JP2017165502A - Article collecting work system, article collecting work method and article collecting work program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an article collecting work system and the like that does not reduce efficiency for an article collecting work even when the variety of articles is enhanced.SOLUTION: The article collecting work system 3 includes: an article relevant information including information having an impact on shipment date and shipment number of arrival articles: a prediction part 4 using a prediction model of calculating a relationship between shipment date and shipment number to predict a shipment prediction date of the arrival articles; and a determination part 5 for allocating the articles of which shipment prediction dates are predicted on the same date to the same shelf position or neighboring shelf positions.SELECTED DRAWING: Figure 11

Description

  The present invention relates to a technique for efficiently collecting articles stored on a shelf.

  Large quantities of goods are stored on huge shelves in warehouses where transporters and warehouses store goods in the course of distribution, and in backyards owned by retailers such as supermarkets and convenience stores. An operation of taking out the articles from the shelves by a person, a forklift, or the like is routinely performed according to demand. The articles handled by these companies have been diversified in recent years. In order to cope with this situation, a technique that enables an operator to efficiently collect a specific article from a shelf has been proposed (see Patent Document 1).

  In the technique described in Patent Document 1, after creating a Pareto chart by ABC analysis corresponding to inventory quantity, sales, and shipping quantity for each article, the article is based on a combination of inventory quantity, sales, and shipping quantity for each article. A dynamic rank is generated every time. Furthermore, with this technology, based on information such as the area of the shelf, the distance traveled between the shelf and the loading / unloading location, the movement time, the number of workers, etc., the total operating time required for loading and unloading each item in the current inventory status Is calculated. In this technique, the calculation value is set as an initial value, and an optimization simulation is performed to minimize the total operation time and the work time of each worker, and the shelf position of the article is changed.

  In other words, in this technology, as an optimization simulation, ABC analysis is performed for each of inventory quantity, sales, and shipment quantity, and a comprehensive evaluation based on the combination of the analysis results is given for each article. Shelf allocation for each article is determined.

JP-A-8-133427

  In Patent Document 1, when a product is shipped, since a plurality of types of articles are collected from a shelf, an operator needs to move to a plurality of locations on the shelf. For this reason, there is a problem that the efficiency of the collection work decreases as the number of types of articles increases.

  The present invention has been made to solve the above problems. The main object of the present invention is to provide a collection work device or the like that does not reduce the efficiency of collection work even if the number of types of articles increases.

In order to solve the above problems, the first feature of the present invention is:
A forecasting means for forecasting the predicted shipment date of the packaged item using a forecasting model for calculating the relationship between the item-related information including information that may affect the shipment date or the shipment number of the packaged item and the shipment number or the shipment date;
Determining means for allocating articles having the same predicted shipping date to the same or nearby shelf positions;
The collection work apparatus provided with.

The second feature of the present invention is that
Use a forecasting model that calculates the relationship between product-related information, including information that may affect the shipment date or number of shipments, and the shipment number or shipment date,
This is a collection work method in which articles having the same predicted shipping date are allocated to the same or nearby shelf positions.

The third feature of the present invention is that
Use a forecasting model that calculates the relationship between product-related information, including information that may affect the shipment date or number of shipments, and the shipment number or shipment date,
This is a collection work program for causing a computer to allocate articles having the same predicted shipping date to the same or nearby shelf positions.

  ADVANTAGE OF THE INVENTION According to this invention, the collection work apparatus etc. which the efficiency of collection work does not fall even if the kind of articles | goods increases can be provided.

It is a block diagram showing the example of a structure of the goods collection work apparatus which concerns on the 1st Embodiment of this invention. It is a table | surface which shows an example of the calendar information in an article | item related information storage part. It is a table | surface which shows an example of the calendar information in an article | item related information storage part. It is a table | surface showing an example of the article position information in an article position information storage part. It is a table | surface showing an example of the other article | item position information in an article | item position information storage part. It is a table | surface showing an example of the shelf position information in an article | item position information storage part. It is a table | surface showing an example of the shelf position information in an article | item position information storage part. It is a flowchart showing the operation example of the collection work apparatus which concerns on the 1st Embodiment of this invention. It is a block diagram showing the example of a structure of the collection work apparatus which concerns on the 2nd Embodiment of this invention. It is a flowchart showing the operation example of the collection work apparatus which concerns on the 2nd Embodiment of this invention. It is a block diagram showing the example of a structure of the collection work apparatus which concerns on the 3rd Embodiment of this invention. It is a block diagram showing the structural example of the information processing apparatus applicable to the collection work apparatus which concerns on each embodiment of this invention.

