JP7419583B1 - Information processing device, information processing method, and information processing program - Google Patents

Abstract

The present invention provides an information processing device, an information processing method, and an information processing program that can easily extract a specific store from a plurality of stores. An information processing device according to the present application includes an acquisition section, a classification section, a determination section, and an extraction section. The acquisition unit acquires transaction object information that is information about transaction objects of each of the plurality of stores. The classification unit classifies the plurality of stores into the plurality of clusters based on the transaction object information acquired by the acquisition unit. The determination unit determines whether a specific store among the plurality of stores has been classified into the same cluster by the classification unit. If the determining unit determines that the specific stores are classified into the same cluster, the extracting unit selects stores other than the specific store that are included in the cluster into which the specific store was classified by the classification unit. Extract as a common store that is a store common to the store. [Selection diagram] Figure 3

Description

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

2. Description of the Related Art Conventionally, transactions of products using electronic commerce (EC) sites have generally been carried out. In addition to each company's own site, EC sites include shopping mall-type EC sites (hereinafter sometimes referred to as EC malls) where multiple stores are open. In such an EC mall, each store puts up transaction objects such as products and services, and sells the put up transaction objects to users.

JP2019-106167A

However, since the multiple stores opening in an EC mall include various stores, when an EC mall operator tries to extract a specific store from among the multiple stores opening in an EC mall, the EC mall The more stores there are in a mall, the more time it takes to extract them.

The present application has been made in view 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 specific store from a plurality of stores. do.

The information processing device according to the present application includes an acquisition section, a classification section, a determination section, and an extraction section. The acquisition unit acquires transaction object information that is information about transaction objects of each of the plurality of stores. The classification unit classifies the plurality of stores into the plurality of clusters based on the transaction object information acquired by the acquisition unit. The determination unit determines whether a specific store among the plurality of stores has been classified into the same cluster by the classification unit. When the determination unit determines that the specific stores are classified into the same cluster, the extraction unit selects stores other than the specific stores that are included in the cluster into which the classification unit has classified the specific stores. Extract as a common store that is a store that is common to the store.

According to one aspect of the embodiment, it is possible to easily extract a specific store from among a plurality of 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 the 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 the user information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of a store information table stored in the store information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of a determination method by the determination unit of the information processing apparatus according to the embodiment. FIG. 7 is a flowchart illustrating an example of information processing by the processing unit of the information processing apparatus according to the embodiment. FIG. 8 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device according to the embodiment.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Below, an information processing apparatus, an information processing method, and a form for implementing an information processing program (hereinafter referred to as an "embodiment") according to the present application will be described in detail with reference to the drawings. Note that the information processing apparatus, information processing method, and information processing program according to the present application are not limited to this embodiment. Moreover, each embodiment can be combined as appropriate within the range that does not conflict with the processing contents. Further, in each of the embodiments below, the same parts are given the same reference numerals, and redundant explanations will be omitted.

[1. An example of information processing]
First, an example of information processing according to the embodiment will be described using FIG. 1. FIG. 1 is a diagram illustrating an example of information processing according to an embodiment, which is executed by an information processing device 1. As shown in FIG.

The information processing device 1 provides information on the transaction objects of each store opened in the EC mall, and mediates or supports the buying and selling of the transaction objects between the store and the user U. The information processing device 1 performs, for example, a function of searching for transaction objects exhibited in an EC mall, a function of searching for stores displayed in an EC mall, and a transaction settlement for transaction objects exhibited in an EC mall. It has functions etc.

The user U of the EC mall operates 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 searching for the search query that is a transaction object exhibited in the EC mall. The information processing device 1 can transmit search results corresponding to the information processing device 1 to the terminal device 2. Thereby, the user U can display search results on the terminal device 2 according to the search query transmitted from the information processing device 1 .

By setting the transaction object name as the search keyword included in the search query, the user U can cause the terminal device 2 to display content that includes one or more transaction object information having the transaction object name indicated by the search keyword. Furthermore, by using the store name as the search keyword included in the search query, the user U can cause the terminal device 2 to display content that includes one or more pieces of transaction target information sold at the store with the store name indicated by the search keyword. I can do it.

As shown in FIG. 1, the information processing device 1 receives 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 opened in an EC mall, and sells transaction objects such as products and services.

The particular store is, for example, a resale store or a fraud store. 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, it is a store that deceives the user U by selling a transaction object or not shipping a transaction object purchased by the user U.

The selection of a specific store is performed, for example, by the EC mall operator O (including vendors entrusted by the operator O). For example, an operator O of an EC mall operates the operator device 3 to select two or more specific stores from a plurality of stores. The selection information shown is transmitted from the operator device 3 to the information processing device 1. The information processing device 1 receives the selection information transmitted from the operator device 3 to accept the above-mentioned selection of a specific store.

