does not have a history of making a payment at a store with a post-transition store ID "002." Therefore, the advertising content providing unit 156 displays advertising content A4 related to the store with a post-transition store ID "002" on the user terminal device 10 of the user. The advertising content A4 to be displayed at this time is determined in advance to be displayed to a user who has visited the store with the pre-transition store ID "001." Therefore, for example, the creator of the advertising content A4 can enhance the promotional effect of the advertisement by creating appealing content in advance, taking into consideration the user's state of mind immediately after visiting the store with the pre-transition store ID "001" (e.g., "I want to drink coffee after a meal"). At this time, the advertising content providing unit 156 may display the user's current location and the location of the advertised store on a map, similar to FIG.

[0038] Furthermore, the advertising content providing unit 156 performs processing for displaying the advertising content on the user terminal device 10, for example, by including the advertising content in a payment completion screen related to the payment information. The processing for displaying the advertising content is, for example, processing for transmitting location information of the advertising content (for example, a URL; Uniform Resource Locator) to the user terminal device 10 along with the content for displaying the payment completion screen. The payment application 20 obtains the advertising content using the URL, embeds the advertising content in area A4 (see FIG. 3 ) of the payment completion screen, and displays the advertising content on the user terminal device 10.

[0039] The advertising content providing unit 156 may include the advertising content in a content screen other than the payment completion screen, or may cause the advertising content to be displayed independently on the user terminal device 10. In the former case, the advertising content providing unit 156 may include the advertising content in, for example, the top page of the payment content and display it on the user terminal device 10. In the latter case, the advertising content providing unit 156 may display the advertising content on the user terminal device 10 in the form of, for example, a push notification.

[0040] [Processing flow] 14 is a flowchart showing an example of the flow of processing executed by the payment server 100. First, the payment content providing unit 120 and the advertisement distribution unit 150 each determine whether the payment server 100 has received payment information (S100). The payment processing unit 130 performs payment processing based on the payment information (S102).

[0041] In parallel, the payment information acquisition unit 152 of the advertisement distribution unit 150 acquires the received payment information and also acquires past payment history information of the user (user related to the payment information) from the user information 172 (S106).

[0042] Next, the advertising content providing unit 156 of the advertising distribution unit 150 searches the advertising distribution conditions 180, extracts a distribution condition ID that matches (applies to) the advertising distribution conditions, and specifies the advertising content to be provided (S108). Then, the advertising content providing unit 156 obtains location information of the specified advertising content from the advertising content information 182 and notifies the payment content providing unit 120 (S110).

[0043] The payment content providing unit 120 includes the location information notified from the advertising content providing unit 156 in a payment completion screen and displays it on the user terminal device 10 (S104).

[0044] According to the process described above, segment information is generated by categorizing the payment history information of multiple users in an electronic payment service that supports payments at physical stores, and advertising content related to the payment behavior of a specific user group indicated by the segment information is provided to users whose payment behavior is similar to that of the user group. This makes it possible to appropriately deliver advertisements that match the behavioral habits and preferences of users.

[0045] [Variations] In the above-described embodiment, advertisement distribution conditions 180 for advertisement content are set in advance based on segment information 178, and when a user's payment information satisfies any of the conditions stored in the advertisement distribution conditions 180, advertisement content corresponding to the condition is distributed to the user terminal device 10. In other words, the distribution of advertisement content in the above-described embodiment is autonomously executed by the payment server 100. In contrast, in this modified example, bidding conditions related to the payment behavior of a specific user group are proposed to the advertiser of a physical store based on segment information 178, thereby improving convenience for the advertiser.

[0046] 15 is a configuration diagram of a payment server 100A according to a modified example. The payment server 100A includes a bidding condition acquisition unit 158, a bidding condition proposal unit 160, and advertisement bidding information 184 in addition to the components of the payment server 100 shown in FIG.

[0047] The bidding conditions acquired by the bidding condition acquisition unit 158 ​​relate to payment information and / or the past payment history of the user related to the payment information. For example, they include some or all of individual conditions such as the payment location (the location of the store related to the payment), store category, payment frequency for each store category, payment amount range, and payment time period. If payment frequency is not included in the bidding conditions, the bidding conditions relate to a single payment. However, if payment frequency is included in the bidding conditions, the bidding conditions include information related to the past payment history of the user related to the payment information.

