Work reproduction method, work reproduction device, and program

Abstract

This system enables highly granular work reproduction, contributing to improved accuracy in predicting work time at the work site. [Solution] The work reproduction method acquires work instruction information that instructs the shipment of goods in the warehouse and work performance information based on the instruction. It classifies the multiple elemental tasks that constitute the work performed based on the instruction into first elemental tasks, in which the time required by the worker does not vary easily, and second elemental tasks, in which the time required by the worker may vary. Based on the work performance information, it adjusts at least one of the start date and time and completion date and time of the second elemental task. Using the start date and time and completion date and time of the first elemental task based on the work performance information and the adjustment result of at least one of the start date and time and completion date and time of the second elemental task, it generates elemental task history information that reproduces the work performance of each of the multiple elemental tasks.

Description

Technical Field

[0001] The present disclosure relates to a work reproduction method, a work reproduction apparatus, and a program.

Background Art

[0002] Patent Document 1 discloses a work situation prediction device that predicts a future work situation in order to evaluate various operations. This work situation prediction device stores work plan data indicating a plan of an input work every predetermined period, stores work result data indicating a result of the input work every predetermined period, and predicts a future work amount every predetermined period from at least one of the work plan data and the work result data. The work situation prediction device predicts the work situation by reflecting the predicted work amount in the work plan data and displays the predicted result.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] It is considered that the work result data indicating the results of various operations in Patent Document 1 often has a large granularity (specifically, the fineness of the data). When there is a need to accurately predict how much working time is required for a certain operation, if the granularity of the work result data is large, there is a problem that the variation in working time is large and it is difficult to accurately predict the working time. That is, it can be said that there is room for improvement in the prior art with respect to accurately predicting the working time according to the content of the work.

[0005] The present disclosure has been devised in view of the above-described conventional situation, and an object thereof is to realize high-granularity work reproduction for improving the prediction accuracy of working time at the work site. [Means for solving the problem]

[0006] This disclosure provides a work reproduction method that acquires work instruction information instructing the shipment of goods in a warehouse and work performance information based on said instruction, classifies a plurality of elemental tasks constituting the work performed based on said instruction into first elemental tasks in which the time required by the worker is unlikely to fluctuate and second elemental tasks in which the time required by the worker may fluctuate, adjusts at least one of the start date and time and completion date and time of the second elemental task based on said work performance information, and generates elemental task history information that reproduces the work performance of each of the plurality of elemental tasks using the start date and time and completion date and time of the first elemental task based on said work performance information and the adjustment result of at least one of the start date and time and completion date and time of the second elemental task.

[0007] Furthermore, this disclosure provides a work reproduction device comprising a processor and a memory, wherein the processor, in cooperation with the memory, acquires work instruction information that instructs the shipment of goods in a warehouse and work performance information based on the instruction, classifies a plurality of elemental tasks constituting the work performed based on the instruction into first elemental tasks in which the time required by the worker is unlikely to fluctuate and second elemental tasks in which the time required by the worker may fluctuate, adjusts at least one of the start date and time and completion date and time of the second elemental task based on the work performance information, and generates elemental task history information that reproduces the work performance of each of the plurality of elemental tasks using the start date and time and completion date and time of the first elemental task based on the work performance information and the adjustment result of at least one of the start date and time and completion date and time of the second elemental task.

[0008] Furthermore, this disclosure provides a program for a computer-based work reproduction device to implement the following processes: acquiring work instruction information that instructs the shipment of goods in a warehouse and work performance information based on said instructions; classifying a plurality of elemental tasks that constitute the work performed based on said instructions into first elemental tasks in which the time required by the worker is unlikely to fluctuate and second elemental tasks in which the time required by the worker may fluctuate; adjusting at least one of the start date and time and completion date and time of the second elemental task based on said work performance information; and generating elemental task history information that reproduces the work performance of each of the plurality of elemental tasks using the start date and time and completion date and time of the first elemental task based on said work performance information and the adjustment result of at least one of the start date and time and completion date and time of the second elemental task.

[0009] These comprehensive or specific embodiments may be implemented as systems, devices, methods, integrated circuits, computer programs, or recording media, or as any combination of systems, devices, methods, integrated circuits, computer programs, and recording media. [Effects of the Invention]

[0010] According to this disclosure, it is possible to achieve highly granular work reproduction that contributes to improving the accuracy of predicting work time at the work site. [Brief explanation of the drawing]

[0011] [Figure 1] This figure shows an example of the system configuration of the work simulation system according to this embodiment. [Figure 2] Diagram showing an example of the data structure of work instruction information. [Figure 3] A schematic diagram showing example procedures for the elemental tasks that make up each process. [Figure 4] A schematic floor plan showing examples of the layout of various areas within the warehouse. [Figure 5] (a) A diagram showing an example of work history information with a certain level of granularity, (b) A diagram showing an example of work history information with a different level of granularity. [Figure 6]This figure shows an example of element work history information generated by on-site reproduction processing. [Figure 7] (a) A diagram showing an example of standard work time and whether or not it varies for each elemental task, (b) A diagram showing an example of movement speed for each worker. [Figure 8] This diagram schematically shows an example of the operation overview of the field reproduction process for management ID "1". [Figure 9] This diagram schematically shows an example of the operation overview of the field reproduction process for management ID "2". [Figure 10] A flowchart showing an example of the operation procedure for the field reproduction process according to this embodiment, in chronological order. [Figure 11] A diagram showing an example of the effect of the on-site reproduction process according to this embodiment. [Figure 12] This diagram illustrates an example of a layout change that involves moving work desks. [Figure 13] This diagram illustrates an example of a work change that involves the deletion of some elements of the outbound process. [Modes for carrying out the invention]

[0012] The following description will detail embodiments specifically disclosing the work reproduction method, work reproduction apparatus, and program related to this disclosure, with appropriate reference to the drawings. However, unnecessarily detailed explanations may be omitted. For example, detailed explanations of already well-known matters and redundant explanations of substantially identical configurations may be omitted. This is to avoid the following description becoming unnecessarily verbose and to facilitate understanding by those skilled in the art. The accompanying drawings and the following description are provided to enable those skilled in the art to fully understand this disclosure and are not intended to limit the subject matter of the claims.

