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

Abstract

To provide an information processing apparatus for formulating an appropriate work plan, an information processing method, a program, and a system.SOLUTION: A host management apparatus 1 includes a communication interface 15 and a processor 11. The communication interface 15 transmits / receives data to / from an external device. The processor 11 acquires an order list from the external device via the communication interface 15, generates, based on the order list, a list of picking operations for picking articles, calculates, based on article data on an article and attribute data on picking means for picking the article, a probability distribution of processing time required for the picking means to process the picking operations included in the list, for each picking means, and allocates the picking operations included in the list to the picking means on the basis of the probability distribution.SELECTED DRAWING: Figure 3

Description

[Technical Field]

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

[0002] In recent years, systems have been provided that use automated guided vehicles to transport shelves that store items to multiple picking stations. At each picking station, a picking means such as an attendant or a robot picks an item from the shelf that has been transported by the automated guided vehicle.

[0003] Some of such systems predict the time (processing time) required for picking by the picking means and formulate an operation plan to optimize throughput.

[0004] However, since the processing time varies, the predicted processing time may deviate from the actual processing time. As a result, conventional systems sometimes fail to optimize throughput even when picking operations are carried out according to the work plan. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 2018-165952 Summary of the Invention [Problem to be solved by the invention]

[0006] In order to solve the above problems, an information processing device, an information processing method, a program, and a system are provided that are capable of formulating an appropriate work plan. [Means for solving the problem]

[0007] According to an embodiment, an information processing device includes an interface and a processor. The interface transmits and receives data to and from an external device. The processor acquires an order list from the external device via the interface, generates a list of picking operations for picking items based on the order list, calculates a probability distribution of processing times for each picking unit to process the picking operations included in the list based on item data related to the items and attribute data related to the picking means that pick the items, and assigns the picking operations included in the list to the picking units based on the probability distribution. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram conceptually illustrating an example of the configuration of a picking system according to an embodiment. [Figure 2] FIG. 2 is a block diagram illustrating an example of the configuration of a picking system according to the embodiment. [Figure 3] FIG. 3 is a block diagram illustrating an example of the configuration of the upper management device according to the embodiment. [Figure 4] FIG. 4 is a block diagram showing an example of the configuration of an AGV according to the embodiment. [Figure 5] FIG. 5 is a graph showing an example of a probability distribution according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of the operation of the upper management device according to the embodiment. [Figure 7] FIG. 7 is a flowchart illustrating an example of the operation of the upper management device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an embodiment will be described with reference to the drawings. A picking system according to an embodiment picks items from shelves in a logistics system or the like. The picking system transports shelves to a picking station using an automated guided vehicle (AGV). The picking system picks items from the shelves at the picking station. The picking system causes a picking means such as an attendant or a robot to pick the items from the shelves. For example, the picking system is used in a logistics center or a warehouse.

[0010] Fig. 1 is a diagram conceptually illustrating an example of the configuration of a picking system 100 according to an embodiment. Fig. 2 is a block diagram illustrating the example of the configuration of the picking system 100. 1 and 2, the picking system 100 includes a plurality of (here, three) picking stations P, a host management device 1, a network 2, an AGV 7, and an AGV shelf 8. The picking station P includes a tray 10, a work management unit 112, and a picking means 113. The network 2 is connected to the host management device 1, the AGV 7, and the work management unit 112.

[0011] The host management device 1 (information processing device) is called a warehouse management system (WMS) and can be realized by one or more computers. The host management device 1 stores item management information related to items stored in the warehouse. The item management information indicates the items stored on each AGV shelf 8 and the positions of the items on the AGV shelf 8.

[0012] The host management device 1 acquires an order list indicating the items to be picked from an external device. Based on the order list, the host management device 1 transports the AGV shelves 8 to each picking station P. The host management device 1 will be described in detail later.

[0013] The network 2 relays communications between the upper management device 1, the AGVs 7, and the work management unit 112. For example, the network 2 is a local area network (LAN). The AGVs 7 may be connected to the network 2 wirelessly.

[0014] The AGV 7 transports the AGV shelf 8 to the picking station P. The AGV 7 operates based on control signals from the upper management device 1 or the work management unit 112. For example, the AGV 7 travels toward a designated loading position and lifts up the AGV shelf 8 at the designated loading position. The AGV 7 travels toward a designated unloading position and unloads the AGV shelf 8 at the designated unloading position.

[0015] The AGV shelf 8 is arranged in the item storage area. The AGV shelf 8 is a shelf that stores items. For example, the AGV shelf 8 stands upright on four support pillars. The height below the shelf of the AGV shelf 8 (height from the floor to the bottom of the shelf) is higher than the height of the AGV 7. This allows the AGV 7 to slip under the shelf of the AGV shelf 8. After slipping under the shelf, the AGV 7 uses a pusher to lift the AGV shelf 8 so that the tips of the support pillars are a few centimeters above the floor, and then travels with the AGV shelf 8 lifted. In this way, the AGV 7 transports the AGV shelf 8.