[0048] The bidding condition acquisition unit 158, for example, provides the advertiser terminal device 70 with an interface for inputting bidding conditions, and acquires the bidding conditions via the interface. Fig. 16 is a diagram showing a screen IM1, which is an example of an interface screen provided to the advertiser terminal device 70. The screen IM1 is provided with, for example, an input window W1 for specifying advertising content by an advertising content ID or the like, an input window W2 for specifying a payment location, an input window W3 for specifying a store category, an input window W4 for specifying a payment time period, an input window W5 for specifying a payment frequency for each store category, an input window W6 for specifying a payment price range, an input window W7 for specifying a bid amount, a send button B1 for instructing transmission of the entered bidding conditions, etc. to the payment server 100, and the like.

[0049] Here, it is assumed that the advertising content itself has already been registered in the payment server 100 and has been assigned an advertising content ID and registered in the advertising content information 182 at the time of entering bidding conditions and the like on the interface screen, but the interface screen may have a function for accepting registration of advertising content. Also, the person who operates the interface screen on behalf of the advertiser will be referred to as the "advertiser" in the following description.

[0050] Input into the input windows W2 to W6 may be performed by manual text input, or input candidates (recommendation conditions) may be presented to the advertiser when the cursor is placed over the input window or when the advertiser taps on the input window, allowing the advertiser to select from the input candidates. Among the individual conditions, the location is specified at a granularity such as city, ward, town, village, nearest station, or shopping street name. Among the individual conditions, the payment frequency for each store category is specified, for example, as "once a week." Instead of the payment frequency for each store category, the total payment amount within a reference period, such as the total payment amount for each store category over the course of a year, may be specified.

[0051] By allowing users to specify such bidding conditions, advertisers can deliver advertising content by narrowing their target to "users who frequently make payments in a certain category in a specific commercial area." However, the number of combinations of payment location, store category, payment time period, payment frequency, and payment price range is enormous, and it can be difficult for advertisers to specify bidding conditions that will be highly effective in advertising.

[0052] Therefore, the bid condition proposal unit 160 proposes to the advertiser terminal device 70 bid conditions related to the payment behavior of a specific user group based on the segment information 178. More specifically, for example, the bid condition proposal unit 160 searches the segment information 178 using the location and store category of the advertiser's physical store, identifies a record with a large number of applicable users from records that match the location and store category, and proposes bid conditions based on the content of the identified record. For example, if the location of the advertiser's physical store is Chiyoda Ward and the store category is a sushi restaurant, the bid condition proposal unit 160 searches the segment information 178 using the location "Chiyoda Ward" and the store category "sushi restaurant," and identifies the record with segment ID "S001" with the largest number of applicable users from among the matching records. Next, the bidding condition proposing unit 160 proposes bidding conditions corresponding to the content of the identified record (for example, bidding condition 1 in FIG. 16, "Survey of 1,000 yen or more at a sushi restaurant in Chiyoda Ward between 11:00 and 12:00, at least once a week") on the screen IM1. When the advertiser clicks the button B2 corresponding to bidding condition 1, the bidding condition proposing unit 160 sets the content of bidding condition 1 in input boxes W1 to W6 on the screen IM1. In this way, by proposing bidding conditions based on the content of records with a large number of matched users among records in the segment information 178 that match the location and store category, the advertiser can set more effective bidding conditions.

[0053] While FIG. 16 illustrates a case where a store category is set in input box W3, it is also possible to set, in more detail, the name of an individual store registered with the electronic payment service as a bidding condition. In this case, the bidding condition proposal unit 160 may propose setting an individual store name as a bidding condition. For example, when an advertiser of a sushi restaurant with store ID "001" in FIG. 7 sets bidding conditions, the bidding condition proposal unit 160 may propose that the bidding condition be "a transaction of 1,000 yen or more at least once a week between 11:00 and 12:00 at sushi restaurants with store ID "007" and "010" in Chiyoda Ward." In this case, the advertiser can further enhance the promotional effectiveness of advertising content by pinpointing the user terminal devices 10 of users who make payments at competing stores.

[0054] 16, only the content of the bidding conditions proposed based on the segment information 178 is displayed. In addition, an estimated number of users who fall under the proposed bidding conditions may be displayed based on the "number of applicable users" in the segment information 178. This allows the advertiser to set the bidding conditions and bid amount while quantitatively assessing the advertising effectiveness of the bid.

