Information processing method, information processing device, and information processing program

Abstract

The information processing device calculates a predicted sales amount, a predicted sales upper limit amount, and a predicted sales lower limit amount for each unit period in the future for a given product, calculates a predicted inventory amount for each unit period in the future for the given product that satisfies a constraint condition in which, in a case where the predicted sales amount becomes the predicted sales upper limit amount, the predicted remaining order amount does not exceed the maximum remaining order amount, and in a case where the predicted sales amount becomes the predicted sales lower limit amount, the predicted inventory amount does not exceed the maximum inventory amount, based on the actual inventory amount, the predicted sales amount, and the predicted inventory amount, calculates a predicted production amount for each unit period in the future for the given product, and outputs the predicted production amount for each unit period.

Description

Technical Field

[0001] This disclosure relates to techniques for calculating the predicted production volume of a given product per unit period and outputting the predicted production volume per unit period. Background Technology

[0002] In the past, companies used the PSI (Production, Sales, Inventory) tool in their ordering operations. The PSI tool forecasts the future sales volume of a product, determines the appropriate inventory level, and then determines the production or order quantity to achieve the forecasted sales volume and the determined inventory level.

[0003] For example, the ordering assistance device shown in Patent Document 1 includes: a demand forecasting processing unit that forecasts demand based on PSI (production / sales / inventory) data; an inventory diagnosis processing unit that determines stockouts and excess inventory of a product based on PSI data; and a visualization processing unit that calculates future inventory data based on PSI data and the demand forecasting results of the demand forecasting processing unit, and displays the future inventory status together with future production / sales data on a time axis of a chart defined by a time axis and inventory levels.

[0004] Additionally, for example, the inventory replenishment system shown in Patent Document 2 includes: a storage device that stores information on the production capacity of multiple items, information on the minimum batch size, unit batch size, and maximum batch size of the inventory replenishment amount for each item, information on the inventory baseline quantity, maximum inventory quantity, and cumulative replenishment quantity for each item, and information on the current effective inventory quantity for each item; and a processing device that calculates the inventory replenishment amount for each item based on the various information stored in the storage device.

[0005] In addition, for example, the production status visualization system shown in Patent Document 3 produces production process model information for each of multiple processes, which can know the required element items, the number of required element items, and the destination of the finished product. For multiple processes, based on the number of element items, the smaller of either the producible number or the production plan number, which represents the maximum number of finished products that can be produced in that process, is set as the production reservation number, and the sum of the production reservation number and the inventory number is determined as the output number.

[0006] However, in the aforementioned prior technologies, while considering the constraints of the production site, the optimal inventory level is determined by forecasting sales volume, but the forecasted production volume is not automatically determined by the forecasted inventory level, which requires further improvement.

[0007] Prior art literature

[0008] Patent documents

[0009] Patent Document 1: Japanese Patent Application Publication No. 2021-174452

[0010] Patent Document 2: Japanese Patent No. 4624191

[0011] Patent Document 3: Japanese Patent Application Publication No. 2022-113032 Summary of the Invention

[0012] This disclosure was made to solve the above-mentioned problems, and its purpose is to provide a technology that can take into account the constraints of the production site and use the predicted sales volume to determine the optimal predicted inventory level, and can use the predicted inventory level to automatically determine the predicted production volume.

[0013] The information processing method disclosed herein is executed by a computer, and the information processing method includes: obtaining the past performance production volume, performance sales volume, performance inventory volume, and performance remaining order volume for a given product in each unit period; obtaining the maximum inventory volume and maximum remaining order volume for the given product in a unit period; based on the performance sales volume, calculating the future predicted sales volume for the given product in each unit period, the upper limit of predicted sales volume allowed if the sales volume is higher than the predicted sales volume, and the lower limit of predicted sales volume allowed if the sales volume is lower than the predicted sales volume; based on the performance inventory volume, the performance remaining order volume, the maximum inventory volume, and the performance remaining order volume, the method calculates the future predicted sales volume for the given product in each unit period, the upper limit of predicted sales volume allowed if the sales volume is higher than the predicted sales volume, and the lower limit of predicted sales volume allowed if the sales volume is lower than the predicted sales volume; and based on the performance inventory volume, the performance remaining order volume, the maximum inventory volume, and the performance remaining order volume, the method calculates the future predicted sales volume for the given product in each unit period. Using the maximum remaining order quantity, the predicted sales quantity, the predicted upper sales limit, and the predicted lower sales limit, calculate the predicted inventory level for each unit period of the given product in the future, satisfying the constraints that, if the predicted sales quantity becomes the predicted upper sales limit, the predicted remaining order quantity does not exceed the maximum remaining order quantity, and if the predicted sales quantity becomes the predicted lower sales limit, the predicted inventory level does not exceed the maximum inventory level; based on the actual inventory level, the predicted sales quantity, and the predicted inventory level, calculate the predicted production quantity for each unit period of the given product in the future; and output the predicted production quantity for each unit period.

[0014] According to this disclosure, it is possible to take into account production site constraints and use forecasted sales volume to determine the optimal forecasted inventory level, and to use the forecasted inventory level to automatically determine the forecasted production volume. Attached Figure Description

[0015] Figure 1 This is a diagram illustrating the structure of the production support system involved in this embodiment.

[0016] Figure 2 This is a diagram illustrating an example of PSI data in this embodiment.

[0017] Figure 3This is a diagram illustrating an example of the setting data in this embodiment.

[0018] Figure 4 This is a flowchart illustrating the predictive processing performed by the information processing apparatus in embodiments of this disclosure.

[0019] Figure 5 This is a schematic diagram illustrating the calculation of the predicted inventory quantity performed by the predicted inventory quantity calculation unit in this embodiment in more detail.

[0020] Figure 6 This is a diagram illustrating an example of the predicted sales volume, predicted upper sales volume, predicted lower sales volume, predicted inventory volume, and predicted production volume displayed on the display unit for each unit period in this embodiment.

[0021] Figure 7 This figure shows an example of a user interface screen displayed on the display unit in this embodiment.

[0022] Figure 8 This is a diagram illustrating an example of a user interface screen displayed on the display unit in this embodiment, which includes the predicted sales volume, predicted inventory volume, and predicted production volume per unit period. Detailed Implementation

[0023] (The understanding that forms the basis of this disclosure)

[0024] The aforementioned previous technologies each had their own problems and did not simultaneously consider all factors and automate the business processes on the production floor.

[0025] Patent Document 1 predicts future production, sales, and inventory levels several months in advance, determines future inventory based on these predictions, and automatically determines the ordering date and order quantity based on the prediction results. However, Patent Document 1 does not consider production site constraints such as maximum inventory levels and maximum remaining order quantities within a unit period.

[0026] Furthermore, Patent Document 2 mentioned above does not use predicted sales volume to calculate inventory replenishment, so it is unknown whether inventory can be further reduced from the current inventory baseline.

[0027] Furthermore, the aforementioned Patent Document 3 only highlights the rectangular area of ​​the number of units that can be produced when the number of units produced is less than the number of units planned for production, and does not automatically calculate the number of units planned for production based on constraints.

[0028] To address the above issues, the following technology has been disclosed.

