JP7845009B2 - Computer program, order quantity adjustment method, and order quantity adjustment device - Google Patents

Description

This invention relates to a computer program for determining an appropriate order quantity, an order quantity adjustment method, and an order quantity adjustment device.

Businesses that sell goods produce or procure goods, store them, and ship them from their inventory. Storage costs increase as the storage period or volume of goods increases. Traditionally, businesses have tried to reduce storage costs by forecasting demand and adjusting inventory levels according to the forecasted demand. Patent Document 1 discloses a technology that reduces storage costs by classifying shipping patterns based on changes in the volume of goods shipped over time and adjusting the order quantity of goods according to the shipping pattern.

Japanese Patent Publication No. 2019-12330

Similar to adjusting order quantities, adjusting order quantities can also reduce storage costs. For example, order quantities can be adjusted by proposing appropriate quantities at the time of order placement. However, the sale of goods involves other costs besides storage, such as production costs or transportation costs, and it is desirable to reduce the total cost, including costs other than storage. Conventional technologies cannot adjust order quantities while considering total costs.

This invention has been made in view of the above circumstances, and its objective is to provide a computer program, an order quantity adjustment method, and an order quantity adjustment device for reducing the total cost related to the sale of goods.

A method for adjusting order quantities according to one embodiment of the present invention is characterized by classifying the goods into one of several types with different shipping trends based on the goods' order or shipment history, calculating a proposed order quantity for the goods according to the type of classification, and adjusting the proposed order quantity to reduce the production cost or transportation cost based on the relationship between the production cost or transportation cost of the goods and the order quantity.

An order quantity adjustment device according to one embodiment of the present invention is characterized by comprising: a classification unit that classifies articles into one of several types with different shipping trends based on the order history or shipping history of the articles; an order quantity calculation unit that calculates an order quantity for the articles according to a method for each type of classified article; and an order quantity adjustment unit that adjusts the order quantity so as to reduce the production cost or the shipping cost of the articles, based on the relationship between the production cost or the shipping cost of the articles and the order quantity.

A computer program according to one embodiment of the present invention is characterized by classifying goods into one of several types with different shipping trends based on the order history or shipment history of the goods, calculating a proposed order quantity for the goods according to the method for each classified type, and causing the computer to perform a process to adjust the proposed order quantity in order to reduce the production cost or the shipment cost based on the relationship between the production cost or the shipment cost of the goods and the order quantity.

In one embodiment of the present invention, the goods subject to order are classified into one of several types with different shipping trends, and the proposed order quantity for the goods is calculated according to the method for each classified type. Goods have shipping trends that correspond to demand. By calculating the proposed order quantity for each classified type of goods, it is possible to calculate an appropriate order quantity that corresponds to demand. Furthermore, the proposed order quantity is adjusted to reduce production costs or transportation costs. This allows for adjusting the order quantity of goods to reduce the total cost, including production costs or transportation costs.

This invention offers excellent benefits, such as reducing the total cost of selling goods, including production and transportation costs.

This is a block diagram showing an example of the internal configuration of an order quantity adjustment device. This is a conceptual diagram showing an example of the contents of item data. This is a conceptual diagram showing an example of the contents of order performance data. This is a conceptual diagram showing an example of the content of production performance data. This is a conceptual diagram showing an example of the contents of incoming goods data. This is a conceptual diagram showing an example of the contents of shipment performance data. This is a flowchart illustrating an example of the order quantity adjustment process performed by the order quantity adjustment device. This is a flowchart showing an example of a subroutine for the classification process in S4. This graph shows an example of how the seven-day moving average of cumulative shipment volume changes over time. This graph shows an example of how the seven-day moving average of cumulative shipment volume changes over time. This flowchart shows an example of a subroutine for calculating order quantities in S5. This is a conceptual diagram showing an example of the content of calculation rule data. This graph shows an example of the relationship between production costs, transportation costs, and order volume. This is a schematic diagram showing an example of an image displayed to output the proposed order volume and cost reduction amount. This is a conceptual diagram illustrating the functionality of a pre-trained model.

The present invention will be described in detail below with reference to drawings illustrating its embodiments.
Figure 1 is a block diagram showing an example of the internal configuration of the order quantity adjustment device 1. The order quantity adjustment device 1 is an information processing device configured using a computer such as a personal computer or a server device. The order quantity adjustment device 1 is used by businesses that produce and ship various types of goods. The order quantity adjustment device 1 is operated by a user who performs the task of determining the order quantity of goods, and executes an order quantity adjustment method.

The order quantity adjustment device 1 comprises a calculation unit 11, a memory 12 for storing temporary data generated during calculations, a storage unit 13, a drive unit 14, an operation unit 15, and a display unit 16. The calculation unit 11 is configured using, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or a multi-core CPU. The calculation unit 11 may also be configured using a quantum computer. The memory 12 is, for example, RAM (Random Access Memory). The storage unit 13 is non-volatile and is, for example, a hard disk or non-volatile semiconductor memory. The drive unit 14 reads information from a recording medium 10 such as an optical disc or portable memory.