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

Subsequently, the information processing device 1 estimates another specific store from among the plurality of stores based on the 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 results, stores that are included in the same cluster as a specific store among stores other than the specific store are classified into other specific stores. Estimated as.

Here, the process of step S2 will be specifically explained. First, the information processing device 1 acquires transaction object information, which is information about transaction objects of each of a plurality of stores (step S2-1).

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

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

The detailed information of the transaction object includes, for example, information indicating the sales price of the transaction object, information indicating the contents of the transaction object, information indicating the shipping fee of the transaction object, and the like. When the transaction object is food, the contents of the transaction object include, for example, the content amount of the transaction object, the transaction object raw materials, the transaction object allergy-related ingredients, the transaction object expiration date, the transaction object nutritional components, etc. Further, when 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 precautions.

The category type number information is information indicating the number of types of transaction target categories sold in the store. Categories are classified, for example, in a tree-like hierarchy. The number of types of categories is, for example, the number of types of categories in the store at the lowest level in the tree-like hierarchy, but may also be the number of types of categories at a level higher than the category at the lowest level.

For example, the major category ``shoes'' includes the intermediate category ``sneakers,'' and the intermediate category ``sneakers'' includes the minor categories ``ladies' sneakers'' and ``men's sneakers.'' , the category ``Ladies' slip-ons,'' the category ``Children's sneakers,'' and so on. In this case, the lowest category is a subcategory.

The transaction object number information is information indicating the number of types of transaction objects sold at the store. The type of transaction object is specified, for example, by the identification code of the transaction object or the model number of the transaction object, but may also be specified by the name of the transaction object.

The information on the number of transaction objects with codes is information indicating 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, a manufacturer code, a product code, a check digit, and the like.

Sales information includes, for example, information indicating the sales amount (order amount) of the transaction object at the store, information indicating the sales number (order number) of the transaction object at the store, information indicating the number of days elapsed since the store opened, and information indicating the transaction object at the store. Contains information indicating the average unshipped period.

The sales amount is, for example, the sales amount (order amount) per unit time (for example, daily, weekly, or monthly) at the store. Further, the sales amount may be the sales amount per unit time for each transaction object in the store or the sales amount (order amount) per unit time for each category. Further, the sales amount is the gross merchandise value (GMV) at the store, but may be the amount after deducting the commission paid by the store to the operator of the EC mall.

The number of sales is the number of sales (number of orders) per unit time (for example, daily, weekly, or monthly) at the store. Further, the number of sales may be the number of sales per unit time for each transaction object in the store or the number of sales (number of orders) per unit time for each category.

The information indicating the number of days that have passed since the store opened in the EC mall includes information that indicates the number of days that have passed since the store started opening at the EC mall. The information indicating the average unshipped period of the transaction object at the store includes information indicating the average value of the unshipped period from the time of order to the start of shipping of the transaction object whose order is accepted at the store.

The cancellation information is information indicating the cancellation rate of transaction objects per unit time (for example, daily, weekly, or monthly) in the store. The cancellation rate of transaction objects is, for example, a value obtained by dividing the number of canceled transaction objects by the number of sold (ordered) transaction objects. Cancellation of a transaction object includes cancellation before the transaction object is shipped, as well as cancellation after the transaction object has been shipped (for example, cancellation due to returned goods).

The mall purchase information includes information indicating the number of purchases of the transaction object at the EC mall by the user U who purchased the transaction object at the store, and information indicating the number of times the user U who purchased the transaction object at the store subsequently purchased the transaction object at the EC mall. Contains information indicating. Below, each of these purchase counts may be referred to as the mall purchase count.

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

For example, the information processing device 1 extracts a plurality of pieces of information as feature information from among the transaction target information, and classifies the plurality of stores into a plurality of clusters based on the plurality of extracted feature information.

The characteristic information includes, for example, information indicating the number of sales at the store (for example, weekly sales number), information indicating the number of types of transaction objects at the store, information indicating the number of types of transaction objects with identification codes at the store, information indicating the number of types of transaction objects at the store, includes two or more of the information indicating the number of types of categories to be traded in.

In addition to or in place of some or all of the above-mentioned information, the characteristic information includes information indicating the cancellation rate of the transaction object in the store, information indicating the number of mall purchases described above, and user evaluation regarding the transaction object in the store. information, information indicating the name of the transaction object in the store, detailed information of the transaction object in the store, and image information of the transaction object in the store.

In step S2-2, the information processing device 1 uses UMAP (Uniform Manifold Approximation and Projection) to reduce the dimensions of the plurality of feature information of each of the plurality of stores, and projects the plurality of stores onto a two-dimensional space.