[0016] Furthermore, shelf identification information that can be read by a fixed camera or a mobile camera may be attached to the AGV shelves 8. Item identification information that can be read by a fixed camera or a mobile camera may also be attached to the items. For example, the shelf identification information and item identification information are barcodes or two-dimensional codes. Note that the picking system 100 may be equipped with multiple readers that read the shelf identification information and item identification information, in addition to the fixed or mobile cameras.

[0017] The picking station P is located in the retrieval work area. The picking station P receives the AGV shelf 8 transported by the AGV 7. The picking station P picks an item from the received AGV shelf 8. The picking station P places the picked item into a tray 10.

[0018] The work management unit 112 manages the picking work at the picking station P. For example, the work management unit 112 includes a display unit, an operation unit, and the like. The work management unit 112 displays information indicating the items to be picked on the display unit in accordance with control from the upper management device 1. The work management unit 112 also accepts input of an operation indicating the items that have been picked from an attendant acting as the picking means 113. The work management unit 112 transmits information indicating the input operation to the upper management device 1.

[0019] For example, the work management unit 112 is a desktop PC, a notebook PC, a tablet PC, or the like.

[0020] The picking means 113 grasps an item from the AGV shelf 8 in accordance with instructions from the upper management device 1. The picking means 113 is a worker or a picking robot. As a worker, the picking means 113 visually checks the items displayed on the work management unit 112 and picks the items. The picking means 113 places the picked item into the tray 10. After placing the item into the tray 10, the picking means 113 inputs an operation indicating the item that has been picked into the work management unit 112.

[0021] Once the necessary items are placed on the tray 10, the tray 10 is ejected from the picking station P. The ejected tray 10 is sent to the next process in the retrieval work area, where the items placed on the tray 10 are packed, sorted, loaded, etc.

[0022] When the tray 10 is discharged from the picking station P, a new empty tray 10 is replenished.

[0023] Furthermore, when the picking means 113 is a picking robot, the picking station P does not need to include the work management unit 112. Furthermore, the picking station P may have both an attendant and a picking robot as the picking means 113. Here, the picking means 113 is assumed to be a worker.

[0024] Next, the upper level management device 1 will be described. FIG. 3 is a block diagram showing an example of the configuration of the upper management device 1 according to the embodiment. The upper management device 1 includes a processor 11, a ROM 12, a RAM 13, an auxiliary storage device 14, a communication interface 15, and the like.

[0025] The processor 11, the ROM 12, the RAM 13, the auxiliary storage device 14, and the communication interface 15 are connected to one another via a data bus or an interface.

[0026] The processor 11 (second processor) has the function of controlling the overall operation of the upper management device 1. The processor 11 may include an internal cache and various interfaces. The processor 11 realizes various processes by executing programs stored in advance in the internal memory, the ROM 12, or the auxiliary storage device 14.

[0027] For example, the processor 11 is a central processing unit (CPU). The processor 11 may be realized by hardware such as a large scale integration (LSI), an application specific integrated circuit (ASIC), or a field-programmable gate array (FPGA).

[0028] The ROM 12 is a non-transitory computer-readable storage medium that stores the above programs. The ROM 12 also stores data and various setting values ​​used by the processor 11 when performing various processes. The RAM 13 is a memory used for reading and writing data.

[0029] The RAM 13 is used as a so-called work area for storing data that is temporarily used when the processor 11 performs various processes.

[0030] The auxiliary storage device 14 is a non-transitory computer-readable storage medium and may store the above programs. The auxiliary storage device 14 also stores data used by the processor 11 when performing various processes, data generated by the processes of the processor 11, various setting values, etc.

[0031] The auxiliary storage device 14 (storage unit) pre-stores item management information indicating items stored on each AGV shelf 8 and the positions of the items on the AGV shelf 8. For example, the item management information stores a shelf code indicating the AGV shelf 8, an item code indicating the item stored on the AGV shelf 8, and the position of the item in association with each other.

[0032] The host management device 1 may be transferred with the above program stored in the ROM 12 or the auxiliary storage device 14, or may be transferred without the above program stored therein. In the latter case, the host management device 1 reads the above program stored in a removable storage medium such as an optical disk or semiconductor memory, and writes the read program to the auxiliary storage device 14. Alternatively, the host management device 1 downloads the above program via a network or the like, and writes the downloaded program to the auxiliary storage device 14.

[0033] The communication interface 15 (interface, second interface) is an interface for transmitting and receiving data to and from various devices. The communication interface 15 connects to the AGV 7, the work management unit 112, and the like. The communication interface 15 also acquires order lists and the like from external devices. For example, the communication interface 15 supports LAN connections and the like. The communication interface 15 may also be composed of an interface for transmitting and receiving data to and from external devices, an interface for transmitting and receiving data to and from the AGV 7, and an interface for transmitting and receiving data to and from the work management unit 112.

