Reusable goods required supply quantity forecasting program, reusable goods required supply quantity forecasting device, reusable goods required supply quantity forecasting method, and recording medium

Abstract

This disclosure provides a program for predicting the required quantity of reusable goods to be delivered, which can predict the required quantity of reusable goods to be delivered based on information regarding the collection of reusable goods. [Solution] The reuse item required delivery quantity prediction program of the present disclosure includes an information acquisition procedure, a prediction procedure, and an information output procedure, wherein the information acquisition procedure acquires reuse item collection information for each collection area, the prediction procedure predicts the required delivery quantity information for reuse items for each delivery area based on the reuse item collection information for each collection area, and the information output procedure outputs the required delivery quantity information for reuse items.

Description

Technical Field

[0001] The present disclosure relates to a reusable item required intake prediction program, a reusable item required intake prediction device, a reusable item required intake prediction method, and a recording medium.

Background Art

[0002] In Patent Document 1, a reusable beverage container management system is disclosed, which includes a store system and a management system. The store system transmits information related to the provision and return of reusable beverage containers, and the management system provides usage history information of reusable beverage containers based on the received information to a container management operator. That is, Patent Document 1 discloses system cooperation between a reusable item borrowing operator having a store system and a reusable item intake operator having a management system.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] A reusable item intake operator predicts the intake amount of reusable items according to the borrowing amount of reusable items. However, predicting the intake amount of reusable items based on the borrowing amount of reusable items requires obtaining the borrowing amount of reusable items through system cooperation between a reusable item intake operator and a reusable item borrowing operator as in the invention according to Patent Document 1.

[0005] Therefore, an object of the present disclosure is to provide a reusable item required intake prediction program, a reusable item required intake prediction device, a reusable item required intake prediction method, and a recording medium that can predict the required intake amount of reusable items based on information related to the collection of reusable items. [Means for solving the problem]

[0006] To achieve the aforementioned objective, the reuse item supply quantity forecasting program of this disclosure is: This includes information acquisition procedures, prediction procedures, and information output procedures. The aforementioned information acquisition procedure acquires reuse item collection information for each collection area, The reuse item collection information includes information on the amount of reuse items collected. The aforementioned prediction procedure predicts the required quantity of reusable items to be delivered to the delivery area based on the reuse item collection information for each collection area. The information output procedure outputs the required delivery quantity information for the reused items. This is a program that causes a computer to execute each of the aforementioned steps.

[0007] The reuse item supply quantity forecasting device disclosed herein is Including an information acquisition unit, a prediction unit, and an information output unit, The aforementioned information acquisition unit acquires reuse item collection information for each collection area. The reuse item collection information includes information on the amount of reuse items collected. The prediction unit predicts the required quantity of reusable items to be delivered to each delivery area based on the reuse item collection information for each collection area. The information output unit outputs the required quantity of reused items. It is a device.

[0008] The method for predicting the required supply quantity of reused items in this disclosure is as follows: This includes an information acquisition process, a prediction process, and an information output process. The aforementioned information acquisition process acquires reuse item collection information for each collection area. The reuse item collection information includes information on the amount of reuse items collected. The prediction process predicts the required quantity of reusable items to be delivered to each delivery area based on the reuse item collection information for each collection area. The information output step outputs the required quantity of reused items. This method involves each of the aforementioned steps being performed by a computer.

[0009] The recording medium disclosed herein is This includes information acquisition procedures, prediction procedures, and information output procedures. The aforementioned information acquisition procedure acquires reuse item collection information for each collection area, The reuse item collection information includes information on the amount of reuse items collected. The aforementioned prediction procedure predicts the required quantity of reusable items to be delivered to the delivery area based on the reuse item collection information for each collection area. The information output procedure outputs the required delivery quantity information for the reused items. This is a computer-readable recording medium on which a program is recorded that causes a computer to execute each of the aforementioned procedures. [Effects of the Invention]

[0010] According to this disclosure, the required quantity of reusable goods can be predicted based on information regarding the collection of reusable goods. [Brief explanation of the drawing]

[0011] [Figure 1] Figure 1 is a block diagram showing an example configuration of the reuse item delivery quantity prediction device of this disclosure. [Figure 2] Figure 2 is a block diagram showing an example of the hardware configuration of the reuse item delivery quantity forecasting device of this disclosure. [Figure 3] Figure 3 is a flowchart showing an example of the procedure using the reuse item supply quantity forecasting program described herein. [Figure 4] Figure 4 is a block diagram showing the configuration of another example of the reuse item delivery quantity prediction device of this disclosure. [Figure 5] Figure 5 is a flowchart showing another example of the procedure using the reuse item supply quantity forecasting program described herein. [Figure 6] Figure 6 is a block diagram showing the configuration of another example of the reuse item delivery quantity prediction device of this disclosure. [Figure 7] FIG. 7 is a flowchart showing another example of the procedure by the reusable item required inclusion amount prediction program of the present disclosure. [Figure 8] FIG. 8 is a schematic diagram showing an example of the usage form of the reusable item required inclusion amount prediction device of the present disclosure.

Embodiments for Carrying Out the Invention

[0012] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. The present disclosure is not limited to the following embodiments. In the following figures, the same parts are denoted by the same reference numerals. Also, unless otherwise specified, the descriptions of the respective embodiments can be mutually referred to, and the configurations of the respective embodiments can be combined unless otherwise specified. In the present disclosure, each drawing may apply to one or more embodiments.

[0013] [Embodiment 1] The reusable item required inclusion amount prediction program of the present disclosure is a program for causing a computer to execute an information acquisition procedure, a prediction procedure, and an information output procedure. The reusable item required inclusion amount prediction program of the present disclosure can also be said to be a program for causing a computer to function as an information acquisition procedure, a prediction procedure, and an information output procedure. Further, the reusable item required inclusion amount prediction program of the present disclosure can also be said to be a program for causing a computer to execute each step of the reusable item required inclusion amount prediction method described later, for example.

[0014] The information acquisition procedure acquires reusable item collection information for each collection area, the prediction procedure predicts reusable item required inclusion amount information for the delivery area based on the reusable item collection information for each collection area, and the information output procedure outputs the reusable item required inclusion amount information.

[0015] Each of the aforementioned procedures can be reinterpreted, for example, by substituting "procedure" with "process." The reuse supply quantity forecasting program of this disclosure may also be recorded on, for example, a computer-readable storage medium. The storage medium is, for example, a non-transitory computer-readable storage medium. The storage medium is not particularly limited and includes, for example, random access memory (RAM), read-only memory (ROM), hard disk (HD), flash memory (e.g., SSD (Solid State Drive), USB flash memory, SD / SDHC card, etc.), optical disc (e.g., CD-R / CD-RW, DVD-R / DVD-RW, BD-R / BD-RE, etc.), magneto-optical disk (MO), floppy disk (FD), etc. The reuse supply quantity forecasting program of this disclosure (for example, also called a programming product or program product) may also be delivered, for example, from an external computer. The "delivery" may be, for example, delivered via a communication network or delivered via a wired device. The reuse item supply quantity forecasting program of this disclosure may be installed and executed on the distributed device, or it may be executed without being installed. An information processing device capable of executing the reuse item supply quantity forecasting program of this disclosure may be, for example, the reuse item supply quantity forecasting device of this disclosure.

