JP7280402B1 - Information processing device, information processing method and information processing program - Google Patents

Abstract

An object of the present invention is to appropriately predict future trends in a physical store. An information processing apparatus according to an embodiment includes an acquisition unit that acquires store information about each actual store included in a store group; a learning unit that learns a learning model that outputs future information about trends. [Selection drawing] Fig. 1

Description

The present invention relates to an information processing device, an information processing method, and an information processing program.

Conventionally, there is a technique for predicting future sales of an online store that opens in an electronic shopping mall based on information about the store. For example, in such technology, funds are provided to the store by purchasing a bond corresponding to the predicted future sales amount from the store (see Patent Document 1, for example).

Japanese Patent No. 6836255

However, the prior art leaves room for improvement. For example, although conventional technology predicts future sales for online stores, it is difficult to apply it to offline physical stores. Therefore, it is desired to appropriately predict future trends in actual stores.

SUMMARY OF THE INVENTION It is an object of the present invention to provide an information processing apparatus, an information processing method, and an information processing program capable of appropriately predicting future trends in a physical store.

In order to solve the above-described problems and achieve the object, an information processing apparatus according to the present invention includes an acquisition unit that acquires store information about each actual store included in a store group; a learning unit that learns a learning model that outputs future information on future trends of the store group when information is input.

ADVANTAGE OF THE INVENTION According to this invention, the future trend in an actual store can be predicted appropriately.

FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. FIG. 2A is a diagram illustrating an example of output results from a learning model according to the embodiment; FIG. 2B is a diagram illustrating an example of output results from the learning model according to the embodiment; FIG. 2C is a diagram illustrating an example of output results from the learning model according to the embodiment; FIG. 3 is a block diagram illustrating a configuration example of the information processing apparatus according to the embodiment; FIG. 4 is a diagram illustrating an example of a store information database according to the embodiment; FIG. 5 is a diagram showing an example of a member store information database according to the embodiment. FIG. 6 is a diagram illustrating an example of an area information database according to the embodiment; FIG. 7 is a diagram illustrating an example of a model database according to the embodiment; FIG. 8 is a diagram illustrating an example of a factoring database according to the embodiment; FIG. 9 is a diagram showing an example of a factoring application screen according to the embodiment. FIG. 10 is a diagram showing an example of a factoring application screen according to the embodiment. FIG. 11 is a flowchart illustrating an example of information processing according to the embodiment; FIG. 12 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus according to the embodiment.

Embodiments for implementing an information processing apparatus, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail below with reference to the drawings. The information processing apparatus, information processing method, and information processing program according to the present application are not limited to this embodiment.

[1. embodiment]
Information processing realized by the information processing apparatus and the like according to the present embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. In addition, in FIG. 1, the information processing etc. which concerns on embodiment shall be implement|achieved by the information processing apparatus 10 which concerns on this embodiment.

As shown in FIG. 1 , an information processing system 1 according to the embodiment includes an information processing device 10 , a user terminal 50 , a payment server 100 , a store terminal 200 and a business operator terminal 300 . The information processing device 10, the user terminal 50, the settlement server 100, the store terminal 200, and the business terminal 300 are connected by wire or wirelessly via a network so as to be able to communicate with each other. The network is, for example, a WAN (Wide Area Network) such as the Internet. The information processing system 1 shown in FIG. 1 may include a plurality of information processing apparatuses 10, user terminals 50, payment servers 100, store terminals 200, and business operator terminals 300, respectively.

An information processing apparatus 10 illustrated in FIG. 1 is an information processing apparatus that executes information processing according to an embodiment, and is realized by a server device, a cloud system, or the like. For example, the information processing device 10 purchases a claim from a member store of the electronic payment service based on information on the electronic payment service related to the electronic payment using the user terminal 50 provided by the payment server 100, thereby providing the member store with Provide factoring services that provide financing.

For example, the settlement server 100 manages the account of the provider (operator) of the transaction object and the account of the user to whom the transaction object is provided, and transfers electronic money between accounts according to the payment request from the user. By doing so, various settlements are realized. In addition, electronic money may be, for example, points or currency used independently by various companies, or may be electronically tradable currency provided by the state such as Japanese yen and dollars. good.

In addition, the settlement server 100 provides profit information regarding profits (coupons, etc.) that are given to the user in the electronic settlement service and that can be used in the electronic settlement service, to the profit provider (in other words, planning, setting, etc. of the coupon). , a person who contributes (provides) the source of the coupon), and manages it in the storage unit of its own device.

In addition, the payment server 100 manages area information including information such as shops located in each area (member shops of the electronic payment service) in the storage unit of its own device. For example, the information processing device 10 includes identification information (area ID) that identifies each area, location information (location, range, etc.) of each area, road information in each area, route information in each area, It stores area information including stores where it is located. Note that the area may be appropriately set to have an arbitrary size range. For example, the area may be divided into meshes of similar size based on latitude and longitude. That is, the area may be an area separated by a regional mesh. In this case, a regional mesh code may be used as the area ID. Note that the above is just an example, and the area may be set based on various information other than the area mesh. For example, areas may be set based on administrative divisions such as "town", "ward", "city", and "prefecture". Also, the area may be set for each facility such as a store, or may be set for each street, shopping street, or the like.

A user terminal 50 shown in FIG. 1 is an information processing device used by a user U. As shown in FIG. The user terminal 50 is realized by, for example, a smart phone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like.

