Information processing device, information processing method, and program

Abstract

The present invention provides an information processing device capable of generating a plan to suppress raw material surplus while achieving sales targets. [Solution] The information processing device includes a first plan generation means that generates a first optimized sales plan result for a product by deriving the number of products to be sold that will satisfy the sales target and maximize gross profit, based on acquired sales targets and the predicted demand for the product based on sales performance data, and a second plan generation means that generates a second optimized sales plan result for a product by optimizing the number of products to be sold included in the first optimized result so as to minimize the surplus of raw materials related to that product, based on the generated first optimized result and acquired raw material information related to the raw materials of the product.

Description

Technical Field

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

Background Art

[0005] Furthermore, depending on the product's production lot, such as when each batch is manufactured in units of 10, it can be difficult to flexibly adjust the quantity of products. Therefore, when considering multiple products, their respective production lots, and the raw materials used to manufacture them, it is extremely difficult to appropriately adjust the sales volume of each product, and such adjustments can take a considerable amount of time.

[0006] One possible countermeasure is to create sales plans for products that do not generate surplus raw materials, and to create corresponding raw material ordering plans. However, generating appropriate sales plans, manufacturing plans, and ordering plans based on employee experience and other factors is highly difficult. The present invention aims to provide an information processing device, an information processing method, and a program that can generate a sales plan that suppresses surplus raw materials while achieving sales targets. [Means for solving the problem]

[0007] The information processing device according to the present invention is characterized by comprising: a first plan generation means that, based on acquired sales targets and the predicted demand for the product based on sales performance data, derives the number of units of the product to be sold that will satisfy the sales targets and maximize gross profit, and generates a first optimized sales plan result for the product; and a second plan generation means that, based on the generated first optimized plan result and acquired raw material information relating to the raw materials of the product, generates a second optimized sales plan result for the product in which the number of units of the product to be sold included in the first optimized plan result is optimized so as to minimize the surplus of raw materials relating to the product. [Effects of the Invention]

[0008] According to the present invention, it is possible to provide an information processing device, an information processing method, and a program that can generate a sales plan that suppresses raw material surplus while achieving sales targets. [Brief explanation of the drawing]

[0009] [Figure 1]This is a diagram showing an example of the configuration of an information processing system. [Figure 2] This is a diagram illustrating an example of an information processing system. [Figure 3] This figure shows an example of a sales plan output. [Figure 4] This figure shows an example of the hardware configuration of an information processing device. [Figure 5] This diagram shows an example of the functional configuration of an information processing device (analysis server). [Figure 6] This is a flowchart showing an example of processing performed by an information processing device (analysis server). [Modes for carrying out the invention]

[0010] Embodiments of the present invention will be described based on the drawings.

[0011] Figure 1 shows an example configuration of an information processing system 100 in one embodiment of the present invention. The information processing system 100 in this embodiment includes a data management server 110, an analysis server 120, and a terminal device 130. The data management server 110, the analysis server 120, and the terminal device 130 are connected to each other via a network NW so that they can communicate with one another. In the example shown in Figure 1, one terminal device 130 is shown, but the number of terminal devices 130 in the information processing system 100 is not particularly limited, and multiple terminal devices 130 may be provided.

[0012] The data management server 110 manages various types of data in the information processing system 100. The data managed by the data management server 110 may include core data such as sales performance data for each product being managed, such as POS (Point of Sale) data, and sales budget data related to sales targets (sales budgets); internal information such as product information, raw material and recipe information for prepared and processed products (in-store packed products and process center products, etc.), and promotional and flyer information such as flyers; and external data such as weather forecast data. The data management server 110 also manages configuration information related to the generation of sales plans for various products (in-store packed products / process center products / out-packed products) by the analysis server 120.

[0013] The analysis server 120 predicts future customer numbers and product demand, and generates sales plans, based on various data and configuration information managed by the data management server 110. For example, the analysis server 120 predicts future customer numbers based on various data and configuration information, and uses the acquired customer prediction results to predict future product demand. Furthermore, for example, the analysis server 120 uses the acquired customer prediction results and demand prediction results to solve a combinatorial optimization problem and generate a sales plan that achieves the sales target (sales budget), maximizes gross profit, and minimizes raw material surplus.

[0014] The terminal device 130 schematically represents a device that serves as an input / output interface for users of the information processing system 100 to access the data management server 110 and the analysis server 120. For example, the terminal device 130 may be used as an input / output interface for users to access the data management server 110 and refer to or update the data managed by the data management server 110. Alternatively, the terminal device 130 may be used as an input / output interface for receiving various instructions from users to the analysis server 120 and for providing users with sales plans generated by the analysis server 120.

[0015] The network NW is not limited in type, as long as it can connect the data management server 110, the analysis server 120, and the terminal device 130 so that they can communicate with each other. For example, the network NW may be the Internet, WAN (Wide Area Network), LAN (Local Area Network), etc. Alternatively, the network NW may be a network compliant with wireless communication standards such as LTE (Long Term Evolution) or 5G. Furthermore, the network NW may be implemented by multiple networks. In this case, the multiple networks may include two or more networks of different types, and the type of transmission path or the communication method applied in some networks may differ from those of other networks. In addition, at least a portion of the communication between the data management server 110, the analysis server 120, and the terminal device 130 may be mediated by other communication devices.