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

The information processing device 1 classifies a plurality of stores projected onto a two-dimensional space into a plurality of clusters. For example, the information processing device 1 classifies multiple stores into multiple clusters using the k-means method. Further, the information processing device 1 can classify a plurality of stores into a plurality of clusters using, for example, spectral clustering, Gaussian mixture models (GMM), or a neural network instead of the k-means method. You can also use other clustering techniques to classify stores into clusters.

Subsequently, the information processing device 1 determines whether two or more specific stores received in step S1 among the plurality of stores classified into a plurality of clusters in step S2-2 are classified into the same cluster ( Step S2-3).

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

Subsequently, in step S2-3, if it is determined that two or more specific stores selected in step S1 are classified into the same cluster, the information processing device 1 determines whether the specific store is included in the classified cluster. A store other than the two or more specific stores selected in step S1 is extracted as a common store, which is a store that has characteristics in common with the two or more specific stores selected in step S1 (step S2 -4). Note that the "features" are the features of the store indicated by the above-mentioned transaction object information and the like.

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, and for example, the type of the two or more specific stores selected in step S1 is a resale store. If so, it 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 receives the selection of two or more specific stores for each of the plurality of types of specific stores in step S1, it extracts common stores for each specific store type. 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 mutually different common stores.

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

Further, if it is determined that the two or more fraudulent stores selected in step S1 are classified into the same cluster, the information processing device 1 determines whether the two or more fraudulent stores selected in step S1 are included in the same cluster. Stores remaining other than the two or more fraudulent stores selected in step S1 are estimated as other fraudulent stores.

The information processing device 1 transmits the extracted information, which is the information on the other specific store estimated in step S2, to the operator device 3, thereby transmitting the information on the other specific store estimated in step S2 to the operator O. Notify (step S3).

In this way, the information processing device 1 receives the selection of a specific store from among a plurality of stores, and estimates another specific store from among the plurality of stores based on the commonality with the specific store. Thereby, the information processing device 1 can easily extract a specific store (for example, a resale store or a fraudulent store) from a plurality of stores opening in the EC mall.

Further, the information processing device 1 classifies the plurality of stores into a plurality of clusters based on transaction object information that is information on the transaction object of each of the plurality of stores, and the information processing device 1 classifies the plurality of stores into a plurality of clusters, and a specific store among the plurality of stores is in the same cluster. Determine whether it has been classified. Then, when it is determined that the specific stores are classified into the same cluster, the information processing device 1 determines that a store other than the specific store that is included in the cluster into which the specific store has been classified is classified as the specific store. Extract as a common store, which is a store with common characteristics. Thereby, the information processing device 1 can easily extract a specific store from among a plurality of stores opening in the EC mall.

Hereinafter, the configuration of the information processing system including the information processing device 1, the terminal device 2, and the operator device 3 that performs such processing will be described in detail.

[2. Information processing system configuration]
FIG. 2 is a diagram illustrating an example of the configuration of the information processing system according to the 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 plurality of terminal devices 2 are used by mutually different users U. The terminal device 2 is, 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 such examples. User U is a user who uses services provided by information processing device 1 and 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.

Each of the information processing device 1, the terminal device 2, and the operator device 3 are connected to each other via a network N so that they can communicate with each other by wire or wirelessly. Note that the information processing system 100 shown in FIG. 2 may include a plurality of information processing apparatuses 1 and the like.

The network N includes, for example, 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). .

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

[3. Configuration of information processing device 1]
FIG. 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 section 10, a storage section 11, and a processing section 12.

[3.1. Communication department 10]
The communication unit 10 is realized by, for example, a NIC (Network Interface Card). The communication unit 10 is connected to the 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 RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 11 includes 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 information regarding the user U. FIG. 4 is a diagram illustrating 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."

"User ID" is an identifier for identifying user U, and is information attached to each user U. "Attribute information" is attribute information indicating the attribute of the user U associated with the "user ID." User U's attributes include, for example, demographic attributes, psychographic attributes, and the like. Demographic attributes are demographic attributes, and include multiple attribute items such as age, gender, occupation, place of residence, annual income, and family structure.

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

“Setting information” is setting information of user U associated with “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 regarding 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 showing 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 start date", and "transaction target information". .

“Store ID” is an identifier for identifying a store, and is information attached to each store. “Store name” is information indicating the name of the store corresponding to the “store ID”. "Store opening start date" is information indicating the date or time when the store corresponding to the "store ID" started opening in the EC mall.

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

[3.3. Processing unit 12]
The processing unit 12 is a controller, and various programs stored in the storage device inside the terminal device 2 use the RAM as a work area by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). This is achieved through execution.

