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

Abstract

To carry out a picking operation more efficiently.SOLUTION: An information processing device includes a processing part. The processing part determines, based on a plurality of shelf data including first identification information of a product, a processing order for a plurality of first order data including second identification information of the product to be picked from at least a part of a plurality of shelves, and one or more shelves from which to pick the product identified by second identification information for each of the plurality of first order data, and a hierarchical clustering, which repeats the process of merging a plurality of similar or matching first order data into clusters, is executed such that the number of clusters is equal to or greater than the number of work stations in which storage containers corresponding to at least some of the plurality of first order data are arranged.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] An embodiment of the present invention relates to an information processing device, an information processing method, a program, and an information processing system. [Background technology]

[0002] There is a known logistics system that uses a shelf-transport type warehouse, in which movable shelves (shelves that store products) are moved to a work station (picking station) by an AGV (Automated Guided Vehicle) or a worker, and the product picking work is performed at the work station.

[0003] Such shelf transport systems are often based on the premise that orders are added sequentially in real time, i.e., they often do not assume that a large number of orders, the processing order of which can be changed, will be given to the system at the same time. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2020-033154 A [Non-patent literature]

[0005] [Non-Patent Document 1] Nils Boysen et al., “Parts-to-picker based order processing in a rack-moving mobile robots environment”, European Journal of Operational Research, Research 262 (2017) 550-562 Summary of the Invention [Problem to be solved by the invention]

[0006] An object of the present invention is to provide an information processing device, an information processing method, a program, and an information processing system that can perform picking work more efficiently. [Means for solving the problem]

[0007] An information processing device according to an embodiment includes a processing unit, which determines, based on a plurality of shelf data including first identification information of a product, a processing order of a plurality of first order data including second identification information of a product to be picked from at least a portion of the plurality of shelves and one or more shelves from which to pick the product identified by the second identification information for each of the plurality of first order data, and executes hierarchical clustering in which a process of merging similar or matching first order data into clusters is repeated such that the number of clusters is equal to or greater than the number of work stations in which containers corresponding to at least a portion of the first order data of the plurality of first order data are arranged. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing an outline of a configuration of an information processing system according to an embodiment. [Diagram 2] FIG. 1 is a block diagram of an information processing apparatus according to an embodiment. [Diagram 3] FIG. 13 is a diagram showing an example of a generated index. [Figure 4] FIG. 13 is a diagram showing an example of a generated hierarchical cluster. [Diagram 5] FIG. 13 is a diagram showing an example of orders sorted by processing order. [Figure 6] FIG. 4 shows an example of clustering the orders in FIG. 3. [Figure 7] FIG. 4 shows an example of clustering the orders in FIG. 3. [Figure 8] FIG. 13 is a diagram showing an example of a rearranged order. [Figure 9] FIG. 13 is a diagram showing an example of a rearranged order. [Figure 10] 11 is a flowchart of an order determination process according to an embodiment. [Figure 11] Clustering flow chart. [Figure 12] Diagram showing an example with three work stations. [Figure 13] Diagram showing an example with three work stations. [Figure 14] 13 is a flowchart of a process for determining the number of orders. [Figure 15] FIG. 13 is a diagram showing an example of determining the processing order of clusters without using similarity. [Figure 16] FIG. 13 is a diagram showing an example of determining the processing order of clusters using similarity. [Figure 17] FIG. 1 is a hardware configuration diagram of an information processing apparatus according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of an information processing apparatus according to the present invention will be described in detail with reference to the accompanying drawings. The present embodiments can be applied to, for example, a logistics system using a warehouse with conveying shelves.

[0010] As described above, in the conventional shelf transport system, orders are selected as picking targets in the order in which they were generated.

[0011] On the other hand, for example, in a logistics system mainly targeting B2B (Business to Business), all orders to be processed within a certain period (for example, on a daily basis) may be given in advance. In such a case, it is possible to change the processing order of multiple orders as long as it is before the shipping deadline. For example, by appropriately rearranging the order processing order in advance and determining in advance the shelf to be assigned to each order, it is possible to improve the rate at which products assigned to multiple orders can be picked from one shelf (simultaneous picking rate), thereby making it possible to improve the efficiency of shelf transportation work and picking work. Conventionally, no consideration has been given to a function that rearranges the processing order of a large number of orders in advance and determines the shelf to be used for each order, with the aim of improving the work efficiency of the system as a whole.

[0012] Therefore, in this embodiment, when multiple order data that is information on unprocessed orders are given, multiple shelf data related to multiple shelves each storing one or more types of products are referenced, and the processing order for the multiple orders and the shelf to be used for each order are determined so as to improve the simultaneous picking rate. Since there is a one-to-one correspondence between order data and orders, determining the processing order for orders is equivalent to determining the processing order for order data. Similarly, processing on orders can be rephrased as processing on order data.

[0013] The shelf data includes a shelf ID, which is information for identifying a shelf, and identification information (first identification information) of one or more types of products currently stored on each shelf as inventory. The shelf data includes, for example, identification information indicating the type of each product constituting a set of products (product set) stored on the shelf.

[0014] The order data includes an order ID that identifies an order, and identification information (second identification information) of one or more types of products to be picked from at least a part of the shelves. The order data indicates, for example, a unit of a shipping instruction for each product to be packed in the same container for the same destination.

[0015] 1 is a diagram showing an outline of the configuration of an information processing system 10 (an example of a shelf transport type system) according to the present embodiment. As shown in FIG. 1, the information processing system 10 includes an information processing device 100, a transport device 200, a movable shelf 30, a work station 11, a plurality of containers 12, a work shelf 13, a display 14, and a network 300.

[0016] The work station 11 represents a work location where picking is performed by a worker 21. Although only one work station 11 is shown in FIG. 1, the information processing system 10 includes multiple work stations 11 .

