JP7507910B1 - Information processing device, information processing method, and information processing program - Google Patents

Abstract

[Problem] To provide an information processing device, information processing method, and information processing program that can easily extract a resale store from among a plurality of stores. [Solution] The information processing device according to the present application includes a reception unit and an estimation unit. The reception unit receives a selection of a resale store from among the plurality of stores. The estimation unit estimates other resale stores from among the plurality of stores based on commonality with the resale store. [Selected Figure] Figure 3

Description

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

Conventionally, electronic commerce (EC) sites have been widely used for trading goods. In addition to each company's own site, there are also shopping mall-type EC sites (hereinafter sometimes referred to as EC malls) where multiple stores are located. In such EC malls, each store offers items for sale, such as goods and services, and sells the offered items to users.

JP 2019-106167 A

The multiple stores opening in an EC mall may include resale stores that resell goods, and the operator of the EC mall may not want to include resale stores in the scope of applications for recommendations, factoring, etc. on the EC mall, for example.

However, since the multiple stores that open in an EC mall include a variety of stores, when an EC mall operator checks each of the multiple stores that open in the EC mall to extract resale stores, the more stores that open in the EC mall, the longer the extraction process takes, which is an issue.

The present application has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can easily extract a resale store from among multiple stores.

The information processing device according to the present application includes a reception unit and an estimation unit. The reception unit receives a selection of a resale store from among a plurality of stores. The estimation unit estimates other resale stores from among the plurality of stores based on commonality with the resale store.

According to one aspect of the embodiment, it is possible to easily extract resale stores from among multiple stores.

FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. FIG. 4 is a diagram illustrating an example of a user information table stored in a user information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of a store information table stored in a store information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of a determination method performed by the determination unit of the information processing device according to the embodiment. FIG. 7 is a flowchart illustrating an example of information processing by the processing unit of the information processing device according to the embodiment. FIG. 8 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment.

Below, the information processing device, information processing method, and information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, information processing method, and information processing program according to the present application are not limited to these embodiments. Furthermore, the embodiments can be appropriately combined as long as they do not cause inconsistencies in the processing content. Furthermore, the same parts in the following embodiments will be given the same reference numerals, and duplicated explanations will be omitted.

[1. An example of information processing]
First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment, which is executed by an information processing device 1.

The information processing device 1 provides information on trade objects of each store located in the EC mall, and mediates or assists in the buying and selling of trade objects between the store and the user U. Such information processing device 1 has, for example, a function to search for trade objects listed in the EC mall, a function to search for stores located in the EC mall, and a function to settle transactions for trade objects listed in the EC mall.

A user U of the EC mall can operate the terminal device 2 to send a search query including a search keyword from the terminal device 2 to the information processing device 1, thereby causing the information processing device 1 to send search results of trading objects listed on the EC mall that correspond to the search query from the terminal device 2. This allows the user U to display on the terminal device 2 the search results that correspond to the search query sent from the information processing device 1.

By setting the name of a trading object as a search keyword to be included in a search query, user U can cause the terminal device 2 to display content that includes one or more pieces of information about a trading object whose name is indicated by the search keyword. In addition, by setting the name of a store as a search keyword to be included in a search query, user U can cause the terminal device 2 to display content that includes one or more pieces of information about a trading object sold at a store whose name is indicated by the search keyword.

As shown in FIG. 1, the information processing device 1 accepts the selection of two or more specific stores from among a plurality of stores (step S1). Each of the plurality of stores is, for example, a virtual store located in an EC mall, and sells trading items such as goods and services.

Specific stores are, for example, resale stores and fraudulent stores. A resale store is a store that resells transaction objects, for example, a store that resells transaction objects without inventory. A fraudulent store is a fraudulent store that commits sales fraud, for example, a store that deceives user U into selling transaction objects or does not ship transaction objects purchased by user U.

The selection of a specific store is performed, for example, by the operator O of the EC mall (including a contractor commissioned by the operator O). For example, the operator O of the EC mall operates the operator device 3 to select two or more specific stores from among a plurality of stores, and selection information indicating the two or more specific stores selected by the operator O is transmitted from the operator device 3 to the information processing device 1. The information processing device 1 accepts the selection information transmitted from the operator device 3, thereby accepting the selection of the specific stores.

In step S1, the information processing device 1 can accept the selection of two or more specific stores from among a plurality of stores for each type of specific store. The types of specific stores are, for example, the resale stores and fraud stores described above, but are not limited to such examples.

Next, the information processing device 1 estimates another specific store from among the multiple stores based on commonality with the two or more specific stores accepted in step S1 (step S2).

For example, the information processing device 1 classifies a plurality of stores into a plurality of clusters, and based on the classification result, estimates stores other than the specific store that are included in the same cluster as the specific store as the other specific store.

Here, the process of step S2 will be described in detail. First, the information processing device 1 acquires transaction object information, which is information on the transaction object of each of the multiple stores (step S2-1).

In step S2-1, the transaction object information acquired by the information processing device 1 includes, for example, target information, category type number information, transaction object number information, code-attached transaction object number information, sales information, cancellation information, and mall purchase information.

The target information is information on a trading object sold in a store and is provided by a user U. Such target information includes one or more of the following: information indicating a user evaluation of the trading object, information indicating the name of the trading object, information indicating an identification code of the trading object, detailed information on the trading object, and image information of the trading object. The user evaluation of the trading object is, for example, the user U's evaluation of the transaction of the trading object, the user U's evaluation of the trading object, the user U's evaluation of the store selling the trading object, etc.

Detailed information on the transaction object includes, for example, information indicating the sales price of the transaction object, information indicating the contents of the transaction object, and information indicating the shipping cost of the transaction object. If the transaction object is food, the contents of the transaction object include, for example, the amount of the transaction object, the raw materials of the transaction object, allergy-related ingredients of the transaction object, the expiration date of the transaction object, and nutritional components of the transaction object. If the transaction object is a home appliance, the contents of the transaction object include, for example, the specifications of the transaction object, an explanation of the transaction object, and cautions for the transaction object.