[0034] Next, we will explain about AGV7. FIG. 4 is a block diagram showing an example of the configuration of the AGV 7 according to the embodiment. The AGV 7 includes a processor 71, a ROM 72, a RAM 73, an auxiliary storage device 74, a communication interface 75, a drive unit 76, a sensor 77, a battery 78, a charging mechanism 79, and tires 70.

[0035] The processor 71 (first processor) has the function of controlling the overall operation of the AGV 7. The processor 71 may be equipped with an internal cache and various interfaces. The processor 71 realizes various processes by executing programs stored in advance in the internal memory, the ROM 72, or the auxiliary storage device 74.

[0036] For example, the processor 71 is a CPU. The processor 71 may be realized by hardware such as an LSI, an ASIC, or an FPGA.

[0037] The processor 71 performs processes such as calculations and controls required for operations such as acceleration, deceleration, stopping, direction changes, and loading and unloading from the AGV shelf 8. The processor 71 generates drive signals and outputs them to each section by executing a program stored in the ROM 72 or the like based on control signals from the upper management device 1 or the work management section 112 or the like.

[0038] For example, the host management device 1 or the work management unit 112 transmits a control signal to move the AGV 7 from its current position to a first position (the position of the target AGV shelf 8) and then from the first position to a second position (the position of the target picking station P). The host management device 1 or the work management unit 112 also transmits a control signal to move the AGV 7 from the second position to the first position. The processor 71 of the AGV 7 outputs a drive signal in response to the control signal transmitted from the host management device 1 or the work management unit 112. This causes the AGV 7 to move from its current position to the first position, from the first position to the second position, and from the second position to the first position. The processor 71 also outputs a drive signal in response to an instruction to load or unload the AGV shelf 8, which is included in the control signal transmitted from the host management device 1 or the work management unit 112. This causes the AGV 7 to lift the AGV shelf 8 using its pusher and lower the lifted AGV shelf 8.

[0039] The ROM 72 is a non-transitory computer-readable storage medium that stores the above-mentioned programs. The ROM 72 also stores data and various setting values ​​used by the processor 71 when performing various processes. The RAM 73 is a memory used for reading and writing data. The RAM 73 is used as a so-called work area for storing data that is temporarily used by the processor 71 when performing various processes.

[0040] The auxiliary storage device 74 is a non-transitory computer-readable storage medium and may store the above-mentioned programs. The auxiliary storage device 74 also stores data used by the processor 71 when performing various processes, data generated by the processes of the processor 71, various setting values, etc.

[0041] The communication interface 75 (first interface) is an interface for transmitting and receiving data to and from the higher level management device 1 or the work management unit 112 via a wireless LAN access point, etc. For example, the communication interface 75 supports wireless LAN connection.

[0042] The drive unit 76 is a motor or the like, and rotates or stops the motor based on a drive signal output from the processor 71. The power of the motor is transmitted to the tires 70 and then to the steering mechanism. The AGV 7 moves to the destination position using the power from the motor. The drive unit 76 functions as a transport mechanism that transports the AGV 7 and the AGV shelf 8.

[0043] Furthermore, with the AGV 7 submerged under the AGV shelf 8, the drive unit 76 rotates the motor (forward rotation) based on the drive signal output from the processor 71. The power from this motor raises the pusher, lifting the AGV shelf 8. Furthermore, after the AGV 7 reaches the destination position, the drive unit 76 rotates the motor (reverse rotation) based on the drive signal output from the processor 71. The power from this motor lowers the pusher, lowering the AGV shelf 8 to the floor.

[0044] The sensor 77 is a plurality of reflective sensors. Each reflective sensor is attached to the periphery of the AGV 7. Each reflective sensor emits a laser beam, detects the time from when the laser beam is emitted until the laser beam is reflected by an object and returns, detects the distance to the object based on the detected time, and notifies the processor 71 of a detection signal. The processor 71 outputs a control signal for controlling the travel of the AGV 7 based on the detection signal from the sensor 77. For example, the processor 71 outputs a control signal such as deceleration or stop to avoid collision with the object based on the detection signal from the sensor 77. Note that a camera may be provided in addition to the sensor 77, and the camera may capture images of the surrounding area and output the captured images to the processor 71. In this case, the processor 71 analyzes the captured images and outputs a control signal such as deceleration or stop to avoid collision with the object.

[0045] The battery 78 supplies the necessary power to the drive unit 76 etc. The charging mechanism 79 is a mechanism that connects the charging station and the battery 78, and the battery 78 is charged with power supplied from the charging station etc. via the charging mechanism 79.

[0046] Next, a description will be given of the functions realized by the upper management device 1. The functions realized by the processor 11 are realized by the processor 11 executing a program stored in the internal memory, the ROM 12, the auxiliary storage device 14, or the like.

[0047] First, the processor 11 has a function of obtaining an order list indicating the items to be picked. The processor 11 acquires an order list from an external device or the like via the communication interface 15. The processor 11 may also receive an order input via an operation unit or the like.

