Information processing systems, information processing methods, and programs

Abstract

This invention provides an information processing system, information processing method, and program that can contribute to reducing reliance on individual expertise in ordering operations at each store. [Solution] In the acquisition step, the information processing device acquires sales performance indicators for each store and each product. In the selection step, for each store and each product, based on the sales performance indicators for that product, it determines whether or not to select a demand forecasting algorithm from among multiple algorithms as the algorithm to be used for ordering that product, thereby selecting a recommended algorithm. In the ordering step, it executes the ordering process using the recommended algorithm. The multiple algorithms include a demand forecasting algorithm that determines the order quantity based on demand forecasts derived from past sales performance, and a conditional algorithm that determines the order quantity based on whether past sales or inventory levels meet certain conditions.

Description

Technical Field

[0001] The present disclosure relates to an information processing system, an information processing method, and a program.

Background Art

[0002] A system for supporting the ordering operation of products has been proposed so that the ordering operation can be performed without relying on the experience or intuition of the person in charge. For example, Patent Document 1 describes an order processing support system that groups some or all of a plurality of items based on past shipment performance data and sets an ordering method for each item based on the group to which it belongs.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, in a plurality of stores with different sales scales and customer groups, the appropriate ordering method may differ for each store. However, the system described in Patent Document 1 above cannot support the selection of the optimal ordering method for each store unit, and there is room for improvement.

[0005] An object of the present disclosure is to provide an information processing system, an information processing method, and a program that can contribute to the depersonalization of the ordering business for each store in view of the above problems.

Means for Solving the Problems

[0006] An information processing system according to one aspect of this disclosure comprises one or more processors and memory. The one or more processors are capable of performing the following steps: an acquisition step in which sales performance indicators are acquired for each store and each product; a selection step in which, for each store and each product, a recommended algorithm is selected by determining whether or not a demand forecasting algorithm should be selected from among a plurality of algorithms as the algorithm to be used for ordering the product, based on the sales performance indicators of that product, the plurality of algorithms include a demand forecasting algorithm that determines the order quantity based on demand forecasts based on past sales performance and a conditional algorithm that determines the order quantity based on whether past sales or inventory quantities meet certain conditions; and an order step in which an order processing is performed using the recommended algorithm.

[0007] An information processing method according to one aspect of this disclosure is a method by which an information processing system performs each of the steps described above.

[0008] A program according to one aspect of this disclosure is a program that causes a computer having one or more processors and memory to perform each of the steps described above. [Effects of the Invention]

[0009] This disclosure provides an information processing system, information processing method, and program that can contribute to reducing reliance on individual expertise in ordering operations at each store. [Brief explanation of the drawing]

[0010] [Figure 1] This is a block diagram showing the overall structure of the information processing system. [Figure 2] This is a block diagram showing the hardware configuration of an information processing device. [Figure 3] Block diagram showing the hardware configuration of headquarters terminals and store terminals. [Figure 4] This is a block diagram showing the functional configuration of the control unit of an information processing device. [Figure 5]This is a sequence diagram showing the first information processing flow. [Figure 6] This figure shows an example of the data structure of a product database. [Figure 7] This figure shows an example of the data structure of a sales performance database. [Figure 8] This is a flowchart showing the selection process flow. [Figure 9] This is a sequence diagram showing the second information processing flow. [Figure 10] This figure shows an example of a confirmation screen. [Figure 11] This figure shows an example of a confirmation screen. [Figure 12] This figure shows an example of a confirmation screen. [Figure 13] This figure shows an example of a confirmation screen. [Modes for carrying out the invention]

[0011] Embodiments of the present disclosure will be described in detail below with reference to the drawings. In each drawing, the same or corresponding elements are denoted by the same reference numerals, and redundant explanations will be omitted where necessary for clarity.

[0012] 1. Hardware Configuration This section describes the hardware configuration of the information processing system 1 according to this embodiment. Figure 1 is a block diagram showing the overall configuration of the information processing system 1 according to Embodiment 1. In the following description, "processor" is synonymous with "circuitry" composed of a central processing unit, etc.

[0013] 1.1 Information Processing System 1 The information processing system 1 is a computer system that manages the sales performance of products for each store of an enterprise and supports and manages the ordering operations of products. The information processing system 1 is used, for example, in the ordering operations of products in retail stores such as supermarkets, drugstores, convenience stores, or home centers. In addition, it can also be applied to the procurement management of food ingredients in a restaurant chain or the replenishment ordering of parts or materials in each factory of a manufacturing company. The information processing system 1 includes an information processing device 2, a head office terminal 3, and a store terminal 4. The information processing device 2, the head office terminal 3, and the store terminal 4 are communicably connected to each other via a network NW such as the Internet or a LAN (Local Area Network).

[0014] 1.2 Information Processing Device 2 The information processing device 2 is a computer such as a server that manages the sales performance of products for each store of an enterprise and supports and manages the ordering operations of products. The information processing device 2 stores and accumulates product data and the sales performance for each store obtained based on the instructions of the head office terminal 3 operated by the head office user described later in the storage unit 22 described later. Next, the information processing device 2 sets the ordering mode for each product based on the instructions of the head office terminal 3. Then, for products whose ordering mode is the automatic ordering mode, the information processing device 2 performs an ordering process based on the selected algorithm for each store, and for products whose ordering mode is the manual ordering mode, the information processing device 2 performs an ordering process based on the input from the store terminal 4 described later. Note that the sales performance of products for each store of the enterprise may be stored in the storage unit 22 with files separated for each store, or may be stored in the storage unit 22 in a format where the sales performance of products for each store is associated on one file.

[0015] FIG. 2 is a block diagram showing the hardware configuration of the information processing device 2 according to Embodiment 1. The information processing device 2 includes a control unit 21, a storage unit 22, and a communication unit 23, and these components are electrically connected to each other via a communication bus 26 inside the information processing device 2.

[0016] The control unit 21 performs processing and control of the overall operation related to the information processing device 2. The control unit 21 is a processor, such as a central processing unit (CPU). The control unit 21 realizes various functions related to the information processing device 2 by reading predetermined programs stored in the memory unit 22. That is, information processing instructions stored in the memory unit 22 can be executed as various functional units included in the control unit 21 by being specifically realized by the control unit 21, which is an example of hardware. The functional configuration will be described in more detail in the next section. Note that the control unit 21 is not limited to being a single unit, and may be implemented with multiple control units 21 for each function, or a combination thereof.

[0017] The storage unit 22 is a storage device including a non-temporary computer-readable medium or a physical storage medium, and stores various types of information as defined above. The storage unit 22 can be implemented, for example, as a storage device such as a solid-state drive (SSD) that stores various programs related to the information processing device 2 executed by the control unit 21, or as a memory such as random access memory (RAM) that stores temporarily necessary information (arguments, arrays, etc.) related to program calculations. The storage unit 22 stores various programs, variables, etc. related to the information processing device 2 executed by the control unit 21.

[0018] The communication unit 23 is a communication interface for connecting to the network NW.

[0019] 1.3 Headquarters Terminal 3 Headquarters terminal 3 is a computer terminal operated by a headquarters user. A headquarters user is, for example, a user of a headquarters that oversees multiple stores of a company. Headquarters terminal 3 can be a smartphone, tablet, personal computer, or other communication terminal capable of input / output. Headquarters terminal 3 transmits product data or sales performance received through operations by the headquarters user to the information processing device 2 via the network NW. Headquarters terminal 3 also provides instructions to the information processing device 2 to set the order mode for each product.