A store terminal 200 shown in FIG. 1 is an information processing device used by a store that provides transaction objects to users. The store terminal 200 is realized by, for example, a POS (Point of Sales) terminal, a smart phone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, a PDA, or the like. In addition, the store terminal 200 displays information distributed by the settlement server 100 using a web browser or an application. Note that the example shown in FIG. 1 shows a case where the store terminal 200 is a POS terminal.

When the user terminal 50 and the store terminal 200 receive control information for realizing predetermined information processing from the information processing device 10, the user terminal 50 and the shop terminal 200 implement information processing according to the control information. Here, the control information includes, for example, a script language such as JavaScript (registered trademark), a style sheet language such as CSS (Cascading Style Sheets), a programming language such as Java (registered trademark), and a markup language such as HTML (HyperText Markup Language). It is written in up language or the like. Note that the predetermined application itself distributed from the settlement server 100 may be regarded as the control information.

A business operator terminal 300 shown in FIG. 1 is, for example, an information processing device used by a business operator that operates each store. The business terminal 300 is realized by a smart phone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, a PDA, or the like. In addition, the operator terminal 300 displays information distributed by the information processing device 10 and the settlement server 100 using a web browser and applications. Note that the example shown in FIG. 1 shows a case where the business terminal 300 is a notebook PC.

[1-1. Payment using the user terminal 50]
Here, an example of payment (electronic payment) using the user terminal 50 will be described prior to the providing process executed by the information processing apparatus 10 . In the following description, a two-dimensional code (QR code (registered trademark)) placed at the store A, which indicates store identification information for identifying the store A, is used by the user U. An example of making a payment using the personal terminal 50 will be described, but the embodiment is not limited to this. An example of settlement described below is also applicable when any user uses any user terminal 50 to make a payment at any store. Moreover, the store identification information may be not only a QR code but also a bar code, a predetermined mark, a number, or the like.

For example, when the user U uses or purchases a payment target (transaction target) such as various products and services at a store A, the user U uses a payment application pre-installed on the user terminal 50. to start. Then, the user U photographs the store identification information installed in the store A via the payment application. In such a case, the user terminal 50 displays a screen for inputting the price to be settled, and accepts the input of the payment amount from the user U or store A clerk. Then, the user terminal 50 provides user identification information for identifying the user U, and store identification information (or information indicated by the store identification information, that is, information indicating the store A (or the operator of the store A) (for example, , shop ID) and payment information indicating the payment amount are transmitted to the information processing apparatus 10 .

In such a case, the information processing apparatus 10 transfers the amount of electronic money indicated by the payment amount from the account of the user U indicated by the user identification information to the account of the store A indicated by the store identification information. The information processing device 10 then transmits a notification to the user terminal 50 that the payment has been completed. In such a case, the user terminal 50 notifies that the payment has been made with electronic money by outputting a screen or a predetermined voice indicating that the payment has been completed.

Note that the settlement using the user terminal 50 is not limited to the processing described above. For example, the payment using the user terminal 50 may be made using the store terminal 200 installed in the store A. For example, the user terminal 50 displays user identification information for identifying the user U on the screen. In such a case, the store terminal 200 installed in the store A reads the user identification information displayed on the user terminal 50 and reads the user identification information (or information indicated by the user identification information, that is, the user Payment information indicating information indicating U (for example, user ID), payment amount, and information identifying store A is transmitted to payment server 100. In such a case, information processing device 10 performs user identification. The amount of electronic money indicated by the settlement amount is transferred from the account of user U indicated by the information to the account of store A, and the store terminal 200 or user terminal 50 of store A displays a screen indicating that the settlement has been completed. You may notify that the payment has been made by outputting a predetermined sound.

In addition, settlement using the user terminal 50 includes not only the process of transferring electronic money from an account charged with electronic money by the user U in advance to the account of the store A, but also a credit card pre-registered by the user U, for example. may be used for settlement. In such a case, for example, the user terminal 50 transfers electronic money for the settlement amount to the account of the store A, and requests the credit card operating company (card company) of the user U for the settlement amount. You may

[1-2. Information processing according to the embodiment]
The information processing apparatus 10 according to the embodiment provides a factoring service to each shop operator based on the payment history of the electronic payment service performed at each shop. Here, the factoring service is a service that provides funds to a business operator by purchasing a portion of the future sales of the store as a bond.

In order to provide such a factoring service, it is necessary to determine the purchase conditions of receivables (hereinafter referred to as factoring conditions) according to the future trends of the store.

Therefore, in the information processing apparatus 10 according to the embodiment, a learning model (hereinafter referred to as a model) for estimating future information indicating future trends of each store is learned, and factoring conditions are determined based on the estimation result of the model. In the following, a case will be described in which a factoring service is provided to a business operator (for example, an operation headquarters) that operates a chain store, and a model for predicting future trends for each chain store is learned. The learning of the model is not limited to the chain store unit, and may be set to arbitrary units such as the store unit and the store category unit.

For example, in the information processing system 1 according to the embodiment, as shown in FIG. (step S1). The settlement server 100 aggregates the settlement information notified from each store, and notifies the information processing device 10 of the transaction information of the electronic settlement service at each store (step S2). For example, the transaction information includes the transaction volume of the electronic payment service at each store, transaction date and time, users who used each store, and information on purchased products.

The information processing device 10 stores the transaction information in the store information database, and learns the model using the chain information obtained by aggregating the store information stored in the store information database for each chain store as learning data (step S3).

Here, the store information includes category information related to the store category of each store, electronic payment service transaction information at each store, geographic information related to location, etc., user information related to users, business hours information related to business hours, etc. Various information about the store is included. Also, the chain information is information obtained by aggregating these store information for each chain store.

