JP7584065B2 - Product recommendation system, product recommendation method, and program - Google Patents

Description

The present disclosure generally relates to a product recommendation system, a product recommendation method, and a program. More specifically, the present disclosure relates to a product recommendation system, a product recommendation method, and a program that recommends products to be sold in a target store.

Patent document 1 describes a product assortment recommendation device that determines a recommended product assortment in order to increase sales through appropriate product inventory management in a business model in which a headquarters manages many stores.

The product assortment recommendation device described in Patent Document 1 calculates first composition information, which is sales amount composition information for products that have a sales record at a target store, based on the sales record of the target store during a predetermined past period. The product assortment recommendation device also calculates second composition information, which is sales amount composition information for products that have not been sold at the target store during the above-mentioned period, based on a prediction model that predicts sales amount composition information for individual products. The product assortment recommendation device then selects a specified number of products in descending order of price indicated by the sales amount composition information from among the products for which the first composition information has been calculated and the products for which the second composition information has been calculated.

WO2018/056220A1

The present disclosure aims to provide a product recommendation system, a product recommendation method, and a program that can easily recommend products suitable for improving the business situation of a target store.

A product recommendation system according to an aspect of the present disclosure includes an acquisition unit and a recommendation unit. The acquisition unit acquires performance information regarding sales performance of products belonging to a product group, first handling information regarding whether the products are handled in target stores belonging to a first store group, and second handling information regarding whether the products are handled in stores belonging to a second store group having a store format different from the first store group. The recommendation unit determines a recommended product from the product group to be recommended for handling in the target store based on the performance information , first handling information , and second handling information acquired by the acquisition unit.
A product recommendation system according to an aspect of the present disclosure includes an acquisition unit and a recommendation unit. The acquisition unit acquires performance information regarding sales performance of products belonging to a product group, and handling information regarding whether the products are handled in target stores belonging to a store group. The recommendation unit determines a recommended product from the product group to be handled in the target store based on the performance information and the handling information acquired by the acquisition unit. The product recommendation system further includes a calculation unit that calculates a degree of commitment to the product in a product category to which the product belongs, based on the history information acquired by the acquisition unit. The degree of commitment is a ratio of the number of purchases of the product to the number of purchases of all products belonging to the product category by the customer. The recommendation unit determines the recommended product by referring to the degree of commitment calculated by the calculation unit.

A product recommendation method according to one aspect of the present disclosure is a product recommendation method executed by one or more processors. The product recommendation method includes an acquisition process and a recommendation process. The acquisition process is a process of acquiring performance information regarding sales performance of products belonging to a product group, first handling information regarding whether the products are handled in target stores belonging to a first store group, and second handling information regarding whether the products are handled in stores belonging to a second store group having a store format different from the first store group . The recommendation process is a process of determining a recommended product from the product group to be handled in the target store based on the performance information , the first handling information , and the second handling information acquired in the acquisition process.
A product recommendation method according to an aspect of the present disclosure is a product recommendation method executed by one or more processors. The product recommendation method includes an acquisition process and a recommendation process. The acquisition process is a process of acquiring performance information on sales performance of a product belonging to a product group, and handling information on whether the product is handled in a target store belonging to a store group. The recommendation process is a process of determining a recommended product from the product group to be handled in the target store based on the performance information and handling information acquired in the acquisition process. The acquisition process further acquires history information on a customer's purchase history for the products belonging to the product group. The method further includes a calculation process of calculating a degree of commitment to the product in the product category to which the product belongs, based on the history information acquired in the acquisition process. The degree of commitment is a ratio of the number of purchases of the product to the number of purchases of all products belonging to the product category by the customer. The recommendation process determines the recommended product by referring to the degree of commitment calculated in the calculation process.

A program relating to one aspect of the present disclosure causes one or more processors to execute the above-mentioned product recommendation method.

FIG. 1 is a schematic diagram showing a configuration of a product recommendation system according to an embodiment of the present disclosure. FIG. 2 is a schematic diagram of a target store in which the above-mentioned product recommendation system is adopted. FIG. 3 is a block diagram of the above-mentioned product recommendation system. FIG. 4 is a conceptual diagram showing a mode of determining a recommended product by the product recommendation system. FIG. 5 is an explanatory diagram of an example of a product category in which a specific customer exists in the above-mentioned product recommendation system. FIG. 6 is a flowchart showing the operation of the product recommendation system.

(1) Overview The product recommendation system 10 (see FIG. 1) according to this embodiment is a system that recommends products 3 (see FIG. 4) that should be handled in a target store 20 (see FIG. 1). The target store 20 here is a store that is a target of support by the product recommendation system 10, among a plurality of stores 2 (see FIG. 1) belonging to a store group 200 (see FIG. 4). As shown in FIG. 2, the target store 20 is a store that displays and sells a plurality of types of products 3 on a plurality of display shelves 201. In this embodiment, a case will be described as an example in which the product recommendation system 10 is introduced in a store 2 of a retail store such as a convenience store, a supermarket, a department store, a drug store, a clothing store, a home appliance retailer, or a home improvement center.

In addition to the target store 20, the store group 200 also includes stores 2 similar to the target store 20. Here, a store 2 similar to the target store 20 is a store that satisfies a specified similarity condition between the target store 20 and the store. For example, when there are multiple stores 2 that are part of a chain such as a corporate chain (regular chain) or a franchise chain, these multiple stores 2 are deemed to mutually satisfy similarity conditions. The similarity conditions may include conditions related to the country, region, business hours, customer demographics, etc.

The product recommendation system 10 according to this embodiment is a system that aims to improve the business situation of the target store 20 by increasing the sales of the target store 20. More specifically, the product recommendation system 10 is a system that aims to improve the sales of the target store 20 by increasing the average customer spending, the average LTV (Life Time Value), or profits (including gross profit and operating profit, etc.) in the target store 20.

In this disclosure, "LTV (Life Time Value)" refers to the price paid by a customer who purchases a product 3 or receives a service as compensation for the product 3 or service over a specified period (Life Time). As an example, if the specified period is one day (24 hours), the amount a customer spends at the target store in one day becomes the customer's LTV. Therefore, in a case where a customer shops at a target store N times (N is 2 or more) in one day, the total amount spent by the customer in N shopping trips becomes the customer's LTV, not the amount spent in one shopping trip. Thus, although LTV appears similar to the customer unit price at first glance, it differs from the customer unit price in that it represents the total amount spent in a specified period.

In this disclosure, "profit" refers to all profits related to sales at the target store 20, including, for example, gross profit (gross sales profit), operating profit, management profit, net income before taxes, and net income after taxes.

The product recommendation system 10 proposes products 3 to be sold at the target store 20, i.e., recommended products 31 (see FIG. 4), as a means for improving the sales of the target store 20 as described above. By selling such proposed recommended products 31, the target store 20 can improve its sales.

As shown in FIG. 3, the product recommendation system 10 includes an acquisition unit 121 and a recommendation unit 122.

The acquisition unit 121 acquires performance information regarding sales performance of the product 3 belonging to the product group 30 and handling information regarding whether the product 3 is handled in the target store 20 belonging to the store group 200. In other words, the acquisition unit 121 acquires performance information regarding sales performance and handling information regarding whether the product 3 is handled for each of the multiple products 3 belonging to the product group 30.