The processing unit 12 may be partially or entirely realized 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 includes an acquisition unit 30, a reception unit 31, an estimation unit 32, an exclusion unit 33, and a provision unit 34, and has information processing functions and operations described below. to realize or carry out. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 3, and may be any other configuration as long as it performs information processing to be described later.

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

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

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

Further, the acquisition unit 30 acquires electronic commerce information in the EC mall provided by the providing unit 34 as part or all of the transaction target information from the providing unit 34, and stores part of the acquired transaction target information in store information storage. It can also be added to the store information table stored in the section 21.

Further, the acquisition unit 30 acquires various 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, part or all of at least one of the attribute information and setting information described above.

Further, the acquisition unit 30 acquires transaction object information, which is information about transaction objects of each of the plurality of stores, from the store information storage unit 21 . The transaction object information includes, for example, the above-mentioned object information, category type number information, object type number information, coded transaction object number information, sales information, cancellation information, mall purchase information, and the like. The acquisition unit 30 also acquires information indicating the store opening start date of each of the plurality of stores.

[3.3.2. Reception Department 31]
The reception unit 31 receives various requests and information from external information processing devices, terminal devices 2, etc. via the communication unit 10.

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

Further, the reception unit 31 receives an order query transmitted from the terminal device 2 via the communication unit 10. The order query includes information for specifying the transaction object for which the user U has decided to order (purchase) and the number thereof.

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 specifying a transaction object for which an order (purchase) has been decided by the user U and which is to be canceled.

Further, the reception unit 31 receives selections of two or more specific stores from a plurality of 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. Specific store types include, but are not limited to, resale stores, fraud stores, and the like.

[3.3.3. Estimation unit 32]
The estimation unit 32 estimates another specific store from among the plurality of stores in the EC mall, based on the commonality with the two or more specific stores whose selection was accepted by the reception unit 31.

The estimation unit 32 classifies the plurality of stores into a plurality of clusters, for example, based on the commonality between the stores specified from the transaction target information of each of the plurality of stores acquired by the acquisition unit 30.

For example, if the specific store accepted by the reception unit 31 is a resale store, the estimation unit 32 selects other resale stores from among the multiple stores based on the results of classifying the multiple stores into multiple clusters. presume.

In addition, for example, if a specific store accepted by the reception unit 31 is a fraudulent store, the estimation unit 32 determines whether other resellers are selected from among the multiple stores based on the results of classifying the multiple stores into multiple clusters. Estimate store.

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

[3.3.3.1. Classification section 40]
The classification unit 40 classifies the plurality of stores into a plurality of clusters based on the transaction target information of each of the plurality of stores acquired by the acquisition unit 30. The classification unit 40 classifies a plurality of stores into a plurality of 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, information indicating the number of sales in the store (for example, weekly sales number), information indicating the number of types of transaction objects in the store, and types of transaction objects with identification codes in the store. and information indicating the number of types of categories to be traded in the store.

If the transaction object is a transaction object with an identification code, the type of transaction object will differ depending on the identification code, and if the transaction object is not a transaction object with an identification code, it will differ depending on the model number of the transaction object. If it is not a transaction object with an identification code and there is no model number, it will differ depending on the product name or category of the transaction object.

Resale stores tend to have a small number of sales (for example, weekly sales) compared to the number of types of transaction objects and categories, and the number of transaction objects with identification codes is small compared to the number of types of transaction objects. There is a tendency that there are few. Additionally, fraudulent stores tend to differ from resale stores and other stores in terms of the number of store sales, the number of types of transaction objects in the store, the number of transaction objects with identification codes in the store, the number of categories of transaction objects in the store, etc. There may be cases where

Therefore, the classification unit 40 includes, for example, information indicating the number of sales in the store (for example, weekly sales), information indicating the number of types of transaction objects in the store, and information indicating the number of types of transaction objects with identification codes in the store. Two or more of the following information is used as the feature information: information indicating the number of categories of transactions in the store, and the like. Thereby, the classification unit 40 can appropriately classify a plurality of stores into a plurality of clusters in order to classify resale stores.

In addition, instead of or in addition to some or all of the above-mentioned information, the characteristic information includes information indicating the sales amount of the transaction object at the store (for example, weekly sales amount), the cancellation rate of the transaction object at the store (for example, , the number of cancellations per week), and information indicating the number of mall purchases.

For example, resale stores tend to have a low sales amount for transactions, a high cancellation rate for transactions, and a low number of mall purchases. Additionally, fraudulent stores may tend to be different from resale stores and other stores in terms of sales amount and number of mall purchases.