[0013] Hereinafter, as embodiments of the work reproduction method, work reproduction apparatus, and program according to the present disclosure, a use case is addressed that targets various operations performed in a warehouse, such as receiving and storing merchandise to be stored, or retrieving and shipping merchandise to be shipped that is already in storage. Needless to say, the embodiments of the work reproduction apparatus according to the present disclosure are not limited to the content of the following description. Also, in the following description, the same reference numerals may be assigned to the same elements to simplify or omit the description.

[0014] 1. Configuration of Work Simulation System First, referring to FIG. 1, the system configuration of the work simulation system 100 according to the present embodiment will be described. FIG. 1 is a diagram showing an example of the system configuration of the work simulation system 100 according to the present embodiment. The work simulation system 100 includes at least an operation terminal 10, a warehouse management system 20, a warehouse control system 30, and a SIM processing device 40. The operation terminal 10 and the warehouse control system 30, the warehouse management system 20 and the warehouse control system 30, and the warehouse control system 30 and the SIM processing device 40 are connected to each other via a wired or wireless network so that data communication is possible. The wireless network may be, for example, a Wide Area Network (WAN), a Local Area Network (LAN), a Long Term Evolution (LTE), mobile communication such as 4G or 5G, power line communication, short-range wireless communication (e.g., Bluetooth (registered trademark) communication), or communication for mobile phones. The wired network may be, for example, a wired LAN or a wired WAN.

[0015] The operation terminal 10 is configured using, for example, a personal computer (PC). The operation terminal 10 receives a user input operation (hereinafter referred to as "user operation") using an input device (not shown) such as a keyboard or a mouse, and requests the warehouse control system 30 to execute various processes according to the input operation. Further, when the operation terminal 10 acquires a machine learning instruction for predicting the working time required for "operation" from the SIM processing device 40 via the warehouse control system 30, the operation terminal 10 executes machine learning using a plurality of learning data associated with the element operations of the corresponding "operation", thereby generating or updating a prediction model according to the machine learning instruction. Details of this machine learning instruction and the learning data associated with the element operations will be described later. The operation terminal 10 includes a memory 11, a processor 12, and a display device 13.

[0016] The memory 11 is configured using, for example, a Random Access Memory (RAM) and a Read Only Memory (ROM), and temporarily holds programs necessary for the operation of the operation terminal 10 and data acquired or generated during operation. The RAM is, for example, a work memory used during the operation of the operation terminal 10. The ROM stores and holds, for example, a program for controlling the operation terminal 10 in advance. Further, when executing machine learning, the memory 11 stores the machine learning program and data in the ROM.

[0017] The processor 12 is composed of at least one of the following: a Central Processing Unit (CPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), or a Graphical Processing Unit (GPU). The processor 12 functions as a controller that oversees the overall operation of the operating terminal 10. The processor 12 performs control processing to coordinate the operation of each part of the operating terminal 10, data input / output processing between the operating terminal 10 and each part, data calculation processing, and data storage processing. The processor 12 operates according to the program stored in the memory 11. When operating, the processor 12 uses the memory 11 to perform various processes in cooperation with it and temporarily stores the data it generates or acquires in the memory 11. Furthermore, when performing machine learning, the processor 12 works in cooperation with the memory 11 to perform machine learning using multiple training data stored in the memory 11.

[0018] The display device 13 is configured using, for example, a Liquid Crystal Display (LCD) or an organic EL display. The display device 13 displays various screens (not shown) generated by the processor 12 based on user operations. In Figure 1, the display device 13 is shown as being provided by the operation terminal 10, but it may be configured separately from the operation terminal 10.

[0019] The warehouse management system 20 manages operations (tasks) within the warehouse (in other words, the logistics center) and supports improvements in work accuracy and efficiency. Specifically, the tasks managed by the warehouse management system 20 include receiving management, which involves receiving goods into the warehouse (e.g., inspection and storage); shipping management, which involves shipping goods out of the warehouse (e.g., retrieval and packaging); inventory management, which involves monitoring the storage status of goods within the warehouse; and progress management, which involves monitoring the progress of various tasks. However, these tasks are merely examples of some of the tasks performed by the warehouse management system 20. The warehouse management system 20 is configured using, for example, one or more personal computers or server computers. The warehouse management system 20 includes memory 21 and a processor 22.

[0020] Memory 21 is configured, for example, using RAM and ROM, and temporarily stores programs necessary for the operation of the warehouse management system 20, as well as data acquired or generated during operation. RAM is, for example, work memory used during the operation of the warehouse management system 20. ROM stores, for example, programs for controlling the warehouse management system 20 in advance. Memory 21 also stores inventory information 23 and incoming / outgoing shipment information 24.

[0021] Inventory information 23 is data that shows the current storage status of each product currently stored in the warehouse. The contents of inventory information 23 may be added, modified, deleted, etc., based on instructions from other operating terminals (not shown in Figure 1) connected to the warehouse management system 20 for data communication, operating terminal 10, or the warehouse control system 30.

[0022] The inbound / outbound information 24 is data that shows detailed information, including the product identification number (ID), for each product that arrives into the warehouse. The inbound / outbound information 24 is data that shows detailed information, including the product identification number (ID), for each product that is shipped out of the warehouse. The contents of the inbound / outbound information 24 may be added, modified, deleted, etc., based on instructions from other operating terminals (not shown in Figure 1) connected to the warehouse management system 20 for data communication, operating terminal 10, or the warehouse control system 30.

[0023] The processor 22 is composed of at least one of the following: a CPU, DSP, FPGA, or GPU. The processor 22 functions as a controller that oversees the overall operation of the warehouse management system 20. The processor 22 performs control processing to coordinate the operation of each part of the warehouse management system 20, data input / output processing between each part of the warehouse management system 20, data calculation processing, and data storage processing. The processor 22 operates according to the program stored in the memory 21. When operating, the processor 22 uses the memory 21 to cooperate in executing various processes and temporarily stores data generated or acquired by the processor 22 in the memory 21.

