Information processing device, information processing method, and program

Abstract

The system uses user attribute information, payment history, and / or machine learning output to issue coupons tailored to each user. [Solution] The information processing device generates input data for input into a machine learning model based on user data read from a user master, transaction history data read from a transaction history DB, and coupon usage status data read from a coupon usage status DB; inputs the input data into the machine learning model and receives the output result, the output result including a user ID and a set of coupon IDs and coupon usage probabilities; retrieves coupon data associated with the coupon IDs included in the output result from a coupon master, generates a first list based on the retrieved coupon data and the output result; and provides the coupon list generated based on the first list to the user as recommendation data.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and a program that issue coupons suitable for each card member by using the attribute information, settlement history, and / or output result of machine learning of the card member.

Background Art

[0002] Card companies provide a passenger service to affiliated stores. In this passenger service, it is known that coupons available at a certain affiliated store (e.g., preferential information such as a 5% discount on the purchase price of a specific product for a specified period, point increase, etc.) are provided to card members via a network to encourage the use of that affiliated store. In a conventional system (Patent Document 1) for promoting card use, a plurality of preferential information was provided to cardholders.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, although it was possible to issue preferential information targeted at the general public or preferential information with a limited number of providers, it was not possible to control the provision of coupons for each card member, and when providing coupons, it was not possible to vary the content of the coupons for each card member. That is, it was not possible to issue coupons suitable for each card member. For this reason, even if a card member obtained a coupon, it was not actively used due to its low personalization.

[0005] Traditional coupon services displayed numerous coupons on a website, requiring cardholders to search for and select the one that suited them best. This type of coupon service was cumbersome for cardholders, and therefore, with the exception of a few, it wasn't widely used. Furthermore, the coupons featured on these services were often planned in advance and may not always align with the current purchasing preferences of the participating merchants' customers.

[0006] While member stores had previously issued the same coupons to many potential customers, they had hoped to issue different coupons based on customer attributes, payment history, etc., but had not been able to do so.

[0007] The present invention was made to solve these problems and aims to provide an information processing device, an information processing method, and a program that issue coupons tailored to each cardholder using the cardholder's attribute information, payment history, and / or machine learning output results. [Means for solving the problem]

[0008] To solve the above problems, an information processing apparatus comprising a control unit and a storage unit according to one aspect of the present invention is: The aforementioned storage unit A user master that stores user data associated with a user, A coupon master that stores coupon data for coupons issued by member stores, A transaction history database that stores transaction history data of card payments associated with the aforementioned user, A coupon usage status DB that stores coupon usage status data for coupons acquired and used by the aforementioned user, It is equipped with, The control unit, Reading the user data from the user master, Reading the transaction history data associated with the user data from the transaction history DB, Reading the coupon usage data associated with the user data from the coupon usage database, Based on the attribute information and survey response results of the user data read out, the transaction history data read out, and the coupon usage status data read out, input data for input into the machine learning model is generated. The process involves inputting the aforementioned input data into a machine learning model and receiving the output result, wherein the output result includes a user ID, a coupon ID, and a set of coupon usage probabilities. The process involves obtaining coupon data associated with the coupon ID included in the output result from the coupon master, and generating a first list based on the obtained coupon data and the output result. The coupon list generated at least based on the first list is provided to the user as recommendation data, It is configured to perform the following: [Effects of the Invention]

[0009] According to the present invention, the information processing device will be able to issue and differentiate coupons tailored to each cardholder by utilizing the cardholder's attribute information, payment history, and / or machine learning output results. Merchants will be able to issue and differentiate coupons according to the customer's attributes, payment history, and / or machine learning output results. Cardholders will no longer need to search for and select a coupon that suits their needs from among a large number of coupons, and will be able to obtain coupons tailored to them based on attribute information, payment history, other members' coupon usage history, business requirements, etc. [Brief explanation of the drawing]

[0010] A detailed understanding of the embodiments disclosed herein can be obtained from the following description illustrated in relation to the accompanying drawings. [Figure 1] This is a configuration diagram of the entire system including the information processing apparatus 10. [Figure 2] This is a system configuration diagram of the information processing apparatus 10. [Figure 3] This is a diagram for explaining an example of the data structure of the user master 106. [Figure 4] This is a diagram for explaining an example of the data structure of the franchise master 107. [Figure 5] This is a diagram for explaining an example of the data structure of the transaction history storage unit 108. [Figure 6] This is a diagram for explaining an example of the data structure of the coupon master 109. [Figure 7] This is a diagram for explaining an example of the data structure of the coupon usage status storage unit 110. [Figure 8] This is a diagram for explaining an example of the data structure of the learned data storage unit 111. [Figure 9] This is a diagram for explaining an example of the data structure of the recommendation information storage unit 112. [Figure 10] This is a flowchart for explaining the coupon recommendation data generation process. [Figure 11] This is a flowchart for explaining the process of inputting input data into a machine-learned model and receiving an output result. [Figure 12] This shows an example of a coupon recommendation screen 1200 that displays coupons of different franchises for each user on the user terminal 11.