The calculation unit 11 causes the drive unit 14 to read the computer program 131 recorded on the recording medium 10, and stores the read computer program 131 in the storage unit 13. The calculation unit 11 then executes the necessary processing for the order quantity adjustment device 1 according to the computer program 131. Note that the computer program 131 may be pre-stored in the storage unit 13 or downloaded from outside the order quantity adjustment device 1. In this case, the order quantity adjustment device 1 does not need to have a drive unit 14.

The operation unit 15 accepts input of information such as text by receiving operations from the user. The operation unit 15 is, for example, a touch panel, keyboard, or pointing device. The display unit 16 displays images. The display unit 16 is, for example, a liquid crystal display or an EL display (Electroluminescent Display). The operation unit 15 and the display unit 16 may be integrated. The order quantity adjustment device 1 may be composed of multiple computers. For example, the order quantity adjustment device 1 may be composed of multiple computers, including a server device for storing data and tablet computers that implement the functions of the operation unit 15 and the display unit 16.

The memory unit 13 stores item data containing information about multiple types of items. Figure 2 is a conceptual diagram showing an example of the contents of the item data. The item data records information about each of the multiple types of items. In the example shown in Figure 2, for each of the multiple types of items, the item ID assigned to identify the item, the item name, the customer ID for identifying the customer of the item, and the customer name are recorded. Furthermore, the category to which the item is classified is recorded for each item. In the example shown in Figure 2, the categories to which the items belong consist of major categories, medium categories, and minor categories. Medium categories are categories that classify items belonging to major categories, and minor categories are categories that further classify items belonging to medium categories. Also, in the example shown in Figure 2, the latest order date for each item is recorded. Multiple pieces of information about each item are interconnected. The item data may also contain other information about the items, and some of the information shown in Figure 2 may not be recorded.

Furthermore, the storage unit 13 stores order performance data, production performance data, inventory performance data, and shipment performance data. Figure 3 is a conceptual diagram showing an example of the contents of the order performance data. The order performance data contains data representing past order performance. In the example shown in Figure 3, for each past order, the order number, order date, customer ID, item ID, order number, order quantity, order unit, and unit price are recorded. Multiple pieces of information related to each order are interconnected. The order performance data may also contain other information related to orders, and some of the information shown in Figure 3 may not be recorded.

Figure 4 is a conceptual diagram showing an example of production performance data. Production performance data records data representing the actual production of goods. In the example shown in Figure 4, for each process performed to produce the goods, the following are recorded: order number, order date, process ID to identify the production process, process name, production date on which the process was executed, input quantity used in the process, quantity produced by the process, and manufacturing cost. Multiple pieces of information related to the production process are interconnected. Production performance data may also contain other information related to production, and some of the information shown in Figure 4 may not be recorded.

Figure 5 is a conceptual diagram showing an example of the contents of receiving performance data. Receiving performance data records data representing the actual receipt of manufactured goods into a warehouse for storage. In the example shown in Figure 5, for each goods receipt, the following information is recorded: order number, order date, receiving date, receiving ID to identify the receipt, quantity received, warehouse ID to identify the warehouse where the goods were received, and warehouse name. Multiple pieces of information related to receiving are interconnected. Receiving performance data may also record other information related to receiving, and some of the information shown in Figure 5 may not be recorded.

Figure 6 is a conceptual diagram showing an example of the contents of shipment performance data. Shipment performance data records data representing the actual shipments of stored goods. In the example shown in Figure 6, for each shipment of goods, the following is recorded: order number, order date, shipment date, receiving ID for the shipped goods, shipment ID to identify the shipment, shipment quantity, warehouse ID for the shipped goods, delivery destination ID to identify the delivery destination, delivery destination name, and sales revenue from the shipment. Multiple pieces of information related to shipments are interconnected. Shipment performance data may also record other information related to shipments, and some of the information shown in Figure 6 may not be recorded.

The order quantity adjustment device 1 performs information processing to adjust the order quantity when an order for goods is received. Figure 7 is a flowchart illustrating an example of the order quantity adjustment process performed by the order quantity adjustment device 1. Hereinafter, steps will be abbreviated as S. The calculation unit 11 performs information processing according to the computer program 131, thereby executing the following process: When an order for goods is received, the user selects the goods to be ordered, and the order quantity adjustment device 1 accepts the selection of goods (S1). In S1, the user operates the operation unit 15, and the order quantity adjustment device 1 accepts the selection of goods. For example, the calculation unit 11 displays a selection screen for selecting goods on the display unit 16. The selection screen displays a list of multiple goods, each with information recorded in the goods data. The user operates the operation unit 15 to select the goods to be ordered from the list of multiple goods, and the calculation unit 11 accepts the selection of goods.

The order quantity adjustment device 1 determines whether the number of past orders for the selected item exceeds a predetermined threshold (S2). In S2, the calculation unit 11 identifies the number of orders for the item based on the order history and determines whether the number of orders exceeds the threshold. For example, the calculation unit 11 identifies the number of orders for the item by reading the item ID of the item from the item data and reading the number of orders associated with the item ID from the order history data. The threshold is a positive value and is either stored in the storage unit 13 in advance or included in the computer program 131. In S2, the number of orders to be determined may be the number of orders over a predetermined period including the present time. Note that in S2, the order quantity adjustment device 1 may also use whether the number of orders is equal to or greater than the threshold as a condition for determination.