Therefore, the classification unit 40 further uses the sales amount of the transaction object (for example, the weekly sales amount), the cancellation rate of the transaction object (for example, the weekly cancellation rate), the number of mall purchases, etc. as characteristic information. Thereby, the classification unit 40 can appropriately classify a plurality of stores including resale stores and fraudulent stores into a plurality of clusters.

Further, the characteristic information may include, in place of or in addition to some or all of the above-mentioned information, information indicating user evaluation of the transaction object in the store, information indicating the name of the transaction object in the store, detailed information of the transaction object in the store, and image information to be traded at the store. Thereby, the classification unit 40 can appropriately classify a plurality of stores including resale stores and fraudulent stores into a plurality of clusters.

In addition, in place of or in addition to some or all of the above-mentioned information, the characteristic information may include one of the following, such as the number of days that have passed since the start date and time of opening a store in the EC mall, and the average unshipped period of transactions for which orders have been accepted. The above can be appropriately classified using a plurality of clusters.

The classification unit 40 uses UMAP to reduce the dimensions of the plurality of feature information of each of the plurality of stores, and projects the plurality of stores onto a two-dimensional space. Note that the method for reducing the dimensionality of feature quantities is not limited to UMAP, and the classification unit 40 may reduce the dimensionality of feature quantities using other dimensionality reduction methods such as t-SNE, PCA, PCA&UMAP, etc. good.

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

In the example described above, the classification unit 40 classifies the plurality of stores into the plurality of clusters by unsupervised clustering, but it is also possible to perform supervised clustering. For example, assume that the reception unit 31 accepts selections between a plurality of specific stores and a plurality of stores other than the specific store for each type of specific store.

In this case, the classification unit 40 uses information indicating the presence or absence of a plurality of specific stores as a label based on the transaction target information of the store whose selection is accepted by the reception unit 31, and labels various information included in the transaction target information. Generate training data as features for each specific store type.

Then, the classification unit 40 uses the generated learning data to create a learning model that takes various information included in the transaction target information as input and outputs a score indicating the possibility that the store is a specific store type. generated every time. This learning model is a model that uses transaction target information of a store to determine whether or not the store is a specific store.

The classification unit 40 uses the above-described learning model to classify whether a store is 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 characteristic information included in the store's transaction target information into a learning model, and determines that the store is a specific store when the score output from the learning model is equal to or higher than a threshold. , otherwise it is determined that the store is not a specific store.

Examples of the learning model include, but are not limited to, logistic regression, GBDT (Gradient Boosting Decision Tree), averaging perception, support vector machine, and neural network.

[3.3.3.2. Judgment unit 41]
The determination unit 41 determines whether two or more specific stores among the plurality of stores have been classified into the same cluster by the classification unit 40. For example, the determining unit 41 determines whether two or more specific stores whose selections are accepted by the accepting unit 31 are all classified into the same cluster.

Further, when the two or more specific stores whose selections are accepted by the reception unit 31 are of multiple types, the determining unit 41 determines whether all of the two or more specific stores of the same type are classified into the same cluster. is determined for each specific store type.

FIG. 6 is a diagram illustrating 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 a plurality of stores are projected by the classification unit 40, all four specific stores whose selection is accepted by the reception unit 31 are classified into the same cluster.

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

[3.3.3.3. Extraction part 42]
Based on the determination result of the determination unit 41, the extraction unit 42 selects a specific store type from among the plurality of stores by using a specific store other than the two or more specific stores whose selection was accepted by the reception unit 31 as a common store. Extract each time. The specific store extracted by the extraction unit 42 is the other specific store estimated by the estimation unit 32.

For example, when the determining unit 41 determines that two or more specific stores are classified into the same cluster, the extracting unit 42 selects a store that is included in the cluster into which the two or more specific stores were classified by the classifying unit 40. Stores other than the specific store are extracted as common stores, which are stores that have characteristics in common with the specific store.

For example, if the type of a specific store determined by the determination unit 41 is only a resale store, and the number of specific stores accepted by the reception unit 31 is four, all of these four specific stores are Assume that the stores are classified into clusters and the number of stores included in such clusters 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 determining unit 41 determines for each specific store type whether two or more specific stores of the same type are classified into the same cluster, the extracting unit 42 classifies the common store as a specific store. Extract by store type.

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

Further, when the type of the specific store determined by the determining unit 41 is a fraudulent store, the extracting unit 42 extracts stores other than the two or more fraudulent stores whose selections were accepted by the receiving unit 31 into other fraudulent stores (common stores). Extract as an example of a store).

[3.3.4. Exclusion part 33]
The exclusion unit 33 can exclude the common store extracted by the extraction unit 42 from being provided with a specific service. Specific services include, for example, recommendations and factoring.