  Next, an embodiment of the present invention will be described with reference to the drawings. In the following description of the drawings, the same or similar parts are denoted by the same or similar reference numerals. However, the drawings schematically show the configuration of the embodiment of the present invention. Furthermore, the embodiment of the present invention described below is an example, and can be appropriately changed within a range in which the essence is the same.

<First Embodiment>
(Collection work device)
A configuration example of the collection work device 100 according to the first embodiment of the present invention will be described with reference to FIG.

  The collection work device 100 includes a shipping date prediction unit 11, a shelf allocation determination unit 12, a display unit 13, an article related information storage unit 14, an article position storage unit 15, and a prediction model storage unit 16.

  The article-related information storage unit 14 stores, for example, weather information, calendar information, shipping history information, and received article attribute information as information related to the article. Information including at least one of these pieces of information is referred to as article related information. The article-related information stored in the article-related information storage unit 14 is information acquired from the outside (weather information) or information acquired from the inside of the collection work device 100 (calendar information, shipping history information, and received item attribute information). is there. The article related information storage unit 14 only needs to be able to temporarily store these pieces of information as preprocessing of calculation processing using a prediction model described later. Note that information (identifier) for identification may be attached to the article.

  The weather information is information representing precipitation, humidity, temperature, wind speed, solar radiation, snow depth, and the like. The weather data classified by region and date published by the Japan Meteorological Agency may be used. In addition to this, the weather information of the article-related information may include information such as a discomfort index that can be calculated based on weather data. Furthermore, the maximum value, the minimum value, the average value, the standard deviation, and the like for each day of the weather information may be included. As the article-related information, at least one or more of the above weather information may be used.

  The calendar information is information indicating the day of the week or the type of holiday (Golden Week, Bon Festival, year-end / New Year holidays, single holidays, etc.). For the calculation process based on a prediction model, which will be described later, it is desirable for the collection work device 100 to handle these calendar information in numerical values. FIG. 2 shows an example of a table for converting information related to the day of the week into numerical values. FIG. 3 shows an example of a table for converting information related to the type of holidays into numerical values.

  The shipping history information is information indicating when and how many articles are shipped (shipping history).

  The received item attribute information is, for example, item attribute information representing properties and characteristics such as the size, color, shape, and price of the received item. For the calculation process based on a prediction model, which will be described later, it is desirable that the collection work device 100 handles the received item attribute information in numerical form. The size of an article is quantified as a vertical dimension, horizontal dimension, height dimension, or volume value. The color of the article is quantified as an RGB value of a representative color of the article when RGB (Red, Green, Blue) is 256 gradations. The shape of the article is quantified as a straight line ratio (a numerical value representing a squareness ratio) detected using Hough transform or the like.

  The article position storage unit 15 stores article position information indicating the position of the article. FIG. 4 shows an example of article position information. The item position information shown in FIG. 4 is a record including items of “predicted shipping date” collected for each piece of information for identifying an item (for example, item 1, item 2, etc.) and “shelf position” of a shelf for storing the item. is there. The predicted shipping date is a date predicted as a shipping date obtained by calculation processing of a prediction model described later. The article position storage unit 15 has a database structure in which the identification date of the article is used as a master key, and the predicted shipping date and the shelf position are arranged for each piece of identification information of the article. However, this is merely an example, and the article position storage unit 15 may have a database configuration in which the predicted shipping date is used as a master key and the corresponding shelf position and article identification information are arranged. FIG. 5 shows article position information in the latter database structure.

