Product recommendation system, product recommendation method, and program
The product recommendation system addresses the challenge of optimizing inventory by using performance and handling data to recommend products that enhance sales and business metrics across diverse store formats, improving store performance.
Patent Information
- Application Number
- JP2021550457
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2019-10-03
- Filing Date
- 2020-09-01
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2040-09-01
AI Technical Summary
Existing product recommendation systems fail to efficiently recommend products that can improve the business situation of target stores by considering sales performance and handling information across a large number of stores with varying conditions and formats, making it difficult to optimize inventory management.
A product recommendation system that acquires performance and handling information from a network of stores, calculates a degree of commitment based on customer purchase history, and determines recommended products using a series of filters to enhance sales and business metrics at the target store.
The system effectively recommends products that enhance sales, customer engagement, and business metrics by considering sales performance and handling information across multiple store formats, facilitating improved inventory management and customer attraction.
Smart Images

Figure 0007584065000001 
Figure 0007584065000002 
Figure 0007584065000003
Abstract
Description
[Technical field]
[0001] 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 for recommending products to be handled in a target store. [Background technology]
[0002] Patent Document 1 describes an item assortment recommendation device that determines a recommended item assortment in order to increase sales through appropriate inventory management of products in a business model in which a headquarters manages many stores.
[0003] The product assortment recommendation device described in Patent Document 1 calculates first composition information, which is sales amount composition information of 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 of 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 of 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. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] WO2018 / 056220A1 Summary of the Invention
[0005] 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.
[0006] A product recommendation system according to an embodiment of the present disclosure includes an acquisition unit and a recommendation unit. The acquisition unit acquires sales performance information on a sales performance of a product belonging to a product group,No. 1 Regarding whether the said product is available at the target stores belonging to the store group No. 1 Handling information and Second handling information regarding whether the product is handled in stores belonging to a second store group having a store format different from that of the first store group; and The recommendation unit acquires the performance information acquired by the acquisition unit. , 1st handling information and the above Second Based on the handling information, recommended products to be handled at the target store are determined from the group of products. 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.
[0007] A product recommendation method according to one embodiment of the present disclosure includes: A product recommendation method executed by one or more processors, the product recommendation method comprising: The method includes an acquisition process and a recommendation process. The acquisition process includes: acquiring sales information on sales results of products belonging to a product group; No. 1 Regarding whether the said product is available at the target stores belonging to the store group No. 1 Handling information and Second handling information regarding whether the product is handled in stores belonging to a second store group having a store format different from that of the first store group; and The recommendation process is a process of acquiring the performance information acquired in the acquisition process. , the first handling information and the above Second This is a process of determining recommended products to be handled at the target store from the group of products based on handling information. A product recommendation method according to an embodiment 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 a product 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.
[0008] A program according to one embodiment of the present disclosure causes one or more processors to execute the above-described product recommendation method. [Brief description of the drawings]
[0009] [Figure 1] FIG. 1 is a schematic diagram showing a configuration of a product recommendation system according to an embodiment of the present disclosure. [Diagram 2] FIG. 2 is a schematic diagram of a target store in which the above-mentioned product recommendation system is adopted. [Diagram 3] FIG. 3 is a block diagram of the above-mentioned product recommendation system. [Figure 4] FIG. 4 is a conceptual diagram showing a mode of determining a recommended product by the product recommendation system according to the embodiment. [Diagram 5]FIG. 5 is a diagram illustrating an example of a product category in which a specific customer exists in the product recommendation system. [Figure 6] FIG. 6 is a flowchart showing the operation of the above-mentioned product recommendation system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0010] (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 that is a retail store such as a convenience store, supermarket, department store, drug store, clothing store, home appliance retailer, or home improvement center.
[0011] 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 predetermined 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 the similarity condition. The similarity condition may include conditions related to the country, region, business hours, customer demographics, etc.
[0012] The product recommendation system 10 according to this embodiment is a system that improves the business situation of the target store 20 by increasing the sales amount of the target store 20. More specifically, the product recommendation system 10 is a system that improves the sales amount 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.