[0016] Next, an example of the configuration of the reuse item required delivery quantity forecasting device of this disclosure will be described with reference to Figure 1. Figure 1 is a block diagram showing an example of the configuration of the reuse item required delivery quantity forecasting device 10 (hereinafter also referred to as "the device 10") of this disclosure. As shown in Figure 1, the device 10 includes an information acquisition unit 11, a forecasting unit 12, and an information output unit 13. The device 10 may also include, for example, an input unit, an output unit, a display unit, and / or a storage unit, although these are not shown. The information acquisition unit 11, the forecasting unit 12, and the information output unit 13 can each execute, for example, the information acquisition procedure, the forecasting procedure, and the information output procedure in the reuse item required delivery quantity forecasting program of this disclosure.

[0017] The device 10 may be, for example, a single device including the aforementioned parts, or it may be a device in which each of the aforementioned parts can be connected via a communication network. Furthermore, the device 10 can be connected to an external device described later via the communication network. The communication network is not particularly limited and can use a known network, for example, it may be wired or wireless. Examples of the communication network include the Internet, WWW (World Wide Web), telephone lines, LAN (Local Area Network), SAN (Storage Area Network), DTN (Delay Tolerant Networking), LPWA (Low Power Wide Area), L5G (Local 5G), etc. Examples of wireless communication include Wi-Fi (registered trademark), Bluetooth (registered trademark), Local 5G, LPWA, etc. The wireless communication may be in the form of direct communication between devices (Ad Hoc communication), infrastructure communication, indirect communication via an access point, etc. The device 10 may be, for example, incorporated into a server as a system. Furthermore, the device 10 may be, for example, a personal computer (PC, e.g., desktop or notebook), smartphone, tablet terminal, etc., on which the program of this disclosure is installed. The device 10 may also be in the form of cloud computing or edge computing, for example, in which at least one of the aforementioned parts is on a server and the other aforementioned parts are on a terminal.

[0018] Figure 2 illustrates a block diagram of the hardware configuration of the device 10. The device 10 includes, for example, a central processing unit (CPU, GPU, etc.) 101, memory 102, bus 103, storage device 104, input device 105, output device 106, communication device 107, etc. Each part of the device 10 is interconnected via the bus 103 through its respective interface (I / F).

[0019] The central processing unit 101 operates in coordination with other components via controllers (system controller, I / O controller, etc.) and is responsible for the overall control of the device 10. In the device 10, the central processing unit 101 executes, for example, the program disclosed herein (reusable product delivery quantity prediction program) and other programs, and also reads and writes various types of information. Specifically, for example, the central processing unit 101 functions as an information acquisition unit 11, a prediction unit 12, and an information output unit 13. The device 10 may also include other computing devices such as a CPU, GPU (Graphics Processing Unit), APU (Accelerated Processing Unit), or a combination thereof as computing devices.

[0020] Bus 103 can also be connected to external devices, for example. Examples of such external devices include external storage devices (external databases, etc.), printers, external input devices, external display devices, and external imaging devices. The device 10 can be connected to an external network (the aforementioned communication network) via a communication device 107 connected to bus 103, for example, and can also be connected to other devices via the external network.

[0021] Memory 102 may be, for example, main memory. When the central processing unit 101 performs processing, memory 102 reads various operational programs, such as the program of this disclosure, stored in the storage device 104 (described later), and the central processing unit 101 receives data from memory 102 and executes the program. The main memory may be, for example, RAM (random access memory). Alternatively, memory 102 may be, for example, ROM (read-only memory).

[0022] The storage device 104 is also called an auxiliary storage device, for example, in relation to the main memory (primary memory). As described above, the storage device 104 stores an operating program including the program of this disclosure. The storage device 104 may be, for example, a combination of a recording medium and a drive for reading and writing to the recording medium. The recording medium is not particularly limited and may be internal or external, for example, an HD (hard disk), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, memory card, etc. The storage device 104 may be, for example, a hard disk drive (HDD) in which the recording medium and the drive are integrated, or a solid state drive (SSD). If the device 10 includes the storage unit, for example, the storage device 104 functions as the storage unit. The storage unit can record, for example, reuse item collection information, required reuse item delivery quantity information, prediction model, reuse item delivery quantity information, corrected reuse item delivery quantity information, reuse item delivery quantity adjustment information, reuse item collection information for prediction model generation, etc., which will be described later.

[0023] In this device 10, the memory 102 and storage device 104 can also store various types of information, such as log information, information obtained from an external database (not shown) or external devices, information generated by this device 10, and information used by this device 10 when executing processing. In this case, the memory 102 and storage device 104 may store, for example, the user information of this device as described above. At least some of the information may be stored on an external server other than the memory 102 and storage device 104, or it may be stored in a distributed manner across multiple terminals using blockchain technology or the like.

[0024] The device 10 further includes, for example, an input device 105 and an output device 106. The input device 105 may include, for example, a pointing device such as a touch panel, trackpad, or mouse; a keyboard; imaging means such as a camera or scanner; a card reader such as an IC card reader or magnetic card reader; an audio input means such as a microphone; and so on. The output device 106 may include, for example, a display device such as an LED display or liquid crystal display; an audio output device such as a speaker; a printer; and so on. In this embodiment 1, the input device 105 and the output device 106 are configured separately, but the input device 105 and the output device 106 may be configured as an integrated unit, such as a touch panel display.

[0025] An example of processing using the reuse item supply quantity forecasting program described herein will be explained in more detail with reference to Figure 3. Figure 3 is a flowchart showing an example of each step of the reuse item supply quantity forecasting program described herein. The reuse item supply quantity forecasting program described herein can be implemented, for example, using the apparatus 10 described herein as shown in Figure 1 or Figure 2. However, the reuse item supply quantity forecasting program described herein is not limited to a program that uses the apparatus 10 described herein.

[0026] The information acquisition unit 11 acquires reuse item collection information for each collection area (S11, information acquisition procedure). The reuse item collection information includes information on the amount of reuse items collected.

[0027] The reuse item collection information is, for example, information regarding the collection of reuse items. The reuse items can be, for example, any reusable items, and their form may be anything. Examples of reuse items include containers, tableware, transportation materials, construction materials, packaging materials, etc. Examples of containers include beverage containers, food containers, container lids, bento / prepared food containers, etc. Examples of tableware include coffee cups, tumblers, glass bottles, food trays, straws, forks, spoons, etc. Examples of transportation materials include cardboard boxes, cushioning materials, product packaging, pallets, containers, etc. Examples of packaging materials include food trays, egg cartons, container packaging materials, etc. The collection of reuse items may be carried out, for example, by the reuse item supplier, or by a party other than the reuse item supplier. A party other than the reuse item supplier may be, for example, the reuse item collection business.

