Proposed system, proposed method, and program

Abstract

We will make effective proposals regarding merchants who accept payment services. [Solution] The address information acquisition unit (101) of the proposed system (1) acquires address information for each of the addresses of multiple users who visit a participating store of a predetermined service and use the service. The score calculation unit (102) calculates a score for each mesh in a region divided into multiple meshes, based on the address information of each of the multiple users, based on the number of users whose address is in that mesh. The proposal unit (103) makes a proposal regarding participating stores based on the score calculated for each mesh.

Description

Technical Field

[0001] The present disclosure relates to a proposal system, a proposal method, and a program.

Background Art

[0002] Conventionally, payment services to which various franchise stores subscribe are known. For example, Patent Document 1 describes an advertisement effect confirmation device that confirms the purchase status of target products shown in targeted advertisements based on credit card payment data and franchise store purchase data. Patent Document 2 describes a store advice method for providing advice such as enhancing customer attraction by specifying, on a map, the area covering the addresses of each of a plurality of customers who visit a franchise store and digitizing the number of customers and households residing in the area for each area.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, although the advertisement effect confirmation device of Patent Document 1 can allow a franchise store to confirm the advertisement effect of a targeted advertisement, it does not make proposals regarding the franchise store, so the convenience of the franchise store could not be sufficiently enhanced. The store advice method of Patent Document 2 can provide advice such as enhancing customer attraction based on the number of customers and households in each area, but since it is not a proposal according to customer usage, effective proposals could not be made.

[0005] One of the purposes of this disclosure is to provide effective suggestions regarding merchants participating in payment services. However, the purposes of this disclosure are not limited to this purpose. [Means for solving the problem]

[0006] The proposal system relating to this disclosure includes: an address information acquisition unit that acquires address information relating to the addresses of multiple users who visit a participating store of a predetermined service and use the service; a score calculation unit that calculates a score based on the number of users whose addresses are located in a mesh in a region divided into multiple meshes, based on the address information of each of the multiple users; and a proposal unit that makes a proposal relating to the participating store based on the score calculated for each mesh. [Effects of the Invention]

[0007] This disclosure can provide effective suggestions regarding merchants participating in payment services. [Brief explanation of the drawing]

[0008] [Figure 1] This figure shows an example of the hardware configuration of the proposed system. [Figure 2] This figure shows an example of a user using payment services at a participating merchant. [Figure 3] This figure shows an example of the functions that will be implemented in the proposed system. [Figure 4] This is a diagram showing an example of a merchant database. [Figure 5] This figure shows an example of a user database. [Figure 6] This figure shows an example of how the score is calculated. [Figure 7] This figure shows an example of the process performed by the proposed system. [Figure 8] This figure shows an example of a function that can be achieved through modification. [Figure 9] This figure shows an example of a location proposed in Modification 6. [Figure 10]This figure shows an example of the input and output of the learning model in Modification Example 9. [Modes for carrying out the invention]

[0009] [1. Hardware configuration of the proposed system] An example of an embodiment of the proposed system, method, and program related to this disclosure will be described. Figure 1 is a diagram showing an example of the hardware configuration of the proposed system. For example, proposed system 1 includes a server 10, a merchant terminal 20, and a user terminal 30. Each of the server 10, merchant terminal 20, and user terminal 30 is connected to a network N such as the Internet or a LAN. Note that there may be multiple units of at least one of the server 10, merchant terminal 20, and user terminal 30.

[0010] Server 10 is a server computer for a predetermined service. The predetermined service is a service provided at a merchant visited by a user. In this embodiment, a payment service is described as an example of a predetermined service. The payment service is a service that provides electronic payment (cashless payment) to the user. In this embodiment, the case in which a card company that issues credit cards provides the payment service is given as an example. That is, a payment service provided by a card company is described as an example of a payment service.

[0011] It should be noted that the payment service is not limited to the examples of this embodiment. The payment service may be a service provided by a business other than a card company. For example, the payment service may be a type that uses a card other than a credit card (e.g., a debit card or a transportation card), a type that uses a means other than a card (e.g., electronic money, a balance not classified as electronic money, a code such as a barcode or two-dimensional code, an account at a financial institution such as a bank, or crypto assets), a type called carrier payment provided by a telecommunications company, a type that uses an ID that can identify the user, a type that uses the IC chip of the user terminal 30, a type that is completed solely by biometric authentication, or other types.

[0012] Furthermore, the specified service is not limited to the example of this embodiment. The specified service may be a service used by a user when visiting a merchant. The specified service may be a service other than a payment service. For example, the specified service may be a check-in service for a user to check into a merchant they have visited, a communication service for a user to apply for communication equipment at a merchant they have visited, or another service. Where the payment service is described as an example in this embodiment, it can be read as a specified service that includes these other services.

[0013] For example, server 10 includes a control unit 11, a storage unit 12, and a communication unit 13. The control unit 11 includes at least one processor. The storage unit 12 includes at least one of volatile memory such as RAM and non-volatile memory such as flash memory. The communication unit 13 includes at least one of a communication interface for wired communication and a communication interface for wireless communication.

[0014] The merchant terminal 20 is a computer belonging to a merchant participating in the payment service. In this embodiment, we take the example of a store that handles goods or services as the merchant, but a merchant is not limited to a store. That is, although the word "merchant" includes the character for "store," it does not necessarily have to be a store. A merchant can be any facility or organization that is generally referred to as a merchant in a payment service. For example, a merchant may be a complex, a public facility, a train station, an airport, an event venue, a hospital, another facility, a beverage manufacturer that installs vending machines, or another organization. Users actually visit the location where the merchant terminal 20 is located and use the payment service.

[0015] For example, the franchise terminal 20 is a POS terminal, a self-checkout terminal, a vending machine, a personal computer, a smartphone, a tablet, or other payment terminal. The franchise terminal 20 includes a control unit 21, a memory unit 22, a communication unit 23, an operation unit 24, a display unit 25, and a reading unit 26. The hardware configurations of the control unit 21, the memory unit 22, and the communication unit 23 may be the same as those of the control unit 11, the memory unit 12, and the communication unit 13, respectively. The operation unit 24 is an input device such as a touch panel or a mouse. The display unit 25 is a display such as a liquid crystal or an organic EL. The reading unit 26 is a device that reads payment means used in the payment service. For example, the reading unit 26 is a card reader, a code reader, a reader / writer, or a camera.

[0016] The user terminal 30 is a user's computer that uses the payment service. For example, the user terminal 30 is a smartphone, a tablet, a personal computer, or a wearable terminal. The user terminal 30 includes a control unit 31, a memory unit 32, a communication unit 33, an operation unit 34, and a display unit 35. The hardware configurations of the control unit 31, the memory unit 32, the communication unit 33, the operation unit 34, and the display unit 35 may be the same as those of the control unit 21, the memory unit 22, the communication unit 23, the operation unit 24, and the display unit 25, respectively.

[0017] Note that the programs stored in the memory units 12, 22, and 32 may be supplied to the server 10, the franchise terminal 20, or the user terminal 30 via the network N. Further, at least one of a reading unit (for example, a memory card slot) that reads a computer-readable information storage medium and an input / output unit (for example, a USB port) for inputting / outputting data with an external device may be included in the server 10, the franchise terminal 20, or the user terminal 30. For example, a program stored in the information storage medium may be supplied to the server 10, the franchise terminal 20, or the user terminal 30 via at least one of the reading unit and the input / output unit.

[0018] Furthermore, proposed system 1 may include at least one computer. The computers included in proposed system 1 are not limited to the example in Figure 1. For example, proposed system 1 may include only server 10. In this case, the merchant terminal 20 and user terminal 30 are located outside of proposed system 1. Proposed system 1 may include server 10 and other computers not shown in Figure 1 (for example, a personal computer of a business operator providing payment services). Proposed system 1 may not include server 10 and may include only other computers not shown in Figure 1.

[0019] [2. Overview of the proposed system] In this embodiment, the proposed system 1 delivers advertisements about specific merchants to a subset of all users of the payment service. This method of delivering advertisements is sometimes called targeted advertising. The advertisements may be aimed at promoting specific products or services handled by the merchants, or they may be aimed at promoting the merchants themselves, rather than specific products or services. Hereafter, when simply referred to as "merchants," it generally means the merchants advertised in the advertisements.

[0020] Figure 2 shows an example of a user using a payment service at a participating merchant. The squares in Figure 2 represent meshes. A mesh is an area used to demarcate regions for statistical information aggregation. A mesh can also be called a parcel. A mesh may demarcate regions on a map, or it may be an area unrelated to a map. A mesh is sometimes called a regional mesh. A mesh may be the same as a known mesh used in statistics. In this embodiment, we take the example where all meshes are the same size and shape, but at least one of the size and shape may differ between one mesh and another.

[0021] In the example in Figure 2, users U1 to U4 whose addresses are within the mesh are shown. In the example in Figure 2, merchants S1 to S3 are located outside the mesh, but merchants S1 to S3 may also be located within the mesh. User U1 has used payment services at merchants S2 and S3. User U2 has used payment services at merchants S1 to S3. User U3 has used payment services at merchant S2. User U4 has used payment services at merchant S3. It is possible to determine which of merchants S1 to S3 each user U1 to U4 used from their payment service usage history.

[0022] In the example in Figure 2, since merchant S1 is only used by user U2, the mesh in Figure 2 may not represent merchant S1's service area. Therefore, even if advertisements for merchant S1 are delivered to users U1-U4, the advertising may not be very effective. For example, even if advertisements for merchant S1 are delivered to users U1, U3, and U4 who have never used merchant S1, users U1, U3, and U4 may not use merchant S1. Similarly, user U2 may have only used merchant S1 once by chance and may not be interested in advertisements for merchant S1.

[0023] On the other hand, in the example in Figure 2, since merchant S2 is used by users U1 to U3, the mesh in Figure 2 may represent the trading area of ​​merchant S2. Therefore, if advertisements for merchant S2 are delivered to users U1 to U4, the advertising may be highly effective. For example, if advertisements for merchant S2 are delivered to user U4, who has never used merchant S2, user U4 may become interested in the advertisement and use merchant S2. In other words, user U4 may be a potential customer of merchant S2. Users U1 to U3, who have used merchant S2 before, may also become interested in the advertisements for merchant S2 and use merchant S2 again.

[0024] In the example in Figure 2, merchant S3 is also used by users U1, U2, and U4, so the mesh in Figure 2 may represent merchant S3's service area. Therefore, if advertisements for merchant S3 are delivered to users U1-U4, the advertising may be highly effective. For example, if an advertisement for merchant S3 is delivered to user U3, who has never used merchant S3, user U3 may become interested in the advertisement and use merchant S3. In other words, user U3 may be a potential customer of merchant S3. Users U1, U2, and U4, who have used merchant S3 before, may also become interested in the advertisement for merchant S3 and use merchant S3 again.