[0029] (1) The information processing method involved in one aspect of this disclosure is executed by a computer, the information processing method comprising: obtaining the past performance production volume, performance sales volume, performance inventory volume, and performance remaining order volume for a given product in each unit period; obtaining the maximum inventory volume and maximum remaining order volume of the given product in a unit period; calculating, based on the performance sales volume, the future predicted sales volume for the given product in each unit period, the upper limit of predicted sales volume allowed when the sales volume is higher than the predicted sales volume, and the lower limit of predicted sales volume allowed when the sales volume is lower than the predicted sales volume; and calculating, based on the performance inventory volume, the performance remaining order volume, and the maximum inventory volume... The system calculates the projected inventory level for each unit period of the given product, satisfying the following constraints: when the projected sales volume reaches the projected sales upper limit, the projected remaining order volume does not exceed the maximum remaining order volume; and when the projected sales volume reaches the projected sales lower limit, the projected inventory level does not exceed the maximum inventory level. Based on the actual inventory level, the projected sales volume, and the projected inventory level, the system calculates the projected production volume for each unit period of the given product; and outputs the projected production volume for each unit period.

[0030] Based on this structure, the projected sales volume for each unit period of a given product in the future, the upper limit of projected sales volume allowed when sales volume exceeds the projected sales volume, and the lower limit of projected sales volume allowed when sales volume falls below the projected sales volume are calculated, based on the actual sales volume of the given product in the past. Furthermore, the projected inventory level for each unit period of the future for a given product is calculated, satisfying the following constraints: if the projected sales volume reaches the upper limit of projected sales volume, the projected remaining order quantity does not exceed the maximum remaining order quantity; and if the projected sales volume reaches the lower limit of projected sales volume, the projected inventory level does not exceed the maximum inventory level. Finally, based on the actual inventory level, the projected sales volume, and the projected inventory level, the projected production volume for each unit period of the future for a given product is calculated.

[0031] Therefore, it is possible to take into account constraints at the production site and use the predicted sales volume to determine the optimal predicted inventory level, and to use the predicted inventory level to automatically determine the predicted production volume.

[0032] (2) In the information processing method described in (1) above, the output may include: outputting the predicted sales volume, the predicted upper limit of sales volume, the predicted lower limit of sales volume, the predicted inventory volume and the predicted production volume for each unit period.

[0033] According to this structure, the predicted sales volume, predicted upper sales volume, predicted lower sales volume, predicted inventory, and predicted production volume for each unit period are output to the display unit, thereby enabling the user to be prompted with the predicted sales volume, predicted upper sales volume, predicted lower sales volume, predicted inventory, and predicted production volume for each unit period.

[0034] (3) In the information processing method described in (1) or (2) above, the information processing method may also include: obtaining the maximum production volume of the given product within a unit period; and increasing the predicted inventory volume in the second unit period before the first unit period if the predicted sales volume in the first unit period exceeds the maximum production volume.

[0035] According to this structure, even if the predicted sales volume in the first unit period exceeds the maximum production volume, the inventory added in advance in the second unit period before the first unit period can be used for sales.

[0036] (4) In any of the information processing methods described in (1) to (3) above, the calculation of the predicted sales volume, the predicted upper limit of sales volume and the predicted lower limit of sales volume may include: inputting the actual sales volume into a prediction model made in advance through learning, obtaining the predicted sales volume, the predicted upper limit of sales volume and the predicted lower limit of sales volume output from the prediction model, and thereby calculating the predicted sales volume, the predicted upper limit of sales volume and the predicted lower limit of sales volume.

[0037] Based on this structure, the predicted sales volume, the upper limit of the predicted sales volume, and the lower limit of the predicted sales volume can be easily calculated using a prediction model that has been learned in advance.

[0038] (5) In any of the information processing methods described in (1) to (4) above, the information processing method may further include: obtaining calendar information related to past and future weeks and holidays, weather information related to past and future weather, and past actual sales volume of similar products of the given product. The calculation of the predicted sales volume, the predicted upper sales volume, and the predicted lower sales volume includes: calculating the predicted sales volume, the predicted upper sales volume, and the predicted lower sales volume based on the actual sales volume of the given product, the calendar information, the weather information, and the actual sales volume of similar products.

[0039] According to this structure, not only the actual sales volume of a given product, but also calendar information related to past and future weeks and holidays, weather information related to past and future weather, and the past actual sales volume of similar products of the given product are used to calculate the predicted sales volume, the upper limit of predicted sales volume, and the lower limit of predicted sales volume. Therefore, the predicted sales volume, the upper limit of predicted sales volume, and the lower limit of predicted sales volume can be calculated with higher accuracy.

[0040] (6) In any of the information processing methods described in (1) to (5) above, the calculation of the predicted inventory may include: using the actual inventory and the actual remaining order quantity in the unit period t-1, the predicted sales quantity in the unit period t, and the variable production quantity in the unit period t, to calculate the predicted inventory and the predicted remaining order quantity in the unit period t; by changing the production quantity, to calculate multiple combinations of the predicted inventory and the predicted remaining order quantity in the unit period t; selecting the combination among the multiple combinations that satisfies the constraint condition and has the smallest total of the predicted inventory and the predicted remaining order quantity; and calculating the predicted inventory in the selected combination as the predicted inventory in the unit period t.

[0041] If we have the projected sales volume and production volume for a unit period t, and the actual inventory volume and actual remaining orders for a unit period t-1, then the projected inventory volume can be calculated. Here, the production volume for a unit period t is the variable. By varying the production volume, multiple combinations of projected inventory volume and projected remaining orders for a unit period t are calculated. Then, the combination that satisfies the constraints and minimizes the total projected inventory volume and projected remaining orders is selected. Finally, the projected inventory volume of the selected combination is calculated as the projected inventory volume for a unit period t.

[0042] Therefore, by calculating the minimum forecast inventory that satisfies the constraints, the forecast inventory can be optimized.

[0043] (7) In any of the information processing methods described in (1) to (6) above, the calculation of the predicted production volume may include: adding the predicted inventory volume to the predicted sales volume, subtracting the actual inventory volume from the volume obtained by the addition, thereby calculating the predicted production volume.

[0044] Based on this structure, the predicted production volume can be calculated by adding the predicted inventory volume to the predicted sales volume and subtracting the actual inventory volume from the sum.

[0045] (8) In any of the information processing methods described in (1) to (7) above, the calculation of the predicted inventory may include: calculating the predicted inventory of each of the multiple warehouses in the case that the given product moves through multiple warehouses from production to sale during each predicted unit period.

[0046] Based on this structure, even when there is a lead time between production and sale, the predicted inventory and predicted production can be calculated by taking the lead time into account.

[0047] Furthermore, this disclosure can be implemented not only as an information processing method that performs the characteristic processes described above, but also as an information processing apparatus or the like that having a characteristic structure corresponding to the characteristic processes performed by the information processing method. Additionally, it can be implemented as a computer program that causes a computer to execute the characteristic processes included in such an information processing method. Therefore, the following other embodiments can also achieve the same effect as the information processing method described above.