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

In addition, factoring is applicable to stores that receive sales proceeds in advance at the EC mall, and the business operator of the store to which factoring is applied is notified by the EC mall operator You can receive sales proceeds in advance.

For example, the exclusion unit 33 can exclude the resale store extracted by the extraction unit 42 from either the recommendation target or the factoring target. Further, the exclusion unit 33 can also exclude the resale store extracted by the extraction unit 42 from the EC mall by causing the resale store to leave the EC mall.

As a result, for example, for resale stores whose resale (for example, no-stock resale) is prohibited in the EC mall's terms and conditions, the services available at the EC mall may be restricted or the store may be forced to leave the EC mall. You can

Furthermore, since resale stores have a higher closing rate than the average store, by excluding resale stores from the application of factoring, it is possible to avoid in advance the difficulty of collecting sales proceeds.

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

[3.3.5. Providing Department 34]
The providing unit 34 provides various information to each of the user U and the operator O by transmitting various information to each of the terminal device 2 and the operator device 3 via the communication unit 10.

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

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

Further, when the receiving unit 31 receives an order query transmitted from the terminal device 2, the providing unit 34 performs buying and selling processing of the transaction target specified by the order query. Further, when the receiving unit 31 receives a cancellation query transmitted from the terminal device 2, the providing unit 34 cancels the order to be traded specified by the cancellation query.

Further, the providing unit 34 transmits extracted information including information on other specific stores extracted as a common store by the extracting unit 42 to the operator device 3 via the communication unit 10, thereby transmitting the extracted information to the operator. Provide to O. The extraction information includes, for example, the store ID of each of the other specific stores extracted as a common store by the extraction unit 42.

Further, the providing unit 34 communicates extracted information including information on the specific store accepted by the receiving unit 31 in addition to information on other specific stores extracted as a common store by the extracting unit 42 to the operator device 3. The extracted information can also be provided to the operator O by transmitting it via the unit 10. In this case, the extracted information includes, for example, the store ID of each of the other specific stores extracted as a common store by the extraction unit 42 and the store ID of the specific store accepted by the reception unit 31.

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

Furthermore, the providing unit 34 can recommend stores to which recommendations are applied. The store recommendation is provided to the user U by, for example, transmitting recommendation information including information indicating a recommended store or a recommended transaction object to the user U's terminal device 2 via the communication unit 10.

The providing unit 34 does not recommend a specific store that has been excluded from the recommendation target by the excluding unit 33. Thereby, the processing unit 12 can exclude the specific store or the transaction target thereof that is excluded from the application target of the recommendation as the recommended store or the recommended transaction target.

Further, the providing unit 34 can perform pre-payment processing of the store's sales proceeds in the EC mall as a payment processing to the operator of the store to which factoring is applied. The providing unit 34 does not perform advance payment processing of sales proceeds to the operator of a specific store excluded from the application of factoring by the excluding unit 33. Thereby, the processing unit 12 can exclude from the factoring target a specific store that has been excluded from the factoring target.

[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 illustrating 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 a query from the terminal device 2 has been received (step S10). If the processing unit 12 determines that the query has been received (step S10: Yes), it performs processing according to the received query (step S11).

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

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

Subsequently, the processing unit 12 determines for each specific store type whether or not the specific stores determined to have been accepted in step S10 are classified into the same cluster (step S15). Then, the processing unit 12 extracts other stores included in the cluster into which the specific store is classified as common stores (for example, resale stores and fraudulent stores) for each type of specific store (step S16).

Subsequently, the processing unit 12 provides the operator O with the extracted information by transmitting the extracted information including the specific store information extracted in step S16 for each specific store type to the operator device 3. (Step S17).

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

If the processing unit 12 determines that the operation end timing has not come (step S18: No), the process proceeds to step S10, and if it determines that the operation end timing has come (step S18: Yes), the process proceeds to FIG. The indicated process ends.

[5. Transformation]
In the above example, the processing unit 12 classifies multiple stores in the same EC mall as classification targets, but may classify multiple stores in different EC malls as classification targets, or may classify multiple stores in different EC malls as classification targets, or Multiple stores on a site can be classified as classification targets.

Further, if the determining unit 41 determines that a plurality of specific stores are not classified into the same cluster by the classifying unit 40, the classifying unit 40 changes the initial value (for example, seed value) etc. The classification process, which is the process of classifying the data into multiple clusters, is repeated. The classification unit 40 repeats the classification process while changing the initial value, for example, until the determination unit 41 determines that a specific store is classified by the classification unit 40 into the same cluster.