  The shelf position is a correspondence between an actual shelf and information that can identify each position in the shelf 1 for storing items for shipment. For example, FIG. 6 is a table showing shelf position information in which information for identifying a position is attached to each section (unit) in a shelf having a 4-stage, 4-row configuration. FIG. 7 is a table showing shelf position information in which information for identifying the position is attached to each section of the shelf 2 in a three-stage and six-row configuration. The information that can identify the position in the shelf is represented by, for example, “(stage) − (column)” (see FIGS. 6 and 7). That is, “1-2” indicates the second row in the first row.

  Information that can identify each section in each shelf is set in advance in the collection work device 100 and is stored in the article position storage unit 15 as shelf position information. The predicted shipment date and shelf position of the item position information are ordered by date by the shelf allocation determination unit 12 (for example, the item scheduled to be shipped on January 1 is scheduled to be shipped on January 2 in the “1-1” section of the shelf 1). May be arranged in the “1-2” section of the shelf 1). Alternatively, the shelf allocation determination unit 12 determines the shelf position based on information such as the distance in the shelf and the distance to the carry-in / out location, the movement time, the number of workers, the number of equipment to be carried out, the total amount of shipped goods, etc. (For example, a shipment day section with a large total amount of shipped goods may be a shelf at a position where the moving distance to the carry-in / out place is the shortest, and a section where the moving distance is the shortest) Etc.).

  The sizes (spaces) of the sections on each shelf may all be the same size. Articles having the same shipping date may be placed at the same or nearby shelf positions by the shelf allocation determination unit 12. Or you may change the magnitude | size of a division according to the total amount of the articles | goods to arrange | position, the magnitude | size, shape, etc. of articles | goods. Or the wall of the division in a shelf may be made movable, and it may be designed so that the size of the division can be changed according to the total amount, size and shape of the article.

  The article position information will be described with reference to FIG. Each record of the article position information represents a position (section) in the shelf where the article to be delivered on the predicted shipment date is entered. For example, the article group whose predicted shipment date is July 15, 2015 is arranged in the section of the third row and the fifth row in the shelf 2. This indicates that the group of articles whose predicted shipment date is July 16, 2015 is arranged in the section of the third row and the sixth row in the shelf 2. This indicates that the group of articles as of July 17, 2015 is arranged in the first row and first row of the shelf 1. When the number of articles with a specific predicted shipping date is very large and does not fit in one shelf position, it may be assigned to a plurality of sections. For example, if the number of articles whose predicted shipment date is July 17, 2015 is large and cannot be stored in the first row and the first row of the shelf 1, the first row and the first row and the second row of the shelf 1 are stored. Stored. In this case, the record of the article position information is “predicted shipping date: 2015/07/17, shelf position: 1-1, 1-2”.

  The prediction model storage unit 16 stores a model (prediction model) for predicting the shipping date of the received goods. The prediction model by the shipping date prediction unit 11 predicts the shipping date of the received goods based on weather information, calendar information, shipping history information, article attribute information, and the like.

  The shipping history information includes, for example, information indicating how many articles have been shipped on the same day of the week (1 week ago, 2 weeks ago, etc.). The prediction model is obtained by learning the relationship between these variables using the shipping history information and item attribute information as explanatory variables and the predicted shipment number of the item as the objective variable. How much does the article-related information contribute to the shipment number? A mathematical expression or function that expresses what to do. Note that the prediction model storage unit 16 stores in advance a prediction model created based on past shipment data of a certain article.

  A general machine learning technique can be applied to create the prediction model. An example of an expression representing a prediction model for obtaining the predicted shipment number is shown below (a, b, c, d are coefficients).

Y = aX1 + bX2 + cX3 + dX4 (Formula 1)
Formula 1 may be assumed that the objective variable (Y: predicted shipment number) is expressed by a linear sum of explanatory variables (X1, X2, X3, X4) using, for example, regression analysis. Also, a non-linear relationship may be assumed. In the explanatory variables of Equation 1, for example, X1 is the average temperature on the shipment date, X2 is numerical information indicating the day of the shipment date, X3 is the number of items shipped on the same day one week before the shipment date, and X4 is You may make it represent the volume value of the said goods, respectively. The explanatory variable is not limited to this, and any variable may be used as long as it represents the above-described weather information, calendar information, shipping history information, and article attribute information. The number of explanatory variables used is not limited to four. The coefficients a, b, c, and d in Equation 1 may be calculated by the least square method or may be calculated by another machine learning technique.