Category number information is information that indicates the number of types of categories of items sold in a store. Categories are classified, for example, in a tree-like hierarchy. The number of category types is, for example, the number of category types in the store at the lowest level in the tree-like hierarchy, but it may also be the number of category types in a higher level than the lowest level categories.

For example, the major category "Shoes" includes the medium category "Sneakers," which in turn includes the smaller categories "Women's Sneakers," "Men's Sneakers," "Women's Slip-ons," and "Children's Sneakers." In this case, the lowest-level categories are the smaller categories.

The number of trading objects information is information that indicates the number of types of trading objects sold in the store. The type of trading object is specified, for example, by the identification code or model number of the trading object, but may also be specified by the name of the trading object, etc.

The coded transaction object quantity information is information that indicates the number of types of transaction objects with identification codes among the transaction objects sold in the store. The identification code is, for example, a JAN (Japanese Article Number) code, and includes, for example, a country code, manufacturer code, product code, check digit, etc.

The sales information includes, for example, information indicating the sales amount (order amount) of the transaction items at the store, information indicating the number of sales (number of orders) of the transaction items at the store, information indicating the number of days since the store opened, and information indicating the average period for which the transaction items at the store remain unshipped.

The sales amount is, for example, the sales amount (order amount) per unit time (for example, per day, week, or month) at the store. The sales amount may also be the sales amount per unit time for each transaction object at the store or the sales amount (order amount) per unit time for each category. The sales amount is the sales scale at the store (GMV: Gross Merchandise Value), but may also be the amount after deducting the commission paid by the store to the operator of the EC mall.

The sales volume is the number of sales (orders) per unit of time (e.g., per day, week, or month) at the store. The sales volume may also be the number of sales per unit of time for each transaction object at the store or the number of sales (orders) per unit of time for each category.

The information indicating the number of days since the store opened includes information indicating the number of days since the store opened in the EC mall. The information indicating the average unshipped period for transaction items at the store includes information indicating the average unshipped period from the time of order to the start of shipping for transaction items that have been accepted at the store.

Cancellation information is information that indicates the cancellation rate of transaction objects per unit of time (e.g., daily, weekly, or monthly) at the store. The cancellation rate of transaction objects is, for example, the number of canceled transaction objects divided by the number of transaction objects sold (ordered). Cancellation of transaction objects includes cancellations of transaction objects before they are shipped, as well as cancellations of transaction objects after they are shipped (e.g., cancellations due to returns).

The mall purchase information includes information indicating the number of times a user U who has purchased a transaction object from a store has purchased the transaction object at the EC mall, and information indicating the number of times a user U who has purchased a transaction object from a store has subsequently purchased the transaction object at the EC mall. Hereinafter, each of these numbers of purchases may be referred to as the number of mall purchases.

Then, the information processing device 1 classifies the multiple stores into multiple clusters based on the transaction target information of each of the multiple stores acquired in step S2-1 (step S2-2). In this way, the information processing device 1 classifies the multiple stores into multiple clusters based on the commonality between the stores identified from the transaction target information.

For example, the information processing device 1 extracts multiple pieces of information that are subject to features from the transaction target information as feature information, and classifies multiple stores into multiple clusters based on the multiple extracted feature information.

The characteristic information may include, for example, two or more of information indicating the store's sales figures (e.g., weekly sales figures), information indicating the number of types of trading items in the store, information indicating the number of types of trading items with identification codes in the store, and information indicating the number of types of categories of trading items in the store.

Furthermore, the characteristic information may include, instead of or in addition to some or all of the above-mentioned information, one or more of information indicating the cancellation rate of the transaction object in the store, information indicating the number of mall purchases as described above, information indicating user ratings regarding the transaction object in the store, information indicating the name of the transaction object in the store, detailed information about the transaction object in the store, and image information about the transaction object in the store.

In step S2-2, the information processing device 1 reduces the dimensionality of the feature information of each of the multiple stores using UMAP (Uniform Manifold Approximation and Projection) and projects the multiple stores into a two-dimensional space.

The feature dimension reduction method is not limited to UMAP, and the information processing device 1 may reduce the dimension of features using other dimension reduction methods, such as t-SNE (t-distributed Stochastic Neighbor Embedding), PCA (Principal Component Analysis), PCA & UMAP, etc.

The information processing device 1 classifies the multiple stores projected onto a two-dimensional space into multiple clusters. For example, the information processing device 1 classifies the multiple stores into multiple clusters by the k-means method. The information processing device 1 can also classify the multiple stores into multiple clusters by using, for example, spectral clustering, Gaussian mixture models (GMM), or neural networks instead of the k-means method, and can also classify the multiple stores into multiple clusters by other clustering methods.

Then, the information processing device 1 determines whether or not two or more specific stores received in step S1 among the multiple stores classified into multiple clusters in step S2-2 are classified into the same cluster (step S2-3).

In step S2-3, if the information processing device 1 has received the selection of two or more specific stores for each of multiple types of specific stores in step S1, it determines for each type of specific store whether the specific stores are classified into the same cluster.

Next, if the information processing device 1 determines in step S2-3 that the two or more specific stores selected in step S1 are classified into the same cluster, it extracts stores included in the cluster into which the specific stores are classified, other than the two or more specific stores selected in step S1, as common stores that share characteristics with the two or more specific stores selected in step S1 (step S2-4). Note that the "characteristics" are the characteristics of the stores indicated in the transaction target information described above, etc.

The common store is a store that is estimated to be a specific store other than the two or more specific stores selected in step S1. For example, if the type of the two or more specific stores selected in step S1 is a resale store, the common store is a resale store other than the two or more resale stores selected in step S1.

In step S2-4, if the information processing device 1 has received a selection of two or more specific stores for each of multiple types of specific stores in step S1, the information processing device 1 extracts a common store for each type of specific store. For example, if the specific stores selected in step S1 are a resale store and a fraud store, the information processing device 1 extracts each of the resale store and the fraud store as different common stores.

For example, if the information processing device 1 determines that two or more resale stores selected in step S1 are classified into the same cluster, it estimates the remaining stores that are included in the same cluster as the two or more resale stores selected in step S1 and are other than the two or more resale stores selected in step S1 as other resale stores.