Further, in the example described above, the determination unit 41 determines whether two or more specific stores among the plurality of stores are classified into the same cluster by the classification unit 40, but the present invention is not limited to such an example. For example, when the number of specific stores accepted by the accepting unit 31 is one, the determining unit 41 determines whether one specific store among the plurality of stores has been classified into the same cluster by the classifying unit 40. do. In this case, the extracting unit 42 extracts specific stores other than the one specific store whose selection was accepted by the accepting unit 31 as common stores from among the plurality of stores for each type of specific store.

In addition, the extraction unit 42 may also select, for example, among a plurality of other specific stores determined to be classified into the same cluster by the determination unit 41, the sales amount (for example, weekly sales amount) is 1 million or less and the sales Other specific stores whose number (for example, weekly sales volume) is 100 or less can also be extracted as common stores.

Furthermore, the classification unit 40 can also perform classification processing (clustering) n times. n is an integer of 2 or more. In this case, when the determination unit 41 determines that a plurality of specific stores are classified into the same cluster by the classification unit 40 m or more times, the extraction unit 42 selects a specific store whose selection has been accepted by the reception unit 31. It is also possible to extract specific stores other than the . m is an integer of 2 or more, and n and m have a relationship of, for example, n>m. Note that m is, for example, a value larger than 1/2 of n, but may be a value that does not depend on n.

In addition, the classification unit 40 calculates the degree of coincidence between the information indicating the contents of the transaction object in the specific store and the information indicating the contents of the transaction object in stores other than the specific store, for each type of transaction object. It is also possible to classify a plurality of stores into a plurality of clusters using a plurality of pieces of feature information that further includes information indicating the degree of matching as the feature information.

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

Furthermore, in the above example, the classification process for a plurality of stores including a plurality of types of specific stores is performed at once, but it is also possible to perform the classification process for a plurality of stores for each specific store type.

[6. Hardware configuration]
The information processing apparatus 1 according to the embodiments described above is realized, for example, by a computer 80 having a configuration as shown in FIG. FIG. 8 is a hardware configuration diagram showing an example of a computer 80 that implements the functions of the information processing device 1 according to the embodiment. The computer 80 includes a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, an 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 a program stored in the ROM 83 or HDD 84 and controls each part. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 is started, programs depending on the hardware of the computer 80, and the like.

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

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

Media interface 87 reads programs or data stored in recording medium 88 and provides them to CPU 81 via RAM 82. The CPU 81 loads this 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 disk), 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 80 functions as the information processing device 1 according to the embodiment, the CPU 81 of the computer 80 realizes the functions of the processing unit 12 by executing a program loaded onto the RAM 82. Furthermore, data in the storage unit 11 is stored in the HDD 84 . The CPU 81 of the computer 80 reads these programs from the recording medium 88 and executes them, but as another example, these programs may be acquired from another device via the network N.

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

Furthermore, each component of each device shown in the drawings is functionally conceptual, and does not necessarily need to be physically configured as shown in the drawings. In other words, the specific form of distributing and integrating each device is not limited to what is shown in the diagram, and all or part of the devices can be functionally or physically distributed or integrated in arbitrary units depending on various loads and usage conditions. Can be integrated and configured.

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 a plurality of server computers, and depending on the function, an external platform etc. may be implemented using an API (Application Programming Interface). The configuration can be changed flexibly, such as by calling it with or network computing.

Furthermore, the embodiments and modifications described above can be combined as appropriate within a range that does not conflict with the processing contents.

[8. effect〕
As described above, the information processing device 1 according to the embodiment includes the acquisition unit 30 that acquires transaction target information that is information on transaction targets of each of a plurality of stores, and the transaction target information acquired by the acquisition unit 30. a classification unit 40 that classifies a plurality of stores into a plurality of clusters based on the classification unit 40; a determination unit 41 that determines whether a specific store among the plurality of stores has been classified into the same cluster by the classification unit 40; and a determination unit When it is determined that the specific stores are classified into the same cluster by the classification unit 41, the classification unit 40 classifies stores other than the specific store that are included in the cluster into which the specific store is classified as common to the specific store. It also includes an extraction unit 42 that extracts a common store that is a store. Thereby, the information processing device 1 can easily extract a specific store from among a plurality of stores.

Further, the specific store is a resale store that resells the transaction object, and the extraction unit 42 extracts the resale store as a common store. Thereby, the information processing device 1 can easily extract a resale store from among a plurality of stores.

Further, the specific store is a fraudulent store that commits sales fraud on the transaction target, and the extraction unit 42 extracts the fraudulent store as a common store. Thereby, the information processing device 1 can easily extract a fraudulent store from among a plurality of stores.

Further, the specific store is one of a plurality of types of specific stores, and the determining unit 41 determines whether or not the specific store has been classified into the same cluster by the classification unit 40 for each type of specific store. The extraction unit 42 extracts common stores for each specific store type. Thereby, the information processing device 1 can easily extract a specific store from among a plurality of stores for each specific store type.