[0028] The collection area is, for example, an area for collecting the reused items. The number of collection areas may be, for example, one or two or more. The collection area may also be, for example, an area where the reused item collection device described later is located. The collection area may be, for example, a different area from the delivery area or the same area as the delivery area.

[0029] The reuse item collection information may, for example, be information based on reuse item return information. The reuse item return information may, for example, be information relating to the return of the reuse item. The reuse item return information may, for example, include reuse item return quantity information. The reuse item return quantity information may, for example, be information relating to the quantity of reuse items returned over a predetermined period. The predetermined period may, for example, be a period in days, a period in hours, minutes, and seconds, or a combination thereof. The reuse item return information may, for example, be information obtained from a reuse item collection device described later, or information obtained from the reuse item borrower's terminal. The return of the reuse item may, for example, be carried out by the reuse item borrower.

[0030] The information regarding the amount of reused items collected is, for example, information regarding the amount of reused items collected during the predetermined period. The amount of reused items collected may be, for example, the number of reused items collected or the weight of the reused items collected.

[0031] The reuse item collection information may further include, for example, reuse item collection-related information. The reuse item collection-related information is, for example, information related to the collection of the reuse items during the predetermined period. The reuse item collection-related information includes, for example, at least one of the following: unreused information, route search count information, weather information at the time of collection, event information at the time of collection, and population information at the time of collection. The unreused information is, for example, information about reuse items that could not be reused among the delivered reuse items. Examples of the unreused information include information about reuse items that were not returned by the reuse item borrowers, information about reuse items that were discarded, etc. The unreused information may be, for example, information about the quantity of reuse items that could not be reused, or information about the proportion of reuse items that could not be reused in the total quantity delivered. The route search count information is, for example, information about the number of route searches with the collection area as the destination. The weather information at the time of collection is, for example, information about the weather at the time of reuse item collection. The event information at the time of collection is, for example, information about whether or not an event was held at the time of reuse item collection. The aforementioned population information at the time of collection may, for example, be information on the population around the collection area at the time of collection of reusable items, or it may be information on the circulating population around the collection area at the time of collection of reusable items. According to this disclosure, for example, the required quantity of reusable items can be predicted in accordance with the information related to the collection of reusable items.

[0032] The reuse item collection information may further include, for example, at least one of the following: reuse item identification information, reuse item type identification information, collection area identification information, and reuse item borrower identification information. The reuse item identification information is, for example, information that can identify the reuse item, such as a QR code (registered trademark). The reuse item type identification information is, for example, information that can identify the type of reuse item, such as a QR code (registered trademark) or information regarding the shape of the reuse item. The collection area identification information is, for example, information that can identify the collection area, such as an identification number. The reuse item borrower identification information is, for example, information that can identify the reuse item borrower, such as an identification number.

[0033] The information acquisition unit 11 may, for example, acquire the reuse item collection information from the reuse item collection device. The reuse item collection device is, for example, a device capable of measuring the quantity of returned reuse items. The reuse item collection device may also be, for example, a device capable of measuring the return date and time of the returned reuse items in addition to the quantity returned. The reuse item collection device may be connected to this device 10, for example, via a wired or wireless communication network. The reuse item collection device may be located in the delivery area or in the collection area, for example. The reuse item collection device may, for example, acquire the reuse item return information when the reuse items are returned and output it to this device 10 via a wired or wireless communication line. This device 10 may, for example, acquire the reuse item return information from the reuse item collection device as the reuse item collection information.

[0034] The information acquisition unit 11 may, for example, acquire the reuse item collection information from the terminal of the reuse item borrower. The reuse item borrower's terminal may, for example, acquire reuse item identification information assigned to the reuse item and output it to the device 10 via application software linked to the reuse item identification information. The reuse item identification information is, for example, information that can identify the reuse item, such as a QR code (registered trademark).

[0035] For example, if the reused goods supplier and the reused goods collection business are different businesses, the information acquisition unit 11 may acquire the reused goods collection information from the reused goods collection business's terminal.

[0036] The information acquisition unit 11 may, for example, acquire the reuse item collection information from the memory 102 or storage device 104 of the device 10, or from the memory or storage device of a device other than the device 10. The information acquisition unit 11 may, for example, acquire the reuse item collection information from the input device 105 of the device 10, or from the input device of a device other than the device 10.

[0037] The prediction unit 12 predicts the required quantity of reusable items to be delivered to each delivery area based on the reuse item collection information for each collection area (S12, prediction procedure).

[0038] The information regarding the required quantity of reused goods to be delivered is, for example, information regarding the quantity of reused goods that need to be delivered to the delivery area within the predetermined period. The quantity of reused goods to be delivered may be, for example, the number of reused goods to be delivered or the weight of the reused goods to be delivered. The delivery of the reused goods may be carried out, for example, by the reused goods supplier.

[0039] The delivery area is, for example, an area for delivering the reused goods. The delivery area may be, for example, a different area from the collection area, or it may be the same area as the collection area. The prediction target for the information on the required delivery quantity of reused goods by the prediction unit 12 may be, for example, one of the delivery areas.

[0040] The prediction unit 12 may, for example, predict the required delivery quantity information for reused items based on the reused item collection information using a regression equation or a prediction model. That is, the prediction unit 12 may, for example, predict the required delivery quantity information for reused items using a regression equation or a prediction model.

[0041] The regression equation is, for example, an equation that, when an explanatory variable including the reused item collection information is input, outputs the required quantity of reused items to be delivered as the dependent variable. The regression equation is, for example, an equation constructed by regression analysis using data that includes an explanatory variable including the reused item collection information and a dependent variable which is the corrected quantity of reused items to be delivered. The corrected quantity of reused items to be delivered may be, for example, as explained later. The regression equation may be, for example, an equation applicable to one of the delivery areas, or an equation applicable to multiple delivery areas in common. The regression equation may be set appropriately by, for example, a method relating to regression analysis. The regression equation may be, for example, a simple regression equation or a multiple regression equation. The regression analysis may be, for example, a simple regression analysis or a multiple regression analysis. The method relating to regression analysis may be, for example, the least squares method.

[0042] The prediction model is, for example, a model that, when an explanatory variable including the reuse item collection information is input, outputs the required quantity of reuse items to be delivered as the target variable. The prediction model is, for example, a prediction model constructed by machine learning using training data that includes an explanatory variable including the reuse item collection information and a target variable which is the corrected quantity of reuse items to be delivered. The training data may include, for example, training data. The prediction model may be, for example, a model applicable to one delivery area, or a model applicable to multiple delivery areas in common. The machine learning method may be, for example, one that can construct the prediction model, and the mode of the machine learning method may be anything. The machine learning method may include, for example, supervised learning. The prediction model may be generated, for example, by the generation unit 14 of Embodiment 2 described later.

[0043] The regression equation may be stored, for example, in the memory 102 or storage device 104 of the device 10, or in the memory or storage device of a device other than the device 10. The prediction model may be stored, for example, in the memory 102 or storage device 104 of the device 10, or in the memory or storage device of a device other than the device 10.