[0017] The shelf 13 can accommodate a plurality of storage containers 12. The plurality of storage containers 12 correspond to, for example, a plurality of orders. The shelf 13 accommodates storage containers 12 corresponding to at least some of the plurality of order data. The display 14 is a display device for displaying information such as work instructions output from the information processing device 100.

[0018] The transport device 200 is a device for moving (transporting) the shelf 30 to the work station 11, and is, for example, an AGV. In this manner, the shelf 30 is movable to the work station 11. Although only one shelf 30 is shown in FIG. 1, in the information processing system 10, a plurality of shelves 30 are prepared, and a shelf 30 selected according to the determined order processing order is moved to the work station 11. When the shelf is moved by the worker 21, the transport device 200 does not need to be provided. The shelf 30 has, for example, a plurality of partitions, and can store a plurality of types of products.

[0019] The network 300 is a network that connects the information processing device 100, the conveying device 200, and the display 14. The network 300 may be any type of network, such as the Internet or a local area network (LAN). The network 300 may be any of a wireless network, a wired network, and a mixed wireless and wired network.

[0020] As shown in Fig. 1, a plurality of storage containers 12 for work corresponding to a plurality of orders are placed on a shelf 13, and an operator 21 can pick the plurality of orders in parallel. Note that picking may be performed by a picking robot or the like instead of the operator 21. Picking is completed for each storage container 12 when all products to be packed have been placed inside. Completed orders (storage containers) are treated as completed and are sequentially removed from the work station 11, and storage containers 12 corresponding to the next order are inserted.

[0021] Fig. 2 is a block diagram showing an example of the configuration of the information processing device 100 according to this embodiment. As shown in Fig. 1, the information processing device 100 includes a reception unit 101, a priority calculation unit 102, a determination unit 103, a distance calculation unit 104, an output control unit 105, an order data storage unit 121, a shelf data storage unit 122, a cluster data storage unit 123, and a station data storage unit 124.

[0022] The reception unit 101 receives input of various data used in the information processing device 100. For example, the reception unit 101 receives a plurality of order data (first order data), a plurality of shelf data, and work station data to be processed. The order data, shelf data, and work station data may be generated by any method, and may be generated, for example, by an external system such as a system that receives orders and a system that manages inventory of products. In addition, the method of inputting each piece of data may be any method, and for example, a method of receiving the data from an external system via the network 300 may be used.

[0023] The order data includes at least an order ID and identification information of the products included in the order. The order ID is expressed, for example, as order O1, order O2, order O3, etc. The identification information of the products is expressed, for example, as product A, product B, product C, etc. The information included in the order data is not limited to this. For example, the order data may include the number and amount of each product.

[0024] The shelf data includes at least a shelf ID and identification information of the products stored on the shelf. The shelf ID is expressed, for example, as shelf R1, shelf R2, shelf R3, etc. The information included in the shelf data is not limited to this. For example, the shelf data may include the number of each product and storage location information of the products, such as which partition on which side of the shelf they are stored in.

[0025] The work station data includes at least a work station ID and the number of storage containers at each of the multiple work stations. The number of storage containers corresponds to the number of orders that can be picked in parallel. The work station ID is information that identifies each of the multiple work stations 11. The work station data may also include information on assigned orders that are scheduled to be processed at each of the multiple work stations.

[0026] The reception unit 101 may receive data other than the order data, shelf data, and work station data, for example, product data including detailed information about each product (size, packaging style, etc.), as supplementary input data.

[0027] The priority calculation unit 102 calculates a priority for each of multiple shelves. The priority is used when the determination unit 103 determines a shelf to allocate to each order. The priority is calculated, for example, so that the priority is larger for a shelf where picking work can be performed more efficiently. For example, the priority calculation unit 102 may calculate the priority by the following method. Create a list (unallocated product list) of product identification information included in the shelf data that is included in any of multiple order data, i.e., products that have been requested in an order but have not been allocated (unallocated products). For unallocated products, calculate the priority (product priority) for each product. The priority for each product is, for example, the number of orders that include the product, i.e., that request the product (number of allocated orders). For each shelf, the total value of the product priorities included in the unallocated product list is calculated as the priority of that shelf (shelf priority).

[0028] Based on the calculated priority of each shelf, the determination unit 103 determines, for each of multiple order data, one or more shelves from which to pick the product from among the shelves that store products whose identification information matches the identification information of the product included in the order data.

[0029] For example, the determination unit 103 may assume that all orders can be processed in parallel (the storage containers 12 corresponding to all orders can be picked in parallel), and may determine the shelf to be used (allocated) for each order and the order ... shelf simultaneous picking rate highest simultaneous picking rate, i.e., the shelf with the highest priority calculated by the priority calculation unit 102, the determination unit 103 may assume that all orders can be processed in parallel (the storage containers 12 corresponding to all orders can be picked in parallel), and may determine the shelf to be used (allocated) for each order and the order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order order shelf simultaneous picking rate highest simultaneous picking rate, i.e., the shelf with the highest priority calculated by the priority calculation unit 102, the determination unit 103 may assume that all orders can be processed in parallel (the storage containers 12 corresponding to all orders can be picked in parallel), and the determination unit 103 may assume that all orders can be processed in parallel (the storage containers 12 corresponding to all orders can be picked in parallel), and the determination unit 103 may assume that all orders can be processed in parallel.

[0030] Furthermore, the determination unit 103 generates an index indicating the shelf determined as the shelf from which the product is to be picked for each order data. The index is, for example, information including the shelf IDs of one or more shelves from which the product is to be picked. A method of generating the index will be described in detail later.

[0031] The distance calculation unit 104 calculates the distance between the multiple indexes generated for each of the multiple order data. The method of calculating the distance will be described in detail later.