[0048] (9) An information processing apparatus according to another aspect of this disclosure comprises: a first acquisition unit for acquiring past performance production volume, performance sales volume, performance inventory volume, and performance remaining order volume for a given product per unit period; a second acquisition unit for acquiring the maximum inventory volume and maximum remaining order volume of the given product per unit period; a first calculation unit for calculating, based on the performance sales volume, the predicted sales volume of the given product per future unit period, an upper limit of predicted sales volume allowed if the sales volume is higher than the predicted sales volume, and a lower limit of predicted sales volume allowed if the sales volume is lower than the predicted sales volume; and a second calculation unit for calculating, based on the performance inventory volume, the performance remaining order volume, and the maximum inventory volume... The system calculates the projected inventory level for each unit period of the given product in the future, based on the maximum remaining order quantity, the projected sales quantity, the projected upper sales limit, and the projected lower sales limit, wherein the projected remaining order quantity does not exceed the maximum remaining order quantity when the projected sales quantity becomes the projected upper sales limit, and the projected inventory level does not exceed the maximum inventory level when the projected sales quantity becomes the projected lower sales limit; the third calculation unit calculates the projected production quantity for each unit period of the given product in the future, based on the actual inventory level, the projected sales quantity, and the projected inventory level; and the output unit outputs the projected production quantity for each unit period.

[0049] (10) The information processing program involved in another aspect of this disclosure enables a computer to perform the following functions: obtain past performance production volume, performance sales volume, performance inventory volume, and performance remaining order volume for a given product in each unit period; obtain the maximum inventory volume and maximum remaining order volume for the given product in a unit period; and, based on the performance sales volume, calculate the future projected sales volume for the given product in each unit period, the upper limit of projected sales volume allowed if the sales volume is higher than the projected sales volume, and the lower limit of projected sales volume allowed if the sales volume is lower than the projected sales volume; and, based on the performance inventory volume, the performance remaining order volume, the maximum inventory volume, and the performance remaining order volume, calculate the future projected sales volume for the given product in each unit period, the upper limit of projected sales volume allowed if the sales volume is higher than the projected sales volume, and the lower limit of projected sales volume allowed if the sales volume is lower than the projected sales volume; and, based on the performance inventory volume, the performance remaining order volume, the maximum inventory volume, and the performance remaining order volume, calculate the future projected sales volume for the given product in each unit period. Given the maximum remaining order quantity, the predicted sales quantity, the predicted upper sales limit, and the predicted lower sales limit, calculate the predicted inventory quantity for each unit period of the given product in the future, satisfying the following constraints: if the predicted sales quantity becomes the predicted upper sales limit, the predicted remaining order quantity does not exceed the maximum remaining order quantity; and if the predicted sales quantity becomes the predicted lower sales limit, the predicted inventory quantity does not exceed the maximum inventory quantity. Based on the actual inventory quantity, the predicted sales quantity, and the predicted inventory quantity, calculate the predicted production quantity for each unit period of the given product in the future, and output the predicted production quantity for each unit period.

[0050] (11) Another aspect of this disclosure relates to a non-transitory computer-readable recording medium recording information processing program, the information processing program causing a computer to perform the following functions: obtaining past performance production volume, performance sales volume, performance inventory volume, and performance remaining order volume for a given product per unit period; obtaining the maximum inventory volume and maximum remaining order volume for the given product per unit period; calculating, based on the performance sales volume, the projected sales volume for the given product per future unit period, the upper limit of projected sales volume allowed if the sales volume is higher than the projected sales volume, and the lower limit of projected sales volume allowed if the sales volume is lower than the projected sales volume; and based on the performance inventory volume and the performance remaining order volume... Using the remaining order quantity, the maximum inventory quantity, the maximum remaining order quantity, the predicted sales quantity, the predicted upper sales limit, and the predicted lower sales limit, calculate the predicted inventory quantity for each future unit period of the given product, which satisfies the following constraints: if the predicted sales quantity becomes the predicted upper sales limit, the predicted remaining order quantity does not exceed the maximum remaining order quantity; and if the predicted sales quantity becomes the predicted lower sales limit, the predicted inventory quantity does not exceed the maximum inventory quantity. Based on the actual inventory quantity, the predicted sales quantity, and the predicted inventory quantity, calculate the predicted production quantity for each future unit period of the given product, and output the predicted production quantity for each unit period.

[0051] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. Furthermore, the embodiments described below represent specific examples of the present disclosure. The numerical values, shapes, constituent elements, steps, and order of steps shown in the following embodiments are examples and are not intended to limit the present disclosure. Additionally, any constituent elements in the following embodiments that are not described in the independent claim representing the highest-level concept will be described as arbitrary constituent elements. Furthermore, various elements can be combined in all embodiments.

[0052] (Implementation Method)

[0053] Figure 1 This is a diagram illustrating the structure of the production support system involved in this embodiment.

[0054] Figure 1 The production support system shown includes an information processing device 1, an input unit 2, and a display unit 3.

[0055] Input unit 2, such as a keyboard, mouse, or touch panel, accepts user input of information. Input unit 2 is communicatively connected to information processing device 1 via wired or wireless means. Alternatively, input unit 2 can also be communicatively connected to information processing device 1 via a network, which can be a local area network (LAN) or a wide area network (WAN).

[0056] The information processing device 1 includes a processor 11, a memory 12, and a communication unit 13. The information processing device 1 is, for example, a personal computer, a tablet computer, or a server.

[0057] The processor 11 is, for example, a CPU (Central Processing Unit). The processor 11 enables the PSI data acquisition unit 111, the setting data acquisition unit 112, the sales forecast calculation unit 113, the inventory forecast calculation unit 114, the production forecast calculation unit 115, and the output unit 116.

[0058] The memory 12 is, for example, a storage device capable of storing various types of information, such as RAM (Random Access Memory), HDD (Hard Disk Drive), SSD (Solid State Drive), or flash memory. The memory 12 stores various types of information.

[0059] Memory 12 stores PSI data and setting data.

[0060] Figure 2 This is a diagram illustrating an example of PSI data in this embodiment. Figure 3 This is a diagram illustrating an example of the setting data in this embodiment.

[0061] PSI data includes: past performance for each unit period of a given product, including performance production, performance sales, performance inventory, and performance remaining orders. For example... Figure 2 As shown, memory 12 stores PSI data corresponding to the product number, date (year and month), actual production volume, actual sales volume, actual inventory, and actual remaining order quantity used to identify the product. For example, in Figure 2 The diagram shows the actual production volume, actual sales volume, actual inventory volume, and actual remaining order volume for product number "a01" in June and July 2023. Furthermore, the unit period in this embodiment is one month, but this disclosure is not particularly limited to this; it can also be one day, one week, or any other period.

[0062] Actual production volume represents the quantity of a given product produced within a unit period. Additionally, when the product is manufactured by another company's factory, production volume is also called order volume. Actual sales volume represents the quantity of a given product sold within a unit period. Actual inventory volume represents the quantity of a given product held as inventory at the end of the unit period. Actual remaining orders volume represents the quantity of a given product ordered within a unit period that was not delivered at the end of the unit period. Furthermore, remaining orders may sometimes arise even if there is existing inventory, for reasons such as wanting to ensure a certain level of inventory.

[0063] In addition, memory 12 can also store PSI data corresponding to the product number used to identify the product and the information used to identify the customer, date, actual production volume, actual sales volume, actual inventory, and actual remaining order quantity.