[0055] When the payment information is acquired by the payment information acquisition unit 152, the advertising content providing unit 156 extracts advertising content for which the payment information matches the bidding conditions. Then, the advertising content providing unit 156 performs processing to display advertising content selected from the extracted advertising content based on predetermined criteria on the user terminal device 10 of the user associated with the payment information.

[0056] The advertising content providing unit 156 selects advertising content, for example, by second pricing based on the bid amount. For example, if advertisers C1, C2, and C3 bid 150 yen, 250 yen, and 270 yen, respectively, advertiser C3, who submitted the highest bid, wins the bid at 251 yen, which is one unit higher than the second-highest bid of 250 yen, and the advertising content of advertiser C3 is delivered. Alternatively, advertising content may be selected based on a criterion similar to eCPM. For example, a criterion such as second pricing may be applied to a value obtained by multiplying the bid amount by the number (or percentage) of payments made via an electronic payment service or coupons used after the user selected the advertising content.

[0057] FIG. 17 is a diagram showing an example of the contents of the advertising bidding information 184. The bidding condition acquisition unit 158 ​​updates the advertising bidding information 184 based on the information entered on the interface screen IM1. The advertising bidding information 184, for example, associates an advertiser ID, which is the advertiser's identification information, with information such as an advertising content ID, bidding conditions, bid amount, and bidding period. The bidding period may be set as "until a separate cancellation notice is received." As shown in the figure, the same advertiser may bid on multiple advertising contents.

[0058] [Processing flow] 18 is a flowchart showing an example of the flow of processing executed by the payment server 100. First, the payment content providing unit 120 and the advertisement distribution unit 150 each determine whether the payment server 100 has received payment information (S200). The payment processing unit 130 performs payment processing based on the payment information (S202).

[0059] In parallel, the payment information acquisition unit 152 of the advertisement distribution unit 150 acquires the received payment information and also acquires the past payment history of the user (the user related to the payment information) from the user information 172 (S206).

[0060] Next, the advertising content providing unit 156 of the advertising distribution unit 150 searches the advertising bidding information 184, extracts advertising content IDs that match (apply to) the information acquired in S206 with the bidding conditions (S208), and selects an advertising content ID by a method such as second pricing according to the bid amount, etc. (S210). Then, the advertising content providing unit 156 acquires location information of the selected advertising content ID from the advertising content information 182 and notifies the payment content providing unit 120 (S212).

[0061] The payment content providing unit 120 includes the location information notified from the advertising content providing unit 156 in a payment completion screen and displays it on the user terminal device 10 (S204).

[0062] According to the process described above, bidding conditions related to the payment behavior of a specific user group are proposed to the advertiser based on segment information 178 that matches the location and store category of the physical store advertiser. This reduces the burden on the advertiser of determining the combination of payment location, store category, payment time zone, payment frequency, payment price range, etc. as bidding conditions, and allows the advertiser to set bidding conditions that are more effective in advertising.

[0063] [Second embodiment] In the above-described embodiment and modified examples, combinations of items such as payment location, store category, payment time zone, payment frequency, and payment price range that have a large number of matching people are defined as segments, and advertising content is delivered to users whose payment history information is similar to that of each segment. On the other hand, in the second embodiment, payment history information of users who meet desired conditions from combinations of items such as payment location, store category, payment time zone, payment frequency, and payment price range is used as learning data to generate a machine learning model using a technique such as deep learning, and the payment history information of any user is input into the generated machine learning model to determine the degree of similarity with the conditions, and advertising content is delivered to users who are determined to be similar to the conditions.

[0064] Fig. 19 is a configuration diagram of a payment server 100B according to the second embodiment. The payment server 100B includes an advertising target extraction unit 154B instead of the segment information generation unit 154 of the payment server 100A shown in Fig. 19, a trained model 178B instead of the segment information 178, and advertising bidding information 184B instead of the advertising bidding information 184.

