JP7337017B2 - Return value setting system and return value setting method - Google Patents

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a return value setting system and a return value setting method for setting a return value that is a value related to a user's use of a settlement service.

2. Description of the Related Art Conventionally, in payment services such as electronic payment or credit card, points or the like are returned at a predetermined return rate to the user's payment amount. It has been proposed to set the return rate at this time according to the attributes of the user (see Patent Document 1, for example).

JP 2014-137811 A

However, simply setting the return rate according to the attributes of the user may not provide an effective return rate for the operator of the payment service. For example, setting such a return rate may not sufficiently improve the profit associated with the user's use of the settlement service.

The present invention has been made in view of the above, and provides a return value setting system and a return value setting method that can appropriately set a return value that is a value related to a user's use of a settlement service. With the goal.

In order to achieve the above object, a return value setting system according to the present invention is a return value setting system for setting a return value, which is a value related to a user's use of a settlement service, and In addition, a reaction information acquisition unit that acquires reaction information indicating the user's reaction to the set return value in using the payment service, and attribute information that indicates the attribute of the user for whom the return value is set are acquired and acquired. a return value setting unit that sets a return value based on the attribute information and the reaction information acquired by the reaction information acquisition unit , wherein the reaction information is obtained from the attribute information, the set return value, and the set return value. is an estimation model in which past return values are input and user reactions corresponding to the attribute information and return values are output .

In the reward value setting system according to the present invention, since the reward value is determined based on the reaction information, the reward value can be set in consideration of how the user reacts to the reward value. Therefore, according to the return value setting system of the present invention, it is possible to appropriately set the return value for the user's use of the settlement service.

By the way, the present invention can be described as an invention of a return value setting system as described above, and can also be described as an invention of a return value setting method as follows. These are substantially the same inventions with only different categories, and have similar actions and effects.

That is, the return value setting method according to the present invention is a return value setting method that is a method of operating a return value setting system that sets a return value that is a value related to a return for a user's use of a payment service, and is a method for setting a return value that is based on user attributes. a reaction information acquiring step of acquiring reaction information indicating a user's reaction in using the payment service to the set return value according to the set return value; a return value setting step of setting a return value based on the acquired attribute information and the reaction information acquired in the reaction information acquisition step, wherein the reaction information comprises the attribute information, the set return value, and the set It is an estimation model that takes a past return value as an input rather than a return value, and outputs the user's reaction according to the attribute information and the return value.

According to the present invention, it is possible to appropriately set the return value for the user's use of the settlement service.

1 is a diagram showing the configuration of a return value setting system according to an embodiment of the present invention; FIG. 4 is a flow chart showing a return value setting method, which is a process executed by the return value setting system according to the embodiment of the present invention; 1 is a diagram showing a hardware configuration of a return value setting system according to an embodiment of the present invention; FIG.

An embodiment of a return value setting system and a return value setting method according to the present invention will be described in detail below with reference to the drawings. In the description of the drawings, the same elements are denoted by the same reference numerals, and overlapping descriptions are omitted.

FIG. 1 shows a return value setting system 10 according to this embodiment. The return value setting system 10 is a system (apparatus) that sets (adjusts) a return value, which is a value related to a user's use of a settlement service. In this embodiment, the return value setting system 10 sets the return rate as the return value. The settlement service is, for example, a service used for settlement (payment) when a user purchases a product or the like, such as electronic settlement or credit card. A user can use a payment service by making a contract with a payment service provider. In the settlement service according to the present embodiment, points are returned to the user at a predetermined return rate for the user's settlement amount (settlement amount). The points to be returned can be used for payment or exchanged for goods or the like, for example. It should be noted that what is returned to the user may be something other than points, such as a refund (cashback) or a reduction in the amount of subsequent payments.

The return value setting system 10 is used, for example, by a payment service provider. The return value setting system 10 sets the return rate for the settlement service of the business operator. The return rate may be set for each user, or may be set to a uniform value regardless of the user. The return value setting system 10 sets the return rate so that the profit of the payment service provider related to the user's use of the payment service increases, as will be described later.