If the number of orders for an item is below a threshold (S2: NO), the order quantity adjustment device 1 identifies similar items to the item being ordered (S3). In S3, the calculation unit 11 identifies other items that belong to a similar category to the item being ordered and have a recent order date as similar items. For example, based on the item data, the calculation unit 11 identifies the major category, medium category, and minor category of the item being ordered, and extracts items from among multiple items that match the major category, medium category, and minor category. If there are no items that match the major category, medium category, and minor category, the calculation unit 11 extracts items that match the major category and medium category. If there are no items that match the major category and medium category, the calculation unit 11 extracts items that match the major category. Based on the item data, the calculation unit 11 identifies the item with the most recent order date among the extracted items as a similar item. In S2, the calculation unit 11 may also identify items that exceed the threshold as similar items.

After S3 is completed, or if the number of orders for the target item exceeds a threshold (S2: YES), the order quantity adjustment device 1 performs a classification process to classify the target item or similar items (S4). In S4, the order quantity adjustment device 1 classifies the target item or similar items into one of several types with different shipping trends. If the number of orders for the target item exceeds a threshold, the order quantity adjustment device 1 performs the S4 process for the target item; if the number of orders for the target item is below the threshold, it performs the S4 process for similar items. The S4 process corresponds to the classification unit.

Figure 8 is a flowchart showing an example of the subroutine for the classification process in S4. The order quantity adjustment device 1 determines whether or not an order for goods was received within the most recent predetermined period (S401). The predetermined period is a period of a predetermined length, such as one year. The calculation unit 11 performs the determination in S401 by identifying the latest order date of the goods based on the goods data and determining whether the latest order date falls within the predetermined period. If there is no order for goods within the most recent predetermined period (S401: NO), the order quantity adjustment device 1 classifies the goods as items that have reached the end of their sales period (S402). Items that have reached the end of their sales period are those for which the period of stable sales has ended. After S402 is completed, the order quantity adjustment device 1 returns the process to the main process.

If an order for goods has been placed within the most recent predetermined period (S401: YES), the order quantity adjustment device 1 determines whether the number of orders for the goods exceeds a predetermined threshold (S403). If the number of orders for the goods in question exceeds the threshold in S2, similarly, the number of orders for the goods exceeds the predetermined threshold. In S403, the calculation unit 11 identifies the number of orders for similar goods based on the order history and determines whether the number of orders exceeds the threshold. If the number of orders for similar goods is below the threshold (S403: NO), the order quantity adjustment device 1 classifies the similar goods as "start-up" goods (S404). Start-up goods are those that have only recently been on the market and have not yet reached a period of stable sales. After S404 is completed, the order quantity adjustment device 1 returns the processing to the main processing.

If the number of orders for an item exceeds a threshold (S403: YES), the order quantity adjustment device 1 calculates the time change in the cumulative shipment quantity (S405). For example, in S405, the calculation unit 11 reads information about the item from the shipment performance data and calculates the cumulative shipment quantity for each shipment day by sequentially adding the shipment quantities in order of oldest shipment date. The calculation unit 11 also obtains the time change in the cumulative shipment quantity by associating the shipment date with the calculated cumulative shipment quantity.

The order quantity adjustment device 1 then extracts the points of change in the slope of the seven-day moving average of the cumulative shipment volume (S406). In S406, the calculation unit 11 calculates the time change of the seven-day moving average of the cumulative shipment volume from the time change of the cumulative shipment volume and searches for the points of change in the slope of the seven-day moving average. By calculating the seven-day moving average of the cumulative shipment volume, the influence of weekly periodic changes on the cumulative shipment volume is reduced. In S406, the calculation unit 11 may also reduce the influence of short-term periodic changes by calculating a moving average of a length other than seven days.

This section describes an example of a method for finding points of change in the slope of the seven-day moving average of cumulative shipments. Figures 9 and 10 are graphs showing examples of the time change of the seven-day moving average of cumulative shipments. In Figures 9 and 10, the horizontal axis represents time, and each position on the horizontal axis corresponds to the shipment date. The vertical axis represents the seven-day moving average of cumulative shipments. In S406, the calculation unit 11 calculates the slope of the seven-day moving average of cumulative shipments within a first period of predetermined length, as shown in Figure 9. The calculated slope is the average slope within the first period. The calculation unit 11 then calculates the slope of the seven-day moving average of cumulative shipments within a second period of predetermined length that is continuous with the first period. The calculated slope is the average slope within the second period. The lengths of the first period and the second period may be the same or different.

The calculation unit 11 calculates the absolute value of the difference between the slope during the first period and the slope during the second period, and determines whether the absolute value of the difference in slopes exceeds a predetermined first reference value. The first reference value is a positive value. If the absolute value of the difference in slopes exceeds the first reference value, the calculation unit 11 designates the boundary point between the first and second periods as a candidate for a change point. If the absolute value of the difference in slopes is less than or equal to the first reference value, the calculation unit 11 determines that there is no change point. The calculation unit 11 sequentially determines candidate change points.