[0064] The data settings include: the maximum production volume, maximum inventory level, and maximum remaining order quantity for a given product within a given period. For example... Figure 3 As shown, memory 12 stores corresponding configuration data for identifying the product number, maximum production quantity within a unit period, maximum inventory quantity within a unit period, and maximum remaining order quantity within a unit period. For example, in Figure 3 The table shows the maximum production volume, maximum inventory, and maximum remaining order quantity for products with product numbers "a01" and "a02" within a given period. Furthermore, the period is the same as the PSI data period, for example, one month.

[0065] Maximum production capacity represents the maximum quantity of a given product that can be produced within a unit period. Maximum inventory represents the maximum quantity of a given product that can be held as inventory within a unit period. Maximum remaining order quantity represents the maximum quantity of a given product ordered within a unit period that is allowed to be delivered even if delivery cannot be made at the end of the unit period.

[0066] Input unit 2 accepts user input of PSI data. The processor 11 of information processing device 1 stores the PSI data input by input unit 2 in memory 12. Additionally, input unit 2 accepts user input of setting data. The processor 11 of information processing device 1 stores the setting data input by input unit 2 in memory 12.

[0067] In addition, the information processing device 1 can also receive PSI data or setting data from external devices such as servers, and store the received PSI data or setting data in the memory 12.

[0068] In addition, input unit 2 accepts user selections for forecasting production volume, sales volume, inventory volume, and remaining order volume for each unit period. Input unit 2 can also accept user selections for forecasting unit periods such as 1 day, 1 week, or 1 month. Furthermore, input unit 2 can also accept user selections for forecasting periods such as 1 week, 1 month, or 6 months.

[0069] The PSI data acquisition unit 111 acquires the past performance production volume, sales volume, inventory volume, and remaining order volume for a given product in each past unit period. The PSI data acquisition unit 111 reads PSI data from the memory 12, which includes the past performance production volume, sales volume, inventory volume, and remaining order volume for the given product in each past unit period. For example, the PSI data acquisition unit 111 can also read PSI data for each month of the past year from the memory 12. Furthermore, the memory 12 stores daily PSI data, and when the monthly production volume, sales volume, inventory volume, and remaining order volume are predicted, the PSI data acquisition unit 111 can also aggregate the daily PSI data to generate monthly PSI data.

[0070] In addition, the PSI data acquisition unit 111 can also acquire the past sales volume of similar products for a given product. The PSI data acquisition unit 111 can also read the past sales volume of similar products from the memory 12.

[0071] The setting data acquisition unit 112 acquires the maximum production quantity, maximum inventory quantity, and maximum remaining order quantity of a given product within a unit period. The setting data acquisition unit 112 reads setting data containing the maximum production quantity, maximum inventory quantity, and maximum remaining order quantity of a given product within a unit period from the memory 12.

[0072] The communications unit 13 acquires calendar information related to past and future weeks and holidays, and weather information related to past and future weather. The communications unit 13 receives calendar information and weather information sent from an external server. The weather information includes, for example, the weather for the past year and the weather for the next week. The weather information can also be used to calculate predicted sales volume on a daily or weekly basis.

[0073] Based on the actual sales volume of a given product, calendar information, weather information, and the actual sales volume of similar products, the sales volume forecasting unit 113 calculates the forecasted sales volume for each unit period of the future for the given product, the upper limit of the forecasted sales volume allowed if the sales volume is higher than the forecasted sales volume, and the lower limit of the forecasted sales volume allowed if the sales volume is lower than the forecasted sales volume. For example, the sales volume forecasting unit 113 calculates the forecasted sales volume, the upper limit of the forecasted sales volume, and the lower limit of the forecasted sales volume for each month of the next 6 months for the given product.

[0074] The sales volume prediction calculation unit 113 inputs the actual sales volume of the given product, calendar information, weather information, and the actual sales volume of similar products into the prediction model that has been prepared in advance through learning, and obtains the predicted sales volume, the upper limit of predicted sales volume, and the lower limit of predicted sales volume output from the prediction model, thereby calculating the predicted sales volume, the upper limit of predicted sales volume, and the lower limit of predicted sales volume.

[0075] The sales volume prediction calculation unit 113 inputs the acquired sales volume of the given product, calendar information, weather information, and the sales volume of similar products, as well as the relationship between the sales volume, the upper limit of sales volume, and the lower limit of sales volume, into a prediction model obtained by machine learning.

[0076] Furthermore, the predictive model is created through machine learning. Examples of machine learning include supervised learning, which uses labeled (output information) teaching data to learn the relationship between input and output; unsupervised learning, which constructs data based solely on unlabeled input; semi-supervised learning, which processes both labeled and unlabeled data; and reinforcement learning, which learns actions to maximize rewards through trial and error. Specific methods of machine learning include neural networks (including deep learning using multi-layered neural networks), genetic programming, decision trees, Bayesian networks, and support vector machines (SVMs). In the machine learning disclosed herein, any of the specific examples listed above may be used.

[0077] Machine learning for predictive models can also take the past three months' actual sales volume, calendar information, weather information, and actual sales volume of similar products as input values, and the current month's sales volume, upper sales limit, and lower sales limit of the given product as output values. Alternatively, the predictive model can further utilize previously calculated predicted sales volume for machine learning. In this case, the difference between actual sales volume and predicted sales volume can be used as teaching data for the upper and lower sales limits.

[0078] Alternatively, the sales volume calculation unit 113 can calculate the projected sales volume, projected upper sales volume, and projected lower sales volume for a given product per unit period based solely on the product's actual sales volume. The sales volume calculation unit 113 can also input the product's actual sales volume into a pre-learned prediction model, obtain the projected sales volume, projected upper sales volume, and projected lower sales volume output from the prediction model, and thereby calculate the projected sales volume, projected upper sales volume, and projected lower sales volume.

[0079] Additionally, the sales volume prediction calculation unit 113 can also calculate the predicted sales volume, predicted upper sales volume, and predicted lower sales volume for a given product per unit period based on at least one of the given product's actual sales volume, calendar information, weather information, and the actual sales volume of similar products. The sales volume prediction calculation unit 113 can also input at least one of the given product's actual sales volume, calendar information, weather information, and the actual sales volume of similar products into a prediction model created in advance through learning, and obtain the predicted sales volume, predicted upper sales volume, and predicted lower sales volume output from the prediction model, thereby calculating the predicted sales volume, predicted upper sales volume, and predicted lower sales volume.

[0080] The forecast inventory calculation unit 114 calculates the forecast inventory level for a given product for each future unit period based on the actual inventory level, actual remaining order quantity, maximum inventory level, maximum remaining order quantity, forecasted sales volume, forecasted upper sales volume, and forecasted lower sales volume, satisfying the following constraints: if the forecasted sales volume is the forecasted upper sales volume, the forecasted remaining order quantity does not exceed the maximum remaining order quantity; and if the forecasted sales volume is the forecasted lower sales volume, the forecasted inventory level does not exceed the maximum inventory level. For example, the forecast inventory calculation unit 114 calculates the forecast inventory level for each month of the next 6 months for a given product.