[0048] For example, the order list is made up of orders that associate items to be picked with delivery destinations of the items, etc. Here, the order list is made up of a plurality of orders. For example, the orders are order slips, etc. The processor 11 also has a function of generating a picking work list for picking work based on an order. A picking operation is a group of operations that can be picked simultaneously by one AGV shelf 8 call.

[0049] For example, when a certain order and another order indicate items to be stored on the same AGV shelf 8, the processor 11 combines the two orders into one picking job. Alternatively, the processor 11 may treat one order as one picking job. Alternatively, when an order indicates multiple items, the processor 11 may generate a picking job for each item in the order.

[0050] Here, it is assumed that the processor 11 has generated a picking work list indicating the work tasks a to c.

[0051] When the picking work list is generated, the processor 11 links the picking work with the AGV shelf 8 that stores the items for the picking work, based on the item management information and the like.

[0052] The processor 11 also has a function of calculating a probability distribution regarding the time (processing time) it takes for each picking means 113 to process each picking task.

[0053] The processor 11 calculates a probability distribution regarding the processing time it takes for the picking means 113 to process the picking operation based on the item data regarding the item in the picking operation and the attribute data regarding the picking means 113.

[0054] For example, the item data consists of an item ID that identifies the type of item, the number of items to be picked, the shape of the item, the material of the item, the weight of the item, a shelf ID that identifies the AGV shelf 8 on which the item is stored, the storage location of the item on the AGV shelf 8, etc.

[0055] Furthermore, when the picking means 113 is a worker, the attribute data may include, for example, a worker ID that identifies the worker, age, gender, height, exercise experience, years of employment, employment type, and the duration of work that has elapsed since the worker started work at the current time.

[0056] Furthermore, when the picking means 113 is a robot, the attribute data is data relating to specifications such as hand mechanism and handleable weight, for example.

[0057] The configuration of the item data and attribute data is not limited to a specific configuration.

[0058] For example, the auxiliary storage device 14 pre-stores item data of each item and attribute data of each picking means 113. The processor 11 acquires the item data related to the item in the picking operation and the attribute data of the picking means 113 from the auxiliary storage device 14.

[0059] The processor 11 may also acquire, via the communication interface 15, item data relating to the item to be picked and attribute data of the picking means 113 from the upper management device 1.

[0060] The processing time is the work time required for the picking means 113 to complete the picking work.

[0061] The probability distribution of the processing time is a function that indicates the probability density of the processing time occurring for a random variable. For example, the probability distribution may be a normal distribution or a gamma distribution.

[0062] FIG. 5 shows an example of a probability distribution calculated by the processor 11. In FIG. 5, the horizontal axis represents the random variable, and the vertical axis represents the probability density of the processing time. In the example shown in FIG. 5, the probability distribution has a shape that peaks at a predetermined value and spreads out to the left and right. The "score" will be described later.

[0063] For example, the auxiliary storage device 14 stores in advance a prediction model that outputs a probability distribution of processing times when product data and attribute data are input. For example, the prediction model outputs parameters (such as a mean value and a variance) that specify a probability distribution function.

[0064] For example, the prediction model is composed of a neural network (e.g., a restricted Boltzmann machine). The prediction model inputs product data and attribute data to the input layer of the neural network, performs calculations based on the weighting coefficients of the neural network, and outputs parameters of a probability distribution function from the output layer of the neural network.

[0065] For example, the weighting coefficients of the prediction model are obtained by learning based on work logs (teaching data) of past picking work. The teaching data is generated by formatting the work logs so that they can be input into the prediction model.

[0066] The training data includes item data and attribute data from past picking operations, and the actual time taken during the past picking operations.

[0067] The prediction model is a model that is trained to output a probability distribution of processing times in the training data in response to input of product data and attribute data in the training data.

[0068] The processor 11 inputs the product data and attribute data into the prediction model and calculates the probability distribution of the processing time.

[0069] As described above, the processor 11 calculates the probability distribution of the processing time it takes for each picking means 113 to process each picking task.

[0070] Here, the processor 11 calculates the probability distribution of the processing times of the workers A to C as the picking means 113. That is, the processor 11 calculates the probability distribution of the processing times for each of the workers A to C to perform each of the tasks a to c.

[0071] The processor 11 also has a function of allocating picking operations to the picking stations P based on the calculated probability distribution of processing times. That is, the processor 11 assigns picking work to each picking means 113.

[0072] For example, the processor 11 allocates picking tasks to each picking means 113 so as to minimize the overall processing time (throughput).

[0073] For example, the processor 11 allocates picking tasks to the picking means 113 using a discrete simulation.

[0074] Specifically, processor 11 generates a plurality of work scenarios that indicate the allocation of picking operations to picking means 113. For a given work scenario, processor 11 samples one or more processing times for each picking operation based on a probability distribution regarding the processing time for each picking operation. For example, processor 11 evaluates the processing time of the work scenario based on the longest processing time required for a picking operation among the sampled processing times. The processor 11 calculates the throughput of the work scenario based on the estimated processing time of each picking work.