[0032] Furthermore, the determination unit 103 determines the order data to be allocated to each of the work stations 11 and the processing sequence of the allocated order data, so as to improve the rate at which products allocated to the order data are picked from one shelf (for example, the rate at which products are picked simultaneously from one shelf: simultaneous picking rate) based on the shelf data and work station data. "Simultaneous" does not mean that the times are exactly the same, This means that orders can be picked from the same shelf without having to calculate the distance. The determination unit 103 determines the processing order of the multiple order data such that the smaller the calculated distance, the closer the order. For example, the determination unit 103 executes hierarchical (agglomerative) clustering that generates clusters represented by a hierarchical structure by repeating a process of merging orders corresponding to an index with a small distance into a cluster. The determination unit 103 then determines the processing order of the orders in each of the multiple work stations 11 such that the orders included in the same cluster are arranged in a similar order.

[0033] Hierarchical clustering finds a pair of two clusters with the smallest distance between the indexes assigned to the clusters, and repeats the process of merging them into one cluster while controlling the size of the clusters to be generated so that the number of clusters generated is equal to or greater than the number of work stations 11. This makes it possible to cluster multiple order data so that multiple orders with corresponding indexes close to each other are included in the same cluster.

[0034] The determination unit 103 stores a binary tree in which the clusters (or orders) before merging are child nodes (child clusters) and the clusters after merging are parent nodes (parent clusters) in the cluster data storage unit 123 as a clustering history. The determination unit 103 also stores a hierarchical cluster representing the current clustering result in the cluster data storage unit 123. When a clustering termination condition is satisfied, a hierarchical cluster representing the final processing result is stored in the cluster data storage unit 123. The determination unit 103 recursively expands the binary tree so that child clusters belonging to the same parent cluster are adjacent, thereby determining the order processing order so that leaves (corresponding to order data) of the binary trees belonging to the same parent cluster are arranged in order of proximity.

[0035] The output control unit 105 controls the output of various information processed by the information processing device 100. For example, the output control unit 105 outputs output information including a set of order data to be assigned to each of the multiple work stations 11, information indicating the order processing sequence (order sequence information), information indicating the shelf to be used (allocated) for each order, and information indicating the order in which the shelves are to be called up for each order (shelf sequence information).

[0036] At least a portion of each of the above units (reception unit 101, priority calculation unit 102, decision unit 103, distance calculation unit 104, and output control unit 105) may be realized by one or more processing units. Each of the above units is realized, for example, by one or more processors. For example, each of the above units may be realized by having a processor such as a CPU (Central Processing Unit) execute a program, that is, by software. Each of the above units may be realized by a processor such as a dedicated IC (Integrated Circuit), that is, by hardware. Each of the above units may be realized by using a combination of software and hardware. When multiple processors are used, each processor may realize one of the units, or two or more of the units.

[0037] The order data storage unit 121 stores order data received by the reception unit 101. The shelf data storage unit 122 stores shelf data received by the reception unit 101. The cluster data storage unit 123 stores data (indexes, binary trees as history, clusters with hierarchical structures, etc.) generated by hierarchical clustering by the determination unit 103. The station data storage unit 124 stores work station data.

[0038] Each memory unit (order data memory unit 121, shelf data memory unit 122, cluster data memory unit 123, station data memory unit 124) can be configured using any commonly used storage medium such as a flash memory, a memory card, a RAM (Random Access Memory), a HDD (Hard Disk Drive), and an optical disc.

[0039] Each storage unit may be realized as a physically different storage medium, or as different storage areas of the same physically same storage medium.Furthermore, each storage unit may be realized by a plurality of physically different storage media.

[0040] Next, a method of generating an index will be described in detail. The determination unit 103 generates an index indicating a shelf determined as a shelf from which to pick up an item for each order data. FIG. 3 is a diagram showing an example of an index to be generated. In FIG. 3, an example of an index generated for an order of an order ID is shown next to each order ID. The index may include information indicating the order in which the shelves are called up. For example, the index may be generated so that the shelf IDs are arranged from left to right according to the call order. An index may be generated that associates shelf IDs with information indicating the call order.

[0041] Next, an example of hierarchical clustering using indexes will be described. Fig. 4 is a diagram showing an example of hierarchical clusters generated by hierarchical clustering when there is one target work station.

[0042] First, the distance calculation unit 104 calculates the distance between the generated indexes. For example, the distance calculation unit 104 calculates the total number of shelves (shelf IDs) that do not match between two indexes as the distance. The distance is not limited to this, and may be calculated by the following method, for example, and the calculation method is not limited. The distance is calculated by multiplying the total number of matching shelves by a negative coefficient. The distance is calculated by multiplying the total number of mismatched shelves and the total number of matched shelves by a coefficient. If a weight is assigned to each shelf in the index, the sum of the weights (which may be weights multiplied by a negative coefficient) for each matching shelf may be used as the distance. For example, if the weight of shelf R5 included in the index of order O1 in Fig. 3 is 2 and the weight of shelf R2 is 1, the distance calculation unit 104 calculates the distance as -2 if only shelf R5 matches, -1 if only shelf R2 matches, and -3 if both shelf R5 and shelf R2 match.

[0043] Next, the determination unit 103 repeats the process of merging orders, clusters, or orders and clusters with indexes that have small distances into one cluster, to generate clusters with a hierarchical structure. In Fig. 3, for example, the order indexes of orders O2 and O5 match in that they only include R5. When using a distance that produces a smaller value for an index that only includes matching shelf IDs, the determination unit 103 merges orders O2 and O5 into one cluster.

[0044] Cluster C1 in Fig. 4 shows the cluster merged in this way. Note that C1 to C9 represent information for identifying each cluster. The determination unit 103 stores a binary tree in the cluster data storage unit 123, in which the two indexes before the merge are child nodes and the cluster after the merge is the parent node. In the same manner, the determination unit 103 repeats the process until the end condition of the clustering is satisfied.

[0045] An example of a single integrated cluster is shown in Fig. 4. As shown in Fig. 4, the index for the cluster after the merge is, for example, the union of the shelf IDs assigned to each order belonging to the cluster.