[0024] The warehouse control system 30 has the role of integrated management of equipment by generating and sending work instructions to various pieces of equipment operating in the warehouse (e.g., transport robots, automated warehouses) based on instructions from the warehouse management system 20. Examples include a monitoring function that visualizes the progress of work in real time and a function that centrally manages the operational performance of equipment. However, these functions are merely examples of some of the functions of the processing performed by the warehouse control system 30. The warehouse control system 30 also instructs the SIM processing unit 40 to execute on-site reproduction processing using the instructions for the warehouse work to be performed (work instruction information) and the actual results of the warehouse work performed (work history information). Details of this on-site reproduction processing will be described later. The warehouse control system 30 is configured using, for example, one or more personal computers or server computers. The warehouse control system 30 includes memory 31 and a processor 32.

[0025] Memory 31 is configured, for example, using RAM and ROM, and temporarily stores programs necessary for the operation of the warehouse control system 30, as well as data acquired or generated during operation. RAM is, for example, work memory used during the operation of the warehouse control system 30. ROM stores, for example, programs for controlling the warehouse control system 30 in advance. Memory 31 also stores work instruction information 33 (see Figure 2) and work history information 34 (see Figures 5(a) and (b)).

[0026] Now, with reference to Figure 2, the work instruction information 33 will be explained. Figure 2 is a diagram showing an example of the data structure of the work instruction information.

[0027] Work instruction information 33 is data that instructs the warehouse management system 20 to ship goods stored in the warehouse by a target date and time. Work instruction information 33 consists of one record having a "management ID", "process", "product ID", and "target date and time" (see Figure 2). In the example in Figure 2, a table TB1 containing multiple work instruction information 33 is shown, and the data of this table TB1 is stored in memory 31. The management ID is an identification number that identifies the work instruction information, the process indicates the work process for the goods (see Figure 3), the product ID is the identification number of the goods targeted by the process, and the target date and time is the date and time until the process for the product ID is completed. Work instruction information 33 is generated by the processor 32 based on inventory information 23 and inbound / outbound information 24 periodically acquired from the warehouse management system 20, for example, and stored in memory 31.

[0028] Here, the work history information 34 will be explained with reference to Figures 5(a) and (b). Figure 5(a) is a diagram showing an example of work history information with a certain level of granularity, and Figure 5(b) is a diagram showing an example of work history information with a different level of granularity. Here, granularity refers to the degree of detail in the data structure (for example, the number of items that make up a record of data).

[0029] Work history information 34 is data that shows the actual work performed in response to work instruction information 33. Work history information 34 consists of one record having "Management ID", "Process", "Work", "Worker ID", "Work Start Date and Time", and "Work Completion Date and Time" (see Figure 5(a)). Alternatively, work history information 34 may also consist of one record having "Management ID", "Process", "Worker ID", "Work Start Date and Time", and "Work Completion Date and Time" (see Figure 5(b)). In other words, the work history information 34 in Figure 5(a) has a higher granularity than the work history information 34 in Figure 5(b), and therefore has a more detailed data structure. The relationship between "process" and "task" in the work history information will be explained later with reference to Figure 3, but for example, in order to complete the process "shipping" for management ID "1", four tasks "outbound, individual packaging, packing, and shipping" must be performed, and in the example in Figure 5(a), the tasks "outbound", "individual packaging", "packing", and "shipping" are performed in that order. The work history information 34 is generated by the processor 32 based on input operations from the operation terminal 10 that input work results (i.e., the start date and time and completion date and time of the task) and stored in memory 31.

[0030] Note that the work history information 34 in Figures 5(a) and 5(b) is the work history information for each task as of 9:32 AM on April 1, 2024. Therefore, the process "Shipping" for management ID "2," for which the completion date and time of the work is not recorded, is currently in an incomplete state (in other words, work in progress) because the "Outbound" task has not yet been completed.

[0031] The processor 32 is composed of at least one of the following: a CPU, DSP, FPGA, or GPU. The processor 32 functions as a controller that oversees the overall operation of the warehouse control system 30. The processor 32 performs control processing to coordinate the operation of each part of the warehouse control system 30, data input / output processing between each part of the warehouse control system 30, data calculation processing, and data storage processing. The processor 32 operates according to the program stored in the memory 31. When operating, the processor 32 uses the memory 31 to cooperate in executing various processes and temporarily stores data generated or acquired by the processor 32 in the memory 31.

[0032] Based on instructions from the warehouse control system 30, the SIM processing device 40 performs on-site reproduction processing to derive the start date and time and completion date and time for each elemental task when the contents of the "task" (see Figure 5(a) or Figure 5(b)) in the work history information 34 stored in the warehouse control system 30 are broken down (in other words, subdivided) into "elemental tasks". The SIM processing device 40 is configured using, for example, one or more personal computers or server computers. The SIM processing device 40 includes a memory 41 and a SIM processor 42.

[0033] Memory 41 is configured, for example, using RAM and ROM, and temporarily stores programs necessary for the operation of the SIM processing device 40, as well as data acquired or generated during operation. RAM is, for example, work memory used during the operation of the SIM processing device 40. ROM stores, for example, programs for controlling the SIM processing device 40 in advance. Memory 41 also stores parameters 43 (see Figures 7(a) and (b)) and element work information 44 (see Figure 3).

[0034] Here, the element work information 44 will be explained with reference to Figures 3 and 4. Figure 3 is a schematic diagram showing an example of the procedure for element work of each work that constitutes the process. Figure 4 is a schematic plan view showing an example of the layout of various areas in the warehouse. As shown in Figure 4, the warehouse has various areas (specifically, the receiving / shipping area W1, the work area W2, and the storage area W3). The receiving / shipping area W1 is composed of the receiving area W11 and the shipping area W12. The receiving area W11 is the area where goods arriving at the warehouse are placed. The shipping area W12 is the area where goods LG scheduled to be shipped from the warehouse are placed on shipping shelves W121 or loaded onto trucks W122, etc.