[0075] The processor 11 similarly calculates the throughput for each work scenario. The processor 11 allocates picking operations to the picking stations P based on the operation scenario with the smallest throughput while satisfying various constraints, etc. For example, the constraints may be time constraints or equalization of processing times among the picking stations P.

[0076] The processor 11 may modify or add a work scenario depending on the throughput value or constraints.

[0077] FIG. 6 shows an example of the operation of the processor 11 in which the processor 11 assigns tasks a to c as picking tasks to the workers A to C as the picking means 113.

[0078] FIG. 6 shows the probability distribution of the processing time required for each of workers A to C to perform each of tasks a to c.

[0079] First, an example of allocation where allocation is not optimized (example (a)) will be described.

[0080] Example (a) shows an example in which tasks a to c are assigned to workers A to C in that order. That is, task a is assigned to worker A. Task b is assigned to worker B. Task c is assigned to worker C.

[0081] In example (a), processor 11 samples 7.5 from the probability distribution of worker A and task a as the processing time for worker A to process task a. Processor 11 samples 5.2 from the probability distribution of worker B and task b as the processing time for worker B to process task b. Processor 11 samples 7.8 from the probability distribution of worker C and task c as the processing time for worker C to process task c. Thus, in example (a), the throughput is 7.8 (slowest of 7.5, 5.2 and 7.8).

[0082] Next, an example of allocation in which allocation is optimized (example (b)) will be described.

[0083] In example (b), tasks a to c are assigned to workers A to C so as to minimize throughput. Task c is assigned to worker A. Task a is assigned to worker B. Task b is assigned to worker C.

[0084] In example (b), processor 11 samples 2.3 from the probability distribution of worker A and task c as the processing time for worker A to process task c. Processor 11 samples 2.6 from the probability distribution of worker B and task a as the processing time for worker B to process task a. Processor 11 samples 2.5 from the probability distribution of worker C and task b as the processing time for worker C to process task b. Thus, in example (b), the throughput is 2.6 (the slowest of 2.3, 2.6 and 2.5).

[0085] The processor 11 also has a function of causing the picking means 113 of each picking station P to process the picking work in accordance with the allocation of the picking work.

[0086] Here, a predetermined picking station P will be described. The processor 11 acquires the picking work assigned to the picking station P (the picking means of the picking station P). After acquiring the picking work, the processor 11 selects the AGV shelf 8 associated with the picking work. After selecting the AGV shelf 8, the processor 11 transports the selected AGV shelf 8 to the picking station P.

[0087] For example, the processor 11 sends a control signal through the communication interface 15 to one of the AGVs 7 to move to the selected AGV shelf 8 .

[0088] When the AGV 7 moves under the AGV shelf 8 in accordance with the control signal, the processor 11 sends a control signal to the AGV 7 via the communication interface 15 to instruct the AGV 7 to lift the AGV shelf 8 .

[0089] When the AGV 7 lifts the AGV shelf 8 in accordance with the control signal, the processor 11 sends a control signal to the AGV 7 via the communication interface 15 to move to the picking station P.

[0090] When the AGV 7 moves to the picking station P in accordance with the control signal, the processor 11 causes the picking means 113 to perform the picking work. That is, the processor 11 displays on the work management unit 112 the item indicated by the picking work.

[0091] Here, the picking means 113 picks the item displayed on the work management unit 112 from the AGV shelf 8. The picking means 113 puts the picked item into the tray 10 corresponding to the picking work.

[0092] When the picking of the item is completed, the processor 11 generates a work log related to the picking work. For example, the work log includes item data of the picked item, attribute data of the picking means 113, and processing time.

[0093] After generating the work log, processor 11 formats the work log. After formatting the work log, processor 11 causes picking station P to pick items in the same manner for the next picking operation. Processor 11 operates in the same manner for each picking operation.

[0094] The processor 11 also causes each picking station to pick items in parallel and simultaneously.

[0095] Furthermore, the processor 11 has a function of updating the prediction model when a predetermined condition (update condition) is satisfied.

[0096] When the picking operation is completed, processor 11 acquires the processing time (actual processing time) that it took for picking means 113 to actually perform the picking operation. After acquiring the actual processing time, processor 11 calculates a score indicating the deviation between the actual processing time and the probability distribution according to a predetermined algorithm.

[0097] As shown in FIG. 5, the processor 11 calculates the score according to the actual processing time. For example, when the actual processing time matches the average value of the probability distribution, the processor 11 calculates a score of "1.00." When the actual processing time is 5% of the lower (or upper) side of the probability distribution, the processor 11 calculates a score of "0.10."

[0098] After calculating the score, the processor 11 determines whether the score is equal to or less than a predetermined threshold. If it determines that the score is equal to or less than the predetermined threshold, the processor 11 updates the prediction model based on the shaped data.

