Method for planning picking path of small and medium-sized flat warehouse under omnichannel mode

Abstract

The application relates to a picking path planning method for a small and medium-sized flat warehouse under a full-channel mode, which comprises the following steps: selecting a current picking order and a corresponding target picking object from a plurality of picking orders distributed to a plurality of picking objects, detecting a plurality of target picking channels in which a replenishment SKU corresponding to a picking SKU associated with the current picking order is stored in the storage location allocation information; determining the sequence of entering the plurality of target picking channels based on the picking waiting time required for the target picking object to enter the target picking channel for picking; generating a target picking path corresponding to the current picking order based on the sequence and the path strategy determined according to the picking order type; and sequentially planning the target picking paths corresponding to the plurality of picking orders to obtain a planning result, thereby solving the problems of serious occupation conflict of picking work, long picking time and low picking efficiency under the full-channel mode in the related art, and minimizing the total picking operation time and improving the picking operation efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent logistics and warehouse management, in particular to a picking path planning method for a small and medium-sized flat warehouse under a full-channel mode. BACKGROUND

[0002] Picking operation is that a picker walks along a picking channel and picks the required SKU from the picking location under the determined warehouse layout and the known location allocation scheme. Under the full-channel retail mode, the picking order includes online orders and offline orders. The online order has the characteristics of multiple varieties and small batches, and generally needs to access multiple discrete locations during picking. Since the picking quantity of each commodity is small, the operation time on a single location is relatively short. The offline order has the characteristics of few varieties and large batches, and only needs to access a small number of locations during picking. Since the batch quantity of commodities is large, the operation time on a single location is relatively long.

[0003] In the related art, in order to ensure the space utilization rate, the width of the picking channel is usually only allowed to pass through a single picker, and the crossing and overtaking of multiple pickers are generally completed in the intersection channel of the entrance and exit of the picking channel. When multiple pickers complete the picking tasks of online and offline picking orders in the warehouse at the same time, it is inevitable that more than one picker will enter the same picking channel. If they move towards each other, congestion will occur at the meeting point. Even if multiple pickers move in the same direction in the same picking channel, due to the different location access requirements of the picking order, the occupation time of each picker in the channel is not consistent. When the rear picker has completed the picking requirement in the channel and the front picker has not completed, the rear picker cannot overtake due to the limitation of the channel width, resulting in congestion. As can be seen, in the multi-picker full-channel flat warehouse where online and offline picking tasks are carried out simultaneously, congestion is prone to occur during picking. When the picking channel where the picking location of the picker is located is accessed by other pickers, the picker may be blocked by other pickers moving in the same direction or in the opposite direction, and therefore must stop and wait. The waiting caused by channel congestion is essentially a conflict of occupation of the same picking channel by different pickers at the same time.

[0004] At present, there is no effective solution to the problem of serious occupation conflict and long picking operation time and low picking efficiency of the picking operation under the full-channel mode in the related art. SUMMARY

[0005] The embodiments of the present application provide a picking path planning method for a small and medium-sized flat warehouse under a full-channel mode, to at least solve the problem of serious occupation conflict and long picking operation time and low picking efficiency of the picking operation under the full-channel mode in the related art.

[0006] The embodiment of the application provides a picking path planning method for a small and medium-sized flat warehouse under a full-channel mode, comprising: after receiving a picking request for picking a plurality of picking orders, obtaining previously planned storage location allocation information, wherein the picking request comprises a picking order type and a picking SKU of the picking order, the storage location allocation information is generated by using a genetic algorithm to plan storage locations for replenishment SKUs considering a goods outbound frequency parameter, a goods correlation parameter and a relocation cost of the replenishment SKUs, and selecting a current picking order and a corresponding target picking object from a plurality of the picking orders allocated to a plurality of picking objects, and detecting a plurality of target picking channels in the storage location allocation information, wherein the target picking channels store the replenishment SKUs corresponding to the picking SKU associated with the current picking order; determining an order of entering the plurality of target picking channels based on a picking waiting time required by the target picking object to enter the target picking channel for picking, and generating a target picking path corresponding to the current picking order based on the order and a path strategy determined according to the picking order type; and planning the target picking paths corresponding to the plurality of picking orders in sequence to obtain a path planning result.

[0007] Compared with the related art, the picking path planning method for a small and medium-sized flat warehouse under a full-channel mode provided by the embodiment of the application selects a current picking order and a corresponding target picking object from a plurality of picking orders allocated to a plurality of picking objects, and detects a plurality of target picking channels in the storage location allocation information, wherein the target picking channels store replenishment SKUs corresponding to a picking SKU associated with the current picking order; determines an order of entering the plurality of target picking channels based on a picking waiting time required by the target picking object to enter the target picking channel for picking, and generates a target picking path corresponding to the current picking order based on the order and a path strategy determined according to the picking order type; and plans the target picking paths corresponding to the plurality of picking orders in sequence to obtain a planning result, thereby solving the problems of serious occupation conflict of picking operations under a full-channel mode, long picking operation time, and low picking efficiency in the related art, relieving the space-time conflict in the picking channel and reducing the waiting time in the picking process under a multi-operation type and multi-picking object operation scenario, minimizing the total picking operation time, and improving the picking operation efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0008] Figure 1 FIG. 1 is a hardware structure block diagram of a terminal of the picking path planning method for a small and medium-sized flat warehouse under a full-channel mode according to the embodiment of the application; Figure 2 FIG. 2 is a flowchart of the picking path planning method for a small and medium-sized flat warehouse under a full-channel mode according to the embodiment of the application; Figure 3 FIG. 3 is a schematic diagram of a node network according to the embodiment of the application; Figure 4is a space-time network diagram of an embodiment of the present application; Figure 5 is an algorithm flow chart for constructing a space-time network of a preferred embodiment of the present application; Figure 6 is a flow chart for path planning of a preferred embodiment of the present application; Figure 7 is a picking path diagram generated after path optimization of an embodiment of the present application; Figure 8 is a space-time network diagram after path optimization of an embodiment of the present application; Figure 9 is a structure diagram of a double-layer coding individual of an embodiment of the present application; Figure 10 is a genotype structure diagram of a double-layer coding individual of an embodiment of the present application; Figure 11 is a reference individual diagram of a primary population of an embodiment of the present application; Figure 12 is a crossover operation diagram of an embodiment of the present application; Figure 13 is a mutation operation diagram of an embodiment of the present application; Figure 14 is a diagram of an order and commodity relationship matrix of an embodiment of the present application; Figure 15 is a diagram of a commodity association matrix of an embodiment of the present application; Figure 16 is a diagram of a commodity association network of an embodiment of the present application; Figure 17 is a structure block diagram of a picking path planning device for a small and medium-sized flat warehouse under a full-channel mode according to an embodiment of the present application. DETAILED DESCRIPTION

[0009] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and explained below in combination with the drawings and embodiments.

[0010] The method embodiments provided in the present embodiment can be executed in a terminal, a computer or a similar computing device. Taking an example of running on a terminal, Figure 1 is a hardware structure block diagram of a terminal for a picking path planning method for a small and medium-sized flat warehouse under a full-channel mode according to an embodiment of the present application. As shown in Figure 1 , the terminal can include one or more (only one is shown in Figure 1 ) processor 102 (the processor 102 can include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the above terminal can also include a transmission device 106 for communication function and an input and output device 108. Those skilled in the art can understand that Figure 1 the structure shown is only schematic, which does not limit the structure of the above terminal. For example, the terminal can also include more or fewer components than Figure 1 shown, or have a different configuration than Figure 1 shown.

[0011] The memory 104 can be used to store a computer program, such as the computer program corresponding to the picking path planning method for small and medium-sized flat warehouses in the full-channel mode in the embodiments of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implements the above-mentioned method. The memory 104 can include a high-speed random access memory, a non-volatile memory, and a memory remotely arranged with respect to the processor 102. The transmission device 106 is used to receive or send data via a network. In an example, the transmission device 106 can include a network adapter or a radio frequency module.

[0012] The embodiment provides a picking path planning method for small and medium-sized flat warehouses in the full-channel mode running on the terminal, Figure 2 is a flowchart of the picking path planning method for small and medium-sized flat warehouses in the full-channel mode according to the embodiments of the present application, as Figure 2 shown, the flowchart includes the following steps:

[0013] Step S201, after receiving a picking request for picking a plurality of picking orders, obtaining previously planned storage location allocation information, wherein the picking request includes a picking order type and a picking SKU of the picking order, and the storage location allocation information is generated by using a genetic algorithm to plan storage location allocation of replenishment SKUs considering a goods delivery frequency parameter, a goods correlation parameter, and a relocation cost of the replenishment SKUs of replenishment orders.