The return value setting system 10, for example, sets the return rate for the period of the payment service campaign. A campaign is carried out, for example, when a payment service provider wants to increase users' use of the payment service, or wants to increase the number of users of the payment service. In this case, the return rates for periods before and after the campaign period are set in advance as normal return rates. Note that the normal return rate may differ between the periods before and after the campaign. A value higher than the normal return rate is set for the return rate during the campaign period. The return value setting system 10 sets the return rate so that the profit of the payment service provider related to the user's use of the payment service increases during and after the campaign period. However, the period for which the return rate is set by the return value setting system 10 does not necessarily have to be the campaign period described above, and may be any period.

In this embodiment, the return value setting system 10 sets the return rate as the return value. However, if the return value set in the settlement service is not the return rate but the return amount, the return value setting system 10 may set the return amount. In this case, for example, when the user uses the settlement service, points corresponding to the set return amount are returned to the user. When setting the return amount, it can be set in the same manner as in the present embodiment.

The return value setting system 10 is realized by a computer such as a server device, for example. Also, the return value setting system 10 may be implemented by a plurality of server devices, that is, computer systems. In addition, the return value setting system 10 may have a communication function and be able to transmit and receive information to and from other devices as necessary.

Next, functions of the return value setting system 10 according to this embodiment will be described. As shown in FIG. 1 , the return value setting system 10 includes a database 11 , a reaction information acquisition unit 12 and a return value setting unit 13 .

The database 11 is a functional unit that stores information necessary for setting the return rate. The database 11 stores contractor data. The contractor data is information related to the user who is the contractor of the payment service for which the return rate is to be set, and is data for each user. The contractor data includes information in which a user identifier, which is information that identifies a user, is associated with basic user attributes such as the user's age, sex, and place of residence.

In addition, the contractor data may include other user attribute information associated with the user identifier. For example, the contractor data may include, as user attribute information, information specifying a service that the user is using (contracting). The information may be, for example, information specifying a payment service used by the user other than the payment service for which the return rate is set. In addition, the information may be information specifying a service other than the settlement service, such as a mobile communication service, an EC (electronic commerce) service, and a video viewing service, used by the user. The information may also include information indicating the content of each service used by the user (for example, the plan or option used). Further, the information may be information indicating the user's usage status of each service (for example, the number of usages per month). Contractor data is input to the database 11 in advance. Input of information to the database 11 is performed by a payment service provider or the like (the same applies to the following information unless otherwise specified). Note that the attributes of the user in this embodiment may be static attributes as the unique properties and characteristics of the user itself, as described above, or may be dynamic attributes that may change depending on time or circumstances. attribute. Also, the user attributes in this embodiment may include statistical attributes, psychological attributes, and behavioral attributes.

The database 11 stores payment data. The payment data is information related to past payments in the payment service for which the return rate is set, and is data for each payment. The payment data includes information in which information such as a user identifier, payment amount, payment time, store where payment was made, and return rate at the time of payment are associated with each other. That is, the payment data is history information indicating the user's usage history of the payment service according to the past return rate. The payment data is acquired from, for example, a payment service system and stored in the database 11 .

The reaction information acquisition unit 12 is a functional unit that acquires reaction information indicating the user's reaction (sensitivity) in using the payment service to the set return value according to the user's attribute. The reaction information acquisition unit 12 may acquire reaction information in which the type of payment service being used is attributed to the user. The reaction information acquisition unit 12 may acquire reaction information according to past return values as well. The reaction information acquisition unit 12 may acquire history information indicating the user's usage history of the payment service according to the past return value, and generate and acquire reaction information based on the acquired history information. Specifically, the reaction information acquisition unit 12 acquires reaction information as follows.

The reaction information acquiring unit 12 calculates the probability P(A) that the user will use the payment service in the target period for which the return rate is set, and the expected payment when the user uses the payment service, for the set return rate. An estimation model (prediction model) for estimating (predicting) the amount M is generated and obtained. Information used for estimating the probability P(A) and the settlement amount M, that is, as explanatory variables to be input to the estimation model, is the return rate R1 in the target period, the return rate R2 in the period immediately before the target period, and the user's Information X indicating an attribute is used. The target period and the immediately preceding period in the estimation model are, for example, a unit period for which the return rate is set, and are assumed to be one month.

Information X indicating user attributes corresponds to information indicating user attributes stored in the database 11 . For user attributes that are quantified, the values are used as explanatory variables. User attributes that are not quantified are quantified by, for example, a 0-1 variable (binary variable, a variable that is 1 if the corresponding condition is met and 0 if not). may Alternatively, each variable may be generated based on a decision tree from information indicating user attributes. Also, any conventional method other than the above may be used for variableizing (numericalizing) each piece of information.