For example, as shown in FIG. 1, the information processing device 10 learns models M1 to M3 (hereinafter also referred to as model M) based on chain information. A model M1 shown in FIG. 1 is a model for estimating a score that considers the group characteristics of each chain store.

For example, the information processing device 10 uses, as learning data, store number information related to the increase or decrease in the number of member stores (hereinafter also referred to as chain stores) affiliated with the chain store, information related to the transaction history of the electronic payment service at each chain store, etc. The model M1 is trained. That is, the model M1 is a model for estimating the increase/decrease in the number of chain stores from the transaction history of the electronic payment service at each chain store as future information about the chain stores.

For example, as shown in FIG. 2A, model M1 is a model for estimating trends in the number of chain stores in chain stores. Note that FIG. 2A is a diagram showing an example of output results from the learning model according to the embodiment. For example, the model M1 estimates the number of stores (the number of chain stores) on a plurality of time axes such as the medium term or the long term, as indicated by broken lines in FIG. 2A.

In this case, the model M1 may be composed of a plurality of models corresponding to the estimated time axis. That is, the model M1 may be composed of a model for estimating the number of stores on the medium-term time axis and a model for estimating the number of stores on the long-term time axis.

Note that the model M1 may be a model that estimates future usage patterns of electronic payment services in the entire chain store as future information. The model M1 may be a model for estimating the withdrawal probability of an electronic payment service member store withdrawing from a chain store. It may be a model that estimates information. Note that withdrawing means that the store withdraws from the electronic payment service due to store closure or other reasons.

The model M2 shown in FIG. 1 is a model for estimating, as future information, information on the future usage of electronic payment services in consideration of area characteristics. For example, the model M2 is a model learned for each area using store information for each area as learning data.

Here, since the weather, demographics, local industries, etc. differ from area to area, it is assumed that needs, business strategies, rival stores, etc. will differ from area to area. Therefore, the information processing apparatus 10 prepares learning data for each area and generates the model M2, thereby visualizing these characteristics for each area.

In the learning stage of the model M2, the information processing device 10 learns the model M2 for each area using, as learning data, information regarding the increase or decrease in the number of chain stores in each area, information regarding the transaction history of the electronic payment service, and the like.

For example, as shown in FIG. 2B, the model M2 is a model that outputs information indicating the withdrawal probability for each area in the chain store. Note that FIG. 2B is a diagram illustrating an example of output results from the learning model according to the embodiment. FIG. 2B exemplifies a case where the areas are seven regional divisions such as Hokkaido, Tohoku, Kanto, Chubu, Kinki, Chugoku, and Kyushu. You may decide to divide. Also, regarding the setting of areas, it is not a requirement that they be adjacent areas, such as setting a plurality of areas with similar demographics as the same area.

The model M3 shown in FIG. 1 is a model for estimating, as future information, information on the future usage of the electronic payment service, taking into account the business hours characteristics of each chain store. For example, the information processing device 10 learns the model M3 using business hours information about the business hours of each chain store and information about the transaction history of the electronic payment service as learning data.

For example, the information processing device 10 learns the model M3 using the total business hours per month for the entire chain store, the number of employees, the transaction amount (monthly sales) of the electronic payment service, etc. as learning data.

For example, as shown in FIG. 2C, model M3 is a model that has learned the relationship between withdrawal probability and business hours (monthly sales/total business hours). Note that FIG. 2B is a diagram illustrating an example of output results from the learning model according to the embodiment. In FIG. 2C, the relationship between the withdrawal probability and business hours is represented two-dimensionally, but it is for convenience of explanation and is not limited to this.

The information processing device 10 can visualize the relationship between business hours and withdrawal probability, for example, by learning such a relationship between business hours and withdrawal probability.

Subsequently, as shown in FIG. 1, when the information processing device 10 receives an application for factoring from the business operator terminal 300 (step S4), the corresponding business operator's chain information is input for each of the models M1 to M3. Thus, a withdrawal score is calculated (step S5).

For example, the information processing device 10 uses the model M1 to calculate a score relating to an increase or decrease in the number of chain stores operated by a business operator as a withdrawal score, and uses the model M2 to calculate a withdrawal score in each area. do. The information processing device 10 also calculates a withdrawal score according to business hours by using the model M3.

Here, the withdrawal score is, for example, a score related to the increase or decrease in the number of chain stores in all chain stores. For example, a higher withdrawal score suggests that chain stores are more likely to decrease, and a lower withdrawal score suggests that chain stores are less likely to decrease or increase in number.

For example, if the number of chain stores increases, it is expected that the usage amount of electronic payment services will increase throughout the chain stores as the number of chain stores increases. Therefore, the withdrawal score is an index for predicting changes in the usage amount of electronic payment services in chain stores, and can also be regarded as a value that quantifies the risk of defaulting on receivables. Specifically, it can be assumed that the lower the withdrawal score, the lower the risk of defaulting on the bond, and the higher the withdrawal score, the higher the risk of defaulting on the bond.

Then, the information processing device 10 determines factoring conditions according to withdrawal scores calculated using the models M1 to M3 (step S6). For example, the information processing device 10 determines favorable factoring conditions for a business operator with a lower withdrawal score, that is, a business operator with a lower possibility of withdrawal and a lower risk of defaulting on its receivables.

For example, the factoring conditions include conditions such as the maximum purchase amount of receivables, collection mode, etc., and the information processing device 10 determines these conditions according to the withdrawal score. For example, the information processing device 10 determines a factoring condition such that the lower the withdrawal score, the higher the maximum purchase amount of the bond.