[0046] Next, the determination unit 103 recursively expands the binary tree so that child clusters belonging to the same parent cluster are adjacent, thereby determining the order of processing the orders so that two orders corresponding to leaf nodes belonging to the same cluster are close to each other.

[0047] FIG. 5 is a diagram showing an example of orders rearranged in a determined processing order. FIG. 5 is an example of orders rearranged based on the clusters shown in FIG. 4. As shown in FIG. 4, the clusters include 10 leaf nodes corresponding to 10 orders. The determination unit 103 determines the processing order of the orders by, for example, recursively tracing the parent-child relationships of the binary tree from the last discovered cluster C9 (expanding the binary tree). In the example of FIG. 4, the determination unit 103 traces the parent-child relationships as follows, and rearranges the orders in the order of the leaves (orders) that are reached, thereby rearranging the orders in the order of FIG. 5. C9 → C8 → C3 → C1 → Order O2 → C1 → Order O5 → C1 → C3 → C2 → Order O9 → C2 → Order O6 → C2 → C3 → C8 → C7 → C5 → C4 → Order O1 → (omitted) → C8 → C9 → Order O8

[0048] In the case where there are multiple work stations 11, all orders are integrated into one cluster as in the example of Fig. 4, and the orders are rearranged according to the determined processing order, and then the order data is divided into data groups for each work station 11. In this method, a situation may arise in which a cluster is forcibly divided to be processed at a different work station 11 midway through. This situation may be one of the factors that reduces the simultaneous picking rate.

[0049] Therefore, in the case where there are multiple work stations 11, the determination unit 103 of this embodiment performs hierarchical clustering so that the number of clusters (cluster count) is equal to or greater than the number of target work stations 11 (station count). In other words, the determination unit 103 controls the size of each of the multiple clusters and does not combine them into one cluster.

[0050] For example, when merging orders into a cluster, if the total number of orders in the cluster after the merge exceeds the target size, the determination unit 103 performs a determination process to exclude the corresponding pairs of orders, clusters, or an order and a cluster from merging candidates.

[0051] The target size is determined based on the assumption that, for example, allocating a cluster larger than the target size to one work station 11 will disrupt the balance of the workload and increase the likelihood of forced division.

[0052] For example, if there are N work stations 11 and M total orders, the target size is determined as M / N so as to level the workload. In this case, whether the size of a cluster exceeds the target size is determined based on a judgment condition, for example, whether the number of orders included in the cluster exceeds the target size.

[0053] The judgment conditions used in the judgment process are not limited to the above, and may be, for example, the following judgment conditions: In addition, the judgment process may be performed so that a candidate is removed from the merging candidates when any of a plurality of judgment conditions is met. ·Whether the total number of items in the cluster after merging exceeds the target size ·Whether the total number of product types in the cluster after merging exceeds the target size

[0054] Furthermore, when there is an order in progress, the determination unit 103 may use information from the work station data to determine the target size so as to level out the sum of the workload of the order in progress and the workload of the order to be newly assigned to each work station 11. An order in progress is, for example, an order that has already been assigned to each work station 11 and cannot be changed, or an order that is currently being worked on. The method of determining the target size in this case will be described later.

[0055] 6 and 7 are diagrams showing an example of clustering the orders in Fig. 3 for two work stations 11. Since the number of orders in Fig. 3 is 10, the target size of the cluster is, for example, 10 / 2=5.

[0056] For example, the number of orders included in cluster C7 is 5, which is the target size. Therefore, no other clusters are merged into cluster C7. That is, when cluster C8 shown in Fig. 6 and cluster C7 shown in Fig. 7 are generated, hierarchical clustering ends.

[0057] 8 and 9 are diagrams showing examples of orders rearranged by the above method based on the clusters shown in FIGS. 6 and 7, respectively.

[0058] Assume that 10 orders rearranged based on the clusters merged into one as in the example of Figure 5 are divided into five orders, 1st to 5th, and five orders, 6th to 10th. In this case, orders O1 and O4, which use the same shelves (R2, R5), are divided and assigned to two work stations 11.

[0059] In contrast, in the example of two clusters generated by the procedure of this embodiment, orders O1 and O4 are both merged into cluster C7 (FIG. 7). Therefore, as shown in FIG. 9, orders O1 and O4 are assigned to the same work station 11. That is, the simultaneous picking rate can be improved.

[0060] Next, a description will be given of the order determination process performed by the information processing device 100 according to this embodiment. Fig. 10 is a flowchart showing an example of the order determination process according to this embodiment.

[0061] The reception unit 101 receives input of a plurality of order data, a plurality of shelf data, and work station data (step S101). The plurality of order data may be acquired by extracting unprocessed order data from the input order list.

[0062] Next, the determination unit 103 selects the shelf with the highest priority for all orders that can be allocated from the selected shelf among the unprocessed order data, and repeatedly adds the shelf ID of the selected shelf to the index, thereby assigning indexes to all orders (step S102).

[0063] Next, the determination unit 103 executes hierarchical clustering (step S103). In the hierarchical clustering, the determination unit 103 generates a binary tree in which the orders or clusters before the merge are child nodes and the clusters after the merge are parent nodes, and stores the generated binary tree in the cluster data storage unit 123. Details of the hierarchical clustering will be described later.

[0064] When the clustering is completed, the determination unit 103 determines which cluster to assign to each work station 11 and the order in which the work stations 11 will process the multiple clusters (step S104).

[0065] Since the size of all generated clusters does not necessarily match the target size, it is possible that the number of generated clusters is greater than the number of work stations 11. In this case, the determination unit 103 may determine clusters to be assigned so as to level the workload of each work station 11. In other words, the determination unit 103 determines multiple order data to be assigned to each of the multiple work stations 11 so that the total number of order data (second order data) being processed (in process) and the number of order data to be assigned among the multiple unallocated order data are leveled among the multiple work stations 11. Determine.