Here, the product group 30 may include products 3 already handled by the target store 20, as well as products 3 handled by stores 2 belonging to the store group 200 other than the target store 20. The product group 30 may also include products 3 handled by other stores 6 (see FIG. 4) belonging to the other store group 600 (see FIG. 4). The "other store group" in this disclosure has a store format different from that of the store group 200. In this embodiment, the other store group 600 is in a different industry from that of the store group 200. The industry of the other store group 600 may include, for example, an online retailer that sells products 3 to customers via a network such as the Internet. As an example, if the store group 200 is a collection of convenience stores, the other store group 600 is a collection of supermarkets (other stores 6), or a collection of drugstores (other stores 6). The multiple other stores 6 belonging to the other store group 600 are stores that satisfy a predetermined similarity condition with each other, similar to the multiple stores 2 belonging to the store group 200.

The recommendation unit 122 determines a recommended product 31 to be recommended for handling at the target store 20 from the product group 30 based on the performance information and handling information acquired by the acquisition unit 121. For example, the recommendation unit 122 extracts one or more products 3 that are not currently handled at the target store 20 from among the multiple products 3 belonging to the product group 30, and determines a recommended product 31 from the one or more products 3 by referring to the individual sales performance of the one or more products 3.

As described above, the product recommendation system 10 of this embodiment is capable of determining, as a recommended product 31, a product 3 that is not handled by the target store 20 and that takes into account sales performance at stores other than the target store 20. Therefore, this embodiment has the advantage of easily recommending a product 3 that has a good sales performance at stores other than the target store 20, that is, a product 3 (recommended product 31) that is expected to be suitable for improving the business situation of the target store 20.

Incidentally, the product recommendation system 10 is particularly useful in cases where the number of stores 2 and other stores 6 that can serve as references for the target store 20 can be large, such as 100 or more, 1,000 or more, or 10,000 or more, such as in the case of convenience stores.

That is, while many stores 2 usually satisfy certain similarity conditions, they operate under different conditions. The same is true for many other stores 6. For this reason, to reflect the huge amount of information across these many stores 2 and other stores 6 in a target store 20 requires calculations that far exceed the processing power of a human, and is simply not feasible for a human to accomplish. Furthermore, information relating to the operation and management of these many stores 2 and other stores 6 changes from time to time (e.g., seasonally), and updating recommended products 31 taking into account the latest information from the many stores 2 and other stores 6 is simply not feasible for a human to accomplish.

In contrast, the product recommendation system 10 according to the present embodiment can process even the large amounts of information that are so large and fluctuating as described above, for example, by using a general information processing device. In this way, the product recommendation system 10 according to the present embodiment is particularly useful in business formats that refer to a large number of stores 2 and other stores 6.

(2) Details The product recommendation system 10 according to this embodiment will be described in detail below. In this embodiment, a convenience store will be described as an example of the store 2 in which the product recommendation system 10 is introduced. That is, the "clerk" is a convenience store clerk (including part-timers and part-timers), and the "customer" is a customer of the convenience store. In this embodiment, it is assumed that the number of stores 2 is 10,000 or more. In the following, a case will be described in which one of the multiple (many) stores 2 is the target store 20, but in reality, each of the multiple stores 2 can be the target store 20. In other words, the product recommendation system 10 can support each of the multiple stores 2, but in the following, for simplicity of explanation, a case will be described in which there is one target store 20.

The product recommendation system 10 is composed of a server device 1. In this embodiment, the product recommendation system 10 is connected to a POS (Point Of Sales) system 21 and a store terminal 22 installed in each of a plurality of stores 2 (including the target store 20) via a network NT1 such as the Internet. Also, in this embodiment, the product recommendation system 10 is connected to a headquarters terminal 51 installed in a chain headquarters 5 that operates a plurality of stores 2 via the network NT1.

Here, the product recommendation system 10 is configured to be able to communicate with each of the POS system 21, the store terminal 22, and the headquarters terminal 51. In this disclosure, "able to communicate" means that signals can be sent and received directly or indirectly via the network NT1 or a repeater, etc., by an appropriate communication method such as wired communication or wireless communication. In this embodiment, the product recommendation system 10 is capable of bidirectional communication with each of the POS system 21, the store terminal 22, and the headquarters terminal 51. Furthermore, in this embodiment, the POS system 21, the store terminal 22, and the headquarters terminal 51 are also configured to be able to communicate with each other.

As described above, each store 2 (including the target store 20) is equipped with one or more POS systems 21 and store terminals 22. A single store 2 may have multiple POS systems 21 and multiple store terminals 22. In FIG. 1, each store 2 is depicted as if it were connected to the network NT1, but in reality, devices such as the POS system 21 and store terminals 22 installed in each store 2 are connected to the network NT1 via a gateway or the like.

Each of the POS system 21 and the store terminal 22 is primarily composed of a computer system having one or more processors and memory. Therefore, the one or more processors execute a program recorded in the memory to function as the POS system 21 and the store terminal 22. The program may be pre-recorded in the memory, may be provided via a telecommunications line such as the Internet, or may be provided recorded on a non-transitory recording medium such as a memory card.

In this embodiment, the POS system 21 is a so-called "ID-POS" capable of handling ID-POS data. The "ID-POS data" referred to here is data in which a "customer ID" is added as customer identification information (ID: identification) to POS data. This type of POS system 21 (ID-POS) obtains customer identification information (customer ID) by authenticating the customer when the customer makes a purchase. Customer authentication may be realized, for example, by various cards such as a membership card, a point card, or a credit card, or may be realized by communication with the customer's mobile information terminal or biometric authentication (including face authentication). The POS system 21 is not limited to ID-POS, and may be a simple POS that does not handle ID-POS data.

The store terminal 22 is an information terminal owned by a clerk or owner of the store 2. The store terminal 22 has a touch panel display as a user interface, and accepts user operations and presents (displays) information to the user.

With such a POS system 21 and store terminal 22, it is possible to transmit at least the purchase history of the product 3 in the store 2 as data to the server device 1 (product recommendation system 10) via the network NT1. In particular, in this embodiment, since the POS system 21 is capable of handling ID-POS data, for example, each time a transaction is made, information on the purchased product 3 can be output as a purchase history in association with the customer's identification information (customer ID).

Furthermore, each store 2 may have devices connected to the network NT1 in addition to the POS system 21 and the store terminal 22. As an example, a device mainly composed of a computer system such as a store computer or a mobile terminal (including a smartphone, a wearable terminal, etc.) carried by each store clerk may be provided in each store 2 and connected to the network NT1.

As described above, the headquarters terminal 51 is installed in the chain headquarters 5 which operates multiple stores 2. The headquarters terminal 51 is mainly composed of a computer system having one or more processors and memory. Therefore, the one or more processors execute a program recorded in the memory to function as the headquarters terminal 51. The program may be pre-recorded in the memory, may be provided via a telecommunications line such as the Internet, or may be recorded on a non-temporary recording medium such as a memory card and provided.

The headquarters terminal 51 has, for example, a touch panel display as a user interface, and accepts user operations and presents (displays) information to the user. Users of the headquarters terminal 51 are primarily operators of the chain headquarters 5.

As shown in FIG. 3, the product recommendation system 10 includes a communication unit 11 and a processing unit 12. The product recommendation system 10 is installed, for example, in a service company that provides the product recommendation system 10, or in an operating company of the store 2. It is preferable that the product recommendation system 10 uses a Paas (Platform as a Service) environment, which is a public cloud environment without management of the OS, runtime, and middleware.