[0081] More specifically, the inventory forecasting unit 114 uses the actual inventory and actual remaining order quantity within unit period t-1, the forecasted sales quantity within unit period t, and the variable production quantity within unit period t to calculate the forecasted inventory and forecasted remaining order quantity within unit period t. Next, the inventory forecasting unit 114 calculates multiple combinations of the forecasted inventory and forecasted remaining order quantity within unit period t by varying the production quantity. Next, the inventory forecasting unit 114 selects the combination among the multiple combinations that satisfies the constraints and has the smallest total of forecasted inventory and forecasted remaining order quantity. Next, the inventory forecasting unit 114 calculates the forecasted inventory quantity of the selected combination as the forecasted inventory quantity within unit period t. Furthermore, the inventory forecasting unit 114 sequentially calculates the forecasted inventory quantities for unit periods t+1, t+2, t+3, t+4, and t+5.

[0082] The production forecast calculation unit 115 calculates the projected production volume for a given product per unit period based on the actual inventory level, the projected sales volume, and the projected inventory level. More specifically, the production forecast calculation unit 115 adds the projected inventory level to the projected sales volume and subtracts the actual inventory level from the sum to calculate the projected production volume.

[0083] The output unit 116 outputs the predicted sales volume, predicted upper sales volume, predicted lower sales volume, predicted inventory, and predicted production volume for each unit period to the display unit 3. Alternatively, the output unit 116 may output only the predicted production volume for each unit period to the display unit 3.

[0084] Display unit 3 is, for example, a liquid crystal display device, which displays the information output by output unit 116. Display unit 3 and information processing device 1 are communicatively connected via wired or wireless means. Alternatively, display unit 3 can also be communicatively connected to information processing device 1 via a network, which can be a local area network (LAN) or a wide area network (WAN).

[0085] Display unit 3 displays the predicted sales volume, predicted upper sales limit, predicted lower sales limit, predicted inventory, and predicted production volume for each unit period. Alternatively, display unit 3 can also display only the predicted production volume for each unit period.

[0086] Next, the prediction processing performed by the information processing apparatus 1 in the embodiments of this disclosure will be described.

[0087] Figure 4 This is a flowchart illustrating the prediction processing performed by the information processing apparatus 1 in the embodiments of this disclosure.

[0088] First, in step S1, the PSI data acquisition unit 111 acquires PSI data including past performance production volume, performance sales volume, performance inventory volume, and performance remaining order volume for a given product in each past unit period. Furthermore, the input unit 2 can also accept user input in advance for determining product information and unit period information.

[0089] Next, in step S2, the setting data acquisition unit 112 acquires setting data including the maximum production volume, maximum inventory volume, and maximum remaining order volume for a given product within a unit period. Furthermore, the input unit 2 can also accept user input of the maximum production volume, maximum inventory volume, and maximum remaining order volume in advance.

[0090] Next, in step S3, the communication unit 13 acquires calendar information related to past and future weeks and holidays, and weather information related to past and future weather, and the PSI data acquisition unit 111 acquires the past sales volume per unit period of similar products of the given product.

[0091] Next, in step S4, the sales volume prediction calculation unit 113 calculates the predicted sales volume, the upper limit of predicted sales volume, and the lower limit of predicted sales volume for the given product per unit period based on the actual sales volume of the given product, calendar information, weather information, and the actual sales volume of similar products. The sales volume prediction calculation unit 113 inputs the actual sales volume of the given product, calendar information, weather information, and the actual sales volume of similar products into a prediction model created through prior learning, and obtains the predicted sales volume, the upper limit of predicted sales volume, and the lower limit of predicted sales volume output from the prediction model.

[0092] Next, in step S5, the predicted inventory calculation unit 114 calculates the predicted inventory for a given product per unit period that satisfies the following constraints based on the actual inventory, actual remaining order quantity, maximum inventory, maximum remaining order quantity, predicted sales quantity, predicted upper sales quantity, and predicted lower sales quantity: when the predicted sales quantity becomes the predicted upper sales quantity, the predicted remaining order quantity does not exceed the maximum remaining order quantity, and when the predicted sales quantity becomes the predicted lower sales quantity, the predicted inventory does not exceed the maximum inventory.

[0093] Here, the calculation of the optimal predicted inventory level is explained in more detail.

[0094] Figure 5 This is a schematic diagram illustrating in more detail the calculation of the predicted inventory by the predicted inventory calculation unit 114 of this embodiment.

[0095] In addition, Figure 5In this context, the unit period is one month. The inventory forecast calculation department 114 calculates the projected inventory levels for the remainder of the month on the 1st of this month. t p represents the projected sales volume for this month t. t+1 This represents the projected sales volume for next month, t+1. t s represents the projected remaining order quantity for this month t. t+1 This represents the projected remaining order quantity for next month, t+1. t-1 This indicates the remaining order quantity for last month's t-1 performance, z t z represents the predicted inventory level for this month (t). t+1 This represents the projected inventory level for next month, t+1. t-1 This indicates the actual inventory level for last month's t-1 period, o t This indicates the production volume of t this month, o t +1 This indicates the production volume for the next month, t+1.

[0096] The order quantity of t this month is expressed in p. t +s t-1 (o) indicates that the spot quantity of t this month is represented by (o) t +z t-1 (This indicates the quantity of goods delivered this month, t). t Constrained by the smaller of this month's order quantity (t) and spot quantity (t). Therefore, this month's delivery quantity (c) t Use min(p) t +s t-1 o t +z t-1 This indicates the projected remaining order quantity s at the end of this month. t For (p) t +s t-1 -c t Forecast inventory level z at the end of this month t For (o) t +z t-1 -c t .

[0097] After obtaining the combination of the remaining order quantity and the actual inventory quantity of the previous month (t-1), t-1 , z t-1 And obtain the predicted sales volume p for this month t. t In the case of production volume o t When determined, the combination of the projected remaining orders and projected inventory at the end of this month (s) t , z t It is determined automatically.

[0098] If the combination of remaining orders and inventory is considered as a single state, then the state changes according to the production volume of each month.

[0099] The inventory forecast calculation section 114 lists multiple production volumes below the maximum production volume. t o2 t The options, ..., calculate the production quantity o1 for multiple production quantities. t o2 t The changes in the respective monthly state (the combination of forecasted remaining orders and forecasted inventory) of each (s1) t z1 t ), (s2) t z2 t Furthermore, the inventory forecasting unit 114 calculates the changes in the status (combination of forecasted remaining orders and forecasted inventory) of each of the multiple production quantities for the next month onwards. Thus, the inventory forecasting unit 114 can calculate the changes in the status (combination of forecasted remaining orders and forecasted inventory) of the previous month to the forecast period (e.g., 6 months later) on a one-month basis.

[0100] Predicting inventory levels and calculating costs y for each state (section 114) i t The total cost of each month's state is chosen to minimize the state transition. The inventory forecasting unit 114 calculates the cost y of each state based on the following mathematical formula (1). i t .

[0101] y i t =f(o) i t |p t +σ + t s t-1 , z t-1 o t -1 ;s0,z0)+f(o i t |p t -σ - t s t-1 , z t-1 o t -1 ;s0,z0)…(1)

[0102] In the above mathematical expression (1), o i t p is a variable t +σ + t s t-1 z t-1 and o t -1Let be the given variables, and s0 and z0 be constants. The cost y for each state... i t The state i and the time t corresponding to o i t It is considered a variable. The given variable is one that relates to time t, but does not depend on state i. The constant is a fixed value that does not depend on either state i or time t.