The calculation unit 11 determines whether other candidate change points are included in a third period of predetermined length that includes the candidate change point. Figure 10 shows an example where two candidate change points are included in the third period. When multiple candidate change points are included in the third period, the calculation unit 11 determines whether the slope change trends are the same or different for two adjacent candidate change points within the third period. If the slope increases in one candidate change point and also increases in the other candidate change point, or if the slope decreases in both candidates, the slope change trends are the same. If the slope increases in one candidate change point and decreases in the other candidate change point, the slope change trends are different. Figure 10 shows an example where the slope change trends are different.

If the slope change trends are the same, the calculation unit 11 excludes the candidate change point at an earlier time point and retains the candidate change point at a later time point. If the slope change trends are different, the calculation unit 11 calculates the absolute difference between the absolute difference in slopes at one candidate change point and the absolute difference in slopes at the other candidate change point. If the calculated absolute value of the difference is less than or equal to a predetermined second reference value, the calculation unit 11 excludes both candidate change points. The second reference value is a positive value. If the calculated absolute value of the difference exceeds the predetermined second reference value, the calculation unit 11 excludes the candidate change point with the smaller absolute value of the slope difference and retains the candidate change point with the larger absolute value of the slope difference. If no other candidate change points are included in the third period containing the candidate change point, the calculation unit 11 identifies the candidate change point as a change point.

The order quantity adjustment device 1 then determines whether there is a change point in the slope of the seven-day moving average of the cumulative shipment volume (S407). In S407, the calculation unit 11 determines whether there is a change point based on the result of the processing in S406. If there is no change point (S407: NO), the order quantity adjustment device 1 classifies the item as a standard item (S408). Standard items are items that have stable sales and demand that hardly changes. After S408 is completed, the order quantity adjustment device 1 returns the processing to the main processing.

If there is a point of change in the slope of the seven-day moving average of cumulative shipment volume (S407: YES), the order quantity adjustment device 1 determines whether the point of change is periodic (S409). For example, in S409, the calculation unit 11 determines whether the point of change is periodic by determining whether the interval between the points of change is a specific interval such as three months or six months, or whether the increase and decrease in the slope are repeated periodically. If the point of change is periodic (S409: YES), the order quantity adjustment device 1 classifies the item as a seasonal item (S410). Seasonal items are items that have stable sales and whose demand changes depending on the season. After S410 is completed, the order quantity adjustment device 1 returns the processing to the main processing.

If the change point does not have periodicity (S409: NO), the order quantity adjustment device 1 determines whether the timing of the change point falls within the most recent predetermined period (S411). In S411, the calculation unit 11 determines whether the time corresponding to the change point falls within the most recent predetermined period. The predetermined period used in S411 may be the same as or different from the predetermined period used in S401. If the timing of the change point does not fall within the most recent predetermined period (S411: NO), the order quantity adjustment device 1 classifies the item as a non-regular item (S412). Non-regular items are items with stable sales and demand that is not affected by seasonal changes. After S412 is completed, the order quantity adjustment device 1 returns the processing to the main processing.

If the timing of the change point falls within the most recent predetermined period (S411: YES), the order quantity adjustment device 1 determines whether the change point is a decrease (S413). In S413, the calculation unit 11 determines whether the most recent change point is a decrease. The calculation unit 11 may also perform the determination in S413 by determining whether there are many decrease changes among the change points included in the predetermined period. If the change point is not a decrease (S413: NO), the order quantity adjustment device 1 proceeds to S412. If the change point is a decrease (S413: YES), the order quantity adjustment device 1 classifies the item as an item nearing the end of its sales period (S414). After S414 is completed, the order quantity adjustment device 1 returns to the main processing. If the number of orders for the item being ordered is below a threshold, the calculation unit 11 executes the processes S401 to S414 for similar items.

In the processing steps S401 to S414, goods are classified based on whether or not an order was placed for a given item within a specified period, the number of orders placed for that item, or the change in the cumulative shipment volume of that item over time. Different shipment trends result in different order trends, order counts, and changes in the cumulative shipment volume over time. Therefore, processing steps S401 to S414 allows for the classification of goods according to their shipment trends. Since differences in shipment trends stem from differences in demand, classifying goods according to their shipment trends allows for the classification of goods according to demand.

After S4 is completed, the order quantity adjustment device 1 executes an order quantity calculation process to calculate the order quantity of the goods. Figure 11 is a flowchart showing an example of a subroutine for the order quantity calculation process in S5. The order quantity adjustment device 1 calculates the proposed order quantity of the goods (S51) using a type-based method that classifies the goods or similar goods to be ordered. The storage unit 13 stores calculation rule data that records the rules for calculating the proposed order quantity for each type of goods or similar goods to be ordered. In S51, the calculation unit 11 calculates the proposed order quantity of the goods according to the rules recorded in the calculation rule data. The process in S51 corresponds to the proposed order quantity calculation unit.

Figure 12 is a conceptual diagram showing an example of the content of calculation rule data. The ordered goods and similar goods are classified into one of the following categories: startup goods, standard goods, seasonal goods, non-standard goods, and discontinued goods. The calculation rules for the projected order quantity are recorded in relation to each category into which the ordered goods or similar goods can be classified. The calculation rules are defined for each category into which the ordered goods or similar goods are classified.