[0025] In this embodiment, the proposed system 1 identifies which users used the payment service at which merchants based on their payment service usage history. The proposed system 1 analyzes which mesh the address of a user who used the payment service at a particular merchant falls into, and calculates a score for each mesh to estimate the merchant's trading area. Based on the score calculated for each mesh, the proposed system 1 determines the target users to whom the merchant's advertisements should be delivered, thereby achieving effective advertisement delivery. The details of the proposed system 1 will be described below.

[0026] [3. Functions to be implemented in the proposed system] Figure 3 shows an example of the functions realized by the proposed system 1. The various components realized by the proposed system 1 in this embodiment can be configured by combining them into a single device or by further distributing them among multiple devices.

[0027] Figure 3 shows the functions implemented by the server 10 among the functions implemented in the proposed system 1. For example, the server 10 includes a data storage unit 100, an address information acquisition unit 101, a score calculation unit 102, and a proposal unit 103. The data storage unit 100 is implemented by the storage unit 12. The address information acquisition unit 101, the score calculation unit 102, and the proposal unit 103 are each implemented by the control unit 11.

[0028] [3-1. Data Storage Unit] The data storage unit 100 stores various data necessary for processing in this embodiment. For example, the data storage unit 100 stores the merchant database DB1 and the user database DB2.

[0029] Figure 4 shows an example of the merchant database DB1. The merchant database DB1 is a database that stores various information about each of multiple merchants. For example, the merchant database DB1 stores merchant ID, name information, address information, score information, advertising information, and target user information. Other information may also be stored in the merchant database DB1. For example, the merchant database DB1 may store user information about users who have used payment services at each of the multiple merchants.

[0030] A merchant ID is an example of merchant identification information that can identify a merchant. Merchant identification information may be other information besides the merchant ID. A merchant may be identified by information other than the merchant ID. For example, merchant identification information may represent the merchant's email address, the merchant's telephone number, the merchant's name, the merchant's address, the merchant's latitude and longitude, the merchant's coordinates, or other information. Name information is information about the merchant's name. For example, name information includes a string that represents the merchant's name.

[0031] Address information is information relating to the address of a merchant. For example, address information includes at least one of the postal code of the location where the merchant is located and a string indicating the specific address of that location. Multiple pieces of address information may be stored in the merchant database DB1 for a single merchant. For example, address information of the actual location where a store or other facility exists (i.e., the place that a user actually visits) may be stored in the merchant database DB1 as the merchant's address information. In this case, the area near the address indicated by the merchant's address information may constitute the merchant's trading area. The merchant's address information may be a postal code, a string indicating the address, or a combination thereof. The merchant's address information may also be information in which the address has been converted to latitude, longitude, or coordinates. The merchant's address information may also be other information relating to the merchant's address.

[0032] For example, the address information of the headquarters or business office of the organization operating the merchant (i.e., a place that users do not actually visit) may be stored in the merchant database DB1 as the merchant's address information. In this case, the area around the address indicated by the merchant's address information may not be within the merchant's service area. The payment service provider may not be able to identify the merchant's service area by looking only at the merchant's address information. Similarly, if the merchant's address information is not stored in the merchant database DB1, the payment service provider may not be able to identify the merchant's service area.

[0033] The score information is information about the score calculated by the score calculation unit 102, which will be described later. Details of the score will be described later. The score information shows the score for each of the multiple meshes. For example, the score information shows the mesh ID and the score for each of the multiple meshes. The mesh ID is an example of mesh identification information that can identify a mesh. The mesh identification information may be other information besides the mesh ID. For example, the mesh identification information may show the address of the mesh, the latitude and longitude of the mesh, the coordinates of the mesh, the name of the mesh, or other information.

[0034] Advertising information is information about the advertisements of participating merchants. Advertising information indicates the specific content of the advertisement. Advertising information may indicate the content of advertisements for specific products or services handled by the participating merchant, or it may indicate the content of advertisements for the participating merchant itself, rather than for specific products or services. Advertising information may indicate benefits to the user (e.g., coupons or campaigns). Advertising information may be in any format used in publicly known advertisements. For example, advertising information may be a file in the form of text, images, videos, HTML or other markup language formats, or a combination thereof.

[0035] Targeted user information is information about users who are targeted for advertising. Targeted users are users who are targeted for advertising. Targeted user information may directly identify targeted users or indirectly identify them. Targeted user information may represent a subset of all users who use the payment service. For example, targeted user information may represent the user ID described below, or the mesh ID described below. If the targeted user information represents the mesh ID, users whose address is in the mesh identified by the mesh ID will be considered targeted users.

[0036] Figure 5 shows an example of a user database DB2. For example, the user database DB2 stores user ID, login account, password, credit card information, address information, and usage history information. The information stored in the user database DB2 is not limited to the example in Figure 5. Other information may be stored in the user database DB2. For example, the user database DB2 may store at least one of the behavior information, browsing information, and entry information, which will be explained in the modified examples below. The user database DB2 may also store destination information related to the delivery of advertisements (for example, email address, phone number, messaging app account, or SNS account).

[0037] A user ID is an example of user identification information that can identify a user. A login account is also an example of user identification information. A login account is user identification information that a user enters to log in to a payment service. The login account may be freely changed by the user. A user ID is user identification information that is managed separately from the login account. In this embodiment, we take the example of a case where there is a login account separate from the user ID (where there are at least two pieces of user identification information), but there may be only one piece of user identification information. In other words, the user ID and the login account do not have to be separated.

[0038] A password is authentication information verified during login. At least one of the login account and password may be the user's biometric information. Credit card information is information about the credit cards the user owns. For example, credit card information includes the credit card number, expiration date, and cardholder name. If a user owns multiple credit cards, the user ID of that user will be associated with the credit card information of each of those credit cards. Credit card information may also correspond to user identification information.

[0039] Address information is information about the address registered by the user with the payment service. In this embodiment, an example is given where the address information indicates the address to which mail from the payment service is delivered. For example, the address information indicates the user's home address. The business operator running the payment service mails the mail to the address indicated by the address information. Multiple pieces of address information may be stored in the user database DB2 for a single user. For example, address information indicating the user's home address and address information indicating the user's work address may be stored in the user database DB2. The address information may also be an address to which mail is not specifically delivered. The user's address information may be a postal code, a string indicating the address, or a combination thereof. The user's address information may also be information in which the address has been converted to latitude, longitude, or coordinates. The user's address information may also be other information related to the user's address.

[0040] Usage history information is information about a user's usage history of payment services. For example, usage history information may show the date and time of use, the merchant used, the amount used, or a combination of these. When a user uses a payment service at a merchant, server 10 updates the user's usage history information to show the current date and time of use, the merchant ID of the merchant, and the amount used. Usage history information may also show the goods or services that were paid for. If a user has multiple credit cards, the usage history information for each of those credit cards is associated with the user's user ID.

[0041] The data stored in the data storage unit 100 is not limited to the examples above. The data storage unit 100 may also store other data necessary for calculating the score. For example, the data storage unit 100 may store data showing the score calculation formula. The data storage unit 100 may also store latitude and longitude data showing the relationship between address and latitude and longitude. In the score calculation described later, the user's address may be converted to latitude and longitude based on the latitude and longitude data.

[0042] For example, the data storage unit 100 may store a mesh database containing various information about each of a plurality of meshes. The mesh database may store mesh IDs, mesh names, mesh location information, mesh size information, and mesh shape information. The mesh database may be similar to databases used in various services such as well-known map services or administrative services.

[0043] [3-2. Address Information Acquisition Section] The address information acquisition unit 101 acquires address information for each of the multiple users who have visited a merchant that is a member of the payment service and used the payment service. When a user visits a merchant, it means that the user goes to the location where the merchant is located. A user who has visited a merchant and used the payment service is a user who has used the payment service to pay for goods or services handled by the merchant. In this embodiment, since the card company uses the payment service, a user who uses a credit card issued by the card company at a merchant is considered a user who has visited a merchant and used the payment service. Even if a user actually visits the location where the merchant is located, a user who makes a payment without using the payment service at the merchant is not considered a user who has used the payment service at the merchant.

[0044] In this embodiment, the merchants where users have used the payment service are indicated in the usage history information. Therefore, the address information acquisition unit 101 identifies which user used the payment service at which merchant based on the usage history information of each of the multiple users stored in the user database DB2. Based on the usage history information of each of the multiple users, the address information acquisition unit 101 identifies multiple users who have used the payment service at the merchants to be processed. The merchants to be processed are the merchants for which the score is calculated. The merchants to be processed can also be defined as the merchants where the users for whom address information is to be acquired have used the payment service. The address information acquisition unit 101 acquires the address information of each of the multiple users who have used the payment service at the merchants to be processed.

[0045] The address information acquisition unit 101 may identify multiple users who visited the merchant and used the payment service based on usage history information for the entire past period, or it may identify multiple users who visited the merchant and used the payment service based on usage history information for a specific period in the past. For example, the address information acquisition unit 101 may identify multiple users who visited the merchant and used the payment service based on usage history information for a predetermined period in the most recent time (for example, the last year).

[0046] In this embodiment, since address information is stored in the user database DB2, the address information acquisition unit 101 acquires the address information of each of the multiple users who used the payment service at the merchant to be processed from the user database DB2. The address information may also be stored in a database other than the user database DB2, a computer other than the server 10, or an information storage medium. The address information acquisition unit 101 may acquire the address information of each of the multiple users who used the payment service at the merchant to be processed from the other database, another computer, or an information storage medium.

[0047] The method by which the address information acquisition unit 101 identifies multiple users who have used the payment service at the merchant to be processed is not limited to the example of this embodiment. The usage history information may be stored in a database other than the user database DB2 (for example, a database dedicated to usage history information), a computer other than the server 10, or an information storage medium. The address information acquisition unit 101 may identify multiple users who have used the payment service at the merchant to be processed based on the usage history information stored in the other database, the other computer, or the information storage medium. For example, if payment history information relating to the history of payments made at each of the multiple merchants is stored in the merchant database DB1, the address information acquisition unit 101 may identify multiple users who have used the payment service at the merchant to be processed based on the payment history information stored in the merchant database DB1.

[0048] For example, if there are multiple merchants to be processed, the address information acquisition unit 101 acquires the address information of each of the multiple users who used the payment service at each of the multiple merchants to be processed. The merchants to be processed may be all merchants of the payment service or some of them. For each merchant to be processed, the address information acquisition unit 101 acquires the address information of each of the multiple users who used the payment service at that merchant.

[0049] For example, if multiple address information is associated with a single user, the address information acquisition unit 101 may acquire all of the multiple address information associated with that single user, or it may acquire only some of the address information. For example, if a single user is associated with both a home address and a work address, the address information acquisition unit 101 may acquire both of these address information, or it may acquire only one of them. If the work address is old and the home address is considered to be more reliable, the address information acquisition unit 101 may acquire only the home address information. Even if the work address is old and the home address is considered to be more reliable, the address information acquisition unit 101 may acquire both address information. In this case, in the score calculation by the score calculation unit 102, the coefficient for the work address may be lower than the coefficient for the home address.