[0103] Here, p t +σ + t p represents the predicted upper limit of sales. t -σ - t This indicates the predicted minimum sales volume. The inventory forecast calculation part 114 selects a production volume of 0. t At that time, even if the predicted sales volume p t Become the upper limit of the predicted sales volume p t +σ + t Predicting the remaining order quantity s t It will not exceed the cost of the maximum remaining order quantity s0. Furthermore, the inventory forecasting unit 114 selects a production quantity of 0... t At that time, even if the predicted sales volume p t Become the lower limit of the predicted sales volume p t -σ - t Predicted inventory level z t It will not exceed the cost of the maximum inventory level z0.

[0104] Furthermore, the functions of the first and second terms in the above mathematical expression (1) are represented by the abstract functions shown in the following mathematical expression (2).

[0105] f(o|p,s,z,o';s0,z0)=α[p+sc-s0] + +β[o+zc-z0] + +γ(p+sc)+ω(o+zc)+η(o-o')…(2)

[0106] In mathematical expression (2), c is min(p+s, o+z), and the function [x] + This means max(0, x). Furthermore, in mathematical expression (2), α, β, γ, ω, and η are coefficients. α, β, γ, and ω satisfy the relationship α, β >> γ, ω.

[0107] The inventory forecasting calculation unit 114 lists all states (a combination of forecasted remaining order quantity and forecasted inventory quantity) up to a given period (e.g., 6 months), and selects the state transition that minimizes the total cost from among the multiple states. As shown in mathematical formula (2), due to the forecasted remaining order quantity s t The cost when the remaining order quantity is greater than the maximum remaining order quantity s0 is greater than the predicted remaining order quantity s. t The cost is less than the maximum remaining order quantity s0, therefore predicting the remaining order quantity s is not chosen. t The state is greater than the maximum remaining order quantity s0. Similarly, due to the predicted inventory quantity z t The cost when the inventory level is greater than the maximum inventory level z0 is greater than the predicted inventory level z. t The cost is less than the maximum inventory level z0, therefore, we do not choose to predict the inventory level z. t The state is greater than the maximum inventory level z0.

[0108] Furthermore, the lower the remaining order quantity and inventory level, the better. Therefore, we choose to predict the remaining order quantity s. t And the predicted inventory level z t The total value is the minimum predicted remaining order quantity s t And the predicted inventory level z t The combination of .

[0109] Furthermore, by considering changes in production volume (o t -o t -1 ), select the same production volume for each month (a combination of forecasted remaining orders and forecasted inventory).

[0110] Based on mathematical formula (2), the inventory forecasting unit 114 calculates the cost of combinations of forecasted remaining orders and forecasted inventory for each of the multiple production quantities within a unit period t, and selects the combination of forecasted remaining orders and forecasted inventory with the lowest cost. The inventory forecasting unit 114 calculates the forecasted inventory in the selected combination as the forecasted inventory for the unit period t. Furthermore, the inventory forecasting unit 114 also calculates the forecasted inventory for periods t+1 and beyond using the same method as described above.

[0111] Furthermore, if the predicted sales volume in the first unit period exceeds the maximum production volume, the predicted inventory volume in the second unit period preceding the first unit period can also be increased by the predicted inventory volume in the second unit period. In this case, the predicted inventory volume calculation unit 114 can also add the amount obtained by subtracting the maximum production volume from the predicted sales volume in the first unit period to the predicted inventory volume in the second unit period.

[0112] Furthermore, the inventory forecasting unit 114 can calculate the forecasted inventory level for each of the multiple warehouses when the given product moves between multiple warehouses during each forecasted unit period, from production to sale. In this way, even when there is a lead time from production to sale, the forecasted inventory level and the forecasted production volume can be calculated taking into account the lead time.

[0113] Return to Figure 4 Next, in step S6, the production forecast calculation unit 115 calculates the projected production volume for a given product per unit period based on the actual inventory, projected sales volume, and projected inventory. Here, the production forecast calculation unit 115 adds the projected inventory and the projected sales volume, and subtracts the actual inventory from the sum to calculate the projected production volume.

[0114] Next, in step S7, the output unit 116 outputs the predicted sales volume, predicted upper sales volume, predicted lower sales volume, predicted inventory volume, and predicted production volume for each unit period to the display unit 3.

[0115] Next, in step S8, the display unit 3 displays the predicted sales volume, the predicted upper sales volume, the predicted lower sales volume, the predicted inventory volume, and the predicted production volume for each unit period.

[0116] Figure 6 This is a diagram showing an example of the predicted sales volume, predicted upper sales volume, predicted lower sales volume, predicted inventory volume, and predicted production volume displayed on display unit 3 in this embodiment for each unit period.

[0117] exist Figure 6 In the display unit 3, the predicted sales volume 31, predicted upper sales volume 32, predicted lower sales volume 33, predicted inventory 34, and predicted production volume 35 are displayed monthly for the six months from November to April. Furthermore, within each month, the predicted sales volume 31 and the predicted upper sales volume 32 are connected by a straight line, and the predicted sales volume 31 and the predicted lower sales volume 33 are also connected by a straight line. This allows users to identify the degree to which the predicted upper sales volume 32 and the predicted lower sales volume 33 deviate from the predicted sales volume 31.

[0118] Furthermore, in this embodiment, the predicted sales volume, the predicted upper sales volume, the predicted lower sales volume, the predicted inventory volume, and the predicted production volume for each unit period are displayed. However, this disclosure is not particularly limited to this, and only the predicted production volume may be displayed.

[0119] Figure 7 This diagram shows an example of the user interface screen displayed on the display unit 3 in this embodiment. Figure 6 The displayed screen only shows the prediction results, but in Figure 7 The user interface shown displays the prediction results and accepts user input for data.

[0120] Figure 7 The user interface screen shown includes: PSI data input area 301, product selection area 302, forecast period selection area 303, maximum production input area 304, production quantity option input area 305, maximum inventory input area 306, maximum remaining order quantity input area 307, coefficient input area 308, sales volume display area 309, inventory display area 310, and production volume display area 311.

[0121] PSI data input area 301 accepts user input of past PSI data. Users drag and drop files containing past PSI data into PSI data input area 301. This inputs the past PSI data to be used in the prediction. Alternatively, users can select a file containing past PSI data from multiple files.

[0122] Product selection area 302 displays a drop-down list of multiple selectable product names, which are chosen by the user. The user selects the desired product name from the drop-down list displayed in product selection area 302.

[0123] The forecast period selection area 303 displays a drop-down list where the user can choose the year and month to begin the forecast. The user selects the starting year and month from the drop-down list displayed in the forecast period selection area 303. Once the starting year and month are selected, the forecast results up to 6 months from the selected year and month are displayed.

[0124] The maximum production quantity input area 304 accepts user input of the maximum production quantity for one month. The minimum unit for production quantity is predetermined per product. Therefore, products may be produced in units of 100, 1000, or 10000. The user enters the maximum production quantity for one month by pressing the plus or minus button displayed in the maximum production quantity input area 304.