After that, the information processing device 10 concludes a contract with the business operator based on the determined factoring conditions, and purchases the receivables from the business operator, thereby providing funds to the business operator (step S7).

In this manner, the information processing apparatus 10 according to the embodiment learns the models M1 to M3 based on each shop information. Therefore, according to the information processing apparatus 10 according to the embodiment, it is possible to appropriately predict future trends in the physical store.

In addition, in the information processing apparatus 10 according to the embodiment, by determining the factoring conditions based on the output results of the models M1 to M3, it is possible to determine appropriate factoring conditions according to the future trends of the physical store.

The purpose of using Models M1 to M3 is not limited to determining factoring conditions. For example, it is possible to avoid withdrawing from electronic payment services, or to use it for sales activities related to new transactions. For example, chain stores or chain stores with high withdrawal scores can be utilized in marketing electronic payment services, such as strengthening sales activities.

[1-3. About the learning process according to the embodiment]
For example, in the above learning data, the chain information of each chain store, the number of changes in the number of chain stores of the chain store, and the label indicating the transaction volume of the electronic payment service (also called "correct information") are associated. Contains data.

Further, for example, as correct information, "1" is assigned when the number of chain stores has decreased, and "0" is assigned when the number of chain stores has not decreased. As correct information, if the number of chain stores has decreased within one year from time X to the chain information up to a certain point (time point X), "1" is assigned, and the number of chain stores has decreased one year from time X. '0' may be assigned if not decremented within the specified time. In this case, the information processing device 10 is a model that estimates (predicts) the probability (possibility) that the number of chain stores will decrease within a desired period (for example, one month, six months, five years, etc.), not limited to one year. can be generated.

For example, the information processing device 10 performs back propagation so that the score output by the model M approaches the correct information (label) associated with the chain information of the chain store input to the model M. The learning process is performed by a method such as For example, when the correct answer information is "1" and the chain information of the chain store to which the correct answer information is assigned is input, the information processing apparatus 10 is configured so that the score output by the model M approaches "1". Then, the learning process is performed. Further, for example, when the correct answer information is "0" and the chain information of the chain to which the correct answer information is assigned is input, the information processing apparatus 10 makes the score output by the model M approach "0". , the learning process is performed.

For example, the information processing apparatus 10 adjusts the values of weights (that is, connection coefficients) that are considered when values are transmitted between nodes by learning processing. In this way, the information processing apparatus 10 learns the model M by processing such as back propagation that corrects the parameters (connection coefficients) so that the error between the output of the model M and the correct information corresponding to the input is reduced. . For example, the information processing device 10 generates the model M by performing processing such as back propagation so as to minimize a predetermined loss function. Thereby, the information processing apparatus 10 can perform learning processing for learning the parameters of the model M. FIG.

Note that the model learning method is not limited to the method described above, and any known technique can be applied. Note that each model may be generated using various conventional techniques related to machine learning as appropriate. For example, a model may be generated using a technology related to supervised learning machine learning such as SVM (Support Vector Machine). Also, for example, model generation may be performed using techniques related to unsupervised machine learning. For example, model generation may be performed using deep learning techniques. For example, the model may be generated using various deep learning techniques such as DNN (Deep Neural Network), RNN (Recurrent Neural Network), and CNN (Convolutional Neural Network). Note that the above description of model generation is an example, and model generation may be performed by a learning method appropriately selected according to obtainable information and the like. That is, if the information processing apparatus 10 can learn the model M so as to output a score corresponding to the correct answer information when the chain information included in the learning data is input, what kind of method can be used to train the model M? You can generate.

[2-1. Configuration example of information processing device]
Next, a configuration example of the information processing apparatus 10 will be described with reference to FIG. FIG. 2 is a block diagram showing a configuration example of the information processing device 10 according to the embodiment. As shown in FIG. 2, the information processing apparatus 10 has a communication section 110, a storage section 120, and a control section .

The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the payment server 100, the business operator terminal 300, and the like.

The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 3, the storage unit 120 has a store information database 121, a member store information database 122, a geographical information database 123, a model database 124, and a factoring database 125.

The store information database 121 is a database that stores information about each store that uses the electronic payment service. FIG. 4 is a diagram showing an example of information stored in the store information database 121 according to the embodiment.

As shown in FIG. 4, the store information database 121 includes "store ID", "member store ID", "store opening date", "store closing date", "category ID", "sales", "handling amount", " Information items such as address,” “business hours,” and “number of employees” are associated with each other and stored.

"Store ID" is an identifier for identifying a store. For example, the shop ID is the shop ID in the electronic payment service. "Member store ID" is an identifier for identifying a chain store to which the store identified by the corresponding store ID is affiliated.

For example, if they are members of the same chain store, they are given the same member store ID. It should be noted that different IDs may be assigned according to the contract mode of each store, even if the stores are members of the same chain store. That is, the "member store ID" may include an identifier for identifying a directly managed store or a franchise store.

The "date of store opening" is the date when the store identified by the corresponding store ID opened, and the "date of closing" is the date when the store identified by the corresponding store ID was closed. ' and 'closed date' may be read as the date of joining the electronic payment service and the date of withdrawal from the electronic payment service, respectively.

"Category ID" is an identifier for identifying the store category of the store identified by the corresponding store ID. For example, the category ID is determined according to the type of industry and the products handled (services handled). In addition, you may make it give category ID of multiple types with respect to one shop.

“Sales” is the monthly sales (i.e., monthly sales) of the store identified by the corresponding store ID, and “Handling” is the electronic payment at the store identified by the corresponding store ID. It is the transaction volume of the service.