[0044] The information output unit 13 outputs the required delivery quantity information for the reused items (S13, information output procedure).

[0045] The information output unit 13 may, for example, output the required quantity of reusable items information to the output device 106 of this device 10, or to the output device of a device other than this device 10. The information output unit 13 may, for example, output the required quantity of reusable items information to the memory 102 or storage device 104 of this device 10, or to the memory or storage device of a device other than this device 10. The information output unit 13 may, for example, store the outputted required quantity of reusable items information in the memory 102 or storage device 104 of this device 10, or to the memory or storage device of a device other than this device 10.

[0046] The method for predicting the required delivery quantity of reusable items as disclosed herein (hereinafter also referred to as the Method of Disclosure) is a method that is implemented by, for example, replacing each "procedure" in the Program of Disclosure with "process". Specifically, the Method of Disclosure includes, for example, an information acquisition process, a prediction process, and an information output process. The information acquisition process acquires information on the collection of reusable items for each collection area. The prediction process predicts the required delivery quantity of reusable items for each delivery area based on the information on the collection of reusable items for each collection area. The information output process outputs the required delivery quantity of reusable items. The Method of Disclosure can be implemented, for example, using the apparatus 10 of the Disclosure shown in Figure 1 or Figure 2. However, the Method of Disclosure is not limited to, for example, a method using the apparatus 10 of the Disclosure. The Method of Disclosure can be implemented by referring to, for example, the descriptions in the Program and the Apparatus of the Disclosure.

[0047] As described above, the reuse item required delivery quantity prediction program of this disclosure can obtain reuse item collection information for each collection area through an information acquisition procedure, predict the required delivery quantity of reuse items for each delivery area based on the reuse item collection information for each collection area through a prediction procedure, and output the required delivery quantity of reuse items through an information output procedure. Therefore, according to this disclosure, the required delivery quantity of reuse items can be predicted based on information regarding the collection of reuse items.

[0048] A cycle for reusing reusable goods includes, for example, a delivery process, a borrowing process, a return process, and a collection process. The delivery process is, for example, a process in which a reusable goods supplier delivers the reusable goods to a delivery area. The delivery area may include, for example, restaurants, convenience stores, offices, educational facilities, and mixed-use commercial facilities. The borrowing process is, for example, a process in which a reusable goods borrower borrows the delivered reusable goods from the delivery area. The return process is, for example, a process in which the reusable goods borrower returns the borrowed reusable goods to a collection area. The collection area may be, for example, a place where a reusable goods collection device, as described later, is located. The collection process is, for example, a process in which the reusable goods supplier collects the returned reusable goods from the collection area. The collection process may also be, for example, a process in which a reusable goods collection business collects the returned reusable goods from the collection area. In this case, the reuse goods supplier may, for example, obtain information regarding the collection of the returned reuse goods from the reuse goods collection business.

[0049] Conventionally, the quantity of reused items delivered was adjusted, for example, by determining the amount of reused items borrowed based on reused item identification information assigned to the reused items obtained by the borrower's terminal. However, this method of adjustment had problems, such as placing a burden on the borrower of the reused items and hindering their borrowing.

[0050] Therefore, to grasp the amount of reused goods that can be borrowed, it is envisioned that a system linkage will be established between the reused goods supplier and the reused goods borrower, as described in Patent Document 1. According to this system linkage, for example, the amount of reused goods that can be borrowed in the delivery area can be grasped, and the amount of reused goods that can be delivered according to the amount borrowed can be determined. However, the establishment of such a system linkage has problems, such as requiring investment of funds and requiring operational burdens.

[0051] The inventors of this disclosure, for example, focused on information regarding the collection of reused goods among the information available to the reused goods supplier in order to resolve these problems. As mentioned above, the quantity of reused goods delivered has been adjusted, for example, according to the quantity of reused goods borrowed. In the operation of the reuse cycle, it is assumed that most of the borrowed reused goods will be returned, for example, by the reused goods borrowers. That is, it is estimated that the quantity of reused goods collected will show a positive correlation with the quantity of reused goods borrowed, for example, which has been used as an indicator of the quantity of reused goods delivered. For this reason, the required quantity of reused goods delivered can be predicted, for example, based on the quantity of reused goods collected. It should be noted that the reason why the required quantity of reused goods delivered can be predicted based on the quantity of reused goods collected is not limited to this estimation, for example.

[0052] Thus, according to this disclosure, the required quantity of reusable goods to be delivered can be predicted based on information regarding the collection of reusable goods. Furthermore, according to this disclosure, the required quantity of reusable goods to be delivered can be predicted without any burden on the borrowers of the reusable goods, thus promoting the borrowing of such goods. Furthermore, according to this disclosure, the required quantity of reusable goods to be delivered can be predicted without the need to establish a system linkage between the reusable goods supplier and the delivery area business operators, thus reducing the financial and operational burdens.

[0053] [Embodiment 2] This document describes another example of the reuse item supply quantity forecasting program described herein.

[0054] Figure 4 is a block diagram showing the configuration of another example of the reuse item required delivery quantity forecasting device 10A. As shown in Figure 4, the reuse item required delivery quantity forecasting device 10A includes a generation unit 14 in addition to the configuration of the reuse item required delivery quantity forecasting device 10 of Embodiment 1. The hardware configuration of the reuse item required delivery quantity forecasting device 10A is the same as that of the reuse item required delivery quantity forecasting device 10 of Figure 2, except that the central processing unit 101 has the configuration of the reuse item required delivery quantity forecasting device 10A of Figure 4 instead of the configuration of the reuse item required delivery quantity forecasting device 10 of Figure 1. In addition, embodiments of this disclosure can be described by referring to, for example, the descriptions relating to other embodiments.

[0055] Another example of processing by the reuse item delivery quantity forecasting program of this disclosure will be explained in more detail with reference to Figure 5. Figure 5 is a flowchart showing an example of each step of the reuse item delivery quantity forecasting program of this disclosure. The reuse item delivery quantity forecasting program of this disclosure can be implemented, for example, using the apparatus 10A of this disclosure shown in Figure 4. Furthermore, the reuse item delivery quantity forecasting program of this disclosure can be implemented, for example, in the hardware configuration of the reuse item delivery quantity forecasting device 10 of this disclosure shown in Figure 2, where the central processing unit 101 has the configuration of the reuse item delivery quantity forecasting device 10A of this disclosure instead of the configuration of the reuse item delivery quantity forecasting device 10 of Figure 1. Note that the reuse item delivery quantity forecasting program of this disclosure is not limited to, for example, a program using the apparatus 10A of this disclosure. The processing of the generation unit 14 will be explained below. The processing of the generation unit 14 can be inserted at any appropriate position in the flowchart of Figure 3 described in the embodiment 1, for example, but as shown in Figure 5, it is preferable that the processing of the generation unit 14 be inserted after S11A, for example.