Mode for Carrying Out the Invention

[0011] (Overall Configuration) FIG. 1 is a configuration diagram of an entire system including an information processing apparatus 10 according to an embodiment of the present invention. The information processing apparatus 10 and the user terminal 11 are communicably connected to each other via a well-known network 13 such as the Internet or a wireless LAN. The information processing apparatus 10 and the franchise computer 12 are communicably connected to each other via a well-known network 14 such as the Internet, a LAN, or a dedicated line. In this specification, the information processing apparatus 10 is described as one apparatus, but the processing of various functions executed by the information processing apparatus 10 may be configured to be executed distributively by a plurality of apparatuses or servers. In FIG. 1, only one user terminal 11 and one franchise computer 12 are shown, but a plurality of these may exist.

[0012] The information processing apparatus 10 generates teacher data for machine learning by extracting attribute information of user data and questionnaire response results from the user master 106, extracting transaction history data from the transaction history storage unit 108, and extracting coupon usage status data from the coupon usage status storage unit 110. The information processing apparatus 10 inputs the teacher data into a machine learning model and causes it to learn. In one embodiment of the present invention, the information processing apparatus 10 may select a predetermined tag based on the attribute information of the user data, the questionnaire response results, and the transaction history data, associate the selected tag with the user, and include the tag in the teacher data for machine learning.

[0013] The information processing apparatus 10 inputs input data generated based on the most recent user data and transaction history data into a machine learning model and receives an output result. The input data may include tags. The information processing apparatus 10 generates a recommended coupon list for each user based on the output result and the data of the special coupon information 607 in the coupon master 109.

[0014] In this specification, "coupon" refers to benefit information that can be used at participating stores when purchasing goods or services. One form of coupon use is for a user to acquire a coupon on a designated website and then make a payment at a participating store associated with the acquired coupon. Later, the coupon acquisition data and payment data are compared to identify the use of the coupon after acquisition, and points or cashback are awarded to the user. Another form of use is for a button such as "Proceed to Shop" to be provided when acquiring a coupon on a designated website. When this button is pressed, the user is redirected to an online shop, and points are awarded when an e-commerce payment is made at that online shop. Coupons may include readable codes such as barcodes or QR codes, and participating stores may award the benefits associated with the coupon to the user by reading the code at the time of payment. Information that a coupon has been used is stored in the coupon usage status storage unit 110 of the information processing device 10.

[0015] The process for generating the training data described above will now be explained in detail. The information processing device 10 generates first input data as training data based on the attribute information of user data and survey response results from the user master 106 up to month N-2, the transaction history data from the transaction history storage unit 108, and the coupon usage status data from the coupon usage status storage unit 110. The information processing device 10 inputs the training data (first input data) into the machine learning model and trains it. The information processing device 10 performs the training data generation process weekly and inputs the generated training data into the machine learning model, thereby allowing the machine learning model to be trained regularly.

[0016] The process for generating the input data to obtain the above output results will be explained in detail. The information processing device 10 generates the attribute information and survey response results of user data from the user master 106 and the transaction history data from the transaction history storage unit 108 as second input data, up to week M+1 of month N-1, i.e., for the most recent three months. The information processing device 10 inputs the second input data into the machine learning model. Subsequently, the information processing device 10 receives the usage probability for each coupon in week M of month N as the output result from the machine learning model. Based on the output result and the data of special coupon information 607 in the coupon master 109, the information processing device 10 generates a list of recommended coupons for each user.

[0017] The information processing device 10 can input coupon acquisition history as training data into a machine learning model, enabling it to recommend the most suitable coupons for each individual user based on not only the user's own coupon acquisition history but also that of other users. The information processing device 10 can provide the recommended coupons to the user terminal 11 in order of highest probability of use, making it easier for users to find coupons that are more suitable for them.