[0016] Referring to Figure 2, an example of the processing of the information processing system 100 in this embodiment will be described. The data management server 110 manages data 201 and configuration information 202. The data 201 managed by the data management server 110 may include, for example, core data such as POS data and sales budget data, internal information such as product information, raw material / recipe information, and sales promotion / flyer information, and external data such as weather forecast data. The configuration information 202 managed by the data management server 110 is configuration information related to the generation of sales plans by the analysis server 120, and includes, for example, information such as the plan start date, plan end date, store code, department, sales targets not met, and profit targets not met.

[0017] POS data is sales performance data for each product, including information such as sales date, sales time, buyer ID (buyer attribute), product name, product code, quantity sold, product identification code (GTIN code), clearance rate, discount amount, and discard flag. Sales budget data is data related to sales targets (sales budget) that show sales plans (sales budget for each department and information on acceptable losses, etc.), including information such as deadline, store code, department, product category, sales target (sales budget), profit target, acceptable loss rate, and event date. Product information is information about products to be sold, including product hierarchy information that defines departments and product categories (major categories), sales date, sales store, product name, product code, product identification code (GTIN code), cost, selling price, required product flag, fixed order quantity, ABC classification based on ABC analysis, sales specifications, and sales specification units. Raw material / recipe information includes information about the raw materials of a product, and recipe information that shows the type and amount of raw materials required for a product. Raw material information includes, for example, raw material code (GTIN code), raw material name, order specifications, order specification units, volume specifications, volume specification units, management specifications, management specification units, cost, and individual order availability flag. Recipe information includes, for example, product identification code (GTIN code), product name, sales specifications, sales specification units, raw material code (GTIN code), raw material name, required quantity specifications, required quantity specification units. Promotional and flyer information includes information such as the period of promotions such as flyers, target products, sales price, and purchase price. Weather forecast data is information regarding the weather forecast for a specified period.

[0018] Here, various standards and standard units will be explained using in-store pack products as an example. The sales standard unit, required quantity standard unit, capacity standard unit, management standard unit, and order standard unit indicate the units of the quantities indicated by their respective standards. For example, they are bags, pieces, sheets, grams (g), etc. The sales standard is the content volume included in each in-store pack product to be sold, and the required quantity standard is the amount of raw materials required for manufacturing each in-store pack product to be sold. The capacity standard is the amount of raw materials included in each management standard, and the management standard is the number of management standard units included in each order standard. The order standard is the number of management standard units, which is the minimum unit when placing an order for raw materials. As an example, when the raw material is frozen tempura and the management standard unit is a bag, the order standard is the minimum number of bags that can be ordered, the capacity standard is the number of frozen tempura in one bag to be delivered, and the sales standard and required quantity standard are the number of frozen tempura in each in-store pack product.

[0019] The analysis server 120 acquires various data (data 201 and setting information 202, etc.) from the data management server 110, and based on the acquired data, predicts the number of future visitors, the demand for products, and generates a sales plan. For example, the analysis server 120 uses a visitor prediction model 211, which is a learned model trained to derive the number of future visitors to a store or the like, inputs the data acquired from the data management server 110 into the visitor prediction model 211 to predict the number of future visitors, and obtains a visitor prediction result 212. In addition, the analysis server 120 uses a demand prediction model 213, which is a learned model trained to derive the future demand for products, inputs the acquired visitor prediction result 212 and the data acquired from the data management server 110 into the demand prediction model 213 to predict the future demand, and obtains a demand prediction result 214.

[0020] Furthermore, the analysis server 120 inputs the obtained customer arrival prediction result 212, demand prediction result 214, etc. into the optimization engine 215, and solves for the optimal solution in the sales plan by the optimization engine 215 based on the solution conditions 221. The analysis server 120 uses the obtained customer arrival prediction result 212, demand prediction result 214, etc., and by the optimization engine 215, solves it as a combinatorial optimization problem to achieve the sales target (sales budget), increase the gross profit, and reduce the surplus of raw materials, thereby generating a sales plan 216 for products as shown in an example in FIG. 3. In this way, the analysis server 120 generates a sales plan 216 that achieves the sales target (sales budget) and realizes the maximization of gross profit and the minimization of the surplus of raw materials.

[0021] Note that an example has been described in which the analysis server 120 uses the customer arrival prediction model 211 and demand prediction model 213, which are learned models, to predict the number of future customers and the demand for products. However, it is not limited to this. The analysis server 120 may apply other known customer arrival prediction methods to predict the number of customers without using a learned model, or may apply other known demand prediction methods to predict the demand. Also, the analysis server 120 may apply a learned model (mathematical optimization model) that has been trained to derive an optimal result that satisfies the conditions as the optimization engine 215 to perform inference and solution of the combinatorial optimization problem, or may use a so-called solver as the optimization engine 215 to perform the solution.