[0014] In the embodiment, the picking path planning method is performed to pick SKUs required by the currently received sales order from the flat warehouse and timely deliver goods from the corresponding warehouse to meet the picking demand, improve the warehouse use efficiency, and reduce the picking and storage costs. In the embodiment, the orders to be picked are purchase or demand orders generated at the moment, and the goods (one good corresponds to one SKU) meeting the demand of a plurality of picking orders are stored in the corresponding flat warehouse before the current moment, and the stored goods are replenished and stored according to the replenishment order generated by estimating how many picking orders will be generated in the future (corresponding to the current) and the required goods at the past moment (corresponding to the current moment). That is, after the corresponding replenishment order arrives at the past moment, all goods corresponding to the replenishment order are planned according to the set storage location allocation method (for example, a method of using a genetic algorithm to plan storage location allocation according to the storage location information of the flat warehouse and the goods delivery frequency parameter, the goods correlation parameter, and the relocation cost of the SKU corresponding to the replenishment order) to obtain the storage location allocation information for representing the storage information of the goods in the flat warehouse (for example, the SKU corresponding to one good, the goods aisle where the SKU is located, the storage location number, and the number of the goods on the storage location).

[0015] In the embodiment, after receiving the corresponding picking request, the planning of the picking path corresponding to the received multiple picking orders is started, at this time, the picking type (online order and offline order) of the corresponding picking order and the goods (that is, the corresponding SKU) needed to be picked for each picking order need to be determined; in the embodiment, determining the picking type of the corresponding picking order is used to select the path strategy adopted for picking the goods required by the picking order, in the embodiment, the path strategies involved include the return strategy, the S-shaped path strategy, and the combined strategy of the return strategy and the S-shaped path strategy, the return strategy refers to generating a sequence according to the goods corresponding to the storage location of the goods in the picking task sheet, entering each channel from the picking channel entrance in a predetermined order, returning to the channel entrance after picking all the required goods in the channel, and the S-shaped path strategy refers to taking the warehouse entrance as the starting point and traversing all the required storage locations in a snake shape according to the channel arrangement order, in the embodiment, because the offline order has the characteristics of few varieties and large quantities, the return strategy is adopted for path planning, and the online order adopts the combined strategy.

[0016] Step S202, from the multiple picking orders allocated to the multiple picking objects, selecting a current picking order and a corresponding target picking object, and detecting, in the storage location allocation information, multiple target picking channels in which the replenishment SKUs corresponding to the picking SKUs associated with the current picking order are stored.

[0017] In the embodiment, the picking of the picking object to the picking SKU in the picking list is realized by accessing the storage location of the picking SKU, and the access to the storage location is realized by accessing the picking channel, and then the picking path planning can be divided into two levels of determining the access sequence of the picking channel and determining the access sequence of the storage location in the channel. Meanwhile, in the embodiment, it is set that only a single picking object is allowed to enter the same picking channel at any time, the access sequence of the picking object in the picking channel is adjusted, so that different picking objects at the same time are located in different picking channels to carry out the work, and the picking waiting time is reduced. In the embodiment, because only a single picking object is allowed to enter the corresponding picking channel at a certain time, it is also determined which picking object enters first, which is the determination of the access sequence. It can be understood that the picking order that is first allocated and the picking object that receives the picking order must be arranged first, that is, the picking object that is first arranged to pick the order is given priority to arrange the picking channel. In the embodiment, the first allocated picking order is taken as the current picking order, and the picking channel and the access sequence of the picking channel that need to be accessed are planned based on the current picking order as the target. Then, after determining the first allocated picking order (corresponding to the current picking order) and the corresponding picking object, the picking object is taken as the target picking object, and the picking order is taken as the target picking order that needs to be picked path planning. In the embodiment, before determining the sequence of each picking object accessing the picking channel, the picking order allocated to each picking object and the picking SKU required by the picking order need to be determined, and then the picking channel required by each picking order and picking object is determined according to the storage location of the required picking SKU in the plane warehouse. Therefore, the replenishment SKU corresponding to each picking SKU of the current picking order and the corresponding storage location are detected from the storage location allocation information representing the replenishment SKU storage condition in the plane warehouse according to the picking SKU corresponding to the current picking order, and then the multiple target picking channels storing the replenishment SKU corresponding to the picking SKU associated with the current picking order are determined according to the picking channel where each storage location is located. Then, based on the actual picking condition (including which picking channel has the corresponding picking object for picking work and which picking channel is idle) in the current plane warehouse and the target picking channel to be picked, the sequence of the target picking object accessing the multiple target picking channels is planned, and the target picking path corresponding to the current picking order is planned.

[0018] In step S203, the sequence of entering the multiple target picking channels is determined in turn based on the picking waiting time required by the target picking object entering the target picking channel for picking, and the target picking path corresponding to the current picking order is generated based on the sequence and the path strategy determined according to the picking order type.

[0019] In the embodiment, the picking waiting time of the picking object at the entrance of the picking channel is determined according to the number of other picking objects queued before the target picking object and the picking time required by each picking object to complete the corresponding picking, and at the same time, the time for the target picking object to walk from the current position to each picking channel (corresponding to the distance between the current position and the entrance of each picking channel) also determines the length of the picking waiting time; in the embodiment, for the determined target picking object and the current picking order, the waiting time is also targeted to be reduced, therefore, the order of the target picking object entering the corresponding target picking channel, that is, the sequence, is adjusted by determining the picking waiting time of the target picking object entering each target picking channel in all target picking channels associated with the target picking object, for example: the target picking object currently to be picked includes channel 1, channel 2, channel 3, channel 4 and channel 5, and all channels currently have no other picking objects for picking, then the channel entering first is determined according to the distance of the target picking object from the five channels, for example: channel 1, after the target picking object completes picking of channel 1 and exits, the corresponding picking waiting time is recalculated at this time, at this time, if at least one of channel 2, channel 3, channel 4 and channel 5 has no other picking objects for picking, the channel with the shortest distance from the current position (corresponding to the walking time, that is, the corresponding picking waiting time) is selected as the next picking channel of the target picking object, if channel 2, channel 3, channel 4 and channel 5 all have other picking objects for picking, then the channel with the shortest picking waiting time is selected as the next picking channel of the target picking object according to the number of picking objects queued under each channel and the picking time required to complete the corresponding picking; at the same time, in the embodiment, after the target picking channel to be entered is selected, the picking in the target picking channel is performed according to the path strategy corresponding to the picking order type corresponding to the current picking order, that is, the target picking object enters and exits the corresponding target picking channel according to the corresponding path strategy, for example: when the current picking order is an offline order, the return strategy is adopted for picking, that is, the target picking object enters the channel opening closest to the warehouse entrance of the target picking channel, and then exits the channel opening after completing the picking, forming a partial path in the target picking channel, and then all the partial paths of the target picking object in the target picking channel sorted in sequence are constructed into the target picking path corresponding to the current picking order.It can be understood that when picking a certain picking order, there will be other picking objects in the multiple picking channels of the flat warehouse to pick other picking orders, and the other picking orders can be picking orders assigned before the certain picking order or picking orders after the certain picking order, in other words, at the same picking time, several or all of the multiple picking orders will be executed, but for several or all of the picking orders executed at the same picking time, the picking of these picking orders is performed in turn according to the priority of the picking order (representing the order in which the picking order is assigned, the picking order assigned first has the highest priority), that is, the first entering picking channel corresponding to the multiple picking orders is selected in order, and the sequence of the subsequent picking channels of the first entering picking channel will change due to the different number of picking SKUs of each picking order in the corresponding picking channel, for example: there are 5 picking SKUs in the first picking channel 1 corresponding to the picking order 1, and there are 2 picking SKUs in the first picking channel 3 corresponding to the picking order 2, then for the picking object of the picking order 2, it can enter the next picking channel 2 before the picking object corresponding to the picking order 1, and the picking object corresponding to the picking order 1 enters the next picking channel 3 later.

[0020] In some optional embodiments, the following steps are further performed: step 1, at the current time, assigning a plurality of picking orders to a plurality of preset picking objects, that is, assigning a picking order to each picking object; step 2, after the assignment, taking the picking object that first receives the picking task (corresponding to the picking order that is first received) as the target picking object, and the corresponding picking order as the current picking order; step 3, identifying the picking order type of the current picking order, and retrieving the target picking channel that needs to be accessed to access the corresponding storage location of all picking SKUs corresponding to the current picking order; step 4, determining whether the target picking channel to be accessed is occupied by other picking objects, if not, performing step 5, otherwise performing step 6; step 5, calculating the distance between the location of the target picking object and all unoccupied target picking channels respectively, selecting the nearest target picking channel as the next target picking channel to be accessed, and generating a route according to the path strategy corresponding to the type of the picking order; if there is more than one unoccupied picking channel, step 7 is performed; step 6, counting the number of picking objects waiting to enter each picking channel to be picked, selecting the picking channel with the fewest picking objects waiting as the next picking channel to be accessed, and generating a route according to the path strategy corresponding to the type of the picking order. If there is more than one picking channel with the fewest picking objects waiting, step 7 is performed; step 7, selecting the picking channel with the most picking SKUs to be picked as the next picking channel to be accessed, and generating a route according to the path strategy corresponding to the type of the picking order, if there is more than one picking channel with the most picking SKUs to be picked, selecting the picking channel closest to the warehouse entrance; step 8, removing the picking SKUs that have been picked from the current picking order, and then sequentially completing the picking planning of the picking order, until all picking orders are completed.