The reaction information acquisition unit 12 learns and generates (derives) the above two estimation models based on the past data (past performance) stored in the database 11 before setting the return rate. For example, a machine learning technique may be used to generate the estimation model. The form of the estimation model may take any form used in conventional machine learning, and may take the form of formulas or tables. The value of the objective variable when performing machine learning is set based on each piece of information of the user identifier, payment amount, and payment time of the payment data. For example, in an estimation model that estimates the probability P(A), the value of the objective variable is set to 1 if the user uses the payment service during the target period, and 0 if not. In the estimation model for estimating the payment amount M, the total payment amount of users whose payment amount is greater than 0 in the target period.

The value of the explanatory variable is set based on the user identifier of the payment data, information on payment time and return rate, and contractor data. The return rate R1 for the target period and the return rate R2 for the period immediately preceding the target period are set based on the user identifier, settlement time, and return rate information of the payment data. Information X indicating user attributes is set based on the contractor data.

Note that the estimation model may be generated by a method other than the above. Note that the information (explanatory variables) to be input to the above estimation model does not necessarily have to be the above, and may include at least information indicating the return rate and user attributes for the set target period.

As described above, the probability P(A) and the settlement amount M are values (return rates R1, R2 , a function of user attributes X), which can be expressed as P(A|R2, R1, X) and M(R2, R1, X), respectively. A user's expected transaction volume (total payment amount for the payment service) during the target period is estimated as follows.
V(R2, R1, X)=P(A|R2, R1, X) M(R2, R1, X)
The reaction information acquisition unit 12 outputs the above estimation model V (R2, R1, X) to the return value setting unit 13 as reaction information. As will be described later, the expected transaction volume V is estimated for the period of the campaign and the period immediately after the campaign. In this case, the user's attribute X in V(R2, R1, X) needs to correspond to each period, for example, one period before the target period. In that case, the user attribute X used for estimation in the period immediately after the campaign cannot be acquired at the time of estimation. Therefore, it is necessary to assume that the user attribute X used here will not change during the campaign period. That is, it is necessary to limit the user attribute X used for estimation.

In the above, an example of generating and acquiring two estimation models for usage probability and expected transaction volume was shown, but three estimation models are divided for usage probability, expected number of settlements, and settlement amount per settlement. or a single estimation model that directly estimates the potential turnover. Also, the reaction information does not necessarily have to be an estimation model as described above, as long as it indicates the user's reaction to the set return value in accordance with the user's attributes in using the payment service.

The return value setting unit 13 acquires attribute information indicating attributes of a user for whom a return value is to be set, and sets a return value based on the acquired attribute information and the reaction information acquired by the reaction information acquisition unit 12. Department. The return value setting unit 13 may set the return value based on the expected profit (expected profit) of the payment service provider through the use of the user's payment service based on the reaction information. Specifically, the return value setting unit 13 sets the return value as follows.

For example, the return value setting unit 13 sets the return rate Rc for the campaign period for each user. The return rate Rb for the period immediately before the campaign and the return rate Rd for the period immediately after the campaign are set in advance and input to the return value setting system 10 (return value setting unit 13). Further, the profit rate Rp of the payment service with respect to the transaction amount of the user of the payment service is set in advance and input to the return value setting system 10 (return value setting unit 13). In addition, the return value setting unit 13 inputs the expected transaction volume estimation model V (R2, R1, X) from the reaction information acquisition unit 12 . The return value setting unit 13 acquires the information X, which is stored in the database 11 and indicates the attribute of the user for whom the return rate Rc is to be calculated.

Based on the user's expected transaction volume V (Rb, Rc, X) during the campaign period and the user's expected transaction volume V (Rc, Rd, X) during the period immediately after the campaign, settlement is made at the return rate Rc during the campaign period. The service provider's expected profit Profit (Rc) is expressed as follows.
Profit (Rc) = (V (Rb, Rc, X) + V (Rc, Rd, X)) Rp - (V (Rb, Rc, X) Rc + V (Rc, Rd, X) Rd)
Expected profit Profit (Rc) is the expected profit during the period of the campaign and the period immediately after the campaign. The first term ((V(Rb, Rc, X)+V(Rc, Rd, X))·Rp) on the right side of the above equation is the profit on the expected transaction volume of the user's payment service. The second term ((V (Rb, Rc, X) · Rc + V (Rc, Rd, X) · Rd)) on the right side of the above equation is the cost (return cost) returned to the user. It is the value subtracted from the profit of the term. In the above formula of Profit(Rc), all values other than Rc are known, so Profit(Rc) is a value corresponding to Rc, that is, a function with Rc as a variable.