[0022] FIG. 3 is a diagram showing an output example of the sales plan generated by the analysis server 120. FIG. 3 shows an example of generating a sales plan for products for one week. For each day, the total sales and the sales target amount (sales budget) based on the sales plan are shown. Also, the product names of products such as "edamame", "sweet potato", "Caesar salad" (outpack products / in-store pack products / process center products) are shown, and for each product, the sales quantity in the sales plan, the sales performance of the previous week, etc. are shown for each day. Note that the example shown in FIG. 3 is just an example, and the output format of the sales plan is not limited to this.

[0023] Referring to Figure 4, an example of the hardware configuration of an information processing device 400 applicable as a data management server 110, an analysis server 120, and a terminal device 130 in the information processing system 100 shown in Figure 1 will be described. As shown in Figure 4, the information processing device 400 in this embodiment has a CPU 401, ROM 402, RAM 403, auxiliary storage device 404, and network I / F 407. The information processing device 400 may also have at least one of an output device 405 and an input device 406. The CPU 401, ROM 402, RAM 403, auxiliary storage device 404, output device 405, input device 406, and network I / F 407 are communicated together via a system bus 408.

[0024] The CPU (Central Processing Unit) 401 is a central processing unit that controls various operations of the information processing device 400. For example, the CPU 401 may control the operation of the entire information processing device 400. The ROM (Read Only Memory) 402 stores control programs, boot programs, etc., that can be executed by the CPU 401. The RAM (Random Access Memory) 403 is the main memory of the CPU 401 and is used as a work area or a temporary storage area for deploying various programs.

[0025] The auxiliary storage device 404 stores various data and programs. The auxiliary storage device 404 is implemented by a storage device capable of temporarily or permanently storing various data, such as an HDD (Hard Disk Drive) or non-volatile memory such as an SSD (Solid State Drive).

[0026] The output device 405 is a device that outputs various types of information and is used to present various types of information to the user. For example, the output device 405 may be implemented by a display device such as a display. The output device 405 may present information to the user by displaying various types of display information. As another example, the output device 405 may be implemented by an acoustic output device that outputs sounds such as voice or electronic sounds. In this case, the output device 405 may present information to the user by outputting sounds such as voice or electronic sounds. Furthermore, the device to which the output device 405 is applied may be appropriately changed depending on the medium used to present information to the user.

[0027] The input device 406 is used to receive various instructions from the user. For example, the input device 406 may include input devices such as a mouse, keyboard, or touch panel. As another example, the input device 406 may include a sound collection device such as a microphone to collect the voice spoken by the user. In this case, the collected voice may be subjected to various analysis processes such as acoustic analysis and natural language processing so that the content of the voice is recognized as an instruction from the user. Furthermore, the device applied as the input device 406 may be changed as appropriate depending on the method of recognizing the user's instructions. In addition, multiple types of devices may be applied as the input device 406.

[0028] Network I / F 407 is used for communication with external devices via a network. The device used as Network I / F 407 may be changed as appropriate depending on the type of communication path and the applicable communication method.

[0029] The CPU 401 loads the program stored in the ROM 402 or auxiliary storage device 404 into the RAM 403 and executes the program, thereby realizing, for example, the functional configuration shown in Figure 5 and the various processes shown in Figure 6. The program for the information processing device 400 may be provided to the information processing device 400 by a recording medium such as a CD-ROM, or it may be downloaded via a network or the like. When the program for the information processing device 400 is provided by a recording medium, the program recorded on the recording medium is installed in the auxiliary storage device 404 when the recording medium is set in a predetermined drive device.

[0030] The configuration shown in Figure 4 is merely an example and does not necessarily limit the hardware configuration of the information processing device 400 in this embodiment. For example, some components such as the output device 405 and the input device 406 may be omitted. Also, for example, configurations may be added as appropriate depending on the functions to be realized by the information processing device 400.

[0031] Figure 5 shows an example of the functional configuration of the analysis server 120 in this embodiment. The analysis server 120 includes a communication unit 501, a control unit 502, an input / output control unit 503, a storage unit 504, an acquisition unit 505, a customer forecasting unit 506, a demand forecasting unit 507, and a sales plan generation unit 508.

[0032] The communication unit 501 is a communication interface for each component of the analysis server 120 to send and receive information with other devices such as the data management server 110 and terminal devices 130 via a network NW. The communication unit 501 can be implemented, for example, by a network I / F 407. In the following description, when each component of the analysis server 120 sends and receives information with other devices, it will be assumed that the information is sent and received via the communication unit 501 unless otherwise specified.

[0033] The control unit 502 is responsible for controlling each component of the analysis server 120. The input / output control unit 503 performs various processes related to presenting various information to the user and receiving information input from the user (e.g., instructions). For example, the input / output control unit 503 may perform processes related to presenting the UI (User Interface) and processes related to receiving input via the UI. This enables the analysis server 120 to recognize instructions from the user and present the user with the results of processing corresponding to those instructions.