  When creating a prediction model for predicting the shipping date, the shipping date prediction unit 11 considers that all the same articles received on the same day are shipped on the same day, and the above objective variable is not the number of shipments. A prediction model may be created as the shipping date of the article. In this case, the shipping date prediction unit 11 outputs the predicted shipping date to the shelf allocation determination unit 12 as predicted shipping date information.

  Specifically, the shipping date prediction unit 11 predicts the shipping date of a received article when information on the arrival date of the article and the number of arrivals of the article are input. The shipment date prediction unit 11 predicts the shipment date of the received item based on the item related information stored in the item related information storage unit 14 and the prediction model stored in the prediction model storage unit 16 in advance. The shipping date information is output to the shelf allocation determination unit 12.

The shipping date prediction unit 11 substitutes article-related information into each variable of the prediction model, thereby predicting the number of shipments (n) for each number of days (m) elapsed from the arrival date with respect to the stock quantity of each article received. Is calculated. That is, the shipping date predicting unit 11 predicts information such as the number of shipments n ₁ after arrival (m) days, the number of shipments n ₂ after arrival (m + 1) days, etc., regarding the number of shipments after arrival of a certain received item. The shipping date prediction unit 11 outputs the number of shipments after the arrival date to the shelf allocation determination unit 12 as predicted shipping date information.

  In determining the allocation of articles to each shelf position, it is preferable that there is also item attribute information so that the number of articles that can be stored in the shelf position can be increased as much as possible. Therefore, the shipping date prediction unit 11 may acquire the item attribute information from the item related information storage unit 14 and input the acquired item attribute information to the shelf allocation determination unit 12.

  The shelf allocation determination unit 12 links (assigns) an item to a section based on the predicted shipment date information for each item input from the shipment date prediction unit 11 and the shelf position information acquired from the item position storage unit 15. I do. The shelf allocation determination unit 12 stores the allocation result in the article position storage unit 15 as article position information. Furthermore, the shelf allocation determination unit 12 outputs article position information to the display unit 13 in response to a request from the user. A plurality of articles having the same predicted shipping date input from the shipping date prediction unit 11 are collectively displayed in the same section. It should be noted that an empty section into which an article has not been carried is also displayed in a state of being marked so as to be recognized as an empty section.

  Note that the predicted shipping date information of the article may not be input from the shipping date prediction unit 11 for reasons such as a new product and no shipping history. In this case, the shelf allocation determination unit 12 may associate the article with the storage shelf position (section) instead of the shelf position associated with the predicted shipping date. Assume that the storage shelf position is set in advance by a management user or the like.

  When the product attribute information is input from the shipping date prediction unit 11, the shelf allocation determination unit 12 calculates an optimal product placement based on the size, shape, etc. of the product included in the product attribute information, and the calculated product placement It may be article position information including information.

  The display unit 13 is a monitor or the like for displaying the article position information calculated by the shelf allocation determination unit 12.

(Operation of collection work device)
The operation of the collection work apparatus 100 of this embodiment will be described with reference to the flowchart shown in FIG.

  In step S <b> 101, when the arrival date and the number of arrivals of a certain article are input, the shipping date prediction unit 11 acquires the article related information of the article from the article related information storage unit 14. Further, the shipping date prediction unit 11 acquires a prediction model from the prediction model storage unit 16.

  In step S <b> 102, the shipping date prediction unit 11 inputs the article related information to the prediction model, and acquires the predicted shipping date information of the received goods. The predicted shipment date information may include article attribute information. The shipping date prediction unit 11 outputs the predicted shipping date information of the article to the shelf allocation determination unit 12.