[0020] Figure 3(A) is a block diagram showing the hardware configuration of the headquarters terminal 3 according to Embodiment 1. The headquarters terminal 3 comprises a control unit 31, a storage unit 32, a communication unit 33, an input unit 34, and a display unit 35, and these components are electrically connected within the headquarters terminal 3 via a communication bus 36. The control unit 31 is a processor such as a CPU. The hardware configuration of the control unit 31, storage unit 32, and communication unit 33 is substantially the same as that of the control unit 21, storage unit 22, and communication unit 23 in the information processing device 2 described above, so a detailed explanation is omitted.

[0021] The input unit 34 may be included in the housing of the headquarters terminal 3, or it may be an external unit. For example, the input unit 34 may be integrated with the display unit 35 and implemented as a touch panel. Of course, instead of a touch panel, switch buttons, a mouse, a QWERTY keyboard, etc., may be used. In other words, the input unit 34 receives operation input made by the headquarters user. This input is transmitted as a command signal to the control unit 31 via the communication bus 36, and the control unit 31 can perform predetermined controls and calculations as needed.

[0022] The display unit 35 may be included in the housing of the headquarters terminal 3, for example, or it may be an external unit. The display unit 35 displays a graphical user interface (GUI) screen that can be operated by the headquarters user. Preferably, the display unit 35 uses a display device such as a CRT display, liquid crystal display, organic EL display, and plasma display, depending on the type of headquarters terminal 3.

[0023] 1.4 Store Terminal 4 Store terminal 4 is a computer terminal operated by a store user within the store. For example, a store user may be a store manager who oversees ordering operations for that store, sales floor staff who perform ordering work on a departmental basis, field staff who handle the practical aspects of order processing, or an area manager who manages multiple stores. Store terminal 4 can be a smartphone, tablet, personal computer, or other communication terminal capable of input / output. Store terminal 4 performs actions requested by the information processing device 2, such as confirming, correcting, or entering new order quantities by the store user, and transmits the results to the information processing device 2. The information processing device 2 then confirms the order quantities.

[0024] Figure 3(B) is a block diagram showing the hardware configuration of the store terminal 4 according to Embodiment 1. The store terminal 4 comprises a control unit 41, a storage unit 42, a communication unit 43, an input unit 44, and a display unit 45, and these components are electrically connected within the store terminal 4 via a communication bus 46. The hardware configuration of the control unit 41, storage unit 42, communication unit 43, input unit 44, and display unit 45 is substantially the same as that of the control unit 31, storage unit 32, communication unit 33, input unit 34, and display unit 35 in the headquarters terminal 3 described above, so a detailed explanation is omitted.

[0025] 2. Functional Configuration This section describes the functional configuration of Embodiment 1, particularly the functional configuration of the information processing device 2. The information processing method described later is executed by the information processing device 2. Figure 4 is a block diagram showing the functional configuration of the control unit 21 of the information processing device 2. The control unit 21 implements the functions of the registration unit 210, setting unit 211, acquisition unit 212, selection unit 213, and order processing unit 214 by executing a program.

[0026] As a first registration step, the registration unit 210 obtains product data from the headquarters terminal 3 and registers the product data in the product database T1, which will be described later. As a second registration step, the registration unit 210 obtains sales performance data for each product from the headquarters terminal 3 and registers it in the sales performance database T2, which will be described later.

[0027] The setting unit 211, as a setting step, sets each product to either manual ordering mode or automatic ordering mode. Manual ordering mode is a mode in which the number of items to be ordered for the product is determined by manual operation by a headquarters user or a store user. Automatic ordering mode is a mode in which the number of items to be ordered for the product is determined using at least one of several algorithms. Specifically, the setting unit 211 sets the ordering mode for each product in accordance with the type of ordering mode received from the headquarters terminal 3. Furthermore, it is preferable that the setting unit 211 sets the ordering mode for each store and each product in accordance with the type of ordering mode that is received, indicating whether it is manual ordering mode or automatic ordering mode. This makes it possible to set the type of ordering mode according to the characteristics of each store and each product.

[0028] The acquisition unit 212, as an acquisition step, acquires sales performance data for each store and each product from the sales performance database T2, and based on this, acquires sales performance indicators for each store and each product. The sales performance indicators are indicators based on the sales performance of each product.

[0029] The selection unit 213 performs the following selection steps for products set to automatic ordering mode. As a selection step, the selection unit 213 selects a recommended algorithm by determining, for each store and each product, whether or not to select a demand forecasting algorithm from among multiple algorithms as the algorithm to be used for ordering that product, based on the sales performance indicators of that product. The multiple algorithms include demand forecasting algorithms and conditional algorithms. Note that the demand forecasting algorithm and conditional algorithms may each have multiple algorithms. For example, the selection unit 213 may select a recommended algorithm from among the first demand forecasting algorithm, the second demand forecasting algorithm, the first conditional algorithm, and the second conditional algorithm to determine the order quantity of a single product at a single store, based on the sales performance indicators of that product.

[0030] The order processing unit 214 executes the order processing using a recommended algorithm as the order step. Specifically, the order processing unit 214 generates an action item related to ordering for each product and presents the action item to the store user. Furthermore, it is preferable that the order processing unit 214 generates an action item related to ordering for each store and each product and presents the action item to the store user of the target store. An action item is an action that the store user is required to confirm or input when placing an order. The order processing unit 214 then determines the order quantity based on the execution of an action from the store terminal 4 in manual ordering mode, and determines the order quantity based on the order quantity determined by the recommended algorithm in automatic ordering mode, and performs the order processing. Note that the automatic ordering mode may include a step in which the store user confirms or corrects the order. In addition, in manual ordering mode, the order quantity may be determined and the order processing performed when the first store user inputs the order quantity as the execution of the first action item at the first store terminal, and the second store user approves the input of the first store user as the execution of the second action item at the second store terminal.

[0031] 3. Operation of Information Processing Device 2 Section 3 will describe the flow of information processing performed by the information processing device 2, with reference to the diagram. The information processing method includes a first information processing step and a second information processing step.

[0032] 3.1 Overview of Information Processing Section 1 First, we will explain the overview of the first information processing performed by Information Processing System 1. The first information processing involves the process from registering product data to selecting an automatic ordering algorithm. Figure 5 is a sequence diagram showing the first information processing flow. First, the headquarters terminal 3 sends a product registration request to the information processing device 2 (S101). At this time, the headquarters terminal 3 sends product data related to the product to be registered to the information processing device 2 along with the registration request. The registration unit 210 of the information processing device 2, upon receiving the registration request, registers the product data in the product database T1, associating it with the product (S102: first registration step).

[0033] Next, the headquarters terminal 3 sends a request to the information processing device 2 to register sales performance (S103). At this time, the headquarters terminal 3 also sends the sales data to be registered, such as POS (Point of Sales) data, to the information processing device 2 along with the registration request. The registration unit 210 of the information processing device 2, upon receiving the registration request, registers the sales performance, which is an aggregate of POS data, in the sales performance database T2, associating it with the product and store (S104: second registration step). Note that the POS data is not limited to the headquarters terminal 3, but may also be sent from the store terminal 4 or other POS terminals. Furthermore, the sales data is not limited to POS data and may include data such as the daily sales volume for each store and each product, or the daily number of customers for each store. In addition, the purchase history may include the PI value, which is the purchase index per 1000 customers passing through the register, for each product.