[0125] The production quantity option input area 305 accepts user input of the number of production quantity options listed when calculating the predicted inventory level. Production quantity options are used when calculating multiple combinations of the predicted remaining order quantity and predicted inventory level per unit period. A larger number of options improves the accuracy of the predicted remaining order quantity and predicted inventory level, but increases the processing time. Conversely, a smaller number of options reduces the accuracy of the predicted remaining order quantity and predicted inventory level, but shortens the processing time. For example, if the user inputs 10 production quantity options and the maximum production quantity is 10,000, 0, 1000, 2000, 3000, ..., 10000 are used as production quantity options (11 options including 0).

[0126] The maximum inventory input area 306 accepts user-inputted maximum inventory for one month.

[0127] The maximum remaining order quantity input area 307 accepts user input for the maximum remaining order quantity for one month.

[0128] The coefficient input area 308 accepts user input of coefficients used to ensure consistent monthly production. The input coefficient is η from the mathematical formula (2) above, multiplied by the difference between the current month's production and the previous month's production. When η increases, the monthly production variation decreases; when η decreases, the monthly production variation increases. Furthermore, η can also be 0. When η is 0, the monthly production variation is not considered when calculating the predicted inventory level.

[0129] Sales volume display area 309 shows the predicted sales volume, predicted upper sales limit, and predicted lower sales limit for each unit period. Figure 7 In the data, the projected sales volume, projected upper sales volume, and projected lower sales volume for the period from January 2024 to six months later are displayed on a monthly basis. Furthermore, sales volume display area 309 not only shows the projected sales volume, projected upper sales volume, and projected lower sales volume for each unit period, but also the actual sales volume for each unit period included in the PSI data. Figure 7 In the data, actual sales volume from April 2023 to 11 months later is displayed on a monthly basis. In addition, projected sales volume and actual sales volume can also be displayed repeatedly.

[0130] Inventory level display area 310 shows the predicted inventory level for each unit period. Figure 7In the data, projected inventory levels from January 2024 to six months later are displayed on a monthly basis. Furthermore, inventory display area 310 shows not only the projected inventory level for each unit period, but also the actual inventory level for each unit period included in the PSI data. Figure 7 In the data, actual inventory levels from April 2023 to 11 months later are displayed on a monthly basis. Furthermore, both projected and actual inventory levels can be displayed repeatedly.

[0131] Production display area 311 shows the predicted production volume per unit period. Figure 7 In the data, projected production volumes from January 2024 to six months later are displayed on a monthly basis. Furthermore, production volume display area 311 shows not only the projected production volume for each unit period, but also the actual production volume for each unit period included in the PSI data. Figure 7 In the data, actual production figures from April 2023 to 11 months later are displayed on a monthly basis. Furthermore, both projected and actual production figures can be displayed repeatedly.

[0132] In addition, the minimum inventory level can be set based on the difference between the predicted sales volume and the predicted upper limit of sales, i.e., the estimation error.

[0133] Figure 8 This figure shows an example of a user interface screen displayed on display unit 3 in this embodiment, which includes the predicted sales volume, predicted inventory volume, and predicted production volume per unit period.

[0134] Figure 8 The user interface shown represents the PSI plan for product number x01. The PSI plan includes: a sales plan (forecasted sales volume), an inventory plan (forecasted inventory level), and a production plan (forecasted production volume). Figure 8 In the display unit 3, the predicted sales volume 41, predicted upper sales volume 42, predicted lower sales volume 43, predicted inventory 44, and predicted production volume 45 are displayed for each of the three months: the current month, the next month, and the month after next. In addition, within each month, the predicted sales volume 41 and the predicted upper sales volume 42 are connected by a straight line, and the predicted sales volume 41 and the predicted lower sales volume 43 are connected by a straight line.

[0135] Upon receiving the actual sales volume of a given product, the sales volume calculation unit 113 automatically calculates the future predicted sales volume 41, the predicted upper sales volume 42, and the predicted lower sales volume 43. The predicted sales volume 41 is represented by dots, and the predicted upper sales volume 42 and the predicted lower sales volume 43 are displayed above and below the predicted sales volume 41. The difference between the predicted sales volume 41 and the predicted upper sales volume 42 is the positive estimate error 421, and the difference between the predicted sales volume 41 and the predicted lower sales volume 43 is the negative estimate error 422. For example, the positive estimate error 421 is +10, and the negative estimate error 422 is -10. The positive estimate error 421 and the negative estimate error 422 can also be different values.

[0136] The positive estimate error 421 is the minimum inventory level (minimum inventory level 441) that should be maintained in inventory planning. Production planning is done with a projected inventory level 44 higher than the minimum inventory level 441. Production planning is done considering the maximum monthly production volume 451 and adjustable production unit quantities. Production unit quantity represents the minimum number of units produced in one month, such as 100 units. Inventory planning is done such that the projected inventory level 44 is as close as possible to the minimum inventory level 441, and the projected inventory level 44 is not lower than the minimum inventory level 441.

[0137] Input unit 2 can also accept adjustments to the positive estimate error 421 made by the user. The user can also adjust the positive estimate error 421 by operating the mouse through the user interface screen. This allows the user's experience with the deviation of the predicted sales volume 41 to be reflected. When the width of the positive estimate error 421 increases, the minimum inventory level 441 increases accordingly.

[0138] Conversely, by manipulating the minimum inventory level 441, the positive estimate error 421 changes. By changing the minimum inventory level 441, users can intuitively understand the extent to which the predicted sales volume 41 is estimated to be at fault.

[0139] Furthermore, when the predicted sales volume 41 exceeds the maximum production volume 451, the production forecast calculation unit 115 increases the previous month's predicted production volume 45. As a result, the predicted inventory level 44 for the previous month increases. This ensures that sales opportunities are not missed. For example, in... Figure 8 In the example, the projected sales volume 41 for the month after next exceeds the maximum production volume 451. Therefore, the projected production volume calculation unit 115 increases the projected production volume 45 for the next month in advance.

[0140] As the projected production volume 45 increases, the projected inventory level 44 increases significantly compared to the minimum inventory level 441. Therefore, at the next month's time, there is excess inventory. However, in the month following, due to the increase in projected sales volume 41, the projected inventory level 44 decreases, and the projected inventory level 44 returns to almost the same level as the minimum inventory level 441.

[0141] Furthermore, the maximum production quantity 451 can be adjusted across multiple product numbers. For example, when producing 100 units of products from two different product numbers, the user can determine the maximum production quantity 451 for each product. For instance, the user can produce 50 units of one product and 50 units of the other, or 70 units of one product and 30 units of the other. Users can also drag the horizontal line indicating the maximum production quantity 451 up and down in the user interface screen of the PSI plan for each product number of interest. When the maximum production quantity 451 is changed, the inventory plan and production plan are recalculated accordingly. When the maximum production quantity 451 of one product number changes, the maximum production quantity 451 of all other product numbers associated with that product number changes in tandem, allowing users to observe each PSI plan and find the optimal balance.

[0142] Furthermore, in the above embodiments, each component may be constructed using dedicated hardware, or implemented by executing software programs suitable for each component. Each component may also be implemented by a program execution unit such as a CPU or processor reading and executing software programs recorded on a recording medium such as a hard disk or semiconductor memory. Alternatively, the program may be implemented via a separate computer system by recording the program on a recording medium and transferring it, or by transferring the program via a network.