[0065] FIG. 20 is a diagram illustrating an example of the contents of trained model 178B. FIG. 20 illustrates trained model 178B, which has been machine-learned to use payment history information of a user that satisfies the following conditions: "Chiyoda Ward" as the payment location, "sushi restaurant" as the store category, and "once a week" as the payment frequency, as input parameters, and to output 1 as the output parameter for the item corresponding to a probability of "90% or more." In FIG. 20, the output probability is set to one of ten values: "0% or more but less than 10%," "10% or more but less than 20%," "20% or more but less than 30%," "30% or more but less than 40%," "40% or more but less than 50%," "50% or more but less than 60%," "60% or more but less than 70%," "70% or more but less than 80%," "80% or more but less than 90%, and "90% or more." However, the present invention is not limited to such a configuration, and it is sufficient that the model is set to output at least two or more values ​​indicating whether or not the value is similar to the set conditions. Multiple patterns of such trained model 178B are generated in advance by changing settings such as payment location, store category, payment time period, payment frequency, and payment price range.

[0066] For example, the advertisement target extraction unit 154B inputs payment history information of a user who registers with an electronic payment service into the trained model 178B and determines whether the user is similar to a user who satisfies the following conditions: payment location is "Chiyoda Ward," store category is "sushi restaurant," and payment frequency is "once a week." The advertisement target extraction unit 154B can determine that a user whose payment history information outputs the maximum value for the items "80% or more but less than 90%" or "90% or more" is a similar user. In other words, a similar user in this case can also be expressed as a user who satisfies the above conditions in an "expanded" sense.

[0067] 21 is a diagram showing a screen IM2, which is an example of an interface screen provided to the advertiser terminal device 70. In addition to the items defined in the screen IM1 of FIG. 16, the screen IM2 has an input window W8 for specifying the acceptable similarity with the bidding conditions to which the advertising content is to be delivered. That is, when the acceptable similarity is specified in the input window W8, the advertising content corresponding to the advertising content ID of the bidding conditions is delivered not only to users who satisfy the bidding conditions (i.e., are 100% similar), but also to users who are determined to have a similarity with the bidding conditions that is equal to or greater than the acceptable similarity, based on the trained model 178B.

[0068] For example, in the example shown in FIG. 21, the bidding conditions are set as payment location "Chiyoda-ku," store category "sushi restaurant," and payment frequency "once a week," and the similarity is set as "70%." In this case, the same advertising content is delivered not only to users who satisfy the bidding conditions but also to users whose payment history information indicates that the output value of the trained model 178B corresponding to the bidding conditions is the maximum value in any of the following categories: "70% or more but less than 80%," "80% or more but less than 90%," or "90% or more." With this configuration, even if the number of users who satisfy the set bidding conditions is small, advertising can be delivered to a larger number of users by expanding the distribution of advertising content to users similar to the users who satisfy the bidding conditions.

[0069] Furthermore, the number of users who meet the bidding conditions and similarity levels set by the advertiser may be displayed on screen IM2 as shown in Fig. 21. This allows the advertiser to set the bidding conditions and similarity levels while balancing the number of people to whom the advertisement is to be distributed and the narrowing down of the target by setting the bidding conditions and similarity levels in detail.

[0070] 22 is a diagram showing an example of the contents of advertising bidding information 184B. In advertising bidding information 184B, for example, an advertiser ID, which is identification information of an advertiser, is associated with information such as an advertising content ID, bidding conditions, similarity, bid amount, and bidding period. Bidding conditions acquisition unit 158 ​​updates advertising bidding information 184 based on the information entered on interface screen IM2.

[0071] The advertising target extraction unit 154B inputs payment history information of users who register with the electronic payment service into the trained model 178B and extracts users who satisfy the bidding conditions defined in the advertising bidding information 184B. The advertising content providing unit 156 performs processing to display advertising content corresponding to the advertising content ID of the bidding conditions on the user terminal device 10 of the extracted user. When advertising content is delivered based on the system's determination rather than through bidding, the advertising content providing unit 156 may deliver the same advertising content to users whose similarity is, for example, 80% or more, in addition to users who satisfy preset delivery conditions. Furthermore, for example, when the number of users who satisfy the preset delivery conditions is less than a threshold, the advertising content providing unit 156 may increase the number of users to whom advertising content is delivered by reducing the allowable similarity from 100% until the number of users becomes equal to or greater than the threshold.

[0072] According to the process described above, a machine learning model is generated using payment history information of users who satisfy desired conditions as learning data, and the payment history information of any user is input into the generated machine learning model to determine the degree of similarity with the conditions, and advertising content is delivered to users who are determined to be similar to the conditions. This makes it possible to appropriately deliver advertisements that match the user's behavioral habits and preferences.