[0034] Next, the headquarters terminal 3 sends a request to the information processing device 2 to set the order mode (S105). Upon receiving the setting request, the setting unit 211 of the information processing device 2 identifies products for which switching to automatic order mode is recommended (S106). The setting unit 211 then controls the display unit 35 of the headquarters terminal 3 so that the order mode setting screen can be displayed (S107). As a result, the headquarters terminal 3 displays the setting screen on the display unit 35. At this time, the setting unit 211 may add recommendation information to the setting screen suggesting that the headquarters user switch to automatic order mode for products that are deemed to be for which switching to automatic order mode is recommended. Note that "the setting unit 211 controls the display unit 35 so that it can be displayed" includes the setting unit 211 sending data related to the above screen to the headquarters terminal 3 and displaying it on the display unit 35 of the headquarters terminal 3, as well as the setting unit 211 sending various data necessary to generate the above screen to the headquarters terminal 3 and generating the screen on the display unit 35. Furthermore, the information processing device 2 may determine whether to recommend switching to automatic ordering mode without receiving a setting request from the headquarters terminal 3.

[0035] The headquarters terminal 3 receives setting operations from the headquarters user and transmits setting information for the ordering mode for each product to the information processing device 2 (S108). The setting unit 211 of the information processing device 2, having received the setting information, sets the ordering mode for each product based on the setting information (S109: setting step).

[0036] Next, the selection unit 213 of the information processing device 2, together with the acquisition unit 212, executes the selection process described later (S110). That is, for each store, the selection unit 213 selects a recommended algorithm based on sales performance indicators for each product set to automatic ordering mode.

[0037] [effect] In this way, the information processing device 2 selects a recommended algorithm for each store and product based on objective indicators. Therefore, since the information processing device 2 can select a recommended algorithm without relying on the experience or intuition of the ordering person, it contributes to the depersonalization and standardization of ordering operations at each store. Furthermore, since supply and demand vary by region and sales strategies differ from store to store, the information processing device 2 can achieve optimal operation according to the characteristics of each store. In addition, this configuration allows for flexible response to special cases such as new stores or experimental stores.

[0038] 3.2 Details of the first information processing step Next, we will explain the details of the first information processing performed by information processing system 1. [First registration step (S102)] In the first registration step, the registration unit 210 registers product data in the product database T1, associating it with the product. The product database T1 is stored in the storage unit 22. Figure 6 shows an example of the data structure of product database T1. Product database T1 has records for each product that associate a product ID T11, a category T12, a sales start date T13, and a unit price T14. In this embodiment, we describe product database T1 for one store, assuming that product database T1 is created for each store. However, the product database may also include a store ID, and product data for each store may be managed in a single database.

[0039] Product ID T11 is information that identifies the product. Category T12 is information representing the category of a product. Category T12 may have a hierarchical structure and may include, for example, major categories and minor categories. For example, a major category indicates the items handled at the sales floor level and is a departmental classification related to the division of sales floor staff or ordering responsibilities. As an example, a major category may be a departmental code in the POS code and may represent produce, meat, fresh fish, prepared foods, or daily necessities. On the other hand, a minor category is a subdivision of the departmental classification and is a classification related to shelf allocation. As an example, a minor category may be a category code in the POS code and may represent pork, tofu, bread, or lactic acid bacteria beverages. The release date T13 is the date on which the product went on sale. The unit cost T14 is the unit cost of that product.

[0040] Although the registration unit 210 receives product data for each product from the headquarters terminal 3, the method of acquiring product data is not limited to this. For example, the registration unit 210 may acquire product data via an API (Application Programming Interface) from an external product management system where product data has already been stored. Alternatively, the registration unit 210 may acquire a CSV file containing aggregated product data for multiple products exported from the external product management system by the headquarters terminal 3 in a batch from the headquarters terminal 3. Furthermore, when acquiring product data in a batch, the registration unit 210 may be configured to determine that records representing the difference since the last acquisition are product data that needs to be newly registered.

[0041] The information processing device 2 manages product data for each product using the product database T1, which can then be used for subsequent second-stage information processing.

[0042] [Second registration step] In the second registration step, the registration unit 210 registers the sales performance of each product for each store in the sales performance database T2. The sales performance database T2 is stored in the storage unit 22. Figure 7 shows an example of the data structure of the sales performance database T2. For each store, the sales performance database T2 has records that associate product ID T21, order date T22, order quantity T23, sales quantity T24, and inventory quantity T25 for each product.

[0043] The order date T22 is the date the product was ordered. Order quantity T23 is the order quantity for that product. Sales quantity T24 represents the actual quantity of the product sold on the day corresponding to the order date, i.e., the quantity sold. The inventory count T25 represents the quantity of goods remaining in stock on the day corresponding to the order date. Furthermore, the sales performance database T2 may also include the number of losses, which indicates the quantity of goods that are no longer in a saleable condition due to damage, deterioration, expiration, or other reasons. Additionally, the sales performance database T2 may also include sales revenue or the number of customers who purchased the goods.

[0044] The information processing device 2 manages the sales performance of each product at each store using the sales performance database T2, and can utilize sales performance indicators based on sales performance for selection processing or subsequent second information processing.

[0045] [Order mode settings (S105~S109)] For products registered for the first time by S102, the setting unit 211 initially sets the ordering mode to manual ordering mode. The setting unit 211 may suggest to the headquarters user that the product be switched to automatic ordering mode once a certain amount of sales data for that product has been accumulated. In other words, in S106, for each product currently set to manual ordering mode, the setting unit 211 determines whether the sales performance indicators meet predetermined conditions to identify products for which a switch to automatic ordering mode is recommended. Then, in S107, the setting unit 211 suggests to the headquarters user that the sales performance indicators meet predetermined conditions and the product is currently set to manual ordering mode be switched to automatic ordering mode. For example, the setting unit 211 may display a screen for setting the ordering mode for each product on the display unit 35 of the headquarters terminal 3, and may place a message or object on that screen prompting the user to switch the aforementioned products to automatic ordering mode.

[0046] Then, in S108, the headquarters terminal 3 may, in response to receiving the headquarters user's acceptance of the order mode switch, transmit setting information to the information processing device 2 indicating that the order mode for the proposed product will be switched to automatic order mode. Upon receiving the setting information, the setting unit 211 may, in S109, switch the order mode for the proposed product from manual order mode to automatic order mode.

[0047] In this way, the information processing device 2 allows users to set the ordering mode for each product. This enables a gradual introduction to the automatic ordering mode. This is particularly effective for new products with limited sales history. Furthermore, allowing discretion on the ground ensures the flexibility of the system.

[0048] Here, the sales performance indicators meeting the predetermined conditions means, for example, that a certain period of time has elapsed since the start of sales, that the sales rate during the predetermined period described later is above a certain value, that the variation in sales volume described later is above a certain value, that the total sales volume or statistical value from the start of sales meets the conditions, or a combination of these. In other words, for products for which a certain amount of sales performance data has been accumulated, the information processing device 2 proposes to the user that they switch to automatic ordering mode. In this manner, the information processing device 2 can broaden the scope of application of automatic ordering mode and further promote the depersonalization and standardization of ordering operations. The information processing device 2 may also automatically switch to automatic ordering mode for products for which the sales performance indicators meet the predetermined conditions, without proposing a switch or obtaining confirmation from the headquarters user. This manner also produces the same effects as described above.

[0049] The sales performance indicators for each product used in the above-mentioned decision to switch products may be aggregated across all stores or for each individual store. In some cases, a product may be initially sold on a trial basis at a limited number of stores, and then expanded to all stores based on its sales performance. In this case, the sales performance indicators used in the above-mentioned decision to switch products may be aggregated across two or more limited stores among the relevant stores.