[0143] The functionality of the devices described in this disclosure is typically implemented, in whole or in part, as integrated circuits, i.e., LSIs (Large Scale Integration). They can be implemented as a single chip, or partially or entirely as a single chip. Furthermore, integrated circuit implementation is not limited to LSIs; it can also be implemented using dedicated circuits or general-purpose processors. Alternatively, it can utilize FPGAs (Field Programmable Gate Arrays) that are programmable after LSI fabrication, or reconfigurable processors that connect and configure the circuitry within a reconfigurable LSI.

[0144] Alternatively, a CPU or other processor can be used to execute programs to achieve some or all of the functions of the apparatus involved in the embodiments of this disclosure.

[0145] Furthermore, the figures used above are illustrative for the purpose of specifically illustrating this disclosure, and this disclosure is not limited to the illustrative figures.

[0146] Furthermore, the order in which the steps shown in the flowchart above are executed is illustrative for the purpose of specifically illustrating this disclosure, and any other order may be used to achieve the same effect. Additionally, some of the above steps may be executed simultaneously (in parallel) with other steps.

[0147] Industrial availability

[0148] The technology disclosed herein is capable of taking into account production site constraints and using forecasted sales volume to determine the optimal forecasted inventory level, and can automatically determine the forecasted production volume using the forecasted inventory level. Therefore, it is useful as a technology for calculating the forecasted production volume per unit period for a given product and outputting the forecasted production volume per unit period.

Claims

1. An information processing method, executed by a computer, The information processing method includes: Get the past performance production, sales, inventory and remaining orders for a given product for each unit period. Obtain the maximum inventory level and maximum remaining order quantity for the given product within a given period; Based on the actual sales volume, calculate the projected sales volume for each unit period of the given product in the future, the upper limit of projected sales volume allowed if the sales volume is higher than the projected sales volume, and the lower limit of projected sales volume allowed if the sales volume is lower than the projected sales volume. Based on the actual inventory level, the actual remaining order level, the maximum inventory level, the maximum remaining order level, the projected sales level, the projected upper sales level, and the projected lower sales level, calculate the projected inventory level for each unit period of the given product that satisfies the following constraints: when the projected sales level becomes the projected upper sales level, the projected remaining order level does not exceed the maximum remaining order level; and when the projected sales level becomes the projected lower sales level, the projected inventory level does not exceed the maximum inventory level. Based on the actual inventory level, the projected sales volume, and the projected inventory level, calculate the projected production volume for each unit period of the given product in the future. and Output the predicted production volume for each unit period.

2. The information processing method according to claim 1, wherein, The output includes: the predicted sales volume, the predicted upper sales volume, the predicted lower sales volume, the predicted inventory volume, and the predicted production volume for each unit period.

3. The information processing method according to claim 1 or 2, wherein, The information processing method further includes: Obtain the maximum production volume of the given product within a unit period; and If the predicted sales volume during the first unit period exceeds the maximum production volume, the predicted inventory level for the second unit period preceding the first unit period will be increased.

4. The information processing method according to claim 1 or 2, wherein, The calculation of the predicted sales volume, the predicted upper sales volume, and the predicted lower sales volume includes: inputting the actual sales volume into a prediction model created in advance through learning, obtaining the predicted sales volume, the predicted upper sales volume, and the predicted lower sales volume output from the prediction model, and thereby calculating the predicted sales volume, the predicted upper sales volume, and the predicted lower sales volume.

5. The information processing method according to claim 1 or 2, wherein, The information processing method further includes: acquiring calendar information related to past and future weeks and holidays, weather information related to past and future weather, and past sales performance of similar products to the given product. The calculation of the predicted sales volume, the predicted upper sales volume, and the predicted lower sales volume includes: calculating the predicted sales volume, the predicted upper sales volume, and the predicted lower sales volume based on the actual sales volume of the given product, the calendar information, the weather information, and the actual sales volume of similar products.

6. The information processing method according to claim 1 or 2, wherein, The calculation of the predicted inventory includes: Using the actual inventory and the actual remaining order quantity within the unit period t-1, the predicted sales quantity within the unit period t, and the variable production quantity within the unit period t, calculate the predicted inventory and the predicted remaining order quantity within the unit period t. By varying the production volume, multiple combinations of the predicted inventory and the predicted remaining order quantity are calculated for the unit period t. Select the combination that satisfies the constraints and has the smallest sum of the predicted inventory and the predicted remaining order quantity; and The predicted inventory level of the selected combination is calculated as the predicted inventory level for the unit period t.

7. The information processing method according to claim 1 or 2, wherein, The calculation of the predicted production volume includes: adding the predicted inventory volume to the predicted sales volume, and subtracting the actual inventory volume from the sum to calculate the predicted production volume.

8. The information processing method according to claim 1 or 2, wherein, The calculation of the predicted inventory includes: calculating the predicted inventory for each of the multiple warehouses as the given product moves through multiple warehouses from production to sale, during each predicted unit period.

9. An information processing device, comprising: The first acquisition department acquires the past performance production volume, performance sales volume, performance inventory volume and performance remaining order volume for each unit period of a given product. The second acquisition unit acquires the maximum inventory and maximum remaining order quantity of the given product within a unit period. The first calculation unit calculates, based on the actual sales volume, the projected sales volume per unit period for the given product in the future, the upper limit of projected sales volume allowed if the sales volume is higher than the projected sales volume, and the lower limit of projected sales volume allowed if the sales volume is lower than the projected sales volume. The second calculation unit calculates the projected inventory for each unit period of the given product in the future, based on the actual inventory, the actual remaining order quantity, the maximum inventory, the maximum remaining order quantity, the projected sales quantity, the projected upper sales quantity, and the projected lower sales quantity, which satisfy the following constraints: when the projected sales quantity becomes the projected upper sales quantity, the projected remaining order quantity does not exceed the maximum remaining order quantity; and when the projected sales quantity becomes the projected lower sales quantity, the projected inventory does not exceed the maximum inventory. The third calculation unit, based on the actual inventory level, the projected sales volume, and the projected inventory level, calculates the projected production volume for each unit period of the given product in the future; and The output unit outputs the predicted production volume for each unit period.

10. An information processing program that enables a computer to perform the following functions: Obtain past performance data for each unit period for a given product, including production volume, sales volume, inventory level, and remaining order quantity. Obtain the maximum inventory level and maximum remaining order quantity for the given product within a given period. Based on the actual sales volume, calculate the projected sales volume per unit period for the given product in the future, the upper limit of projected sales volume allowed if the sales volume is higher than the projected sales volume, and the lower limit of projected sales volume allowed if the sales volume is lower than the projected sales volume. Based on the actual inventory level, the actual remaining order quantity, the maximum inventory level, the maximum remaining order quantity, the projected sales volume, the projected upper sales limit, and the projected lower sales limit, calculate the projected inventory level for each unit period of the given product that satisfies the following constraints: if the projected sales volume reaches the projected upper sales limit, the projected remaining order quantity does not exceed the maximum remaining order quantity; and if the projected sales volume reaches the projected lower sales limit, the projected inventory level does not exceed the maximum inventory level. Based on the actual inventory level, the projected sales volume, and the projected inventory level, calculate the projected production volume per unit period for the given product in the future. Output the predicted production volume for each unit period.

Images