[0035] The work area W2 is divided into the receiving work area W21, the shipping work area W22, and the document shelf W23. The receiving work area W21 is the area where necessary tasks (e.g., inspection) are performed for storing goods received from the receiving area W11 in the storage area W3. The shipping work area W22 is the area where necessary tasks (e.g., packaging) are performed for shipping goods that have been transported from the storage area W3, and includes at least individual packaging shelves W221, work desks W222, packaging shelves W223, and work desks W224. The document shelf W23 is the area where documents recording various information about received goods are stored for each product. This information includes, for example, information about the product shelves in the storage area W3 where the goods are stored.

[0036] Storage area W3 is the area where goods that have been processed for storage in the receiving area W21 and transported by cart KT, etc., are stored. In the example in Figure 4, storage area W3 has multiple product shelves (specifically, product shelves A, B, C, D, E, F, G, H, I). Goods brought to storage area W3 are stored on one of the product shelves until they are shipped.

[0037] In the example in Figure 3, under "Process" F1, which corresponds to the major category of warehouse work to be performed in warehouse WH, four "tasks" corresponding to the subcategories of the lower level are provided. Specifically, the subcategories are task "Outbound," task "Individual Packaging," task "Packing," and task "Shipping." In other words, each "task" is composed of multiple elemental tasks that are broken down (subdivided) according to their content. Elemental task information 44 shows information on multiple elemental tasks that are associated with a single task and executed in order when a single task is composed of multiple elemental tasks.

[0038] The "Outbound" operation F11 has multiple elemental operations. Specifically, the "Outbound" operation has elemental operation information 44 which includes the elemental operations "Move to document shelf" F111, "Retrieve document" F112, "Move to product shelf" F113, "Retrieve product" F114, "Move to individual packaging shelf" F115, and "Store product" F116, and these elemental operations are executed in this order. The "Outbound" operation has three movement operations and three operation operations. Movement operations are elemental operations in which an operator moves within the warehouse (an example of a first elemental operation), and there is little variation in the time required for these operations by operators. On the other hand, operation operations are elemental operations performed by an operator at the relevant location within the warehouse (an example of a second elemental operation), and there may be variation in the time required for these operations by operators.

[0039] "Move to Invoice Shelf" F111 is an element task to move to the invoice shelf W23 located in the work area W2. "Retrieve Invoice" F112 is an element task to retrieve the invoice for the product to be shipped from the invoice shelf W23. "Move to Product Shelf" F113 is an element task to move from the invoice shelf W23 to the storage area W3 using a cart KT or similar to find the product to be shipped. "Retrieve Product" F114 is an element task to retrieve the product to be shipped from the product shelf indicated on the invoice, etc. "Move to Individual Packaging Shelf" F115 is an element task to move and carry the product retrieved from the storage area W3 to the individual packaging shelf W221 in the shipping work area W22 using a cart KT or similar. "Store Product" F116 is an element task to store the product carried using a cart KT or similar into the individual packaging shelf W221.

[0040] Furthermore, the "Packaging" task F12 has multiple elemental tasks. That is, the "Packaging" task has elemental task information 44 which includes the elemental tasks "Move to packaging shelf" F121, "Retrieve product" F122, "Move to work desk" F123, "Packaging" F124, "Move to packing shelf" F125, and "Store product" F126, and these elemental tasks are executed in that order. Similarly, the "Packaging" task has three movement tasks and three operation tasks.

[0041] "Move to individual packaging shelf" F121 and "Retrieve product" F122 are identical to "Move to individual packaging shelf" F115 and "Retrieve product" F116, respectively, so the explanation of the overlapping content will be omitted. "Move to work desk" F123 is an element task that moves from individual packaging shelf W221 in shipping work area W22 to work desk W222 in the same shipping work area W22. "Individual packaging" F124 is an element task that wraps the products brought to work desk W222 individually with wrapping paper. "Move to packing shelf" F125 is an element task that moves from work desk W222 in shipping work area W22 to packing shelf W223 in the same shipping work area W22. "Store product" F126 is an element task that stores the individually packaged products into the packing boxes located on packing shelf W223.

[0042] Furthermore, the "packing" task F13 has multiple elemental tasks. That is, the "packing" task has elemental task information 44 which includes the elemental tasks "move to packing shelf" F131, "get goods" F132, "move to work desk" F133, "pack" F134, "move to shipping shelf" F135, and "store packing box" F136, and these elemental tasks are executed in that order. Similarly, the "packing" task has three movement tasks and three operation tasks.

[0043] "Move to packing shelf" F131 and "Retrieve product" F132 are identical to "Move to packing shelf" F125 and "Retrieve product" F126, respectively, so the explanation of the overlapping content will be omitted. "Move to work desk" F133 is an element task that moves from packing shelf W223 in shipping work area W22 to work desk W224 in the same shipping work area W22. "Pack" F134 is an element task that packs the product that has been brought to work desk W224. "Move to shipping shelf" F135 is an element task that moves from work desk W222 in shipping work area W22 to shipping area W12. "Store in packing box" F136 is an element task that stores the packed product in the prepared packing box located on shipping shelf W121.

[0044] Furthermore, the "shipping" task F14 has multiple elemental tasks. That is, the "shipping" task has elemental task information 44 which includes the elemental tasks "move to shipping rack" F141, "get packing box" F142, "move to truck" F143, and "load" F134, and these elemental tasks are executed in that order. Similarly, the "shipping" task has two movement tasks and two operation tasks.

[0045] "Move to shipping shelf" F141 is identical to "Move to shipping shelf" F135, so the explanation of the redundant content will be omitted. "Get packing box" F143 is an element operation to retrieve the product to be shipped, which is located on shipping shelf W121 in shipping area W12. "Move to truck" F143 is an element operation to move from shipping shelf W121 in shipping area W12 to truck W122 in the same shipping area W12. "Load" F144 is an element operation to load packing boxes containing multiple products into the delivery area of ​​truck W122.

[0046] Here, parameter 43 will be explained with reference to Figures 7(a) and (b). Figure 7(a) is a diagram showing an example of standard work time and whether or not there is variation for each element work, and Figure 7(b) is a diagram showing an example of movement speed for each worker. Parameter 43 is, for example, the data in table TB6 shown in Figure 7(a) and the data in table TB7 shown in Figure 7(b), but is not limited to these data. For example, parameter 43 may also include the data of work instruction information 33 and work history information 34 transmitted from the warehouse control system 30.