[0034] The memory unit 504 schematically represents a memory area for storing various data and programs. For example, the memory unit 504 may store data and programs for each component of the analysis server 120 to execute processing. The memory unit 504 may also store a customer prediction model for predicting the number of customers, a demand prediction model for predicting the amount of demand, and a trained model (mathematical optimization model) that performs inference on a combinatorial optimization problem related to sales planning as an optimization engine. Furthermore, the memory unit 504 may store the processing results of the customer prediction unit 506 (customer prediction results), the processing results of the demand prediction unit 507 (demand prediction results), and the processing results of the sales plan generation unit 508 (sales plan, which is the optimization result).

[0035] The acquisition unit 505 acquires various data for generating a sales plan in the analysis server 120. For example, the acquisition unit 505 acquires data used for predicting the number of visitors in the visitor prediction unit 506, data used for predicting the amount of demand in the demand prediction unit 507, and data used for generating a sales plan in the sales plan generation unit 508. For example, the acquisition unit 505 acquires sales performance data (POS data), sales budget data, product information, raw material / recipe information, and setting information from the data management server 110. In addition, for example, the acquisition unit 505 may further acquire promotional / flyer information and weather forecast data.

[0036] For example, the acquisition unit 505 acquires information such as the sales date, sales time, product name, product code, number sold, product identification code (GTIN code), clearance rate, discount amount, and discard flag from sales performance data (POS data), and acquires information such as the due date, store code, department, and sales target (sales budget) from sales budget data. In addition, the acquisition unit 505 acquires information such as product hierarchy information, sales date, sales store, product name, product code, product identification code (GTIN code), department, product classification (major category), cost, selling price, sales specifications, and sales specification units from product information, and acquires information such as raw material code (GTIN code), raw material name, order specifications, order specification units, capacity specifications, capacity specification units, cost, individual order possible flag, product identification code (GTIN code), product name, sales specifications, sales specification units, raw material code (GTIN code), raw material name, required quantity specifications, and required quantity specification units from raw material / recipe information. Furthermore, the acquisition unit 505 acquires, for example, the plan start date, plan end date, store code, and department information from the setting information as conditions for solving the combinatorial optimization problem. This is just one example, and the acquisition unit 505 may acquire other information in addition to the information described above.

[0037] The customer forecasting unit 506 predicts the future number of customers at a store, etc., based on sales performance data (POS data), etc., acquired by the acquisition unit 505, and obtains the forecast result (customer forecast result). For example, the customer forecasting unit 506 predicts the future number of customers by inputting the sales performance data (POS data) acquired by the acquisition unit 505 into the customer forecasting model. The acquired customer forecast result is, for example, a daily forecast of the number of customers at each store, and includes information on the date, store code, and the number of customers predicted. The customer forecasting unit 506 may also predict the future number of customers based on sales performance data (POS data) and weather forecast data.

[0038] The demand forecasting unit 507 predicts the future demand for products based on the customer forecasting results obtained by the customer forecasting unit 506 and the sales performance data (POS data) and product information obtained by the acquisition unit 505, and obtains the forecast result (demand forecast result). For example, the demand forecasting unit 507 predicts the future demand for products by inputting the customer forecasting results obtained by the customer forecasting unit 506 and the sales performance data (POS data) and product information obtained by the acquisition unit 505 into the demand forecasting model. The obtained demand forecast result is, for example, a product-specific and daily demand forecast for each store, and includes information such as date, store code, product code, sales specifications, and sales forecast quantity.

[0039] The sales plan generation unit 508 generates a sales plan for a product based on various data (including setting information) acquired by the acquisition unit 505, customer forecasting results acquired by the customer forecasting unit 506, and demand forecasting results acquired by the demand forecasting unit 507. The sales plan generation unit 508 generates the sales plan by solving a combinatorial optimization problem that achieves the sales target (sales budget), maximizes gross profit, and minimizes raw material surplus.

[0040] The sales plan generation unit 508 includes a first plan generation unit 509 and a second plan generation unit 510. The first plan generation unit 509 optimizes the initial sales plan based on acquired sales target data, customer forecast results, demand forecast results, etc., and generates a sales plan (initial sales plan) for products that achieve the sales target (sales budget) while maximizing gross profit. The second plan generation unit 510 optimizes raw material adjustments based on the sales plan (initial sales plan) generated by the first plan generation unit 509 and raw material / recipe information, etc., and generates a sales plan by adjusting the sales quantity of products to suppress the surplus of raw materials related to the products to be sold (to avoid surplus raw materials). The sales plan generated by the first plan generation unit 509 is an example of the first optimization result, and the sales plan generated by the second plan generation unit 510 is an example of the second optimization result.

[0041] The following describes how the first plan generation unit 509 and the second plan generation unit 510 generate sales plans. The first plan generation unit 509 generates a sales plan (initial sales plan) for products that maximizes gross profit while achieving the sales target (sales budget), taking into account the demand forecast results obtained by the demand forecasting unit 507. The first plan generation unit 509 also calculates various values ​​used when the second plan generation unit 510 generates the sales plan for products. Here, simply increasing the sales quantity of all products would maximize gross profit, but this would result in inventory and waste losses. Therefore, the sales plan is generated by adjusting the sales forecast correction range, which defines an upper limit on the sales quantity to prevent a large deviation from the sales quantity in the demand forecast. The sales forecast correction range is a parameter that indicates how much of a difference in sales quantity from the sales forecast is allowed in the sales plan. The sales forecast correction range is set to a value of 1 or greater so that the sales quantity does not fall below the demand quantity in the demand forecast (stockout of products).