[0050] Furthermore, the above-mentioned predetermined conditions may further include ensuring that the prediction accuracy is above a certain level when the product is set to automatic ordering mode. Specifically, the above-mentioned predetermined conditions may include that, for products currently set to manual ordering mode, the difference between the predicted order quantity and the actual order quantity, or the difference between the predicted sales quantity (demand forecast) and the actual sales quantity, is below a predetermined value or within a predetermined range (switching condition). The predicted order quantity or predicted sales quantity is the order quantity or sales quantity determined using the recommended algorithm selected when the product is set to automatic ordering mode. In particular, the predicted sales quantity is the sales quantity predicted using the demand forecasting algorithm among several algorithms. Alternatively, the predicted order quantity or predicted sales quantity may be calculated for each selectable algorithm, and the algorithm with the smallest statistical difference from the actual order quantity or sales quantity may be used to determine whether the statistical difference satisfies the predetermined conditions, thereby determining whether to switch to automatic ordering mode. In other words, the information processing device 2 proposes switching to automatic ordering mode when the prediction accuracy of the order quantity in automatic ordering mode is above a certain level. This configuration allows for automation to be promoted at a time of high prediction accuracy, thus preventing ordering errors due to incorrect automation. Furthermore, by having the information processing device 2 determine and propose whether automation should be performed based on objective predictive accuracy, it eliminates the need for decisions to rely on the experience or intuition of the person in charge, thereby further promoting the reduction of reliance on individual expertise.

[0051] Furthermore, in this configuration, for products unsuitable for automated ordering, the information processing device 2 maintains the ordering mode in manual ordering mode. Since such products can be appropriately excluded from automation, the stability of the entire ordering process is ensured. In addition, instead of automating all products uniformly, by gradually switching to automation starting with products that have high prediction accuracy, it is possible to achieve gradual or planned automation while minimizing anxiety and confusion on-site.

[0052] [Selection process (S110)] In S110, the acquisition unit 212 and the selection unit 213 perform the following selection process. Specifically, the acquisition unit 212 acquires sales performance data for each store and each product from the sales performance database T2 and calculates sales performance indicators for each store and each product based on this data (acquisition step). Then, for each store and each product, the selection unit 213 selects a recommended algorithm to be used for ordering that product from among several algorithms based on the sales performance indicators for that product (selection step). At this time, the selection unit 213 selects a recommended algorithm by determining whether or not to select a demand forecasting algorithm as the algorithm to be used for ordering that product. Furthermore, it is preferable that the selection unit 213 decides, based on the sales performance indicators, to use either a demand forecasting algorithm, which is an algorithm based on demand forecasting, or a conditional algorithm, which is a rule-based algorithm that does not use demand forecasting, as the algorithm to be used for ordering that product.

[0053] (Sales performance indicators) The sales performance indicators used in algorithm selection are calculated based on sales performance registered in the sales performance database T2. Specifically, the above-mentioned sales performance indicators are values ​​calculated based on at least one of the following: the number of units sold for a product during a specified period, the sales revenue for a product during a specified period, and the elapsed time since the product's sales began. For example, the above-mentioned sales performance indicators include at least one of the following: the elapsed time since the product's sales began, the sales rate of the product during a specified period, or the variability of sales. The sales rate is the total or statistical value of the number of units sold for that product during a specified period, and may include, for example, the percentage of days during a specified period where the product meets a specified condition (e.g., the number of units sold is above, below, or within a specified range), the average number of units sold per day for that product, the median number of units sold per day for that product, or the minimum number of units sold for that product during a specified period. The sales rate is an indicator that shows how much of the product is sold per day, whether it is selling continuously, or whether there is stable demand. Sales variability refers to the statistical variability of sales over a given period, and can be, for example, the variance, standard deviation, or coefficient of variation obtained by dividing the standard deviation by the mean. Sales variability is an indicator for determining the predictability of order quantities. For example, the sales performance indicators mentioned above may also include predictive accuracy, which indicates the degree of error between the actual sales volume of the product over a given period and the predicted order quantity determined by the algorithm when that algorithm is selected.

[0054] (Specific example of selection process) Specifically, the selection unit 213 selects a recommended algorithm by determining whether or not to select a demand forecasting algorithm as the algorithm to be used for ordering each product set in the automatic ordering mode of each store, based on one of the sales performance indicators. For example, the selection unit 213 decides, based on the sales performance of the product, whether to use a demand forecasting algorithm, which is an algorithm based on demand forecasting, or a conditional algorithm, which is a rule-based algorithm that does not use demand forecasting, as the algorithm to be used for ordering that product. Furthermore, the determination for algorithm selection may be divided into multiple stages. For example, the selection unit 213 makes a first determination based on one of the sales performance indicators for each product set in the automatic ordering mode of each store, and then makes a second determination based on another of the sales performance indicators, and selects a recommended algorithm based on the results of the first and second determinations.

[0055] As an example, the first determination uses the sales rate of a product over a predetermined period, and the second determination uses the variability of sales volume. By considering the sales rate, the selection unit 213 can suppress the impact of extreme sales data and accurately reflect the actual sales frequency. In particular, for products where there are days with extremely low sales rates, the error in demand forecasting tends to be large, so it can be used as an indicator to decide whether to use a demand forecasting algorithm or a conditional algorithm. Furthermore, the tendency of variability in sales volume varies depending on the characteristics of the product. For example, seasonal products or campaign products are seasonal, while fresh produce or dairy products are not. Also, there are products such as umbrellas, hand warmers, or raincoats, where demand is irregular and sudden, resulting in low inventory turnover, but the impact of stockouts is significant. By considering the variability of sales volume, the selection unit 213 can select an algorithm that is appropriate to the characteristics of each product.

[0056] Generally, for products where a certain number of days have passed since the start of sales and stable demand is recognized, a demand forecasting algorithm is recommended. Many products handled by supermarkets meet the above conditions because sales stabilize above a certain level after a certain number of days have passed since the start of sales. In other words, in supermarkets, the recommended algorithm for many products converges to a demand forecasting algorithm. Therefore, in this embodiment, the selection unit 213 selects a recommended algorithm based on sales performance indicators, first considering whether or not to select a demand forecasting algorithm as the recommended algorithm. As will be described in detail later, there are different types of demand forecasting algorithms, and the demand forecasting algorithm that yields the highest accuracy differs depending on the variability of sales. Therefore, by deciding which of the multiple demand forecasting algorithms to use based on the variability of sales, it is possible to achieve a more accurate determination of the order quantity. For example, when the variability of sales meets predetermined conditions, a demand forecasting algorithm using machine learning (learning-type demand forecasting algorithm) may be recommended, and when the predetermined conditions are not met, a statistical-based inventory-type algorithm (statistical-type demand forecasting algorithm) may be recommended.

[0057] In this example, the selection unit 213 selects a conditional algorithm if it does not select a demand forecasting algorithm. This is because for products where a certain number of days have passed since the start of sales but stable demand has not been observed, the error in demand forecasting tends to be large, making an algorithm that determines the order quantity based on rules without performing demand forecasting more suitable. For example, if the selection unit 213 determines that a demand forecasting algorithm is unsuitable based on sales performance indicators, it selects a cell-by-one type conditional algorithm as the recommended algorithm.

[0058] Figure 8 is a flowchart showing the selection process flow shown in S110. Figure 8 describes the flow of determining the recommended algorithm by making a step-by-step determination from three types of algorithms: the first demand forecasting algorithm, the second demand forecasting algorithm, and the conditional algorithm, using two sales performance indicators: sales rate and sales volume variability. First, the acquisition unit 212 acquires sales performance data from the sales performance database T2 for each product set to automatic ordering mode for each store, and calculates sales performance indicators such as sales rate and sales volume variability based on this data (S121). Next, in S122, the selection unit 213 makes a first determination of whether the sales rate of the product during a predetermined period meets the first condition. If the first determination is negative, that is, if the sales rate does not meet the first condition (NO in S122), the selection unit 213 selects the conditional algorithm (S123). On the other hand, if the first determination is positive, that is, if the sales rate satisfies the first condition (YES in S122), the selection unit 213 makes a second determination to determine whether the variability in the number of products sold satisfies the second condition (S124). If the second determination is positive, that is, if the variability satisfies the second condition (YES in S124), the selection unit 213 selects the first demand forecasting algorithm as the recommended algorithm (S125). Alternatively, if the second determination is negative, that is, if the variability does not satisfy the second condition (NO in S124), the selection unit 213 selects the second demand forecasting algorithm as the recommended algorithm (S126). The selection unit 213 then registers the recommended algorithm for ordering for each store and each product (S127).