In addition, when the information processing device 1 determines that two or more fraudulent stores selected in step S1 are classified into the same cluster, it estimates the remaining stores that are included in the same cluster as the two or more fraudulent stores selected in step S1 and are other than the two or more fraudulent stores selected in step S1 as other fraudulent stores.

The information processing device 1 notifies the operator O of the information on the other specific stores estimated in step S2 by transmitting the extracted information, which is information on the other specific stores estimated in step S2, to the operator device 3 (step S3).

In this way, the information processing device 1 accepts the selection of a specific store from among multiple stores, and infers another specific store from among the multiple stores based on commonality with the specific store. This allows the information processing device 1 to easily extract a specific store (e.g., a resale store or a fraud store) from among multiple stores that open in an EC mall.

The information processing device 1 also classifies the multiple stores into multiple clusters based on transaction target information, which is information on the transaction targets of each of the multiple stores, and determines whether a specific store among the multiple stores has been classified into the same cluster. If the information processing device 1 determines that the specific store has been classified into the same cluster, it extracts stores other than the specific store that are included in the cluster into which the specific store has been classified as common stores that share characteristics with the specific store. This allows the information processing device 1 to easily extract a specific store from among the multiple stores opening in the EC mall.

The following provides a detailed explanation of the configuration of an information processing system that includes an information processing device 1, a terminal device 2, and an operator device 3 that perform such processing.

2. Configuration of Information Processing System
2 is a diagram showing an example of a configuration of an information processing system according to an embodiment. As shown in FIG. 2, the information processing system 100 according to the embodiment includes an information processing device 1, a plurality of terminal devices 2, and an operator device 3.

The multiple terminal devices 2 are used by different users U. The terminal devices 2 are, for example, a notebook PC (Personal Computer), a desktop PC, a smartphone, a tablet PC, or a wearable device. The wearable device is, for example, smart glasses or a smart watch, but is not limited to these examples. The user U is a user who uses a service provided by the information processing device 1 or the like.

The operator device 3 is a terminal device used by the operator O. The operator device 3 and the terminal device 2 are, for example, a notebook PC, a desktop PC, a smartphone, a tablet PC, etc., but are not limited to such examples.

The information processing device 1, the terminal device 2, and the operator device 3 are connected to each other via the network N so that they can communicate with each other via wired or wireless communication. Note that the information processing system 100 shown in FIG. 2 may include multiple information processing devices 1, etc.

The network N includes, for example, a WAN (Wide Area Network) such as the Internet and mobile communication networks such as LTE (Long Term Evolution), 4G (4th Generation), and 5G (5th Generation: 5th generation mobile communication system).

The terminal device 2 and the operator device 3 can connect to the network N via short-range wireless communication such as a mobile communication network, Bluetooth (registered trademark), or a wireless LAN (Local Area Network), and communicate with the information processing device 1.

3. Configuration of information processing device 1
3 is a diagram showing an example of the configuration of the information processing device 1 according to the embodiment. As shown in FIG. 3, the information processing device 1 includes a communication unit 10, a storage unit 11, and a processing unit 12.

3.1. Communication unit 10
The communication unit 10 is realized by, for example, a network interface card (NIC). The communication unit 10 is connected to a network N by wire or wirelessly, and transmits and receives information to and from various other devices. For example, the communication unit 10 transmits and receives information to and from the terminal device 2 and the operator device 3 via the network N.

3.2. Storage unit 11
The storage unit 11 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 11 has a user information storage unit 20 and a store information storage unit 21.

[3.2.1. User information storage unit 20]
The user information storage unit 20 stores various pieces of information related to the user U. Fig. 4 is a diagram showing an example of a user information table stored in the user information storage unit 20 according to the embodiment.

In the example shown in FIG. 4, the user information table stored in the user information storage unit 20 includes information on items such as "User ID (Identifier)," "Attribute Information," and "Setting Information."

The "user ID" is an identifier that identifies a user U, and is information that is assigned to each user U. The "attribute information" is attribute information that indicates the attributes of the user U associated with the "user ID." The attributes of the user U are, for example, demographic attributes and psychographic attributes. The demographic attributes are demographic attributes, and include multiple attribute items such as age, sex, occupation, place of residence, annual income, and family structure.

Psychographic attributes are psychological attributes and include, for example, multiple attribute items related to lifestyle, values, interests, etc. For example, each of the multiple attribute items in the psychographic attributes is an object of interest to the user U, such as cars, clothes, travel, games, camping, motorcycles, trains, home appliances, or computers.

The "setting information" is the setting information of the user U associated with the "user ID." Note that the information stored in the user information storage unit 20 is not limited to the information described above, and may include various information related to the user U.

[3.2.2. Store information storage unit 21]
The store information storage unit 21 stores information about each store. Fig. 5 is a diagram illustrating an example of a store information table stored in the store information storage unit 21 according to the embodiment.

In the example shown in FIG. 5, the store information table stored in the store information storage unit 21 includes information on items such as "store ID," "store name," "store opening date," and "transaction target information."

"Store ID" is an identifier that identifies a store, and is information assigned to each store. "Store name" is information that indicates the name of the store corresponding to the "Store ID." "Store opening date" is information that indicates the date or date and time that the store corresponding to the "Store ID" began opening in the EC mall.

"Transaction target information" includes, for example, the above-mentioned target information, category type number information, target type number information, coded transaction target number information, sales information, cancellation information, and mall purchase information.

3.3. Processing section 12
The processing unit 12 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) by executing various programs stored in a storage device inside the terminal device 2 using a RAM as a working area.

The processing unit 12 may be realized in whole or in part by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 3, the processing unit 12 has an acquisition unit 30, a reception unit 31, an estimation unit 32, an exclusion unit 33, and a provision unit 34, and realizes or executes the functions and actions of the information processing described below. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 3, and may be other configurations as long as they perform the information processing described below.

3.3.1. Acquisition unit 30
The acquisition unit 30 acquires various information from an external information processing device, the terminal device 2 or the like via the communication unit 10 , and stores the acquired information in the storage unit 11 .