[0021] Step S204, sequentially planning the target picking paths corresponding to the plurality of picking orders to obtain a path planning result.

[0022] Through the above steps S201 to S204, the problem of serious picking task occupation conflict, long picking task time, and low picking efficiency in the related art under the full-channel mode is solved, and in the multi-task type and multi-picking object operation scenario, the time and space conflict in the picking channel is relieved, the waiting time in the picking process is reduced, the total picking operation time is minimized, and the picking operation efficiency is improved.

[0023] In some embodiments, selecting the current picking order and the corresponding target picking object from multiple picking orders assigned to multiple picking objects includes the following steps: after assigning multiple picking orders to multiple picking objects, determining the order in which each picking object receives the picking order, selecting the picking order with the earliest assignment order to obtain the current picking order, and taking the picking object with the earliest assignment order as the target picking object.

[0024] In some embodiments, the location allocation information detects multiple target picking channels that store replenishment SKUs corresponding to the picking SKUs associated with the current picking order, achieved through the following steps:

[0025] Step 21: The planar warehouse grid corresponding to the location allocation information is converted into a node network. The node network includes picking lanes, picking lane nodes, and cross lane nodes. A picking lane node is associated with two replenishment SKUs allocated in the same picking lane. Cross lane nodes are used to represent one of the entrances and exits of each picking lane.

[0026] In this embodiment, reference Figure 3 The node network shown represents the NM-1 type planar warehouse model rasterized into a node network. The passable area is discretized into path nodes, including intersection nodes and picking channel nodes. All path nodes within a picking channel are picking channel nodes. Except for the intersection nodes at the warehouse entrance and exit, each picking channel has one intersection node at its entrance and exit. Actions such as intersections and overtaking between different pickers (picking objects) are only allowed to occur at intersection nodes. The waiting area is also located at the intersection nodes at the picking channel entrance and exit. The picking channel index k is generated from the aisle index i using the following formula: I represents the set of cargo channels; in this embodiment, the path nodes at the warehouse entrance and exit of the flat warehouse are set to o=0, and the remaining nodes are numbered starting from the intersection node at the entrance of the picking channel k=1, increasing with the cargo location index, while also including the intersection node at the exit of the picking channel k=1, and so on, to complete the generation of all path node numbers; construct the two-dimensional coordinates (o) of path node o. x ,o y ), x-coordinate o x The value is the index k of the corresponding picking channel, and the ordinate of the picking channel node is the index p of the corresponding storage location. Specifically, the two-dimensional coordinate of node o=0 is set to (0,0), the ordinate of the intersection node at the entrance of each picking channel is set to 0, and the ordinate of the intersection node at the exit is set to p+1. In this embodiment, a replenishment SKU is stored in a storage location, that is, a replenishment SKU can be referred to by a storage location index. At the same time, a picking channel node corresponds to a storage location index and is associated with at least one replenishment SKU.

[0027] Step 22, among the replenishment SKUs associated with the picking channel nodes of all picking channels, search for a replenishment SKU which is one of the picking SKUs associated with the current picking order, and determine the picking channel node associated with the searched replenishment SKU.

[0028] In the present embodiment, by searching for the picking SKU in the storage location index representing the replenishment SKU, when the storage location index corresponding to the replenishment SKU matching the picking SKU is searched, it indicates that the picking channel node corresponding to the storage location index stores at least one replenishment SKU matching the picking SKU, and the picking channel where the picking channel node is located is the target picking channel corresponding to the current picking order.

[0029] Step 23, take the picking channel with at least one picking channel node as the target picking channel.

[0030] Through the above steps 21 to 23, the storage location storing the picking item corresponding to each picking order and the picking channel are determined, which provides a data basis for planning the picking path corresponding to the picking order.

[0031] In some embodiments, based on the picking waiting time required for the target picking object to enter the target picking channel for picking, the order of entering the multiple target picking channels is determined in sequence, and based on the order and the path strategy determined according to the type of the picking order, the target picking path corresponding to the current picking order is generated, which is achieved by the following steps:

[0032] Step 31, obtain the space-time network generated by sequentially planning the multiple picking orders, wherein the space-time network includes multiple space-time arcs corresponding to the multiple picking orders, the space-time arc includes at least one space-time sub-arc corresponding to the corresponding space-time state, the space-time sub-arc includes a picking space-time sub-arc, a waiting space-time sub-arc and a walking space-time sub-arc, and the space-time state includes walking, waiting and picking.

[0033] In this embodiment, the space-time network is generated by preliminary picking planning of multiple picking orders. Specifically, multiple picking orders are assigned to corresponding picking objects (corresponding pickers), and then the priority of the corresponding picking order is determined according to the order in which the picking tasks are received. After that, multiple picking orders are sequentially planned according to the priority, and in the planning process, the congestion disposal strategy of allowing only a single picking object to enter the congestion of the same picking channel at any time is used as a hard constraint to plan the picking path of multiple picking orders, and the position of each picking object in the picking operation of the picking order is described together with the space-time state (including walking, waiting, picking), and the time of each space-time state is quantified, so that the state of the picking object in the warehouse at a certain moment is described as a set of space-time arcs, and thus the corresponding space-time network is obtained. Based on the space-time network shown in Figure 4 The space-time state of the picking process of the two pickers is described as follows: the path nodes corresponding to the picking locations of picker A are 5, 16, 26, and 27, and the path nodes corresponding to the picking locations of picker B are 4 and 12. Before the picking path is adjusted, the access order of the picking channels corresponding to the two picking orders is 0→1→3→4→0 and 0→1→2→0, respectively. Both pickers need to enter channel 1 for work. Picker A starts from node o=0 at time t=0 and reaches path node o=1 at time t=1.5. According to the combined path strategy, it returns to node o=1 at t=12.5 after picking SKU at node o=5, during which it occupies picking channel 1. Then it visits the remaining nodes and returns to the warehouse entrance at t=53. Picker B starts from o=0 at time t=1 and reaches node o=1 at t=2.5. Since channel 1 is already occupied by picker A at this time, it can only wait for 10s at node o=1. After picker A leaves, it enters channel 1 and completes the remaining picking tasks, returning to o=0 at t=44. It should be noted that in this embodiment, the picking path of each picking order in the space-time network is a picking path that avoids channel congestion, but does not consider the waiting time caused by avoiding congestion. That is, there is a waste of waiting time caused by channel congestion, and there is still room for optimization of picking path planning. That is, the waiting time caused by congestion is considered to be reduced in order to achieve the goal of minimizing the total picking operation time.

[0034] Step 32, based on the space-time network and the greedy strategy, respectively determine the target waiting space-time sub-arc generated by the current entering each target picking channel, and select the target picking channel corresponding to the target waiting space-time sub-arc with the shortest waiting time, to obtain the intended picking channel to be entered currently, wherein the target waiting space-time sub-arc is used to represent the space-time arc generated by the target picking object walking from the current position to the intersection channel node as the target entrance, and waiting at the intersection channel node, and the target entrance includes the channel mouth closest to the current position among the corresponding entrance and exit of the intended picking channel.

[0035] In the embodiment, the target waiting space-time sub-arc includes the walking space-time arc of the target picking object from the current position to the target entrance, and also includes the waiting space-time arc at the target entrance, when there is no other picking object queuing at the target entrance of the target picking channel, the corresponding waiting space-time arc is empty, and the target waiting space-time sub-arc includes the walking space-time arc; in the embodiment, the selection of the target entrance is determined according to the corresponding path strategy, and is affected by the exit when exiting from the last picking channel, for example: when passing through the current picking channel according to the combined strategy and using the S-shaped path strategy, the corresponding current position is the exit of the last picking channel, at this time, the channel mouth closest to the intended picking channel from the current position is the channel mouth of the intended picking channel away from one end of the flat warehouse entrance and exit, that is, the exit corresponding to the intended picking channel.

[0036] Step 33, after generating a plurality of picking space-time sub-arcs and a plurality of walking space-time sub-arcs in the intended picking channel according to the path strategy corresponding to the picking order type, taking the end node of the last walking space-time sub-arc corresponding to the current intended picking channel as the current position, the repeated operation of selecting the next intended picking channel to be entered and the corresponding target entrance is performed, to sequentially determine the next target picking channel to be entered, and determine the order of entering a plurality of target picking channels.