[0013] 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 a target store in one day is the LTV of this customer. 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 this customer in N shopping trips is the LTV of this customer, not the amount spent in one shopping trip. Thus, although LTV may appear similar to the unit price per customer at first glance, it differs from the unit price per customer in that it represents the total amount spent in a specified period.
[0014] 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.
[0015] The product recommendation system 10 proposes products 3 to be sold in 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.
[0016] As shown in FIG. 3, the product recommendation system 10 includes an acquisition unit 121 and a recommendation unit 122.
[0017] The acquisition unit 121 acquires performance information on sales performance of the products 3 belonging to the product group 30, and handling information on whether the products 3 are handled in the target stores 20 belonging to the store group 200. In other words, the acquisition unit 121 acquires performance information on sales performance and handling information on whether the products 3 are handled for each of the multiple products 3 belonging to the product group 30.
[0018] Here, the product group 30 may include the product 3 already handled by the target store 20, as well as the product 3 handled by the store 2 belonging to the store group 200 other than the target store 20. The product group 30 may also include the product 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 the product 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 drug stores (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.
[0019] The recommendation unit 122 determines a recommended product 31 to be recommended for sale 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 the multiple products 3 belonging to the product group 30, and determines the recommended product 31 from the one or more products 3 by referring to the individual sales performance of the one or more products 3.
[0020] As described above, the product recommendation system 10 of this embodiment can determine, as a recommended product 31, a product 3 that is not handled by the target store 20 and that takes into consideration sales records 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 record 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.
[0021] 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.
[0022] That is, usually, many stores 2 are operating under different conditions, although they meet certain similarity conditions. The same goes for many other stores 6. For this reason, in order to reflect the huge amount of information across these many stores 2 and other stores 6 in a certain target store 20, calculations far exceeding the processing power of a human are required, which is impossible for a human to achieve. Moreover, information on the operation and management of these many stores 2 and other stores 6 changes from time to time (e.g., seasonally), and updating the recommended products 31 taking into account the latest information on the many stores 2 and other stores 6 is impossible for a human to achieve.
[0023] In contrast, the product recommendation system 10 according to the present embodiment can process even the above-mentioned huge and fluctuating information by using, for example, a general information processing device. In this way, the product recommendation system 10 according to the present embodiment is particularly useful in a business format that refers to a large number of stores 2 and other stores 6.
[0024] (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 taken 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-time and part-time workers), and the "customer" is a customer at the convenience store. In this embodiment, it is assumed that there are 10,000 or more stores 2. In the following, a case will be described in which one of the multiple (large number) 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 in which there is only one target store 20 will be described as an example.
[0025] 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 a target store 20) through 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 the plurality of stores 2 through the network NT1.
[0026] 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.
[0027] As described above, at least one POS system 21 and at least one store terminal 22 are installed in each store 2 (including the target store 20). A plurality of POS systems 21 and a plurality of store terminals 22 may be installed in one store 2. 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 the store terminal 22 installed in each store 2 are connected to the network NT1 via a gateway or the like.
[0028] Each of the POS system 21 and the store terminal 22 mainly comprises a computer system having one or more processors and a 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, or may be provided via a telecommunication line such as the Internet, or may be provided by recording it on a non-transitory recording medium such as a memory card.
[0029] In particular, in this embodiment, the POS system 21 is a so-called "ID-POS" capable of handling ID-POS data. The "ID-POS data" here refers to 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, biometric authentication (including face authentication), or the like. Note that the POS system 21 is not limited to an ID-POS, and may be a simple POS that does not handle ID-POS data.
[0030] The store terminal 22 is an information terminal owned by a clerk or an owner of the store 2. The store terminal 22 has a touch panel display as a user interface, and receives operations from a user and presents (displays) information to the user.
[0031] Such a POS system 21 and store terminal 22 can 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, the POS system 21 can handle ID-POS data, and therefore, 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).
[0032] Furthermore, each store 2 may have devices connected to the network NT1 other than 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.
[0033] As described above, the headquarters terminal 51 is installed in the chain headquarters 5 which operates multiple stores 2. The headquarters terminal 51 mainly comprises a computer system having one or more processors and a 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-transitory recording medium such as a memory card and provided.