[0099] The processor 11 may update the prediction model when the number of times the score is equal to or less than a predetermined threshold exceeds a predetermined threshold.

[0100] Furthermore, the processor 11 may update the prediction model when the score is equal to or less than a predetermined threshold for any of the picking means 113. Furthermore, the processor 11 may update the prediction model when the scores for a predetermined number or more of the picking means 113 exceed a predetermined threshold.

[0101] Furthermore, processor 11 may not need to update the prediction model if an abnormality occurs, such as an interrupted picking operation or an accident. For example, processor 11 determines whether an abnormality has occurred using a camera installed at picking station P. If an abnormality occurs, processor 11 does not update the prediction model or does not count up the number of times the score has fallen below a predetermined threshold. In this way, processor 11 prevents unnecessary updates to the prediction model by not using the processing time in the event of an abnormality for updating.

[0102] The processor 11 may also update the prediction model every time a predetermined time elapses. The processor 11 may also update the prediction model every time a predetermined number of picking operations are processed. The processor 11 may also update the prediction model in accordance with an operation by an operator.

[0103] Next, an example of the operation of the upper level management device 1 will be described. FIG. 7 is a flowchart for explaining an example of the operation of the upper management device 1.

[0104] First, the processor 11 of the upper management device 1 acquires an order list (S11). Upon acquiring the order list, the processor 11 generates a picking work list indicating picking work based on the order list (S12).

[0105] When the picking work list is generated, the processor 11 links the picking work with the AGV shelf 8 (S13). When the picking work is linked with the AGV shelf 8, the processor 11 updates the prediction model based on the work log and the like (S14).

[0106] After updating the prediction model, processor 11 calculates a probability distribution of the processing time it takes for each picking means 113 to process each picking task (S15). After calculating the probability distribution, processor 11 performs a simulation based on the probability distribution (S16). After performing the simulation, processor 11 assigns picking tasks to each picking means 113 based on the results of the simulation (S17).

[0107] After allocating the picking work to each picking means 113, the processor 11 calls the AGV shelf 8 to the picking station P in accordance with the allocation (S18). After calling the AGV shelf 8 to the picking station P, the processor 11 causes the picking means 113 to pick the item (S19).

[0108] When the picking means 113 picks an item, the processor 11 generates a work log (S20). After generating the work log, the processor 11 formats the work log (S21).

[0109] After formatting the work log, the processor 11 determines whether the update condition is satisfied (S22). If it is determined that the update condition is satisfied (YES in S22), the processor 11 returns to S14.

[0110] When processor 11 determines that the update condition is not satisfied (S22, NO), processor 11 determines whether there is an unprocessed picking operation (S23). When processor 11 determines that there is an unprocessed picking operation (S23, YES), processor 11 returns to S18.

[0111] When it is determined that there is no unprocessed picking operation (S23, NO), the processor 11 ends the operation.

[0112] The processor 11 may execute steps S18 to S22 for each picking station P in parallel.

[0113] The processor 11 may also calculate a probability distribution of the transport time for the AGV 7 to transport the AGV shelf 8 to the picking station P. For example, the auxiliary storage device 14 pre-stores a model that outputs a probability distribution of the transport time when AGV data related to the AGV 7 is input.

[0114] For example, the AGV data includes a device ID for identifying the AGV 7 (or the type of AGV 7), years of use, charge rate, status (standby, in use, returning, etc.), the position of the AGV 7, and the position of the AGV shelf 8 to be transported.

[0115] The processor 11 inputs the AGV data into the model and calculates the probability distribution of the transportation time. The processor 11 may allocate picking tasks to the picking means 113 further based on the probability distribution of the delivery times.

[0116] The processor 11 may also assign, to each AGV 7, an AGV shelf 8 to be transported by that AGV 7, based on the probability distribution of the transport time.

[0117] Furthermore, if the picking means 113 is a robot, the processor 11 may calculate a distribution of the picking success probability (the probability that the picking means 113 can place an item into the tray 10 without dropping it). The processor 11 may also allocate picking tasks to the picking means 113 based on the distribution of the success probability.

[0118] The auxiliary storage device 14 may also store a prediction model for each picking means 113. In this case, the processor 11 may input item data into the prediction model for a specific picking means 113 to calculate the probability distribution of the processing time of the specific picking means 113. The processor 11 may also learn the prediction model for the specific picking means 113 by using a prediction model for a picking means 113 similar to the specific picking means 113 as an initial model.

[0119] The predictive model may also be a generalized linear model.

[0120] In addition, the processor 11 may change the order of picking work at the picking station P depending on the progress of work at the picking station P, etc., in order to avoid interference with the calling of the AGV shelf 8 or waiting time at the picking station P.

[0121] Furthermore, the processor 11 may change the allocation of picking work that has not yet called up the AGV shelf 8 between the picking stations P.

[0122] The processor 11 may also execute a stochastic programming method to directly obtain an optimization solution for a system with uncertainty. In this case, the processor 11 may solve the problem by using the calculated probability distribution as the distribution of variables in the formulation of the optimization problem.