[0047] Table TB6, shown in Figure 7(a), is an example of parameter 43. It associates the standard work time and whether or not there is temporal variation for each of the multiple elemental work tasks that constitute a "task" corresponding to a lower level of the major category "process." The data in Table TB6 is stored as parameter 43 in memory 41. The elemental work tasks in Table TB6 are limited to the latter of "operation" elemental work tasks, rather than "movement" elemental work tasks. This is because "movement" elemental work tasks are less likely to experience significant temporal variation due to the worker. In the example in Figure 7(a), the elemental work task "product acquisition" is defined as taking "60" seconds as its standard work time, but because this elemental work "product acquisition" is prone to temporal variation due to the worker, the presence or absence of variation is defined as "yes." Similarly, the elemental work task "product storage" is defined as taking "20" seconds as its standard work time, but because this elemental work "product storage" is prone to temporal variation due to the worker, the presence or absence of variation is defined as "yes." On the other hand, the element task "document acquisition" is defined as taking a standard work time of "10" seconds. However, because this element task "document acquisition" is a relatively simple task, there is little variation in the time taken by workers, so the presence or absence of variation is defined as "none".

[0048] Table TB7, shown in Figure 7(b), is an example of parameter 43, associating "worker" with "movement speed." The data in table TB7 is stored as parameter 43 in memory 41. The worker's movement speed may vary slightly depending on the worker's walking speed. Therefore, table TB7 is referenced when performing the field reproduction process (see below), taking into account the movement speed of the worker actually performing the elemental task.

[0049] The SIM processor 42 is composed of at least one of the following: a CPU, DSP, FPGA, or GPU. The SIM processor 42 functions as a controller that oversees the overall operation of the SIM processing unit 40. The SIM processor 42 performs control processing to coordinate the operation of each part of the SIM processing unit 40, data input / output processing between each part of the SIM processing unit 40, data calculation processing, and data storage processing. The SIM processor 42 operates according to the program stored in the memory 41. When operating, the SIM processor 42 uses the memory 41 to perform various processes in cooperation with the memory, and temporarily stores data generated or acquired by the SIM processor 42 in the memory 41. The SIM processor 42, in cooperation with the memory 41, realizes the functions of the field reproduction unit 45.

[0050] The field reproduction unit 45 executes field reproduction processing using the parameters 43 and element work information 44 stored in the memory 41 to generate element work history information 46 (see Figure 6). Field reproduction processing is a process that, when the work constituting a process is broken down (subdivided) into multiple element work, uses the parameters 43 and element work information 44 to derive (determine) the start date and time and the completion date and time of each element work.

[0051] Here, with reference to Figure 6, the element work history information 46, which is a deliverable of the on-site reproduction process, will be explained. Figure 6 is a diagram showing an example of element work history information 46 generated by the on-site reproduction process. The element work history information 46 in Figure 6 consists of element work history information TB4 generated in correspondence with the process of management ID "1" in Figure 5(a) or Figure 5(b), and element work history information TB5 generated in correspondence with the process of management ID "2".

[0052] In Figure 6, the element work history information TB4 and TB5, respectively, are data that associate element work, the worker who performed the element work, and the start and completion dates of the work for each process (e.g., shipping) with management IDs "1" and "2". Specifically, the elements work, the worker who performed the element work, and the start and completion dates of the work. For example, in the work history information 34 of Figure 5(a), for the process (e.g., shipping) with management ID "1", the start and completion dates of each task (i.e., shipping, individual packaging, packing, shipping) are recorded. In the work history information 34 of Figure 5(b), for the process (e.g., shipping) with management ID "1", the start and completion dates of the work for the entire process are recorded. However, the data in the work history information 34 of Figures 5(a) and 5(b) alone could not be used to derive or know the start and completion dates of each of the multiple element work actually performed to complete the "shipping" task or the "dispatch" process.

[0053] Therefore, the field reproduction unit 45 of the SIM processing device 40 according to this embodiment generates elemental work history information 46 by deriving the start date and time and completion date and time for each elemental work that constitutes the work through field reproduction processing. This allows the warehouse manager to understand exactly what elemental work was performed and how long it took to complete the "shipping" operation. Furthermore, by preparing multiple training data sets that pair elemental work with the time required for that elemental work and then performing machine learning, it becomes possible to construct an inference model that can predict the time required for elemental work.

[0054] In the work history information 34 in Figure 5(a) or Figure 5(b), for the process "Shipping" with management ID "1", the start date and time and completion date and time of all tasks (outbound, individual packaging, packing, shipping) or the entire process are recorded. However, for the process "Shipping" with management ID "2", the start date and time and completion date and time of all tasks are not recorded. In other words, the process "Shipping" with management ID "2" is still in a work-in-progress state. Even if the target is a process in such a work-in-progress state, as long as information on the start date and time of the work is recorded, the field reproduction unit 45 can predict the completion date and time of that work-in-progress process through field reproduction processing (see Figure 6).

[0055] 2. Overview and Operating Procedure of On-Site Reproduction Process Next, with reference to Figures 8 to 10, the overview and operation procedure of the field reproduction process performed by the SIM processing device 40 according to this embodiment will be described. Figure 8 is a schematic diagram showing an example of the operation overview of the field reproduction process for management ID "1". Figure 9 is a schematic diagram showing an example of the operation overview of the field reproduction process for management ID "2". Figure 10 is a flowchart showing an example of the operation procedure of the field reproduction process according to this embodiment in chronological order. The series of processes in Figure 10 are executed by the SIM processor 42 of the SIM processing device 40.