[0034] The headquarters terminal 51 has, for example, a touch panel display as a user interface, and receives operations from a user and presents (displays) information to the user. Users of the headquarters terminal 51 are mainly operators of the chain headquarters 5, etc.
[0035] 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. The product recommendation system 10 preferably uses a Paas (Platform as a Service) environment, which is a public cloud environment without management of the OS, runtime, and middleware.
[0036] The communication unit 11 is a communication interface. In particular, the communication unit 11 is a communication interface connectable to a network NT1 and has a 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.
[0037] The processing unit 12 is configured to perform overall control of the product recommendation system 10. The processing unit 12 can be realized, for example, by a computer system including one or more processors (microprocessors) and one or more memories. That is, 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 be provided via a telecommunications line such as the Internet, or recorded on a non-transitory recording medium such as a memory card.
[0038] 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 actual configurations, but represent functions realized by the processing unit 12.
[0039] The acquisition unit 121 acquires performance information and handling information. Specifically, the acquisition unit 121 acquires performance information from, for example, a server device of a service provider that provides purchase data including a purchase history of the product 3 or storage on a cloud (cloud computing) through the network NT1. The acquisition unit 121 also acquires handling information by communicating with, for example, at least one of the POS system 21, the store terminal 22, and the headquarters terminal 51 of the target store 20 through the network NT1.
[0040] In this embodiment, the acquiring unit 121 acquires performance information by performing appropriate statistical processing on the purchase data. Also, in this embodiment, the acquiring unit 121 acquires performance information based on purchase data collected in a server device of a service provider or in a cloud storage device or the like for a predetermined period (e.g., several years).
[0041] Here, as an example, the purchase data is collected in a server device of the service provider or a storage on a cloud by a user (customer) using an application provided to the user by the service provider. For example, it is assumed that the application is installed in an information terminal such as a smartphone owned by the customer. In this case, the receipt handed to the customer when the customer purchases the product 3 at the store 2 or another store 6 is captured by a camera installed in the information terminal via the application. Then, the application applies appropriate image processing to the image captured by the camera, and information such as the purchase history of the 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 application is then transmitted to a server device of the service provider or a storage on a cloud.
[0042] The purchase data may include, as purchase history, information such as the name of the product 3, the product category of the product 3, the sales amount of the product 3 (including, for example, the price and the quantity), the purchase date of the product 3 (for example, a weekday or a holiday), and the time period when the product 3 was purchased. The purchase data may also include, as purchase history, information such as the location (for example, prefecture and / or city / ward / town / village) of the store 2 (or other store 6) where the product 3 was purchased, and the store format (for example, a convenience store or supermarket) of the store 2 (or other store 6). The purchase data may also include, as customer information, information such as the ID of the customer who purchased the product 3, the customer's gender, the customer's age, and the customer's family structure.
[0043] In the present disclosure, a "product category" is a label for classifying products 3 according to 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, a product category may be a medium category that further classifies a large category into multiple medium categories, and specific examples of medium categories within food include medium categories such as soft drinks, alcohol, bento, prepared foods, sweets, snacks, and ice cream. Furthermore, a product category may be a small category that further classifies a medium category into multiple small categories, and specific examples of small categories within soft drinks include small categories such as barley tea, green tea, black tea, coffee, lactic acid drinks, carbonated drinks, mineral water, and sports drinks.
[0044] As described above, in this embodiment, the purchase data is not limited to information on the store 2 belonging to the store group 200, but also includes information on the other stores 6 belonging to the other store group 600. In other words, the purchase data includes a huge amount of data, i.e., big data, on 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 the store 2 or the other stores 6. Note that the purchase data is not limited to information acquired from receipts, and may include, for example, ID-POS data. In other words, the means for collecting purchase data from the store group 200 and the other store group 600 is not particularly limited.
[0045] The performance information is information on the sales performance of the product 3 belonging to the product group 30. The information on the sales performance of the product 3 may include information on the sales performance of the product 3 in the target store 20, as well as information on the sales performance of the product 3 in stores 2 other than the target store 20. Furthermore, the information on the sales performance of the product 3 may include information on the sales performance of the product 3 in other stores 6 belonging to the other store group 600. The product group 30 includes the product 3 handled in the target store 20, as well as the product 3 handled in stores 2 other than the target store 20 belonging to the store group 200. Furthermore, the product group 30 includes the product 3 handled in the other store 6 belonging to the other store group 600. In other words, in this embodiment, the product group 30 includes the product 3 handled by the other store group 600, which has a store format different from that of the store group 200.