[0066] Any method of allocation for leveling may be used, for example, a method using an algorithm for combinatorial optimization problems called bin packing. For example, the determination unit 103 allocates multiple clusters in descending order of size to a work station in which the total size of one or more allocated clusters is smaller than that of other work stations.

[0067] For example, suppose that there are two work stations 11, 11A and 11B, and the total number of orders is 15. Also suppose that four clusters are generated: cluster C1 with two orders, cluster C2 with three orders, cluster C3 with four orders, and cluster C4 with six orders.

[0068] For example, the determination unit 103 rearranges the clusters in descending order of size and assigns the clusters, starting with the largest, to the work stations 11 with the smallest total sizes of the already assigned clusters. In the above example of four clusters, the determination unit 103 determines the allocation in the following order: cluster C4 for work station 11A, cluster C3 for work station 11B, cluster C2 for work station 11B, and cluster C1 for work station 11A.

[0069] When multiple clusters are assigned to one work station 11, the processing order of the multiple clusters may be determined in any manner. For example, a method may be used in which the processing order is determined in the order in which the clusters are assigned to the work station 11.

[0070] Returning to the explanation of Fig. 10, the determination unit 103 determines the order processing order so that two orders corresponding to leaf nodes belonging to the same cluster are close to each other by recursively expanding the binary tree so that child clusters belonging to the same parent cluster are adjacent (step S105), and generates an order list in which the order data is arranged in the determined processing order. When multiple clusters are assigned to one work station 11, the determination unit 103 combines the order lists determined for the multiple clusters according to the cluster processing order determined in step S104 so as not to disrupt the order order in the original order list.

[0071] The output control unit 105 outputs an order list including the order data whose order has been determined, and work instructions according to the shelf to be used for each order (step S106).

[0072] The output control unit 105 may take advantage of the fact that the simultaneous picking rate is calculated for each shelf during the shelf determination process to calculate at least one of the number of picking operations required for each shelf and the predicted total work time, and output this together with information on the shelf from which each item included in the order data will be picked.

[0073] For example, the simultaneous picking rate of a shelf is the number of types of products that can be picked simultaneously from that shelf for multiple orders. In this case, the number of picking operations can be calculated as the same value as the simultaneous picking rate. The time required for a picking operation can be calculated, for example, by multiplying the number of picking operations by a unit time. The unit time represents a predetermined time for one picking operation.

[0074] Next, the clustering in step S103 will be described in detail with reference to a flow chart of an example of the clustering.

[0075] The determining unit 103 rearranges the order data in index order (step S201). The determination unit 103 determines the target size from, for example, the number of stations and the order data (step S202). For example, the determination unit 103 determines the target size to be a value obtained by dividing the total number of order data by the number of stations.

[0076] The determining unit 103 finds pairs of orders, clusters, or an order and a cluster, in which the distance between the indexes is the smallest and equal to or less than a threshold (step S203). Note that the distance between the indexes is calculated by the distance calculating unit 104.

[0077] The determining unit 103 determines whether the size of the cluster after merging the found pair exceeds the target size (step S204). If the size exceeds the target size (step S204: Yes), the determining unit 103 excludes the pair from the merging candidates (step S205), and returns to step S203 to repeat the process.

[0078] If the target size is not exceeded (step S204: No), the determination unit 103 judges whether or not a mergeable pair exists (step S206). If a mergeable pair exists (step S206: Yes), the determination unit 103 merges the pair into one cluster (step S207). The determination unit 103 updates a binary tree in which the order or cluster before the merge is a child node and the cluster after the merge is a parent node, and stores the updated binary tree in the cluster data storage unit 123 (step S208), and then returns to step S203 and repeats the process.

[0079] If there is no pair that can be merged (step S206: No), the clustering ends.

[0080] In this manner, in this embodiment, by using multiple order data and multiple shelf data obtained in advance, the processing order of multiple order data, the shelf to be used for each order, and the calling order can be determined so that picking work can be carried out more efficiently.

[0081] In actual operation, there may be a situation where a group of orders (batches) is input in several separate times, or where the number of work stations 11 used during the processing of one batch is changed and replanned, etc. Therefore, even when such a situation occurs, it is necessary to maintain a high simultaneous picking rate.

[0082] As described above, when there are orders in process, it is possible to use information from the work station data so that the sum of the workload of the orders in process and the workload of the additional orders to be assigned to each work station 11 is leveled at each work station 11.

[0083] The processing in such a case will be described below with reference to Fig. 12 to Fig. 14. Fig. 12 and Fig. 13 show an example in which there are three work stations 11 (hereinafter referred to as work stations WS1, WS2, and WS3). The number of containers indicates the number of storage containers 12. Once an order has been spread into a storage container 12, the allocation cannot be changed in principle, since there is a possibility that some products may have been allocated.

[0084] 12 and 13, the black bars indicate the number of orders that have already been assigned to each work station 11 and cannot be changed (orders for which picking has not been completed), and the white bars indicate the number of orders to be newly assigned to work stations 11 and the processing order to be determined. The left side of the arrows shows an example in which it is assumed that the orders to be added are assigned only to work station WS1. The right side of the arrows shows a case in which the orders to be added are assigned so that the numbers of orders at multiple work stations 11 are as even as possible.

[0085] The determination unit 103 determines the number of orders to be assigned to each work station 11 so that the sum of the number of orders already assigned (black bars) and the number of additional orders to be distributed (white bars) is as equal as possible among the multiple work stations 11, as shown to the right of the arrows in Figures 12 and 13.

[0086] 14 is a flowchart showing an example of a process for determining the number of orders in this case. In the following, the k-th (k is an integer between 1 and the number of stations) work station 11 among the multiple work stations 11 may be referred to as work station k.

[0087] The determination unit 103 calculates the sum S of the number of in-process orders N(k) and the number of additional orders at the work station k (step S301). The determination unit 103 calculates the average number of orders M at each work station 11 by dividing the sum S by the number of stations (step S302).

