Home delivery product recommendation device and home delivery product recommendation program

Abstract

We aim to further improve personalized recommendation technology, ultimately leading to increased customer convenience and higher average customer spending. [Solution] A product delivery recommendation device for products with a predetermined order delivery schedule, comprising: current date and time acquisition means for acquiring current date and time information; order date and time acquisition means for acquiring order start date and time and order deadline date and time information; order date and time acquisition means for acquiring order start date and time and order deadline date and time information; time interval calculation means for calculating the time interval between the current date and time and the order deadline date and time; product recommendation means for recommending products based on the user's multiple past purchase history of products and the current date and time; and display quantity calculation means for calculating the number or percentage of recommended products by the product recommendation means to be displayed in the recommended product display area according to the time interval.

Description

Technical Field

[0001] The present invention relates to a home delivery product recommendation device and a home delivery product recommendation program.

Background Art

[0002] As one of the recommendation technologies in online shopping and EC (electronic commerce) sites, personalized recommendation is known, which analyzes the past purchase history and browsing history of users by algorithms and recommends products that the user is likely to buy for the purpose of improving customer convenience and customer unit price (see, for example, Patent Documents 1 and 2).

[0003] Non-Patent Document 1 also describes a recommendation engine having a plurality of respective features. For example, in the case of an EC site for a regular home delivery service of organic vegetables, new products are recommended by a novelty engine according to the customer's preference, and then re-purchase is recommended by a repeatability engine. If the purchase is also made at this timing, the purchase interval is grasped, and the periodicity engine recommends at the timing considered to be optimal for each customer, and measures for leading to regular product purchases are described.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Non-Patent Documents

[0005]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] Personalized recommendations are a technology that predicts the demand of each individual customer, asking "who is likely to buy what and when," and recommending products at the most effective time for that customer. Continuous improvement and refinement of its effectiveness are required.

[0007] This invention was proposed in view of the above points, and in one aspect aims to further improve personalized recommendation technology, thereby improving customer convenience and increasing the average customer spending. [Means for solving the problem]

[0008] To solve the above problems, the home delivery product recommendation device according to the present invention is a home delivery product recommendation device for products for which a predetermined order delivery schedule has been set, and comprises: current date and time acquisition means for acquiring current date and time information; order date and time acquisition means for acquiring order start date and time and order deadline date and time information for the product; time interval calculation means for calculating the time interval between the current date and time and the order deadline date and time; product recommendation means for recommending products based on the user's multiple past purchase history of the product and the current date and time; and display quantity calculation means for calculating the number or percentage of recommended products by the product recommendation means to be displayed in the recommended product display area according to the time interval. [Effects of the Invention]

[0009] According to embodiments of the present invention, in one respect, it is possible to further improve personalized recommendation technology, and consequently improve customer convenience and increase the average customer spending. [Brief explanation of the drawing]

[0010] [Figure 1] This figure shows an example configuration of the regular home delivery product recommendation system 100 according to this embodiment. [Figure 2] This figure shows an example of the functional configuration of the recommendation machine 20 according to this embodiment. [Figure 3]This diagram illustrates the order delivery schedule information according to this embodiment. [Figure 4] This is a diagram (part 1) illustrating the recommendation engine according to this embodiment. [Figure 5] This is a diagram (part 2) illustrating the recommendation engine according to this embodiment. [Figure 6] This is a diagram (part 3) illustrating the recommendation engine according to this embodiment. [Figure 7A] This figure illustrates the EC site screen (immediately after the order start time) 1 according to this embodiment. [Figure 7B] This figure illustrates the EC site screen (immediately after the order start time) 2 according to this embodiment. [Figure 7C] This diagram illustrates the EC site screen (immediately after the order start time) 3 according to this embodiment. [Figure 8A] This figure illustrates the EC site screen (immediately before the order deadline) 1 according to this embodiment. [Figure 8B] This figure illustrates the EC site screen (just before the order deadline) 2 according to this embodiment. [Figure 9] This is a flowchart showing the recommended product display control process according to this embodiment. [Modes for carrying out the invention]

[0011] Embodiments of the present invention will be described in detail with reference to the drawings. <System Configuration> Figure 1 shows an example configuration of the regular home delivery product recommendation system 100 according to this embodiment. The regular home delivery product recommendation system 100 in Figure 1 includes a home delivery online shopping server 10, a recommendation machine 20, various DBs (databases) 30, and user terminals 40, which are connected via a network 50.