The information processing device 1 also includes a reception unit 31 that accepts selection of a specific store from among a plurality of stores. Thereby, the information processing device 1 can easily extract a specific store from among a plurality of stores.

In addition, transaction object information includes information indicating the number of transaction objects sold in the store, information indicating the number of types of transaction objects in the store, information indicating the number of types of transaction objects with identification codes in the store, and information indicating the number of transaction objects in the store with identification codes. Contains two or more of the information indicating the number of types of categories. Thereby, the information processing device 1 can accurately extract a specific store from among a plurality of stores.

Moreover, the transaction object information further includes information indicating the cancellation rate of the transaction object at the store. Thereby, the information processing device 1 can accurately extract a specific store from among a plurality of stores.

Further, the transaction object information includes one or more of the following: information indicating user evaluation regarding the transaction object, information indicating the name of the transaction object, detailed information about the transaction object, and image information of the transaction object. Thereby, the information processing device 1 can accurately extract a specific store from among a plurality of stores.

Further, the information processing device 1 includes an exclusion unit 33 that excludes the common store extracted by the extraction unit 42 from the application targets of recommendation or factoring. Thereby, the information processing device 1 can exclude a specific store from among the plurality of stores from being subject to recommendation or factoring.

Although the embodiments of the present application have been described above in detail based on the drawings, this is merely an example, and various modifications and improvements can be made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure section of the invention. It is possible to implement the invention in other forms.

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

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 Providing unit 40 Classification unit 41 Judgment Part 42 Extraction part 100 Information processing system N Network

Claims (11)

an acquisition unit that acquires transaction object information that is information on transaction objects of each of the plurality of stores;
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 a specific store among the plurality of stores has been classified into the same cluster by the classification unit;
If the determination unit determines that the specific stores are classified into the same cluster, stores other than the specific store that are included in the cluster into which the classification unit has classified the specific store are classified as An information processing device comprising: an extraction unit that extracts a common store that is a store that is common to a specific store. The particular store is
A resale store that resells the transaction object,
The extraction section is
The information processing device according to claim 1, wherein the resale store is extracted as the common store. The particular store is
It is a fraudulent store that carries out sales fraud for the transaction target,
The extraction section is
The information processing device according to claim 1, wherein the fraudulent store is extracted as the common store. The particular store is
is one of several types of specific stores;
The determination unit includes:
determining whether the specific store is classified into the same cluster by the classification unit for each type of the specific store;
The extraction section is
The information processing apparatus according to any one of claims 1 to 3, wherein the common store is extracted for each type of the specific store. The information processing apparatus according to any one of claims 1 to 3, further comprising a reception unit that accepts selection of the specific store from among the plurality of stores. The transaction target information is
Information indicating the number of sales of the transaction object at the store, information indicating the number of types of the transaction object at the store, information indicating the number of types of the transaction object with an identification code at the store, and information indicating the number of types of the transaction object at the store, and information indicating the number of types of the transaction object at the store. The information processing device according to any one of claims 1 to 3, characterized in that the information processing device includes two or more of the information indicating the number of types of categories. The transaction target information is
The information processing device according to any one of claims 1 to 3, further comprising information indicating a cancellation rate of the transaction object in the store. The transaction target information is
Claims 1 to 3, characterized in that the information includes one or more of the following: information indicating a user evaluation of the transaction object, information indicating the name of the transaction object, detailed information of the transaction object, and image information of the transaction object. The information processing device according to any one of the above. The information processing apparatus according to any one of claims 1 to 3, further comprising an exclusion unit that excludes the common store extracted by the extraction unit from an application target of recommendation or factoring. An information processing method performed by a computer, the method comprising:
an acquisition step of acquiring transaction target information that is information on transaction targets of each of the plurality of stores;
a classification step of classifying the plurality of stores into a plurality of clusters based on the transaction target information acquired in the acquisition step;
a determination step of determining whether a specific store among the plurality of stores has been classified into the same cluster by the classification step;
If it is determined in the determination step that the specific store is classified into the same cluster, a store other than the specific store that is included in the cluster into which the specific store was classified in the classification step is An information processing method comprising: an extraction step of extracting a common store that is a store that is common to a specific store. an acquisition procedure for acquiring transaction target information that is transaction target information for each of the plurality of stores;
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 procedure for determining whether a specific store among the plurality of stores is classified into the same cluster by the classification procedure;
If it is determined by the determination procedure that the specific store is classified into the same cluster, a store other than the specific store that is included in the cluster into which the specific store was classified by the classification procedure is An information processing program that causes a computer to execute an extraction procedure for extracting a common store that is a store that is common to a specific store.

Images