[0056] The information acquisition unit 11 further acquires, for example, information on the corrected quantity of reusable items delivered to the delivery area (S11A, information acquisition procedure). That is, in S11A, the information acquisition unit 11 acquires, for example, the information on the collection of reusable items for each collection area and the information on the corrected quantity of reusable items delivered to the delivery area.

[0057] The corrected reused goods delivery volume information is, for example, information obtained by correcting the reused goods delivery volume information for the predetermined period based on reused goods delivery volume adjustment information for the delivery area. The reused goods delivery volume information is, for example, information regarding the amount of reused goods delivered during the predetermined period. The amount of reused goods delivered may be, for example, the number of reused goods delivered or the weight of the reused goods delivered.

[0058] The reused goods delivery quantity adjustment information is, for example, information relating to adjustments made after delivery to the delivery quantity of the reused goods during the predetermined period. The reused goods delivery quantity adjustment information includes, for example, at least one of an increase adjustment information and a decrease adjustment information. The increase adjustment information is, for example, information relating to an increase adjustment to the delivery quantity of the reused goods during the predetermined period. The increase adjustment information is set as, for example, "+100 units" if the reused goods are increased by 100 units after delivery. The decrease adjustment information is, for example, information relating to a decrease adjustment to the delivery quantity of the reused goods during the predetermined period. The decrease adjustment information is set as, for example, "-100 units" if the reused goods are decreased by 100 units after delivery.

[0059] The correction of the reused goods delivery quantity information based on the reused goods delivery quantity adjustment information is performed, for example, by subtracting or adding the reused goods delivery quantity adjustment information to the reused goods delivery quantity information. The result of the correction of the reused goods delivery quantity information based on the reused goods delivery quantity adjustment information may be, for example, the execution result itself, or the absolute value of the execution result.

[0060] The reused goods delivery volume adjustment information includes, for example, at least one of temporary fluctuation adjustment information and seasonal fluctuation adjustment information. The temporary fluctuation adjustment information is, for example, information relating to adjustments for temporary fluctuations in the delivery volume of the reused goods. The temporary fluctuation is, for example, a temporary fluctuation in the delivery volume of the reused goods over time. The seasonal fluctuation adjustment information is, for example, information relating to adjustments for seasonal fluctuations in the delivery volume of the reused goods. The seasonal fluctuation is, for example, a seasonal fluctuation in the delivery volume of the reused goods over time.

[0061] The generation unit 14 generates the prediction model by machine learning using training data that includes, for example, explanatory variables including the reuse item collection information and a target variable which is the corrected reuse item delivery quantity information (S14, generation procedure).

[0062] Furthermore, the reuse item collection information may include, for example, distance-corrected reuse item collection quantity information. The distance-corrected reuse item collection quantity information is, for example, information obtained by correcting the reuse item collection quantity information based on the distance between the collection area and the delivery area. The correction process for the reuse item collection quantity information based on the distance between the collection area and the delivery area may be performed, for example, by dividing the reuse item collection quantity information by the distance between the collection area and the delivery area. According to this disclosure, for example, the influence that the distance between the collection area and the delivery area has on the reuse item collection information can be corrected.

[0063] The prediction unit 12 predicts the required quantity of reused items to be delivered using the prediction model (S12A, prediction procedure). The prediction model is, for example, a model that, when an explanatory variable including the reused item collection information is input, outputs the required quantity of reused items to be delivered as the target variable.

[0064] S13 is performed, for example, in the same way as S13 in Embodiment 1.

[0065] The method for predicting the required delivery quantity of reused goods as disclosed herein (hereinafter also referred to as the Method of Disclosure) is a method that is implemented by, for example, replacing each "procedure" in the Program of Disclosure with "process". Specifically, the Method of Disclosure further includes, for example, a generation process, wherein the information acquisition process further acquires corrected reused goods delivery quantity information for the delivery area, and the generation process generates the prediction model by machine learning using training data that includes explanatory variables including reused goods collection information and a target variable which is the corrected reused goods delivery quantity information. The Method of Disclosure can be implemented, for example, using the apparatus 10A of the Disclosure shown in Figure 4. However, the Method of Disclosure is not limited to, for example, a method using the apparatus 10A of the Disclosure. The Method of Disclosure can be implemented by, for example, referring to the descriptions in the Program and the Apparatus of the Disclosure.

[0066] According to the reuse item required delivery quantity prediction program of this disclosure, for example, an information acquisition procedure can further acquire corrected reuse item delivery quantity information for the delivery area, and a generation procedure can generate the prediction model by machine learning using training data that includes explanatory variables including reuse item collection information and a target variable which is the corrected reuse item delivery quantity information. Therefore, according to this disclosure, the required delivery quantity of reuse items can be predicted based on information regarding the collection of reuse items. Furthermore, according to this disclosure, for example, the required delivery quantity of reuse items can be predicted based on information regarding the collection of reuse items using the prediction model.

[0067] [Embodiment 3] This document describes another example of the reuse item supply quantity forecasting program described herein.

[0068] Figure 6 is a block diagram showing the configuration of another example of the reuse item required delivery quantity forecasting device 10B. As shown in Figure 6, the reuse item required delivery quantity forecasting device 10B includes a generation unit 14 and a selection unit 15 in addition to the configuration of the reuse item required delivery quantity forecasting device 10 of Embodiment 1. The hardware configuration of the reuse item required delivery quantity forecasting device 10B is the same as that of the reuse item required delivery quantity forecasting device 10 of Figure 2, except that the central processing unit 101 has the configuration of the reuse item required delivery quantity forecasting device 10B of Figure 6 instead of the configuration of the reuse item required delivery quantity forecasting device 10 of Figure 1. In addition, embodiments of this disclosure can be described by referring to, for example, the descriptions relating to other embodiments.

[0069] Another example of processing by the reuse item delivery quantity forecasting program of this disclosure will be explained in more detail with reference to Figure 7. Figure 7 is a flowchart showing an example of each step of the reuse item delivery quantity forecasting program of this disclosure. The reuse item delivery quantity forecasting program of this disclosure can be implemented, for example, using the apparatus 10B of this disclosure shown in Figure 6. Furthermore, the reuse item delivery quantity forecasting program of this disclosure can be implemented, for example, in the hardware configuration of the reuse item delivery quantity forecasting device 10 of Figure 2, where the central processing unit 101 has the configuration of the reuse item delivery quantity forecasting device 10B of Figure 6 instead of the configuration of the reuse item delivery quantity forecasting device 10 of Figure 1. Note that the reuse item delivery quantity forecasting program of this disclosure is not limited to, for example, a program using the apparatus 10B of this disclosure. The processing of the generation unit 14 and the selection unit 15 will be explained below. The processing of the generation unit 14 can be appropriately inserted at any position in the flowchart of Figure 5 described in the second embodiment, for example, but as shown in Figure 7, it is preferable that the processing of the generation unit 14 be inserted after S15, for example. The processing of the selection unit 15 can be appropriately inserted at any position in the flowchart of Figure 5 described in the second embodiment, for example, but as shown in Figure 7, it is preferable that the processing of the selection unit 15 be inserted after S11A, for example.