[0088] The determination unit 103 determines whether or not there is a work station k that satisfies N(k)>M (step S303). If there is a work station k that satisfies N(k)>M (step S303: Yes), the determination unit 103 excludes the work station k from targets for new order allocation because there is no room for new order allocation (step S304). After that, the determination unit 103 returns to step S301 and repeats the process for the remaining work stations 11 to be allocated.

[0089] If there is no work station k that satisfies N(k)>M (step S303: No), the decision unit 103 calculates MN(k) orders as the number of orders J(k) to be newly assigned for each work station k (step S305).

[0090] The calculated number of orders J(k) can be used for at least two purposes. The first purpose is to use the maximum value of the multiple J(k) calculated for multiple work stations k as the target size for clustering.

[0091] The second purpose is to use it as reference data when determining which cluster to assign to each work station k. For example, the determination unit 103 selects a cluster to assign according to the number of orders J(k) of each work station k. The assignment method may be, for example, a method that uses an algorithm for combinatorial optimization problems called bin packing.

[0092] For example, suppose there are two work stations 11, work station WS1 and work station WS2, and the total number of orders is 15. Furthermore, suppose that four clusters have been generated, each with two orders: cluster C1, cluster C2, cluster C3, cluster C4, and cluster C5. Furthermore, suppose that work station WS1 has seven in-process orders remaining. In this case, the number of newly assigned orders J(k=WS1) is four, and the number of orders J(k=WS2) is 11.

[0093] The determination unit 103 rearranges the clusters in descending order of size, and assigns the clusters with the smallest order numbers J(k) to the work stations 11 in descending order of size. In the above example, the determination unit 103 determines the clusters to be assigned in the following order: cluster C4 to work station WS2, cluster 3 to work station WS2, cluster 2 to work station WS1, and cluster C1 to work station WS1 (or WS2).

[0094] If there are any in-process orders remaining, they are sorted with the in-process orders at work station 11. There is a high possibility that the simultaneous picking rate will be higher if a cluster with a high similarity (which uses similar shelves) is assigned to the work station 11. Therefore, the determination unit 103 may assign one or more clusters (first cluster) included in the multiple clusters to a work station 11 that is processing in-process order data that has a higher similarity to the multiple order data included in the cluster than the other work stations 11.

[0095] Furthermore, when determining the processing order of multiple clusters in each work station 11, if a cluster that is more similar to an order in progress is processed first, the order in progress and the added order are processed in parallel, and the simultaneous picking rate between the orders is more likely to be increased. Therefore, when allocating multiple clusters (first cluster) to one work station, the determination unit 103 may determine the processing order to be earlier for a cluster that has a higher similarity to the order data in progress.

[0096] The similarity may be calculated by any method, but may be calculated by the same method as the above-mentioned method for calculating the distance between indexes. For example, the determination unit 103 regards a group of in-process orders as a cluster, assigns an index to the cluster by the same method as above, and calculates the similarity between the cluster and the order based on the distance between the indexes.

[0097] An example will be described using Figures 15 and 16. Assume that three clusters C1, C2, and C3 are generated by clustering, there are two work stations 11, WS1 and WS2, and order groups 1501 and 1502 are orders in process at work stations WS1 and WS2, respectively. Note that in Figures 15 and 16, the letters A to K represent order IDs.

[0098] FIG. 15 is a diagram showing an example of determining the processing order of clusters when the similarity with in-process orders is not taken into consideration. In FIG. 15, for example, the largest cluster C2 is assigned to the work station WS1, and the other clusters are assigned to the work station WS2. The processing order of clusters at the work station WS2 is cluster C1, cluster C3. At the work station WS1, the in-process orders (H, I, K) included in the order group 1501 do not match the orders (A, E, F, G) included in the newly assigned cluster. Therefore, the simultaneous picking rate cannot be improved.

[0099] Fig. 16 is a diagram showing an example of determining the processing order of clusters when considering the similarity with in-process orders. In Fig. 16, the largest cluster C2 is assigned to the work station WS2 with a higher similarity, and clusters C1 and C3 are assigned to the work station WS1. Also, because cluster C3 has a higher similarity with in-process orders 1501 than cluster C1, the processing order is determined to be first.

[0100] Next, a hardware configuration of the information processing device according to the embodiment will be described with reference to Fig. 17. Fig. 17 is an explanatory diagram showing an example of a hardware configuration of the information processing device according to the embodiment.

[0101] The information processing device according to the embodiment includes a control device such as a CPU 51 and a ROM (Read Only Memory). The computer includes storage devices such as a memory (RAM) 52 and a RAM 53, a communication I / F 54 that connects to a network and performs communication, and a bus 61 that connects each unit.

[0102] The programs executed by the information processing device according to the embodiment are provided in advance in the ROM 52 or the like.

[0103] The program executed by the information processing device according to the embodiment may be in an installable format. Alternatively, the program may be provided as a computer program product by being recorded in an executable format on a computer-readable recording medium such as a CD-ROM (Compact Disk Read Only Memory), a flexible disk (FD), a CD-R (Compact Disk Recordable), or a DVD (Digital Versatile Disk).

[0104] Furthermore, the program executed by the information processing device according to the embodiment may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network. Also, the program executed by the information processing device according to the embodiment may be provided or distributed via a network such as the Internet.

[0105] The programs executed by the information processing device according to the embodiment can cause the computer to function as each unit of the information processing device described above. In this computer, the CPU 51 can read the programs from a computer-readable storage medium onto a main storage device and execute the programs.