[0037] Step 34, for the target picking channels determined in sequence, a plurality of picking space-time sub-arcs and a plurality of walking space-time sub-arcs located in the corresponding target picking channel are generated in sequence, and the target waiting space-time sub-arc corresponding to the corresponding target picking channel, a plurality of picking space-time sub-arcs and a plurality of walking space-time sub-arcs are combined into the target space-time arc corresponding to the corresponding target picking channel, and the picking links corresponding to a plurality of target space-time arcs are combined into the target picking path corresponding to the current picking order.

[0038] Through the above steps 31 to 34, considering the optimization of the picking path planning for reducing congestion waiting time waste based on the space-time network corresponding to the picking path, the goal of minimizing the total picking operation time is achieved, the waiting time of the picker is reduced, the picking path conflict problem in the multi-operation type and multi-picker operation scene is alleviated, and thus the total length of the overall picking process is shortened.

[0039] In some embodiments, based on the space-time network and the greedy strategy, the target waiting space-time sub-arc generated by the current entering each target picking channel is determined respectively by the following steps:

[0040] Step 41, based on the space-time network, determine whether each target picking channel is currently associated with the corresponding space-time arc.

[0041] In this embodiment, by determining whether the target picking channel is currently associated with the corresponding space-time arc, it is determined whether the target picking channel is occupied by other picking objects.

[0042] Step 42, in the case of determining that the corresponding target picking channel is currently not associated with the corresponding space-time arc, determine the first walking space-time sub-arc corresponding to the target picking channel not associated with the space-time arc, and take the first walking space-time sub-arc as the target waiting space-time sub-arc, wherein the first walking space-time sub-arc is used to represent that the target picking object is on the first picking link within the first walking time, the first picking link is used to represent the physical path of the target picking object walking from the current position to the intersection channel node corresponding to the entrance of the picking channel, and the waiting time corresponding to the target waiting space-time sub-arc includes the first walking time.

[0043] In this embodiment, when it is determined that the target picking channel is not associated with the corresponding space-time arc, it means that the corresponding target picking channel is not occupied and can be accessed by the target picking object, and the corresponding target picking channel is determined as the next accessed target picking channel by the target picking object according to the distance between the current position of the target picking object and each target picking channel, that is, the first walking time corresponding to the first walking space-time sub-arc, and the first walking time is also used as the waiting time corresponding to the target waiting space-time sub-arc.

[0044] Step 43, in the case of determining that the corresponding target picking channel is currently associated with the corresponding space-time arc, determine the first walking space-time sub-arc and the first waiting space-time sub-arc corresponding to the corresponding target picking channel, and take the first walking space-time sub-arc and the first waiting space-time sub-arc as the target waiting space-time sub-arc, wherein the first waiting space-time sub-arc is used to represent that the target picking object waits at the intersection channel node corresponding to the entrance of the picking channel, and the waiting time corresponding to the target waiting space-time sub-arc includes the corresponding first walking time and the waiting time corresponding to the first waiting space-time sub-arc.

[0045] In the embodiment, when it is determined that the corresponding spatiotemporal arc of the target picking channel is occupied by other picking objects, and when the target picking object has no other available target picking channel to select, the target picking object needs to wait until the picking objects currently picking in the plurality of target picking channels complete picking, and then select one of the picking channels that is allowed to access first as the next target picking channel to access. At this time, the first walking spatiotemporal sub-arc and the first waiting spatiotemporal sub-arc of the target picking object from the current position to each target picking channel are determined, and the waiting time corresponding to the first waiting spatiotemporal sub-arc includes the picking time of at least one other picking object that completes picking in the corresponding target picking channel before the target picking object. The picking time of one other picking object that completes picking includes the total picking time calculated according to the picking time (for example, 3 seconds) required for picking the corresponding article (corresponding to one picking SKU) at each picking channel node, the walking time between the plurality of picking channel nodes, and the walking time from the last picking channel node to the exit of the target picking channel, and the sum of the total picking time and the two walking times is taken as the picking time of one picking object that completes picking. In the embodiment, when determining the waiting time corresponding to the target waiting spatiotemporal sub-arc of the target picking channel, the picking time required by at least one other picking object and the first walking time of the first walking spatiotemporal sub-arc corresponding to the target picking object are taken as the corresponding waiting time.

[0046] Through steps 41 to 43 described above, the target waiting spatiotemporal sub-arc generated by the current entry into each target picking channel is determined, and then the picking waiting time required by the target picking object to enter each target picking channel for picking is determined.

[0047] In some embodiments, a plurality of picking spatiotemporal sub-arcs and a plurality of walking spatiotemporal sub-arcs located in the corresponding target picking channel are generated, and the following steps are implemented:

[0048] Step 51: According to the path strategy corresponding to the picking order type, the intersection channel nodes through which the target picking object enters and exits the target picking channel are respectively determined, to obtain the first intersection channel node and the second intersection channel node.

[0049] In the embodiment, the first cross-channel node is taken as the entrance of the target picking channel, and the second cross-channel node is taken as the exit of the target picking channel. It can be understood that, according to the corresponding path strategy, the first cross-channel node and the second cross-channel node can be the same channel port. For example, when the picking order is an offline order and the path strategy is a return strategy, the first cross-channel node and the second cross-channel node are both the channel port close to the entrance of the planar warehouse. For another example, when the picking order is an online order and the strategy of entering and exiting the target picking channel is an S-shaped path strategy, the first cross-channel node and the second cross-channel node are respectively the channel ports at both ends of the target picking channel.

[0050] In some optional embodiments, the picking order type includes an online picking type and an offline picking type, and the first cross-channel node and the second cross-channel node are determined according to the path strategy corresponding to the picking order type, by the following steps:

[0051] In step 511, when the picking order type is the offline picking type, the path strategy is determined as the return path strategy, and the cross-channel node corresponding to the entrance of the target picking channel is taken as the first cross-channel node and the second cross-channel node.

[0052] In step 512, when the picking order type is the online picking type, the path strategy is determined as the combined path strategy composed of the S-shaped path strategy and the return path strategy, and after taking the entrance of the target picking channel as the first cross-channel node, the target picking object is determined to start from the starting point of the last first channel node of the target picking channel, to exit the target picking channel along the candidate exit respectively and walk to the walking distance corresponding to the first channel node of the next target picking channel, and the candidate exit corresponding to the shortest walking distance is taken as the second cross-channel node, wherein the candidate exit includes one of the entrance and the exit of the target picking channel.

[0053] In step 52, among all the picking channel nodes corresponding to the target picking channel, the picking channel nodes in which the picking SKUs to be picked are stored are sequentially searched to obtain the first channel nodes, and after the node paths between the first cross-channel node and the first channel node, the adjacent two first channel nodes, and the last first channel node and the second cross-channel node are determined, the walking time of the target picking object in the corresponding node path and the corresponding node path are converted into the corresponding walking space-time sub-arc, and the node position of each first channel node and the corresponding picking time of the target picking object are converted into the corresponding picking space-time sub-arc.

[0054] In the embodiment, based on the corresponding node path and time, the spatio-temporal state is described to describe the picking process of the target picking object in the target picking channel.

[0055] In step 53, according to the sequence, it is determined whether the target picking channel is the last picked target picking channel, and in the case where the target picking channel is the last picked target picking channel, the walking path and the corresponding walking time between the second cross-channel node corresponding to the last picked target picking channel and the plane warehouse entrance are converted into the end walking spatio-temporal sub-arc, and the end walking spatio-temporal sub-arc is taken as one of the walking spatio-temporal sub-arc corresponding to the last picked target picking channel.

[0056] In the embodiment, after a picking order is picked, the picking object needs to return to the plane warehouse entrance, and the walking time of the picking object returning to the plane warehouse entrance is also the corresponding picking time, therefore, by adding the walking time corresponding to the end walking spatio-temporal sub-arc to the corresponding picking time, the total time of picking a picking order is quantified, and the accurate time parameter is improved to achieve the goal of minimizing the total picking operation time.

[0057] Through the above steps 51 to 53, the plurality of picking spatio-temporal sub-arc and the plurality of walking spatio-temporal sub-arc located in the corresponding target picking channel are generated.

[0058] In some embodiments, before determining the sequence of entering the plurality of target picking channels, the following steps are also implemented:

[0059] In step 61, the plurality of target picking channels associated with each picking order and the picking channel access sequence are determined respectively, and based on the picking channel access sequence and the path strategy corresponding to the picking order type, the first path of the corresponding picking object in the plurality of target picking channels is determined.