[0018] The information processing device 10 can generate tags based on all or part of the user's attribute information, survey responses, location information, and transaction history data, and set the generated tags to the user tags 306 in the user data. In other words, tags generated based on all or part of each user's attribute information, survey responses, location information, and transaction history data can be associated with each user. Furthermore, the information processing device 10 can generate each tag at a predetermined interval (for example, on a predetermined day each month) and update the value of the user tags 306 with the generated tags. By associating tags with coupons, the information processing device 10 can select coupons to provide to the user based on the information in the user's tags.

[0019] The information processing device 10 can automatically display the selected coupon in the application used by the user and notify the user that the coupon has been granted (for example, via push notification, email notification, etc.). Based on the location information provided by the user terminal 11, the information processing device 10 queries the coupon master 109 to extract coupons from participating stores whose location information matches that of a specific area 608. From the extracted coupons, the information processing device 10 can prioritize providing those with high usability to the user terminal 11 based on the user's attribute information, survey responses, and transaction history data.

[0020] The user terminal 11 may be any type of device capable of operating in a wireless environment (e.g., a smartphone, a tablet, etc.) and is not limited to any specific device. The user terminal 11 can transmit the answers to the questionnaire provided by the information processing device 10 to the information processing device 10. The user terminal 11 can execute the application program according to the present invention and display information such as coupons transmitted from the information processing device 10 via the application program on its display.

[0021] The merchant computer 12 may be any type of device capable of operating in a wired or wireless environment (e.g., a PC, a tablet, etc.), and is not limited to any specific device.

[0022] The merchant computer 12 can transmit attribute information of users that the merchant wishes to target among potential customers, and coupon data associated with that attribute information, to the information processing device 10. The merchant computer 12 can transmit special coupon information to the information processing device 10. The merchant computer 12 can specify the coupon distribution time and / or distribution area for the information processing device 10. The coupon distribution time may be immediate (i.e., real time) or for a predetermined period (for example, from immediately before the event to the day of the event). The distribution area indicates a geographical area, and for example, when the user terminal 11 enters that geographical area, a coupon selected based on the user's attribute information, survey responses, and transaction history data is pushed to the user terminal 11.

[0023] Coupons can be of various types. For example, there may be coupons that can be used repeatedly after acquisition as long as they are within their validity period, coupons that can only be used once, coupons that can only be used by first-time users at the participating store, or coupons that award bonus points for multiple payments under specific conditions. The information processing device 10 can associate point services with coupons and change the coupon redemption rate when points are used for payment at the time of settlement (for example, 5% discount → 6% discount, +3.0% points awarded, etc.).

[0024] (System Configuration) Figure 2 is a system configuration diagram of an information processing device 10 according to an embodiment of the present invention. As shown in Figure 2, the information processing device 10 includes a control unit 101, a main memory unit 102, an auxiliary memory unit 103, an IF unit 104, and an output unit 105, which are interconnected by a bus 120 or the like, similar to a general computer. The information processing device 10 may include a user master 106, a merchant master 107, a transaction history storage unit 108, a coupon master 109, a coupon usage status storage unit 110, a learned data storage unit 111, and a recommendation information storage unit 112 in the form of a file / database (DB).

[0025] The control unit 101, also known as the central processing unit (CPU), controls each component of the information processing device 10 and performs data calculations. It also reads various programs stored in the auxiliary storage unit 103 into the main memory unit 102 and executes them. The main memory unit 102, also known as main memory, stores various received data, computer-executable instructions, and data after calculations performed by those instructions. The auxiliary storage unit 103 is a storage device such as a hard disk drive (HDD) or solid-state drive (SSD), and is used for long-term storage of data and programs.

[0026] The embodiment shown in Figure 2 describes an embodiment in which the control unit 101, main memory unit 102, and auxiliary storage unit 103 are located inside the same computer. However, in other embodiments, the information processing device 10 can be configured to achieve parallel distributed processing by multiple computers by using multiple control units 101, main memory unit 102, and auxiliary storage unit 103. In another embodiment, it is also possible to set up multiple servers for the information processing device 10, and have multiple servers share a single auxiliary storage unit 103.

[0027] The IF unit 104 acts as an interface (IF) for sending and receiving data with other systems and devices, and also provides an interface for receiving various commands and input data (various masters, tables, etc.) from the system operator. The output unit 105 provides a display screen for displaying the processed data and printing means for printing the data.