The communication unit 11 is a communication interface. In particular, the communication unit 11 is a communication interface that can be connected to the network NT1, and has the function of communicating through the network NT1. This allows the product recommendation system 10 to communicate with each of the POS system 21, the store terminal 22, and the headquarters terminal 51 through the network NT1. The communication protocol of the communication unit 11 can be selected from various well-known wired and wireless communication standards.

The processing unit 12 is configured to perform overall control of the product recommendation system 10. The processing unit 12 may be realized, for example, by a computer system including one or more processors (microprocessors) and one or more memories. In other words, the one or more processors execute one or more programs (applications) stored in one or more memories to function as the processing unit 12. Here, the programs are pre-recorded in the memory of the processing unit 12, but they may also be provided via a telecommunications line such as the Internet, or recorded on a non-temporary recording medium such as a memory card.

As shown in Fig. 3, the processing unit 12 includes an acquisition unit 121, a recommendation unit 122, and a calculation unit 123. In Fig. 3, the acquisition unit 121, the recommendation unit 122, and the calculation unit 123 do not represent physical configurations, but represent functions realized by the processing unit 12.

The acquisition unit 121 acquires performance information and handling information. Specifically, the acquisition unit 121 acquires performance information via the network NT1, for example, from a server device of a service provider that provides purchasing data including the purchase history of the product 3, or from storage on the cloud (cloud computing). The acquisition unit 121 also communicates via the network NT1 with at least one of the POS system 21, store terminal 22, and headquarters terminal 51 of the target store 20, for example, to acquire handling information.

In this embodiment, the acquisition unit 121 acquires performance information by performing appropriate statistical processing on the purchase data. Also, in this embodiment, the acquisition unit 121 acquires performance information based on purchase data collected in a server device of a service provider or in cloud storage or the like over a predetermined period (e.g., several years).

Here, as an example, the purchase data is collected in the service provider's server device or cloud storage, etc., by the user using an application provided to the user (customer) by the service provider. For example, assume that the above application is installed on an information terminal such as a smartphone owned by the customer. In this case, the customer takes an image of the receipt handed to them when they purchase product 3 at store 2 or another store 6 with a camera installed in the information terminal via the above application. The application then applies appropriate image processing to the image taken by the camera, and information such as the purchase history of product 3 written on the receipt is linked to customer information such as the customer's ID as purchase data. The purchase data acquired by the above application is then sent to the service provider's server device or cloud storage, etc.

The purchasing data may include, as purchase history, information such as the name of product 3, the product category of product 3, sales amount of product 3 (including, for example, price and quantity), purchase date of product 3 (for example, weekday or holiday), and time of day when product 3 was purchased. The purchasing data may also include, as purchase history, information such as the location (for example, prefecture and/or city/ward/town/village) of store 2 (or other store 6) where product 3 was purchased, and the store type (for example, convenience store or supermarket) of store 2 (or other store 6). The purchasing data may also include, as customer information, information such as the ID of the customer who purchased product 3, the customer's gender, the customer's age, and the customer's family composition.

In the present disclosure, a "product category" is a label for classifying products 3 by use, function, customer demographic, etc., and may be a relatively large classification (large category) such as food, clothing, medicine, beauty-related products, electrical appliances, or daily necessities. Furthermore, product categories may be medium categories that further classify large categories into multiple categories, and specific examples of medium categories include soft drinks, alcohol, bento boxes, prepared foods, sweets, snacks, and ice cream in the food category. Furthermore, product categories may be small categories that further classify medium categories into multiple categories, and specific examples of small categories include barley tea, green tea, black tea, coffee, lactic acid drinks, carbonated drinks, mineral water, and sports drinks in the soft drink category.

As described above, in this embodiment, the purchasing data is not limited to information from store 2 belonging to the store group 200, but also includes information from other stores 6 belonging to the other store group 600. In other words, the purchasing data includes a huge amount of data, i.e., big data, about the products 3 purchased by each of a large number of customers at one of the stores 2 (or other stores 6), regardless of whether it is store 2 or other stores 6. Note that the purchasing data is not limited to information obtained from receipts, and may include, for example, ID-POS data. In other words, the means for collecting purchasing data from the store group 200 and other store group 600 are not particularly limited.

The performance information is information relating to the sales performance of product 3 belonging to product group 30. The information relating to the sales performance of product 3 may include information relating to the sales performance of product 3 in target store 20, as well as information relating to the sales performance of product 3 in stores 2 other than target store 20. Furthermore, the information relating to the sales performance of product 3 may include information relating to the sales performance of product 3 in other stores 6 belonging to other store group 600. Product group 30 includes products 3 handled in target store 20, as well as products 3 handled in stores 2 other than target store 20 belonging to store group 200. Product group 30 also includes products 3 handled in other stores 6 belonging to other store group 600. In other words, in this embodiment, product group 30 includes products 3 handled by other store group 600, which has a store format different from that of store group 200.

Examples of the product 3 include food, clothing, medicine, beauty-related products, electrical appliances, and daily necessities. The product 3 is managed by item or SKU (Stock Keeping Unit). In this embodiment, SKU is used to manage the product 3. In this disclosure, "SKU (Stock Keeping Unit)" means the smallest management unit in product order management or inventory management. For example, even products with the same product name are counted as individual SKUs due to differences in size, color, package, or number of pieces, and are classified as SKUs in units smaller than items. In this disclosure, "item" means one product in a broad sense, and for example, products with the same product name are counted as one item. As an example, if there are three types of product named "ABC bread", 4 slices, 5 slices, and 6 slices, the number of items for "ABC bread" is "1" and the number of SKUs is "3".

The sales performance may include, for example, the sales amount and profit of the product 3. In addition, in this embodiment, the sales performance includes the ratio of the sales amount of the product 3 to the total sales amount of all the products 3 belonging to a specific product group among the product group 30, in other words, the product share. In other words, the performance information includes the sales share (product share) of the product 3 to the total sales of the specific product group among the product group 30. As an example, the specific product group is all the products 3 handled by the other store group 600. Also, as an example, the specific product group is all the products 3 belonging to any product category (e.g., food, etc.). The specific product group is not limited to a part of the product group 30, but may be the entire product group 30. In addition, in this embodiment, the sales performance includes the ranking of the sales share of the product 3 in the specific product group. In other words, the performance information includes the ranking of the share (product share) in the specific product group.

The handling information is information regarding whether or not the target store 20 handles the product 3. In other words, the handling information includes information regarding whether or not each product 3 belonging to the product group 30 is currently being handled in the target store 20. Note that the handling information may also include information regarding whether or not each product 3 belonging to the product group 30 has been handled in the target store 20 in the past.

In this embodiment, the acquisition unit 121 further acquires similarity information regarding the similarity of the products 3 belonging to the product group 30 with the products 3 handled in the target store 20. The "similarity" here means, for example, the overall similarity of the product 3 with respect to the genre, ingredients, taste, concept (premium product, etc.), target customer base, price range, etc. For example, when two products 3 that are sold by different manufacturers and have the same product category, namely "green tea," and the same target customer base or price range, the similarity between these two products 3 is high. For example, the similarity information may include information regarding whether each product 3 belonging to the product group 30 is similar to at least one product 3 among all the products 3 handled in the target store 20.