  In step S103, when the predicted shipment date information of a certain article is input, the shelf allocation determination unit 12 refers to the article position information in the article position storage unit 15 and already has another article position information on the same predicted shipment date. Check whether it is stored. If the item position information of another item on the same predicted shipping date is already stored in the item position storage unit 15, the process proceeds to step S104. If another item position information on the same predicted shipping date is not stored in the item position storage unit 15, the process proceeds to step S105.

  In step S <b> 104, the shelf allocation determination unit 12 acquires the article position information of another article on the same predicted shipment date from the article position storage unit 15.

  In step S105, the shelf allocation determination unit 12 performs allocation to the shelf position corresponding to the predicted shipment date information of the article to be processed. The predicted shipment date and shelf position of the item position information are ordered by date by the shelf allocation determination unit 12 (for example, the item scheduled to be shipped on January 1 is scheduled to be shipped on January 2 in the “1-1” section of the shelf 1). May be arranged in the “1-2” section of the shelf 1). Further, the shelf allocation determination unit 12 registers the execution result as article position information (predicted shipment date and shelf position of the article) linked to information for identifying the article (see FIGS. 4 and 5).

  In step S <b> 106, the shelf allocation determination unit 12 stores the allocation execution result, that is, the item position information for the received item in the item position storage unit 15.

  In step S107, the shelf allocation determination unit 12 outputs the article position information on the same predicted shipping date including the article to be processed to the display unit 13 (see FIG. 5). A user (a collection worker, an article transporter, or the like) transports an article to a predetermined shelf position based on the article position information output on the display unit 13 on the same predicted shipment date. Alternatively, the article position information on the same predicted shipping date may be transmitted to the transfer robot, and the transfer process based on the article position information may be performed. Thereby, a plurality of types of articles may be stored in one shelf position.

  In step S103, the shelf allocation determination unit 12 investigates whether another article position information on the same predicted shipping date is already stored. This is different information, for example, the same shelf position or the same You may investigate whether the information of goods is already stored. This is because, depending on the circumstances of the user, it may be desired to check other articles already stored in the same shelf position (section) (to check the free space capacity). Furthermore, it is to be able to cope with the case where it is desired to check other shelf positions of the same item (same items are stored in different sections for shipping on different shipping days). In this case, in step S107, the shelf allocation determination unit 12 outputs article position information in accordance with the user's request. For example, if the user's request is “same shelf position”, the shelf allocation determination unit 12 displays the article to be processed and other articles already stored in the same shelf position. If the user's request is “the same item”, the shelf allocation determination unit 12 displays the item to be processed and at least one predicted shipment date associated with the item. This can be realized by using existing relational database technology.

  The arrival of goods may be performed several times a day. Therefore, the shipping date prediction process for the received goods in the shipping date prediction unit 11 and the allocation of the article to the shelf position in the shelf allocation determination unit 12 may be performed every time the arrival is received. Alternatively, batch processing may be performed for one day.

  As described above, in the first embodiment of the present invention, the efficiency of the collection work does not decrease even if the number of articles to be received and shipped increases. This is because the shelf allocation determination unit 12 uses the predicted shipping date predicted by the shipping date prediction unit 11 to allocate the shelf position for each predicted shipping date instead of for each item. The worker can finish the collection work from one section in a certain shelf at the time of shipment. Thereby, the collection work can be completed in a short time.

<Second Embodiment>
A collection work apparatus 200 according to a second embodiment of the present invention will be described with reference to FIG. The collection work device 200 includes a shipping date prediction unit 11, a shelf allocation determination unit 12, a display unit 13, an article related information storage unit 14, an article position storage unit 15, a prediction model storage unit 16, a correction unit 17, and an input unit 18. I have.

  When receiving a correction instruction from a user or the like, the correction unit 17 takes out the article position information of the article allocated to the shelf position from the article position storage unit 15, corrects the article position information according to the correction instruction, and updates and registers it.

  The correction instruction is based on the article position information output by the shelf allocation determination unit 12, and when an operator collects articles that are scheduled to be shipped from a specific shelf position, an article that is not scheduled to be shipped due to some mistake is displayed on the shelf. This is an instruction issued when it is found that the object is placed at a position. Or it is an instruction | indication for correcting allocation to the shelf position of an article | item, when the goods to be shipped are not put on the said shelf position.