[0070] S11A is performed, for example, in the same way as S11A in Embodiment 2.

[0071] The selection unit 15 selects, for example, the reused item collection information for generating a prediction model from the reused item collection information based on the corrected reused item delivery quantity information (S15, selection procedure). The reused item collection information for generating a prediction model includes, for example, at least the reused item collection quantity information.

[0072] The selection unit 15 may, for example, select the reused item collection information for generating the prediction model from the reused item collection information based on the corrected reused item delivery quantity information by variable selection. The variable selection is performed, for example, on a regression equation constructed by regression analysis using data including explanatory variables including the reused item collection information and a target variable which is the corrected reused item delivery quantity information. The variable selection is, for example, a method of selecting explanatory variables that fit the target variable from a plurality of explanatory variables based on the variable selection criteria. The variable selection may be appropriately selected from, for example, known methods. Examples of the variable selection methods include the variable increase method, the variable decrease method, the variable increase / decrease method, and the variable decrease / increase method. The criteria for variable selection in the variable selection may be appropriately selected from, for example, known criteria. Examples of the criteria for variable selection include the coefficient of determination, the adjusted coefficient of determination, the Akaike Information Criterion (AIC), and the Bayesian Information Criterion (BIC).

[0073] The generation unit 14 generates the prediction model by machine learning using training data that includes, for example, explanatory variables including the reused product collection information for prediction model generation and the target variable which is the corrected reused product delivery quantity information (S14A, generation procedure). The reused product collection information for prediction model generation and the corrected reused product delivery quantity information may be used, for example, for additional training of the trained prediction model in addition to generating the prediction model. Examples of such additional training include transfer learning and fine tuning.

[0074] S12A is performed, for example, in the same way as S12A in Embodiment 2.

[0075] S13 is performed, for example, in the same way as S13 in Embodiment 1.

[0076] The method for predicting the required delivery quantity of reused goods as disclosed herein (hereinafter also referred to as the Method of Disclosure) is a method that is implemented by, for example, replacing each "procedure" in the Program of Disclosure with "process". Specifically, the Method of Disclosure further includes, for example, a selection process, wherein the information acquisition process further acquires corrected reused goods delivery quantity information for the delivery area, the selection process selects reused goods recovery information for prediction model generation from the reused goods recovery information based on the corrected reused goods delivery quantity information, and the generation process generates the prediction model by machine learning using training data that includes explanatory variables including the reused goods recovery information for prediction model generation and a target variable which is the corrected reused goods delivery quantity information. The Method of Disclosure can be implemented, for example, using the apparatus 10B of the Disclosure shown in Figure 6. However, the Method of Disclosure is not limited to, for example, the method using the apparatus 10B of the Disclosure. The Method of Disclosure can be implemented by, for example, by referring to the descriptions in the Program and the Apparatus of the Disclosure.

[0077] According to the reuse item required delivery quantity prediction program of this disclosure, for example, an information acquisition procedure further acquires corrected reuse item delivery quantity information for the delivery area, a selection procedure selects reuse item recovery information for prediction model generation from the reuse item recovery information based on the corrected reuse item delivery quantity information, and a generation procedure generates the prediction model by machine learning using training data that includes explanatory variables including the reuse item recovery information for prediction model generation and an objective variable which is the corrected reuse item delivery quantity information. Therefore, according to this disclosure, the required delivery quantity of reuse items can be predicted based on information regarding the recovery of reuse items. Furthermore, according to this disclosure, for example, a more accurate prediction model can be generated. Furthermore, according to this disclosure, for example, the required delivery quantity of reuse items can be predicted based on information regarding the recovery of reuse items using the more accurate prediction model.

[0078] [Embodiment 4] An example of how the device described in this disclosure can be used will be explained below with reference to Figure 8. However, this disclosure is not limited to the following explanation.

[0079] In this disclosure, the cycle for reusing reusable items includes, for example, the delivery process, the borrowing process, the return process, and the collection process described in Embodiment 1. As shown in Figure 8, three collection areas (collection areas A to C) are each arranged, for example, with reusable item collection devices A to C. Each of the reusable item collection devices is connected to this device, for example, via a wireless communication network.

[0080] First, this device acquires reuse item collection information for each collection area from each of the reuse item collection devices. Specifically, a reuse item borrower borrows a beverage container, which is a reuse item, from a coffee shop (shown as a delivery area in Figure 8), which is a reuse item borrowing business, and receives a beverage service using the borrowed reuse item. As shown in Figure 8, after drinking the beverage, the reuse item borrower returns the borrowed reuse item to one of the reuse item collection devices A to C located in collection areas A to C outside the coffee shop (outside the delivery area). As shown in Figure 8, each of the reuse item collection devices located in collection areas A to C transmits, for example, the number of returned reuse items and the date and time of return to this device via a wireless communication network as reuse item return information for each collection area. This device, for example, receives the information on the return of reused items for each collection area from each of the reused item collection devices as reused item collection information for each collection area.

[0081] Next, the reuse supplier executes the delivery of reused goods based on the required quantity of reused goods information. Specifically, the device stores, for example, a predictive model relating to the required quantity of reused goods information in its storage device. The device inputs, for example, the reused goods collection information as an explanatory variable into the predictive model. The predictive model, for example, executes a predictive process based on the explanatory variable and outputs the required quantity of reused goods information as the target variable as the execution result. The device displays, for example, the required quantity of reused goods information on a display, which is an output device on the terminal of the reused goods supplier. The reused goods supplier, for example, determines the required quantity of reused goods to be delivered based on the displayed required quantity of reused goods information. As shown in Figure 8, the reused goods supplier delivers the required quantity of reused goods to the coffee shop (shown as the delivery area in Figure 8) as a delivery of reused goods based on the required quantity of reused goods information. Thus, according to this disclosure, the required quantity of reusable goods to be delivered can be predicted based on information regarding the collection of reusable goods.