[0042] Specifically, the first planning generation unit 509 solves the combinatorial optimization problem with equations (1) and (2) shown below as the objective function and equations (3) to (6) as constraints, and obtains the daily sales figures for each product, the daily raw material usage figures for each raw material, and the daily sales forecast correction range.

[0043] Equation (1) maximizes the gross profit on a product. The cost of raw materials used in the product is taken as the cost, and the goal is to maximize the sum of (selling price - cost). In equation (1), the number of raw materials used is the number used in units of the raw material management standard. Equation (2) minimizes the sales forecast adjustment range relative to the demand forecast. In equation (2), the gross profit of the product (selling price of the product - cost of the product) is also considered in order to maximize gross profit, but the gross profit of the product may be excluded. Alternatively, the selling price of the product may be used instead of the gross profit of the product. By adding the gross profit of the product (selling price of the product) to equation (2), the penalty value during the search for a solution in the combinatorial optimization problem increases, allowing the system to approach the desired value (optimal solution) faster and improving the processing speed. The set values ​​in equation (2) are arbitrary set values ​​depending on the solution conditions.

[0044]

number

[0045] Equation (3) shows the conditions for sales targets (sales budgets) for a given period, and represents a constraint that the total of all sales during the given period must be equal to or greater than the total of the sales targets (sales budgets) for that period. Equation (4) shows the conditions regarding the upper limit of sales volume for each product, representing a constraint that sales volume must be less than or equal to (demand quantity in demand forecast × sales forecast adjustment range) to prevent sales volume from increasing too much. In equation (4), the ABC ratio is the ratio applied according to the product category determined by ABC analysis. For example, it is set to 1.0 for products in category A, 0.4 for products in category B, and 0.0 for products in category C. The adjustment value is set according to the markup rate (gross profit margin), for example. For example, the adjustment value used is calculated as (1 + (markup rate of the product - average markup rate for the product category) × weight of the markup rate). By applying the adjustment coefficient shown in equation (4), it becomes possible to set a higher upper limit on sales volume in the sales plan for products that sell well and have a high markup rate (gross profit margin). Note that the ABC ratio and adjustment value shown here are just examples and are not limited to these; the ABC ratio and adjustment value can be set arbitrarily.

[0046]

number

[0047] Equation (5) shows the conditions for the ratio of the daily sales forecast adjustment range, and represents the constraint to make the sales forecast adjustment range proportional to the number of visitors, based on the idea that the number of sales is proportional to the number of visitors. Equation (6) shows the conditions regarding the required number of raw materials for each raw material, representing a constraint that the required number of each raw material must be greater than or equal to the number of raw materials used. In equation (6), the number of raw materials used is the number used in units of the raw material's management standard.

[0048]

number

[0049] The first plan generation unit 509 uses a trained model (mathematical optimization model) that has been trained to derive optimization results that satisfy the conditions to solve the combinatorial optimization problem shown by equations (1) to (6) above, thereby obtaining the daily sales figures for each product, the daily raw material usage figures for each raw material, and the daily sales forecast correction range. In addition to the trained model (mathematical optimization model), a so-called solver may also be used to solve the combinatorial optimization problem shown by equations (1) to (6) above, thereby obtaining the daily sales figures for each product, the daily raw material usage figures for each raw material, and the daily sales forecast correction range.

[0050] Furthermore, at least one of the following equations (7) to (10) may be added to the constraints so that the first planning generation unit 509 obtains the daily and product sales figures, the daily and raw material usage figures, and the daily sales forecast correction range. Equation (7) shows the conditions regarding the sales target (sales budget) for the event day, and represents a constraint that the total sales for the event day must be equal to or greater than the total sales target (sales budget) for the event day. Equation (8) shows the conditions for the gross profit target for a given period, and represents a constraint that the sum of all gross profits for the given period must be equal to or greater than the sum of the gross profit targets for that period. Equation (9) shows the conditions for the gross profit target on the event day, representing the constraint that the total gross profit on the event day must be equal to or greater than the total gross profit target for the event day. Equation (10) shows the condition regarding the lower limit of the number of products sold, and represents a constraint that the number of products sold must be 1 or more in accordance with the requirement to secure the sales volume in the sales plan.

[0051]

number

[0052] Next, the generation of the sales plan by the second planning unit 510 will be explained. Based on the sales plan (initial sales plan) generated by the first planning unit 509, the second planning unit 510 generates a sales plan for products that minimizes the waste of raw materials without significantly changing the sales volume in the sales plan (initial sales plan). If the products are prepared using the sales volume in the sales plan (initial sales plan), a large amount of raw materials may be wasted depending on the capacity specifications of the raw materials. Therefore, the second planning unit 510 adjusts the sales volume in the sales plan to minimize the waste of raw materials, taking into account other products and raw materials.