[0046] 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".
[0047] 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 share (product share) of the sales 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. As an example, the specific product group is all the products 3 belonging to an arbitrary 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 share (product share) of the sales 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.
[0048] 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 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.
[0049] 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 in the same product category, the subcategory "green tea," and have the same target customer base or price range, are sold by different manufacturers, 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.
[0050] In the present embodiment, the acquisition unit 121 further acquires history information regarding the purchase history of the customer 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 in a predetermined period (e.g., several years).
[0051] 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 located only 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 body 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.
[0052] The calculation unit 123 calculates the repeat rate based on the history information acquired by the acquisition unit 121. The repeat rate indicates 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 indicates the rate at which the customer purchases "coffee A" again from among multiple types of coffee included in the product category of "coffee". For example, if a customer purchases 100 bottles of coffee over a predetermined period (e.g., several years), of which 30 bottles are "coffee A", the repeat rate is 30%. In other words, the repeat rate can be said to indicate the strength of preference for a particular product 3 among multiple types of products 3 in the same product category, in other words, the customer's commitment to the product 3.
[0053] The recommendation unit 122 determines, from the product group 30, recommended products 31 to be recommended for sale 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 determining whether the products 3 belonging to the product group 30 match predetermined conditions while referring to the information acquired by the acquisition unit 121. As a result, the recommendation unit 122 determines, as recommended products 31, one or more products 3 from the product group 30 that match the multiple types of predetermined conditions most closely or whose match degree is greater than a threshold value.
[0054] 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 improve the business situation, for example, by deciding whether or not to handle the recommended products 31 in the target store 20, or by deciding to handle other products 3 based on the recommended products 31.
[0055] Hereinafter, a specific description will be given of the multiple filter processes executed by the recommendation unit 122. In the following description, for convenience of explanation, the multiple filter processes are referred to as a "first filter process" to a "seventh filter process", respectively, but the order in which the filter processes are executed is not uniquely determined.
[0056] 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, when 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 immediately preceding 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."
[0057] In the first filtering process, the recommendation unit 122 determines the selected category based on the performance information. In the first filtering 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 3 sold, etc., in a predetermined period (e.g., several years). The sales amount of the product 3 and the number of products 3 sold may include the sales amount of the product 3 and the number of products 3 sold in the target store 20, as well as the sales amount of the product 3 and the number of products 3 sold in stores 2 other than the target store 20. In addition, the sales amount of the product 3 and the number of products 3 sold may include the sales amount of the product 3 and the number of products 3 sold in other stores 6 belonging to the other store group 600. As a specific example, the recommendation unit 122 determines, as the selected category, one or more product categories in which the total sales amount of the product 3 is higher than a predetermined sales amount, 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 multiple product categories. In other words, the recommendation unit 122 executes the first filter process to determine, as recommended products 31, the products 3 that belong to a selected category (specific category) identified based on the management indicators of the target store 20 from among the product group 30.
[0058] In the second filtering process, the recommendation unit 122 determines a selection category (specific category) based on the performance information. In the second filtering process, the selection category is determined so that the product 3 purchased by the specific customer belongs to the category. The "specific customer" in the present disclosure is a so-called heavy user of the 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 purchases the product 3 at the store 2 more than a predetermined number of times in a predetermined period (for example, one week).
[0059] FIG. 5 shows an example of a product category in which specific customers exist. In the example shown in FIG. 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 FIG. 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 FIG. 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.
[0060] Particularly, 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, among 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.
[0061] 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 a change in the product 3 handled at the target store 20. For this reason, when the 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 can be expected that the product 3 newly handled at the target store 20 (recommended product 31) will be more likely to contribute to increased sales.