[0059] In this way, selecting a recommended algorithm through multi-stage evaluation allows for a multifaceted assessment of sales patterns, enabling more appropriate decisions. This makes it possible to select an algorithm that is less dependent on individual expertise and is suited to the characteristics of the product.

[0060] The sales performance indicators used when selecting a recommended algorithm may be defined for each product or store. For example, the information processing device 2 may pre-store the first and second conditions in the storage unit 22 for each store and each product, and use them in the selection process. Furthermore, the sales performance indicators used and the conditions for those sales performance indicators may differ depending on the product category. For example, the information processing device 2 may pre-store the sales performance indicators and conditions to be used for each product category in the storage unit 22, and use them in the selection process. Defining the sales performance indicators and conditions to be used for each product or product category enables flexible control according to the characteristics of the product or product category. Also, defining the conditions to be used for each store allows for adaptation to the demand scale, sales trends, or sales strategies of each store. With uniform conditions, there is a risk of mistakenly identifying a product that happened to sell a little as a target for demand forecasting, which may lead to a decrease in forecasting accuracy or ordering errors. However, this approach prevents misrecognition and overreactions, enabling more appropriate ordering control. Moreover, even if the number of product types and stores increases, the system can be operated while maintaining its overall flexibility and practicality by adjusting the conditions individually.

[0061] [Timing of setting the algorithm] The selection process may be performed periodically or irregularly. Furthermore, the recommended algorithm selected in the selection process may be updated each time an order is placed. For example, the selection unit 213 may execute a selection process for the current order each time the information processing device 2 receives an order start request from the store terminal 4 during the order process. Alternatively, the selection unit 213 may execute a selection process for the next order each time the order process is completed. With this configuration, the recommended algorithm is dynamically selected based on sales performance at the time of ordering, so even if sales change, the optimal algorithm can be selected for each order based on the latest sales performance. It can also respond immediately to seasonal and regional influences.

[0062] Furthermore, the recommended algorithm selected in the selection process may be used continuously until predetermined conditions are met. For example, the selection unit 213 may continue to select the recommended algorithm used in the previous order process as the recommended algorithm for the current order process until at least one of the sales performance indicators meets a predetermined condition. More specifically, for each product, the selection unit 213 may continue to select the recommended algorithm used in the previous order process as the recommended algorithm for the current order process until the sales rate or the variation in the number of units sold for that product since the selection of the recommended algorithm for that product meets a predetermined condition. By using the same recommended algorithm until a certain condition is met, the system load can be reduced. In addition, this configuration can avoid business confusion caused by frequent changes in the recommended algorithm.

[0063] For example, the selection unit 213 may re-select the recommended algorithm in response to the fact that the variation in the number of products sold no longer satisfies the second condition. In this case, the selection unit 213 may propose to the headquarters terminal 3 that the recommended algorithm be changed and perform the re-selection in response to obtaining approval from the headquarters user.

[0064] [Demand forecasting algorithm] Here, the demand forecasting algorithm is an algorithm that determines the order quantity based on demand forecasts derived from past sales performance. For example, the demand forecasting algorithm is a learning-type demand forecasting algorithm that calculates the predicted sales quantity for each store and each product using a trained algorithm that has been trained on past daily sales performance and sales status using machine learning, and then determines the order quantity based on the predicted sales quantity. In this case, the determination of the order quantity based on the predicted sales quantity is a decision method that determines the order quantity from the difference between the predicted sales quantity and the current inventory. The machine learning model used in the learning-type demand forecasting algorithm can be any model that can ultimately determine the order quantity, and can be a regression model, a time series model (e.g., weighted moving average model, exponential smoothing model, moving average model, etc.), a decision tree model, a random forest model, a neural network model, an LLM (Large Language Model), etc., or a combination thereof. Furthermore, the learning-type demand forecasting algorithm may be a combination of a first forecasting model that predicts the number of customers for each store based on past sales performance and sales conditions, and a second forecasting model that calculates the predicted sales volume by multiplying the predicted number of customers by the demand coefficient for each product (the probability of purchase when 1000 customers visit), and then determines the order volume based on the predicted sales volume.

[0065] For example, the first prediction model predicts the number of customers for each store based on past sales performance for that store as a whole, specifically, the number of customers and sales conditions. For example, the first prediction model is a trained model that has learned store information, past date information, past customer numbers, and past sales conditions, and predicts the number of customers for the store on the day to be predicted from input data including the store to be predicted, the date, and sales conditions. The number of customers may be included in the sales performance database T2, calculated from POS data, or calculated by subtracting the average customer spending from the sales included in the sales performance. Also, for example, the machine learning model used in the first prediction model can be determined as appropriate, as described above.

[0066] The second prediction model forecasts demand for each product based on the predicted number of customers. For example, the second prediction model takes information about the product to be predicted, store information, and the predicted number of customers as input data, and outputs the predicted sales volume of that product for that day. The second prediction model may be a machine learning model trained using product information, store information, actual customer numbers, and the sales volume of that product for that day as training data.

[0067] Furthermore, the demand forecasting algorithm may employ a statistical inventory algorithm that statistically determines the order quantity based on past sales performance or inventory history based on past sales performance. A statistical inventory algorithm is, for example, one that determines the order quantity based on the current inventory level and a statistical baseline inventory based on past sales performance, assuming periodic ordering. More specifically, a statistical inventory algorithm is one that determines the order quantity based on a statistical demand forecast based on past sales performance, safety stock, and current inventory. Both learning-based demand forecasting algorithms and statistical inventory algorithms are algorithms that use demand forecasting, but the most suitable algorithm may differ depending on the characteristics of the product.

[0068] Sales information can include, for example, event information. The order processing unit 214 preferably performs demand forecasting in its demand forecasting algorithm that takes into account event information around the target store. In this case, the information processing unit 2 uses the presence or absence of an event, the category of the event, or a rank indicating how much the number of customers will change due to the event as sales information from the store terminal 4 to train the demand forecasting algorithm. The order processing unit 214 may also correct the demand forecast output from the demand forecasting algorithm based on the event information obtained from the store terminal 4.

[0069] Sales information can be, for example, weather information. The order processing unit 214 preferably performs demand forecasting in its demand forecasting algorithm that takes into account weather information around the stores being forecasted. In this case, the information processing unit 2 trains the demand forecasting algorithm using the type of weather, such as sunny, cloudy, or rainy, or a rank indicating how much the number of customers changes depending on the weather, as sales information. The order processing unit 214 may also correct the demand forecast output from the demand forecasting algorithm based on weather information for that area obtained from the store's location information via the internet or the like.

[0070] Furthermore, the order processing unit 214 may determine whether a product being sold for the first time will be affected by the event or weather, and if it is affected, it may correct the predicted sales quantity for each product output from the second prediction model based on the event or weather information.

[0071] The order processing unit 214 then calculates the order quantity based on the predicted sales quantity output from the demand forecasting algorithm.