[0060] In step 62, according to the picking sequence determined according to the allocation sequence of allocating the plurality of picking orders to the plurality of picking objects, the order of the plurality of picking objects entering the same target picking channel is determined, and one target picking channel does not allow multiple picking objects to enter at the same time.

[0061] In step 63, according to the order, the congestion waiting time required for the picking object to enter the corresponding target picking channel for picking is determined, and based on the first path and the congestion waiting time corresponding to each target picking channel, the picking time and the walking time required for the picking object to pick in the corresponding target picking channel, the picking position and the spatio-temporal state are associated and mapped, and at least the initial spatio-temporal sub-arc for picking in each target picking channel is generated, wherein the congestion waiting time is determined according to the picking time and the walking time required for the picking object of the previous picking order to pick in the corresponding target picking channel.

[0062] Step 64, generating an initial space-time arc corresponding to the picking order according to the initial space-time sub-arc corresponding to the multiple target picking channels associated with the picking order, and generating a space-time network according to the initial space-time arcs respectively corresponding to the multiple picking orders.

[0063] Through the above steps 61 to 64, the space-time network corresponding to the multiple picking orders is described, and the data basis for calling the corresponding space-time network when planning the picking path is provided.

[0064] Reference Figures 3 to 8 The path planning process of the preferred embodiment of the present application is described as follows:

[0065] In this embodiment, a mathematical model of picking path planning considering channel congestion is established, so that the congestion handling strategy of allowing only a single picker to enter the congestion of the same picking channel at any time is implemented as a hard constraint, and the walking, waiting and picking time of the picker during the work process is quantified, and the target function of minimizing the total picking operation time is constructed to achieve the goal of relieving channel congestion. In this embodiment, the corresponding mathematical model is set as follows: (1) the flat warehouse has only one entrance (I / O), and the picker starts from the entrance when performing the picking task and returns to the entrance after completing the picking task; (2) each SKU in the picking list can be searched in the warehouse, that is, out-of-stock is not allowed; (3) the SKU location assignment scheme is fixed when starting to pick each picking list; (4) the picking list is divided into online and offline two kinds, each picker can pick any kind of picking list, each picking list can be completed by one picker at a time, and the picker must complete the picking of all SKUs in the picking list; (5) the path nodes are divided into picking channel nodes and intersection channel nodes, and each storage location can be accessed through the corresponding picking channel node; (6) the same time only one picker is allowed in the picking channel node (no intersection is allowed), and the number of pickers on the intersection channel node is not limited (intersection is allowed); (7) for the case that any SKU is stored in multiple storage locations, the storage location with the smallest aisle number / storage location number (referred to as the to-be-picked storage location) is preferentially accessed when picking it; (8) the to-be-picked storage location of any SKU in each picking list needs to be accessed only once, that is, the corresponding picking channel node needs to be accessed only once when picking any SKU; (9) there is a time interval between the arrival times of any two picking lists, that is, there is a time interval between the start times of any two picking tasks; (10) the picking time of a SKU in the online and offline picking list is constant respectively; (11) the walking speed of each picker is uniform; in this embodiment, the work process of the picker (including walking, waiting and picking) is mapped to the time-space arc in the time-space network, the time consumption of each link is quantified through the time period information in the time-space arc, and the time-space waiting arc is used to depict the congestion state of the picking channel. Since the completion of the overall picking task depends on the completion time of the slowest picker, in order to shorten the total length of the overall picking process, the objective function of minimizing the maximum value of the operation time of all pickers is established. The objective function of the picking path planning model is as follows: ; constraint conditions: (1), ensure that each SKU in the picking list has a to-be-picked storage location and can be accessed through the corresponding path node; (2) ensure that all SKUs in the picking list (including online and offline picking lists) are picked, and the constraint is: ; ; (3) ensure that the picker starts from the I / O and returns, and the constraint is: ; (4) Ensure that online orders are picked using a combined path strategy and offline orders are picked using a return-to-the-path strategy: , , (5) Constraints To ensure that the number of pickers entering and leaving each spatiotemporal network vertex is equal, where o∈O\{0} represents excluding warehouse entrance and exit nodes from the node set; (6) Ensure that there is only one spatiotemporal arc between adjacent nodes, i.e., the coupling constraint between the spatiotemporal arc and the physical link of the operation route, the constraint formula is: (7) indicates that the system generates only one picking list at a time, where Represents all spatiotemporal arcs originating from the warehouse entrance / exit (node ​​0), with the following constraint: (8) Ensure that only one picker is allowed to enter the same picking lane at any given time, wherein This indicates excluding all waiting arcs from the set of spacetime arcs. The starting and ending points of the spacetime arc are both internal nodes of the picking channel k, and the constraint is: (9) Dynamic update constraint of the spatiotemporal arc set: After each generation of the picker path, the spatiotemporal arc set A will be updated based on the current channel blocking time. k Dynamic updates ensure that newly generated arcs do not conflict with already occupied time periods, with the following constraint: A new For the latest set of spatiotemporal arcs generated by the spatiotemporal network construction algorithm; Ⅱ() is the indicator function, if the spatiotemporal arc With blocktime k If the defined time periods overlap, then selecting that spatiotemporal arc is prohibited; where, Indicates SKU s The path node o corresponding to the location to be picked represents the location allocation scheme; the two-dimensional coordinates of path node o are (ox, oy). The two-dimensional coordinates are ( , h1 represents the width of the picking aisle; h2 represents the width of the cargo aisle; h3 represents the width of the storage location; M represents the total number of storage locations per aisle; K represents the set of picking aisles, K={1,2,…,[(N-1) / 2]}; k represents the picking aisle index, k=[(i-1) / 2],k∈K, i represents the storage location index; O represents the set of warehouse path node indices (I / O node number is 0); Qc represents the set of cross-aisle nodes, Qc∈O; Qa represents the set of picking aisle nodes, Q a ∈O; O k,c O represents the entrance and exit nodes of picking channel k. k,c ∈Q c ;O k,adenotes the set of nodes in picking aisle k, O k,a ∈ Q a ; denotes a path node, ∈ O; U denotes the set of pickers; u denotes the u-th picker, B denotes the set of picking orders, B online denotes the set of online orders, B online ∈ B; B offine denotes the set of offline orders, B offine ∈ B; b u denotes the picking order of the u-th picker, b u ∈ B; T denotes the set of task times; denotes a task time, ∈ T; denotes the expected occupancy time of picking aisle k; denotes the waiting time of picking aisle k; denotes the picking time of a SKU in an online picking order; denotes the picking time of a SKU in an offline picking order; t u denotes the final time of the u-th picker to complete the current task; A denotes the set of all types of space-time arcs; A V denotes the set of space-time walk arcs, A V ∈ A; A W denotes the set of space-time waiting arcs, A W ∈ A; A H denotes the set of space-time picking arcs, ; denotes the set of online task space-time picking arcs, ; denotes the set of offline task space-time picking arcs, ; a u denotes the space-time arc of the u-th picker, a u ∈ A; denotes the space-time walk arc of the u-th picker, ; denotes the space-time waiting arc of the u-th picker, ; denotes the space-time picking arc of the u-th picker, ; Q denotes the set of vertices in the space-time network; (o, t) denotes a vertex in the space-time network, (o, t) ∈ Q; E denotes the set of physical links between adjacent nodes; denotes a physical link between adjacent nodes, ; denotes the space-time arc formed by the picker being active on the physical link from time t to ; v uR represents the travel speed of the u-th picker; R represents the working route of all pickers. Represents a node The distance between them; D1 represents the node under the return strategy. The distance between them; D2 represents the distance under the combined path strategy. The distance between them; This indicates the blocking time of the picking channel k; Let u be the decision variable, and let u be the spatiotemporal arc when the picker chooses. That is, from time t to In physical link During the event, Otherwise, it is 0; As a decision variable, when the u-th picker chooses the physical link hour, Otherwise, it is 0.