[0056] Figure 8 illustrates the work history information (see Figure 5(a)) as of 9:32 AM on April 1, 2024, showing the "Outbound" task of process "Shipping" with worker "A" as the target of the on-site reproduction process. According to the work history information 34 in Figure 5(a), the start date and time of this "Outbound" task is recorded as 9:00 AM on April 1, 2024, and the end date and time is recorded as 9:10 AM on April 1, 2024. The on-site reproduction unit 45 of the SIM processor 42 of the SIM processing device 40 classifies the multiple elemental tasks constituting the "Outbound" task into "Movement" elemental tasks and "Operation" elemental tasks based on the elemental task information 44 stored in the memory 41. As a result, as shown in Figure 8, the elemental tasks for "movement" are classified as elemental tasks "move to slip shelf" F111, elemental tasks "move to product shelf" F113, and elemental tasks "move to individual packaging shelf" F115, while the elemental tasks for "operation" are classified as elemental tasks "receive slip" F112, elemental tasks "receive product" F114, and elemental tasks "store product" F116.

[0057] Furthermore, the field simulation unit 45 provisionally derives the start and completion dates and times for each elemental task constituting the "outbound" operation by adding the standard work time required for worker "A" to complete each elemental task, based on table TB6 in Figure 7(a) and table TB7 in Figure 7(b). This provisional deriving also takes into account the movement speed of table TB7 in Figure 7(b). According to this provisional deriving, the completion date and time for the last elemental task of the "outbound" operation, "product storage," becomes "9:09:20," which is 40 seconds earlier than the actual completion date and time of the "outbound" operation, "9:10:00." In other words, simply adding the standard work times would result in a 40-second deficit. Therefore, the field simulation unit 45 adjusts the standard work time for elemental tasks where there is a variation in standard work time, thereby correcting at least one of the start and completion dates and times for those elemental tasks.

[0058] Specifically, the field reproduction unit 45 adjusts the standard work time (60 seconds) of the element task "product acquisition" F114 by 1.5 times to 90 seconds, and further adjusts the standard work time (20 seconds) of the element task "product storage" F116 by the same 1.5 times to 30 seconds. As a result, the field reproduction unit 45 can derive the work start date and work completion date and time for each element task so that they match the actual work start date and work completion date and time in the work history information table TB2 in Figure 5(a) (see Figure 6).

[0059] Figure 9 illustrates the "Outbound" task of the "Shipping" process with management ID "2" in the work history information (see Figure 5(a)) as of 9:32 a.m. on April 1, 2024, as an example of the target of the on-site reproduction process. According to the work history information 34 in Figure 5(a), the start date and time of this "Outbound" task is recorded as 9:30 a.m. on April 1, 2024, but the completion date and time is not recorded, indicating that it is in a work-in-progress state. The on-site reproduction unit 45 of the SIM processor 42 of the SIM processing device 40 classifies the multiple elemental tasks that constitute the "Outbound" task into "Movement" elemental tasks and "Operation" elemental tasks based on the elemental task information 44 stored in the memory 41. As a result, as shown in Figure 9, the elemental tasks for "movement" are classified as elemental tasks "move to slip shelf" F111, elemental tasks "move to product shelf" F113, and elemental tasks "move to individual packaging shelf" F115, while the elemental tasks for "operation" are classified as elemental tasks "receive slip" F112, elemental tasks "receive product" F114, and elemental tasks "store product" F116.

[0060] Furthermore, based on table TB6 in Figure 7(a) and table TB7 in Figure 7(b), the field reproduction unit 45 provisionally derives the start date and completion date and time for each elemental task constituting the "Outbound" operation by adding the standard work time required for worker "B" to complete each elemental task. In this provisional deriving, the movement speed of table TB7 in Figure 7(b) is also taken into account, and the start date and completion date and time for each elemental task "Move to document shelf" F111 and elemental task "Retrieve document" F112, which constitute the "Outbound" operation and were incomplete as work history information, can be derived. In this provisional deriving, the field reproduction unit 45 uses the standard work times for each elemental task "Move to document shelf" F111 and elemental task "Retrieve document" F112 of the "Outbound" operation as they are.

[0061] In Figure 10, the SIM processor 42 reads and acquires work instruction information 33 and work history information 34 transmitted from the warehouse control system 30 from the memory 41 (St1). The SIM processor 42 reads and acquires parameters 43 and element work information 44 from the memory 41 (St2). The SIM processor 42 executes the process in step St3 for each relevant work (e.g., outbound, individual packaging, packing, shipping).

[0062] Specifically, the SIM processor 42 classifies the multiple elemental tasks constituting the relevant task into "movement" elemental tasks and "operation" elemental tasks based on the elemental task information 44 (St3-1). Based on the worker's movement speed corresponding to table TB6 in Figure 7(a) and table TB7 in Figure 7(b), the SIM processor 42 uses the standard work time as is for "movement" elemental tasks, uses the standard work time as is for "operation" elemental tasks where there is "no" variation in standard work time, and uses the standard work time to adjust at least one of the work start date and time and work completion date and time in the work history information for "operation" elemental tasks where there is "variation" in standard work time (St3-2). The SIM processor 42 generates elemental task history information for each relevant task (see Figure 6) using the processing result of step St3-2 (St3-3).

[0063] The SIM processor 42 generates and outputs element work history information for the process using the processing results of steps St1 to St3 (St4). Based on the element work history information generated in step St4, the SIM processor 42 generates training data for each element work of each "operation" that contains the start date and time and the completion date and time of that element work. The SIM processor 42 generates machine learning instructions for an estimation model to predict the work duration of the corresponding element work using multiple training data, and sends them to the operation terminal 10 (St5).

[0064] 3. Effects of on-site reproduction processing Next, with reference to Figures 11 to 13, examples of the effects of the field reproduction processing of the SIM processing device 40 according to this embodiment will be explained. Figure 11 is a diagram showing an example of the effects of the field reproduction processing according to this embodiment. Figure 12 is a diagram showing an example of a layout change that involves the movement of a work desk. Figure 13 is a diagram showing an example of a work change that involves the deletion of some of the elements of the outbound work.

[0065] As shown in Figure 11, before the field reproduction process according to this embodiment was performed (before application of field reproduction), when targeting work history H1 which has multiple work histories H11, H12, ..., prediction models MD11, MD12, ... for predicting the work duration corresponding to each work history were individually generated by machine learning or the like. The shipping process in work history H11 corresponds to the major category process F1 (e.g., shipping) according to this embodiment. In other words, without the application of the field reproduction process, regardless of the classification of elemental work into "movement" and "operation", it was necessary to prepare training data corresponding to each work in order to predict the total value of the work duration of all work in work history H11 of the shipping process performed within the shipping process, and the preparation of training data was not easy. Furthermore, there was a problem that the prediction accuracy of the prediction model itself, which was generated after complicated preparation, was difficult to improve because some work histories in the shipping process were less likely to vary in duration depending on the worker, while others were more likely to vary. The same was true for work history H12 of the ○ process.