[0106] A configuration example of the embodiment will be described below. (Configuration example 1) determining a processing order for a plurality of first order data items including second identification information of one or more types of products to be picked from at least a portion of the plurality of shelves, based on a plurality of shelf data items including first identification information of one or more types of products stored on each of the plurality of shelves, and one or more shelves from which to pick the products identified by the second identification information for each of the plurality of first order data items; performing hierarchical clustering, which repeats a process of merging a plurality of the first order data that are similar or coincident with each other into clusters, such that a number of clusters, which is the number of clusters obtained by the hierarchical clustering, is equal to or greater than a number of stations, which is the number of work stations in which containers corresponding to at least some of the first order data among the plurality of the first order data are disposed; A processing unit is provided. Information processing device. (Configuration example 2) The processing unit includes: Allocating the plurality of clusters in descending order of size to a work station having one or more allocated clusters each having a smaller total size than the other work stations; The information processing device according to configuration example 1. (Configuration example 3) The processing unit includes: determining a plurality of the first order data to be allocated to each of the plurality of the work stations such that the sum of the number of the second order data being processed and the number of the first order data to be allocated among the plurality of the first order data is equalized among the plurality of the work stations; The information processing device according to configuration example 1 or 2. (Configuration Example 4) The processing unit includes: assigning one or more first clusters included in the plurality of clusters to the work station currently processing the second order data having a higher similarity to the plurality of first order data included in the first cluster than to other work stations; The information processing device according to configuration example 3. (Configuration Example 5) The processing unit includes: When allocating a plurality of the first clusters to one of the work stations, a processing order of a first cluster having a higher similarity to the second order data is determined earlier among the plurality of the first clusters. The information processing device according to configuration example 4. (Configuration Example 6) The processing unit includes: calculating a higher priority for each of the plurality of shelves as the number of the first identification information items that match the second identification information items included in the plurality of first order data items increases; determining, for the first order data including the second identification information that matches the first identification information included in the shelves selected in descending order of priority, the selected shelves as one or more shelves from which the product identified by the second identification information is to be picked; 6. The information processing device according to any one of configuration examples 1 to 5. (Configuration Example 7) The processing unit further outputs information indicating at least one of a number of times of picking operations for each of the plurality of shelves, the number being calculated based on a ratio of picking products allocated to the first order data from one shelf, and a time period for the picking operations. The information processing device according to any one of configuration examples 1 to 6. (Configuration Example 8) the processing unit generates, for each of the plurality of first order data, an index indicating one or more shelves from which the product is to be picked out of shelves storing the product having the first identification information that matches the second identification information, based on the priority calculated for each of the plurality of shelves, and determines the processing order by using the generated index. The information processing device according to any one of configuration examples 1 to 7. (Configuration Example 9) The processing unit includes: Calculating distances between the plurality of indexes generated for each of the plurality of first order data; The processing order is determined so that the smaller the distance, the closer the order. The information processing device according to configuration example 8. (Configuration Example 10) The processing unit includes: determining the processing order by recursively expanding the clusters so that child clusters having a common parent cluster are adjacent to each other; The information processing device according to configuration example 9. (Configuration Example 11) The processing unit includes: outputting output information indicating the processing order and the one or more shelves determined for each of the plurality of first order data; The information processing device according to any one of configuration examples 1 to 10. (Configuration Example 12) A plurality of said shelves are movable to a plurality of said work stations. The information processing device according to any one of configuration examples 1 to 11. (Configuration Example 13) The processing unit includes: determining the processing order and one or more shelves from which to pick products identified by the second identification information for each of the plurality of first order data, based on the plurality of shelf data, so as to improve a ratio of picking products allocated to the plurality of first order data from one shelf; 13. The information processing device according to any one of configuration examples 1 to 12. (Configuration Example 14) The processing unit includes: determining the processing order and one or more shelves from which the product identified by the second identification information is to be picked; performing said hierarchical clustering; A determination unit, The information processing device according to configuration example 1. (Configuration Example 15) An information processing method executed by an information processing device, determining a processing order for a plurality of first order data items including second identification information of one or more types of products to be picked from at least a portion of the plurality of shelves, based on a plurality of shelf data items including first identification information of one or more types of products stored on each of the plurality of shelves, and one or more shelves from which to pick the products identified by the second identification information for each of the plurality of first order data items; performing hierarchical clustering, which repeats a process of merging a plurality of the first order data that are similar or coincident with each other into clusters, such that a number of clusters, which is the number of clusters obtained by the hierarchical clustering, is equal to or greater than a number of stations, which is the number of work stations in which containers corresponding to at least some of the first order data among the plurality of the first order data are disposed; Information processing methods. (Configuration Example 16) On the computer, determining a processing order of a plurality of first order data including second identification information of one or more types of products to be picked from at least a portion of the plurality of shelves based on a plurality of shelf data including first identification information of one or more types of products stored on each of the plurality of shelves, and one or more shelves from which to pick the products identified by the second identification information for each of the plurality of first order data; performing hierarchical clustering, which repeats a process of merging a plurality of similar or matching first order data into clusters, such that a number of clusters obtained by the hierarchical clustering is equal to or greater than a number of stations, which is the number of work stations in which containers corresponding to at least some of the first order data among the plurality of first order data are disposed; A program for executing the above. (Configuration Example 17) An information processing system including a conveying device, an information processing device, and a work station, The conveying device conveys a plurality of shelves housing products to the work station; The information processing device includes: determining a processing order for a plurality of first order data items including second identification information of one or more types of products to be picked from at least a portion of the plurality of shelves, based on a plurality of shelf data items including first identification information of one or more types of products stored on each of the plurality of shelves, and one or more shelves from which to pick the products identified by the second identification information for each of the plurality of first order data items; performing hierarchical clustering, which repeats a process of merging a plurality of the first order data that are similar or coincident with each other into clusters, such that a number of clusters, which is the number of clusters obtained by the hierarchical clustering, is equal to or greater than a number of stations, which is the number of work stations in which containers corresponding to at least some of the first order data among the plurality of the first order data are disposed; A processing unit is provided. Information processing system.