[0012] The home delivery online shopping server 10 is a web server that provides an EC site for a business operator that operates a home delivery service for fresh food, daily necessities, etc. A user (member) accesses and logs in to the EC site using the user terminal 40, and selects and orders home delivery products. On the EC site, the home delivery products are categorized and displayed in a predetermined product display column, and a recommended product display area where recommended products (recommended items) determined by the recommendation machine 20 are displayed is provided.

[0013] The recommendation machine 20 has a plurality of recommendation engines described later, and is a recommendation device that analyzes the past purchase history of each user, calculates, and outputs products that the user is likely to buy. The output recommended products are displayed in the recommended product display area for the user on the EC site.

[0014] The user terminal 40 is, for example, a PC (personal computer), a smartphone, a tablet terminal, etc., and is a terminal of a member user who uses the home delivery service. A predetermined application program, a general-purpose web browser, etc. for accessing and logging in to the EC site of the home delivery online shopping server 10 are installed in advance in the user terminal 40. The user accesses and logs in to the EC site using the user terminal 40, and selects and orders (purchases) desired products. The ordered products are delivered to the delivery destination such as the user's home according to the home delivery schedule.

[0015] (Functional configuration) FIG. 2 is a diagram showing a functional configuration example of the recommendation machine 20 according to the present embodiment. The recommendation machine 20 mainly has a current date and time acquisition unit 101, an order date and time acquisition unit 102, a time interval calculation unit 103, a product recommendation unit 104, and a display amount calculation unit 105.

[0016] The current date and time acquisition unit 101 has a function of acquiring information on the current date and time.

[0017] The order date and time acquisition unit 102 has the function of acquiring information on the order start date and time and the order deadline date and time for products for which a predetermined order delivery schedule has been set.

[0018] The time interval calculation unit 103 has the function of calculating the time interval between the current date and time and the order deadline date and time (i.e., the remaining time until the order deadline date and time) based on the current date and time and the order deadline date and time.

[0019] The product recommendation unit 104 has the function of recommending products based on the user's past purchase history and the current date and time. The product recommendation unit 104 corresponds to a recommendation engine that includes a novelty engine, a repetition engine, a periodicity engine, and a preference engine, but in particular, the engine that has the function of recommending products based on the user's past purchase history and the current date and time corresponds to the periodicity engine.

[0020] The display quantity calculation unit 105 has a function to calculate the number or percentage of recommended products to be displayed in the recommended product display area according to the time interval between the current date and time and the order deadline date and time (the time remaining until the order deadline).

[0021] The recommendation machine 20 can be implemented using a general-purpose computer. Specifically, the recommendation machine 20 includes hardware such as an arithmetic processing unit (CPU, etc.), memory, input / output interfaces, and communication interfaces. The functions of the recommendation machine 20 are realized by the arithmetic processing unit executing processing according to computer programs stored in memory. That is, each functional unit is realized by a computer program executed on the hardware resources such as the arithmetic processing unit and memory of the computer that constitutes the recommendation machine 20. These functional units may also be read as "means," "modules," "units," or "circuits." Furthermore, some of the functional units may be located in the memory of the recommendation machine 20 or in external storage devices on the network. In addition, each functional unit of the recommendation machine 20 may be implemented not only by a single server device, but also as a system consisting of multiple devices with distributed functions. Furthermore, the above computer programs may be stored in a storage medium that can be read by the computer.

[0022] (Database) The DB30 according to this embodiment includes a user DB, a product DB, a purchase history DB, and order delivery schedule information.

[0023] The user database is a database where user information of members who use the delivery service is registered. For example, it includes user information such as the user's name, age, address, family, and preferences, as well as the login ID and login password for the e-commerce site on the delivery online shopping server.

[0024] The product database is a database (product master) where products sold as home delivery items are registered. Product information includes, for example, product code, product name, JAN code, product category, price, quantity, stock quantity, and producer. Recommended products are selected from the products registered in the product database.

[0025] The purchase history database is a database that records the history of products a user has purchased in the past. It includes at least purchase history information for each user, such as the product code, product name, purchase date and time, purchase price, and purchase quantity.

[0026] Figure 3 illustrates the order and delivery schedule information according to this embodiment. The order and delivery schedule information is information regarding the period during which products can be ordered and the delivery date. Generally, in the case of a regular delivery service, there is a set period during which orders can be placed, and products are ordered during a fixed period each week and delivered on a fixed day of the week.