[0082] Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure can be made as can be understood by those skilled in the art within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0083] <Note> Some or all of the above embodiments may be described as follows, but are not limited to the following: (Note 1) This includes information acquisition procedures, prediction procedures, and information output procedures. The aforementioned information acquisition procedure acquires reuse item collection information for each collection area, The reuse item collection information includes information on the amount of reuse items collected. The aforementioned prediction procedure predicts the required quantity of reusable items to be delivered to the delivery area based on the reuse item collection information for each collection area. The information output procedure outputs the required delivery quantity information for the reused items. A program for predicting the required delivery quantity of reusable items, which causes a computer to perform each of the above steps. (Note 2) The aforementioned reuse item collection information further includes reuse item collection-related information, The aforementioned reuse item collection-related information includes at least one of the following: information on items not yet reused, information on the number of route searches, weather information at the time of collection, event information at the time of collection, and population information at the time of collection. The program for predicting the required supply quantity of reused items as described in Appendix 1. (Note 3) The aforementioned prediction procedure uses a prediction model to predict the required delivery quantity information for the reused items, The aforementioned prediction model is a model that, when given explanatory variables including the reuse item collection information, outputs the required quantity of reuse items as the target variable. A program for predicting the required delivery quantity of reused items as described in Appendix 1 or 2. (Note 4) Further including the generation procedure, The aforementioned information acquisition procedure further acquires information on the corrected quantity of reused items delivered to the delivery area. The aforementioned corrected reused goods delivery volume information is information obtained by correcting the reused goods delivery volume information based on the reused goods delivery volume adjustment information for the delivery area. The generation procedure generates the predictive model by machine learning using training data that includes explanatory variables including the reused item collection information and a target variable which is the corrected reused item delivery quantity information. The program for predicting the required supply quantity of reused items, as described in Appendix 3. (Note 5) The reuse item collection information includes distance-corrected reuse item collection quantity information, The distance-corrected reuse item collection quantity information is information obtained by correcting the reuse item collection quantity information based on the distance between the collection area and the delivery area. The program for predicting the required supply quantity of reused items, as described in Appendix 4. (Note 6) The aforementioned information on adjusting the quantity of reused goods delivered includes at least one of the following: temporary fluctuation adjustment information and seasonal fluctuation adjustment information. A program for predicting the required delivery quantity of reused items as described in Appendix 4 or 5. (Note 7) The selection procedure is further included, The selection procedure involves selecting reused item collection information for predictive model generation from the reused item collection information based on the corrected reused item delivery volume information. The reuse item collection information for generating the prediction model includes at least the reuse item collection quantity information, The generation procedure generates the prediction model by machine learning using training data that includes explanatory variables including reuse item collection information for generating the prediction model and a target variable which is the corrected reuse item delivery quantity information. A program for predicting the required supply quantity of reusable items, as described in any of the appendices 4 to 6. (Note 8) Including an information acquisition unit, a prediction unit, and an information output unit, The aforementioned information acquisition unit acquires reuse item collection information for each collection area. The reuse item collection information includes information on the amount of reuse items collected. The prediction unit predicts the required quantity of reusable items to be delivered to each delivery area based on the reuse item collection information for each collection area. The information output unit outputs the required quantity of reused items. A device for predicting the required delivery quantity of reused goods. (Note 9) The aforementioned reuse item collection information further includes reuse item collection-related information, The aforementioned reuse item collection-related information includes at least one of the following: information on items not yet reused, information on the number of route searches, weather information at the time of collection, event information at the time of collection, and population information at the time of collection. A device for predicting the required delivery quantity of reused items as described in Appendix 8. (Note 10) The prediction unit predicts the required delivery quantity information for reused items using a prediction model. The aforementioned prediction model is a model that, when given explanatory variables including the reuse item collection information, outputs the required quantity of reuse items as the target variable. A device for predicting the required delivery quantity of reused items as described in Appendix 8 or 9. (Note 11) It further includes a generating section, The information acquisition unit further acquires information on the corrected quantity of reused items delivered to the delivery area. The aforementioned corrected reused goods delivery volume information is information obtained by correcting the reused goods delivery volume information based on the reused goods delivery volume adjustment information for the delivery area. The generation unit generates the prediction model by machine learning using training data that includes explanatory variables including the reused item collection information and the target variable which is the corrected reused item delivery quantity information. A device for predicting the required delivery quantity of reused items as described in Appendix 10. (Note 12) The reuse item collection information includes distance-corrected reuse item collection quantity information, The distance-corrected reuse item collection quantity information is information obtained by correcting the reuse item collection quantity information based on the distance between the collection area and the delivery area. A device for predicting the required delivery quantity of reused items as described in Appendix 11. (Note 13) The aforementioned information on adjusting the quantity of reused goods delivered includes at least one of the following: temporary fluctuation adjustment information and seasonal fluctuation adjustment information. A device for predicting the required delivery quantity of reused items as described in Appendix 11 or 12. (Note 14) Further including the selected section, The selection unit selects reused item collection information for predictive model generation from the reused item collection information based on the corrected reused item delivery volume information. The reuse item collection information for generating the prediction model includes at least the reuse item collection quantity information, The generation unit generates the prediction model by machine learning using training data that includes explanatory variables, which include information on the collection of reused items for generating the prediction model, and an objective variable, which is the corrected amount of reused items delivered. A device for predicting the required delivery quantity of reusable items as described in any of Appendix 11 to 13. (Note 15) This includes an information acquisition process, a prediction process, and an information output process. The aforementioned information acquisition process acquires reuse item collection information for each collection area. The reuse item collection information includes information on the amount of reuse items collected. The prediction process predicts the required quantity of reusable items to be delivered to each delivery area based on the reuse item collection information for each collection area. The information output step outputs the required quantity of reused items. A method for predicting the required quantity of reusable goods, wherein each of the above steps is performed by a computer. (Note 16) The aforementioned reuse item collection information further includes reuse item collection-related information, The aforementioned reuse item collection-related information includes at least one of the following: information on items not yet reused, information on the number of route searches, weather information at the time of collection, event information at the time of collection, and population information at the time of collection. Method for predicting the required quantity of reused items to be delivered, as described in Appendix 15. (Note 17) The aforementioned prediction process predicts the required delivery quantity information for the reused items using a prediction model. The aforementioned prediction model is a model that, when given explanatory variables including the reuse item collection information, outputs the required quantity of reuse items as the target variable. Method for predicting the required delivery quantity of reused items as described in Appendix 15 or 16. (Note 18) Further including the production process, The aforementioned information acquisition process further acquires information on the corrected quantity of reused items delivered to the delivery area. The aforementioned corrected reused goods delivery volume information is information obtained by correcting the reused goods delivery volume information based on the reused goods delivery volume adjustment information for the delivery area. The generation step generates the predictive model by machine learning using training data that includes explanatory variables including the reused item collection information and a target variable which is the corrected reused item delivery quantity information. Method for predicting the required quantity of reused items to be delivered, as described in Appendix 17. (Note 19) The reuse item collection information includes distance-corrected reuse item collection quantity information, The distance-corrected reuse item collection quantity information is information obtained by correcting the reuse item collection quantity information based on the distance between the collection area and the delivery area. Method for predicting the required supply quantity of reused items as described in Appendix 18. (Note 20) The aforementioned information on adjusting the quantity of reused goods delivered includes at least one of the following: temporary fluctuation adjustment information and seasonal fluctuation adjustment information. Method for predicting the required quantity of reused items to be delivered, as described in Appendix 18 or 19. (Note 21) The selection process is further included, The selection process involves selecting reused item collection information for predictive model generation from the reused item collection information based on the corrected reused item delivery volume information. The reuse item collection information for generating the prediction model includes at least the reuse item collection quantity information, The generation step generates the prediction model by machine learning using training data that includes explanatory variables including reuse item collection information for generating the prediction model and a target variable which is the corrected reuse item delivery quantity information. Method for predicting the required supply quantity of reusable items as described in any of Appendix 18 to 20. (Note 22) This includes information acquisition procedures, prediction procedures, and information output procedures. The aforementioned information acquisition procedure acquires reuse item collection information for each collection area, The reuse item collection information includes information on the amount of reuse items collected. The aforementioned prediction procedure predicts the required quantity of reusable items to be delivered to the delivery area based on the reuse item collection information for each collection area. The information output procedure outputs the required delivery quantity information for the reused items. A computer-readable recording medium containing a program that causes a computer to perform each of the aforementioned steps. (Note 23) The aforementioned reuse item collection information further includes reuse item collection-related information, The aforementioned reuse item collection-related information includes at least one of the following: information on items not yet reused, information on the number of route searches, weather information at the time of collection, event information at the time of collection, and population information at the time of collection. Recording medium as described in Appendix 22. (Note 24) The aforementioned prediction procedure uses a prediction model to predict the required delivery quantity information for the reused items, The aforementioned prediction model is a model that, when given explanatory variables including the reuse item collection information, outputs the required quantity of reuse items as the target variable. Recording medium as described in Appendix 22 or 23. (Note 25) Further including the generation procedure, The aforementioned information acquisition procedure further acquires information on the corrected quantity of reused items delivered to the delivery area. The aforementioned corrected reused goods delivery volume information is information obtained by correcting the reused goods delivery volume information based on the reused goods delivery volume adjustment information for the delivery area. The generation procedure generates the predictive model by machine learning using training data that includes explanatory variables including the reused item collection information and a target variable which is the corrected reused item delivery quantity information. Recording medium as described in Appendix 24. (Note 26) The reuse item collection information includes distance-corrected reuse item collection quantity information, The distance-corrected reuse item collection quantity information is information obtained by correcting the reuse item collection quantity information based on the distance between the collection area and the delivery area. Recording medium as described in Appendix 25. (Note 27) The aforementioned information on adjusting the quantity of reused goods delivered includes at least one of the following: temporary fluctuation adjustment information and seasonal fluctuation adjustment information. Recording medium as described in Appendix 25 or 26. (Note 28) The selection procedure is further included, The selection procedure involves selecting reused item collection information for predictive model generation from the reused item collection information based on the corrected reused item delivery volume information. The reuse item collection information for generating the prediction model includes at least the reuse item collection quantity information, The generation procedure generates the prediction model by machine learning using training data that includes explanatory variables including reuse item collection information for generating the prediction model and a target variable which is the corrected reuse item delivery quantity information. A recording medium as described in any of the appendices 25 to 27. [Industrial applicability]