[0066] However, according to the field reproduction process of this embodiment, when the work history H21 of the shipping process in the work history H2 is targeted, the work history H21 provides work history H211 (i.e., the start date and time and completion date and time of each elemental task that constitutes the work) for each subdivided task of the shipping process (e.g., outbound shipping, individual packaging, packing, etc.). For example, "work history H2111 for moving to the slip shelf", "work history H2112 for obtaining the slip", etc. are obtained. Therefore, by breaking it down into elemental tasks performed by the worker, it is possible to generate estimation models MD2112, MD2212, etc. by focusing on elemental tasks that are prone to variations in work duration, thereby reducing variations in work duration and making it easier to make highly accurate predictions. The same applies to the work history H22 of the ○ process.

[0067] For example, as shown in Figure 12, consider a scenario where the position of workbench W224 is changed due to a change in the warehouse layout WH. Even in this case, it is assumed that the time required for the elemental task of moving to workbench W224 by the worker will not change significantly, and that the time required for the elemental tasks of the operation performed at workbench W224 will not change significantly either. Therefore, even if the position of workbench W224 is changed, it is assumed that the prediction accuracy of the inference model generated for each elemental task of "operation" by the on-site reproduction processing by the SIM processing device 40 will not decrease. In other words, even if a layout change occurs, it becomes possible to achieve a robust simulation of the time required for work in warehouse operations.

[0068] Furthermore, as shown in Figure 13, for example, suppose the elemental tasks "move to the slip shelf" and "receive slip" of a task (e.g., outbound shipment) become unnecessary. This is because, for example, the slips are no longer on paper but are always displayed on a computer device such as the operation terminal 10. Even in this case, it is considered that the elemental task "move to the slip shelf" is an elemental task of "move," and even if an inference model for "receive slip" has already been generated, it can be discarded. Therefore, even if there is a change in elemental tasks, such as the deletion of some elemental tasks of a task (e.g., outbound shipment), it is considered that the prediction accuracy of the inference model generated for each of the other elemental tasks constituting the same task will not decrease due to the on-site reproduction processing by the SIM processing device 40.

[0069] (Summary of this disclosure) The above description of embodiments discloses the technical concepts corresponding to the following items.

[0070] (Item 1) The method for reproducing the work related to this disclosure is: The system acquires work instruction information that directs the shipment of goods from the warehouse and work performance information based on the said instructions. The multiple elemental tasks that constitute the work performed based on the aforementioned instructions are classified into a first elemental task in which the time required by the worker is unlikely to vary (for example, the "movement" elemental task) and a second elemental task in which the time required by the worker may vary (for example, the "operation" elemental task), Based on the aforementioned work performance information, adjust at least one of the start date and completion date and time of the second element work. Using the start date and completion date and time of the first elemental work based on the work performance information and the adjustment result of at least one of the start date and completion date and time of the second elemental work, elemental work history information is generated that reproduces the work performance of each of the multiple elemental work. Method for reproducing the work. This work reproduction method allows for high-granularity work reproduction, which contributes to improving the accuracy of work time predictions at the work site. This is achieved by classifying each element of work, which is broken down (subdivided) into multiple elemental tasks, into those that are prone to variation in work time and those that are not, and then focusing on the elements that are prone to variation and adjusting their work time according to actual work performance.

[0071] (Item 2) In the method for reproducing the work described in item 1, Obtain elemental work information indicating multiple elemental work tasks that constitute the aforementioned work, Based on the aforementioned element work information, the work is classified into the first element work and the second element work. As a result, according to the work reproduction method, the multiple component tasks that make up the work can be appropriately classified into first component tasks and second component tasks.

[0072] (Item 3) In the method for reproducing the work described in item 1, Referencing a first table (table TB6) that associates the standard work time, which is the average value of the work time required for each of the aforementioned elemental tasks, with whether or not there is any variation in the work time required, adjust at least one of the start date and time (work start date and time) and the completion date and time (work completion date and time) of the second elemental task. As a result, according to the work reproduction method, the start date and completion date and time of the second elemental task in the on-site reproduction process can be appropriately adjusted, taking into account the standard work time for each elemental task and whether or not it varies.

[0073] (Item 4) In the work reproduction method described in any one of items 1 to 3, Referencing a second table (table TB7) that associates a coefficient for multiplying the work duration of the first elemental work for each worker, the start date and time (work start date and time) and completion date and time (work completion date and time) of the first elemental work are derived based on the work performance information. As a result, according to the work reproduction method, the start date and time and completion date and time of the first element work can be appropriately derived by treating the worker's movement speed as a coefficient representing the ratio to the standard movement speed.

[0074] (Item 5) In the work reproduction method described in any one of items 1 to 4, Multiple learning data sets are prepared, each having the start date and completion date and time of the second elemental work based on the elemental work history information. The system is instructed to run a machine learning program for an inference model that uses multiple training data sets to predict the start date and completion date and time of the second elemental task. This allows for the construction of an estimation model that accurately predicts the time required to complete each second-element task, which may have variations in standard work time, according to the work reproduction method. As a result, it becomes possible to make highly accurate predictions for warehouse operations as a whole.

[0075] (Item 6) In the work reproduction method described in any one of items 1 to 5, If the work performed based on the above instructions consists of multiple sub-works, the multiple elemental work constituting the sub-works is classified into a first elemental work and a second elemental work for each sub-work. As a result, according to the work reproduction method, even if a task consists of multiple hierarchical levels (e.g., major category, medium category, minor category), it can be similarly broken down into the smallest unit of elemental work, and the time required for each elemental work can be adjusted.