Since the goods subject to orders are not classified as "start-up" goods, no calculation rules are associated with the "start-up" goods that are classified as such. In the example shown in Figure 12, for the "regular" goods that are classified as "order-subjects," the calculation rule is associated with calculating the estimated order quantity by multiplying the average monthly shipment volume of the goods during the stable period by a predetermined positive constant A. The stable period is a time when goods are shipped steadily; for example, it is a period when the shipment volume within a predetermined period of a predetermined length exceeds a predetermined baseline.

In the example shown in Figure 12, for seasonal goods classified as target items, the calculation rule is associated with calculating the projected order quantity by multiplying the average monthly shipment volume of the item in the same season as the current month within the stable period by a constant A. For non-regular goods classified as target items, the calculation rule is associated with calculating the projected order quantity by multiplying the monthly shipment volume in the month closest to the slope of the seven-day moving average of cumulative shipment volume for the most recent A month by a constant A. For discontinued goods classified as target items, the calculation rule is associated with calculating the projected order quantity by multiplying the monthly shipment volume of the item in the discontinued period by a constant A. For any type of similar goods classified, the calculation rule is associated with calculating the projected order quantity by multiplying the average monthly shipment volume of similar goods in the start-up period by a constant A. Other calculation rules may be associated with each type of goods classified as target items or similar goods.

In S51, the calculation unit 11 reads the calculation rule associated with the classification of the ordered item or similar item from the calculation rule data, and calculates the estimated order quantity of the item according to the read calculation rule. If the number of orders for the ordered item exceeds the threshold, the calculation unit 11 calculates the estimated order quantity of the ordered item according to the calculation rule associated with the classification of the ordered item. If the number of orders for the ordered item is below the threshold, the calculation unit 11 calculates the estimated order quantity of the ordered item according to the calculation rule associated with the classification of similar items.

The order quantity adjustment device 1 then adjusts the proposed order quantity to reduce the production cost or transportation cost of the goods (S52). In S52, for example, the calculation unit 11 obtains the relationship between production cost and order quantity based on production performance data, and the relationship between transportation cost and order quantity based on shipment performance data, and adjusts the proposed order quantity according to the relationship between production cost or transportation cost and order quantity. For example, based on the relationship between production quantity and manufacturing cost recorded in the production performance data, the calculation unit 11 uses the production quantity as the order quantity, and the value obtained by dividing the manufacturing cost by the production quantity as the unit cost of production, and obtains the relationship between production cost and order quantity. For example, the shipment performance data records the sales freight associated with shipment, and based on the relationship between shipment quantity and transportation quantity recorded in the shipment performance data, the calculation unit 11 uses the shipment quantity as the order quantity, and the value obtained by dividing the sales freight by the shipment quantity as the unit cost of transportation, and obtains the relationship between transportation cost and order quantity. The processing in S52 corresponds to the proposed order quantity adjustment unit.

Figure 13 is a graph illustrating an example of the relationship between production costs, transportation costs, and order volume. The horizontal axis represents order volume, and the vertical axis represents the cost per unit of order volume. Figure 13 shows the changes in manufacturing costs and sales freight with respect to order volume. Manufacturing costs correspond to production costs, and sales freight corresponds to transportation costs. While costs tend to decrease with increasing order volume, they can also increase with increasing order volume. Changes in production costs and changes in transportation costs do not always coincide.

In Figure 13, the proposed order quantity is shown by a dashed line. At S52, the calculation unit 11 adjusts the proposed order quantity so that the cost (production cost) decreases if the proposed order quantity is changed within a predetermined range. The calculation unit 11 may change the proposed order quantity if the sum of manufacturing costs and sales freight decreases, or if either manufacturing costs or sales freight decreases. The calculation unit 11 may perform multiple adjustments. If the cost reduction resulting from changing the proposed order quantity within a predetermined range is less than or equal to a predetermined amount, the calculation unit 11 does not need to change the proposed order quantity.

The order quantity adjustment device 1 then determines whether the item is a repeat order (S53). The calculation unit 11 refers to the order history data and determines that the item is a repeat order if there is a record of orders for the item, and that the item is not a repeat order if there is no record of orders for the item. If the item is not a repeat order (S53: NO), the order quantity adjustment device 1 outputs a proposed order quantity (S54). In S54, the calculation unit 11 outputs the proposed order quantity by displaying an image containing the adjusted proposed order quantity on the display unit 16. After S54 is completed, the order quantity adjustment device 1 returns the processing to the main processing.

If the item is a repeat order (S53: YES), the order quantity adjustment device 1 calculates the cost reduction compared to previous orders of the item (S55). In S55, for example, the calculation unit 11 calculates the production cost and transportation cost at the current order quantity based on the relationship between production cost, transportation cost, and order quantity, using order performance data. The current order quantity can be the previous order quantity or the average of past order quantities. Similarly, the calculation unit 11 calculates the storage cost at the current order quantity and the storage cost related to the adjusted order quantity proposal, based on the relationship between the storage cost of the item and the order quantity, using inbound data. The calculation unit 11 also calculates the total cost, including storage costs, production costs, and transportation costs. The calculation unit 11 calculates the cost reduction by calculating the difference between the cost at the current order quantity and the costs related to the proposed order quantity and the adjusted order quantity proposal. The cost reduction can be easily obtained by comparing costs based on order performance data.