For example, the acquisition unit 30 acquires user information, which is information about the user U, from an external information processing device or a terminal device 2, etc., via the communication unit 10, and adds the acquired user information to a user information table in the user information storage unit 20.

The acquisition unit 30 also acquires some or all of the transaction target information for each of the multiple stores via the communication unit 10 from an external information processing device or a store terminal device, and adds some or all of the acquired transaction target information to a store information table stored in the store information storage unit 21.

The acquisition unit 30 can also acquire information on electronic commerce in the EC mall provided by the provision unit 34 from the provision unit 34 as part or all of the transaction target information, and add part of the acquired transaction target information to the store information table stored in the store information storage unit 21.

The acquisition unit 30 also acquires various types of information from the storage unit 11. For example, the acquisition unit 30 acquires user information, which is information about the user U, from the user information storage unit 20 or the like. The user information acquired by the acquisition unit 30 includes, for example, a part or all of at least one of the attribute information and setting information described above.

The acquisition unit 30 also acquires transaction target information, which is information on the transaction targets of each of the multiple stores, from the store information storage unit 21. The transaction target information includes, for example, the above-mentioned target information, category type number information, target type number information, code-attached transaction target number information, sales information, cancellation information, and mall purchase information. The acquisition unit 30 also acquires information indicating the opening date of each of the multiple stores.

3.3.2. Reception unit 31
The reception unit 31 receives various requests and information from an external information processing device, the terminal device 2, and the like via the communication unit 10.

For example, the reception unit 31 receives a search query sent from the terminal device 2 via the communication unit 10. Such a search query includes information that identifies, for example, the name of the transaction object, the category of the transaction object, or the name of the store.

The reception unit 31 also receives an order query sent from the terminal device 2 via the communication unit 10. The order query includes information for identifying the transaction object and the quantity for which the user U has decided to order (purchase), etc.

The reception unit 31 also receives a cancellation query sent from the terminal device 2 via the communication unit 10. The cancellation query includes information for identifying the transaction object that has been decided to be ordered (purchased) by the user U and is subject to cancellation.

The reception unit 31 also receives a selection of two or more specific stores from among the multiple stores included in the EC mall from the operator O or the like. The reception unit 31 receives selection information transmitted from the operator device 3. The selection information includes information for identifying each of the two or more specific stores selected by the operator O.

The specific store selected by the operator O or the like is, for example, one or more types of specific stores among multiple types of specific stores. The types of specific stores are, for example, resale stores, fraud stores, etc., but are not limited to such examples.

3.3.3. Estimation unit 32
The estimation unit 32 estimates another specific store from among the multiple stores in the EC mall, based on commonality with the two or more specific stores whose selections have been accepted by the acceptance unit 31.

The estimation unit 32 classifies the multiple stores into multiple clusters, for example, based on commonalities between the stores identified from the transaction target information of each of the multiple stores acquired by the acquisition unit 30.

For example, when a specific store accepted by the acceptance unit 31 is a resale store, the estimation unit 32 estimates other resale stores from among the multiple stores based on the result of classifying the multiple stores into multiple clusters.

In addition, for example, when a specific store accepted by the acceptance unit 31 is a fraudulent store, the estimation unit 32 estimates other resale stores from among the multiple stores based on the result of classifying the multiple stores into multiple clusters.

The estimation unit 32 includes a classification unit 40 that classifies a plurality of stores into a plurality of clusters, a determination unit 41 that determines whether or not two or more target specific stores, which are two or more specific stores whose selections have been accepted by the acceptance unit 31, have been classified into the same cluster, and an extraction unit 42 that extracts stores that share characteristics with the two or more target specific stores as other specific stores (common stores) based on the determination result of the determination unit 41. The classification unit 40, the determination unit 41, and the extraction unit 42 will be described in detail below.

3.3.3.1. Classification Unit 40
The classification unit 40 classifies the multiple stores into multiple clusters based on the transaction target information of each of the multiple stores acquired by the acquisition unit 30. The classification unit 40 classifies the multiple stores into multiple clusters using, for example, two or more pieces of information included in the transaction target information as characteristic information.

The characteristic information used by the classification unit 40 includes, for example, two or more of information indicating the store's sales figures (e.g., weekly sales figures), information indicating the number of types of trading items in the store, information indicating the number of types of trading items with identification codes in the store, and information indicating the number of types of categories of trading items in the store.

The type of trading object differs for each identification code if the trading object is an identification code-attached trading object, differs for each model number of the trading object if the trading object is not an identification code-attached trading object, and differs for each product name or category of the trading object if the trading object is not an identification code-attached trading object and does not have a model number.

Resale stores tend to have low sales numbers (e.g., weekly sales numbers) relative to the number of types of traded items and the number of types of categories, and tend to have few traded items with identification codes relative to the number of types of traded items. Fraudulent stores may also tend to differ from resale stores and other stores in terms of the store's sales numbers, the number of types of traded items at the store, traded items with identification codes at the store, and the number of types of categories of traded items at the store.

The classification unit 40 uses, as characteristic information, two or more pieces of information, such as information indicating the store's sales volume (e.g., weekly sales volume), information indicating the number of types of trading objects in the store, information indicating the number of types of trading objects with identification codes in the store, and information indicating the number of types of categories of trading objects in the store. This allows the classification unit 40 to appropriately classify multiple stores into multiple clusters in order to classify resale stores.

In addition, the characteristic information may further include, in place of or in addition to some or all of the above-mentioned information, one or more of information indicating the sales amount of the transaction item in the store (e.g., the sales amount per week), information indicating the cancellation rate of the transaction item in the store (e.g., the number of cancellations per week), and information indicating the number of mall purchases.

For example, resale stores tend to have low sales amounts for traded items, a high cancellation rate for traded items, and a low number of mall purchases. Fraudulent stores may also have different tendencies from resale stores and other stores in terms of sales amounts for traded items and the number of mall purchases.