[0053] Specifically, the second planning generation unit 510 solves the combinatorial optimization problem with equations (11) to (13) as the objective function and equations (14) to (20) as constraints, and obtains the daily and product sales figures, the daily and raw material usage figures, and the daily and product increase ratios.

[0054] Equation (11) maximizes the gross profit on the product. Using the cost of raw materials used in the product as the cost, it maximizes the sum of (selling price - cost). Equation (12) minimizes the surplus of raw materials related to the product. In equation (12), the loss corresponds to the monetary value of the surplus raw materials. Note that in equations (11) and (12), the number of raw materials used is the number used in units of the raw material management standard. Equation (13) minimizes the increase ratio of sales to the initial sales volume for a product. If the sales volume in the sales plan generated by the second plan generation unit 510 exceeds the sales volume in the initial sales plan generated by the first plan generation unit 509, it becomes possible to impose a penalty during the search for a solution in the combinatorial optimization problem according to the ratio from the initial sales volume. This penalty based on the increase ratio may be further adjusted to take into account the gross profit of the product by adding (selling price of the product - cost of the product) × (weight related to the increase ratio penalty) to the increase ratio expressed in equation (13). If the penalty based on the increase ratio is the same, increasing the sales volume of a product with a large gross profit per unit sold is more effective for maximizing gross profit, so a more appropriate solution can be obtained by setting the penalty proportional to the value of the gross profit of the product (selling price of the product - cost of the product).

[0055]

number

[0056] Equation (14) shows the conditions for sales targets (sales budgets) for a given period, and represents a constraint that the total of all sales during the given period must be equal to or greater than the total of the sales targets (sales budgets) for that period. Equation (15) shows the condition regarding the lower limit of the number of units sold for a product, representing a constraint that the number of units sold must exceed the number of units sold in the sales plan (initial sales plan) or the quantity demanded in the demand forecast (the smaller of the two), and if there is no unit to calculate, at least one unit must be sold. Equation (16) shows the conditions regarding the required number of raw materials for each raw material, representing the constraint that the required number of each raw material must be greater than or equal to the number of raw materials used. In equation (16), the number of raw materials used is the number used in units of the raw material's management standard.

[0057]

number

[0058] Equation (17) shows the conditions regarding the range of sales quantities in the sales plan, and expresses the constraint that the number of sales must be at least the number obtained by multiplying the number of sales in the sales plan (initial sales plan) by the allowable ratio (0.9 in this example), and less than or equal to the number required to consume the surplus raw materials, or the number obtained by multiplying the number of sales in the sales plan (initial sales plan) by the allowable ratio (1.1 in this example), or the minimum production quantity (number of units produced per batch, 1 in this example). Note that the allowable ratio and minimum production quantity shown here are just examples and are not limiting, and the allowable ratio and minimum production quantity can be set arbitrarily. Equation (18) shows a condition regarding the range of raw material usage, and in the case of raw materials that cannot be individually ordered, it represents a constraint that the number of raw materials used must be within ±1 set of the number of raw materials used in the sales plan (initial sales plan). In other words, the number of raw materials used is limited so that the difference between the number of raw materials used in the sales plan (initial sales plan) and the number of raw materials used in the generated sales plan is within 1 set. Note that in equation (18), the number of raw materials used is the number used in the raw material's management standard unit. Here, in this embodiment, raw materials that cannot be individually ordered are described as raw materials that are expected to be ordered as one of several raw materials together with other raw materials such as cooking oil. Therefore, the unit of raw material usage in equation (18) is described as a unit (set) that combines several raw materials. However, it is not limited to this. The unit of raw material usage may be any unit relating to individual raw materials, such as quantity, packaging, can, and box. Furthermore, in this embodiment, a form is described in which the difference in the number of raw materials used is limited to 1 set. However, it is not limited to this. The difference in the number of raw materials used may be two or more predetermined numbers, or it may be a predetermined number specified by the user.

[0059]

number

[0060] Equation (19) shows the conditions regarding the sales growth rate for each product, and represents a constraint that the sales growth rate must be greater than or equal to (sales in the sales plan (initial sales plan) / demand in the demand forecast) (however, it must be 0 or greater). Equation (20) shows the conditions regarding the increase ratio of total requirements for each raw material, and represents a constraint that the increase ratio of total requirements must be greater than or equal to (total requirements based on sales volume in the sales plan (initial sales plan) / total requirements based on demand volume in the demand forecast) (however, it must be 0 or greater). Products that require less raw material require a larger increase in production volume to consume the raw material, so this constraint suppresses imbalances due to differences in raw material requirements for products and reduces the deviation from the sales volume in the initial sales plan. Note that all increase ratios are the increase ratio relative to the demand volume based on demand forecasts.

[0061]

number

[0062] The second plan generation unit 510 uses a trained model (mathematical optimization model) that has been trained to derive optimization results that satisfy the conditions to solve the combinatorial optimization problem shown by equations (11) to (20) above, thereby obtaining the daily and product sales figures, the daily and raw material usage figures, and the daily and product growth ratios. Note that, in addition to the trained model (mathematical optimization model), a so-called solver may also be used to solve the combinatorial optimization problem shown by equations (11) to (20) above, thereby obtaining the daily and product sales figures, the daily and raw material usage figures, and the daily and product growth ratios.