[0062] 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 in the target store 20 from among the product group 30 as the selected category. That is, the recommendation unit 122 determines products that are not handled in the target store 20 (non-handled products) as the recommended products 31. In other words, the recommendation unit 122 excludes products that are handled in the target store from the recommended products 31. For example, if the target store 20 does not handle alcoholic beverages, alcoholic beverages may be included in the selected category. Also, for example, if the target store 20 handles "ballpoint pen A," 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.
[0063] 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) in the product group 30 as the selection category. That is, the recommendation unit 122 determines the recommended products 31 based on the occupancy rate. In particular, in this embodiment, it is preferable to execute the second filter process before executing 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 restricts 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 in 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 restricts the set of products 3 with a relatively high occupancy rate from this set of products 3 as the selection category.
[0064] In this embodiment, the recommendation unit 122 determines a set of products 3 whose occupancy rates are 1st to several tens (for example, 30th) as the selected category. That is, in this embodiment, the recommendation unit 122 determines the recommended products 31 based on the ranking of the occupancy rate. Note that the recommendation unit 122 may determine a set of products 3 whose occupancy rates exceed a predetermined threshold as the selected category.
[0065] 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 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 a set of products 3 with occupancy rates of 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 occupancy rates of "ice cream A", "ice cream B", and "ice cream C" in the product category "ice cream" are 5%, 3%, and 1%, respectively, and the occupancy rates of "coffee A" and "coffee B" in the product category "coffee" are 4% and 2%, respectively. In this case, the recommendation unit 122 determines a set of "ice cream A" with the occupancy rate of 1st place, "coffee A" with the occupancy rate of 2nd place, and "ice cream B" with the occupancy rate of 3rd place as the selected category.
[0066] 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 product 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, it is assumed that the product group 30 includes "salmon onigiri A", "salmon onigiri B", and "kelp onigiri A", and only "salmon onigiri A" is currently handled in the target store 20. In this case, since "kelp onigiri A" has a different taste from "salmon onigiri A", it is determined that the similarity to "salmon onigiri A" is relatively low, and it is highly likely that the recommendation unit 122 will include it in the selection category. 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.
[0067] 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" 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.
[0068] 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 having a repeat rate higher than a predetermined threshold value from among the product group 30 as the selected category. In this embodiment, the repeat rate used in the sixth filter process is, for example, an average value of the repeat rates for one or more specific customers.
[0069] 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. That is, 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 a 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 a 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.
[0070] 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 a "product A" that can be ordered nationwide and a "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, the difficulty of ordering is considered to be relatively low, and it is highly likely that the product A will be included in the selection category by the recommendation unit 122. On the other hand, since the area in which "product B" can be ordered is outside the Kansai region, it is considered to be relatively difficult to order, and it is highly likely that the product B will not be included in the selection category by the recommendation unit 122.
[0071] In this embodiment, the recommendation unit 122 determines, as the recommended product 31, one or more products 3 filtered by sequentially executing the above-mentioned first filter process to the seventh filter process. 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-mentioned 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, as the selected category, a set of products 3 with a occupancy rate of 1st to tens of products out of the products 3 not handled in the target store 20. On the other hand, when the fourth filter process is executed before the third filter process is executed, the recommendation unit 122 determines, as the selected category, a set of products 3 with a occupancy rate of 1st to tens of products out of the products 3 not 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 an administrator of the product recommendation system 10.
[0072] (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).
[0073] As described above, the product recommendation system 10 of this embodiment can determine, as a recommended product 31, a product 3 that is not handled by the target store 20 and that takes into consideration sales records 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 record 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.
[0074] (4) Variations 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, the same function as 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.
[0075] The product recommendation method according to one embodiment includes an acquisition process and a recommendation process. The acquisition process is a process of acquiring 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 process is a process of 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 product recommendation method described above.
[0076] Modifications of the above-described embodiment are listed below. The modifications described below can be applied in appropriate combination.
[0077] 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, thereby realizing 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 provided by being recorded 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 by different names 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.
[0078] Furthermore, it is not essential for the product recommendation system 10 that multiple functions are integrated into 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 cloud (cloud computing) or the like.
[0079] Conversely, at least some of the functions of the product recommendation system 10 that are distributed across multiple devices in the above-described embodiment may be integrated into one housing.