[0028] The user master 106 stores user data, which is master information associated with a user. In this specification, a user may mean a cardholder. In the embodiments described herein, "card" is used as an example of a credit card, but "card" may include any payment card other than a credit card, such as a prepaid card, debit card, or electronic money. Credit cards may include both proprietary cards and co-branded cards, or only any type of card may be included. Figure 3 is a diagram illustrating an example of the data structure of the user master 106. The user master 106 may include a user ID 301, user information 302, card number 303, attribute information 304, survey response results 305, and user tags 306, but is not limited to these data items and can include other data items as well. For example, the user data stored in the user master 106 may have information indicating the point in time the data is from, and immediately after an update, it may also have information about the user data before the update.

[0029] User ID 301 is an identifier that identifies the user who holds the card. User information 302 indicates information related to the user, such as username, notification information such as email address, and authentication information for logging into sites provided by the information processing device 10. Card number 303 indicates one or more card numbers associated with the user. In other words, a user can hold one or more cards. This card may be a family card held by a family member of the user.

[0030] Attribute information 304 indicates attribute information associated with the user, such as age (20s, 50s, etc.), gender, place of residence (e.g., prefecture, city / county / district, etc.), occupation, employment status, and whether or not the user has a family. Survey response results 305 indicate information from a survey provided by the information processing device 10 to understand the preferences of the user and / or the user's family. User tags 306 indicate keywords for assigning coupons to the user. The value of the user tag can be generated based on all or some of the user's attribute information, survey response results, location information, and transaction history data.

[0031] Returning to Figure 2, the merchant master 107 stores merchant data, which is master information for merchants. Figure 4 is a diagram illustrating an example of the data structure of the merchant master 107. The merchant master 107 can include merchant ID 401 and merchant information 402, but is not limited to these data items and can include other data items as well.

[0032] Merchant ID 401 is the identifier for the merchant. A merchant refers to a store, facility, or e-commerce business that enters into a merchant agreement with a credit card company or similar entity to provide specific services such as card payments. Merchant Information 402 shows information about the merchant, such as the merchant's name, industry, and geographical area of ​​location.

[0033] Returning to Figure 2, the transaction history storage unit 108 stores transaction history data for card payments associated with the user. Figure 5 is a diagram illustrating an example of the data structure of the transaction history storage unit 108. The transaction history storage unit 108 may include payment ID 501, sales date 502, card number 503, merchant ID 504, merchant name 505, industry 506, and payment amount 507, but is not limited to these data items and can include other data items as well.

[0034] The payment ID 501 is the identifier of the payment that formed the basis of the transaction history data. The sales date 502 indicates the date the payment was made. The card number 503 indicates the card number of the card used for the payment. The merchant ID 504 indicates the identifier of the merchant where the payment was made. The merchant name 505 indicates the name of the merchant where the payment was made. The industry 506 indicates the industry of the merchant where the payment was made. The payment amount 507 indicates the payment amount for the transaction.

[0035] Returning to Figure 2, the coupon master 109 stores coupon data, which is master information for coupons issued by participating merchants. Figure 6 is a diagram illustrating an example of the data structure of the coupon master 109. The coupon master 109 can include coupon ID 601, merchant information 602, coupon name 603, validity period 604, benefit details 605, target users 606, special coupon information 607, and specific area 608, but is not limited to these data items and can include other data items as well.

[0036] Coupon ID 601 is the identifier of the coupon, which is benefit information that can be used at participating stores when purchasing goods or services. Participating store information 602 shows information about participating stores where the coupon can be used, such as the identifier of the participating store, the store name, the type of business, and the geographical area. Coupon name 603 shows the name of the coupon, such as the store name or campaign name. Validity period 604 shows the period during which the coupon can be used. Benefit details 605 shows the benefits that the user can receive by using the coupon, such as a discount on the payment amount (e.g., a discount through cashback), increased points awarded, or acquisition of novelty items.

[0037] Target users 606 indicate information about users who are eligible to receive coupons, such as users tagged with a specific name, users of a specific age group, or residents or employees of a specific geographical area. Target users 606 may be determined by the participating store providing the benefit or an organization associated with that store (e.g., a department store). Special coupon information 607 indicates information about coupons to be provided to the user when there are no coupons from participating stores recommended to the user, or information about coupons from participating stores that are always provided to users who meet certain conditions. Specific area 608 indicates the area conditions for providing the participating store's coupon to the user terminal 11 when the user terminal 11 enters a specific area. Area conditions may be, for example, within a certain range from a specific point.