[0066] In this embodiment, to accurately depict the spatiotemporal state of pickers during the picking process and quantify their walking, waiting, and picking times, a spatiotemporal network is introduced to describe the order picking process. The NM-1 type planar warehouse model is rasterized into a physical node network, referencing... Figure 3 As shown, and using two pickers as an example, the following is a description of... Figure 4 The spatiotemporal network shown; to directly access the spatiotemporal network of the order picking process when planning picking routes, refer to... Figure 5 The process shown includes: Step 1, inputting the path node index set O and the job time set T; Step 2, iterating through the job times t, then executing Step 3; Step 3, iterating through the path nodes o, then executing Step 4; Step 4, adding the vertex (o,t) in the spatiotemporal network to the spatiotemporal vertex set Q, then executing Step 5; Step 5, determining whether the path node o belongs to the intersecting channel node O. c If yes, proceed to step 6; otherwise, proceed to step 7. Step 6: Add a spacetime wait arc. The set A of spacetime waiting arcs (t, t+1) W Then, proceed to step 13; step 7: determine whether path node o belongs to picking channel node O. a If yes, proceed to step 8; otherwise, proceed to step 9. Step 8: Determine if the picking order of the u-th picker is an online picking order. If yes, proceed to step 10; otherwise, proceed to step 11. Step 9: Add a time-space travel arc. To the set of spacetime travel arcs A V Then, proceed to step 13; step 10, add a spatiotemporal picking arc ( To the online task spatiotemporal picking arc set , then step 12 is performed; step 11, adding the time-space picking arc ( ) ) to the set of offline task time-space picking arcs , then step 12 is performed; step 12, merging the set of online task time-space picking arcs and the set of offline task time-space picking arcs into the set of time-space picking arcs A H , then step 13 is performed; step 13, merging the set of time-space waiting arcs A W , the set of time-space picking arcs A H and the set of time-space walking arcs A V into the set of time-space arcs A; step 14, traversing all path nodes o and all job times t in a loop; step 15, outputting the set of time-space arcs A.

[0067] In this embodiment, referring to Figure 6 , in order to meet the constraint that only one picker can work in the picking channel at any time, a block time interval table (blocktime k ) is used in the algorithm to record the cumulative occupation time of the picking channel, and according to the job type (online or offline picking list) of the picker in the channel, the required time for picking SKU and the walking time under the corresponding path strategy can be determined, so that the expected occupation time of the picker for a picking channel k , the waiting time of the picker in the channel k can be obtained according to blocktime k and , further, the job path of the next picker is generated under the constraint of , until all job paths in the time-space network are generated; in this embodiment, the greedy strategy (selecting the picking channel with the smallest ) and the dynamic updating mechanism (blocktime k ) are used to reduce the waiting time of the picker and alleviate the picking path conflict problem in the multi-job type and multi-picker job scenario, so as to shorten the total time of the overall picking process; specifically, the process includes: step 1, inputting the set of picking order B, the set of job times T, the set of time-space arcs A, and the location allocation scheme X, then step 2 is performed; step 2, initializing blocktime k , R, t, o u , t u, after which step 3 is executed; step 3, determine if the job time t < T, if yes, execute step 4, otherwise, the process ends; step 4, iterate through all pickers starting from the first picker, after which step 5 is executed; step 5, determine if picker u is a picker belonging to the set of pickers U, if yes, execute step 6, otherwise, execute step 20; step 6, process picker u, after which step 7 is executed; step 7, obtain the SKU storage node, after which step 8 is executed until step 8; step 8, calculate the channel occupancy and waiting time, after which step 9 is executed; step 9, select the next picking channel k*, after which step 10 is executed; step 10, construct the space-time walk arc , after which step 11 is executed; step 11, determine if , if yes, execute step 12, otherwise, execute step 13; step 12, construct the space-time waiting arc , after which step 16 is executed; step 13, determine if b u ∈B online , if yes, execute step 14, otherwise, execute step 15; step 14, construct the online space-time picking arc , after which step 16 is executed; step 15, construct the offline space-time picking arc , after which step 16 is executed; step 16, merge the space-time arcs , after which step 17 is executed; update the state: t u , , blocktime k , o u , after which step 18 is executed; update the space-time network, after which step 19 is executed; step 19, increment the picker index u by one; step 20, determine if B = ∅, if yes, execute step 21, otherwise, execute step 22; step 21, construct the space-time walk arc to the return entrance , after which step 23 is executed; step 22, update the global time t = min(t u ), after which step 3 is executed; step 23, merge the path R ← a u , after which step 24 is executed; step 24, calculate the objective function F(R), after which step 25 is executed; step 25, output: R, F(R).

[0068] Reference is made to Figure 7 and Figure 8Taking the picking of two picking orders as an example, the corresponding path planning and space-time path planning process is explained. Picker A performs online order picking tasks, and picker B performs offline order picking tasks, both of which walk with the combination strategy and the return path strategy. The algorithm identifies that picking channel 1 has been occupied by picker A, so when planning the path for picker B, it is selected to avoid picking channel 1, and the access order of its picking channel is adjusted to 0→2→1→0. When picker A works in picking channel 1 from time t = 1.5 to t = 2.5, picker B is guided to enter the unoccupied picking channel 2 to carry out the work; when picker B completes the picking task of node o = 12 and reaches node o = 1 at the entrance of picking channel 1 at time t = 29.5, picker A has left the channel 1, and then enters it to complete the picking task of node o = 4. The latest picking path of picker B avoids the 10 s waiting time at node o = 1 before adjustment, and completes this picking job at time t = 44 in advance to return to the entrance and exit.

[0069] In some embodiments, before obtaining the storage location allocation information planned before the current, the following steps are also implemented:

[0070] Step 71, obtain a plurality of first SKUs associated with the first replenishment order and a plurality of second SKUs associated with the second replenishment order, and determine the target information corresponding to the first SKU and the second SKU respectively, wherein the target information at least includes the commodity out-of-warehouse frequency parameter and the commodity correlation degree parameter determined according to the preset statistical method, and the target information of the second SKU further includes the original storage location information corresponding to the second SKU; in the embodiment, in order to meet the demand for picking orders, it is necessary to store the corresponding goods in the flat warehouse in advance, that is, to store the corresponding goods in the warehouse storage location of the flat warehouse before receiving the picking order, at the same time, by taking the improvement of picking efficiency as the optimization target, and adopting the storage location allocation method including two types of rules of out-of-warehouse frequency and commodity correlation, the storage location allocation with the minimum picking distance is realized; in the embodiment, before the storage location allocation planning is performed, according to the historical order data, the out-of-warehouse frequency parameter and the commodity correlation degree parameter corresponding to each replenishment SKU in the replenishment order have been completed, and the out-of-warehouse frequency parameter and the commodity correlation degree parameter can be used as the known parameter for the storage location allocation planning when the replenishment order arrives; in the embodiment, in the storage location allocation planning process triggered by the arrival of the replenishment batch, the replenishment batch includes new batch allocation and old batch reallocation, for the new batch allocation, the goods in the new batch order are arranged on the corresponding storage location, but for the old batch reallocation, the goods in the old batch order will be moved, that is, in the old batch reallocation process, if the goods in the old batch are allocated to a new storage location, the goods need to be moved, and the moving operation will generate moving cost, which will affect the picking cost, therefore, in the embodiment, it is necessary to consider whether to move the goods in the old batch according to the moving cost and the corresponding picking cost, that is, to reallocate the old batch, and the moving operation is based on the original storage location information of the old batch goods.

[0071] Step 72, double-layer coding and initialization of storage location allocation based on target information and corresponding target SKU, to generate a plurality of double-layer coding individuals.

[0072] In the embodiment, in order to realize the double-layer decision of storage location allocation and moving operation, a double-layer coding solving algorithm based on genetic algorithm and a genetic operator suitable for double-layer coding are adopted; in the embodiment, the method of symbolic coding is selected to arrange the allocation of storage locations, at the same time, in order to completely describe the two situations of arranging storage locations for new batches of goods and reallocating storage locations for old batches of goods, the storage allocation and moving decision are decoupled to avoid the coupling of decision variables, and a double-layer coding structure is designed.

[0073] In the embodiment, the first layer of the double-layer encoding describes the mapping relationship between the new batch and the old batch of goods and the storage location, which is represented as a storage location code. Specifically, the storage location code X is divided into NXM segments according to the total number of storage locations, where N is the total number of aisles, and M is the number of storage locations per aisle. The arrangement order of the storage location index follows a double-loop traversal, i.e., the outer loop is the aisle number i, and the inner loop is the storage location number p. Each segment represents a gene, and each gene represents the type of goods stored at the storage location (i, p). The value of the gene is the index s of the type of goods, i.e., the SKU code. In this embodiment, the SKU code is in the form of integer encoding, and the non-existent SKU code is set to 0. Therefore, the storage location code adopts a matrix-type symbolic encoding structure, where the row vector corresponds to the aisle number, and the column vector represents the storage location sequence. The genotype can be represented by expanding the row as follows: wherein, when , the p-th storage location of aisle i stores goods s; in this embodiment, the second layer of encoding is designed to record the relocation information of the old batch, which is represented as a relocation code Y. Specifically, the relocation code Y is divided into NXM segments according to the total number of storage locations, and each segment represents a gene. Each gene represents the relocation situation of the old batch stored at the storage location. The value of each segment gene is the new storage location index ( ) to which the old batch stored at the storage location (i, p) is relocated. Since this layer of encoding is used to record the relocation information of the old batch of goods, only the genes corresponding to the storage locations that store the old batch of goods are recorded. Specifically, in the case where no relocation occurs, the original storage location index is taken as the gene value. The storage location code adopts conditional coordinate encoding, and the genotype can be represented as: wherein, y ip =∅ indicates that the storage location (i, p) does not store the old batch of goods, indicates that the old batch of goods is relocated from (i, p) to ( ); therefore, a double-layer encoding individual is represented in the form of genes as: | ], and the corresponding structure can be referred to as shown in Figure 9 .