[0073] The above describes the form for carrying out the present invention using an embodiment, but the present invention is not limited to such an embodiment, and various modifications and substitutions can be made within the scope that does not deviate from the gist of the present invention. [Explanation of symbols]

[0074] 10 User terminal device 20. Payment App 50 Store terminal equipment 60 Store Code Image 70 Advertiser terminal device 100 Payment Server 120 Payment Contents Department 130 Payment processing unit 150 Advertising distribution unit (advertising distribution device) 152 Payment Information Acquisition Department 154 Segment information generation unit 156 Advertising Content Provider 158 Bidding Conditions Acquisition Department 160 Bidding Conditions Proposal Department 170 Storage section 172 User Information 174 Payment Content Information 176 Store Information 178 Segment Information 180 Advertisement Delivery Conditions 182 Advertising Content Information 184 Advertising Bidding Information

Claims

1. a payment information acquisition unit that acquires payment information of a user of the electronic payment service; a similarity determination unit that uses the payment information history as input and determines whether the payment behavior of the user is similar to the payment behavior of a specific user group using a trained model that has been machine-learned to output a similarity to the payment behavior of a specific user group; an advertising content providing unit that, when it is determined that the payment behavior of the user is similar to the payment behavior of the specific user group, provides advertising content related to the payment behavior of the specific user group to a user terminal device of the user; Advertisement delivery device.

2. the electronic payment service processes payments for purchases at physical stores; The trained model is a model trained using features including at least one of a payment location, a store category, a payment time period, a payment frequency, and a payment price range of the physical store. The advertisement distribution device according to claim 1 .

3. The similarity determination unit determines that the payment behavior of the user is similar to the payment behavior of the specific user group when the similarity output from the trained model is equal to or greater than a threshold. The advertisement distribution device according to claim 1 .

4. the advertising content providing unit provides the advertising content to the user terminal device by including it in a payment completion screen of the electronic payment made by the user. The advertisement distribution device according to claim 1 .

5. a payment information acquisition unit that acquires payment information of a user of the electronic payment service; a reception unit that receives a threshold value for determining the similarity of payment behavior with a specific user group; a similarity determination unit that uses a trained model that has been machine-learned to input the payment information history and output a similarity to the specific user group, and determines that the payment behavior of the user is similar to the payment behavior of the specific user group if the output similarity is equal to or greater than the threshold value; Judgment device.

6. and an advertising content providing unit that, when it is determined that the payment behavior of the user is similar to the payment behavior of the specific user group, provides advertising content related to the payment behavior of the specific user group to a user terminal device of the user. The determination device according to claim 5 .

7. the receiving unit receives a designation of the threshold value from an advertiser terminal device used by an advertiser of the advertising content; The determination device according to claim 6.

8. the advertising content providing unit calculates the number of users of the electronic payment service whose output similarity is equal to or greater than the threshold, and provides the number to the advertiser terminal device; The determination device according to claim 7 .

9. The computer Obtain payment information of users of electronic payment services, Using a trained model that has been machine-learned to input the payment information history and output a similarity to a specific user group, it is determined whether the payment behavior of the user is similar to the payment behavior of the specific user group; When it is determined that the payment behavior of the user is similar to the payment behavior of the specific user group, advertising content related to the payment behavior of the specific user group is provided to the user terminal device of the user. Ad delivery methods.

10. The computer Obtain payment information of users of electronic payment services, Accept a threshold value for determining the similarity of payment behavior with a specific user group; Using a trained model that has been machine-learned to input the payment information history and output a similarity to the specific user group, if the output similarity is equal to or greater than the threshold, it is determined that the user's payment behavior is similar to the payment behavior of the specific user group. Judgment method.

11. On the computer, Acquire payment information of users of electronic payment services, Using a trained model that has been machine-learned to input the payment information history and output a similarity to a specific user group, determine whether the payment behavior of the user is similar to the payment behavior of the specific user group; When it is determined that the payment behavior of the user is similar to the payment behavior of the specific user group, causing a user terminal device of the user to provide advertising content related to the payment behavior of the specific user group. program.

12. On the computer, Acquire payment information of users of electronic payment services, Accepting a threshold value for determining the similarity of payment behavior with a specific user group; a trained model that has been machine-learned to input the payment information history and output a similarity to the specific user group, and if the output similarity is equal to or greater than the threshold, determine that the user's payment behavior is similar to the payment behavior of the specific user group; program.

Images