The classification unit 40 therefore uses, as additional characteristic information, the sales amount of the transaction object (e.g., the weekly sales amount), the cancellation rate of the transaction object (e.g., the weekly cancellation rate), the number of mall purchases, etc. This allows the classification unit 40 to appropriately classify multiple stores, including resale stores and fraudulent stores, into multiple clusters.

In addition, the characteristic information may include one or more of information indicating user ratings of the trading object in the store, information indicating the name of the trading object in the store, detailed information of the trading object in the store, and image information of the trading object in the store, instead of or in addition to some or all of the above-mentioned information. This allows the classification unit 40 to appropriately classify multiple stores, including resale stores and fraudulent stores, into multiple clusters.

In addition, the characteristic information can appropriately classify one or more of the following into multiple clusters in place of or in addition to some or all of the above information: the number of days since the store's opening date and time in the EC mall, the average unshipped period for transaction items for which orders have been accepted, etc.

The classification unit 40 reduces the dimension of the feature information of each of the multiple stores using UMAP, and projects the multiple stores into a two-dimensional space. Note that the method for reducing the dimension of the feature is not limited to UMAP, and the classification unit 40 may reduce the dimension of the feature using other dimension reduction methods, such as t-SNE, PCA, or PCA & UMAP.

The classification unit 40 classifies the multiple stores projected onto the two-dimensional space into multiple clusters. For example, the classification unit 40 classifies the multiple stores into multiple clusters using the k-means method. The classification unit 40 can also classify the multiple stores into multiple clusters using, for example, spectral clustering, a mixture of Gaussian distributions (GMM), or a neural network instead of the k-means method, or can classify the multiple stores into multiple clusters using other clustering methods.

In the above example, the classification unit 40 classifies the multiple stores into multiple clusters by unsupervised clustering, but supervised clustering can also be performed. For example, assume that the reception unit 31 receives a selection of multiple specific stores and multiple stores other than the specific store for each type of specific store.

In this case, the classification unit 40 generates learning data for each type of specific store based on the transaction target information of the store whose selection has been accepted by the acceptance unit 31, using information indicating the presence or absence of multiple specific stores as labels, and using various types of information included in the transaction target information as features.

The classification unit 40 then uses the generated learning data to generate a learning model for each type of specific store that inputs various information included in the transaction target information and outputs a score indicating the possibility that the store is a specific store. Such a learning model is a model that uses the transaction target information of a store to determine whether or not the store is a specific store.

The classification unit 40 uses the learning model described above to classify a store as either a cluster included in a specific store or a cluster not included in a specific store. For example, the classification unit 40 inputs two or more pieces of feature information included in the transaction target information of a store into the learning model, and if the score output from the learning model is equal to or greater than a threshold, it determines that the store is a specific store, and if not, it determines that the store is not a specific store.

Learning models include, but are not limited to, logistic regression, GBDT (Gradient Boosting Decision Tree), averaged perception, support vector machine, and neural network.

3.3.3.2. Determination unit 41
The determination unit 41 determines whether or not two or more specific stores among the multiple stores have been classified into the same cluster by the classification unit 40. For example, the determination unit 41 determines whether or not the two or more specific stores whose selections have been accepted by the acceptance unit 31 have all been classified into the same cluster.

In addition, when the two or more specific stores selected and accepted by the acceptance unit 31 are of multiple types, the judgment unit 41 judges for each type of specific store whether or not all of the two or more specific stores of the same type are classified into the same cluster.

Fig. 6 is a diagram showing an example of a determination method by the determination unit 41 of the information processing device 1 according to the embodiment. In the example shown in Fig. 6, in the two-dimensional space onto which the classification unit 40 projects multiple stores, all four specific stores whose selections are accepted by the acceptance unit 31 are classified into the same cluster.

In the example shown in FIG. 6, the four specific stores whose selections have been accepted by the accepting unit 31 are all specific stores of a single type (e.g., only resale stores). In this case, the determining unit 41 determines that all four specific stores whose selections have been accepted by the accepting unit 31 are classified into the same cluster.

[3.3.3.3. Extraction Unit 42]
The extraction unit 42 extracts, as common stores for each type of specific store, specific stores other than the two or more specific stores selected by the reception unit 31 from the multiple stores based on the determination result of the determination unit 41. The specific stores extracted by the extraction unit 42 are the other specific stores estimated by the estimation unit 32.

For example, when the determination unit 41 determines that two or more specific stores are classified into the same cluster, the extraction unit 42 extracts stores other than the specific stores that are included in the cluster into which the classification unit 40 classifies the two or more specific stores as common stores that share characteristics with the specific stores.

For example, suppose that the type of specific store determined by the determination unit 41 is only a resale store, the number of specific stores accepted by the acceptance unit 31 is four, all of these four specific stores are classified into the same cluster, and the number of stores included in this cluster is 10. In this case, the extraction unit 42 extracts each of the remaining six stores classified into the same cluster as these four specific stores as common stores.

For example, when the determination unit 41 determines for each type of specific store whether two or more specific stores of the same type are all classified into the same cluster, the extraction unit 42 extracts a common store for each type of specific store.

For example, when the type of a specific store determined by the determination unit 41 is a resale store, the extraction unit 42 extracts stores other than the two or more resale stores whose selection has been accepted by the acceptance unit 31 as other resale stores (an example of a common store).

In addition, when the type of the specific store determined by the determination unit 41 is a fraudulent store, the extraction unit 42 extracts stores other than the two or more fraudulent stores whose selection has been accepted by the acceptance unit 31 as other fraudulent stores (an example of a common store).

3.3.4. Exclusion Unit 33
The exclusion unit 33 can exclude the common store extracted by the extraction unit 42 from the provision targets of the specific service. The specific service is, for example, recommendation or factoring.

The target of the recommendation is the target of the recommendation as a store proposed to the user U by the providing unit 34, and information about the store to which the recommendation is applied is included in the recommendation information as information recommended to the user U by the providing unit 34, for example.

Furthermore, the target of factoring is a store that receives sales proceeds in advance from an EC mall, and the operator of a store that is the target of factoring can receive sales proceeds in advance from the operator of the EC mall.