[0074] In some specific embodiments, it is assumed that the planar warehouse has 2 aisles, each aisle has 5 storage locations, and there are a total of ten storage locations. There is a type of goods stored at storage locations (2, 1) and (2, 2), and its SKU code is 3, which is referred to as the old batch of SKU3. At this time, if three types of goods need to be allocated to storage locations, their SKU codes are 1, 2, and 3, which are referred to as the new batch of SKU1, SKU2, and SKU3, respectively. They need to be allocated 2, 3, and 1 storage locations, respectively. Referring to Figure 10, a two-layer coded individual is generated by the following method: SKU1 is placed in the location (1,1), (1,2), and similarly SKU2 is placed in (1,3), (1,4), (1,5), SKU3 is placed in (2,3), X={1,1,2,2,2,3,3,3,0,0} is the genotype of the individual location code, indicating a possible location allocation scheme; Y={,,,,, (2,1), (2,2),,,} is the genotype of the individual transfer code, indicating the transfer operation that needs to be performed on the old batch of goods, [X|Y]=[{1,1,2,2,2,3,3,3,0,0}|{,,,,, (2,1), (2,2),,,}] is the complete genotype of the individual.

[0075] In this embodiment, before generating the initial population, the initialization of the population needs to be completed to ensure that the population individuals always meet the historical storage constraints; since the old batch is already stored in the location, the original storage location of the old batch is known, after generating the initial population, the storage location of the old batch may change after subsequent genetic operations, in order to accurately depict the specific information of the transfer operation in the code, the reference individual needs to be generated in advance when constructing the initial population, that is, the genes corresponding to the stored old batch of goods in the location code X are assigned values, taking the SKU code as the value; similarly, the genes corresponding to the stored old batch of goods in the location code Y are assigned values, taking the original location index as the value; specifically, taking the above-mentioned one location allocation scheme as an example, the old batch of SKU3 has been stored in the location (2,1), (2,2), at this time, the reference individual of the initial population is generated: [X|Y]=[{0,0,0,0,0,3,3,0,0,0}|{,,,,, (2,1), (2,2),,,}], wherein x ip =0 in the location code X indicates that the location is empty, y ip =∅ in the transfer code Y indicates that the location corresponding to the locus does not store the old batch, and there is no need to record the transfer information, the reference individual of the generated initial population is shown in Figure 11 .

[0076] At step 73, the preset genetic algorithm and the target fitness function are used to perform preset genetic evolution operation and evolution iteration on the storage location sub-coding body of the double-layer coding individual, and based on the storage location sub-coding body corresponding to the completed genetic evolution operation, the transfer code of the transfer sub-coding body corresponding to the double-layer coding individual is updated until the target double-layer coding body corresponding to the current replenishment order is obtained, and the storage location allocation information is decoded from the storage location sub-coding body corresponding to the target double-layer coding body, wherein the target fitness function is constructed according to the product out-of-warehouse frequency parameter and the product correlation degree parameter associated with the storage location code of the corresponding storage location sub-coding body and the transfer cost associated with the transfer code, the storage location code is used to represent the storage location arrangement of a target SKU, and the transfer code is used to represent a change in storage location arrangement.

[0077] In the present embodiment, the corresponding genetic evolution operation and genetic evolution iteration are performed by using the genetic algorithm, which is clear and implementable to those skilled in the art, and the difference lies in the genetic evolution operation specifically adopted in the present embodiment: for example, adaptive crossover operator, adaptive local mutation strategy, at the same time, the present embodiment also constructs the corresponding target fitness function based on the product out-of-warehouse frequency, the correlation degree between commodities and the transfer cost, and then performs selection, crossover and mutation of the genetic evolution operation through the function value of the corresponding target fitness function, until the corresponding target double-layer coding body including the storage location allocation information is finally generated.

[0078] In the present embodiment, in the process of carrying out the storage space allocation planning, a storage space allocation mathematical model based on replenishment event driving is also constructed to mathematically model the process of the storage space allocation planning, and a target value corresponding to a target function is solved according to the set target function through the constructed storage space allocation mathematical model, and then a corresponding storage space allocation scheme is obtained; in the present embodiment, the following settings are made for the storage space allocation mathematical model: (1) the warehouse has only one entrance (I / O); (2) each storage space stores only a single SKU, and the same SKU can be stored in multiple storage spaces; (3) the volume of a single commodity of any SKU does not exceed the maximum capacity of a single storage space, that is, a storage space can store at least one commodity of the same SKU; (4) only two batches of commodities, new and old, are distinguished, the SKU of the new batch of commodities to be allocated to a storage space is the new batch, and the SKU stored in the storage space is the old batch, and the new and old batches can both include multiple SKUs; (5) the number of commodities of each SKU in the new and old batches is known, so the number of storage spaces required for each SKU in the new batch is known information; (6) the storage location information of all SKUs in the old batch is known; (7) for the same SKU, both the new and old batches can exist at the same time, but the storage spaces of the two batches are not allowed to be combined; (8) the total number of storage spaces must meet the requirement of the number of storage spaces required for each SKU in the new and old batches; (9) the picking personnel can obtain the storage location of the target commodity in real time through the information system, and the cost of personnel familiar with the location of the commodity is not considered, that is, only the carrying distance is considered when calculating the picking and relocation cost; (10) the storage height of a single storage space does not exceed the reachable range of the standing staff, that is, no vertical movement occurs when working at the storage space, and the plane polyline distance is used when calculating the distance; (11) the personnel always walk in the center of each aisle, and can directly access the storage spaces on both sides in the same longitudinal aisle without plane movement; (12) when making a decision, the commodity out-of-warehouse frequency parameter F s and the association degree between commodities are known parameters; in the present embodiment, the target function for allocating storage spaces considering the commodity out-of-warehouse frequency is constructed : , the target function for allocating storage spaces considering the association relationship between commodities is constructed : , and the target function considering the relocation cost is constructed : ; the corresponding constraint conditions are set as follows: 1, the constraint of the number of storage spaces storing each SKU commodity is: ; 2, each storage space stores only a single SKU, and the constraint is: ; 3, each old batch storage space must be and can only be relocated to a target storage space, and the constraint is: ; 4, relocation conflict avoidance constraint: when the old batch s old is relocated from the original storage space to a new target storage space (When not at the original location) target location It must not be occupied by any SKU, and the constraint is: 5. Adjacent Allocation Constraint within the Same Cargo Lane: Different locations of the same product are preferentially allocated consecutively within a single cargo lane. The constraint formula is as follows: 6. Adjacent Allocation Constraint Across Lanes: When the available storage spaces in a single lane are insufficient to meet the storage requirements of goods, continuous allocation is performed across adjacent lanes (⌈⋅⌉ indicates rounding up). The constraint formula is: In this embodiment, the storage location allocation mathematical model is a multi-objective optimization model. Solving the multi-objective model requires considering factors such as the frequency of goods leaving the warehouse, the correlation between goods, and the transfer distance, so that each objective function moves towards the optimal direction within a certain range to achieve the optimal overall objective. In this embodiment, weights are assigned to the three objective functions, and a scalarization method is used to transform the multi-objective optimization model of the storage location allocation model into a single-objective optimization model. The objective function expression is as follows: minF=θ1minf1+θ2minf2+θ3minf3,θ1+θ2+θ3=1,θ1,θ2,θ3∈(0,1). In this embodiment, minF is used as the corresponding objective fitness function, and the objective value of the objective fitness function is used as the corresponding fitness value. In this embodiment, I represents the set of lane indices, I={1,2,…,N}, P represents the set of storage location indices, P={1,2,…,M}, and N represents the total number of lanes. M represents the number of cargo bays per single cargo bay. i, Both represent a channel index, i, ∈I; Each represents a location index, p. ∈P; Let S represent the p-th storage location in the i-th aisle, and let S represent the product SKU code set, S={1,2,…,s}. Both represent a SKU code, s, ;Num s S represents the total number of storage locations required to store one 's'; old S represents the set of SKUs from the old batch. old ∈S;s old This represents an old batch of s, s old ∈S old L old L represents the set of original storage locations occupied by the old batch. old = ;F s This indicates the frequency of outbound shipments of s; Indicates s and The degree of correlation between them ∈ [0, 1], h represents the storage height limit of the storage location; h1 represents the width of the picking channel; h2 represents the width of the storage channel; h3 represents the width of the storage location; h4 represents the width of the cross channel; represents the storage location and the distance between the storage location represents the storage location and the distance between the storage location represents the storage location and the distance between the storage location represents the storage location and the distance 1 (via the cross channel near the access end) between the storage location represents the storage location and the distance 2 (via the cross channel far from the access end) between the storage location is a decision variable, representing when the s is stored in the storage location , 0 otherwise; is a decision variable, representing when the old batch s old is moved from the original storage location to the target storage location , 0 otherwise.