[0050] [3-3. Score Calculation Section] The score calculation unit 102 calculates a score for each mesh in a region divided into multiple meshes, based on the address information of each of the multiple users, based on the number of users who have an address in that mesh. For each merchant to be processed, the score calculation unit 102 calculates a score based on the number of users who have an address in each of the multiple meshes, based on the address information of each of the multiple users who visited the merchant and used the payment service.

[0051] In the example shown in Figure 2, the mesh is square, but the shape of the mesh can be any shape. The shape of the mesh is not limited to the example of this embodiment. For example, the mesh may be a quadrilateral such as a rectangle or rhombus, a polygon other than a quadrilateral, a circle, an ellipse, or any other shape. The size of the mesh can also be any size. Multiple mesh shapes and multiple mesh sizes may be mixed together. At least one of the mesh shape and size may differ depending on the region.

[0052] In this embodiment, we take the example of a case where the entire country of Japan is divided into meshes. That is, the regions shown on the map of Japan are divided into meshes. The regions divided into meshes are not limited to the example of this embodiment. The regions divided into meshes may be any region. For example, a part of Japan may be divided into meshes. All or part of another country other than Japan may be divided into meshes. Regions that are not classified as countries may be divided into meshes.

[0053] For example, the score calculation unit 102 aggregates the number of users whose addresses, as indicated by the address information, are included in each mesh. The score calculation unit 102 may convert the addresses indicated by the address information into latitude and longitude coordinates and then determine whether or not those latitude and longitude coordinates are included in the mesh. If other information (e.g., coordinates) is used, the score calculation unit 102 may convert the addresses indicated by the address information into other information and then determine whether or not that other information is included in the mesh.

[0054] The score calculation unit 102 may also choose to aggregate only the meshes that are within a predetermined distance from the merchant being processed. The score calculation unit 102 may obtain the aggregation result (the number of users whose addresses are included in the mesh) as the score, or it may perform a separate process to calculate the score based on the aggregation result. The score calculation unit 102 performs the same process for each of the multiple merchants and calculates the score for each mesh of each of the multiple merchants.

[0055] Figure 6 shows an example of how the score is calculated. In this embodiment, the self-mesh score and the surrounding mesh score are calculated as examples of the score. Hereafter, unless otherwise specified, the self-mesh score and the surrounding mesh score will simply be referred to as the score. In the example in Figure 6, 24 meshes are shown in a 4x5 grid. In the upper left example of Figure 6, there are 3 users who used the merchant being processed in the mesh in the 2nd column of the 1st row. There are 2 users who used the merchant being processed in the mesh in the 3rd column of the 2nd row. There is 1 user who used the merchant being processed in the mesh in the 4th column of the 2nd row. There is 1 user who used the merchant being processed in the mesh in the 5th column of the 4th row.

[0056] For example, as shown in the upper right of Figure 6, the score calculation unit 102 aggregates the number of users whose addresses are located in each mesh, and calculates its own mesh score, which represents the number of such users in that mesh, as the score for that mesh. Having an address in a mesh means that an address is included within the mesh. The score calculation unit 102 obtains the number of users who have used the merchants to be processed as its own mesh score. For each merchant to be processed, the score calculation unit 102 calculates its own mesh score for each of the multiple meshes, associates it with the merchant ID of the merchant, and stores the score information of the own mesh score in the merchant database DB1.

[0057] In the upper right example of Figure 6, the score calculation unit 102 obtains 3 as the self-mesh score for the mesh in the second column of the first row, which is the number of users who have an address in that mesh among the multiple users who visited the target merchant and used the payment service. The score calculation unit 102 obtains 2 as the self-mesh score for the mesh in the third column of the second row, which is the number of users who have an address in that mesh among the multiple users who visited the target merchant and used the payment service. The score calculation unit 102 obtains 1 as the self-mesh score for the mesh in the fourth column of the second row, which is the number of users who have an address in that mesh among the multiple users who visited the target merchant and used the payment service. The score calculation unit 102 obtains 1 as the self-mesh score for the mesh in the fifth column of the fourth row, which is the number of users who have an address in that mesh among the multiple users who visited the target merchant and used the payment service. Since there are no users who visited the target merchant and used the payment service in other meshes, the score calculation unit 102 obtains 0 as the self-mesh score for the other meshes.

[0058] For example, as shown in the lower left of Figure 6, the score calculation unit 102 aggregates the number of users whose addresses are in each mesh, and obtains the surrounding mesh score based on the number of users in other meshes surrounding the mesh as the score for the mesh. Surroundings are up, down, left, right, upper left, upper right, lower right, lower left, or a combination of these. In the example in Figure 6, with a certain mesh as the reference point, the eight directions of up, down, left, right, upper left, upper right, lower right, and lower left of that mesh correspond to the surroundings, but any one to seven of these may also correspond to the surroundings.

[0059] For example, the score calculation unit 102 calculates the surrounding mesh score for each of the multiple meshes based on the self-mesh score of each of the multiple meshes. In the example in the lower left of Figure 6, the score calculation unit 102 assigns the self-mesh score of each of the multiple meshes to the other meshes surrounding that mesh. As shown in the lower right of Figure 6, the score calculation unit 102 calculates the surrounding mesh score of the other meshes by summing the self-mesh scores assigned to those other meshes. For each merchant being processed, the score calculation unit 102 calculates the surrounding mesh score for each of the multiple meshes, associates it with the merchant ID of the merchant, and stores the score information of the surrounding mesh scores in the merchant database DB1.

[0060] In the lower left example of Figure 6, the score calculation unit 102 propagates the mesh score of 3, which is the mesh in the second column of the first row, to the left, lower left, bottom, lower right, and right meshes. The score calculation unit 102 propagates the mesh score of 2, which is the mesh in the third column of the second row, to the top, upper left, left, lower left, bottom, lower right, right, and upper right meshes. The score calculation unit 102 propagates the mesh score of 1, which is the mesh in the fourth column of the second row, to the top, upper left, left, lower left, bottom, lower right, right, and upper right meshes. The score calculation unit 102 propagates the mesh score of 1, which is the mesh in the fifth column of the fourth row, to the top, upper left, and left meshes. As shown in the lower right of Figure 6, the score calculation unit 102 calculates the surrounding mesh score by summing these propagated mesh scores for each mesh.

[0061] The score calculation unit 102 may calculate only its own mesh score without calculating the surrounding mesh score. The score calculation unit 102 may include a function to calculate its own mesh score without including a function to calculate the surrounding mesh score. In this embodiment, since the own mesh score is calculated in order to calculate the surrounding mesh score, the score calculation unit 102 calculates its own mesh score as a prerequisite for calculating the surrounding mesh score.

[0062] Furthermore, the method for calculating the own mesh score and the method for calculating the surrounding mesh scores are not limited to the examples of this embodiment. The score calculation unit 102 may calculate the score for each of the multiple meshes based on the address information of each of the multiple users. For example, instead of obtaining the number of users whose addresses are included in the mesh as the own mesh score, the score calculation unit 102 may calculate the own mesh score by multiplying that number by a weighting coefficient. The weighting coefficient may be common to all meshes, or it may be defined for each mesh.

[0063] For example, the score calculation unit 102 may obtain a value as the surrounding mesh score by multiplying the mesh score of a given mesh by a predetermined weighting coefficient, rather than equally assigning the mesh score of that mesh to the surrounding meshes. The weighting coefficient may be common to all meshes, or it may be defined for each mesh. The weighting coefficient may be determined according to the positional relationship between the reference mesh and the other meshes.

[0064] In this embodiment, the score calculation unit 102 adds 1 to the score regardless of the number of times a user has visited a merchant and used the payment service, as long as the user has visited the merchant and used the payment service. The score calculation unit 102 may calculate the score so that the more times the user uses the service, the greater the increase in the score. Alternatively, for example, the score calculation unit 102 may calculate the score so that the more the user spends, the greater the increase in the score.

[0065] [3-4. Proposal Department] The proposal unit 103 makes suggestions regarding merchants based on the score calculated for each mesh. A suggestion regarding a merchant can be any suggestion related to a merchant for which a score has been calculated. Suggestions may be made to any party. In this embodiment, an example is given where the proposal unit 103 makes a suggestion to a business operator that operates a payment service (for example, a person in charge of delivering advertisements), but the proposal unit 103 may make suggestions to other parties. These other parties may be the merchant being processed, other merchants, a business operator that operates other services that cooperate with the payment service, or a user.

[0066] In this embodiment, the suggestion unit 103 may suggest target users for advertisements related to member stores based on a score calculated for each mesh. That is, in this embodiment, we take the example of a case where determining target users corresponds to suggesting member stores. Suggestions related to member stores are not limited to the example in this embodiment. Other examples of suggestions related to member stores will be described in the modifications described later. Suggestions related to member stores are a concept that encompasses the example described in this embodiment and the example described in the modifications.

[0067] In this embodiment, since the advertising information of individual merchants is stored in the merchant database DB1, the target users can be defined as users who will receive the advertisements indicated by the advertising information. When the proposal unit 103 proposes target users, it means that the proposal unit 103 outputs information that can identify the target users. This output may be on a screen or as data output. For example, the proposal unit 103 may propose target users by displaying a list of target users on the business terminal of the payment service provider. The proposal unit 103 may also propose target users by sending list data indicating a list of target users to the business terminal.

[0068] For example, the proposal unit 103 may propose all or some of the users whose addresses are in meshes with a score above a threshold among multiple meshes (for example, all users whose addresses are in meshes with a score above a threshold but who have never used the target merchant, or a randomly selected portion of all such users) as target users for distribution. The threshold may be a fixed value or a variable value. If the threshold is a variable value, the threshold may be calculated based on the score of each of the multiple meshes, or the threshold may be determined according to the regional characteristics of the mesh (for example, whether the mesh is in an urban area or a suburb). The proposal unit 103 may propose all or some of the users whose addresses are in meshes with a score above a predetermined rank among multiple meshes as target users for distribution.

[0069] In this embodiment, since the self-mesh score is calculated, the proposal unit 103 makes a proposal based on the self-mesh score calculated for each mesh. The proposal unit 103 may propose all or some of the users whose address is in a mesh with a self-mesh score of or above a threshold among multiple meshes (for example, all users whose address is in a mesh with a self-mesh score of or above a threshold who have never used the merchant being processed, or a randomly selected portion of all such users) as target users for distribution. The proposal unit 103 may also propose all or some of the users whose address is in a mesh with a self-mesh score of or above a predetermined rank among multiple meshes as target users for distribution.