[0076] (Item 7) The work reproduction device related to this disclosure is It is equipped with a processor (SIM processor 42) and memory (41), The aforementioned processor, in cooperation with the memory, The system acquires work instruction information that directs the shipment of goods from the warehouse and work performance information based on the said instructions. The multiple elemental tasks that constitute the work performed based on the aforementioned instructions are classified into a first elemental task in which the time required by the worker is unlikely to vary (for example, the "movement" elemental task) and a second elemental task in which the time required by the worker may vary (for example, the "operation" elemental task), Based on the aforementioned work performance information, adjust at least one of the start date and completion date and time of the second element work. Using the start date and completion date and time of the first elemental work based on the work performance information and the adjustment result of at least one of the start date and completion date and time of the second elemental work, elemental work history information is generated that reproduces the work performance of each of the multiple elemental work. Work reproducing device. As a result, the work reproduction device, when a task is broken down (subdivided) into multiple elemental tasks, classifies each elemental task into those that are prone to variation in work time and those that are not, and then adjusts the work time of the elemental tasks that are prone to variation to match actual work performance. This enables high-granularity work reproduction that contributes to improving the accuracy of predicting work time at the work site.

[0077] (Item 8) The program related to this disclosure is In a computer-based work reproduction device, A process for acquiring work instruction information that instructs the shipment of goods in the warehouse and work performance information based on said instruction, A process of classifying multiple elemental tasks that constitute the work to be performed based on the above instructions into a first elemental task in which the time required for the work by the worker is unlikely to vary and a second elemental task in which the time required for the work by the worker may vary, A process to adjust at least one of the start date and completion date and time of the second element work based on the work performance information, A process to generate element work history information that reproduces the work performance of each of the multiple element work, using the start date and completion date and time of the first element work based on the work performance information and the adjustment result of at least one of the start date and completion date and time of the second element work, program. According to the program, when a task is broken down (subdivided) into multiple elemental tasks, each elemental task is classified into those that are prone to variation in work time and those that are not. Then, the program focuses on the elements that are prone to variation and adjusts their work time according to actual work performance. This enables highly granular work reproduction, which contributes to improving the accuracy of work time predictions at the work site.

[0078] While embodiments have been described above with reference to the attached drawings, this disclosure is not limited to such examples. It is clear to those skilled in the art that various modifications, alterations, substitutions, additions, deletions, and equivalents can be conceived within the scope of the claims, and these are also understood to fall within the technical scope of this disclosure. Furthermore, the components of the embodiments described above can be combined in any way without departing from the spirit of the invention. [Industrial applicability]

[0079] The technology disclosed herein is useful as a work reproduction method and work reproduction apparatus that realize highly granular work reproduction to improve the accuracy of predicting work time at the work site. [Explanation of Symbols]

[0080] 10 Operating terminal 11 memory 12 processors 13 Display Devices 20 Warehouse Management Systems 21 memory 22 processors 23 Inventory Information 24. Inbound and Outbound Information 30 Warehouse control system 31 memory 32 processors 33 Work Instruction Information 34. Work History Information 40 SIM Processing Units 41 memory 42 SIM processors 43 parameters 44 Element Work Information 45. Scene Reconstruction Department 46 Element Work History Information 100 Work Simulation Systems

Claims

1. The system acquires work instruction information that directs the shipment of goods from the warehouse and work performance information based on the said instructions. The multiple component tasks that constitute the work performed based on the above instructions are classified into a first component task in which the time required for the work by the worker is unlikely to vary, and a second component task in which the time required for the work by the worker may vary. Based on the aforementioned work performance information, adjust at least one of the start date and completion date and time of the second element work. Using the start date and completion date and time of the first elemental work based on the work performance information and the adjustment result of at least one of the start date and completion date and time of the second elemental work, elemental work history information is generated that reproduces the work performance of each of the multiple elemental work. Method for reproducing the work.

2. Obtain elemental work information indicating multiple elemental work tasks that constitute the aforementioned work, Based on the aforementioned element work information, the work is classified into the first element work and the second element work. The method for reproducing the work described in claim 1.

3. Referencing a first table that associates the standard work time, which is the average work time for each elemental work, with the presence or absence of variation in the work time, adjust at least one of the start date and time and completion date and time of the second elemental work. The method for reproducing the work described in claim 1.

4. Referencing a second table that associates a coefficient for multiplying the work time of the first elemental task for each worker, the start date and completion date and time of the first elemental task are derived based on the work performance information. The method for reproducing the work described in claim 1.

5. A plurality of learning data sets are prepared, each having the start date and completion date and time of the second elemental work based on the elemental work history information. The system is instructed to run a machine learning model for predicting the start date and completion date and time of the second elemental task using multiple training data sets. The method for reproducing the work described in claim 1.

6. If the work performed based on the above instructions consists of multiple sub-works, the multiple elemental work constituting the sub-work is classified into a first elemental work and a second elemental work for each sub-work. The method for reproducing the work described in claim 1.

7. Equipped with a processor and memory, The aforementioned processor, in cooperation with the memory, The system acquires work instruction information that directs the shipment of goods from the warehouse and work performance information based on the said instructions. The multiple component tasks that constitute the work performed based on the above instructions are classified into a first component task in which the time required for the work by the worker is unlikely to vary, and a second component task in which the time required for the work by the worker may vary. Based on the aforementioned work performance information, adjust at least one of the start date and completion date and time of the second element work. Using the start date and completion date and time of the first elemental work based on the work performance information and the adjustment result of at least one of the start date and completion date and time of the second elemental work, elemental work history information is generated that reproduces the work performance of each of the multiple elemental work. Work reproducing device.

8. In a computer-based work reproduction device, A process for acquiring work instruction information that instructs the shipment of goods in the warehouse and work performance information based on said instruction, A process of classifying multiple elemental tasks that constitute the work to be performed based on the above instructions into a first elemental task in which the time required for the work by the worker is unlikely to vary and a second elemental task in which the time required for the work by the worker may vary, Based on the aforementioned work performance information, a process is performed to adjust at least one of the start date and completion date and time of the second element work. A process to generate element work history information that reproduces the work performance of each of the multiple element work, using the start date and completion date and time of the first element work based on the work performance information and the adjustment result of at least one of the start date and completion date and time of the second element work, program.

Images