The exclusion unit 33 can, for example, exclude a resale store extracted by the extraction unit 42 from either the target of recommendation application or the target of factoring application. The exclusion unit 33 can also exclude a resale store extracted by the extraction unit 42 from the EC mall by having the store leave the EC mall.

This makes it possible, for example, to restrict the services available to a resale store that is prohibited from reselling (e.g., inventory-less resale) under the terms of the EC mall, or to expel the store from the EC mall.

In addition, because resale stores have a higher closure rate than average stores, excluding resale stores from the scope of factoring can prevent difficulties in collecting sales proceeds in advance.

The exclusion unit 33 can also, for example, exclude a fraudulent store extracted by the extraction unit 42 from either the target of recommendation application or the target of factoring application. The exclusion unit 33 can also exclude a fraudulent store extracted by the extraction unit 42 from the EC mall by having the store leave the EC mall.

3.3.5. Providing unit 34
The providing unit 34 provides various information to the user U and the operator O, respectively, by transmitting the various information to the terminal device 2 and the operator device 3, respectively, via the communication unit 10.

For example, the providing unit 34 provides an electronic commerce service to the user U. For example, when a search query transmitted from the terminal device 2 is received by the receiving unit 31, the providing unit 34 transmits search results based on information included in the search query to the terminal device 2 via the communication unit 10, thereby providing the search results to the user U.

Search results based on the information included in the search query include, for example, information on one or more transaction objects corresponding to the information included in the search query, information on one or more stores corresponding to the information included in the search query, etc. User U can refer to the search results provided by the information processing device 1 and displayed on the terminal device 2 to search for transaction objects that he or she wishes to purchase, etc.

When the reception unit 31 receives an order query sent from the terminal device 2, the providing unit 34 performs a buying and selling process for the transaction object identified in the order query. When the reception unit 31 receives a cancel query sent from the terminal device 2, the providing unit 34 cancels the order for the transaction object identified in the cancel query.

The providing unit 34 also provides the extracted information, including information on other specific stores extracted as common stores by the extracting unit 42, to the operator device 3 via the communication unit 10, thereby providing the extracted information to the operator O. The extracted information includes, for example, the store IDs of each of the other specific stores extracted as common stores by the extracting unit 42.

The providing unit 34 can also provide the extracted information to the operator O by transmitting the extracted information including information on the specific store accepted by the accepting unit 31 in addition to information on other specific stores extracted as common stores by the extracting unit 42 to the operator device 3 via the communication unit 10. In this case, the extracted information includes, for example, the store ID of each of the other specific stores extracted as common stores by the extracting unit 42 and the store ID of the specific store accepted by the accepting unit 31.

The providing unit 34 can also extract information including the above-mentioned extraction information for each of multiple types of specific stores as the extraction information. In this case, the extraction information includes, for example, information indicating the type of each of the multiple specific stores.

The providing unit 34 can also recommend stores to which the recommendations are applicable. For example, the store recommendations are provided to the user U by transmitting recommendation information including information indicating a recommended store or a recommended transaction target to the terminal device 2 of the user U via the communication unit 10.

The providing unit 34 does not recommend a specific store that has been excluded from the application of recommendations by the excluding unit 33. This allows the processing unit 12 to exclude a specific store or a transaction target that has been excluded from the application of recommendations as a recommended store or a recommended transaction target.

The providing unit 34 can also perform a prepayment process of the sales proceeds of the store at the EC mall as a settlement process to the operator of the store that is the subject of factoring. The providing unit 34 does not perform a prepayment process of the sales proceeds to the operator of a specific store that has been excluded from the subject of factoring by the excluding unit 33. This allows the processing unit 12 to exclude a specific store that has been excluded from the subject of factoring from the subject of factoring.

4. Processing Procedure
Next, a procedure of information processing by the processing unit 12 of the information processing device 1 according to the embodiment will be described. Fig. 7 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

As shown in FIG. 7, the processing unit 12 of the information processing device 1 determines whether or not a query has been received from the terminal device 2 (step S10). If the processing unit 12 determines that a query has been received (step S10: Yes), it performs processing according to the received query (step S11).

When the processing of step S11 is completed or when it is determined that a query has not been received (step S10: No), the processing unit 12 determines whether or not selection information has been received from the operator device 3 (step S12).

If the processing unit 12 determines that the selection information has been received (step S12: Yes), the processing unit 12 acquires transaction target information for each of the multiple stores (step S13). Then, the processing unit 12 classifies the multiple stores into multiple clusters based on the transaction target information for each of the multiple stores acquired in step S13 (step S14).

Next, the processing unit 12 determines whether the specific stores determined to have been accepted in step S10 are classified into the same cluster for each type of specific store (step S15). Then, the processing unit 12 extracts other stores included in the cluster into which the specific store is classified as common stores (e.g., resale stores and fraud stores) for each type of specific store (step S16).

Then, the processing unit 12 provides the extracted information to the operator O by transmitting the extracted information including the information on the specific stores extracted in step S16 for each of the specific store types to the operator device 3 (step S17).

When the processing of step S17 is completed or when it is determined that the selection information has not been received (step S12: No), the processing unit 12 determines whether or not the operation end timing has arrived (step S18). The processing unit 12 determines that the operation end timing has arrived, for example, when the power supply of the information processing device 1 is turned off.

If the processing unit 12 determines that the operation end time has not yet arrived (step S18: No), it transitions to step S10, and if it determines that the operation end time has arrived (step S18: Yes), it terminates the processing shown in FIG. 7.

5. Transformation
In the above example, the processing unit 12 classified multiple stores in the same EC mall as classification targets, but it can also classify multiple stores in multiple different EC malls as classification targets, or classify multiple stores in an e-commerce site other than an EC mall as classification targets.

Furthermore, when the determination unit 41 determines that multiple specific stores have not been classified into the same cluster by the classification unit 40, the classification unit 40 changes an initial value (e.g., a seed value) and repeats the classification process, which is a process of classifying multiple stores into multiple clusters. For example, the classification unit 40 repeats the classification process while changing the initial value, until the determination unit 41 determines that specific stores have been classified into the same cluster by the classification unit 40.