The return value setting unit 13 obtains the return rate Rc ^* for the period of the campaign that maximizes the expected profit Profit (Rc) as follows.
Rc ^* =argmax{Profit(Rc)}
When calculating the return rate Rc ^* for the period of the campaign, the upper limit of Rc may be given as a constraint as necessary. The return value setting unit 13 calculates the return rate Rc ^* for the campaign period by, for example, a conventional mathematical optimization technique. The return value setting unit 13 may calculate the return rate Rc ^* for all users whose contractor data is stored in the database 11, or may calculate the return rate Rc ^* for some preset users. may

In addition, the return value setting unit 13 sets the amount Σ _U {V(Rb, Rc, X)·Rc} (campaign cost) to be returned to the user during the campaign period to be equal to or less than the preset budget amount. A return rate Rc ^* for each user that maximizes the total _ΣU Profit(Rc) of all users of the expected profit Profit(Rc) may be obtained after setting a constraint condition. This calculation can be performed, for example, by conventional combinatorial optimization. Further, the return value setting unit 13 may calculate a uniform return rate Rc for all users for whom the return rate Rc for the period of the campaign is calculated. In that case, the return value setting unit 13 obtains one return rate Rc ^* that maximizes the total _ΣU Profit(Rc) of the expected profits Profit(Rc) of all the users.

In addition, the expected transaction amount V (Rc, Rd, X) in the period immediately after the campaign of Profit (Rc) used to calculate the return rate Rc ^* during the campaign period is may be multiplied by the length of the period in which the expected profit immediately after the campaign is considered to calculate the return rate Rc ^* for the campaign period. For example, the unit period corresponding to the return rates R1 and R2 in the estimation model for estimating the expected transaction volume V (R2, R1, X) is one month, and the length of the period considering the expected profit immediately after the campaign is In the case of three months, V (Rc, Rd, X) of Profit (Rc) may be set to 3V (Rc, Rd, X) to calculate the return rate Rc ^* for the campaign period. Normally, the period during which the normal return rate Rd is set after the campaign is longer than the period of the campaign, and in calculating the return rate Rc ^* during the campaign period, the period during which the normal return rate Rd is set is set longer. This is because it is considered appropriate to consider it.

The return value setting unit 13 outputs information indicating the return rate set as described above by a preset method. For example, the return value setting unit 13 may store information indicating the return rate set for each user in the database 11 as return rate data so that it can be referred to. Alternatively, the return value setting unit 13 may display the information on a display device included in the return value setting system 10 so that the payment service provider or the like can refer to the information. A payment service provider or the like refers to the information, for example, to carry out a campaign with that return rate. Also, the output of information indicating the return rate set by the return value setting unit 13 may be performed by a method other than the above. For example, the return value setting unit 13 may transmit information indicating the set return rate to another device, module, or the like. The functions of the return value setting system 10 according to the present embodiment have been described above.

Subsequently, the return value setting method, which is the processing (operation method of the return value setting system 10) executed by the return value setting system 10 according to the present embodiment, will be described using the flowchart of FIG. This processing is performed at the timing when the return rate is set. For example, this process may be triggered by an operation by a payment service provider or the like.

In this process, first, the reaction information acquisition unit 12 acquires reaction information indicating the reaction of the user in using the payment service with respect to the set return rate according to the user's attribute (S01, reaction information acquisition step ). Subsequently, the return rate setting unit 13 acquires attribute information indicating the attribute of the user for whom the return rate is to be set, and the return rate is set based on the acquired attribute information and the reaction information acquired by the reaction information acquisition unit 12. is set (S02, return value setting step). Subsequently, the return value setting unit 13 outputs information indicating the set return rate (S03). The above is the processing executed by the return value setting system 10 according to the present embodiment.