  The correction unit 17 outputs information that prompts correction processing in accordance with the correction instruction. For example, when an article that is not scheduled to be shipped is placed at a shelf position corresponding to a specific day, the correction unit 17 provides a space for storing only such a surplus article group in one section of the shelf and stores the space there. The information instructing is output. In addition, when the item to be shipped is not placed on the shelf position corresponding to the day, the correction unit 17 confirms the space for storing only the surplus article group in addition to the shelf position. From there, it outputs information instructing to collect goods as needed. The position of the shelf corresponding to the day on which the item to be shipped will be stored before the space for storing only the surplus item group is provided in a section of the shelf, or after the space is provided but no item is placed May not be placed in. In this case, the correction unit 17 instructs to take the necessary quantity from the place where the predicted shipment date is farthest among the places where the article is stored in the shelf.

  When the correction unit 17 detects a situation where an article not scheduled to be shipped is placed at a shelf position corresponding to a specific day and a situation where an article scheduled to be shipped is not placed at a shelf position corresponding to that day, The shipment date prediction unit 11 may be requested to re-predict the shipment date and the number of shipments for all articles.

  The input unit 18 is an interface that receives a correction instruction from a user or the like.

In the present embodiment, in the same manner as in the first embodiment, in addition to the allocation to the shelf not for each type of item but for each predicted shipping date, even if the shipping date is predicted incorrectly, Since the reallocation to the shelves is performed, the influence on the subsequent collection work can be reduced.
(Operation of collection work device)
The correction operation of the collection work device 200 of this embodiment will be described with reference to the flowchart shown in FIG. The overall operation of the collection work device 200 is the same as that shown in the flowchart of FIG.

  In step S201, the correction unit 17 receives a correction instruction from the user or the like via the input unit 18 or the like. The correction instruction includes information for identifying the article, shelf position, predicted shipping date, predicted shipping number, and the like.

  In step S202, the correction unit 17 corrects the article position information in the article position storage unit 15 based on the correction instruction, and performs update registration.

  In step S203, the correction unit 17 requests the shipping date prediction unit 11 to re-predict the shipping date and the number of shipments for the updated article position information. The shipping date prediction unit 11 performs prediction calculation using a prediction model for the updated article position information, and acquires the predicted shipping date information of the updated article. The predicted shipment date information may include article attribute information. The shipping date prediction unit 11 outputs the predicted shipping date information of the article to the shelf allocation determination unit 12.

  In step S <b> 204, the shelf allocation determination unit 12 allocates the updated article and the shelf position, and stores the allocation execution result, that is, the article location information for the updated article, in the article location storage unit 15.

  In step S205, the shelf allocation determination unit 12 outputs the article position information on the same predicted shipping date including the article to be processed to the display unit 13 (see FIG. 5). Note that article position information such as information on the same shelf position or the same article may be output. The display unit 13 displays the output article position information.

  Note that it is also possible to omit the processing of step S203 and step S204 and use article position information corrected based on the content of the correction instruction.

  As described above, in the second embodiment of the present invention, in addition to the effects of the first embodiment, even if the shipment date of an item is predicted or the assignment is incorrect, the item is restored to the shelf. Can be assigned. For this reason, the influence on subsequent collection work can be reduced. This is because the correction unit 17 updates the article position information in accordance with the correction instruction.

<Third Embodiment>
The collection work apparatus 3 concerning the 3rd Embodiment of this invention is demonstrated with reference to FIG. The collection work device 3 includes a prediction unit 4 and a determination unit 5.

  The prediction unit 4 predicts the predicted shipment date of the packaged item using a prediction model that calculates the relationship between the item-related information including information that may affect the shipment date or the shipment number of the packaged item and the shipment number or the shipment date. To do.

  The determination unit 5 allocates articles having the same predicted shipping date to the same or nearby shelf positions.

  In the present embodiment, the efficiency of the collection work does not decrease even if the types of articles increase. This is because the determination unit 5 uses the predicted shipping date predicted by the prediction unit 4 to assign the shelf position to each predicted shipping date instead of every item. The worker can finish the collection work from one section in a certain shelf at the time of shipment. Thereby, the collection work can be completed in a short time.