In the above example, the determination unit 41 determines whether two or more specific stores among the multiple stores have been classified into the same cluster by the classification unit 40, but is not limited to such an example. For example, when the number of specific stores accepted by the acceptance unit 31 is one, the determination unit 41 determines whether one specific store among the multiple stores has been classified into the same cluster by the classification unit 40. In this case, the extraction unit 42 extracts specific stores other than the one specific store whose selection has been accepted by the acceptance unit 31 as common stores from the multiple stores for each type of specific store.

The extraction unit 42 can also extract, as a common store, other specific stores that have a sales amount (e.g., weekly sales amount) of 1 million or less and a sales volume (e.g., weekly sales volume) of 100 or less from among multiple other specific stores that are determined by the determination unit 41 to be classified into the same cluster.

The classification unit 40 can also perform the classification process (clustering) n times. n is an integer equal to or greater than 2. In this case, when the determination unit 41 determines m or more times that multiple specific stores have been classified into the same cluster by the classification unit 40, the extraction unit 42 can also extract a specific store other than the specific store whose selection has been accepted by the acceptance unit 31. m is an integer equal to or greater than 2, and n and m have a relationship of, for example, n>m. Note that m is, for example, a value greater than 1/2 of n, but may be a value independent of n.

The classification unit 40 can also calculate the degree of agreement between information indicating the contents of the transaction object in a specific store and information indicating the contents of the transaction object in stores other than the specific store for each type of transaction object, and classify multiple stores into multiple clusters using multiple pieces of characteristic information that further include information indicating the calculated degree of agreement as characteristic information.

The classification unit 40 can also estimate, for example, information that is useful for classification processing among information included in the transaction target information of each of a plurality of stores. For example, the classification unit 40 compares, for each piece of information, information included in the transaction target information of a specific store with information included in transaction target information other than the specific store, and estimates information with a large difference as information useful for classification processing. In this case, the classification unit 40 uses information that is estimated to be useful for classification processing as characteristic information.

In the above example, the classification process for multiple stores including multiple types of specific stores is performed together, but it is also possible to perform classification process for multiple stores by specific store type.

6. Hardware Configuration
The information processing device 1 according to the embodiment described above is realized by a computer 80 having a configuration as shown in Fig. 8. Fig. 8 is a hardware configuration diagram showing an example of the computer 80 that realizes the functions of the information processing device 1 according to the embodiment. The computer 80 has a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, a HDD (Hard Disk Drive) 84, a communication interface (I/F) 85, an input/output interface (I/F) 86, and a media interface (I/F) 87.

The CPU 81 operates based on the programs stored in the ROM 83 or the HDD 84, and controls each part. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 starts up, and programs that depend on the hardware of the computer 80.

The HDD 84 stores programs executed by the CPU 81 and data used by such programs. The communication interface 85 receives data from other devices via the network N (see FIG. 2) and sends the data to the CPU 81, and transmits data generated by the CPU 81 to other devices via the network N.

The CPU 81 controls output devices such as a display and a printer, and input devices such as a keyboard or a mouse, via the input/output interface 86. The CPU 81 acquires data from the input devices via the input/output interface 86. The CPU 81 also outputs data generated via the input/output interface 86 to the output devices.

The media interface 87 reads a program or data stored in the recording medium 88 and provides it to the CPU 81 via the RAM 82. The CPU 81 loads the program from the recording medium 88 onto the RAM 82 via the media interface 87 and executes the loaded program. The recording medium 88 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.

For example, when the computer 80 functions as the information processing device 1 according to the embodiment, the CPU 81 of the computer 80 executes a program loaded onto the RAM 82 to realize the functions of the processing unit 12. In addition, the data in the storage unit 11 is stored in the HDD 84. The CPU 81 of the computer 80 reads and executes these programs from the recording medium 88, but as another example, these programs may be obtained from another device via the network N.

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

In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

For example, the information processing device 1 described above may be realized by a terminal device and a server computer, or may be realized by multiple server computers. Also, depending on the function, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

The above-described embodiments and variations can be combined as appropriate to the extent that they do not cause inconsistencies in the processing content.

8. Effects
As described above, the information processing device 1 according to the embodiment includes a reception unit 31 that receives a selection of a resale store from among a plurality of stores, and an estimation unit 32 that estimates other resale stores from among the plurality of stores based on commonality with the resale store. This allows the information processing device 1 to easily extract a resale store from among the plurality of stores.

The information processing device 1 also includes an acquisition unit 30 that acquires transaction target information, which is information on the transaction target of each of the multiple stores, and the estimation unit 32 includes a classification unit 40 that classifies the multiple stores into multiple clusters based on the transaction target information acquired by the acquisition unit 30, a determination unit 41 that determines whether or not a resale store among the multiple stores has been classified into the same cluster by the classification unit 40, and an extraction unit 42 that extracts stores other than the resale store that are included in the cluster into which the resale store has been classified by the determination unit 41 among the multiple stores as other resale stores. This allows the information processing device 1 to accurately extract resale stores from the multiple stores.

The resale store is one of multiple types of resale stores, and the determination unit 41 determines for each type of resale store whether the resale store has been classified into the same cluster by the classification unit 40, and the extraction unit 42 extracts other resale stores for each type of resale store. This allows the information processing device 1 to extract resale stores for each type of resale store from among multiple stores.

In addition, the trading object information estimates other resale stores based on two or more of information indicating the number of trading objects sold at the store, information indicating the number of types of trading objects at the store, information indicating the number of types of trading objects with identification codes at the store, and information indicating the number of types of categories of trading objects at the store. This allows the information processing device 1 to accurately extract resale stores from among multiple stores.

In addition, the transaction target information estimates other resale stores based on information indicating the cancellation rate of transaction targets at a store. This allows the information processing device 1 to accurately extract resale stores from among multiple stores.

The trading target information estimates other resale stores based on one or more of information indicating user ratings on the trading target, information indicating the name of the trading target, detailed information on the store's trading target, and image information on the trading target. This allows the information processing device 1 to accurately extract resale stores from among multiple stores.