[0027] For example, in the case of the weekly subscription delivery service shown in Figure 3, users can place orders during the order period, for example, from 12:00 AM on Tuesday (order start time) to 12:00 PM on Sunday (order deadline time). Orders for the week are closed at the order deadline time, and those orders are delivered, for example, on Wednesday of the following week. Needless to say, the order and delivery schedule information may be determined individually for each region based on the user's address. It may also be a weekly subscription service with two or more terms.

[0028] (Recommendation engine) Figure 4 is a diagram (part 1) illustrating the recommendation engine according to this embodiment. As shown in Figure 4, the recommendation machine 20 according to this embodiment has a recommendation engine with multiple different algorithms, including, for example, a novelty engine, a repetition engine, a periodicity engine, and a preference engine.

[0029] The novelty engine is a recommendation engine designed to encourage first-time purchases. It has the function of recommending new products, such as new products or promotional items, that the user has not previously purchased, thereby contributing to the expansion of their purchase range.

[0030] The repetition engine is a recommendation engine designed to encourage repeat purchases. It recommends products that the user has previously purchased once, contributing to an increase in purchase frequency.

[0031] The periodicity engine is a recommendation engine designed to encourage users to make purchases three or more times. It recommends products that a user has previously purchased two or more times, contributing to increased purchase frequency. Based on the user's purchase history of repeatedly purchased items, the periodicity engine identifies the purchase cycle (purchase interval) of those items and recommends them when the purchase cycle (e.g., a regular week) arrives, encouraging repeat purchases. Product recommendations by the periodicity engine can also be seen as a function to prevent users from forgetting to buy cyclical items.

[0032] The preference engine is a recommendation engine designed to encourage users to purchase products that match their preferences. In the case of the preference engine, recommended products can include both new products and products the user has previously purchased. For example, based on user information such as preferences, age, and family, and / or preference information based on the user's purchase history, it can recommend matching new products (situations where you want to encourage first-time purchases) and products the user has previously purchased (situations where you want to encourage repeat purchases), either alone or in combination with other novelty engines or periodicity engines.

[0033] Figure 5 is a diagram (part 2) illustrating the recommendation engine according to this embodiment. The recommended products in the novelty engine are new products, while the recommended products in the repetition engine and periodicity engine are products that have been used before. The recommendation machine 20 calculates a purchase likelihood score and a priority based on the score for each product from among the multiple recommended products for each engine, and recommends products with higher priority to be displayed more frequently based on the calculation results shown in Figure 5 (the recommendation priority list for each recommendation engine). The score is calculated comprehensively by combining various parameters, such as user preferences (preference engine), as well as the product's market sales (popularity), time elapsed since release, whether it is a staple product, seasonality, inventory level, and promotion level (a weight value indicating the degree to which the delivery service provider particularly wants to sell the product).

[0034] Figure 6 is a diagram (part 3) illustrating the recommendation engine according to this embodiment. The recommendation processing of the recommendation engine 20 will be explained using the following model case.

[0035] Step S1: The recommendation engine 20 recommends product A, a new product, based on the novelty engine (or preference engine). At this point, the user does not purchase the new product (week n).

[0036] Step S2: The recommendation engine 20 recommends product A again based on the novelty engine (or preference engine). At this time, the user is considered to have purchased the new product (week n+1). Information about the purchased product A, along with the purchase date and time, is recorded in the purchase history DB as the first purchase history.

[0037] Step S3: Recommendation engine 20 recommends product A from the experienced products (purchased only once in the past) based on the iteration engine. Assume that the user did not purchase the new product at this time (week n+2).

[0038] Step S4: Based on the repetition engine, the recommendation engine 20 recommends product A from the experienced products (purchased only once in the past). At this time, the user is considered to have purchased the new product (week n+3). Information about the purchased product A is recorded in the purchase history DB as the second purchase, along with the purchase date and time. The recommendation engine 20 also determines that the purchase interval (purchase cycle) for product A for that user is 2 weeks based on the purchase history DB for the first purchase date and time (week n+1) and the second purchase date and time (week n+3), and stores the information of the user, product A, and purchase cycle in association.