[0107] Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0108] 10. Information Processing Systems 11 Work Station 12 Containment Container 13 Shelves 14 Display 30 Shelves 100 Information processing device 101 Reception 102 Priority calculation unit 103 Decision Section 104 Distance calculation unit 105 Output control section 121 Order data storage unit 122 Shelf data storage unit 123 Cluster Data Storage Unit 124 Station data storage unit 200 Transport device 300 Network

Claims

1. determining a processing order for a plurality of first order data items including second identification information of one or more types of products to be picked from at least a portion of the plurality of shelves, based on a plurality of shelf data items including first identification information of one or more types of products stored on each of the plurality of shelves, and one or more shelves from which to pick the products identified by the second identification information for each of the plurality of first order data items; performing hierarchical clustering, which repeats a process of merging a plurality of the first order data that are similar or coincident with each other into clusters, such that a number of clusters, which is the number of clusters obtained by the hierarchical clustering, is equal to or greater than a number of stations, which is the number of work stations in which containers corresponding to at least some of the first order data among the plurality of the first order data are disposed; A processing unit is provided. Information processing device.

2. The processing unit includes: allocating the plurality of clusters in descending order of size to a work station having one or more allocated clusters each having a smaller total size than the other work stations; The information processing device according to claim 1 .

3. The processing unit includes: determining a plurality of the first order data to be allocated to each of the plurality of the work stations such that the sum of the number of the second order data being processed and the number of the first order data to be allocated among the plurality of the first order data is equalized among the plurality of the work stations; The information processing device according to claim 1 .

4. The processing unit includes: assigning one or more first clusters included in the plurality of clusters to the work station currently processing the second order data having a higher similarity to the plurality of first order data included in the first cluster than to other work stations; The information processing device according to claim 3 .

5. The processing unit includes: When a plurality of the first clusters are assigned to one of the work stations, a processing order of a first cluster having a higher similarity to the second order data is determined earlier among the plurality of the first clusters. The information processing device according to claim 4.

6. The processing unit includes: calculating a priority level for each of the plurality of shelves such that the number of the first identification information items that match the second identification information items included in the plurality of first order data items is greater; determining, for the first order data including the second identification information that matches the first identification information included in the shelves selected in descending order of priority, the selected shelves as one or more shelves from which the product identified by the second identification information is to be picked; The information processing device according to claim 1 .

7. The processing unit calculates a number of picking operations for each of the plurality of shelves based on a ratio of picking products to be allocated to the first order data from one shelf; and and a time for the picking operation. The information processing device according to claim 1 .

8. the processing unit generates, for each of the plurality of first order data, an index indicating one or more shelves from which the product is to be picked out of shelves storing the product having the first identification information that matches the second identification information, based on the priority calculated for each of the plurality of shelves, and determines the processing order by using the generated index. The information processing device according to claim 1 .

9. The processing unit includes: Calculating distances between the indexes generated for each of the first order data; The processing order is determined so that the smaller the distance, the closer the order. The information processing device according to claim 8.

10. The processing unit includes: determining the processing order by recursively expanding the clusters so that child clusters having a common parent cluster are adjacent to each other; The information processing device according to claim 9.

11. The processing unit includes: outputting output information indicating the processing order and the one or more shelves determined for each of the plurality of first order data; The information processing device according to claim 1 .

12. A plurality of said shelves are movable to a plurality of said work stations. The information processing device according to claim 1 .

13. The processing unit includes: determining the processing order and one or more shelves from which to pick products identified by the second identification information for each of the plurality of first order data, based on the plurality of shelf data, so as to improve a ratio of picking products allocated to the plurality of first order data from one shelf; The information processing device according to claim 1 .

14. The processing unit includes: determining the processing order and one or more shelves from which the product identified by the second identification information is to be picked; performing said hierarchical clustering; A determination unit is included. The information processing device according to claim 1 .

15. An information processing method executed by an information processing device, determining a processing order for a plurality of first order data items including second identification information of one or more types of products to be picked from at least a portion of the plurality of shelves, based on a plurality of shelf data items including first identification information of one or more types of products stored on each of the plurality of shelves, and one or more shelves from which to pick the products identified by the second identification information for each of the plurality of first order data items; A hierarchical clustering process is performed by repeating a process of merging a plurality of the first order data that are similar or coincident with each other into a cluster. The plurality of clusters obtained by the hierarchical clustering process is then subjected to the hierarchical clustering process. is executed so that the number of clusters, which is the number of the first order data, is equal to or greater than the number of stations, which is the number of work stations in which containers corresponding to at least some of the first order data are arranged. Information processing methods.

16. On the computer, determining a processing order of a plurality of first order data including second identification information of one or more types of products to be picked from at least a portion of the plurality of shelves, based on a plurality of shelf data including first identification information of one or more types of products stored on each of the plurality of shelves, and one or more shelves from which to pick the products identified by the second identification information for each of the plurality of first order data; executing hierarchical clustering, which repeats a process of merging a plurality of similar or matching first order data into clusters, such that a number of clusters obtained by the hierarchical clustering is equal to or greater than a number of stations, which is the number of work stations in which containers corresponding to at least some of the first order data among the plurality of first order data are disposed; A program for executing the above.

17. An information processing system including a conveying device, an information processing device, and a work station, The conveying device conveys a plurality of shelves housing products to the work station; The information processing device includes: determining a processing order for a plurality of first order data items including second identification information of one or more types of products to be picked from at least a portion of the plurality of shelves, based on a plurality of shelf data items including first identification information of one or more types of products stored on each of the plurality of shelves, and one or more shelves from which to pick the products identified by the second identification information for each of the plurality of first order data items; performing hierarchical clustering, which repeats a process of merging a plurality of the first order data that are similar or coincident with each other into clusters, such that a number of clusters, which is the number of clusters obtained by the hierarchical clustering, is equal to or greater than a number of stations, which is the number of work stations in which containers corresponding to at least some of the first order data among the plurality of the first order data are disposed; A processing unit is provided. Information processing system.

Images