The order quantity adjustment device 1 outputs the proposed order quantity and the cost reduction amount (S56). In S56, the calculation unit 11 displays an image on the display unit 16 that includes the proposed order quantity, the cost at the current order quantity, the cost related to the adjusted proposed order quantity, and the cost reduction amount. Figure 14 is a schematic diagram showing an example of an image displayed to output the proposed order quantity and the cost reduction amount. The total cost reduction amount is displayed in relation to the proposed order quantity. Figure 14 shows an example where the total cost reduction amount is displayed for three different proposed order quantities. For example, Proposal 1 shown in Figure 14 is the proposed order quantity calculated in S51, while Proposals 2 and 3 are the proposed order quantities adjusted in S52.

Furthermore, in the example shown in Figure 14, the order quantity, unit price, storage cost per unit, manufacturing cost per unit, selling freight per unit, and inventory period are displayed in relation to the current order quantity and each proposed order quantity. Storage cost per unit corresponds to storage costs, manufacturing cost per unit corresponds to production costs, and selling freight per unit corresponds to transportation costs. By displaying the individual costs for both the current order quantity and the proposed order quantities, cost comparison becomes possible. Additionally, by displaying the total cost reduction for the proposed order quantities, it becomes easy to confirm the cost reduction effect compared to the current order quantity.

In the example shown in Figure 14, further information regarding the ordered items is displayed. Information about the items is read from the item data and displayed. If the process of identifying similar items is not performed, information about similar items may not be displayed. The user can then review the item information and perform cost comparisons and verify the amount of cost reduction. The content shown in Figure 14 is an example of information output; other information may be output in S56, and some of the information shown in Figure 14 may not be output. After S56 is completed, the order quantity adjustment device 1 returns the process to the main process.

The order quantity adjustment device 1 then determines the order quantity and unit price of the goods (S6). In S6, for example, with an image containing information about the current order quantity and proposed order quantity displayed on the display unit 16 (as shown in Figure 14), the user operates the operation unit 15 to select either the current order quantity or one of the proposed order quantities. The order quantity is selected based on the selection of the current order quantity or one of the proposed order quantities. The unit price associated with the order quantity is also selected. The user confirms the potential costs and cost reductions before selecting the order quantity and unit price. The calculation unit 11 receives the selection of the order quantity and unit price and determines the order quantity and unit price of the goods to the selected order quantity and unit price. Note that the unit price may be entered separately from the order quantity. The calculation unit 11 stores the determined order quantity and unit price of the goods in the storage unit 13.

The order quantity adjustment device 1 then performs order processing (S7). In S7, for example, the calculation unit 11 performs processes such as notifying the customer of the order quantity and unit price of the goods, creating documents, or recording the order details in the order performance data. The order quantity adjustment device 1 then determines whether there are other items to be ordered (S8). In S8, for example, the calculation unit 11 displays an input screen on the display unit 16 for inputting whether there are other items to be ordered, and the user inputs whether there are other items to be ordered by operating the operation unit 15, and the calculation unit 11 makes a determination based on the input. If there are other items to be ordered (S8: YES), the calculation unit 11 returns the process to S1. If there are no other items to be ordered (S8: NO), the calculation unit 11 terminates the order quantity adjustment process.

As detailed above, in this embodiment, the order quantity adjustment device 1 classifies goods into one of several types with different shipping trends and calculates the proposed order quantity for each type of goods. Each item has different shipping trends, such as not yet having a stable sales period, selling steadily, or selling periodically. Shipping trends are determined by demand. By calculating the proposed order quantity for each type of goods, it is possible to calculate an appropriate order quantity according to demand. Furthermore, the order quantity adjustment device 1 adjusts the proposed order quantity to reduce production costs or transportation costs. This allows for adjustment of the proposed order quantity to reduce the total cost of shipping goods, including production costs or transportation costs. By using the adjusted proposed order quantity as the actual order quantity for goods, it becomes possible to reduce the total cost related to the sale of goods.

For items that have only recently gone on sale and have few orders, the shipping trend is unclear, making demand forecasting difficult. In this embodiment, the order quantity adjustment device 1, when the number of orders for the target item is low, identifies similar items, classifies these similar items according to their shipping trend, and calculates a proposed order quantity for the target item using a method corresponding to the classification of the similar items. This makes it possible to classify items with few orders and unclear shipping trends, and to calculate an appropriate proposed order quantity based on demand. Furthermore, it is possible to reduce the total sales costs even for items with few orders.

Furthermore, the order quantity adjustment device 1 may perform processing using a trained model in order to perform the classification processing in S4. In this configuration, the order quantity adjustment device 1 is equipped with a trained model used to classify the ordered items or similar items. The trained model is realized by the arithmetic unit 11 executing information processing according to the computer program 131. The storage unit 13 stores the data necessary to realize the trained model 132.