[0039] Step S5: Based on the cycle engine, the recommendation engine 20 recommends product A from the experienced products (purchased at least twice in the past) for which this week (this week) is the purchase cycle (week n+5). Note that in week n+4, the recommendation engine 20 does not recommend product A, which is not the purchase cycle. In week n+4, the recommendation engine 20 should recommend some other product, such as another product, that is the purchase cycle for that week.

[0040] Step S6: Based on the cycle engine, the recommendation engine 20 recommends product A from among the experienced products (purchased at least twice in the past) for which this week (this week) is the purchase cycle (week n+7). In this way, the cycle engine recommends product A at periodic timings when the user is highly likely to purchase product A, thereby leading to regular purchases of product A.

[0041] <Online shopping site for home delivery> The recommended products according to this embodiment are dynamically displayed on the e-commerce site for home delivery online shopping, based on the remaining time until the order deadline, i.e., the current date and time and the order deadline. This will be explained in detail below with reference to an example of the e-commerce site screen. The e-commerce site screen is generated by the home delivery online shopping server 10 and displayed on the screen of the user terminal 40.

[0042] (EC site screen immediately after the order start time) Figure 7A is a diagram illustrating the EC site screen (immediately after the order start time) 1 according to this embodiment. The EC site's top screen immediately after the order start time shown in Figure 7A includes, for example, the current logged-in user 401, the current date and time 402, the order delivery schedule for the current term 403, content 404, and a recommended product display area 405.

[0043] Here, according to the order delivery schedule information or order delivery schedule 403 shown in Figure 3, users can place orders during the order period from 12:00 AM on Tuesdays (order start time) to 12:00 PM on Sundays (order deadline time). Also, the current date and time 402 is "2024 / 10 / 1 (Tue) 14:00", which is immediately after the order start time and there is still plenty of time before the order deadline.

[0044] The recommended product display area 405 shown in Figure 7A includes the first recommended product display area 405a, the second recommended product display area 405b, and the third recommended product display area 405c. The first recommended product display area 405a displays recommended products recommended by the novelty engine, the second recommended product display area 405b displays recommended products recommended by the preference engine, and the third recommended product display area 405c displays recommended products recommended by the repetition engine.

[0045] Figure 7B is a diagram illustrating the EC site screen (immediately after the order start time) 2 according to this embodiment. Compared to Figure 7A, the recommended product display area 405 shown in Figure 7B displays recommended products recommended by the novelty engine, recommended products recommended by the preference engine, and recommended products recommended by the repetition engine, all within a single area. That is, the recommended product display area 405 may be divided into recommended product display areas for each engine, depending on the screen design specifications, or it may be a mixed recommended product display area that does not separate recommended products from each engine.

[0046] Figure 7C illustrates the EC site screen (immediately after the order start time) 3 according to this embodiment. The EC site order cart screen shown in Figure 7C is a screen that displays the items in the user's order cart (shopping basket). The order cart screen also has a fourth recommended product display area 405d, which displays recommended products recommended by the periodicity engine. As described above, the periodicity engine encourages repurchases (repeat purchases) by recommending the product when it is time for a cycle (for example, a cycle week). In particular, on the order cart screen, which is the final confirmation screen (screen just before purchase), the engine recommends any periodic products that the user may have forgotten to buy but have not yet added to their order cart, in order to further improve the purchase frequency and average transaction value.

[0047] Furthermore, from the perspective of improving purchase frequency and unit price, it is desirable that the recommended product display area 405d, which is recommended by the periodic engine, be placed on the shopping cart screen, but it is not necessarily limited to being displayed only on the shopping cart screen. It may also be displayed on the top screen or other screens, taking into account screen space constraints and the display balance of recommended product display areas from other engines.

[0048] (EC site screen just before the order deadline) Figure 8A is a diagram illustrating the EC site screen (just before the order deadline) 1 according to this embodiment. In the EC site screen shown in Figure 8A, the current date and time 402 is "2024 / 10 / 6 (Sun) 10:00", indicating that there is little time left until the order deadline. In other words, the EC site screen shown in Figure 8A is the top screen of the EC site just before the order deadline.

[0049] Comparing the top screen in Figure 7A, which is immediately after the order start time and still has ample time before the order deadline, to the top screen in Figure 8A, the recommended products displayed in the recommended product display area 405a are switched from recommended products recommended by the novelty engine to recommended products recommended by the periodicity engine. In other words, on the top screen immediately before the order deadline, many recommended products recommended by the periodicity engine are displayed.