[0084] According to this disclosure, the required quantity of reusable goods can be predicted based on information regarding the collection of reusable goods. Therefore, this disclosure can be widely and usefully used in various fields where there is a need to supply reusable goods. [Explanation of Symbols]

[0085] 10, 10A, 10B Reusable Product Delivery Quantity Prediction Device 11 Information acquisition department 12 Prediction Section 13. Information Output Unit 14 Generation part 15 Selection Department 101 Central Processing Unit 102 memory 103 Bus 104 Storage device 105 Input device 106 Output device 107 Communication devices

Claims

1. This includes information acquisition procedures, prediction procedures, and information output procedures. The aforementioned information acquisition procedure acquires reuse item collection information for each collection area, The reuse item collection information includes information on the amount of reuse items collected. The aforementioned prediction procedure predicts the required quantity of reusable items to be delivered to the delivery area based on the reuse item collection information for each collection area. The information output procedure outputs the required delivery quantity information for the reused items. A program for predicting the required delivery quantity of reusable items, which causes a computer to perform each of the above steps.

2. The aforementioned reuse item collection information further includes reuse item collection-related information, The aforementioned reuse item collection-related information includes at least one of the following: information on items not yet reused, information on the number of route searches, weather information at the time of collection, event information at the time of collection, and population information at the time of collection. A program for predicting the required delivery quantity of reusable goods according to claim 1.

3. The aforementioned prediction procedure uses a prediction model to predict the required delivery quantity information for the reused items, The aforementioned prediction model is a model that, when given explanatory variables including the reuse item collection information, outputs the required quantity of reuse items as the target variable. A program for predicting the required delivery quantity of reusable goods according to claim 1.

4. Further including the generation procedure, The aforementioned information acquisition procedure further acquires information on the corrected quantity of reused items delivered to the delivery area. The aforementioned corrected reused goods delivery volume information is information obtained by correcting the reused goods delivery volume information based on the reused goods delivery volume adjustment information for the delivery area. The generation procedure generates the predictive model by machine learning using training data that includes explanatory variables including the reused item collection information and a target variable which is the corrected reused item delivery quantity information. A program for predicting the required delivery quantity of reusable goods as described in claim 3.

5. The reuse item collection information includes distance-corrected reuse item collection quantity information, The distance-corrected reuse item collection quantity information is information obtained by correcting the reuse item collection quantity information based on the distance between the collection area and the delivery area. A program for predicting the required delivery quantity of reusable goods as described in claim 4.

6. The aforementioned information on adjusting the quantity of reused goods delivered includes at least one of the following: temporary fluctuation adjustment information and seasonal fluctuation adjustment information. A program for predicting the required delivery quantity of reusable goods as described in claim 4.

7. The selection procedure is further included, The selection procedure involves selecting reused item collection information for predictive model generation from the reused item collection information based on the corrected reused item delivery volume information. The reuse item collection information for generating the prediction model includes at least the reuse item collection quantity information, The generation procedure generates the prediction model by machine learning using training data that includes explanatory variables including reuse item collection information for generating the prediction model and a target variable which is the corrected reuse item delivery quantity information. A program for predicting the required delivery quantity of reusable goods according to any one of claims 4 to 6.

8. Including an information acquisition unit, a prediction unit, and an information output unit, The aforementioned information acquisition unit acquires reuse item collection information for each collection area. The reuse item collection information includes information on the amount of reuse items collected. The prediction unit predicts the required quantity of reusable items to be delivered to each delivery area based on the reuse item collection information for each collection area. The information output unit outputs the required quantity of reused items. A device for predicting the required delivery quantity of reused goods.

9. This includes an information acquisition process, a prediction process, and an information output process. The aforementioned information acquisition process acquires reuse item collection information for each collection area. The reuse item collection information includes information on the amount of reuse items collected. The prediction process predicts the required quantity of reusable items to be delivered to each delivery area based on the reuse item collection information for each collection area. The information output step outputs the required quantity of reused items. A method for predicting the required quantity of reusable goods, wherein each of the above steps is performed by a computer.

10. This includes information acquisition procedures, prediction procedures, and information output procedures. The aforementioned information acquisition procedure acquires reuse item collection information for each collection area, The reuse item collection information includes information on the amount of reuse items collected. The aforementioned prediction procedure predicts the required quantity of reusable items to be delivered to the delivery area based on the reuse item collection information for each collection area. The information output procedure outputs the required delivery quantity information for the reused items. A computer-readable recording medium containing a program that causes a computer to perform each of the aforementioned steps.

Images