In addition, in this embodiment, the acquisition unit 121 further acquires history information regarding the customer's purchase history for the products 3 belonging to the product group 30. For example, the history information may include, for each product 3 belonging to the product group 30, the number of purchases of the product 3 or the purchase frequency for each customer over a predetermined period (e.g., several years).

In addition, in this embodiment, the acquisition unit 121 further acquires ordering information regarding the ordering of the product 3 belonging to the product group 30. For example, the ordering information may include information regarding whether or not it is possible to order the product 3 at the target store 20 for each product 3 belonging to the product group 30. Specifically, if the target store 20 is located in Kansai and the sales network for the product 3 is only located in Kanto, the ordering information for the product 3 is information indicating that it is impossible to order the product at the target store 20 or that the difficulty of ordering is relatively high. Also, for example, if the product 3 is an independently planned product (private brand) independently planned by the management parent company of the other store group 600, the ordering information for the product 3 is information indicating that it is impossible to order the product at the target store 20.

The calculation unit 123 calculates the repeat rate based on the history information acquired by the acquisition unit 121. The repeat rate represents the frequency with which the product 3 is purchased again by the same customer in the product category to which the product 3 belongs. For example, assume that the product category is "coffee" and the product 3 purchased by the customer is "coffee A". In this case, the repeat rate represents the proportion of times that this customer purchases "coffee A" again from multiple types of coffee included in the product category of "coffee". For example, if a customer purchases 100 bottles of coffee over a certain period (e.g., several years), of which 30 are "coffee A", the repeat rate is 30%. In other words, the repeat rate represents the strength of preference for a specific product 3 among multiple types of products 3 in the same product category, in other words, the customer's commitment to the product 3.

The recommendation unit 122 determines, from the product group 30, recommended products 31 to be recommended for handling at the target store 20, based on the information acquired by the acquisition unit 121 (mainly performance information and handling information in this case). Specifically, the recommendation unit 122 executes multiple types of filtering processes for the products 3 belonging to the product group 30, determining whether or not the products 3 match predetermined conditions while referring to the information acquired by the acquisition unit 121. As a result, the recommendation unit 122 determines, from the product group 30, one or more products 3 that match the multiple types of predetermined conditions most closely, or whose degree of match is greater than a threshold, as the recommended products 31.

The recommended products 31 determined by the recommendation unit 122 can be viewed by users, such as the owner of the target store 20, using the store terminal 22. The user who viewed the recommended products 31 can use the presented recommended products 31 to help improve the business situation, such as deciding whether or not to sell the recommended products 31 in the target store 20, or deciding to sell other products 3 based on the recommended products 31.

Below, we will explain in detail the multiple filter processes executed by the recommendation unit 122. In the following explanation, for convenience of explanation, the multiple filter processes are referred to as the "first filter process" to the "seventh filter process", respectively, but the order in which the filter processes are executed is not uniquely determined.

Here, when performing each filter process, the recommendation unit 122 refers to the selected category determined by the filter process executed immediately before. For example, if the recommendation unit 122 executes the first filter process, in the second filter process, the second filter process is executed on a set of products 3 included in the selected category determined by the first filter process. Therefore, in the following description of each filter process, if another filter process has been executed immediately before, "among the product group 30" should be read as "among the selected categories determined by the previous filter process of the product group 30." Also, in the following description of each filter process, if another filter process has been executed immediately before, "determine the selected category" should be read as "further limit the selected category."

In the first filter process, the recommendation unit 122 determines the selected category based on the performance information. In the first filter process, the selected category is determined to be a product category that can contribute to an increase in the sales of the target store 20, such as food, based on a management index that is an index related to the management of the target store 20. Hereinafter, the selected category determined based on the management index is also referred to as a specific category. The management index may include the sales amount of the product 3 and the number of products sold of the product 3 in a predetermined period (e.g., several years). The sales amount of the product 3 and the number of products sold of the product 3 may include the sales amount of the product 3 and the number of products sold of the product 3 in the target store 20, as well as the sales amount of the product 3 and the number of products sold of the product 3 in stores 2 other than the target store 20. In addition, the sales amount of the product 3 and the number of products sold of the product 3 may include the sales amount of the product 3 and the number of products sold of the product 3 in other stores 6 belonging to the other store group 600. As a specific example, the recommendation unit 122 determines, as the selected categories, one or more product categories in which the total sales amount of the products 3 is higher than a predetermined sales amount, from among a plurality of product categories (e.g., large categories) belonging to the product group 30. Here, the recommendation unit 122 may adopt medium or small categories instead of large categories as the plurality of product categories. In other words, by executing the first filter process, the recommendation unit 122 determines, as the recommended products 31, the products 3 that belong to the selected category (specific category) identified based on the management indicators of the target store 20 from among the product group 30.

In the second filter process, the recommendation unit 122 determines a selection category (specific category) based on the performance information. In the second filter process, the selection category is determined so that the product 3 purchased by the specific customer belongs to it. In the present disclosure, the "specific customer" is a so-called heavy user of a convenience store who uses both a convenience store (store 2 in the store group 200) and a supermarket (other store 6 in the other store group 600) and uses the convenience store relatively frequently. In other words, the "specific customer" is a customer who purchases the product 3 (including not only the product 3 that is actually purchased but also other products 3 in the product category to which the product 3 belongs) in both the store group 200 and the other store group 600, and who uses the store group 200 more frequently than a threshold value (second threshold value). Here, the "customer whose frequency is greater than the threshold value" is, for example, a customer of the store group 200 whose total purchase amount of the product 3 at any store 2 belonging to the store group 200 is greater than a predetermined amount. Additionally, a "customer whose frequency is greater than a threshold" is a customer of the store group 200 who has purchased the product 3 at the store 2 more than a predetermined number of times in a predetermined period (for example, one week).

Figure 5 shows an example of a product category in which specific customers exist. In the example shown in Figure 5, four product categories, "ice cream," "rice balls," "cup noodles," and "frozen foods," are listed as product categories in which specific customers exist. In each product category, a bar graph shows the proportion of customers who use only the store group 200, customers who use only the other store group 600, and customers who use both the store group 200 and the other store group 600 (specific customers). In Figure 5, the proportion of customers who use only the store group 200 in each product category is shown by a blank area A1, and the proportion of customers who use only the other store group 600 is shown by a dotted area A2. In Figure 5, the proportion of specific customers in each product category is shown by a hatched area A3. For example, when comparing the product categories "rice balls" and "frozen foods," the product category "rice balls" has a larger proportion of specific customers.

In particular, in this embodiment, the recommendation unit 122 determines, as the selected category (specific category), a product category in which the proportion of the specific customer is greater than a threshold value among one or more product categories to which the product 3 purchased by the specific customer belongs as described above. In other words, the selected category is determined to be a product category in which the proportion of the specific customer is greater than a threshold value (third threshold value). In the example shown in FIG. 5, it is assumed that, of the four product categories "ice cream," "rice balls," "instant noodles," and "frozen foods," the product category in which the proportion of the specific customer is greater than a threshold value (e.g., 15%) is the product category "ice cream." In this case, the recommendation unit 122 determines the product category "ice cream" as the selected category.

Here, since the specific customer is a customer who uses the store group 200 relatively frequently, it is considered that the specific customer is likely to notice changes in the product 3 handled at the target store 20. For this reason, when a product 3 that was only handled at the other store group 600 starts to be handled at the target store 20, the specific customer is likely to notice the newly started product 3 compared to other customers. Therefore, by determining the product 3 focused on the specific customer as the recommended product 31 by the second filter process, it is expected that the product 3 newly handled at the target store 20 (recommended product 31) will be more likely to contribute to increased sales.