[0050] Figure 8B is a diagram illustrating the EC site screen (just before the order deadline) 2 according to this embodiment. In the EC site screen shown in Figure 8B, the current date and time 402 is "2024 / 10 / 6 (Sun) 10:00", indicating that there is little time left until the order deadline.

[0051] Comparing the top screen in Figure 7B, which is immediately after the order start time and still has plenty of time before the order deadline, the top screen in Figure 8B displays more recommended products recommended by the periodicity engine in the recommended product display area 405.

[0052] Thus, according to this embodiment, on the EC site screen, the proportion of recommended products recommended by the periodicity engine, based on the amount of time remaining until the order deadline, i.e., the time distance between the current date and time and the order deadline, is displayed more frequently than recommended products recommended by other engines.

[0053] As mentioned above, the periodicity engine encourages repeat purchases by recommending products when a periodicity (e.g., a periodic week) arrives. In particular, on the final confirmation screen (the screen just before purchase), the shopping cart screen, by giving an extra push recommendation of periodic products that the user may have forgotten to buy but haven't yet added to their shopping cart, it is possible to further improve purchase frequency and average transaction value.

[0054] Furthermore, in this embodiment, we focus on the usefulness of the periodicity engine itself, which provides one last push recommendation of items that users tend to forget to buy, and the timing of that recommendation. In particular, by providing one last push recommendation of items that users tend to forget to buy but have not yet added to their shopping cart, just before the order deadline, it is possible to further improve the frequency of purchases and the average purchase price.

[0055] In fact, according to a comparison of A / B test results conducted by the applicant using an actual e-commerce site, actively controlling the display of recurring purchase items (recommended items by the cycle engine) that were not yet in the shopping cart at the last possible time when orders could be placed, close to or just before the order deadline, resulted in an increase in purchase frequency and average transaction value compared to when no such active display control was implemented.

[0056] However, regardless of whether the order deadline is approaching or imminent, simply actively displaying items that are not yet in the shopping cart and are prone to being forgotten could potentially increase the purchase frequency and average price of those items. However, under the constraints of the recommended product display area space or the number of recommended products displayed on the screen, the purchase frequency and average price will be lowered as a result of the reduction in the display of recommended products by the novelty engine and the repetition engine, thus disrupting the optimal purchase cycle in the model case shown in Figure 6. In other words, overall, an improvement in purchase frequency and average price cannot be expected in the long term.

[0057] <Recommended Product Display Control Processing> Figure 9 is a flowchart illustrating the recommended product display control process according to this embodiment. This flowchart is executed when, for example, a user accesses and logs into an e-commerce site, and the delivery online shopping server 10 receives a request from the user terminal 40 to display the e-commerce site screen, and the recommendation machine 20 receives a request from the delivery online shopping server 10 to acquire recommended product information. Furthermore, the following steps (hereinafter referred to as "S") can be realized by having the arithmetic processing unit of the recommendation machine 20 read and execute a program capable of performing the processing.

[0058] S1: The recommendation machine 20 obtains the current date and time information from the clock (timekeeping device).

[0059] S2: Recommendation machine 20 retrieves the order start date and time and order deadline date and time from the order delivery schedule information.

[0060] S3: Recommendation machine 20 determines whether the current date and time is within the order start date and time and the order deadline date and time, thereby determining whether the current date and time is an orderable time. If it is determined that the current date and time is an orderable time, proceed to S4. If it is determined that the current date and time is not an orderable time, proceed to END because it is outside the orderable time.

[0061] S4: Recommendation machine 20 calculates the time interval (remaining time) until the order deadline based on the current date and time and the order start date and time. The remaining time until the order deadline can also be considered the time distance between the current date and time and the order deadline.

[0062] S5: The recommendation machine 20 calculates the display ratio of recommended products based on the time interval (remaining time) until the order deadline, such that when there is little time remaining until the order deadline (the time distance between the current date and the order deadline is small), the display ratio of recommended products recommended by the periodicity engine is higher than the display ratio of recommended products recommended by other engines, compared to when there is a lot of time remaining until the order deadline (the time distance between the current date and the order deadline is large). Recommended products recommended by the periodicity engine are products that have been determined to be in the purchase cycle (e.g., a cycle week) based on the current date and time.