[0070] In this embodiment, since the surrounding mesh score is calculated, the proposal unit 103 makes a proposal based on the surrounding mesh score calculated for each mesh. The proposal unit 103 may propose all or some of the users whose addresses are in a mesh with a surrounding mesh score of or above a threshold (for example, all users whose addresses are in a mesh with a surrounding mesh score of or above a threshold, but who have never used the merchant being processed, or a randomly selected portion of all such users) as target users for distribution. The proposal unit 103 may also propose all or some of the users whose addresses are in a mesh with a surrounding mesh score of or above a predetermined rank as target users for distribution.

[0071] The proposal unit 103 may make proposals based on both its own mesh score and the surrounding mesh score. For example, the proposal unit 103 may calculate a total mesh score for each mesh by adding its own mesh score and the surrounding mesh score, and make proposals based on this total mesh score. The total mesh score may be a simple sum of the own mesh score and the surrounding mesh score, or it may be calculated after multiplying by a predetermined coefficient. The total mesh score may also be the average value of the own mesh score and the surrounding mesh score. The average value may be a simple average or a weighted average.

[0072] For example, the suggestion unit 103 may suggest users as target users for distribution if their own mesh score is equal to or greater than the first threshold, and their address is located in a mesh where the surrounding mesh score is equal to or greater than the second threshold. The second threshold may be the same as or different from the first threshold. Suggestions may also be made based on an OR condition instead of such an AND condition. That is, the suggestion unit 103 may suggest users as target users for distribution if their own mesh score is equal to or greater than the first threshold, or their address is located in a mesh where the surrounding mesh score is equal to or greater than the second threshold.

[0073] For example, the proposal unit 103 may propose users as target users for distribution if their address is located in a mesh where its own mesh score is ranked 1st or higher, and the surrounding mesh scores are ranked 2nd or higher. The 2nd rank may be the same as or different from the 1st rank. In this case as well, the proposal may be made based on an OR condition rather than an AND condition. That is, the proposal unit 103 may propose users as target users for distribution if their address is located in a mesh where its own mesh score is ranked 1st or higher, or the surrounding mesh scores are ranked 2nd or higher.

[0074] [4. Processes executed in the proposed system] Figure 7 shows an example of the processing performed by the proposed system 1. In Figure 7, the processing performed by the server 10 is shown among the processing performed by the proposed system 1. The processing in Figure 7 is performed when the control unit 11 executes the program stored in the storage unit 12. The steps in Figure 7 are an example of a provision method.

[0075] As shown in Figure 7, the server 10 determines the merchants to be processed based on the merchant database DB1 (ST1). In ST1, the server 10 determines any merchant from among all merchants whose merchant IDs are stored in the merchant database DB1 as the merchants to be processed. For example, if the server 10 is calculating a score for all merchants, it may determine the merchants to be processed one by one in ascending order of their merchant IDs. If a representative of the business operator running the payment service specifies the merchants to be processed, the server 10 may determine the specified merchants as the merchants to be processed.

[0076] Server 10 obtains the address information of each of the multiple users who visited the merchants to be processed and used the payment service, as determined in ST1, based on the user database DB2 (ST2). In ST2, Server 10 identifies the multiple users who visited the merchants to be processed and used the payment service, based on the usage history information stored in the user database DB2. Server 10 obtains the address information of each of the identified users from the user database DB2. Based on the address information obtained in ST2, Server 10 calculates its own mesh score for each mesh (ST3). The method for calculating the own mesh score in ST3 is as explained with reference to Figure 6. Based on the own mesh score calculated in ST3, Server 10 calculates the surrounding mesh score for each mesh (ST4). The method for calculating the surrounding mesh score in ST4 is as explained with reference to Figure 6.

[0077] Server 10 determines the target users for each merchant based on its own mesh score calculated in ST3 and the surrounding mesh scores calculated in ST4, and makes a proposal to the payment service provider (ST5). Server 10 determines whether to terminate this process (ST6). In ST6, the determination may be made based on any conditions. For example, in ST6, Server 10 may determine whether to terminate this process by determining whether all merchants have become targets for processing. If it is determined in ST6 not to terminate this process (ST6:N), the process returns to ST1, and the next merchant to be processed is determined. If it is determined in ST6 to terminate this process (ST6:Y), this process terminates.

[0078] Furthermore, Server 10 may deliver advertisements to the target users proposed in ST5 based on the advertising information of the merchant being processed. After the target users are proposed in ST5, the final target users may be determined by a person in charge of the payment service provider, and Server 10 may deliver advertisements to these final target users. Advertisement delivery may be carried out by any method. For example, Server 10 may deliver advertisements to the target users' email addresses, phone numbers, messaging app accounts, or social networking service accounts. Server 10 may also deliver advertisements on the payment service screen when a target user logs into the payment service.

[0079] [5. Summary of Embodiments] The proposed system 1 of this embodiment acquires address information for each of the multiple users who visit a merchant that accepts payment services and use the payment service. Based on the address information of each of the multiple users, the proposed system 1 calculates a score for each mesh in a region divided into multiple meshes, based on the number of users whose addresses are in that mesh. Based on the score calculated for each mesh, the proposed system 1 makes suggestions regarding merchants. This enables the proposed system 1 to make effective suggestions regarding merchants. For example, the proposed system 1 can make suggestions that correspond to the merchant's trading area estimated from the score calculated based on the address information of users who actually visited the merchant and used the payment service. Even if the merchant's address information is not stored in the merchant database DB1, or if the merchant's address information stored in the merchant database DB1 is not the actual location of the facility, the proposed system 1 can estimate the merchant's trading area by looking at which areas users actually use the merchant, without using the merchant's address information, so the proposed system 1 can make suggestions that correspond to the actual usage situation of the merchant.

[0080] Furthermore, Proposed System 1 aggregates the number of users whose addresses are located in each mesh and calculates a self-mesh score for that mesh, which represents the number of such users. Based on the self-mesh score calculated for each mesh, Proposed System 1 makes recommendations. This allows Proposed System 1 to make effective recommendations regarding merchants by utilizing the self-mesh score, which represents the number of users who have actually visited merchants and used payment services. For example, even if there are users in a mesh with a high self-mesh score who have never visited a merchant being processed, these users may be potential customers. Proposed System 1 can estimate users who could become potential customers from the self-mesh score.

[0081] Furthermore, Proposed System 1 aggregates the number of users whose addresses are located in each mesh. Proposed System 1 obtains a surrounding mesh score based on the number of users in other meshes surrounding the mesh, and uses this score for the mesh. Proposed System 1 makes recommendations based on the surrounding mesh score calculated for each mesh. This allows Proposed System 1 to make effective recommendations regarding merchants by utilizing the surrounding mesh score, which is influenced by the number of users in the meshes surrounding the mesh where users who have actually visited merchants and used payment services reside. For example, even if a mesh has many users who have never visited the target merchant, if there are many users in the surrounding meshes who have visited the target merchant, the surrounding mesh score will be high. In this way, meshes with high surrounding mesh scores may have many potential customers, so Proposed System 1 can estimate users who could become potential customers from the surrounding mesh score.

[0082] Furthermore, Proposed System 1 proposes target users for advertising related to member stores based on a score calculated for each mesh. This enables Proposed System 1 to deliver effective advertising related to member stores. For example, Proposed System 1 can identify users who could become potential customers as target users based on the score calculated for each mesh. Even if the address information of a member store differs from the actual location of the facility, Proposed System 1 can propose target users based on the estimated trade area of ​​the member store calculated by the score calculated for each mesh.

[0083] [6. Variant] This disclosure is not limited to the embodiments described above. This disclosure may be modified as appropriate without departing from the spirit of this disclosure.

[0084] Figure 8 shows an example of a function realized by a modified version. For example, the server 10 includes an action presence / absence information acquisition unit 104, a browsing presence / absence information acquisition unit 105, an entry presence / absence information acquisition unit 106, a mesh feature information acquisition unit 107, and a user feature information acquisition unit 108. Each of the action presence / absence information acquisition unit 104, browsing presence / absence information acquisition unit 105, entry presence / absence information acquisition unit 106, mesh feature information acquisition unit 107, and user feature information acquisition unit 108 is realized by the control unit 11.

[0085] [6-1. Variation 1] For example, the targeting of users may be repeated. In one embodiment, when an advertisement from a merchant is delivered to multiple target users, some of these users may purchase the goods or services related to the advertisement, while others may not. When the same merchant's advertisement is delivered again, the score for each mesh may be calculated taking into account whether or not the target users have purchased the goods or services related to the previously delivered advertisement.

[0086] The proposed system 1 of Modification 1 includes an action presence / absence information acquisition unit 104. The action presence / absence information acquisition unit 104 acquires action presence / absence information regarding whether or not the target user performed an action related to the advertisement after the advertisement has been delivered to the target user. An action related to the advertisement is an action of the user that the advertiser intends to perform. For example, if an advertisement for a product or service is delivered, the purchase of the product or service constitutes an action related to the advertisement. If a coupon for a product or service is delivered as an advertisement, the use of the coupon constitutes an action related to the advertisement. If checking in at a participating store is delivered as an advertisement, the use of the check-in service constitutes an action related to the advertisement. If the advertisement indicates other content (e.g., a campaign), any action corresponding to the other content (e.g., entering the campaign) should constitute an action related to the advertisement.

[0087] Action information indicates either a first value indicating that the target user performed an action related to the advertisement, or a second value indicating that the target user did not perform an action related to the advertisement. The initial value of action information may be the second value. Action information may not take the first or second value, but may also be information that identifies products or services purchased by the user regardless of the advertisement.

[0088] In Modification 1, we take the example of a case where the user database DB2 stores the behavior information. At the time the advertisement is delivered, the behavior information associated with the user ID of the target user will show the second value. For example, when a user uses a payment service to perform an action related to the advertisement at a merchant, the merchant terminal 20 sends the server 10 the behavior information (i.e., the behavior information with the first value) indicating that the user performed an action related to the advertisement, along with the credit card information. When the server 10 receives the credit card information and behavior information from the merchant terminal 20, it stores the behavior information in the user database DB2 in association with the credit card information.

[0089] Furthermore, the merchant terminal 20 can identify that an action related to the advertisement has been taken by any means. For example, if the advertisement delivered to the user terminal 30 includes a code that can identify a product or service (e.g., a barcode or a two-dimensional code), the merchant terminal 20 may identify that the product or service related to the advertisement has become the subject of payment by reading the code with the reader unit 26. The merchant terminal 20 may also store information that can identify the product or service related to the advertisement (e.g., an ID of the product or service) in the storage unit 22 in advance, and determine whether or not the product or service subject to payment is related to the advertisement based on that information.