The trained model may be constructed using hardware. For example, the trained model may consist of hardware including a processor and memory for storing the necessary programs and data. Alternatively, the trained model may be implemented using a quantum computer. Alternatively, the trained model may be located outside the order quantity adjustment device 1, and the order quantity adjustment device 1 may execute processing using the external trained model. For example, the trained model may be implemented using the cloud.

Figure 15 is a conceptual diagram illustrating the functionality of a pre-trained model. The pre-trained model is pre-trained to output classification information indicating the classification result of an item when given the time-dependent change in the cumulative shipment volume of an item as input. The time-dependent change in the cumulative shipment volume of an item is time-series data consisting of the cumulative shipment volume values at each point in time. For example, the classification information includes the probability of an item being classified into categories such as startup items, standard items, seasonal items, non-standard items, and discontinued items. For example, the pre-trained model is constructed using a neural network such as a CNN (Convolutional Neural Network), LSTM (Long Short-Term Memory), or transformer. The pre-trained model may also be a model using methods other than neural networks.

The trained model is generated through machine learning using training data. The training of the trained model is performed using a computer-based learning device. The training data includes multiple datasets that correlate the time-dependent changes in the cumulative shipment volume of goods with the classification results of those goods. For example, the classification results of the goods are those obtained by processing S401 to S414.

In machine learning, the learning device inputs the time-dependent changes in the cumulative shipment volume of items included in the training data into a base model for the trained model. The model then performs calculations based on the input of the time-dependent changes in the cumulative shipment volume and outputs classification information. The learning device adjusts the model's calculation parameters to minimize the error between the classification information output by the model and the classification result associated with the time-dependent changes in the cumulative shipment volume of the input items. For example, if the classification result in the training data is a standard item, the parameters are adjusted so that the model outputs classification information indicating that the probability of classifying an item as a standard item is approximately 100%, and the probability of classifying it as another type is approximately 0%. For example, parameter adjustment can be performed using backpropagation.

The learning device performs machine learning by repeatedly processing multiple datasets included in the training data and adjusting the model parameters. A trained model is generated through this adjustment of the computation parameters. For example, the final adjusted parameters are stored in the storage unit 13, and the computation unit 11 performs information processing using these parameters, thereby realizing the trained model.

In this configuration, the order quantity adjustment device 1 performs processing using a trained model in the classification process of S4. In S4, the calculation unit 11 calculates the time change in the cumulative shipment quantity of the ordered item or similar item and inputs the time change in the cumulative shipment quantity to the trained model. The trained model outputs classification information in response to the input of the time change in the cumulative shipment quantity. The calculation unit 11 acquires the classification information output by the trained model and classifies the ordered item or similar item according to the classification information. For example, the calculation unit 11 classifies the ordered item or similar item into the type with the highest probability indicated by the classification information among items in the startup phase, standard items, seasonal items, non-standard items, and items in the discontinued period. Even in this configuration, an appropriate order quantity proposal according to demand is calculated, making it possible to reduce the total cost related to the sale of goods.

In the embodiments described above, production costs were included in the total cost of selling goods. However, the order quantity adjustment device 1 may also handle goods where production costs are not included in the total cost. For example, if goods are procured by purchasing rather than producing them, production costs are not included in the total cost. In this configuration, the order quantity adjustment device 1 uses procurement costs instead of production costs for processing. Even in this configuration, the order quantity adjustment device 1 can reduce the total cost of selling goods by determining an appropriate order quantity.

The present invention is not limited to the embodiments described above, and various modifications are possible within the scope of the claims. That is, embodiments obtained by combining technical means appropriately modified within the scope of the claims are also included in the technical scope of the present invention.

The matters described in each embodiment can be combined with each other. Furthermore, the independent and dependent claims described in the claims can be combined with each other in any combination, regardless of the form of reference. Moreover, while the claims use a multi-claim format (claims referencing two or more other claims), this is not the only format. A multi-claim format (multi-multi-claim) that references at least one multi-claim may also be used.

(Note 1)
Based on the order history or shipment history of the goods, the goods are classified into one of several types with different shipment trends.
The estimated order quantity for the aforementioned items is calculated using the type-based classification method.
A computer program characterized by causing a computer to perform a process to adjust the proposed order quantity in order to reduce the production cost or the transportation cost of the said goods, based on the relationship between the production cost or the transportation cost of the said goods and the order quantity.

(Note 2)
The computer program according to Appendix 1, characterized in that it causes the computer to further perform a process of calculating the amount of cost reduction based on a comparison of the adjusted proposed order volume with the actual order volume.

(Note 3)
The computer program according to Appendix 1 or 2, characterized in that it causes a computer to perform a process of classifying the said items into one of the multiple types based on whether or not an order for the said items was received within a predetermined period, the number of orders for the said items, or the change in the cumulative shipment volume of the said items over time.

(Note 4)
A computer program according to any one of the appendices 1 to 3, characterized in that it causes a computer to perform a process of calculating an estimated order quantity for the said goods in accordance with rules for calculating an estimated order quantity for the said goods based on the shipment record of the said goods, which are determined for each type of classified goods.