[0063] (Calculation example 1) When the orderable period is divided into two halves at a predetermined date and time. Order start date and time: 2024 / 10 / 1 12:00 Order deadline: 2024 / 10 / 6 12:00 Order availability time: 120 hours Number of recommended products displayed: 14 ·first half Current date and time: 2024 / 10 / 1 12:00 Time remaining until order deadline: 120 hours Novelty Engine Recommended Products: 4 items Recommended products by the preference engine: 3 items Recommended products from the iterative engine: 3 items Recommended products from the periodic engine: 4 items Display rate of recommended products from the periodic engine: 4 / 14 • Second half (within 24 hours remaining until the order deadline) Current date and time: 2024 / 10 / 6 12:00 Time remaining until order deadline: 24 hours Novelty Engine Recommended Products: 0 Recommended products by the preference engine: 3 items Recommended products from the iterative engine: 3 items Recommended products from the periodic engine: 8 items Display rate of recommended products from the periodic engine: 8 / 1

[0064] (Calculation example 2) When the order availability period is divided into multiple predetermined dates and times Order start date and time: 2024 / 10 / 1 12:00 Order deadline: 2024 / 10 / 6 12:00 Order availability time: 120 hours Number of recommended products displayed: 14 • First period Current date and time: 2024 / 10 / 1 12:00 Time remaining until order deadline: 120 hours Novelty Engine Recommended Products: 4 items Recommended products by the preference engine: 3 items Recommended products from the iterative engine: 3 items Recommended products from the periodic engine: 4 items Display rate of recommended products from the periodic engine: 4 / 14 • Second period (within 48 hours remaining until the order deadline) Current date and time: 2024 / 10 / 5 12:00 Time remaining until order deadline: 48 hours Recommended products from the novelty engine: 3 items Recommended products by the preference engine: 2 items Recommended products from the iterative engine: 2 items Recommended products from the periodic engine: 7 items Display rate of recommended products from the periodic engine: 7 / 14 • Third period (within 24 hours remaining until the order deadline) Current date and time: 2024 / 10 / 1 12:00 Time remaining until order deadline: 24 hours Novelty Engine Recommended Products: 0 Recommended products by the preference engine: 2 items Recommended products from the iterative engine: 2 items Recommended products from the periodic engine: 10 items Display rate of recommended products from the periodic engine: 8 / 14

[0065] Furthermore, it can be said that the recommendation machine 20 calculates the "number of displays" for recommended products based on the remaining time until the order deadline, such that when there is little time remaining until the order deadline, the number of recommended products recommended by the periodic engine is greater than the number of recommended products recommended by other engines, compared to when there is a lot of time remaining until the order deadline.

[0066] Needless to say, the above-mentioned calculation examples 1 and 2 are illustrative explanations to facilitate understanding of the S5 process. In reality, the number of recommended products and their display percentage recommended by the periodic engine are dynamically calculated according to the remaining time until the order deadline, using a given calculation formula to satisfy S5.

[0067] S6: The recommendation machine 20 retrieves information on recommended products to be displayed in the recommended product display area from the calculation results (for example, each recommendation priority list in Figure 5) according to the calculated display ratio and sends it to the home delivery online shopping server 10. For example, the information on recommended products includes the product ID, product name, product image, product price, and display position (including display priority) indicating which recommended product display area to display it in.

[0068] As described above, the recommendation machine 20 according to this embodiment increases the display ratio of recommended products recommended by the periodicity engine compared to recommended products recommended by other engines when there is little time remaining until the order deadline on an e-commerce site for home delivery shopping, compared to when there is a lot of time remaining until the order deadline. This makes it possible to further improve purchase frequency and average transaction value by actively recommending periodic products that have been forgotten and have not yet been added to the shopping cart, in order to give customers one last push when there is little time remaining until the order deadline, just before the deadline. In other words, the regular home delivery product recommendation system 100 according to this embodiment makes it possible to further improve personalized recommendation technology, and in one respect, to improve customer convenience and increase average transaction value.

[0069] The following points will also be mentioned. The periodic products according to this embodiment are different from regular subscription products that users reserve to purchase weekly, monthly, or on a specified date. In the case of regular subscription products, the order and purchase are automatically placed on the purchase date specified by the user, without requiring any operation of the user's shopping cart.

[0070] • In S6, the recommendation machine 20 can retrieve product information from the online shopping server 10 to exclude products already in the shopping cart from the recommendations, so that the recommended products displayed in the recommended product display area do not overlap with products already in the shopping cart. Alternatively, if the online shopping server 10 receives a recommended product from the recommendation machine 20 that overlaps with a product already in the shopping cart, it may retrieve a different recommended product.