"Address information" is information about the address of the store identified by the corresponding store ID. For example, "address information" may include information regarding the location of the store, the size of the store, the presence or absence of a parking lot, and the like.

"Business hours" is information about the business hours of the store identified by the corresponding store ID, and "Number of employees" is information about the number of employees of the store identified by the corresponding store ID. The number of employees may be information about the total number of employees working at the corresponding store, or may include the number of employees working at one time. Further, the number of employees may include information on the number of employees for each type of employment (regular employees, part-time workers, etc.).

Returning to the description of FIG. 3, the member store information database 122 will be described. The member store information database 122 is a database that stores information on member stores. FIG. 5 is a diagram showing an example of information stored in the member store information database 122 according to the embodiment.

As shown in FIG. 5, the member store information database 122 associates information items such as "member store ID", "number of stores", "total business hours", "number of employees", and "monthly sales" with each other. Remember.

"Member store ID" is an identifier for identifying a chain store, and "number of stores" is the number of chain stores identified by the corresponding member store ID. "Total business hours" is the sum of business hours per month for all chain stores identified by corresponding member store IDs, and "Number of employees" is the number of employees for all chain stores.

Also, "monthly sales" is the sales of the whole chain store identified by the corresponding member store ID for one month. Note that the monthly sales may be the total transaction volume of the electronic payment services of the entire chain store.

Returning to the description of FIG. 3, the geographic information database 123 will be described. The geographic information database 123 is a database that stores geographic information. FIG. 6 is a diagram showing an example of information stored in the geographic information database 123 according to the embodiment.

As shown in FIG. 6, for example, the geographic information database 123 stores items of information such as "area ID", "population information", and "store information" in association with each other. "Area ID" is an identifier for identifying each area.

"Population information" is information about the population in the area identified by the corresponding area ID. Population information includes information on vital statistics (population by age and gender), statistical information on annual income and wages in an area, information on the flow of people in an area by hour, and information on users of electronic payment services.

"Store information" is information about stores opened in the area identified by the corresponding area ID. For example, as shown in FIG. 6, the store information is information about stores corresponding to each store category such as category 1 and category 2. FIG. The category here is, for example, the store category, and the store information stores information about stores belonging to similar or the same store category. In addition, the store category may be such that each store is classified according to the type of business, or according to the products handled.

It should be noted that, for example, the category may be set for each chain store, and in this case, the store information stores information related to the chain store of the same chain store. In this case, for example, store information includes information indicating the geographical distribution of chain stores (how each chain store is distributed in the map information), rent (or land price) of each chain store, etc. etc. may be included.

Returning to the description of FIG. 3, the model database 124 will be described. The model database 124 is a database that stores models. FIG. 7 is a diagram showing an example of information stored in the model database 124 according to the embodiment.

As shown in FIG. 7, the model database 124 stores items of information such as "model ID", "usage", "model data" and "learning data" in association with each other. "Model ID" is an identifier for identifying each model.

"Usage" indicates the usage of the model identified by the corresponding model ID. In the example shown in FIG. 7, the usage includes "group characteristics", "area characteristics (AR1 to AR3)", and "business hours characteristics".

"Model data" is the data body of the model identified by the corresponding model ID, and "learning data" is the learning model for generating the model identified by the corresponding model ID.

Returning to the description of FIG. 3, the factoring database 125 will be described. The factoring database 125 stores various information regarding factoring. FIG. 8 is a diagram showing an example of information stored in the factoring database 125 according to the embodiment.

As shown in FIG. 8, the factoring database 125 stores items of information such as "member store ID", "score information", and "factoring information" in association with each other. "Member store ID" is an identifier for identifying a chain store.

"Score information" is the score for the chain store identified by the corresponding merchant ID. "Factoring information" indicates whether factoring of the corresponding chain store is being used. For example, a chain store whose "factoring information" is "-" (hyphen) indicates that the store does not use factoring.

A chain store whose "factoring information" is factoring information #2 indicates that it is a chain store that is using factoring. Information is stored.

Returning to the description of FIG. 3, the control unit 130 will be described. The control unit 130 is a controller. For example, various programs stored in a storage device inside the information processing apparatus 10 are controlled by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like, and the RAM is used as a work area. It is realized by executing as Also, the control unit 130 is implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 130 according to the embodiment includes an acquisition unit 131, a learning unit 132, an estimation unit 133, and a determination unit 134, and implements or executes information processing functions and actions described below.

The acquisition unit 131 acquires store information about each actual store and stores it in the store information database 121 . For example, the acquisition unit 131 acquires from the payment server 100 transaction information related to electronic payment service transactions at physical stores. For example, the acquisition unit 131 may acquire sales information related to sales at a physical store. The sales information is information related to store sales including transaction volume of the settlement service provided by the settlement server 100 and other settlement means such as cash and credit card. For example, the acquisition unit 131 acquires sales information through questionnaires to each actual store or chain store headquarters. It should be noted that the acquisition unit 131 may estimate the sales information from the transaction history of the electronic payment service at each physical store. Further, the sales information may be, for example, monthly sales, or profit for one month (amount obtained by subtracting expenses from monthly sales).

In addition, the acquisition unit 131 acquires business hours information and employee information as store information about each store. Acquisition unit 131 acquires business hours information and employee information, for example, by conducting a web page (store homepage, etc.) related to each actual store or conducting a questionnaire to each store. It should be noted that the acquisition unit 131 may estimate business hours information from the time of use of the electronic payment service. For example, the acquisition unit 131 may estimate the business hours of each store based on the time when the electronic payment service is used and the time when the electronic payment service is not used.