[0123] The picking system 100 may also be provided with a station for warehousing and perform warehousing work. In this case, the processor 11 may calculate a probability distribution regarding the processing ability of each worker for the item replenishment work, as in the retrieval work, and assign the warehousing work to a station based on the probability distribution. The picking system 100 may also be a system for loading items from trays or cardboard boxes onto the AGV shelf 8 as a warehousing work.

[0124] Processor 11 may also calculate a probability distribution regarding the number of future shipments of goods from data in which past shipment records are supplemented with information such as day of the week, seasonal events, statistics, etc. Processor 11 may probabilistically grasp changes in the number of goods in stock in the simulation system from the calculated probability distribution, and based on this, determine plans regarding the number of goods in stock in the warehouse and replenishment timing.

[0125] The functions of the upper management device 1 may be realized by a warehouse execution system (WES) or a warehouse control system (WCS).

[0126] The picking system configured as described above calculates a probability distribution of the processing time it takes for a picking means to perform a picking task.The picking system assigns picking tasks to picking means based on the probability distribution.As a result, the picking system can create a work plan that takes into account the variation in processing time.

[0127] Although several 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 embodied 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 within the scope and spirit of the invention, and are also included in the scope of the invention and its equivalents as defined in the claims. The inventions described in the claims of the present application as originally filed are as follows: [Appendix 1] an interface for transmitting and receiving data to and from an external device; obtaining an order list from the external device through the interface; generating a list of picking operations for picking items based on the order list; calculating, for each of the picking means, a probability distribution of a processing time required for the picking means to process the picking work included in the list based on item data related to the items and attribute data related to the picking means that picks the items; assigning the picking operations included in the list to the picking means based on the probability distribution; a processor; An information processing device comprising: [Appendix 2] The processor: calculating the processing time in which the picking operation will be completed with a predetermined probability based on the probability distribution; Allocating the picking work to the picking means based on the calculated processing time. 2. The information processing device according to claim 1. [Appendix 3] a storage unit that stores a model that outputs the probability distribution when the item data and the attribute data are input; the processor inputs the item data and the attribute data into the model to calculate the probability distribution; 3. The information processing device according to claim 1 or 2. [Appendix 4] the model is a model for causing the processor to function to perform an operation based on weighting coefficients of the neural network on the product data and the attribute data input to an input layer of the neural network, and to output the probability distribution from an output layer of the neural network, the weighting coefficients are obtained by learning using the product data, the attribute data, and the probability distribution as training data. 4. The information processing device according to claim 3. [Appendix 5] The processor updates the model when a predetermined update condition is satisfied. 5. The information processing device according to claim 3 or 4. [Appendix 6] the processor updates the model when the update condition based on the actual processing time taken by the picking means to actually process the picking work assigned to the picking means is satisfied. 6. The information processing device according to claim 5. [Appendix 7] The processor: calculating a score relating to a deviation between the probability distribution and the actual processing time; updating the model when the update condition based on the score is satisfied; 7. The information processing device according to claim 6. [Appendix 8] The item data is composed of at least one of an item ID that identifies the type of the item, the number of the items to be picked, the shape of the items, the material of the items, the weight of the items, a shelf ID that identifies the shelf on which the items are stored, or a storage position of the items on the shelf. 8. An information processing device according to any one of appendices 1 to 7. [Appendix 9] the picking means is a worker, The attribute data is composed of at least one of a worker ID for identifying the worker, age, sex, height, exercise experience, years of employment, employment type, or the duration of work that has elapsed since the worker started working at the current time. 9. An information processing device according to any one of appendices 1 to 8. [Appendix 10] The items are stored on shelves transported by automated guided vehicles. 10. An information processing device according to any one of appendices 1 to 9. [Appendix 11] 1. An information processing method executed by a processor, comprising: Get the order list, Generate a list of picking operations for picking items based on the order list; calculating, for each of the picking means, a probability distribution of a processing time required for the picking means to process the picking work included in the list based on item data related to the items and attribute data related to the picking means that picks the items; assigning the picking operations included in the list to the picking means based on the probability distribution; Information processing methods. [Appendix 12] A program executed by a processor, the processor, The ability to get an order list, A function for generating a list of picking operations for picking items based on the order list; a function of calculating, for each of the picking means, a probability distribution of a processing time for the picking means to process the picking work included in the list, based on item data related to the items and attribute data related to the picking means that picks the items; a function of allocating the picking operations included in the list to the picking means based on the probability distribution; A program to make this happen. [Appendix 13] A system including an information processing device and an automated guided vehicle, The automated guided vehicle is a first interface for transmitting and receiving data to and from the information processing device; a transport mechanism for transporting shelves for storing items; a first processor that uses the transport mechanism to transport the shelf to a picking station that includes a picking means that picks the item under control of the information processing device; Equipped with The information processing device includes: a second interface for transmitting and receiving data to and from an external device and the automated guided vehicle; acquiring an order list from the external device through the second interface; generating a list of picking operations for picking the items based on the order list; calculating, for each of the picking means, a probability distribution of a processing time required for the picking means to process the picking work included in the list based on item data related to the items and attribute data related to the picking means that picks the items; assigning the picking operations included in the list to the picking means based on the probability distribution; causing the automated guided vehicle to transport the shelf storing the item for the picking operation assigned to the picking means to the picking station equipped with the picking means through the second interface; a second processor; and Equipped with system. [Explanation of symbols]