[0072] [Conditional Algorithms] Conditional algorithms determine order quantities based on whether past sales or inventory levels meet certain conditions. Examples of conditional algorithms include the cell-by-one algorithm and the fixed-quantity ordering algorithm. The cell-by-one algorithm determines the next order quantity based on the most recent sales. The fixed-quantity ordering algorithm determines the order quantity for each product based on a predetermined sales performance indicator when inventory falls below a set level. Since the cell-by-one algorithm and the fixed-quantity ordering algorithm are well-known algorithms, detailed explanations will be omitted.

[0073] 3.3 Overview of Information Processing Section 2 Next, we will explain the overview of the second information processing performed by Information Processing System 1. The second information processing refers to the process from the request to start the order processing to the completion of the order processing. Figure 9 is a sequence diagram showing the second information processing flow. First, the store terminal 4 sends a request to the information processing device 2 to start the order processing (S131). For example, the store terminal 4 may send the above-mentioned request to start the order processing by accepting a login operation from a store user.

[0074] Upon receiving a start request, the order processing unit 214 of the information processing device 2 obtains the order mode and recommended algorithm corresponding to the store, which are determined for each product (S132). Next, the order processing unit 214 calculates the order quantity based on the recommended algorithm for products for which the automatic order mode is set as the order mode (S133). Next, the order processing unit 214 generates an action item for each product, corresponding to the mode set for that product, which relates to ordering that product (S134). At this time, the order processing unit 214 may generate an action item for each product and for each store. Next, the order processing unit 214 presents the action item to the store user by controlling the display unit 45 of the store terminal 4 so that the action item confirmation screen can be displayed (S135). At this time, for products set to automatic order mode, the order processing unit 214 may display the order quantity determined by the recommended algorithm on the action item confirmation screen on the terminal operated by the user, in particular the store terminal 4 operated by the store user.

[0075] The store terminal 4 receives input and confirmation operations from the store user who has viewed the confirmation screen (S136), and transmits the input information and confirmation information to the information processing device 2 (S137). The order processing device 214, having received the input information and confirmation information, confirms the order quantity and executes the order processing based on the confirmed order quantity (S138).

[0076] [effect] In this manner, the order processing unit 214 presents action items to store users, giving them the opportunity to confirm and modify order quantities. This ensures system flexibility. The order processing unit 214 also generates action items according to the order mode. This clarifies the items that the person in charge needs to confirm and input, improving usability, streamlining operations, and preventing omissions. Furthermore, while the order mode is set by a headquarters user, the confirmation of action items and the execution of actions are performed by store users. This configuration allows for the optimization of order operations based on role-sharing. In addition, reducing the authority of store users promotes de-personalization.

[0077] 3.4 Details of the second information processing step Next, we will explain the details of the second information processing performed by information processing system 1. [Action Item] Action items are fields that indicate actions that store users are required to confirm or enter when placing an order. Actions are divided into required actions and optional actions. Required action items indicate actions that must be completed by the store user in order to execute the subsequent order process. Optional action items indicate optional actions that are not required to execute the subsequent order process, but which the store user can confirm or enter.

[0078] For example, for products set to manual ordering mode, the action of entering the order quantity is a required action. For example, for products set to automatic ordering mode, the action of confirming the order quantity is generally an optional action. However, for the above products, if an error occurs in determining the order quantity using the recommended algorithm, the action of requesting confirmation of the cause of the error and subsequent action may become a required action. An example of an error occurring is when at least some of the sales performance indicators for that product are missing, or when the values ​​such as the inventory quantity registered in the sales performance database T2 are inappropriate.

[0079] [Action Item Confirmation Screen] Figures 10, 11, 12, and 13 show examples of action item confirmation screens. As shown in Figure 10, the confirmation screen 60 includes a category list, which is a list of categories of products that can be ordered. Specifically, the confirmation screen 60 has items 61 for each category (e.g., subcategory) included in the product database T1, and each item 61 can be selected by the store user. The confirmation screen 60 may also include an alert object 62. The alert object 62 indicates an alert for the category to which a product with an unprocessed required action item belongs. In other words, the order processing unit 214 generates a category list using the product database T1, and if there is a product with an unprocessed action item among the required action items, it displays an alert along with the category list on the store terminal 4.

[0080] This configuration makes it easier for users to check required action items that have not yet been processed, categorized by type, which in turn further improves work efficiency.

[0081] When a store user selects any of the items 61, the store terminal 4 transitions the display screen to the confirmation screen 70 shown in Figure 11. The confirmation screen 70 includes a list of orderable products belonging to the selected category, along with a list of corresponding action items 72. Each action item 72 is surrounded by an order mode tag 73 indicating the order mode for the corresponding product. For products that require mandatory actions such as inventory quantity correction, if the mandatory action has not yet been processed, the action item 72 may include an action tag 74. For products that require the manual order mode to input the order quantity, if the mandatory action has not yet been processed, the action item 72 may include an action tag 75. The action tags 74 and 75 may be configured in a way that allows recognition of at least one of the type of action and the processing status of the action.

[0082] Furthermore, the confirmation screen 70 may include tabs 71 for filtering action items 72 based on at least one of the action type, order mode, and action processing status. In this figure, the tab 71 labeled "Requires Confirmation" is selected, which causes the required action items to be displayed on the store terminal 4. In this way, the order processing unit 214 generates a list of essential action items from among the action items necessary to execute the order processing, and displays this list on the store terminal 4.

[0083] This configuration makes it easier for store users to see the essential actions they need to take that day, thereby further improving operational efficiency. Furthermore, by eliminating the requirement for confirmation or approval in the automatic ordering mode, operational efficiency can be further enhanced.

[0084] The tags used for filtering are not limited to the examples above; they may also be category tags from a different perspective of the product, or tags for the department that handles the product. Furthermore, filtering settings may be automatically configured according to the department of the store user performing the operation. The store user's department is linked to their account.

[0085] In the confirmation screen 70 shown in Figure 11, when a store user selects an action item 72 with an order mode tag 73 indicating manual ordering mode, the store terminal 4 transitions the display screen to the confirmation screen 80 shown in Figure 12. The confirmation screen 80 is an input screen for the order quantity of a product set to manual ordering mode. On the confirmation screen 80, tab 81 for entering the order quantity is selected. The confirmation screen 80 includes a predicted sales quantity 83 and an input area 84 for entering the order quantity. The predicted sales quantity 83 is an estimate of the predicted sales quantity calculated using a predetermined prediction formula based on past order quantities, sales quantities, or current inventory quantities. Alternatively, the predicted sales quantity 83 may be the predicted sales quantity calculated using one of the algorithms in automatic ordering mode. In this configuration, store users can determine the order quantity for the day while referring to the predicted sales quantity. In addition to tab 81 for entering the order quantity, the confirmation screen 80 may also have tabs for checking past order quantities or sales quantities, checking inventory quantities, and checking product data. In this configuration, store users can determine the order quantity for the day while referring to recent order quantities, inventory quantities, and sales quantities, etc. The store terminal 4 then transmits the input information regarding the order quantity received from the store user to the information processing device 2.

[0086] Furthermore, in response to a store user performing an input action for the order quantity on the store terminal 4, the order processing unit 214 may update the processing status of the action and remove the action item 72 for that product from the "To be confirmed" tab 71.