In the third filter process, the recommendation unit 122 determines the selected category based on the handling information. In the third filter process, the recommendation unit 122 determines a set of products 3 that are not currently handled at the target store 20 from the product group 30 as the selected category. In other words, the recommendation unit 122 determines products that are not handled at the target store 20 (non-handled products) as the recommended products 31. In other words, the recommendation unit 122 excludes products that are handled at the target store from the recommended products 31. For example, if alcoholic beverages are not handled at the target store 20, alcoholic beverages may be included in the selected category. Also, for example, if "ballpoint pen A" is handled at the target store 20, ballpoint pens other than "ballpoint pen A" that belong to the product category "ballpoint pen" (such as "ballpoint pen B") may be included in the selected category.

In the fourth filter process, the recommendation unit 122 determines the selection category based on the performance information. In the fourth filter process, the recommendation unit 122 determines a set of products 3 with a relatively high product share (occupancy rate) among the product group 30 as the selection category. In other words, the recommendation unit 122 determines the recommended products 31 based on the occupancy rate. In particular, in this embodiment, it is preferable to perform the second filter process before performing the fourth filter process. In this case, according to the above definition of the replacement, in the fourth filter process, the recommendation unit 122 further limits the set of products 3 with a relatively high occupancy rate in the selection category to which the products 3 purchased by the specific customer belong among the product group 30 as the selection category. In other words, in this case, the fourth filter process focuses only on the set of products 3 purchased by the specific customer, and further limits the set of products 3 with a relatively high occupancy rate from this set of products 3 as the selection category.

In this embodiment, the recommendation unit 122 determines a set of products 3 whose occupancy rates are 1st to several tens (e.g., 30th) as the selected category. That is, in this embodiment, the recommendation unit 122 determines the recommended products 31 based on the ranking of occupancy rates. Note that the recommendation unit 122 may also determine a set of products 3 whose occupancy rates exceed a predetermined threshold as the selected category.

In the fourth filter process, the recommendation unit 122 determines the selected category by referring only to the occupancy rate, regardless of the product category. In other words, the product categories of the products 3 included in the selected category may be not only one, but also multiple. For example, it is assumed that the recommendation unit 122 determines the set of products 3 with occupancy rates from 1st to 3rd place as the selected category. It is also assumed that the product group 30 includes only the product category "ice cream" and the product category "coffee". It is further assumed that the occupancies of "ice cream A", "ice cream B", and "ice cream C" in the product category "ice cream" are 5%, 3%, and 1%, respectively, and that the occupancies of "coffee A" and "coffee B" in the product category "coffee" are 4% and 2%, respectively. In this case, the recommendation unit 122 determines the set of "ice cream A" with the occupancy rate first, "coffee A" with the occupancy rate second, and "ice cream B" with the occupancy rate third, as the selected category.

In the fifth filter process, the recommendation unit 122 determines the selection category based on the similarity information. That is, in the fifth filter process, the recommendation unit 122 determines the recommended products 31 by referring to the similarity information acquired by the acquisition unit 121. In this embodiment, the recommendation unit 122 determines a set of products 3 that are relatively low in similarity to the products 3 handled in the target store 20 as the selection category by referring to the similarity information. For example, assume that the product group 30 includes "Salmon Onigiri A", "Salmon Onigiri B", and "Kombu Onigiri A", and only "Salmon Onigiri A" is currently handled in the target store 20. In this case, since "Kombu Onigiri A" has a different taste from "Salmon Onigiri A", it is determined that the similarity to "Salmon Onigiri A" is relatively low, and is likely to be included in the selection category by the recommendation unit 122. On the other hand, even if "Salmon Onigiri B" has the same taste as "Salmon Onigiri A," if it is more expensive than "Salmon Onigiri A," it is considered to have a relatively low similarity to "Salmon Onigiri A" and may be included in the selection category by the recommendation unit 122.

In the fifth filter process, by excluding from the recommended products 31 products 3 having the same function as the product 3 currently being handled in the target store 20, cannibalization that may occur when a product 3 having the same function is handled in the target store 20 can be prevented. For example, if "high-quality bread A" is already being handled in the target store 20, and "high-quality bread B", which is different from "high-quality bread A", is set as the recommended product 31, there is a possibility that "high-quality bread A" and "high-quality bread B" will compete with each other in the target store 20. On the other hand, in this embodiment, since "high-quality bread B" is excluded from the recommended products 31 by the fifth filter process, it is possible to avoid the above-mentioned competition.

In the sixth filter process, the recommendation unit 122 determines the selected category based on the repeat rate. That is, in the sixth filter process, the recommendation unit 122 determines the recommended products 31 by referring to the repeat rate calculated by the calculation unit 123. In this embodiment, the recommendation unit 122 determines a set of products 3 from the product group 30 whose repeat rate is higher than a predetermined threshold as the selected category. In this embodiment, the repeat rate used in the sixth filter process is, as an example, the average repeat rate for one or more specific customers.

In the sixth filter process, the recommendation unit 122 determines the selected category by referring only to the repeat rate, regardless of the product category. In other words, the product category of the product 3 included in the selected category may be not only one, but also multiple. For example, it is assumed that the recommendation unit 122 determines the set of products 3 with repeat rates from 1st to 3rd as the selected category. It is also assumed that the product group 30 includes only the product category "beer" and the product category "bread". It is further assumed that the repeat rates of "beer A", "beer B", and "beer C" in the product category "beer" are 20%, 30%, and 10%, respectively, and that the repeat rates of "bread A" and "bread B" in the product category "bread" are 25% and 18%, respectively. In this case, the recommendation unit 122 determines the set of "beer B" with the first repeat rate, "bread A" with the second repeat rate, and "beer A" with the third repeat rate as the selected category.

In the seventh filter process, the recommendation unit 122 determines the selection category based on the order information. That is, in the seventh filter process, the recommendation unit 122 determines the recommended product 31 by referring to the order information acquired by the acquisition unit 121. In this embodiment, the recommendation unit 122 determines a set of products 3 that are relatively easy to order at the target store 20 from among the product group 30 as the selection category. For example, assume that the product group 30 includes "product A" that can be ordered nationwide and "product B" that can be ordered mainly in the Hokkaido area, and the target store 20 is located in Kansai. In this case, since "product A" is easy to order at the target store 20, it is considered to have a relatively low ordering difficulty, and it is highly likely that the recommendation unit 122 will include it in the selection category. On the other hand, since "product B" can be ordered only in an area other than Kansai, it is considered to have a relatively high ordering difficulty, and it is highly likely that the recommendation unit 122 will not include it in the selection category.

In this embodiment, the recommendation unit 122 determines one or more products 3 filtered by sequentially executing the first filter process to the seventh filter process as the recommended products 31. Here, the order in which the recommendation unit 122 executes the first filter process to the seventh filter process is not limited to the above order, and the recommended products 31 presented by the recommendation unit 122 may vary depending on the order in which they are executed. For example, when the fourth filter process is executed after the third filter process as in this embodiment, the recommendation unit 122 determines a set of products 3 with a occupancy rate of 1st to tens of products 3 among the products 3 not handled in the target store 20 as the selected category. On the other hand, when the fourth filter process is executed before the third filter process is executed, the recommendation unit 122 determines a set of products 3 with a occupancy rate of 1st to tens of products 3 as the selected category, regardless of whether the products are handled in the target store 20. The order in which the first filter process to the seventh filter process are executed may be appropriately determined, for example, by the administrator of the product recommendation system 10.