Subsequently, a modified example according to this embodiment will be described. In the above-described embodiment, the estimation model used as the reaction information was not changed according to the period, but different estimation models may be used according to the period. For example, an estimation model for estimating the expected transaction volume in the period of the campaign and an estimation model for estimating the expected transaction volume in the period immediately after the campaign different from the estimation model may be used. Each estimation model can be generated from each data of the database 11 when the campaign was conducted in the past. In this case, since the timing related to the user's attribute X can be set for each estimation model, it is not necessary to set the above-described limitation on the user's attribute X. FIG.

Also, the return rate may be set for each user segment, which is a group of users, rather than for each user. In this case, for example, a method of calculating the uniform return rate for each user segment can be applied. In that case, the estimation model used as reaction information may be an estimation model for each user segment. Also, the user segments may be divided into active users (active users) and dormant users (inactive users). An active user is a user who has used the payment service for a certain period of time in the past (for example, the past one month), and a dormant user is a user who has not used the payment service for the certain period of time in the past.

In addition, if the transaction amount data for different return rates, that is, the payment data in the database 11 is not sufficiently accumulated to generate an accurate estimation model, the return value setting unit 13 uses a method based on the bandit algorithm to obtain a return value. You can set a rate. That is, even if the return rate setting unit 13 sets a return rate that strikes a balance between the “search” for examining the reaction of the return rate where the expected transaction amount is unclear and the “utilization” for setting the return rate at which a profit can be expected. good. Specifically, by executing a “contextual bandit algorithm” with user attribute information as “context”, the selected return rate as “behavior”, and expected profit as “reward”, we can perform “search” and “search” on a user-by-user basis. The return rate may be updated while maintaining a precise balance with “utilization”.

In the present embodiment, the return rate is determined based on the expected transaction amount of the user according to the return rate and the user's attributes, which are reaction information. Therefore, considering how users react to the return rate (specifically, how much users will use the payment service for the set return rate), You can set the return rate so that the person's profit increases. That is, according to this embodiment, it is possible to appropriately set the return rate for the user's use of the settlement service.

Further, as in the above-described embodiment, the reaction information may be the type of payment service being used as an attribute of the user. According to this configuration, it is possible to appropriately set the return rate in consideration of the user's reaction according to the type of payment service being used. Note that it is not always necessary to use the attributes of the above-described embodiment as the attributes of the user related to the reaction information, and arbitrary attributes of the user may be used.

Further, as in the above-described embodiment, the return rate related to the reaction information is not only the return rate R1 of the period for which the return rate is set, but also the return rate R2 of the period immediately before the target period, that is, the past return rate. may also be in accordance with According to this configuration, it is possible to appropriately set the return rate in consideration of the user's reaction according to the transition of the return rate. However, the return rate related to the reaction information does not need to be a different return rate for a plurality of periods, and may be only the return rate for the period for which the return rate is set.

Further, as in the above-described embodiment, reaction information may be generated and acquired based on the user's payment service usage history corresponding to past return values. According to this configuration, the reaction information can be obtained reliably and appropriately, and the return rate can be set reliably and appropriately. However, it is not always necessary to generate reaction information based on the usage history, and reaction information prepared in advance may be acquired.

Also, as in the above-described embodiment, the return rate may be set based on the expected profit of the payment service provider through the use of the payment service by the user based on the reaction information. According to this configuration, it is possible to appropriately set the return rate from the viewpoint of the profit of the payment service provider. However, the setting of the return rate may be performed based on setting criteria other than the above.

Moreover, the setting of the return rate may be performed by a method using a bandit algorithm as in the above-described embodiment. According to this configuration, even if sufficient transaction volume data for different return rates is not accumulated, a balance is achieved between accumulating transaction volume data suitable for generating an estimation model and improving profits. You can set the redemption rate that can be taken and realized. However, it is not always necessary to use the bandit algorithm method.

It should be noted that the block diagrams used in the description of the above embodiments show blocks in units of functions. These functional blocks (components) are implemented by any combination of at least one of hardware and software. Also, the method of realizing each functional block is not particularly limited. That is, each functional block may be implemented using one device physically or logically coupled, or directly or indirectly using two or more physically or logically separated devices (e.g. , wired, wireless, etc.) and may be implemented using these multiple devices. A functional block may be implemented by combining software in the one device or the plurality of devices.

Functions include judging, determining, determining, calculating, calculating, processing, deriving, examining, searching, checking, receiving, transmitting, outputting, accessing, resolving, selecting, choosing, establishing, comparing, assuming, expecting, assuming, Broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, assigning, etc. can't For example, a functional block (component) that makes transmission work is called a transmitting unit or a transmitter. In either case, as described above, the implementation method is not particularly limited.