[0090] Furthermore, the merchant terminal 20 may transmit information to the server 10 that can identify the goods or services to be paid for, regardless of whether the goods or services to be paid for relate to an advertisement. The server 10 may receive this information from the merchant terminal 20 and determine whether or not the goods or services to be paid for relate to an advertisement. Goods or services related to advertisements may be indicated in the advertisement information. Based on the result of this determination, the server 10 may store activity information in the user database DB2. The server 10 may obtain information from the merchant terminal 20 or user terminal 30 indicating whether or not a coupon shown in the advertisement was used, or whether or not a check-in was performed at a merchant shown in the advertisement, and update the activity information.

[0091] For example, the behavior information acquisition unit 104 acquires behavior information for any user from the user database DB2. When a process is executed to identify the next target users for distribution, the behavior information acquisition unit 104 may acquire behavior information for each of multiple users who have visited the target merchant and used the payment service from the user database DB2. If behavior information is stored in a database other than the user database DB2, a computer other than the server 10, or an information storage medium, the behavior information acquisition unit 104 may acquire behavior information from the other database, other computer, or information storage medium.

[0092] In Modification 1, the score calculation unit 102 calculates the next score to be used in the next target user proposal based on the behavior information. For example, when the score calculation unit 102 calculates the score for a certain mesh, it includes users who have an address in that mesh, have visited a target merchant and used the payment service, and whose behavior information indicates that they have taken action related to the advertisement, as the target of the score calculation for that mesh (the target of the count of users in that mesh). In other words, the score calculation unit 102 excludes users from the calculation of the score for that mesh whose behavior information indicates that they have not taken action related to the advertisement.

[0093] Furthermore, the score calculation unit 102 may also include in the calculation of the score for a mesh users who have an address in the mesh and who have visited a merchant subject to processing and used the payment service, but whose behavior information indicates that they did not perform any advertising-related actions. For example, the score calculation unit 102 may calculate the score based on a formula in which the weight coefficient of users whose behavior information indicates that they performed an advertising-related action is higher than the weight coefficient of users whose behavior information indicates that they did not perform an advertising-related action. In Modification 1, the users and weight coefficients subject to the score calculation differ from the embodiment, but other aspects of the score calculation are the same as in the embodiment. For example, the score calculation unit 102 may calculate both its own mesh score and the surrounding mesh score, or it may calculate only one of them.

[0094] In Modification 1, the suggestion unit 103 suggests the next target users for distribution based on the next score calculated for each mesh. Although the method for calculating the next score differs from that of the embodiment, the method by which the suggestion unit 103 suggests the next target users after the next score has been calculated may be the same as the process in the embodiment. For example, the suggestion unit 103 may determine users whose address is in a mesh with a next score of or above a threshold as the next target users for distribution. The suggestion unit 103 may also determine users whose address is in a mesh with a next score of or above a predetermined rank as the next target users for distribution.

[0095] In Modification 1, the proposed system 1 acquires behavioral information after an ad has been delivered to the target users. Based on the behavioral information, the proposed system 1 calculates the next score to be used in proposing the next target users. Based on the next score calculated for each mesh, the proposed system 1 proposes the next target users. As a result, the proposed system 1 can propose target users that take behavioral information into account, thus proposing target users that will be more effective with the ad. For example, other users who live in the same mesh as a user who has actually purchased a product or service related to the ad, actually used a coupon related to the ad, or checked in at a participating store indicated by the ad are likely to be potential customers. By reflecting whether a user is such a person in the score, the proposed system 1 can propose target users that will be more effective with the ad. The proposed system 1 can increase the conversion rate from the ad.

[0096] [6-2. Variation 2] For example, in Modification 1, the proposal unit 103 may exclude target users who did not take any action related to the advertisement from the target users for the next delivery. When the proposal unit 103 excludes a user from the target users for the next delivery, it means that the proposal unit 103 does not decide that the user will be included in the target users for the next delivery. In other words, target users who did not take any action related to the advertisement in past deliveries are not included in the user group that the proposal unit 103 uses to determine the target users for the next delivery.

[0097] For example, the proposal unit 103 does not target all of the multiple users whose addresses are in a mesh area with a score above a threshold, but rather excludes users whose behavior information indicates that they did not take any action related to the advertisement. The proposal unit 103 targets users whose behavior information indicates that they did not take any action related to the advertisement, as well as new users who have not yet received an advertisement, from among the multiple users whose addresses are in a mesh area with a score above a threshold.

[0098] For example, the proposal unit 103 may choose not to target all users whose address is in a mesh area with a score of a certain rank or higher, but rather to exclude users whose behavior information indicates they did not take any action related to advertising. The proposal unit 103 may also choose to target users whose behavior information indicates they took action related to advertising, and new users who have not yet received advertising, from among the multiple users whose address is in a mesh area with a score of a certain rank or higher.

[0099] In the modified version 2, proposed system 1 excludes target users who did not take any action related to the advertisement from the target users for the next advertisement. This allows proposed system 1 to exclude past target users who were not affected by the advertisements delivered in the past, thereby improving the effectiveness of the next advertisement. For example, proposed system 1 can increase the conversion rate of the next advertisement.

[0100] [6-3. Modified Example 3] For example, as in the embodiment, when an advertisement from a merchant is delivered to multiple target users, some of these target users will view the advertisement, while others will not. When the same merchant's advertisement is delivered again, the score for each mesh may be calculated taking into consideration whether or not the target users viewed the previously delivered advertisement.

[0101] The proposed system 1 of Modification 3 includes a viewing status information acquisition unit 105. The viewing status information acquisition unit 105 acquires viewing status information regarding whether or not the target user viewed the advertisement after the advertisement has been delivered to the target user. Viewing an advertisement can also be defined as displaying the advertisement. For example, if an advertisement is delivered by email, opening the email may be equivalent to viewing the advertisement. If an advertisement is delivered by various messages such as short messages, viewing the message may be equivalent to viewing the advertisement. If an advertisement is delivered on the screen of a payment service, displaying the screen may be equivalent to viewing the advertisement.

[0102] Viewing status information indicates either a first value indicating that the target user viewed the advertisement, or a second value indicating that the target user did not view the advertisement. The initial value of viewing status information may be the second value. Viewing status information may not take the first or second value, but may be information that identifies the advertisement viewed by the target user.

[0103] In variation 3, we take the example of a case where viewing information is stored in the user database DB2. At the time the advertisement is delivered, the viewing information associated with the user ID of the target user will show the second value. For example, when a user views an advertisement on user terminal 30, user terminal 30 sends viewing information (i.e., viewing information with the first value) indicating that the user viewed the advertisement, along with some user identification information (e.g., user ID), to server 10. When server 10 receives the user identification information and viewing information from merchant terminal 20, it stores the viewing information in user database DB2 in association with the user identification information.

[0104] Furthermore, the user terminal 30 can identify that the user has viewed the advertisement by any means. For example, if the advertisement is delivered via email, the user terminal 30 may use the email software's open function to identify that the user has viewed the advertisement. If the advertisement is delivered via various messaging methods such as short messages, the user terminal 30 may use the messaging software's read receipt function to identify that the user has viewed the advertisement.

[0105] For example, the viewing status information acquisition unit 105 acquires viewing status information for any user from the user database DB2. When a process is executed to identify the next target users for distribution, the viewing status information acquisition unit 105 may acquire viewing status information for each target user who has previously received advertisements from the target merchant from the user database DB2. If viewing status information is stored in a database other than the user database DB2, a computer other than the server 10, or an information storage medium, the viewing status information acquisition unit 105 may acquire viewing status information from the other database, other computer, or information storage medium.

[0106] In the modified example 3, the score calculation unit 102 calculates the next score to be used in the next target user proposal, based on the viewing status information. For example, when the score calculation unit 102 calculates the score for a certain mesh, it includes users who have an address in that mesh and who have received advertisements from the target merchants, and whose viewing status information indicates that they viewed the advertisement, as the target of the score calculation for that mesh (the target of the count of users in that mesh). In other words, the score calculation unit 102 excludes users whose viewing status information indicates that they did not view the advertisement from the calculation of the score for that mesh.

[0107] Furthermore, the score calculation unit 102 may also include users whose addresses are in a mesh and who have received advertisements from the affiliated stores being processed, as part of the calculation of the mesh's score, even if the viewing status information indicates that the advertisement was not viewed. For example, the score calculation unit 102 may calculate the score based on a formula in which the weight coefficient for users whose viewing status information indicates that the advertisement was viewed is higher than the weight coefficient for users whose viewing status information indicates that the advertisement was not viewed. In Modification 3, the users and weight coefficients included in the score calculation differ from the embodiment, but other aspects of the score calculation are the same as in the embodiment. For example, the score calculation unit 102 may calculate both its own mesh score and the surrounding mesh score, or it may calculate only one of them.

[0108] In Modification 3, the suggestion unit 103 suggests the next target users for distribution based on the next score calculated for each mesh. Although the method for calculating the next score differs from that of the embodiment, the method by which the suggestion unit 103 suggests the next target users after the next score has been calculated may be the same as the process in the embodiment. For example, the suggestion unit 103 may determine users whose address is in a mesh with a next score of a threshold or higher as the next target users for distribution. The suggestion unit 103 may also determine users whose address is in a mesh with a next score of a predetermined rank or higher as the next target users for distribution.

[0109] In the modified version 3, the proposed system 1 obtains viewing information after the ad has been delivered to the target users. Based on the viewing information, the proposed system 1 calculates the next score to be used in suggesting the next target users. Based on the next score calculated for each mesh, the proposed system 1 suggests the next target users. As a result, the proposed system 1 can suggest target users that take viewing information into account, thus suggesting target users that will be more effective with the ad. For example, other users who live in the same mesh as a user who actually viewed the ad are likely to be potential customers. By reflecting whether a user is such a person in the score, the proposed system 1 can suggest target users that will be more effective with the ad. The proposed system 1 can increase the conversion rate from advertising.

[0110] [6-4. Modification 4] For example, there are advertisements that require entry from the target audience. Entry is an action taken to generate the benefit shown in the advertisement. The benefit may be an increased point redemption rate, point accrual, discounts, free prizes, free service use, monetary benefits, or other perks. In the embodiment, if an advertisement from a merchant is delivered to multiple target audiences, some of these target audiences will enter, while others will not. When the same merchant's advertisement is delivered again, the score for each mesh may be calculated taking into account whether or not the target audience entered after receiving the advertisement in the past.

[0111] The proposed system 1 of Modification 4 includes an entry status information acquisition unit 106. The entry status information acquisition unit 106 acquires entry status information regarding whether or not a target user has entered the advertisement after the advertisement has been delivered to the target user. A target user entering the advertisement means that the target user performs an entry operation for entry. The entry operation is accepted by the advertisement. For example, selecting a link in the advertisement, selecting a user interface part included in the advertisement (e.g., a button), or other operations may correspond to an entry operation.

[0112] The entry status information indicates either a first value indicating that the target user has entered, or a second value indicating that the target user has not entered. The initial value of the entry status information may be the second value. The entry status information may not take the first or second value, but may also be information that identifies the advertisement that the target user has entered.