(3) Operation An example of the operation of the product recommendation system 10 of this embodiment will be described below with reference to FIG. 6. First, the acquisition unit 121 of the product recommendation system 10 acquires various information such as performance information and handling information through the network NT1 (S1). Next, the calculation unit 123 of the product recommendation system 10 calculates a repeat rate based on the history information acquired by the acquisition unit 121 (S2). Then, the recommendation unit 122 of the product recommendation system 10 sequentially executes the first filter process (S3), the second filter process (S4), the third filter process (S5), the fourth filter process (S6), the fifth filter process (S7), the sixth filter process (S8), and the seventh filter process (S9). In this way, the recommendation unit 122 determines one or more products 3 filtered by sequentially executing the first filter process to the seventh filter process as recommended products 31 (S10).

As described above, in the product recommendation system 10 of this embodiment, it is possible to determine, as a recommended product 31, a product 3 that is not handled by the target store 20 and that takes into consideration sales performance at stores other than the target store 20 (including other stores 6). Therefore, this embodiment has the advantage of easily recommending a product 3 that has a good sales performance at stores other than the target store 20, that is, a product 3 (recommended product 31) that is expected to be suitable for improving the business situation of the target store 20.

(4) Modifications The above-described embodiment is merely one of various embodiments of the present disclosure. The above-described embodiment can be modified in various ways depending on the design, etc., as long as the object of the present disclosure can be achieved. In addition, functions similar to those of the product recommendation system 10 according to the above-described embodiment may be embodied in a product recommendation method, a computer program, or a non-transitory recording medium having a computer program recorded thereon.

The product recommendation method according to one embodiment includes an acquisition process and a recommendation process. The acquisition process is a process for acquiring performance information regarding the sales performance of product 3 belonging to a product group 30, and handling information regarding whether product 3 is handled in a target store 20 belonging to a store group 200. The recommendation process is a process for determining a recommended product 31 from the product group 30 that is recommended to be handled in the target store 20, based on the performance information and handling information acquired in the acquisition process. Furthermore, a program according to one embodiment causes one or more processors to execute the above-mentioned product recommendation method.

Below, we list some variations of the above-mentioned embodiment. The variations described below can be applied in appropriate combinations.

The product recommendation system 10 in the present disclosure includes a computer system, for example, in a server device 1 or the like. The computer system is mainly composed of a processor and a memory as hardware. The processor executes a program recorded in the memory of the computer system to realize the function of the product recommendation system 10 in the present disclosure. The program may be pre-recorded in the memory of the computer system, provided through an electric communication line, or recorded and provided in a non-transitory recording medium such as a memory card, an optical disk, or a hard disk drive that can be read by the computer system. The processor of the computer system is composed of one or more electronic circuits including a semiconductor integrated circuit (IC) or a large-scale integrated circuit (LSI). The integrated circuits such as IC or LSI referred to here are called differently depending on the degree of integration, and include integrated circuits called system LSI, VLSI (Very Large Scale Integration), or ULSI (Ultra Large Scale Integration). Furthermore, a field-programmable gate array (FPGA) that is programmed after the manufacture of the LSI, or a logic device that can reconfigure the connection relationship inside the LSI or reconfigure the circuit partition inside the LSI, can also be adopted as a processor. The electronic circuits may be integrated in one chip or distributed among multiple chips. The chips may be integrated in one device or distributed among multiple devices. The computer system referred to here includes a microcontroller having one or more processors and one or more memories. Thus, the microcontroller is also composed of one or more electronic circuits including a semiconductor integrated circuit or a large-scale integrated circuit.

In addition, it is not essential for the product recommendation system 10 that multiple functions in the product recommendation system 10 are concentrated in one housing, and the components of the product recommendation system 10 may be distributed across multiple housings. Furthermore, at least some of the functions of the product recommendation system 10, for example, some of the functions of the server device 1, may be realized by the cloud (cloud computing) or the like.

Conversely, in the above-described embodiment, at least some of the functions of the product recommendation system 10 that are distributed across multiple devices may be consolidated within a single housing.

In addition, the use of the product recommendation system 10 is not limited to convenience stores, and the product recommendation system 10 may be introduced in a store 2 other than a convenience store. As an example, the product recommendation system 10 may be introduced in a food service facility such as a restaurant. In this case, the food or the like provided to the customer corresponds to the product 3.

Furthermore, product 3 is not limited to being a tangible product, but may also be an intangible product.

In addition, the user interface in the store terminal 22, etc., is not limited to a touch panel display, and may have an input device such as a keyboard, a pointing device, a mechanical switch, or a gesture sensor. Furthermore, the user interface may include a display device such as a projector that projects an image using projection mapping technology. The user interface may also have a voice input/output unit instead of or in addition to the touch panel display. In this case, the user interface can present various information to the store clerk, etc., by using voice output from the speaker. Furthermore, the user interface can perform voice recognition and semantic analysis processing on the voice signal output from the microphone, allowing the store clerk, etc. to operate by voice (voice input).

In addition, in the above-described embodiment, the product recommendation system 10 includes a calculation unit 123, but the calculation unit 123 is not essential. In other words, the product recommendation system 10 needs to include at least an acquisition unit 121 and a recommendation unit 122.

Furthermore, the sales form of the product 3 in the store 2 is not limited to a form in which multiple products 3 are displayed in the store, as in the above-mentioned embodiment. For example, the product 3 may be sold in a form in which a vending machine that stocks multiple products 3 is used to settle the payment for the product 3 selected by the customer and dispense the product 3. Furthermore, even if multiple products 3 are displayed in the store and sold, the sales form may be one in which the customer settles the payment without the assistance of a store clerk, for example, by using a self-checkout.

In the above embodiment, the recommendation unit 122 determines the recommended product 31 by executing all of the first filter process to the seventh filter process, but this is not limited to the above. For example, the recommendation unit 122 may determine the recommended product 31 by executing some of the first filter process to the seventh filter process. In other words, the recommendation unit 122 may determine, as the recommended product 31, one or more products 3 filtered from the product group 30 based on at least the performance information and the handling information.

In the above embodiment, the recommendation unit 122 may further execute an eighth filter process in addition to the first to seventh filter processes. In the eighth filter process, the recommendation unit 122 determines, based on the handling information, a set of products 3 from the product group 30, excluding products 3 that have been handled in the target store 20 in the past, as a selected category. In other words, the recommendation unit 122 may exclude products 3 that have been handled in the target store 20 in the past from the recommended products 31. The recommendation unit 122 may also exclude products 3 that have been handled in the target store 20 during a specified period in the past from the recommended products 31. As an example, it is assumed that the target store 20 handled the product category "clothing" in the past (for example, several years ago). In this case, the recommendation unit 122 determines, as a selected category, a set of products 3 from the product group 30, excluding the product category "clothing".

In the above embodiment, the recommendation unit 122 may exclude products 3 whose product share (occupancy rate) is smaller than a threshold value (first threshold value) in the fourth filter process from the selected category. In other words, the recommendation unit 122 may exclude products 3 whose occupancy rate is smaller than a threshold value (first threshold value) from the recommended products 31. As an example, assume that there is a "product C" whose occupancy rate ranking satisfies the condition of the fourth filter process in the above embodiment. In this case, if the occupancy rate of "product C" is smaller than the threshold value, "product C" will be excluded from the selected category.