[0063] Furthermore, by adding at least one of the aforementioned equations (7) to (9) to the constraints, the second planning generation unit 510 may obtain the daily and product sales figures, the daily and raw material usage figures, and the daily and product increase ratios.

[0064] Figure 6 is a flowchart showing an example of processing by the analysis server 120 in this embodiment. In step S601, the acquisition unit 505 acquires various data for generating a product sales plan. For example, the acquisition unit 505 acquires sales performance data (POS data), sales budget data, product information, raw material / recipe information, and setting information from the data management server 110. In addition, the acquisition unit 505 may further acquire promotional / flyer information and weather forecast data.

[0065] In step S602, the customer forecasting unit 506 predicts the number of customers in a future target period (for example, the following week) at a store, etc., based on the sales performance data (POS data), etc., acquired in step S601, and obtains the forecast result (customer forecast result). For example, the customer forecasting unit 506 predicts the number of future customers by inputting the sales performance data (POS data), etc., acquired in step S601 into the customer forecasting model.

[0066] In step S603, the demand forecasting unit 507 forecasts the demand for the product in a future target period (for example, the following week) based on the sales performance data (POS data) and product information acquired in step S601 and the customer visit forecast result acquired in step S602, and obtains the forecast result (demand forecast result). For example, the demand forecasting unit 507 forecasts the future demand for the product by inputting the sales performance data (POS data) and product information acquired in step S601 and the customer visit forecast result acquired in step S602 into the demand forecasting model.

[0067] Next, the sales plan generation unit 508 uses the various data (including setting information) acquired in step S601, the customer forecast results acquired in step S602, and the demand forecast results acquired in step S603 to execute the processes in steps S604 to S607. The sales plan generation unit 508 repeatedly executes the processes in steps S604 to S607 for each solution condition based on the setting information acquired in step S601, and generates a sales plan for the product for a future target period (for example, the following week).

[0068] When the processing in steps S604 to S607 begins, in step S605, the first plan generation unit 509 of the sales plan generation unit 508 optimizes the initial sales plan based on customer forecast results and demand forecast results, etc., and generates a sales plan (initial sales plan) for the products. For example, the first plan generation unit 509 solves the aforementioned equations (1) and (2) as objective functions and equations (3) to (6) as constraints, thereby obtaining the number of sales per day and per product, the number of raw materials used per day and per raw material, and the daily sales forecast correction range, and generates a sales plan for the products that maximizes gross profit while achieving the sales target (sales budget).

[0069] In step S606, the second plan generation unit 510 of the sales plan generation unit 508 performs raw material adjustment optimization based on the sales plan (initial sales plan) generated in step S605 and generates a sales plan for the product. For example, the second plan generation unit 510 solves the aforementioned combinatorial optimization problem with equations (11) to (13) as the objective function and equations (14) to (20) as constraints, obtaining the number of sales per day and per product, the number of raw materials used per day and per raw material, and the increase ratio per day and per product, and generates a sales plan for the product that maximizes gross profit while achieving the sales target (sales budget) and minimizing the surplus of raw materials, including information on the number of raw materials used per raw material.

[0070] In step S607, the sales plan generation unit 508 repeats the processes from steps S604 to S607 if there are any unprocessed resolution conditions, and proceeds to step S608 if there are no unprocessed resolution conditions. In this way, by repeating the processes from steps S604 to S607 for each resolution condition, a sales plan for the target period of the future is generated that achieves the sales target (sales budget), maximizes gross profit, and minimizes raw material surplus.

[0071] In step S608, the sales plan generation unit 508 outputs the sales plan for the target period of the future, which was generated by the aforementioned processing, to the user, for example, via the input / output control unit 503. Then, the processing of the flowchart shown in Figure 6 is completed. As a result, a user who has received a sales plan for the product that has been generated to achieve sales targets (sales budgets), maximize gross profit, and minimize raw material surplus can obtain an appropriate sales plan and raw material ordering plan based on the information provided.

[0072] According to this embodiment, the analysis server 120 optimizes the initial sales plan based on the sales target and the predicted demand for the product, so as to maximize gross profit while achieving the sales target (sales budget), and generates a product sales plan (initial sales plan). Then, based on the generated product sales plan (initial sales plan) and raw material / recipe information regarding the raw materials of the product, the analysis server 120 optimizes raw material adjustments so as to minimize the surplus of raw materials, and generates a product sales plan that also includes information on the number of raw materials used for each raw material. As a result, the analysis server 120 can generate a plan that maximizes gross profit and suppresses raw material surplus while achieving the sales target (sales budget). For example, users such as employees can obtain an appropriate product sales plan and raw material ordering plan based on the plan generated by the analysis server 120. Therefore, it becomes possible to stabilize the freshness of products and reduce costs in raw material inventory management. In addition, it becomes unnecessary to adjust sales quantities, etc., to minimize raw material surplus, and the workload of employees can be reduced.