[0113] In variation 4, we take the example of a case where entry status information is stored in the user database DB2. Immediately after an advertisement is delivered, the entry status information associated with the user ID of the target user will show the second value. For example, when a user enters at user terminal 30, user terminal 30 sends to server 10 some user identification information (e.g., user ID) along with entry status information indicating that the user has entered (i.e., entry status information with the first value). When various advertisements are delivered, the entry status information may also include information that can identify the advertisement that has been entered. When server 10 receives user identification information and entry status information from merchant terminal 20, it stores the entry status information in user database DB2 in association with the user identification information.

[0114] For example, the entry status information acquisition unit 106 acquires entry status information for any user from the user database DB2. When a process is executed to identify the next target users for distribution, the entry status information acquisition unit 106 may acquire entry status information for each target user who has previously received advertisements from the target merchant from the user database DB2. If entry status information is stored in a database other than the user database DB2, a computer other than the server 10, or an information storage medium, the entry status information acquisition unit 106 may acquire entry status information from the other database, other computer, or information storage medium.

[0115] In the modified example 4, the score calculation unit 102 calculates the next score to be used in the next target user proposal based on the entry status information. For example, when the score calculation unit 102 calculates the score for a certain mesh, it includes users who have an address in that mesh and who have received advertisements from the target merchants, and whose entry status information indicates that they have entered, as the target of the score calculation for that mesh (the target of the count of users in that mesh). In other words, the score calculation unit 102 excludes users who, among those users, whose entry status information indicates that they have not entered, from the calculation of the score for that mesh.

[0116] Furthermore, the score calculation unit 102 may also include users who have an address in a mesh and who have received advertisements from the affiliated stores being processed, but who were not entered as indicated by the entry status information, in the calculation of the score for that mesh. For example, the score calculation unit 102 may calculate the score based on a formula in which the weight coefficient of users who were entered as indicated by the entry status information is higher than the weight coefficient of users who were not entered as indicated by the entry status information. In Modification 4, the users and weight coefficients included in the score calculation differ from the embodiment, but other aspects of the score calculation are the same as in the embodiment. For example, the score calculation unit 102 may calculate both its own mesh score and the surrounding mesh score, or it may calculate only one of them.

[0117] In Modification 4, the suggestion unit 103 suggests the next target users for distribution based on the next score calculated for each mesh. Although the method for calculating the next score differs from that of the embodiment, the method by which the suggestion unit 103 suggests the next target users after the next score has been calculated may be the same as the process in the embodiment. For example, the suggestion unit 103 may determine users whose address is in a mesh with a next score of a threshold or higher as the next target users for distribution. The suggestion unit 103 may also determine users whose address is in a mesh with a next score of a predetermined rank or higher as the next target users for distribution.

[0118] In the modified version 4, the suggestion system 1 obtains entry status information after the ad has been delivered to the target users. Based on the entry status information, the suggestion system 1 calculates the next score to be used in suggesting the next target users. Based on the next score calculated for each mesh, the suggestion system 1 proposes the next target users. As a result, the suggestion system 1 can propose target users that take entry status information into account, thus proposing target users that will be more effective with the ad. For example, other users who live in the same mesh as a user who entered after seeing the ad are likely to be potential customers. By reflecting whether a user is such a user in the score, the suggestion system 1 can propose target users that will be more effective with the ad. The suggestion system 1 can increase the conversion rate from the ad.

[0119] [6-5. Variation 5] For example, by combining Modifications 1 to 4, a score may be calculated based on behavior information, viewing information, and entry information. Modification 5 explains a case where the weighting coefficients for determining the next target user differ based on whether the target user purchased the product or service related to the advertisement, whether the target user viewed the advertisement, and whether the target user entered the advertisement.

[0120] The proposed system 1 of Modification 5 includes an action presence / absence information acquisition unit 104, a viewing presence / absence information acquisition unit 105, and an entry presence / absence information acquisition unit 106. The action presence / absence information acquisition unit 104, the viewing presence / absence information acquisition unit 105, and the entry presence / absence information acquisition unit 106 are as described in Modifications 1 to 4, respectively. The score calculation unit 102 of Modification 5 calculates the next score to be used in the next delivery target user proposal based on the action presence / absence information, the viewing presence / absence information, the entry presence / absence information, and coefficients corresponding to this information.

[0121] In the modified example 5, the data storage unit 100 stores a calculation formula for calculating the next score. The calculation formula is substituted with the activity status information, browsing status information, and entry status information. The calculation formula includes a purchase status coefficient, which is multiplied by the activity status information; a browsing status coefficient, which is multiplied by the browsing status information; and an entry status coefficient, which is multiplied by the entry status information. The score calculation unit 102 calculates the next score based on the activity status information, browsing status information, and entry status information of each of the multiple users who visited the merchant and used the payment service, as well as the purchase status coefficient, browsing status coefficient, and entry status information.

[0122] The purchase coefficient, viewing coefficient, and entry information may be the same as or different from each other. For example, if purchase is considered important in the score calculation, the purchase coefficient may be higher than the viewing coefficient and entry information. If viewing is considered important in the score calculation, the viewing coefficient may be higher than the purchase coefficient and entry information. If entry is considered important in the score calculation, the entry information may be higher than the purchase coefficient and viewing coefficient.

[0123] In Modification 5, the suggestion unit 103 suggests the next target users for distribution based on the next score calculated for each mesh. Although the method for calculating the next score differs from that of the embodiment, the method by which the suggestion unit 103 suggests the next target users after the next score has been calculated may be the same as the process in the embodiment. For example, the suggestion unit 103 may determine users whose address is in a mesh with a next score of a threshold or higher as the next target users for distribution. The suggestion unit 103 may also determine users whose address is in a mesh with a next score of a predetermined rank or higher as the next target users for distribution.

[0124] The proposed system 1 in modified example 5 acquires behavior information, viewing information, and entry information. Based on the behavior information, viewing information, entry information, and coefficients corresponding to this information, the proposed system 1 calculates the next score to be used in proposing the next target users for advertising. Based on the next score calculated for each mesh, the proposed system 1 proposes the next target users for advertising. As a result, the proposed system 1 can propose target users that are highly effective for advertising because they are based on a score that comprehensively considers behavior information, viewing information, and entry information. For example, the proposed system 1 can calculate scores according to which of the following is given more importance in the score calculation: whether a purchase was made, whether a view was made, or whether an entry was made.

[0125] [6-6. Variation 6] For example, the suggestions made by the suggestion unit 103 are not limited to suggestions for target users. Modification 6 describes an example of another suggestion made by the suggestion unit 103. In Modification 6, the suggestion unit 103 suggests locations for new member stores based on scores calculated for each mesh. New member stores may belong to the same group as the member stores whose scores were calculated, or they may belong to a different group. If a member store is a store that sells goods or services, the group is a chain of stores.

[0126] Modification 6 takes the example of a group that includes multiple member stores. For example, if the member stores are convenience stores, the group is a convenience store chain. The address information acquisition unit 101 acquires the address information of multiple users who visit each of the multiple member stores belonging to the group and use the payment service. The score calculation unit 102 may calculate a score for each individual member store belonging to the group, but in Modification 6, it calculates the score for the entire group. The proposal unit 103 may also make proposals for each individual member store belonging to the group, but in Modification 6, it makes proposals for the entire group.

[0127] Figure 9 shows an example of a location proposed in Modification 6. Figure 9 shows an example where a proposal is made based on the self-mesh score. For example, the proposal unit 103 obtains the address information of each of the multiple member stores belonging to the group from the member store database DB1. The proposal unit 103 aggregates the number of member stores with addresses in each mesh and calculates a member store score that indicates the number for that mesh. The upper left of Figure 9 shows the member store score. The score calculation unit 102 calculates the self-mesh score in the same manner as in the embodiment or Modifications 1 to 5. The upper right of Figure 9 shows the self-mesh score.

[0128] For example, the proposal unit 103 proposes a mesh where its own mesh score is relatively high and the merchant score is relatively low as a location for a new merchant to open. The lower part of Figure 9 shows a mesh that is a location for a new merchant to open. The proposal unit 103 may propose a location to a business operator that operates a payment service by providing information on the mesh at the bottom of Figure 9. The proposal unit 103 may also propose a location to the merchant being processed or other merchants by providing information on the mesh at the bottom of Figure 9. In the example at the bottom of Figure 9, the mesh in the first row and second column has a relatively high own mesh score and a relatively low merchant score. This mesh has many users who use merchants and no merchants have opened yet, so it is expected to attract customers.

[0129] For example, the proposal unit 103 may propose a mesh where its own mesh score is above the third threshold and the franchisee score is below the fourth threshold as a location for a new franchisee to open. The fourth threshold may be the same as or different from the third threshold. For example, the proposal unit 103 may propose a mesh where its own mesh score is above a predetermined third rank and the franchisee score is below a predetermined fourth rank as a location for a new franchisee to open. The fourth rank may be the same as or different from the third rank.

[0130] Furthermore, the proposal unit 103 may propose locations for new franchise stores based on its own mesh score, rather than specifically on the franchise store score. In other words, the proposal unit 103 does not need to calculate the franchise store score. For example, a mesh with a relatively low own mesh score may not be within the trading area of ​​an existing franchise store, and therefore could potentially become the trading area of ​​a new franchise store. For this reason, the proposal unit 103 may propose a mesh with a relatively low own mesh score as a location for a new franchise store. The proposal unit 103 may also propose a mesh with a self-mesh score below a predetermined threshold, or a mesh with a self-mesh score below a predetermined rank, as a location for a new franchise store.

[0131] In the modified version 6, proposed system 1 suggests locations for new franchise stores based on a score calculated for each mesh. This allows proposed system 1 to suggest locations for new franchise stores. For example, proposed system 1 can improve convenience for franchise stores considering opening a new store by suggesting locations for new franchise stores.

[0132] [6-7. Variation 7] For example, in Modification 6, the scores of each of the competing franchisees may be taken into consideration when making a location proposal. If the convenience store chain described in Modification 6 corresponds to a group, the scores corresponding to each of the multiple franchisees belonging to convenience store chain X and the scores corresponding to each of the multiple franchisees belonging to convenience store chain Y, which competes with convenience store chain X, may be taken into consideration when proposing the opening of new stores for at least one of convenience store chains X and convenience store chain Y.

[0133] In Modification 7, the address information acquisition unit 101 acquires address information corresponding to each of multiple competing merchants. The address information corresponding to a merchant is the address information of each of the multiple users who visited the merchant and used the payment service. In Modification 7, since multiple merchants are processed together, the address information acquisition unit 101 acquires the address information of each of the multiple users who visited each of the multiple merchants being processed and used the payment service.

[0134] For example, multiple competing member stores may be designated by the administrator of the proposed system 1, or industry information regarding the business type of each member store may be stored in the member store database DB1, and multiple competing member stores may be identified based on the industry information. The address information acquisition unit 101 can identify multiple competing member stores by any means and acquire the address information for each of those multiple member stores.