The information processing device 1 also includes an exclusion unit 33 that excludes other resale stores estimated by the estimation unit 32 from the application of recommendations or factoring. This allows the information processing device 1 to exclude a specific store from among multiple stores from the application of recommendations or factoring.

The above describes the embodiments of the present application in detail based on the drawings, but this is merely an example, and the present invention can be implemented in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the disclosure section of the invention.

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

REFERENCE SIGNS LIST 1 Information processing device 2 Terminal device 3 Operator device 10 Communication unit 11 Storage unit 12 Processing unit 20 User information storage unit 21 Store information storage unit 30 Acquisition unit 31 Reception unit 32 Estimation unit 33 Exclusion unit 34 Provision unit 40 Classification unit 41 Determination unit 42 Extraction unit 100 Information processing system N Network

Claims (11)

A reception unit that receives a selection of a resale store from among a plurality of stores;
An acquisition unit that acquires transaction object information, which is information on a transaction object of each of the plurality of stores;
and an estimation unit that estimates another resale store from among the plurality of stores based on a commonality with the resale store ;
The estimation unit is
A classification unit that classifies the plurality of stores into a plurality of clusters based on the transaction target information acquired by the acquisition unit;
a determination unit that determines whether the resale store among the plurality of stores is classified into the same cluster by the classification unit;
an extraction unit that extracts, from among the plurality of stores, stores that are included in the cluster into which the resale store is classified by the determination unit and are other than the resale store, as the other resale store;
23. An information processing apparatus comprising: A reception unit that receives a selection of a fraudulent store from among a plurality of stores;
An acquisition unit that acquires transaction object information, which is information on a transaction object of each of the plurality of stores;
An estimation unit that estimates another fraudulent store from among the plurality of stores based on a commonality with the fraudulent store,
The estimation unit is
A classification unit that classifies the plurality of stores into a plurality of clusters based on the transaction target information acquired by the acquisition unit;
a determination unit that determines whether the fraudulent store among the plurality of stores is classified into the same cluster by the classification unit;
an extraction unit that extracts, from among the plurality of stores, stores that are included in the cluster into which the fraudulent store is classified by the determination unit and are other than the fraudulent store, as the other fraudulent stores.
23. An information processing apparatus comprising: The resale store:
It is one of several types of resale stores,
The determination unit is
Determining whether the resale stores are classified into the same cluster by the classification unit for each type of the resale store;
The extraction unit is
The information processing device according to claim 1 , wherein the other resale stores are extracted for each type of the resale store. The estimation unit is
The information processing device described in claim 1 or 3, characterized in that the other resale store is estimated based on two or more of information indicating the number of trading items sold at the store, information indicating the number of types of the trading items at the store, information indicating the number of types of the trading items with identification codes at the store, and information indicating the number of types of categories of the trading items at the store. The estimation unit is
The information processing device according to claim 1 or 3 , characterized in that the other resale store is estimated based on information indicating a cancellation rate of transaction objects in the store. The estimation unit is
The information processing device described in claim 1 or 3, characterized in that the other resale store is estimated based on one or more of information indicating user ratings of the trading item of the store, information indicating the name of the trading item, detailed information of the trading item, and image information of the trading item. The information processing device according to claim 1 or 3, further comprising an exclusion unit that excludes the other resale store estimated by the estimation unit from targets for recommendation or factoring. 1. A computer-implemented information processing method, comprising:
A reception process for receiving a selection of a resale store from among a plurality of stores;
An acquisition step of acquiring transaction object information which is information on a transaction object of each of the plurality of stores;
and estimating another resale store from among the plurality of stores based on a commonality with the resale store ;
The estimation step includes:
A classification step of classifying the plurality of stores into a plurality of clusters based on the transaction target information acquired by the acquisition step;
a determination step of determining whether the resale store among the plurality of stores is classified into the same cluster by the classification step;
and an extraction step of extracting, from among the plurality of stores, stores included in the cluster into which the resale store is classified by the determination step and other than the resale store as the other resale store.
23. An information processing method comprising: 1. A computer-implemented information processing method, comprising:
A reception process for receiving a selection of a fraudulent store from among a plurality of stores;
An acquisition step of acquiring transaction object information which is information on a transaction object of each of the plurality of stores;
and an estimation step of estimating another fraudulent store from among the plurality of stores based on a commonality with the fraudulent store,
The estimation step includes:
A classification step of classifying the plurality of stores into a plurality of clusters based on the transaction target information acquired by the acquisition step;
a determination step of determining whether the fraudulent store among the plurality of stores is classified into the same cluster by the classification step;
and extracting, as the other fraudulent stores, stores other than the fraudulent store that are included in the cluster into which the fraudulent store is classified by the determination step from among the plurality of stores.
23. An information processing method comprising: A procedure for accepting the selection of a resale store from multiple stores,
An acquisition step of acquiring transaction object information which is information on a transaction object of each of the plurality of stores;
and an estimation step of estimating another resale store from among the plurality of stores based on a commonality with the resale store ;
The estimation procedure comprises:
A classification step of classifying the plurality of stores into a plurality of clusters based on the transaction target information acquired by the acquisition step;
a determination step of determining whether the resale store among the plurality of stores is classified into the same cluster by the classification step;
and an extraction step of extracting, from among the plurality of stores, stores included in the cluster into which the resale store is classified by the determination step, other than the resale store, as the other resale store.
23. An information processing program comprising: A reception procedure for accepting the selection of the fraudulent store from among multiple stores;
An acquisition step of acquiring transaction object information which is information on a transaction object of each of the plurality of stores;
and an estimation step of estimating another fraudulent store from among the plurality of stores based on a commonality with the fraudulent store.
The estimation procedure comprises:
A classification step of classifying the plurality of stores into a plurality of clusters based on the transaction target information acquired by the acquisition step;
a determination step of determining whether the fraudulent store among the plurality of stores is classified into the same cluster by the classification step;
and an extraction step of extracting, as the other fraudulent stores, stores other than the fraudulent store that are included in the cluster into which the fraudulent store is classified by the determination step among the plurality of stores.
23. An information processing program comprising:

Images