For example, the return value setting system 10 according to an embodiment of the present disclosure may function as a computer that performs information processing of the present disclosure. FIG. 3 is a diagram showing an example of the hardware configuration of the return value setting system 10 according to one embodiment of the present disclosure. The return value setting system 10 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

Note that in the following description, the term "apparatus" can be read as a circuit, device, unit, or the like. The hardware configuration of the return value setting system 10 may be configured to include one or more of each device shown in the figure, or may be configured without some of the devices.

Each function of the return value setting system 10 is performed by causing the processor 1001 to perform calculations, controlling communication by the communication device 1004, It is realized by controlling at least one of data reading and writing in the memory 1002 and the storage 1003 .

The processor 1001, for example, operates an operating system to control the entire computer. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic device, registers, and the like. For example, each function in the return value setting system 10 described above may be implemented by the processor 1001 .

The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 to the memory 1002, and executes various processes according to these. As the program, a program that causes a computer to execute at least part of the operations described in the above embodiments is used. For example, each function of the return value setting system 10 may be implemented by a control program stored in the memory 1002 and running on the processor 1001 . Although it has been explained that the above-described various processes are executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. FIG. Processor 1001 may be implemented by one or more chips. Note that the program may be transmitted from a network via an electric communication line.

The memory 1002 is a computer-readable recording medium, and is composed of at least one of, for example, ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), and RAM (Random Access Memory). may be The memory 1002 may also be called a register, cache, main memory (main storage device), or the like. The memory 1002 can store executable programs (program code), software modules, etc. for performing information processing according to an embodiment of the present disclosure.

The storage 1003 is a computer-readable recording medium, for example, an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disc, a magneto-optical disc (for example, a compact disc, a digital versatile disc, a Blu-ray disk), smart card, flash memory (eg, card, stick, key drive), floppy disk, magnetic strip, and/or the like. Storage 1003 may also be called an auxiliary storage device. The storage medium included in the return value setting system 10 may be, for example, a database including at least one of the memory 1002 and the storage 1003, a server, or other suitable medium.

The communication device 1004 is hardware (transmitting/receiving device) for communicating between computers via at least one of a wired network and a wireless network, and is also called a network device, a network controller, a network card, a communication module, or the like.

The input device 1005 is an input device (for example, keyboard, mouse, microphone, switch, button, sensor, etc.) that receives input from the outside. The output device 1006 is an output device (eg, display, speaker, LED lamp, etc.) that outputs to the outside. Note that the input device 1005 and the output device 1006 may be integrated (for example, a touch panel).

Devices such as the processor 1001 and the memory 1002 are connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between devices.

Further, the return value setting system 10 includes hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array). part or all of each functional block may be implemented by the hardware. For example, processor 1001 may be implemented using at least one of these pieces of hardware.

The processing procedures, sequences, flowcharts, etc. of each aspect/embodiment described in this disclosure may be rearranged as long as there is no contradiction. For example, the methods described in this disclosure present elements of the various steps using a sample order, and are not limited to the specific order presented.

Input/output information and the like may be stored in a specific location (for example, memory), or may be managed using a management table. Input/output information and the like can be overwritten, updated, or appended. The output information and the like may be deleted. The entered information and the like may be transmitted to another device.

The determination may be made by a value represented by one bit (0 or 1), by a true/false value (Boolean: true or false), or by numerical comparison (for example, a predetermined value).

Each aspect/embodiment described in the present disclosure may be used alone, may be used in combination, or may be used by switching according to execution. In addition, the notification of predetermined information (for example, notification of “being X”) is not limited to being performed explicitly, but may be performed implicitly (for example, not notifying the predetermined information). good too.

Although the present disclosure has been described in detail above, it should be apparent to those skilled in the art that the present disclosure is not limited to the embodiments described in this disclosure. The present disclosure can be practiced with modifications and variations without departing from the spirit and scope of the present disclosure as defined by the claims. Accordingly, the description of the present disclosure is for illustrative purposes and is not meant to be limiting in any way.

Software, whether referred to as software, firmware, middleware, microcode, hardware description language or otherwise, includes instructions, instruction sets, code, code segments, program code, programs, subprograms, and software modules. , applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, and the like.