[0135] For example, the address information acquisition unit 101 acquires address information corresponding to each of several merchants belonging to different groups. Which groups are to be processed may be specified by the business operator operating the payment service, or if group identification information that can identify the group to which a merchant belongs is stored in the merchant database DB1, all groups indicated by the group identification information may be processed in order. The address information acquisition unit 101 may also acquire address information corresponding to each of several merchants in the same industry that compete with each other, regardless of the group.

[0136] In the modified example 7, the score calculation unit 102 calculates the score for each mesh of each of the multiple member stores. For example, the score calculation unit 102 calculates the score for each mesh of each of the multiple member stores by performing the same processing as in the embodiment and modified examples 1 to 6 for each member store. For example, if address information corresponding to each of the multiple member stores belonging to different groups is obtained, the score calculation unit 102 calculates the score for each mesh of each of the multiple member stores belonging to each of the multiple groups.

[0137] In the modified example 7, the suggestion unit 103 proposes the location of a new franchise store corresponding to at least one of the multiple franchise stores, based on the score calculated for each mesh of the multiple franchise stores. For example, if a score is calculated for each of the multiple franchise stores belonging to different groups, the suggestion unit 103 proposes the location of a new franchise store belonging to at least one of the multiple groups, based on the score for each mesh of the multiple franchise stores belonging to that group.

[0138] For example, the proposal unit 103 calculates the franchisee score for each of the multiple groups in the same manner as in the modified example 6. The proposal unit 103 proposes a mesh among the multiple meshes in which the sum of its own mesh score is relatively high and the sum of its franchisee scores is relatively low as a location for a new franchisee to open. The proposal unit 103 may also propose a mesh in which the sum of its own mesh score is equal to or greater than the 5th threshold and the sum of its franchisee scores is less than the 6th threshold as a location for a new franchisee to open. The 6th threshold may be the same as or different from the 5th threshold. The proposal unit 103 may also propose a mesh in which the sum of its own mesh score is equal to or greater than a predetermined 5th rank and the sum of its franchisee scores is less than a predetermined 6th rank as a location for a new franchisee to open. The 6th rank may be the same as or different from the 5th rank.

[0139] In Modification 7, the Proposal Unit 103 may also propose locations for new franchise stores based on the individual mesh scores of multiple franchise stores, rather than specifically on franchise store scores. That is, in Modification 7, the Proposal Unit 103 does not need to calculate franchise store scores. For example, a mesh where the sum of the individual mesh scores of multiple franchise stores is relatively low may not be within the trading area of ​​an existing franchise store, and therefore could potentially become the trading area of ​​a new franchise store. For this reason, the Proposal Unit 103 may propose a mesh with a relatively low sum as a location for a new franchise store. The Proposal Unit 103 may also propose a mesh where the sum is below a predetermined threshold, or a mesh where the sum is below a predetermined rank, as a location for a new franchise store.

[0140] For example, the proposal unit 103 may suggest a mesh as a location where a new merchant should open, where the sum of the mesh scores of each of the multiple merchants is relatively low, and the number of users with an address (for example, users who have never used payment services at any of the multiple merchants) is relatively high. The proposal unit 103 may also suggest a mesh as a location where a new merchant should open, where the sum is below a predetermined threshold, and the number of such users is above a predetermined threshold. The proposal unit 103 may also suggest a mesh as a location where a new merchant should open, where the sum is below a predetermined rank, and the number of such users is above a predetermined rank.

[0141] The proposed system 1 in modified example 7 obtains address information corresponding to each of several competing franchise stores. The proposed system 1 calculates a score for each mesh for each of the multiple franchise stores. Based on the scores calculated for each mesh for each of the multiple franchise stores, the proposed system 1 proposes a location for a new franchise store corresponding to at least one of the multiple franchise stores. In this way, the proposed system 1 can propose a location for a new franchise store by comprehensively considering multiple competing franchise stores. For example, the proposed system 1 can improve convenience for franchise stores considering opening a new store by proposing a location for the new franchise store.

[0142] [6-8. Variation 8] For example, individual meshes may have characteristics unique to that mesh. If a mesh has little land or a higher population density than its surroundings, it may be better to use a different method for calculating the score. For example, a mesh with little land may have a lower coefficient for the surrounding mesh score so that it is less affected by the score of the adjacent mesh. If a mesh has a higher population density than its surroundings, the coefficient may be set lower than that of other surrounding meshes so that the score of that mesh does not become excessively high. In Modification 8, the score is calculated according to the characteristics of the mesh.

[0143] The proposed system 1 of Modification 8 includes a mesh feature information acquisition unit 107. The mesh feature information acquisition unit 107 acquires mesh feature information relating to features in a mesh. Features in a mesh are the characteristics of the area represented by the mesh. Features in a mesh may be geographical features or demographic features. For example, the mesh feature information may represent features in a mesh such as topography, population, population density, average age, traffic volume, presence or absence of railways, industry, weather, or a combination thereof.

[0144] In the modified example 8, the data storage unit 100 stores mesh feature information in a mesh database. The mesh database also stores other information such as mesh IDs. The mesh feature information acquisition unit 107 acquires mesh feature information from the mesh database. The mesh feature information may also be stored in a database other than the mesh database, a computer other than the server 10, or an information storage medium. The mesh feature information acquisition unit 107 may acquire mesh feature information from a database, a computer, or an information storage medium.

[0145] In Modification 8, the score calculation unit 102 calculates a score for each mesh based on the mesh feature information of that mesh. In Modification 8, the mesh feature information is substituted into the score calculation formula. If multiple items such as topography and population are included in the mesh feature information, each of the multiple items is substituted into the score calculation formula. The score calculation formula includes a coefficient that is multiplied by the mesh feature information. If multiple items are included in the mesh feature information, the score calculation formula includes the coefficient of each of the multiple items. The score calculation unit 102 calculates a score for each mesh based on the mesh feature information of that mesh and the score calculation formula. The processing of the proposal unit 103 after the score has been calculated may be the same as in the embodiment or Modifications 1 to 7.

[0146] In the modified version 8, proposed system 1 acquires mesh feature information. For each mesh, proposed system 1 calculates a score based on the mesh feature information of that mesh. As a result, proposed system 1 can calculate the score considering the features of the mesh, thereby improving the accuracy of the proposal.

[0147] [6-9. Modification 9] For example, the process by which the proposal unit 103 makes a proposal based on the score is not limited to the embodiments and modifications 1 to 8. Modification 9 describes a case where a proposal is made based on a learning model that has been trained using a machine learning technique. The machine learning technique may be the same as known techniques. For example, the learning model may be a neural network, a support vector machine, a large-scale language model, or another model. The learning model may be input not only the score but also user characteristics.

[0148] The proposed system 1 of Modification 9 includes a user characteristic information acquisition unit 108. The user characteristic information acquisition unit 108 acquires user characteristic information about the characteristics of each of several users who have visited a merchant and used the payment service. User characteristics can be any characteristics that may influence the use of the payment service. For example, user characteristics may be the user's demographic information (e.g., age, age group, gender, or occupation), the user's usage history information, information about the usage history of other services other than the payment service, or other information. They may also be information stored in the user database DB2 associated with the user ID.

[0149] In Modification 9, the user database DB2 is assumed to store user characteristic information. The user characteristic information acquisition unit 108 acquires user characteristic information for each of multiple users who have visited a merchant and used the payment service from the user database DB2. User characteristic information may also be stored in a database other than the user database DB2, a computer other than the server 10, or an information storage medium. The user characteristic information acquisition unit 108 may acquire user characteristic information from a database other than the user database DB2, a computer other than the server 10, or an information storage medium.

[0150] Figure 10 shows an example of the input and output of the learning model in Modification 9. The suggestion unit 103 of Modification 9 takes the score calculated for each mesh and the user characteristic information of each of the multiple users who visited the target merchant and used the payment service as input to the learning model, which has learned the relationship between the training score and user characteristic information and the content of the training suggestion, and makes a suggestion based on the output from the learning model.

[0151] The training data used in training a learning model includes an input portion that is input to the learning model during training, and an output portion that represents the correct answer during training. The input portion consists of training scores and user feature information. The output portion consists of the training proposal content. In Modification 9, the case where training is performed by Server 10 is given as an example, but training may be performed by a computer other than Server 10. Server 10 trains the learning model so that when the input portion of the training data is input to the learning model, the output portion of the training data is output. The input portion may include user feature information for each of multiple users for training, or it may include user feature information for one user for training. Similarly, during estimation, it may include user feature information for each of multiple users to be estimated, or it may include user feature information for one user for estimation.

[0152] For example, a learning model includes a program that processes the data input to it (e.g., calculates an embedding representation) and parameters referenced by that program (e.g., weights or biases). Server 10 calculates a loss that shows the difference between the output from the learning model during learning and the output portion of the training data. Server 10 trains the learning model by adjusting the parameters to minimize the loss. The loss function used in calculating the loss is stored in the data storage unit 100. The method for calculating the loss may be a known method. For example, Server 10 may calculate the loss based on a loss function used in backpropagation or gradient descent and then train the learning model.

[0153] For example, the proposal unit 103 inputs the score calculated for each mesh and the user characteristic information of each of the multiple users who visited the target merchant and used the payment service into a trained model. The trained model calculates an embedded representation of this information input to itself based on the parameters adjusted during training. The trained model outputs the content of the proposal according to the embedded representation. In the case where target users are proposed, as in the embodiment, the trained model outputs the mesh that should be the target users as the content of the proposal. The proposal unit 103 determines all or some of the users whose addresses are in the mesh output from the trained model as target users. In the case where a location is proposed, as in the modified example 6, the trained model outputs the location of a new merchant. The proposal unit 103 proposes the location output from the trained model.

[0154] The proposed system 1 in modified example 9 acquires user feature information about the characteristics of each of multiple users. The proposed system 1 inputs the score calculated for each mesh and the user feature information of each of the multiple users into a learning model that has learned the relationship between the training score and user feature information and the content of the training proposals, and makes a proposal based on the output from the learning model. As a result, the proposed system 1 can make proposals that take user characteristics into consideration in the learning model, thereby improving the accuracy of the proposals.

[0155] [6-10. Other variations] For example, the above variations may be combined.

[0156] For example, the functions described as being implemented on server 10 may be implemented on merchant terminal 20, user terminal 30, or other computers. The functions described as being implemented on server 10 may be shared among multiple computers. For example, the functions described as being implemented on server 10 may be shared among multiple computers.