[0128] 1...upper management device, 2...network, 7...AGV, 8...AGV shelf, 10...tray, 11...processor, 12...ROM, 13...RAM, 14...auxiliary storage device, 15...communication interface, 70...tire, 71...processor, 72...ROM, 73...RAM, 74...auxiliary storage device, 75...communication interface, 76...drive unit, 77...sensor, 78...battery, 79...charging mechanism, 100...picking system, 112...work management unit, 113...picking means.

Claims

1. an interface for transmitting and receiving data to and from an external device; a storage unit for storing a model that outputs a probability distribution; obtaining an order list from the external device through the interface; generating a list of picking operations for picking items based on the order list; calculating, for each of the picking means, the probability distribution of the processing time for the picking means to process the picking operation included in the list, based on inputting item data related to the items and attribute data related to the picking means that picks the items into the model; assigning the picking operations included in the list to the picking means based on the probability distribution; a processor; An information processing device comprising:

2. The processor: calculating the processing time in which the picking operation will be completed with a predetermined probability based on the probability distribution; Allocating the picking work to the picking means based on the calculated processing time. The information processing device according to claim 1 .

3. the model is a model for causing the processor to function to perform an operation based on weighting coefficients of the neural network on the product data and the attribute data input to an input layer of the neural network, and to output the probability distribution from an output layer of the neural network, the weighting coefficients are obtained by learning using the product data, the attribute data, and the probability distribution as training data. The information processing device according to claim 1 .

4. The processor updates the model when a predetermined update condition is satisfied. The information processing device according to claim 1 or 3.

5. the processor updates the model when the update condition based on the actual processing time taken by the picking means to actually process the picking work assigned to the picking means is satisfied. The information processing device according to claim 4 .

6. The processor: calculating a score relating to a deviation between the probability distribution and the actual processing time; updating the model when the update condition based on the score is satisfied; The information processing device according to claim 5 .

7. The item data is composed of at least one of an item ID that identifies the type of the item, the number of the items to be picked, the shape of the items, the material of the items, the weight of the items, a shelf ID that identifies the shelf on which the items are stored, or a storage position of the items on the shelf. The information processing device according to claim 1 .

8. the picking means is a worker, The attribute data is composed of at least one of a worker ID for identifying the worker, age, sex, height, exercise experience, years of employment, employment type, or the duration of work that has elapsed since the worker started working at the current time. The information processing device according to claim 1 .

9. The items are stored on shelves transported by automated guided vehicles. The information processing device according to any one of claims 1 to 8.

10. 1. An information processing method executed by a processor, comprising: Get the order list, Generate a list of picking operations for picking items based on the order list; calculating, for each of the picking means, a probability distribution of a processing time for the picking means to process the picking operation included in the list, based on inputting item data related to the items and attribute data related to a picking means that picks the items into a model that outputs a probability distribution; assigning the picking operations included in the list to the picking means based on the probability distribution; Information processing methods.

11. A program executed by a processor, the processor, The ability to get an order list, A function for generating a list of picking operations for picking items based on the order list; a function of calculating, for each picking means, a probability distribution of a processing time for the picking means to process the picking operation included in the list, based on inputting item data related to the items and attribute data related to the picking means that picks the items into a model that outputs a probability distribution; a function of allocating the picking operations included in the list to the picking means based on the probability distribution; A program to make this happen.

12. A system including an information processing device and an automated guided vehicle, The automated guided vehicle is a first interface for transmitting and receiving data to and from the information processing device; a transport mechanism for transporting shelves for storing items; a first processor that uses the transport mechanism to transport the shelf to a picking station that includes a picking means that picks the item under control of the information processing device; Equipped with The information processing device includes: a second interface for transmitting and receiving data to and from an external device and the automated guided vehicle; obtaining an order list from the external device through the second interface; generating a list of picking operations for picking the items based on the order list; calculating, for each of the picking means, a probability distribution of a processing time required for the picking means to process the picking work included in the list based on item data related to the items and attribute data related to the picking means that picks the items; assigning the picking operations included in the list to the picking means based on the probability distribution; causing the automated guided vehicle to transport the shelf storing the item for the picking operation assigned to the picking means to the picking station equipped with the picking means through the second interface; a second processor; and Equipped with system.

13. The information processing device a storage unit that stores a model that outputs the probability distribution when the item data and the attribute data are input; the processor inputs the item data and the attribute data into the model to calculate the probability distribution; The system of claim 12.

Images