(Note 5)
Based on the order history of the said goods, it is determined whether the number of orders for the said goods exceeds a predetermined threshold.
If the number of orders for the aforementioned item exceeds the threshold, the item is classified into one of the aforementioned multiple types.
If the number of orders for the aforementioned item is below the threshold, similar items similar to the aforementioned item are identified based on the category to which the aforementioned item belongs.
Based on the order history or shipment history of the aforementioned similar items, the aforementioned similar items are classified into one of the aforementioned multiple types.
A computer program according to any one of the appendices 1 to 4, characterized in that it causes a computer to perform a process of calculating the estimated order quantity of the said similar articles by classifying them by type.

1 Order quantity adjustment device 10 Recording medium 11 Calculation unit 13 Storage unit 131 Computer program

Claims (10)

When receiving an order for goods,
Based on the order history or shipment history of the aforementioned items, the items are classified into one of several types with different shipment trends.
The estimated order quantity for the aforementioned items is calculated using the type-based classification method.
A computer program characterized by causing a computer to perform a process of obtaining a relationship between the production cost of the said item and the order quantity of the said item based on the production record of the said item, obtaining a relationship between the transportation cost of the said item and the order quantity based on the shipment record of the said item, and adjusting the proposed order quantity to reduce the production cost or the transportation cost based on the relationship between the production cost or the transportation cost and the order quantity. The computer program according to claim 1, characterized in that it causes the computer to further perform a process of calculating the amount of cost reduction based on a comparison of the adjusted proposed order volume with the actual order volume. Based on the order history or shipment history of the goods, the goods are classified into one of several types with different shipment trends.
The estimated order quantity for the aforementioned items is calculated using the type-based classification method.
Based on the relationship between the production cost or transportation cost of the said goods and the order quantity, the proposed order quantity is adjusted to reduce the production cost or transportation cost .
The amount of cost reduction is calculated based on a comparison between the adjusted proposed order volume and the actual order volume.
A computer program characterized by causing a computer to perform a process. A computer program according to any one of claims 1 to 3, characterized in that it causes a computer to perform a process of classifying the said items into one of the plurality of types based on whether or not an order for the said items was placed within a predetermined period, the number of orders for the said items, or the change in the cumulative shipment volume of the said items over time. A computer program according to any one of claims 1 to 3, characterized in that it causes a computer to perform a process of calculating an estimated order quantity for the said goods in accordance with rules for calculating an estimated order quantity for the said goods based on the actual shipment record of the said goods, which are defined for each type of classified said goods. Based on the order history of the said goods, it is determined whether the number of orders for the said goods exceeds a predetermined threshold.
If the number of orders for the aforementioned item exceeds the threshold, the item is classified into one of the aforementioned multiple types.
If the number of orders for the aforementioned item is below the threshold, similar items similar to the aforementioned item are identified based on the category to which the aforementioned item belongs.
Based on the order history or shipment history of the aforementioned similar items, the aforementioned similar items are classified into one of the aforementioned multiple types.
A computer program according to any one of claims 1 to 3 , characterized in that it causes a computer to perform a process of calculating the estimated order quantity of the said similar articles by classifying them by type. When receiving an order for goods,
Based on the order history or shipment history of the aforementioned items, the items are classified into one of several types with different shipment trends.
The estimated order quantity for the aforementioned items is calculated using the type-based classification method.
Based on the production record of the said item, the relationship between the production cost of the said item and the order quantity of the said item is obtained; based on the shipment record, the relationship between the transportation cost of the said item and the order quantity of the said item is obtained; and based on the relationship between the production cost or the transportation cost and the order quantity, the proposed order quantity is adjusted to reduce the production cost or the transportation cost.
A method for adjusting order quantities, characterized by performing the processing by computer . Based on the order history or shipment history of the goods, the goods are classified into one of several types with different shipment trends.
The estimated order quantity for the aforementioned items is calculated using the type-based classification method.
Based on the relationship between the production cost or transportation cost of the said goods and the order quantity, the proposed order quantity is adjusted to reduce the production cost or transportation cost .
The amount of cost reduction is calculated based on a comparison between the adjusted proposed order volume and the actual order volume.
A method for adjusting order quantities, characterized by performing the processing by computer . A classification unit that , upon receiving an order for an item, classifies the item into one of several types with different shipping trends based on the order history or shipping history of the item,
An order quantity calculation unit calculates the order quantity for the aforementioned items using a method that classifies the items by type,
An order quantity adjustment device comprising: an order quantity adjustment unit that obtains a relationship between the production cost of the said item and the order quantity of the said item based on the production record of the said item; obtains a relationship between the transportation cost of the said item and the order quantity based on the shipment record of the said item; and adjusts the order quantity proposal so as to reduce the production cost or the transportation cost based on the relationship between the production cost or the transportation cost and the order quantity. A classification unit that classifies the aforementioned items into one of several types with different shipping trends based on the order history or shipping history of the items,
An order quantity calculation unit calculates the order quantity for the aforementioned items using a method that classifies the items by type,
An order quantity adjustment unit adjusts the order quantity proposal to reduce the production cost or transportation cost of the said goods based on the relationship between the production cost or transportation cost of the said goods and the order quantity.
A cost reduction calculation unit calculates the amount of cost reduction based on a comparison between the adjusted proposed order volume and the actual order volume.
An order quantity adjustment device characterized by being equipped with the following features.