[0157] [7. Addendum] For example, the proposed system can also be configured as follows:

[0158] (1) An address information acquisition unit that acquires address information for each of the addresses of multiple users who visit a participating store of a designated service and use the said service, A score calculation unit calculates a score for each mesh in a region divided into multiple meshes, based on the address information of each of the multiple users, based on the number of users whose address is located in that mesh. Based on the score calculated for each mesh, a proposal unit makes proposals regarding the member stores, A proposal system that includes this. (2) The score calculation unit aggregates the number of users whose addresses are located in each mesh, and calculates a mesh score for that mesh, which represents the number of users in that mesh, as the score for that mesh. The proposal unit makes the proposal based on the mesh score calculated for each mesh. (1) The proposed system described above. (3) The score calculation unit aggregates the number of users whose addresses are located in each mesh, and obtains the surrounding mesh score based on the number of users in other meshes surrounding the mesh as the score for that mesh. The proposal unit makes the proposal based on the surrounding mesh score calculated for each mesh. The proposed system as described in (1) or (2). (4) The proposal unit proposes target users for advertising related to the member store based on the score calculated for each mesh. A proposed system described in any of (1) to (3). (5) The proposed system further includes an action presence / absence information acquisition unit that acquires action presence / absence information regarding whether or not the target user performed an action related to the advertisement after the advertisement was delivered to the target user. The score calculation unit calculates the next score to be used in the next proposal for the target user based on the behavior information, The proposal unit proposes the next target users for delivery based on the next score calculated for each mesh. (4) The proposed system. (6) The proposal unit excludes the target users who did not purchase the action from the target users for the next distribution. (5) The proposed system. (7) The proposed system further includes a viewing status information acquisition unit that acquires viewing status information regarding whether or not the target user viewed the advertisement after the advertisement has been delivered to the target user. The score calculation unit calculates the next score to be used in the next proposal for the target user of the next distribution, based on the viewing status information. The proposal unit proposes the next target users for delivery based on the next score calculated for each mesh. A proposed system described in any of (4) to (6). (8) The proposed system further includes an entry status information acquisition unit that acquires entry status information regarding whether or not the target user entered the advertisement after the advertisement has been delivered to the target user, The score calculation unit calculates the next score to be used in the next proposal for the target user for distribution, based on the entry status information. The proposal unit proposes the next target users for delivery based on the next score calculated for each mesh. A proposed system described in any of (4) to (7). (9) The proposed system is, A behavior information acquisition unit acquires behavior information regarding whether or not the target user purchased the product or service related to the advertisement after the advertisement has been delivered to the target user. A viewing status information acquisition unit acquires viewing status information regarding whether or not the target users viewed the advertisement after the advertisement was delivered to the target users, An entry status information acquisition unit acquires entry status information regarding whether or not the target user entered the advertisement after the advertisement has been delivered to the target user, It further includes, The score calculation unit calculates the next score to be used in the next suggestion for the target user for distribution, based on the activity information, the viewing information, the entry information, and coefficients corresponding to this information. The proposal unit proposes the next target users for delivery based on the next score calculated for each mesh. A proposed system described in any of (4) to (8). (10) The proposal unit proposes locations for new member stores based on the score calculated for each mesh. A proposed system described in any of (1) to (9). (11) The address information acquisition unit acquires the address information corresponding to each of the multiple member stores that compete with each other. The score calculation unit calculates the score for each of the meshes of the plurality of member stores, The proposal unit proposes the location of the new franchise store corresponding to at least one of the multiple franchise stores, based on the score calculated for each of the meshes of the multiple franchise stores. The proposed system described in (10). (12) The proposed system further includes a mesh feature information acquisition unit that acquires mesh feature information relating to the features in the mesh, The score calculation unit calculates the score for each mesh based on the mesh feature information of that mesh. A proposed system described in any of (1) to (11). (13) The proposed system further includes a user characteristic information acquisition unit that acquires user characteristic information relating to the characteristics of each of the multiple users, The proposal unit inputs the score calculated for each mesh and the user characteristic information of each of the multiple users to a learning model that has learned the relationship between the training score and the user characteristic information and the content of the training proposal, and makes the proposal based on the output from the learning model. A proposed system described in any of (1) to (12). [Explanation of Symbols]

[0159] 1 Proposal System, 10 Server, 11,21,31 Control Unit, 12,22,32 Storage Unit, 13,23,33 Communication Unit, 20 Merchant Terminal, 30 User Terminal, 24 Operation Unit, 25 Display Unit, 26 Reading Unit, 100 Data Storage Unit, 101 Address Information Acquisition Unit, 102 Score Calculation Unit, 103 Proposal Unit, 104 Action Presence / Absence Information Acquisition Unit, 105 Browsing Presence / Absence Information Acquisition Unit, 106 Entry Presence / Absence Information Acquisition Unit, 107 Mesh Feature Information Acquisition Unit, 108 User Feature Information Acquisition Unit, N Network, DB1 Merchant Database, DB2 User Database.

Claims

1. An address information acquisition unit that acquires address information for each of the addresses of multiple users who visit a participating store of a designated service and use the said service, A score calculation unit that, based on the address information of each of the multiple users, aggregates the number of users whose address is in a mesh in a region divided into multiple meshes, and calculates a surrounding mesh score based on the number of users in other meshes surrounding the mesh, as a score based on the number of users whose address is in a mesh; A proposal unit that makes proposals regarding the member store based on the surrounding mesh score calculated for each of the aforementioned meshes, A proposal system that includes this.

2. The score calculation unit aggregates the number of users whose addresses are located in each mesh, and calculates a mesh score for that mesh, which represents the number of users in that mesh, as the score for that mesh. The proposal unit makes the proposal based on the mesh score calculated for each mesh. The proposed system according to claim 1.

3. An address information acquisition unit that acquires address information relating to the address of each of several users who visit a store affiliated with a predetermined service and use the service, A score calculation unit calculates a score for each mesh in a region divided into multiple meshes, based on the address information of each of the multiple users, based on the number of users whose address is located in that mesh. Based on the score calculated for each mesh, a proposal unit proposes target users who will be targeted to receive advertisements for the affiliated stores, An action presence / absence information acquisition unit acquires action presence / absence information regarding whether or not the target user took any action related to the advertisement after the advertisement was delivered to the target user. Includes, The score calculation unit calculates the next score to be used in the next proposal for the target user based on the behavior information, The proposal unit proposes the next target users for delivery based on the next score calculated for each mesh. Proposed system.

4. The proposal unit excludes the users who did not take the action mentioned above from the list of users to be delivered next time. The proposed system according to claim 3.

5. An address information acquisition unit that acquires address information relating to the address of each of several users who visit a store affiliated with a predetermined service and use the service, A score calculation unit calculates a score for each mesh in a region divided into multiple meshes, based on the address information of each of the multiple users, based on the number of users whose address is located in that mesh. Based on the score calculated for each mesh, a proposal unit proposes target users who will be targeted to receive advertisements for the affiliated stores, A viewing status information acquisition unit acquires viewing status information regarding whether or not the target users viewed the advertisement after the advertisement was delivered to the target users, Includes, The score calculation unit calculates the next score to be used in the next proposal for the target user of the next distribution, based on the viewing status information. The proposal unit proposes the next target users for delivery based on the next score calculated for each mesh. Proposed system.

6. An address information acquisition unit that acquires address information relating to the address of each of several users who visit a store affiliated with a predetermined service and use the service, A score calculation unit calculates a score for each mesh in a region divided into multiple meshes, based on the address information of each of the multiple users, based on the number of users whose address is located in that mesh. Based on the score calculated for each mesh, a proposal unit proposes target users who will be targeted to receive advertisements for the affiliated stores, An entry status information acquisition unit acquires entry status information regarding whether or not the target user entered the advertisement after the advertisement has been delivered to the target user, Includes, The score calculation unit calculates the next score to be used in the next proposal for the target user for distribution, based on the entry status information. The proposal unit proposes the next target users for delivery based on the next score calculated for each mesh. Proposed system.

7. An address information acquisition unit that acquires address information relating to the address of each of several users who visit a store affiliated with a predetermined service and use the service, A score calculation unit calculates a score for each mesh in a region divided into multiple meshes, based on the address information of each of the multiple users, based on the number of users whose address is located in that mesh. Based on the score calculated for each mesh, a proposal unit proposes target users who will be targeted to receive advertisements for the affiliated stores, A behavior information acquisition unit acquires behavior information regarding whether or not the target user purchased the product or service related to the advertisement after the advertisement has been delivered to the target user. A viewing status information acquisition unit acquires viewing status information regarding whether or not the target users viewed the advertisement after the advertisement was delivered to the target users, An entry status information acquisition unit acquires entry status information regarding whether or not the target user entered the advertisement after the advertisement has been delivered to the target user, Includes, The score calculation unit calculates the next score to be used in the next suggestion for the target user for distribution, based on the activity information, the viewing information, the entry information, and coefficients corresponding to this information. The proposal unit proposes the next target users for delivery based on the next score calculated for each mesh. Proposed system.

8. The proposal unit proposes locations for new member stores based on the score calculated for each mesh. The proposed system according to any one of claims 1 to 7.

9. The address information acquisition unit acquires the address information corresponding to each of the multiple member stores that compete with each other. The score calculation unit calculates the score for each of the meshes of the plurality of member stores, The proposal unit proposes the location of the new franchise store corresponding to at least one of the multiple franchise stores, based on the score calculated for each of the meshes of the multiple franchise stores. The proposed system according to claim 8.

10. The proposed system further includes a mesh feature information acquisition unit that acquires mesh feature information relating to the features in the mesh, The score calculation unit calculates the score for each mesh based on the mesh feature information of that mesh. The proposed system according to any one of claims 1 to 7.

11. The proposed system further includes a user characteristic information acquisition unit that acquires user characteristic information relating to the characteristics of each of the multiple users, The proposal unit inputs the score calculated for each mesh and the user characteristic information of each of the multiple users to a learning model that has learned the relationship between the training score and the user characteristic information and the content of the training proposal, and makes the proposal based on the output from the learning model. The proposed system according to any one of claims 1 to 7.

12. A computer, An address information acquisition step involves obtaining address information for each of the addresses of multiple users who visit a participating store of a designated service and use the said service, A score calculation step in which, based on the address information of each of the multiple users, the number of users whose address is in a mesh is aggregated for each mesh in a region divided into multiple meshes, and a surrounding mesh score is calculated as a score based on the number of users whose address is in a mesh, based on the number of such users in other meshes surrounding the mesh. A proposal step in which a proposal is made regarding the member store based on the surrounding mesh score calculated for each mesh, A proposed method for carrying out this.

13. An address information acquisition unit that acquires address information for each of the multiple users who visit a participating store of a specified service and use the said service. A score calculation unit that, based on the address information of each of the multiple users, aggregates the number of users whose address is in a mesh in a region divided into multiple meshes, and calculates a surrounding mesh score based on the number of users in other meshes surrounding the mesh, as a score based on the number of users whose address is in the mesh. Based on the surrounding mesh score calculated for each of the aforementioned meshes, the proposal unit makes a proposal regarding the affiliated store. A program that makes a computer function.

Images