Software, instructions, information, etc. may also be sent and received over a transmission medium. For example, the software uses wired technology (coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), etc.) and/or wireless technology (infrared, microwave, etc.) to create websites, Wired and/or wireless technologies are included within the definition of transmission medium when sent from a server or other remote source.

As used in this disclosure, the terms "system" and "network" are used interchangeably.

In addition, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, may be expressed using relative values from a predetermined value, or may be expressed using other corresponding information. may be represented.

As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Judgement", "determining" are, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (eg, lookup in a table, database, or other data structure); Also, "judgment" and "determination" are used for receiving (e.g., receiving information), transmitting (e.g., transmitting information), input, output, access (accessing) (for example, accessing data in memory) may include deeming that a "judgment" or "decision" has been made. In addition, "judgment" and "decision" are considered to be "judgment" and "decision" by resolving, selecting, choosing, establishing, comparing, etc. can contain. In other words, "judgment" and "decision" may include considering that some action is "judgment" and "decision". Also, "judgment (decision)" may be read as "assuming", "expecting", "considering", or the like.

The terms "connected", "coupled", or any variation thereof, mean any direct or indirect connection or coupling between two or more elements, It can include the presence of one or more intermediate elements between two elements being "connected" or "coupled." Couplings or connections between elements may be physical, logical, or a combination thereof. For example, "connection" may be read as "access". As used in this disclosure, two elements are defined using at least one of one or more wires, cables, and printed electrical connections and, as some non-limiting and non-exhaustive examples, in the radio frequency domain. , electromagnetic energy having wavelengths in the microwave and optical (both visible and invisible) regions, and the like.

As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly specified otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

Any reference to elements using the "first," "second," etc. designations used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, reference to a first and second element does not imply that only two elements can be employed or that the first element must precede the second element in any way.

Where "include," "including," and variations thereof are used in this disclosure, these terms are inclusive, as is the term "comprising." is intended. Furthermore, the term "or" as used in this disclosure is not intended to be an exclusive OR.

In this disclosure, where articles have been added by translation, such as a, an, and the in English, the disclosure may include the plural nouns following these articles.

In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean that "A and B are different from C". Terms such as "separate," "coupled," etc. may also be interpreted in the same manner as "different."

DESCRIPTION OF SYMBOLS 10... Return value setting system, 11... Database, 12... Reaction information acquisition part, 13... Return value setting part, 1001... Processor, 1002... Memory, 1003... Storage, 1004... Communication device, 1005... Input device, 1006... Output Device, 1007...Bus.

Claims (6)

A return value setting system for setting a return value that is a value related to a return for a user's use of a payment service,
a reaction information acquisition unit that acquires reaction information indicating the user's reaction to the use of the payment service with respect to the set return value according to the user's attribute;
a return value setting unit that acquires attribute information indicating an attribute of a user for whom a return value is to be set, and sets a return value based on the acquired attribute information and the reaction information acquired by the reaction information acquisition unit;
with
The reaction information is an estimation model in which attribute information, a set return value, and a return value past the set return value are input, and the user's reaction according to the attribute information and the return value is output. Return value setting system. 2. The return value setting system according to claim 1, wherein the reaction information acquisition unit acquires reaction information in which the type of payment service used is attributed to the user. 3. The reaction information acquisition unit acquires history information indicating a user's usage history of the settlement service according to past return values, and generates and acquires reaction information based on the acquired history information. The return value setting system described in . 4. The return value setting according to any one of claims 1 to 3 , wherein the return value setting unit sets the return value based on the expected profit of the payment service provider from the user's use of the payment service based on the reaction information. system. The return value setting system according to any one of claims 1 to 4 , wherein the return value setting unit sets the return value by a method based on a bandit algorithm. A return value setting method, which is a method of operating a return value setting system for setting a return value that is a value related to a user's use of a settlement service, comprising:
a reaction information acquiring step of acquiring reaction information indicating the reaction of the user in using the payment service to the set return value according to the user's attribute;
a return value setting step of acquiring attribute information indicating an attribute of a user for whom a return value is to be set, and setting a return value based on the acquired attribute information and the reaction information acquired in the reaction information acquiring step;
including
The reaction information is an estimation model in which attribute information, a set return value, and a return value past the set return value are input, and the user's reaction according to the attribute information and the return value is output. How to set the return value.

Images