(Information processing device)
In each embodiment of the present invention, each component of the collection work device represents a functional unit block. Part or all of the components of the collection work device are realized by an arbitrary combination of an information processing device 500 and a program as shown in FIG. 12, for example. The information processing apparatus 500 includes the following configuration as an example.

CPU (Central Processing Unit) 501
ROM (Read Only Memory) 502
-RAM (Random Access Memory) 503
A program 504 loaded into the RAM 503
A storage device 505 for storing the program 504
A drive device 507 for reading / writing the recording medium 506
A communication interface 508 connected to the communication network 509
An input / output interface 510 for inputting / outputting data
-Bus 511 connecting each component
Each component of the collection work device in each embodiment is realized by the CPU 501 acquiring and executing a program 504 that realizes these functions. The program 504 that realizes the function of each component of the collection work device is stored in advance in the storage device 505 or the RAM 503, for example, and is read by the CPU 501 as necessary. Note that the program 504 may be supplied to the CPU 501 via the communication network 509 or may be stored in the recording medium 506 in advance, and the drive device 507 may read the program and supply it to the CPU 501.

  There are various modifications to the method for realizing the collection work device. For example, the collection work device may be realized by an arbitrary combination of the information processing device 500 and a program that are separately provided for each component. A plurality of constituent elements included in each device may be realized by an arbitrary combination of one information processing device 500 and a program.

  In addition, some or all of the components of the collection work device are realized by other general-purpose or dedicated circuits, processors, or combinations thereof. These may be configured by a single chip or may be configured by a plurality of chips connected via a bus.

  Part or all of each component of the collection work device may be realized by a combination of the above-described circuit and the like and a program.

  When some or all of the components of the collection work device are realized by a plurality of information processing devices and circuits, the plurality of information processing devices and circuits may be centrally arranged or distributedly arranged. May be. For example, the information processing apparatus, the circuit, and the like may be realized as a form in which each is connected via a communication network, such as a client and server system and a cloud computing system.

3: Collection work device 4: Prediction unit 5: Determination unit 11: Shipment date prediction unit 12: Shelf allocation determination unit 13: Display unit 14: Article related information storage unit 15: Article position storage unit 16: Prediction model storage unit 17 : Correction unit 18: Input unit 100: Collection work device 200: Collection work device 500: Information processing device 501: CPU
503: RAM
504: Program 505: Storage device 506: Recording medium 507: Drive device 508: Communication interface 509: Communication network 510: Input / output interface 511: Bus

Claims (6)

Prediction for predicting the predicted shipment date of the packaged item using a prediction model for calculating the relationship between the item-related information including information that may affect the shipment date or the number of shipments of the packaged item and the number of shipments or the shipment date Means,
Determining means for allocating articles having the same predicted shipping date to the same or nearby shelf positions;
A collection work device comprising: The article-related information includes at least one of weather information, calendar information, shipping history information, and arrival item attribute information indicating a property or characteristic of the arrival item.
The collection work apparatus according to claim 1. The prediction model is a model that machine-learns the relationship between the explanatory variable and the objective variable, using the article related information as an explanatory variable, a shipping forecast date of the article or a predicted shipping quantity of the article as an objective variable,
The product collection work apparatus of Claim 1 or Claim 2. The collection work according to any one of claims 1 to 3, further comprising correction means for re-execution of the assigned article and the assignment of the article to the shelf position in accordance with a correction command input from outside. apparatus. Using a prediction model for calculating the relationship between the article-related information including information that may affect the shipment date or the number of shipments of the packaged item and the number of shipments or the shipment date,
A collection work method in which articles having the same predicted shipping date are allocated to the same or nearby shelf positions. Using a prediction model for calculating the relationship between the article-related information including information that may affect the shipment date or the number of shipments of the packaged item and the number of shipments or the shipment date,
A collection work program for causing a computer to allocate an article having the same predicted shipping date to the same or a nearby shelf position.

Images