[0038] Returning to Figure 2, the coupon usage status storage unit 110 stores coupon usage status data indicating that a coupon has been acquired and used by a user. Figure 7 is a diagram illustrating an example of the data structure of the coupon usage status storage unit 110. The coupon usage status storage unit 110 may include user ID 701, user information 702, coupon ID 703, coupon acquisition date 704, coupon usage date 705, merchant ID 706, card number 707, and payment amount 708, but is not limited to these data items and can include other data items as well.

[0039] User ID 701 is an identifier that identifies the user who obtained and used the coupon. User information 702 indicates the user name and attribute information associated with the user ID. Coupon ID 703 is an identifier of the coupon used. Coupon acquisition date 704 indicates the date the user obtained the coupon, and coupon usage date 705 indicates the date the user used the coupon. In this invention, since the information processing device 10 grants the coupon to the user, the acquisition date is the same as the grant date. Merchant ID 706 indicates the identifier of the merchant where the coupon was used. Card number 707 indicates the card number used for payment when the coupon was used. Payment amount 708 indicates the payment amount when the coupon was used.

[0040] Returning to Figure 2, the trained data storage unit 111 stores trained data used when outputting information to recommend coupons to the user. The trained data is generated from the data stored in the user master 106, transaction history storage unit 108, coupon master 109, and coupon usage status storage unit 110. Figure 8 is a diagram illustrating an example of the data structure of the trained data storage unit 111. The trained data storage unit 111 can include user ID 801, coupon ID 802, coupon usage date 803, merchant ID 804, merchant name 805, user attribute information 806, survey response results 807, user tag 808, merchant industry 809, and payment amount 810, but is not limited to these data items and can include other data items as well.

[0041] User ID 801 is an identifier that identifies the user. Coupon ID 802 is an identifier for the coupon. Coupon Usage Date 803 is the date on which payment was made using the coupon. Merchant ID 804 and Merchant Name 805 indicate the identifier and name of the merchant where payment was made using the coupon. User Attribute Information 806 shows the attribute information of the user who made payment using the coupon at the merchant, such as age, gender, place of residence, occupation, employment status, and whether or not they have a family. Survey Response Results 807 shows the information of the survey results answered by the user. User Tag 808 shows a quantitative representation of the user's consumer behavior characteristics. Merchant Industry 809 indicates the industry of the merchant where payment was made using the coupon. Payment Amount 810 indicates the payment amount of the payment made using the coupon.

[0042] Returning to Figure 2, the recommendation information storage unit 112 stores recommendation data for coupons to be provided to the user. Figure 9 is a diagram illustrating an example of the data structure of the recommendation information storage unit 112. The recommendation information storage unit 112 may include user ID 901, coupon ID 902, coupon name 903, coupon validity period 904, coupon content 905, and coupon usage probability 906, but is not limited to these data items and can include other data items as well.

[0043] User ID 901 is an identifier that identifies the user. Coupon ID 902 is an identifier for the coupon. Coupon Name 903 indicates the name of the coupon, for example, the name of the participating store or campaign. Coupon Validity Period 904 indicates the period during which the coupon can be used. Coupon Details 905 indicates the details of the benefits that the user can receive by using the coupon (e.g., discount (cashback), point increase, etc.). Coupon Usage Probability 906 indicates the estimated probability of a user using the coupon, based on the trained data.

[0044] (Processing flow: Recommendation data generation process) Figure 10 is a flowchart illustrating the coupon recommendation data generation process according to the present invention. In the following processing flow, for the sake of explanation, user data is read one by one and the processing described below is performed; however, in the present invention, multiple user data may be read and processed together.

[0045] In S1001, the information processing device 10 reads user data from the user master 106. The read user data may include information such as user ID, user information (user name, notification recipient information, etc.), card number, attribute information (age, gender, place of residence, occupation, employment type, workplace, family status, etc.), survey response results, and user tags. The survey response results may include information such as whether the user prefers coupons for everyday shopping or coupons for special, high-value purchases, whether they prefer e-commerce (online) coupons or coupons for physical stores, and which category of coupons they would like from among multiple categories (e.g., fashion, gourmet, lifestyle, healthcare, beauty, travel, leisure / outdoor, hobbies, etc.). Survey questions are generated by the information processing device 10 at any time, asked to the user, and stored in the user master 106 after receiving the user's response. The survey may be conducted at any interval. User tags are generated based on all or some of the following information: user attribute information, survey responses, location information, and transaction history data, and are updated at predetermined intervals.