In the above embodiment, the product group 30 includes the products 3 already handled by the target store 20 and the products 3 handled by stores 2 other than the target store 20 among the stores 2 belonging to the store group 200, but is not limited to this. For example, the product group 30 may include only the products 3 handled by the other store group 600.

In the above embodiment, the calculation unit 123 calculates the repeat rate representing the frequency with which the product 3 is purchased again by the same customer in the product category to which the product 3 belongs based on the history information acquired by the acquisition unit 121, but this is not limited to the above. For example, the calculation unit 123 may calculate a similar repeat rate representing the frequency with which products 3 having functions similar to the product 3, including the product 3, are purchased again by the same customer in the product category to which the product 3 belongs. Here, the "product having a similar function" is, for example, unsweetened black tea other than "unsweetened black tea A" when the product 3 is "unsweetened black tea A". In this case, the recommendation unit 122 may determine the selection category based on the similar repeat rate instead of the repeat rate in the sixth filter process. Also, for example, the calculation unit 123 may calculate both the repeat rate and the similar repeat rate. The recommendation unit 122 may determine the selection category based on the repeat rate and the similar repeat rate in the sixth filter process.

In the above-described embodiment, the recommendation unit 122 may execute each of the above filter processes independently of the execution results of other filter processes. That is, the recommendation unit 122 may execute each filter process for all products 3 belonging to the product group 30. In this case, the recommendation unit 122 may weight each filter process and calculate a recommendation score for each product 3. Then, the recommendation unit 122 may determine, as recommended products 31, one or more products 3 whose recommendation scores are equal to or greater than a predetermined score.

In the above-described embodiment, the recommendation unit 122 may determine the recommended product 31 not only from the product 3 not handled by the target store 20, but also from the product 3 currently handled by the target store 20. When a product 3 currently handled by the target store 20 is determined as the recommended product 31, a user such as the owner of the target store 20 can take measures such as increasing the stock of the product 3 or placing the product 3 on a shelf where it is easily visible to the public.

In the above embodiment, the other store group 600 is in a different industry from the industry of the store group 200, but this is not limited to the above. For example, the other store group 600 may be in the same industry as the store group 200, but in a different series from the series of the store group 200. Specifically, if the store group 200 is a collection of "A-series" convenience stores, the other store group 600 may be a collection of "B-series" convenience stores.

(summary)
As described above, the product recommendation system (10) according to the first aspect includes an acquisition unit (121) and a recommendation unit (122). The acquisition unit (121) acquires performance information on sales performance of a product (3) belonging to a product group (30) and handling information on whether the product (3) is handled in a target store (20) belonging to a store group (200). The recommendation unit (122) determines a recommended product (31) to be handled in the target store (20) from the product group (30) based on the performance information and handling information acquired by the acquisition unit (121).

This aspect has the advantage of making it easier to recommend products (3) (recommended products (31)) that are suitable for improving the business situation of the target store (20).

In the product recommendation system (10) relating to the second aspect, in the first aspect, the recommendation unit (122) determines a product (3) that is not handled in the target store (20) as a recommended product (31).

This aspect has the advantage of attracting customers by encouraging the target store (20) to carry a product (3) (recommended product (31)) that was not previously carried in the target store (20).

In the product recommendation system (10) according to the third aspect, in the first or second aspect, the performance information includes the share of the sales of the product (3) in the total sales of a specific product group among the product groups (30). The recommendation unit (122) determines the recommended product (31) based on the share.

According to this aspect, by proactively including products (3) that are expected to contribute to improving the business situation of the target store (20) in the recommended products (31), it is possible to encourage the target store (20) to handle products (3) (recommended products (31)) that are more suitable for improving the business situation.

In the product recommendation system (10) according to the fourth aspect, in the third aspect, the performance information includes a occupancy ranking in a specific product group. The recommendation unit (122) determines a recommended product (31) based on the occupancy ranking.

According to this aspect, by proactively including products (3) that are expected to contribute to improving the business situation of the target store (20) in the recommended products (31), it is possible to encourage the target store (20) to handle products (3) (recommended products (31)) that are more suitable for improving the business situation.

In the product recommendation system (10) relating to the fifth aspect, in the third or fourth aspect, the recommendation unit (122) excludes products (3) whose occupancy rate is smaller than the occupancy threshold (first threshold) from the recommended products (31).

According to this embodiment, by excluding products (3) that are expected to be unlikely to contribute to improving the business situation of the target store (20) from the recommended products (31), it is possible to encourage the target store (20) to handle products (3) (recommended products (31)) that are more suitable for improving the business situation.

In the product recommendation system (10) relating to the sixth aspect, in any of the first to fifth aspects, the recommendation unit (122) excludes products (3) that were previously handled at the target store (20) from the recommended products (31).

According to this aspect, for example, by excluding from the recommended products (31) products (3) that have not contributed to improving the business situation of the target store (20) in the past, it is possible to encourage the store to handle products (3) (recommended products (31)) that are more suitable for improving the business situation.

In the product recommendation system (10) relating to the seventh aspect, in any of the first to sixth aspects, the product group (30) includes products (3) handled by another store group (600) having a store format different from the store format of the store group (200).

According to this aspect, the store group (200) can be encouraged to handle the product (3) (recommended product (31)) that it did not previously handle, which has the advantage of making it easier to attract customers from other store groups (600) to the target store (20).

In the product recommendation system (10) relating to the eighth aspect, in the seventh aspect, the product group (30) includes only products (3) handled by the other store group (600).

According to this aspect, the store group (200) can be encouraged to handle the product (3) (recommended product (31)) that it did not previously handle, which has the advantage of making it easier to attract customers from other store groups (600) to the target store (20).

In the product recommendation system (10) relating to the ninth aspect, in the seventh or eighth aspect, the recommendation unit (122) determines, as a recommended product (31), a product (3) from the group of products (30) that belongs to a specific category identified based on a management indicator, which is an indicator related to the management of the target store (20).

According to this embodiment, there is an advantage that it is easier to recommend a product (3) (recommended product (31)) suitable for improving the business situation of the target store (20) compared to a case where the recommended product (31) is not determined from a specific category.

In the product recommendation system (10) according to the tenth aspect, in the ninth aspect, the specific category is determined so that the product (3) purchased by the specific customer belongs to the specific category. The specific customer is a customer who purchases the product (3) from both the store group (200) and the other store group (600) and who uses the store group (200) with a frequency greater than a frequency threshold (second threshold).

According to this aspect, there is an advantage that the utilization rate of the target store (20) by a specific customer can be further improved by encouraging the specific customer to handle the product (3) (recommended product (31)) that the specific customer is expected to purchase.

In the product recommendation system (10) relating to the eleventh aspect, in the tenth aspect, the specific category is determined to be a product category in which the proportion of specific customers among purchasers of products (3) belonging to the specific category is greater than a proportion threshold (third threshold).

According to this aspect, there is an advantage that the utilization rate of the target store (20) by a specific customer can be further improved by encouraging the specific customer to handle the product (3) (recommended product (31)) that the specific customer is expected to purchase.