[0087] Furthermore, in the confirmation screen 70 shown in Figure 11, when a store user selects an action item 72 with an order mode tag 73 indicating automatic ordering mode, the store terminal 4 transitions the display screen to the confirmation screen 90 shown in Figure 13. In the confirmation screen 90, a tab 91 for confirming and correcting the order quantity is selected. The confirmation screen 90 includes a predicted sales quantity 93 and an input area 94 for correcting the order quantity determined by the recommendation algorithm. The input area 94 may temporarily reflect the order quantity determined by the recommendation algorithm, but this order quantity can be corrected by the store user. The predicted sales quantity 93 is an estimate of the predicted sales quantity calculated using a predetermined prediction formula based on past order quantities, sales quantities, or current inventory quantities. In this manner, if the order quantity calculated by the recommendation algorithm is inappropriate, such as not being a realistic quantity, the store user can correct the order quantity for the day while referring to the predicted sales quantity. If inventory correction is necessary, an alert object 92 is attached to the tab 91 for checking the inventory quantity. In this manner, the store user can grasp at a glance what needs to be done when ordering this product. In response to a store user modifying the inventory count, the order processing unit 214 may recalculate the order quantity using the recommended algorithm.

[0088] Even if the action item is an optional item, the order processing unit 214 may display a screen on the headquarters terminal 3 for confirming and modifying the order quantity, as shown in the confirmation screen 90. In this case, the order processing unit 214 may accept modifications from store users within a predetermined modification period. The store terminal 4 then transmits the input information regarding the modification of the order quantity received from the store user, or confirmation information indicating that the order quantity has been confirmed, to the information processing unit 2.

[0089] [Order Processing (S138)] In S138, the order processing unit 214 determines the order quantity based on the input information and confirmation information, and executes the order processing based on the determined order quantity. At this time, the order processing unit 214 may directly place an order with the wholesaler by transmitting order data such as company ID, store ID, product ID, delivery date, unit price, and order quantity to a device managed by the wholesaler. Alternatively, the order processing unit 214 may indirectly place an order with an external ordering system by providing the order data via an API, or by converting the data to a predetermined file format such as CSV format and uploading the file. At this time, the order processing unit 214 may use different file formats for the files input to the ordering system depending on the type of ordering system. Note that file format refers to the data structure, encoding method, or format of the file.

[0090] While the present disclosure has been described above with reference to embodiments, it is not limited thereto. Various modifications to the structure and details of the present disclosure are possible, which can be understood by those skilled in the art within the scope of the invention.

[0091] <Variation> For example, in the embodiment described above, the setting of the order mode in the first information processing is performed by a headquarters user, while the confirmation of the action item and the execution of the action in the second information processing are performed by a store user. However, both steps may be performed by the same user. As an example, the confirmation of the action item and the execution of the action in the second information processing may be performed by a headquarters user.

[0092] In this case, the manual ordering mode may include a planned ordering mode that processes orders for multiple stores in a single batch. Specifically, the ordering processing unit 214 determines the allocation ratio of orders between stores in response to receiving order quantity inputs from headquarters users for products set in planned ordering mode. At this time, the ordering processing unit 214 may perform demand forecasting for each store using a demand forecasting algorithm and determine the allocation ratio based on the forecasted sales volume. In this configuration, ordering operations can be completed at headquarters, thereby reducing the burden of ordering operations at stores and promoting the depersonalization of ordering operations.

[0093] Furthermore, after determining the allocation ratio of order quantities between stores, the order processing unit 214 may control the system so that store users can view an action item to confirm the order quantity for products set in the planned order mode. In addition, the order processing unit 214 may control the system so that store users can modify the order quantity indicated by the action item during the modification period. In this configuration, each store can concentrate on the task of confirming the allocated order quantity, and the task of determining the order quantity at each store can be omitted.

[0094] While Embodiments 1 and 2 describe a case where the information processing device 2 is a single device, some or all of the components of the information processing device 2 may be realized by multiple information processing devices or circuits. Furthermore, the processor in each embodiment may be synonymous with circuits composed of a central processing unit or the like. In this case, the multiple information processing devices or circuits may be centrally located or distributed. For example, the information processing devices or circuits may be realized in a form where each is connected via a communication network, such as a client-server system or a cloud computing system. Also, the functions of the information processing device 2 may be provided in SaaS (Software as a Service) format.

[0095] Some or all of the above embodiments may also be described as follows, but are not limited to the following: (Note 1) An information processing system comprising one or more processors and memory, The one or more processors mentioned above are capable of performing the following steps: In the acquisition step, sales performance indicators are obtained for each store and each product. In the selection step, for each store and each product, a recommended algorithm is selected by determining whether or not to select the demand forecasting algorithm from among several algorithms as the algorithm to be used for ordering that product, based on the aforementioned sales performance indicators for that product. The aforementioned plurality of algorithms include a demand forecasting algorithm that determines the order quantity based on demand forecasts derived from past sales performance, and a conditional algorithm that determines the order quantity based on whether past sales or inventory levels meet certain conditions. In the ordering step, the ordering process is executed using the recommended algorithm. Information processing system. (Note 2) The aforementioned processor 1 or more A further step can be performed to display the order quantity determined by the aforementioned recommended algorithm on the user terminal operated by the user. The information processing system described in Appendix 1. (Note 3) The aforementioned sales performance indicator is a value calculated based on at least one of the following: the number of units sold of the product during a predetermined period, the sales revenue of that product, and the elapsed time since the start of sales of that product. The information processing system described in Appendix 1 or 2. (Note 4) The conditions for the sales performance indicators used when selecting the recommended algorithm are determined for each product or store. An information processing system as described in any one of the items 1 to 3 of the appendix. (Note 5) The aforementioned sales performance indicator includes the degree of sales of the product and the variability in the number of units sold during the predetermined period. In the selection step, the one or more processors A first determination is made as to whether the sales rate during the predetermined period meets the first condition. A second determination is made as to whether the variation in the number of sales of the aforementioned product satisfies the second condition. Based on the results of the first and second determinations, the recommended algorithm is selected. An information processing system as described in any one of the items 1 to 4 of the appendix. (Note 6) The aforementioned sales performance indicator includes the degree of sales of the product and the variability in the number of units sold during the predetermined period. In the selection step, the one or more processors For each product, the recommended algorithm used in the previous order processing is continued to be selected as the recommended algorithm for the current order processing until the sales rate or sales volume variation since the selection of the recommended algorithm for that product meets a predetermined condition. An information processing system as described in any one of the items 1 to 5 of the appendix. (Note 7) The aforementioned processor 1 or more For each product, a setting step can be performed to set the order quantity to either a manual ordering mode, where the user manually determines the order quantity for that product, or an automatic ordering mode, where the order quantity is determined using at least one of the aforementioned multiple algorithms. For products set to the automatic ordering mode, the selection step is executed. An information processing system as described in any one of the items 1 to 6 of the appendix. (Note 8) In the setting step, the one or more processors For products where the sales performance indicators meet the predetermined conditions and the product is set to manual ordering mode, the user is offered the option to switch to automatic ordering mode. In response to the user's acceptance of the switch, the system switches to the automatic ordering mode. The information processing system described in Appendix 7. (Note 9) The predetermined conditions in the setting step include, for products set to manual ordering mode, that the difference between the predicted order quantity and the actual sales quantity, or the difference between the predicted sales quantity and the actual sales quantity, satisfies the switching condition. The predicted order quantity is the order quantity determined using the recommended algorithm selected when the product is set to the automatic ordering mode. The aforementioned forecasted sales volume is the sales volume predicted using the demand forecasting algorithm, which is one of the multiple algorithms mentioned above. The information processing system described in Appendix 8. (Note 10) The one or more processors mentioned above, in the ordering step, For each product, an action item is generated that corresponds to the mode set for that product, and is related to ordering that product. The aforementioned action item is presented to the user. An information processing system as described in any one of the items 7 to 9 of the appendix. (Note 11) The aforementioned processor 1 or more In the setting step described above, the mode is set for each product in accordance with the type of mode received from the headquarters terminal operated by the headquarters user. In the ordering step, the action item is displayed on a store terminal operated by the store user. The information processing system described in Appendix 10. (Note 12) The one or more processors mentioned above, in the ordering step, A list of essential action items necessary to execute the order processing is generated from the aforementioned action items, and the list is displayed on the store terminal. The information processing system described in Appendix 11. (Note 13) The aforementioned processor 1 or more In the ordering step, a category list is generated, which is a list of categories of products that can be ordered. If there are any products among the required action items that have unprocessed action items, an alert is displayed on the store terminal along with the category list for the category to which the product with the unprocessed action item belongs. The information processing system described in Appendix 12. (Note 14) The information processing system performs each of the steps described in any one of the appendices 1 to 13. Information processing methods. (Note 15) A program for causing a computer having one or more processors and memory to perform each of the steps described in any one of the appendices 1 to 13. [Explanation of symbols]