[0046] In S1002, the information processing device 10 queries the transaction history storage unit 108 based on the card number of the user data it has read, and reads transaction history data for a predetermined period associated with the user. The predetermined period may be a period that is sufficient to secure a sufficient amount of data to generate recommendation data, for example, the most recent year or the most recent six months.

[0047] In S1003, the information processing device 10 queries the coupon usage status storage unit 110 based on the read user ID and reads the coupon usage status data associated with the user.

[0048] In S1004, the information processing device 10 determines whether the transaction history data read in S1002 exists. If it determines that it exists, the process proceeds to S1005; on the other hand, if it determines that it does not exist, the process proceeds to S1008.

[0049] In S1005, the information processing device 10 determines whether the coupon usage data read in S1003 exists. If it determines that the coupon usage data exists, the process proceeds to S1006; otherwise, the process proceeds to S1007.

[0050] In S1006, the information processing device 10 generates input data based on the attribute information and survey response results of the user data read from the user master 106, the transaction history data from the transaction history storage unit 108, and the coupon usage status data from the coupon usage status storage unit 110, inputs it into the machine learning model, and receives the output result. The input data may include information such as user ID, coupon ID, coupon usage date, merchant ID, merchant name, whether or not a coupon was used, attribute information (age, gender, place of residence, occupation, employment type, family status, etc.), merchant industry, and payment amount, but the present invention is not limited to this information and may include any other information. The output result may include the user ID and a set of one or more coupon IDs and coupon usage probability.

[0051] The information processing device 10 reads coupon data from the coupon master 109 based on the output coupon ID, processes the data in association with the user ID, and generates it as a first list. The first list may include, for example, a user ID, a set of one or more coupon IDs and coupon usage probabilities, and coupon data, but the present invention is not limited to this information and may include any other information.

[0052] Now, with reference to Figure 11, the process performed in S1006 will be explained in more detail.

[0053] In S1101, the information processing device 10 generates training data (first input data) based on user data from the user master 106 up to month N-2, coupon usage data from the coupon usage status storage unit 110, and transaction history data from the transaction history storage unit 108. N represents the current month. The user data may include all or part of the attribute information 304, the survey response results 305, and the user tag information 306. The information processing device 10 inputs the generated training data into a machine learning model for training. This training may be performed at a predetermined time each month.

[0054] In S1102, the information processing device 10 generates input data (second input data) for the machine learning model based on user data from the user master 106 for the most recent three months up to week M+1 of month N-1, and transaction history data from the transaction history storage unit 108. The user data may include all or part of the attribute information 304, the survey response results 305, and the user tag 306 information. The information processing device 10 inputs the input data and a prompt to the machine learning model requesting it to calculate the probability of using each coupon in week M of month N based on this input data. The information processing device 10 may execute the process in S1102 at a predetermined time before week M of month N arrives. M can represent the following week, but it may also be the week after that.

[0055] In S1103, the information processing device 10 obtains coupon usage probability data for week M of month N as an output result from the machine learning model. In one embodiment of the present invention, a collaborative filtering algorithm may be used to display coupons that other users similar to the user themselves would use. The calculation of coupon usage probability may be performed based on attribute information identical or similar to the user, survey response results, and coupon usage data of other users who have all or part of the user tag.

[0056] In S1104, the information processing device 10 queries the coupon master 109 based on the coupon ID included in the usage probability data for each acquired coupon to obtain coupon data, processes the data by associating the usage probability data for each coupon with the acquired coupon data and the user ID, and generates a first list. The first list may include, for example, the user ID, one or more coupon IDs and a set of usage probabilities, but the present invention is not limited to this information and may include any other information.

[0057] Returning to Figure 10, in S1007, the information processing device 10 calculates the number of settlements and the total settlement amount for each industry from the transaction history data read in S1002. For example, if the following number of settlements and total settlement amounts are calculated, User (20s, male, residing in ◇◇ Ward, △△ City) 1st place: "Hobby" category - XX items, XX million yen 2nd place: "Gourmet" category, △ items, 〇 million yen The information processing device 10 estimates that coupons for industries in categories with a high number of recent transactions and / or high transaction amounts are more beneficial to the user, and reads coupon data associated with the estimated industry categories from the coupon master 109. The number of items read may be a predetermined number, and more coupons may be read for higher-ranking categories. If there are categories with a high number of transactions but low transaction amounts, and categories with a low number of transactions but high transaction amounts, the information processing device 10 may be configured to predetermine which is more beneficial to the user.

[0058] The information processing device 10 processes the read coupon data by associating it with the user ID and generates it as a second list. The data structure of the second list may be the same as the data structure of the first list.