In the product recommendation system (10) according to the twelfth aspect, in any of the first to eleventh aspects, the acquisition unit (121) further acquires similarity information regarding the similarity between the product (3) belonging to the product group (30) and the product (3) handled at the target store (20). The recommendation unit (122) determines the recommended product (31) by referring to the similarity information acquired by the acquisition unit (121).

According to this aspect, it is possible to attract customers by encouraging them to handle a product (3) (recommended product (31)) that has a function that was not previously handled at the target store (20), for example.

In the product recommendation system (10) according to the thirteenth aspect, in any of the first to twelfth aspects, the acquisition unit (121) further acquires history information relating to the customer's purchase history for a product (3) belonging to a product group (30). The product recommendation system (10) further includes a calculation unit (123). The calculation unit (123) calculates a repeat rate representing the frequency with which the product (3) is purchased again by the same customer in the product category to which the product (3) belongs, based on the history information acquired by the acquisition unit (121). The recommendation unit (122) determines a recommended product (31) by referring to the repeat rate calculated by the calculation unit (123).

According to this embodiment, there is an advantage that the number of repeat customers can be increased by encouraging the target store (20) to carry products (3) (recommended products (31)) that are expected to be purchased repeatedly by customers.

In the product recommendation system (10) according to the fourteenth aspect, in any of the first to thirteenth aspects, the acquisition unit (121) further acquires order information regarding the order of a product (3) belonging to the product group (30). The recommendation unit (122) determines a recommended product (31) by referring to the order information acquired by the acquisition unit (121).

According to this aspect, there is an advantage that the product (3) (recommended product (31)) to be handled at the target store (20) can be determined by taking into consideration the difficulty of ordering the product (3) at the target store (20).

The product recommendation method according to the fifteenth aspect includes an acquisition process and a recommendation process. The acquisition process is a process for acquiring performance information on the sales performance of a product (3) belonging to a product group (30) and handling information on whether the product (3) is handled in a target store (20) belonging to a store group (200). The recommendation process is a process for determining a recommended product (31) from the product group (30) to be handled in the target store (20) based on the performance information and handling information acquired in the acquisition process.

This aspect has the advantage of making it easier to recommend products (3) (recommended products (31)) that are suitable for improving the business situation of the target store (20).

The program relating to the 16th aspect causes one or more processors to execute the product recommendation method of the 15th aspect.

This aspect has the advantage of making it easier to recommend products (3) (recommended products (31)) that are suitable for improving the business situation of the target store (20).

The configurations relating to the second to fourteenth aspects are not essential configurations for the product recommendation system (10) and may be omitted as appropriate.

10 Product recommendation system 121 Acquisition unit 122 Recommendation unit 123 Calculation unit 20 Target store 200 Store group 600 Other store group 3 Product 30 Product group 31 Recommended product

Claims (18)

an acquisition unit that acquires sales information on products belonging to a product group, first handling information on whether the products are handled in target stores belonging to a first store group, and second handling information on whether the products are handled in stores belonging to a second store group that has a store format different from that of the first store group ;
A recommendation unit that determines a recommended product to be handled at the target store from the product group based on the performance information , the first handling information , and the second handling information acquired by the acquisition unit.
Product recommendation system. an acquisition unit that acquires sales information on products belonging to a product group and handling information on whether the products are handled in a target store belonging to a store group;
a recommendation unit that determines a recommended product to be handled at the target store from the group of products based on the performance information and the handling information acquired by the acquisition unit,
The acquiring unit further acquires history information regarding a customer's purchase history for products belonging to the product group,
A calculation unit calculates a degree of attachment to the product in a product category to which the product belongs based on the history information acquired by the acquisition unit,
The degree of commitment is a ratio of the number of times the customer has purchased the product to the number of times all products belonging to the product category have been purchased by the customer,
The recommendation unit determines the recommended product by referring to the degree of preference calculated by the calculation unit.
Product recommendation system. The recommendation unit determines a product that is not handled in the target store as the recommended product.
The product recommendation system according to claim 1 or 2. The performance information includes a share of the sales of the product in the total sales of a specific product group among the product groups,
The recommendation unit determines the recommended product based on the occupancy rate.
The product recommendation system according to any one of claims 1 to 3. The performance information includes a ranking of the occupancy rate in the specific product group,
The recommendation unit determines the recommended products based on the ranking of the occupancy rates.
The product recommendation system according to claim 4. The recommendation unit excludes products whose occupancy rate is less than an occupancy threshold from the recommended products.
The product recommendation system according to claim 4 or 5. The recommendation unit excludes products that have been handled in the target store in the past from the recommended products.
The product recommendation system according to any one of claims 1 to 6. The store format of the first store group is a convenience store, and the store format of the second store group is a supermarket.
The product recommendation system of claim 1 . The product group includes only products handled by the second store group,
The product recommendation system according to claim 1. The recommendation unit determines, from the group of products, products belonging to a specific category identified based on a management index, which is an index related to the management of the target store, as the recommended products.
The product recommendation system of claim 1 . the specific category is determined so that products purchased by specific customers who purchase the products at both the first store group and the second store group and who use the first store group with a frequency greater than a frequency threshold belong to the specific category;
The product recommendation system according to claim 10. The specific category is determined so that a ratio of the specific customers among the purchasers of the products belonging to the specific category is greater than a ratio threshold.
The product recommendation system according to claim 11. The acquisition unit further acquires similarity information regarding a similarity between the products belonging to the product group and products handled at the target store,
the recommendation unit determines the recommended product by referring to the similar information acquired by the acquisition unit.
The product recommendation system according to any one of claims 1 to 12. The acquiring unit further acquires history information regarding a customer's purchase history for products belonging to the product group,
a calculation unit that calculates a repeat rate representing a frequency at which the product is repurchased by the same customer in a product category to which the product belongs, based on the history information acquired by the acquisition unit;
The recommendation unit determines the recommended product by referring to the repeat purchase rate calculated by the calculation unit.
The product recommendation system of claim 1 . The acquiring unit further acquires order information regarding orders for products belonging to the product group,
The recommendation unit determines the recommended product by referring to the order information acquired by the acquisition unit.
The product recommendation system according to any one of claims 1 to 14. 1. A product recommendation method executed by one or more processors, comprising:
an acquisition process for acquiring performance information on sales performance of products belonging to a product group, first handling information on whether the products are handled in target stores belonging to a first store group, and second handling information on whether the products are handled in stores belonging to a second store group having a store format different from that of the first store group;
A recommendation process for determining a recommended product to be handled at the target store from the product group based on the performance information, the first handling information, and the second handling information acquired in the acquisition process.
Product recommendation methods. 1. A product recommendation method executed by one or more processors, comprising:
An acquisition process for acquiring sales information on products belonging to a product group and handling information on whether the products are handled in a target store belonging to a store group;
A recommendation process for determining a recommended product to be handled at the target store from the group of products based on the performance information and the handling information acquired in the acquisition process,
The acquisition process further acquires history information regarding a customer's purchase history for products belonging to the product group,
The method further includes a calculation process of calculating a degree of attachment to the product in a product category to which the product belongs based on the history information acquired in the acquisition process,
The degree of commitment is a ratio of the number of times the customer has purchased the product to the number of times all products belonging to the product category have been purchased by the customer,
In the recommendation process, the recommended product is determined by referring to the degree of preference calculated in the calculation process.
Product recommendation methods. One or more processors,
Executing the product recommendation method according to claim 16 or 17,
Program.

Images