[0096] 1. Information Processing System 2. Information Processing Device 3. Headquarters terminal 4 Store terminals 21 Control Unit 22 Memory section 23 Communications Department 26 Communications Bus 31 Control Unit 32 Storage section 33 Communications Department 34 Input section 35 Display section 36 Communications Bus 41 Control Unit 42 Storage section 43 Communications Department 44 Input section 45 Display section 46 Communications Bus 60 Confirmation screen 61 items 62 Alert Objects 70 Confirmation screen 71 tabs 72 Action Items 73 Order Mode Tag 74 Action Tags 75 Action Tags 80 Confirmation screen 81 tabs 83 Projected sales 84 Input Area 90 Confirmation screen 91 tabs 92 Alert Objects 93 Projected sales 94 Input Area T1 Product Database T11 Product ID T12 Category T13 Release Date T14 Unit price T2 Sales Performance Database T21 Product ID T22 Order Date T23 Order Quantity T24 Sales figures T25 Quantity in stock 211 Acquisition Department 212 Setting Section 213 Selection Section 214 Order Processing Unit

Claims

1. An information processing system comprising one or more processors and memory, The one or more processors mentioned above are capable of performing the following steps: In the acquisition step, sales performance indicators are obtained for each store and each product. The aforementioned sales performance indicator includes the variability in the number of units sold of the product over a predetermined period and the degree of sales of the product, and the degree of sales is an indicator calculated based on the number of units sold of the product over the predetermined period, and is a different indicator from the variability in the number of units sold. In the selection step, for each store and each product, A first determination is made as to whether the sales performance meets the first condition. A second determination is made as to whether the variation in the number of sales of the aforementioned product satisfies the second condition. If the results of the first and second determinations satisfy predetermined conditions, a demand forecasting algorithm is selected from among multiple algorithms as the recommended algorithm for ordering the product. If the results of the first and second determinations do not satisfy the predetermined conditions, a conditional algorithm is selected as the recommended algorithm. The aforementioned plurality of algorithms include a demand forecasting algorithm that determines the order quantity based on demand forecasts derived from past sales performance, and a conditional algorithm that determines the order quantity based on whether past sales or inventory levels meet certain conditions. In the ordering step, the ordering process is executed using the recommended algorithm. Information processing system.

2. An information processing system comprising one or more processors and memory, The one or more processors mentioned above are capable of performing the following steps: In the acquisition step, sales performance indicators are obtained for each store and each product. The aforementioned sales performance indicator includes the variability in the number of units sold of the product over a predetermined period and the degree of sales of the product, and the degree of sales is an indicator calculated based on the number of units sold of the product over the predetermined period, and is a different indicator from the variability in the number of units sold. In the selection step, for each store and each product, if the sales performance indicator for that product meets the predetermined conditions, the demand forecasting algorithm is selected as the recommended algorithm to be used for ordering that product from among multiple algorithms, and if the sales performance indicator for that product does not meet the predetermined conditions, the conditional algorithm is selected as the recommended algorithm. The aforementioned plurality of algorithms include a demand forecasting algorithm that determines the order quantity based on demand forecasts derived from past sales performance, and a conditional algorithm that determines the order quantity based on whether past sales or inventory levels meet certain conditions. In the ordering step, the ordering process is executed using the selected recommended algorithm. In the update step, in response to a trigger occurring to update the recommended algorithm, it is determined for each product whether the sales performance or sales volume variation since the selection of the recommended algorithm for that product meets predetermined change conditions, and if the change conditions are not met, the recommended algorithm is not changed. Information processing system.

3. An information processing system comprising one or more processors and memory, The one or more processors mentioned above are capable of performing the following steps: In the acquisition step, sales performance indicators are obtained for each store and each product. The aforementioned sales performance indicator includes the degree of sales calculated based on the number of units sold for the product during a predetermined period. In the selection step, for each store and each product, if the sales performance of that product meets the predetermined conditions, a demand forecasting algorithm is selected as the recommended algorithm to be used for ordering that product from among multiple algorithms, and if the sales performance does not meet the predetermined conditions, a conditional algorithm is selected as the recommended algorithm. The aforementioned plurality of algorithms include a demand forecasting algorithm that determines the order quantity based on demand forecasts derived from past sales performance, and a conditional algorithm that determines the order quantity based on whether past sales or inventory levels meet certain conditions. In the ordering step, the ordering process is executed using the recommended algorithm. Information processing system.

4. An information processing system comprising one or more processors and memory, The one or more processors mentioned above are capable of performing the following steps: In the acquisition step, sales performance indicators are obtained for each store and each product. The aforementioned sales performance indicator includes the variation in the number of units sold for the product over a specified period. In the selection step, if the variation in the number of units sold for each store and each product during the predetermined period satisfies predetermined conditions, the demand forecasting algorithm is selected as the recommended algorithm to be used for ordering the product from among multiple algorithms; if the variation in the number of units sold for the product does not satisfy the predetermined conditions, the conditional algorithm is selected as the recommended algorithm. The aforementioned plurality of algorithms include a demand forecasting algorithm that determines the order quantity based on demand forecasts derived from past sales performance, and a conditional algorithm that determines the order quantity based on whether past sales or inventory levels meet certain conditions. In the ordering step, the ordering process is executed using the recommended algorithm. Information processing system.

5. An information processing system comprising one or more processors and memory, The one or more processors mentioned above are capable of performing the following steps: In the acquisition step, sales performance indicators are obtained for each store and each product. The aforementioned sales performance indicator includes the variation in the number of units sold for the product over a specified period. In the selection step, if the variation in the number of units sold for each store and each product during the predetermined period meets the predetermined conditions, a learning-type demand forecasting algorithm is selected as the recommended algorithm for ordering that product; if the variation in the number of units sold does not meet the predetermined conditions, a statistical-based inventory algorithm is selected as the recommended algorithm. The aforementioned learning-type demand forecasting algorithm is an algorithm that determines the order quantity by forecasting demand based on past sales performance using machine learning. The aforementioned statistical inventory-based algorithm is an algorithm that determines the order quantity based on statistical demand forecasts derived from past sales performance. In the ordering step, the ordering process is executed using the recommended algorithm. Information processing system.

6. The one or more processors mentioned above are: A further step can be performed to display the order quantity determined by the aforementioned recommended algorithm on the user terminal operated by the user. The information processing system according to any one of claims 1 to 5.

7. The first condition or the second condition is determined for each product or store. The information processing system according to claim 1.

8. The predetermined conditions used to determine the selection of the recommended algorithm are determined for each product or each store. The information processing system according to any one of claims 1 to 5.

9. The information processing system performs each step described in any one of claims 1 to 5. Information processing methods.

10. A program for causing a computer, which comprises one or more processors and memory, to perform each of the steps described in any one of claims 1 to 5.

Images