[0059] In S1008, the information processing device 10 determines at least one piece of information from the attribute information of the user data read in S1001 (age, gender, place of residence, occupation, employment type, workplace, family status, etc.) as a prediction condition. Based on the determined prediction condition (for example, the three factors of age, gender, and place of residence), the information processing device 10 queries the user master 106 to calculate the number of each user preference shown in the questionnaire response results 305 or user tag 306. For example, if the following numbers are calculated, User (30s, female, XX city) 1st place: "Fashion" category (xxxxx items) 2nd place: "Gourmet" category △△△△△ items 3rd place: "Hobby" category ◇◇◇◇ items The information processing device 10 estimates that higher-ranking categories are more popular, and reads coupon data associated with the industry of the estimated category from the coupon master 109. The number of items read may be a predetermined number, and more coupons may be read for higher-ranking categories.

[0060] The information processing device 10 processes the read coupon data by associating it with the user ID and generates it as a third list. The data structure of the third list may be the same as the data structure of the first list.

[0061] In S1009, the information processing device 10 merges the first to third lists generated by the processes in S1006 to S1008 to generate a list of recommended coupons for each user.

[0062] In S1010, the information processing device 10 queries the coupon master 109 to read coupon data that contains information in the special coupon information 607. If the information of the target user 606 in the read coupon data matches the specified information among the attribute information 304 associated with the user, the information processing device 10 adds the coupon data to the coupon list generated in S1009. As a result, a user's coupon list can include information from one of the first to third lists as well as the special coupon information, enabling the recommendation of different coupons to each user. The information contained in the special coupon information 607 can also indicate a coupon that is given to all users, such as "Give this coupon to all users regardless of the user's attribute information." In this case, the information processing device 10 can add the coupon to the coupon list for all users. Furthermore, if there is no coupon data that contains information in the special coupon information 607, a user's coupon list will only contain information from one of the first to third lists. In this case, the coupon list of a user is likely to be different from that of other users.

[0063] The information processing device 10 can provide the coupon list generated by the above processing to the user terminal 11 as user-specific coupon recommendation data. One user may receive recommendation data based on the first list, another user may receive recommendation data based on the second list, and yet another user may receive recommendation data based on the third list.

[0064] Figure 12 shows an example of a coupon recommendation screen 1200 that displays different coupons from participating merchants for each user on the user terminal 11. The coupon recommendation screen 1200 includes at least a coupon information display area 1201. The coupon information display area 1201 is an area that displays information about coupons recommended to the user.

[0065] The information processing device 10 can display different coupons to each user, even for coupons from the same merchant, via the coupon recommendation screen 1200. In Figure 12(a), user A is a user who has been using contactless payment for some time, so they receive the usual benefits. However, in Figure 12(b), user B has just started using contactless payment, so they are shown benefits that are more favorable than the usual benefits to encourage them to use the service. Information such as whether or not users use various services such as contactless payment and when they started using them is stored in the user master 106, and the information processing device 10 can use this information to display different coupons.

[0066] Subsequently, the user can obtain the benefits indicated on the coupon by using the acquired coupon when making a payment at a participating store, just as before. Information on the used coupon is transmitted from the participating store's computer to the information processing device 10, and the coupon usage status data in the coupon usage status storage unit 110 is updated.

[0067] Although the principles of the present invention have been described above with reference to exemplary embodiments, those skilled in the art will understand that various embodiments with modifications in configuration and details can be realized without departing from the spirit of the invention. That is, the present invention can take the form of, for example, a system, apparatus, method, program, or storage medium. [Explanation of symbols]

[0068] 10 Information Processing Devices 11 User terminals 12. Merchant Computer 13, 14 Network 101 Control Unit 102 Main memory 103 Auxiliary storage 104 IF section 105 Output section 106 User Master 107 Merchant Master 108 Transaction history storage unit 109 Coupon Master 110 Coupon Usage Status Storage Unit 111 Pre-trained data storage unit 112 Recommendation Information Storage Unit

Claims

1. An information processing device comprising a control unit and a storage unit, The aforementioned storage unit is A user master that stores user data associated with a user, A coupon master that stores coupon data for coupons issued by member stores, A transaction history database that stores transaction history data of card payments associated with the aforementioned user, A coupon usage status DB stores coupon usage status data for coupons acquired and used by the aforementioned user, Equipped with, The control unit, Reading the user data from the user master, Reading the transaction history data associated with the user data from the transaction history DB, The coupon usage status data associated with the user data is read from the coupon usage status DB, Based on the attribute information and survey response results of the user data read out, the transaction history data read out, and the coupon usage status data read out, input data for input into the machine learning model is generated. The process involves inputting the aforementioned input data into a machine learning model and receiving the output result, wherein the output result includes a user ID, a coupon ID, and a set of coupon usage probabilities. The coupon data associated with the coupon ID included in the output result is obtained from the coupon master, and a first list is generated based on the obtained coupon data and the output result. The coupon list generated at least based on the first list is provided to the user as recommendation data, An information processing device configured to perform the following actions.