[0071] The recommendation machine 20 can perform the calculation process for recommended products (for example, the process of creating and updating the priority recommendation list shown in Figure 5) at times such as when a user accesses and logs into the e-commerce site, or when the delivery online shopping server 10 receives a request from the user terminal 40 to display the e-commerce site screen.

[0072] However, the timing of the recommended product calculation process is not limited to these times. For example, from the perspective of reducing the load cost associated with increasing the calculation frequency, the calculation may occur before the timing when the user accesses and logs into the EC site, or before the timing when the delivery online shopping server 10 receives a request from the user terminal 40 to display the EC site screen. Alternatively, the timing may be hourly, daily, weekly, or term-based. Even if the calculation is performed before the timing when the user accesses and logs into the EC site, or before the timing when the delivery online shopping server 10 receives a request from the user terminal 40 to display the EC site screen, if there are calculation results (for example, the recommendation priority list in Figure 5) available at that time, in S6 the recommendation machine 20 will retrieve a number of products in order of priority corresponding to the display ratio for each recommendation engine from that recommendation priority list, and send them to the delivery online shopping server 10 as information on the recommended products to be displayed in the recommended product display area. For example, in the calculation example 1 described above, from the recommendation priority list, a total of 4 products with priority levels 1 to 4 according to the periodicity engine are obtained in the first half, and a total of 8 products with priority levels 1 to 8 according to the periodicity engine are obtained in the second half, as information on the recommended products to be displayed in the recommended product display area.

[0073] While the present invention has been described with specific examples in the form of preferred embodiments, it is clear that various modifications and changes can be made to these examples without departing from the broad spirit and scope of the invention as defined in the claims. In other words, the details of the examples and the accompanying drawings should not be construed as limiting the present invention. [Explanation of Symbols]

[0074] 10 Home Delivery Online Shopping Server 20 Recommendation Machines 30 DB 40 User terminals 50 Networks 100 Home Delivery Product Recommendation System 101 Current Date and Time Acquisition Unit 102 Order Date and Time Acquisition Section 103 Time interval calculation unit (remaining time calculation unit) 104 Product Recommendation Department 105 Display amount calculation section

Claims

1. A product delivery recommendation device for products for which a predetermined order delivery schedule has been set, A means for obtaining information about the current date and time, An order date and time acquisition means for acquiring information on the order start date and time and the order deadline date and time for the aforementioned product, A time interval calculation means for calculating the time interval between the current date and time and the order deadline date and time, A product recommendation means that recommends recommended products based on the user's past purchase history of the aforementioned products and the current date and time, A display quantity calculation means that calculates the number or percentage of the recommended products to be displayed in the recommended product display area according to the aforementioned time interval, A home delivery product recommendation device characterized by having [a certain feature].

2. The aforementioned display quantity calculation means is The shorter the aforementioned time interval, the greater the number or proportion of recommended products to be displayed in the recommended product display area. A home delivery product recommendation device according to claim 1, characterized by the above.

3. The aforementioned display quantity calculation means is In the case of the first time interval, calculate the first number or first percentage of the recommended products to be displayed in the recommended product display area. In the case of a second time interval shorter than the first time interval, calculate a second number greater than the first number or a second percentage greater than the first percentage of the recommended products to be displayed in the recommended product display area. A home delivery product recommendation device according to claim 1, characterized by the above.

4. The aforementioned product recommendation means is Based on the user's past purchase history of the said product, the purchase cycle of the said product for the said user is identified, and the product for which the current date and time corresponds to the purchase cycle is recommended. A home delivery product recommendation device according to claim 1, characterized by the above.

5. The recommended products displayed in the aforementioned recommended product display area will not be duplicates of products already in the shopping cart. A home delivery product recommendation device according to claim 1, characterized by the above.

6. Computers, A means for obtaining information about the current date and time, An order date and time acquisition means for acquiring information on the order start date and time and order deadline date and time for products for which a predetermined order delivery schedule has been set, A time interval calculation means for calculating the time interval between the current date and time and the order deadline date and time, A product recommendation means that recommends recommended products based on the user's past purchase history of the aforementioned products and the current date and time, A display quantity calculation means that calculates the number or percentage of the recommended products to be displayed in the recommended product display area according to the aforementioned time interval, A home delivery product recommendation program designed to function as such.

Images