[0073] In the above description, the analysis server 120 predicts the number of visitors and the demand for products in the future. However, the prediction may be made by another device different from the analysis server 120, and the analysis server 120 may acquire the prediction results from the other device and generate a sales plan for the products. Also, in the above description, the analysis server 120 (sales plan generation unit 508) generates a sales plan for products based on both the visitor prediction results and the demand prediction results. However, the sales plan may be generated based only on the demand prediction results without using the visitor prediction results.

[0074] Furthermore, the analysis server 120 may acquire manufacturer data such as the order availability date, lead time, and other constraint information from the manufacturer that supplies the raw materials, and generate a sales plan for the product taking into account the manufacturer's constraints.

[0075] The embodiments described above are not limited to in-store packaged products prepared and packaged within each store, but can also be applied to products prepared and packaged at process centers such as food factories, so-called process center products, and products where raw materials or food are processed and packaged outside the store, so-called out-packed products.

[0076] It should be noted that the embodiments described above are merely examples of how the present invention can be implemented, and the technical scope of the present invention should not be interpreted as being limited by them. In other words, the present invention can be implemented in various forms without departing from its technical concept or its main features. [Explanation of Symbols]

[0077] 100 Information Processing Systems 110 Data Management Server 120 Analysis Servers 130 Terminal devices 501 Communications Department 502 Control Unit 503 Input / Output Control Unit 504 Storage section 505 Acquisition Department 506 Visitor Forecasting Department 507 Demand Forecasting Department 508 Sales Planning Department 509 First plan generation unit 510 Second plan generation unit

Claims

1. A first plan generation means that generates a first optimized sales plan for the product by deriving the number of units of the product to be sold that will satisfy the sales target and maximize gross profit, based on the acquired sales target and the predicted demand for the product based on sales performance data, An information processing device comprising: a second plan generation means for generating a second optimization result for a sales plan for the product, which is optimized based on the first optimization result generated and raw material information relating to the raw materials of the product obtained, such that the number of sales of the product included in the first optimization result is optimized so as to minimize the surplus of the raw materials relating to the product.

2. The information processing apparatus according to claim 1, characterized in that the second plan generation means performs optimization by setting the maximum number among the number required to consume the surplus raw materials, the number obtained by multiplying the first optimization result by an allowable ratio, and the minimum production number as constraints.

3. The information processing apparatus according to claim 1 or 2, characterized in that the second plan generation means performs optimization by limiting the difference between the number of raw materials used in the first optimization result and the number of raw materials used in the second optimization result to a predetermined number.

4. The information processing apparatus according to claim 1 or 2, characterized in that the first plan generation means optimizes by setting the number obtained by multiplying the predicted demand for the product by a correction coefficient as a constraint, and generates the first optimization result.

5. The information processing apparatus according to claim 4, characterized in that the correction coefficient is set according to the classification obtained by ABC analysis of the product.

6. The first plan generation means optimizes by setting the predicted demand for the product as the lower limit of the number of units sold for the product as a constraint, and generates the first optimization result. The information processing apparatus according to claim 1 or 2, characterized in that the second plan generation means performs optimization by setting the number of sales of the product in the first optimization result as the lower limit of the number of sales of the product as a constraint condition.

7. The information processing apparatus according to claim 1 or 2, wherein the second plan generation means performs optimization by setting, as a constraint, the increase ratio of the number of units sold of the product to the predicted demand for the product to be equal to or greater than the increase ratio of the number of units sold of the product in the first optimization result to the predicted demand for the product.

8. The information processing apparatus according to claim 1, characterized in that it has a demand forecasting means for predicting the demand for the product based on the sales performance data.

9. The system includes a customer prediction means that predicts the number of customers based on the aforementioned sales performance data. The information processing apparatus according to claim 8, characterized in that the demand forecasting means forecasts the demand for the product based on the number of visitors predicted by the visitor forecasting means and the sales performance data.

10. The information processing apparatus according to claim 1 or 2, characterized in that the aforementioned product is an in-store package product.

11. The information processing apparatus according to claim 1 or 2, characterized in that the aforementioned product is a process center product.

12. An information processing method performed by an information processing device, A first plan generation step that generates a first optimized sales plan for the product by deriving the number of units of the product to be sold that will satisfy the sales target and maximize gross profit, based on the acquired sales target and the predicted demand for the product based on sales performance data, An information processing method characterized by comprising: a second plan generation step, which generates a second optimization result of a sales plan for the product, which is optimized based on the first optimization result that has been generated and raw material information relating to the raw materials of the product that has been acquired, so as to minimize the surplus of the raw materials relating to the product, and which includes the number of sales of the product included in the first optimization result that has been generated.

13. In the computer of the information processing device, A first plan generation step that generates a first optimized sales plan for the product by deriving the number of units to be sold that will satisfy the sales target and maximize gross profit, based on the acquired sales target and the predicted demand for the product based on sales performance data, A program that causes the program to execute a second plan generation step, which generates a second optimized sales plan for the product, based on the first optimized sales result generated and the raw material information for the raw materials of the product obtained, by optimizing the number of sales of the product included in the first optimized sales result so that the surplus of raw materials for the product is minimized.

Images