[0080] Furthermore, the use of the product recommendation system 10 is not limited to convenience stores, and the product recommendation system 10 may be installed in stores 2 other than convenience stores. As an example, the product recommendation system 10 may be installed in a food service facility such as a restaurant. In this case, food or the like provided to customers corresponds to the product 3.
[0081] Furthermore, the product 3 is not limited to a tangible product, but may be an intangible product.
[0082] 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 by projection mapping technology. Furthermore, the user interface may 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 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).
[0083] In the above embodiment, the product recommendation system 10 includes the calculation unit 123, but the calculation unit 123 is not essential. That is, the product recommendation system 10 only needs to include at least the acquisition unit 121 and the recommendation unit 122.
[0084] The sales form of the product 3 in the store 2 is not limited to the form in which a plurality of products 3 are displayed in the store as in the above embodiment. For example, the product 3 may be sold in a form in which a vending machine that stocks a plurality of products 3 is used to settle the account for the product 3 selected by the customer and dispense the product 3. Furthermore, even if a plurality of products 3 are displayed in the store and sold, the sales form may be such that the customer settles the account without the assistance of a store clerk by using, for example, a self-checkout.
[0085] 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 thereto. 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.
[0086] In the above embodiment, the recommendation unit 122 may further execute an eighth filtering process in addition to the first to seventh filtering processes. In the eighth filtering process, the recommendation unit 122 determines, as a selected category, a set of products 3, excluding products 3 that were previously handled in the target store 20, from the product group 30, based on the handling information. That is, the recommendation unit 122 may exclude products 3 that were previously handled in the target store 20 from the recommended products 31. In addition, the recommendation unit 122 may exclude products 3 that were handled in the target store 20 during a predetermined 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, excluding the product category "clothing" from the product group 30.
[0087] 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.
[0088] 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 belonging to the store group 200 other than the target store 20, 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.
[0089] 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 the present invention is not limited to this. 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 similar functions" refers to unsweetened black tea other than "unsweetened black tea A" when the product 3 is, for example, "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.
[0090] In the above-described embodiment, the recommendation unit 122 may execute each of the above filter processes regardless of the execution results of other filter processes. That is, the recommendation unit 122 may execute each filter process on 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.
[0091] In the above-described embodiment, the recommendation unit 122 may determine the recommended product 31 not only from the products 3 not handled in the target store 20 but also from the products 3 currently handled in the target store 20. When a product 3 currently handled in 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.
[0092] In the above embodiment, the other store group 600 is in a different business type from the business type 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 business type as the store group 200, but may be in a different series from the store group 200. Specifically, if the store group 200 is a collection of "A-type" convenience stores, the other store group 600 may be a collection of "B-type" convenience stores.
[0093] (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).
[0094] This embodiment has the advantage that it is easy to recommend the product 3 (recommended product 31) that is suitable for improving the business situation of the target store 20.
[0095] In the product recommendation system (10) according to the second aspect, in the first aspect, the recommendation unit (122) determines a product (3) that is not handled in a target store (20) as a recommended product (31).
[0096] According to this embodiment, there is an advantage that it is possible to attract customers by encouraging the target store (20) to handle the product (3) (recommended product (31)) that was not previously handled in the target store (20).
[0097] In the product recommendation system (10) according to the third aspect, in the first or second aspect, the performance information includes a sales share of the product (3) in the total sales of a specific product group (30) among the product groups (30). The recommendation unit (122) determines a recommended product (31) based on the share.
[0098] According to this embodiment, 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.
[0099] In the product recommendation system (10) according to the fourth aspect, in the third aspect, the performance information includes a share ranking in a specific product group. The recommendation unit (122) determines a recommended product (31) based on the share ranking.
[0100] According to this embodiment, 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.
[0101] In the product recommendation system (10) according to the fifth aspect, in the third or fourth aspect, the recommendation unit (122) excludes the product (3) whose occupancy rate is smaller than the occupancy threshold (first threshold) from the recommended products (31).
[0102] According to this embodiment, by excluding the products (3) that are 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) that are more suitable for improving the business situation (recommended products (31)).