2. This involves querying the aforementioned coupon master to retrieve a second coupon data containing special coupon information, If the information of the target user of the second coupon data read out matches predetermined information among the attribute information of the user data, the second coupon data is added to the coupon list. The information processing apparatus according to claim 1, configured to further perform the following:

3. Determine whether the retrieved transaction history data exists, and then determine whether the retrieved coupon usage status data exists, If the retrieved transaction history data exists and the retrieved coupon usage status data exists, The process involves generating input data to be input into the aforementioned machine learning model, The input data is input to the machine learning model, and the output result is received. The coupon data associated with the coupon ID included in the output result is obtained from the coupon master, and a first list is generated based on the obtained coupon data and the output result. The information processing apparatus according to claim 1, further configured to perform the following:

4. Determine whether the retrieved transaction history data exists, and then determine whether the retrieved coupon usage status data exists, If the retrieved transaction history data exists, and the retrieved coupon usage status data does not exist, To calculate the number of settlements and the total settlement amount for each industry from the transaction history data read out, Reading third coupon data from the coupon master that is associated with the industry in which the calculated number of transactions and / or total transaction amount is relatively large, To generate a second list based on the third coupon data, The coupon list generated at least based on the second list is provided to the user as recommendation data, The information processing apparatus according to claim 1, configured to further perform the following:

5. Determine whether the retrieved transaction history data exists, and then determine whether the retrieved coupon usage status data exists, If the transaction history data read out does not exist, Determine at least one piece of attribute information from the read user data as a prediction condition, Based on the aforementioned prediction conditions, the user master is queried to calculate the number of users for each user preference indicated in the user data's survey responses or user tags, The fourth coupon data, associated with the industry category having a relatively large number of the calculated user preferences, is read from the coupon master. To generate a third list based on the aforementioned fourth coupon data, Providing the coupon list generated at least based on the third list to the user as recommendation data to the user, The information processing apparatus according to claim 1, configured to further perform the following:

6. The process involves generating training data based on the user data from the user master up to month N-2, the coupon usage data from the coupon usage database, and the transaction history data from the transaction history database, where N represents the current month. The training data is input into the machine learning model to train the machine learning model, The information processing apparatus according to claim 1, configured to further perform the following:

7. Based on the user data in the user master for the most recent three months and the transaction history data in the transaction history DB, the input data for input into the machine learning model is generated. The process involves inputting the aforementioned input data and a prompt requesting the model to calculate the probability of using each coupon in week M of month N based on the aforementioned input data, where N represents the current month and M represents the following week. The output results, including the probability of coupon usage data for each coupon in week M of month N, are obtained from the aforementioned machine learning model. The information processing apparatus according to claim 6, which is configured to further perform the following:

8. A method performed by an information processing device comprising a control unit and a storage unit, The aforementioned storage unit is A user master that stores user data associated with a user, A coupon master that stores coupon data for coupons issued by member stores, A transaction history database that stores transaction history data of card payments associated with the aforementioned user, A coupon usage status DB stores coupon usage status data for coupons acquired and used by the aforementioned user, Equipped with, The control unit reads the user data from the user master, The control unit reads the transaction history data associated with the user data from the transaction history DB, The control unit reads the coupon usage status data associated with the user data from the coupon usage status DB, The control unit generates input data for input into the machine learning model based on the attribute information and survey response results of the user data read out, the transaction history data read out, and the coupon usage status data read out. The control unit inputs the input data into a machine learning model and receives the output result, wherein the output result includes a user ID, a coupon ID, and a coupon usage probability set. The control unit obtains coupon data associated with the coupon ID included in the output result from the coupon master, and generates a first list based on the obtained coupon data and the output result. The control unit provides the user with a coupon list generated at least based on the first list as recommendation data for the user. A method for providing this.

9. A program that, when executed, causes a computer to perform the method described in claim 8.

Images