Further, the acquisition unit 131 may estimate employee information after estimating which user is an employee based on the position information of each user terminal 50 . For example, the acquisition unit 131 may aggregate the general length of stay at each actual store, and then estimate users who stay longer than the typical length of stay as employees. Note that the acquisition unit 131, for example, based on the electronic payment service provided by the payment server 100 or the registration information of the portal site linked to the electronic payment service, from the information on the workplace of each user to the employee at each store may be specified.

The acquisition unit 131 also acquires area information about each area. The area information includes, for example, demographics (population by generation), the number of users of electronic payment services, and information on the floating population (flow of people) in each area.

Also, for example, the area information may include information on land prices, rent market prices (land prices) in each area, and salary market prices for each industry. For example, the acquisition unit 131 acquires these area information from an external server (not shown).

The learning unit 132 learns the models M1 to M3 based on the various information acquired by the acquisition unit 131. FIG. As described above, the model M1 is a model for estimating future trends of chain stores in consideration of group characteristics of each chain store.

For example, in the learning stage of the model M1, the learning unit 132 learns, as learning data, the transaction history regarding the transaction volume of the electronic payment service of each chain store affiliated with the chain store and the data regarding the number of stores of the chain store.

For example, the learning unit 132 learns the model M1 using, as learning data, chain information obtained by aggregating store information about chain stores of each chain store for each chain store.

For example, the learning data includes data in which chain information of each chain store is associated with a label (also referred to as "correct information") indicating the increase or decrease in the number of affiliated stores of the chain store or the transaction volume of the electronic payment service. be

Further, for example, as correct information, "1" is assigned when the number of chain stores has decreased, and "0" is assigned when the number of chain stores has not decreased. For example, when the correct answer information is "1" and the chain information of the chain store to which the correct answer information is assigned is input, the learning unit 132 makes the score output by the model M1 approach "1". , the learning process is performed. Further, for example, when the correct information is "0", the information processing apparatus 10 sets the score output by the model M1 to "0" when the chain information of the chain store to which the correct information is assigned is input. Learning processing is performed so as to approach. The learning unit 132 may learn the model M1 using "1" when the number of chain stores has increased and "0" when the number of chain stores has not increased as correct information.

In the learning stage of the model M1, the learning unit 132 sets "1" when the transaction volume of the electronic payment service in the entire chain store has decreased (or increased) as correct information, and the transaction volume of the electronic payment service has decreased (or The learning of the model M1 may be performed with "0" indicating the case of no increase.

Here, the store group is a chain store unit, but is not limited to this, and the store group may be a store category (for example, convenience store, drug store, etc.), the customer base of each store, the customer unit price, etc. Arbitrary store groups may be created according to. That is, the model M1 may be learned by creating a store group of a plurality of actual stores with similar customer unit prices or similar customer bases.

In addition, the learning unit 132 performs learning for each area with respect to the model M2 that outputs future information in consideration of area characteristics. That is, the model M2 is generated for each area.

In this case, the learning data includes data obtained by dividing the chain information used for the learning data of the model M1 by area, data on the market rent (or land price) in the corresponding area, data on the population, and the like.

At this time, as the learning data, the number of actual stores whose store category is similar to the target store (chain store) in the learning target area and the sales amount of each of those stores may be used.

In other words, for example, the learning of the model M2 may be performed in consideration of the demand of the entire store category in the relevant area. To give a more specific example, for example, in the Osaka area, demand for takoyaki and okonomiyaki is higher than in other areas, and the number of stores and sales are said to be higher than in other areas.

In the model M2, it is possible to visualize the characteristics of an area based on the overall store category, number of stores, and sales in the area. In other words, the learning unit 132 learns the model M2 based on not only the information about the chain store in the relevant area, but also the entire store category or store information of the same trade, so that the characteristics of the target area are properly learned. can be reflected.

The learning unit 132 also learns a model M3 that outputs future information in consideration of business hours characteristics. In this case, the learning data includes, for example, information on business hours per month for the entire chain store, data on the actual increase or decrease in the number of chain stores, and data on the monthly transaction volume of electronic payment services. .

Here, the business hours information includes information on the total business hours per month in each store, working hours per employee, and business hours. The business hours include, for example, 24-hour business, late-night business, early-morning business, closed days, and the like.

The learning data for the model M3 is generated based on business hours information and electronic payment service transaction information. For example, sales per hour (monthly sales / total business hours), sales per employee ( monthly sales/number of employees), labor unit price, and electronic payment service transaction volume.

For example, the learning unit 132 associates data indicating a decrease in the number of chain stores with correct information "1" and data indicating that the number of chain stores has not decreased with a label indicating correct information "0" to create the model M3. do the learning.

In addition, the learning unit 132 provides the correct information "1" for the data of the store where the transaction volume of the electronic payment service has increased (or decreased), and the correct information for the data of the store where the transaction volume of the electronic payment service has not increased (or decreased). The model M3 may be learned using the learning data associated with the information "0".

In the above example, the case of learning the models M1 to M3 using the transaction volume of the electronic payment service as learning data has been described. ~M3 may be learned.

The estimating unit 133 uses the model M learned by the learning unit 132 to estimate the future trend of the physical store. For example, the learning unit 132 estimates the future information of the chain store by inputting the chain information of the target chain store into the model M1. The future information here includes, for example, the withdrawal score (withdrawal probability) of the chain store, information related to the increase or decrease in the number of chain stores in the chain store, the increase or decrease in the transaction volume of the electronic payment service for the entire chain store, etc. may be

The estimating unit 133 also inputs the chain information of the chain stores in the target area to the target model M2, respectively, to estimate future information on the usage pattern of the electronic payment service in the chain stores in each area.