[0103] In the product recommendation system (10) according to the sixth aspect, in any of the first to fifth aspects, the recommendation unit (122) excludes products (3) that were previously handled in the target store (20) from the recommended products (31).
[0104] According to this embodiment, 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 target store (20) to handle products (3) (recommended products (31)) that are more suitable for improving the business situation.
[0105] In the product recommendation system (10) according 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 that of the store group (200).
[0106] According to this embodiment, 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).
[0107] In the product recommendation system (10) according to the eighth embodiment, the product group (30) in the seventh embodiment includes only the products (3) handled by the other store group (600).
[0108] According to this embodiment, 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).
[0109] In the product recommendation system (10) according to the ninth aspect, in the seventh or eighth aspect, the recommendation unit (122) determines, as a recommended product (31), a product (3) from a group of products (30) that belongs to a specific category identified based on a management index, which is an index related to the management of the target store (20).
[0110] This embodiment has the advantage that it is easier to recommend a product (3) (recommended product (31)) that is 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.
[0111] 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).
[0112] According to this embodiment, there is an advantage that the utilization rate of the target store (20) by the 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.
[0113] In the product recommendation system (10) according 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).
[0114] According to this embodiment, there is an advantage that the utilization rate of the target store (20) by the 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.
[0115] 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 in 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).
[0116] According to this embodiment, for example, there is an advantage in that it is possible to attract customers by encouraging the target store (20) to handle a product (3) (recommended product (31)) having a function that was not previously handled in the target store (20).
[0117] In a product recommendation system (10) according to a thirteenth aspect, in any of the first to twelfth aspects, an acquisition unit (121) further acquires history information on a 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 indicating a frequency at 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).
[0118] 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 the product (3) (recommended product (31)) that is expected to be purchased repeatedly by the customer.
[0119] 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 related to an order for a product (3) belonging to a product group (30). The recommendation unit (122) determines a recommended product (31) by referring to the order information acquired by the acquisition unit (121).
[0120] This embodiment has the advantage that the product (3) (recommended product (31)) handled at the target store (20) can be determined taking into consideration the difficulty of ordering the product (3) at the target store (20).
[0121] 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 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.
[0122] This embodiment has the advantage that it is easy to recommend the product 3 (recommended product 31) that is suitable for improving the business situation of the target store 20.
[0123] A program according to a sixteenth aspect causes one or more processors to execute the product recommendation method according to the fifteenth aspect.
[0124] This embodiment has the advantage that it is easy to recommend the product 3 (recommended product 31) that is suitable for improving the business situation of the target store 20.
[0125] The configurations according to the second to fourteenth aspects are not essential for the product recommendation system (10) and may be omitted as appropriate. [Explanation of symbols]
[0126] 10 Product Recommendation System 121 Acquisition Department 122 Recommendation section 123 Calculation section 20 Target stores 200 stores 600 other stores 3 items 30 product groups 31 Recommended Products
Claims
1. 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 group of products based on the performance information, the first handling information, and the second handling information acquired by the acquisition unit. Product recommendation system.
2. An acquisition unit that acquires sales information regarding products belonging to a product group and handling information regarding whether or not the products are handled in target stores 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 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 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.
3. 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.
4. The performance information includes a share of 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.
5. 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.
6. 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.
7. 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.
8. 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 .
9. The product group includes only products handled by the second store group, The product recommendation system according to claim 1.
10. The recommendation unit determines, from among the group of products, products belonging to a specific category identified based on a management index that is an index related to the management of the target store, as the recommended products. The product recommendation system of claim 1 .
11. 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.
12. The specific category is determined to be a product category in which the proportion of the specific customers among the purchasers of the product belonging to the specific category is greater than a proportion threshold. The product recommendation system according to claim 11.
13. 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.
14. The acquisition 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 that indicates 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 .
15. The acquisition 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.
16. 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.
17. 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.
18. To one or more processors: Executing the product recommendation method according to claim 16 or 17, program.
Citation Information
Patent Citations
Marketing skill quantification method, marketing skill quantification program, personal evaluation support program and merchandise sales support program
JP2006285681A
Information providing device, program and information providing method
JP2015162182A
Product lineup recommendation device, product lineup recommendation method, and product lineup recommendation program
WO2018056220A1