For example, the future information here is the withdrawal score of the chain store in the corresponding area, but information about the number of chain stores in each area, the increase or decrease in the transaction volume of the electronic payment service for the entire chain store, etc. may be

The estimating unit 133 also inputs chain information including business hours information about the business hours of the target chain store into the model M3, thereby estimating future information about the usage mode of the electronic payment service at the chain store. For example, model M3 is a model that outputs a withdrawal score in a chain store from business hours information, a model that outputs a score related to the future transaction value of an electronic payment service in a chain store, or a model that outputs a future number of chain stores. It may be a model that estimates

For example, the business hours information here includes various information related to business hours, such as the total business hours per month at the target chain store (sum of the business hours of each chain store), the number of hours per employee It includes the number of working hours per month (total business hours/number of employees), the labor unit price per employee (monthly sales/number of employees), and the like.

The estimating unit 133 may estimate future information for each chain store at a predetermined cycle, or may estimate future information for the chain store upon receiving an application for factoring from the chain store.

The determination unit 134 determines factoring conditions based on the estimation results from the estimation unit 133 . For example, the determination unit 134 determines factoring conditions for the chain store based on the estimation results of the estimation unit 133 and preset factoring rules. For example, factoring conditions include purchase amount of receivables, collection mode, fees, and the like.

Note that the determining unit 134 may determine the factoring conditions based on a model learned by using the factoring conditions when the receivables are actually purchased and the collection status thereof as learning data, for example.

For example, such a model learns that the correct information is when the receivables can be collected or when the receivables cannot be collected based on the score information about the chain store and the factoring conditions when the receivables are actually purchased. It can be generated using data.

Here, an example of the application procedure for factoring will be described with reference to FIGS. 9 and 10. FIG. 9 and 10 are diagrams showing an example of a factoring application screen. In the example shown in FIG. 9, an entry field for the operator to enter the amount required this time and the repayment rate from the monthly launch is also displayed on the screen that displays the conditions that can be applied for (that is, the factoring conditions). be.

For example, the business operator can apply for the purchase of receivables up to the maximum monetization amount presented by the factoring conditions, and can also set the repayment rate for the receivables.

When the business operator inputs the amount and repayment rate shown in FIG. 9 and selects the next button, the screen transitions to the screen shown in FIG. On the screen shown in FIG. 10, information related to confirmation of application details and a button to transition to the terms of use are displayed. Factoring is established based on the content of the application.

For example, when factoring is established, the determination unit 134 stores the application details in the factoring database 125 (see FIG. 3) and notifies the settlement server 100 of information on the repayment rate. As a result, the settlement server 100 can collect the funds for the credit by deducting the amount corresponding to the repayment rate from the monthly sales of the business operator based on the repayment rate.

[3. Processing procedure of information processing according to the embodiment]
Next, an example of a processing procedure executed by the information processing apparatus 10 according to the embodiment will be described with reference to FIG. 11 . FIG. 11 is a flowchart illustrating an example of information processing according to the embodiment;

As shown in FIG. 11, first, the information processing device 10 acquires information about the store (step S101), and learns the learning models (models M1 to M3) based on the information about the store (step S102). .

Subsequently, the information processing apparatus 10 determines whether or not factoring has been accepted by access from the business operator terminal 300 (step S103). When the information processing apparatus 10 accepts factoring from the operator terminal 300 (step S103; Yes), it proceeds to the process of step S104, and when not accepting factoring (step S103; No), returns to the process of step S101.

Subsequently, the information processing device 10 uses the learning models (models M1 to M3) to calculate the score of the business operator (step S104), and determines factoring conditions based on the score (step S105). Then, the information processing device 10 ends the process.

[4. Modification]
By the way, in the above-described embodiment, the case has been described with a real store as the target, but the present invention is not limited to this. For example, stores that provide services by combining offline sales and online sales may be targeted. For example, in this case, for online sales, model M is learned using, for example, the sales history of various EC sites as learning data. Further, for example, in such a case, the model M for offline sales and the model M for online sales may be learned together, and the model M for offline sales and the model M for online sales may be used separately. You may make it learn.

[5. effect〕
The information processing apparatus 10 according to the embodiment includes an acquisition unit 131 that acquires store information about each actual store included in the store group, and when the store information acquired by the acquisition unit 131 is input, the information processing apparatus 10 acquires future trends of the store group. and a learning unit 132 that learns a learning model that outputs future information about. Therefore, according to the information processing apparatus 10 according to the embodiment, it is possible to appropriately predict future trends in the physical store.

Also, the learning unit 132 according to the embodiment learns a learning model that outputs the future information for each chain store as a store group. Therefore, according to the information processing apparatus 10 according to the embodiment, it is possible to appropriately predict the future trend of chain stores.

Also, the learning unit 132 according to the embodiment learns a learning model using information about the sales amount of each actual store as learning data. Therefore, according to the information processing apparatus 10 according to the embodiment, it is possible to appropriately predict the sales of the store group.

In addition, the learning unit 132 according to the embodiment learns a learning model using information about the transaction volume of the payment service performed at each actual store as learning data. Therefore, according to the information processing apparatus 10 according to the embodiment, it is possible to appropriately predict the transaction volume of the electronic payment service in the store group.

In addition, the learning unit 132 according to the embodiment learns a learning model that outputs future information regarding usage patterns of payment services in the store group. Therefore, it is possible to appropriately predict how the electronic payment service will be used in the store group.

Also, the learning unit 132 according to the embodiment learns a learning model that outputs future information on the transaction volume of the payment service in the store group. Therefore, according to the information processing apparatus 10 according to the embodiment, it is possible to appropriately predict the transaction volume of the electronic payment service in the store group.

Also, the learning unit 132 according to the embodiment learns a learning model that outputs a withdrawal score for withdrawal from the payment service as future information. Therefore, according to the information processing apparatus 10 according to the embodiment, it is possible to provide various services considering the withdrawal score.

In addition, the learning unit 132 according to the embodiment learns a learning model for estimating future information regarding changes in the future number of physical stores in the store group. Therefore, according to the information processing apparatus 10, various services can be provided in consideration of changes in the number of stores.

The information processing apparatus 10 according to the embodiment also includes a determining unit 134 that determines purchase conditions for purchasing bonds of the store group based on future information output from the learning model learned by the learning unit 132 . Therefore, according to the information processing apparatus 10 according to the embodiment, it is possible to appropriately determine the purchase conditions of the bond.

In addition, the learning unit 132 according to the embodiment learns a learning model that outputs the probability that the receivables of the store group will become uncollectible as future information. Determine favorable purchase terms. Therefore, according to the information processing apparatus 10 according to the embodiment, it is possible to appropriately determine the purchase conditions of the bond.

Further, an information processing method according to an embodiment is an information processing method executed by a computer, comprising: an acquiring step of acquiring store information about each actual store included in a store group; and a learning step of learning a learning model that outputs future information about the future trend of the store group when inputting . Therefore, according to the information processing method according to the embodiment, it is possible to appropriately predict future trends in the physical store.

Further, the information processing program according to the embodiment includes an acquisition procedure for acquiring store information related to each actual store included in a store group, and when inputting the store information acquired by the acquisition procedure, the store information related to the future trend of the store group. and a learning procedure for learning a learning model that outputs future information. Therefore, according to the information processing program according to the embodiment, it is possible to appropriately predict future trends in the physical store.

[6. Hardware configuration]
Further, the information processing apparatus 10 according to the embodiment described above is implemented by a computer 1000 configured as shown in FIG. 12, for example. FIG. 12 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus 10 according to the embodiment. Computer 1000 has CPU 1100 , RAM 1200 , ROM 1300 , HDD 1400 , communication interface (I/F) 1500 , input/output interface (I/F) 1600 and media interface (I/F) 1700 .

The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400 and controls each section. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. Communication interface 1500 receives data from other devices via network (communication network) N, sends the data to CPU 1100, and transmits data generated by CPU 1100 to other devices via network N. FIG.

Through an input/output interface 1600, the CPU 1100 connects an output device such as a display and a printer, and an input device such as a keyboard and a mouse (in FIG. 12, the output device and the input device are collectively referred to as "input/output device"). ). CPU 1100 acquires data from an input device via input/output interface 1600 . CPU 1100 also outputs the generated data to an output device via input/output interface 1600 .

Media interface 1700 reads programs or data stored in recording medium 1800 and provides them to CPU 1100 via RAM 1200 . CPU 1100 loads such a program from recording medium 1800 onto RAM 1200 via media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. etc.

For example, when the computer 1000 functions as the information processing apparatus 10 according to the embodiment, the CPU 1100 of the computer 1000 implements the functions of the control section 40 by executing programs loaded on the RAM 1200 . The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired via the network N from another device.

As described above, some of the embodiments of the present application have been described in detail based on the drawings. It is possible to carry out the invention in other forms with modifications.

[7. others〕
Further, among the processes described in the above embodiments and modifications, all or part of the processes described as being performed automatically can be performed manually, or described as being performed manually. All or part of the processing can also be performed automatically by a known method. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

Also, each component of each device illustrated is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to the one shown in the figure, and all or part of them can be functionally or physically distributed and integrated in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

Also, the above-described embodiments and modifications can be appropriately combined within a range that does not contradict the processing contents.

Also, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

1 information processing system 10 information processing device 50 user terminal 100 payment server 121 store information database 122 member store information database 123 geographic information database 124 model database 125 factoring database 130 control unit 131 acquisition unit 132 learning unit 133 estimation unit 134 determination unit 200 Store terminal 300 Business operator terminal M model (an example of a learning model)

Claims (3)

an acquisition unit that acquires store information of each of the actual stores, including transaction history of settlement services performed at each of the actual stores included in the store group;
a learning unit that learns a learning model that outputs future information on future trends of the store group when the store information acquired by the acquisition unit is input;
with
The learning unit
An information processing apparatus that learns the learning model that outputs, as the future information, a withdrawal score indicating that the actual shop included in the shop group withdraws from the member shop of the payment service. A computer-executed information processing method comprising:
an acquisition step of acquiring store information of each of the physical stores including transaction history of settlement services performed at each of the physical stores included in the store group;
a learning step of learning a learning model that outputs future information on future trends of the store group when the store information acquired in the acquisition step is input;
including
The learning step includes:
An information processing method, comprising: learning the learning model that outputs, as the future information, a withdrawal score indicating that the actual shop included in the shop group withdraws from the member shop of the payment service. an acquisition procedure for acquiring store information of each of the physical stores including transaction history of payment services performed at each of the physical stores included in the store group;
a learning procedure for learning a learning model that outputs future information on future trends of the store group when the store information acquired by the acquisition procedure is input;
on the computer, and
The learning procedure includes:
An information processing program for learning the learning model that outputs, as the future information, a withdrawal score indicating that the actual shop included in the shop group withdraws from the member shop of the payment service.

Images