[0079] Through the above steps 71 to 73, the storage location allocation information planning based on the replenishment batch arrival is realized, so as to improve the picking efficiency during the picking operation through the planned storage location allocation information, and the total picking operation time is minimized.

[0080] In some embodiments, after generating a plurality of double-layer coded individuals, the following steps are further implemented:

[0081] Step 81, tournament selection operation is performed on the plurality of double-layer coded individuals to obtain a plurality of candidate double-layer coded individuals.

[0082] In this embodiment, the tournament selection operator is adopted, and the double-layer coded individual with higher fitness (calculated according to the corresponding target fitness function) is selected as the parent through random competition. k double-layer coded individuals are randomly selected from the population, their fitness is compared, and the double-layer coded individual with the highest fitness is selected as the parent. The process is repeated until a sufficient number of parent individuals are selected, and a plurality of candidate double-layer coded individuals are obtained. In this embodiment, by adjusting the tournament size k, the selection pressure can be flexibly controlled: when k is large, the selection pressure is large, and the probability of selecting excellent individuals is high; when k is small, the selection pressure is small, and the population diversity is good.

[0083] ​Step 82, randomly selecting any two alternative bin sub-codes from the plurality of alternative double-layer coding individual bin sub-codes as an intended bin sub-code group, and selecting at least two target SKU corresponding bin codes from all bin codes corresponding to the two alternative bin sub-codes of the intended bin sub-code group, then performing cross and bin conflict correction on the selected bin codes from the corresponding two alternative bin sub-codes to generate two corresponding first bin sub-codes, and updating the corresponding transfer bin code of the bin code that has been moved in the bin conflict correction.

[0084] In some optional embodiments, with reference to Figure 12 The cross and bin conflict correction on the selected bin codes from the corresponding two alternative bin sub-codes to generate two corresponding first bin sub-codes is achieved by the following steps:

[0085] Step 821, respectively determining the first cross bin code and the second cross bin code from the selected bin codes from the two alternative bin sub-codes, and determining the coding bit without bin code in each alternative bin sub-code.

[0086] Step 822, determining the bin code with the same coding bit as the second cross bin code from all bin codes of the alternative bin sub-code corresponding to the first cross bin code, replacing all second cross bin codes with the determined bin code, and correcting the second cross bin code that is not on the coding bit corresponding to the first cross bin code and the coding bit without bin code to the coding bit without bin code to obtain the first bin sub-code corresponding to the alternative bin sub-code corresponding to the first cross bin code.

[0087] Step 823, determining the bin code with the same coding bit as the first cross bin code from all bin codes of the alternative bin sub-code corresponding to the second cross bin code, replacing all first cross bin codes with the determined bin code, and correcting the first cross bin code that is not on the coding bit corresponding to the second cross bin code and the coding bit without bin code to the coding bit without bin code to obtain the first bin sub-code corresponding to the alternative bin sub-code corresponding to the second cross bin code.

[0088] In the embodiment, the SKU-based adaptive crossover operator is adopted, taking SKU as the basic crossover unit, ensuring that the number of occupied storage locations for each SKU remains unchanged, and achieving adaptability through dynamic adjustment of the crossover ratio parameter c; in the embodiment, the M candidate double-layer coded individuals are randomly divided into M / 2 groups, and the candidate double-layer coded individuals in each group are paired, that is, an intended storage location sub-coding group is formed, for each group of candidate double-layer coded individuals, a part of SKUs are randomly selected for crossover according to the crossover ratio parameter c, and the parameter c is dynamically adjusted to adapt to different scales; in the embodiment, in order to ensure that the constraint condition of "each storage location storing only a single SKU" is always met, a conflict detection and repair mechanism is added in the crossover operator: when the crossover causes a storage location conflict, an idle storage location redistribution strategy is executed, and the SKU on the conflict storage location is randomly mapped to an idle storage location, after generating a new storage location code X, the transfer code Y is updated, and the transfer information of the old batch of goods is recorded.

[0089] In a specific example, it is assumed that the planar warehouse has 2 aisles, each aisle has 5 storage locations, a total of ten storage locations, SKU3 in the old batch of goods occupies two storage locations (2,1), (2,2), SKU1, SKU2, SKU3 in the new batch of goods need to be allocated 2, 3, and 1 storage locations respectively, after population initialization, two candidate double-layer coded individuals are selected from the initial double-layer coded individuals, denoted as Parent1: [X|Y]=[{1,1,2,2,2,3,3,3,0,0}|{,,,,,(2,1),(2,2),,,}] and Parent2: [X|Y]=[{3,0,0,1,1,3,3,2,2,2}|{,,,,,(2,1),(2,2),,,}], the crossover ratio parameter c is set to 1.0 for global crossover, that is, each SKU in the storage location code X of the two individuals is randomly selected for exchange, and the reference Figure 12, the specific cross process is as follows: step 1, select the cross position in the two alternative double-layer encoded individual location codes, for Parent1, select the location (1,1) of SKU1, (1,3), (1,4) of SKU2, (2,2) of SKU3; for Parent2, select (1,4) of SKU1, (2,3), (2,4) of SKU2, (1,1) of SKU3. Step 2, perform global cross based on SKU, pair Parent1 and Parent2, take each SKU as a basic cross unit, and exchange the selected locations. In this embodiment, when crossing, first take Parent1 as the individual needing cross processing, and take Parent2 as the individual providing cross units, first exchange the SKUs on the locations (1,1), (1,4), (2,3), (2,4) of Parent2 to the locations (1,1), (1,4), (2,3), (2,4) of Parent1, before exchange, the empty locations of Parent1 are (1,1), (1,3), (1,4), (2,2) (2,4) (2,5), after exchange, because the location (2,3) is not empty, the SKU2 on the location (2,3) of Parent2 conflicts with the SKU3 on the location (2,3) of Parent1, at this time, correct the SKU2 provided by Parent2 from the location (2,3) of Parent1 to the location (2,5); when taking Parent2 as the individual needing cross processing, and taking Parent1 as the individual providing cross units, first exchange the SKUs on the locations (1,1), (1,3), (1,4), (2,2) of Parent1 to the locations (1,1), (1,3), (1,4), (2,2) of Parent2, before exchange, the empty locations of Parent2 are (1,1), (1,2), (1,3), (1,4) (2,3) (2,4), after exchange, because the location (2,2) is not empty, the SKU3 on the location (2,2) of Parent1 conflicts with the SKU2 on the location (2,2) of Parent2, at this time, correct the SKU3 provided by Parent1 from the location (2,2) of Parent2 to the location (2,4), and thus two new location sub-encodings are obtained.Step 3, updating the transfer code Y: the original location (2, 2) of the SKU3 old batch in Y:Parent1 no longer stores SKU3, searching for the nearest location (2, 4) storing SKU3, updating the value of the locus corresponding to the original location in the Child1 transfer code to (2, 4), and finally obtaining two corresponding double-layer encoding individuals: Child1: [X|Y]=[{3,1,0,1,2,3,0,3,2,2}|{,,,,,(2,1),(2,4),,,};Child2: [X|Y]=[{1,0,2,2,1,3,3,0,3,2}|{,,,,,(2,1),(2,2),,,}].

[0090] Step 83, randomly selecting a set number of location codes from all location codes of all first location sub-codes, and performing crossover mutation on each group of location codes to generate a second location sub-code corresponding to each first location sub-code, and updating the transfer code corresponding to the location code that has moved in the crossover mutation to obtain the location sub-code of the double-layer encoding individual that completes the genetic evolution iteration.

[0091] In this embodiment, referring to Figure 13 , an adaptive local mutation strategy is adopted to focus on local search and diversity maintenance. First, a slight mutation is performed with an initial probability p mo =0.1 to randomly exchange the values of two loci in the individual location code X, and then update the transfer code Y.

[0092] To obtain the target parameters corresponding to the replenishment SKU, in some embodiments, the commodity out-of-warehouse frequency parameters and commodity correlation parameters corresponding to the first SKU and the second SKU are determined by a predetermined statistical method, including the following steps:

[0093] Step 91, using one-hot encoding to construct a matrix of a plurality of historical order data and a third SKU required by the historical order data, generating an order commodity correlation matrix with historical order data as rows and SKUs as columns.

[0094] In this embodiment, one-hot encoding is used to represent the demand for commodity SKUs in different historical orders, and an order commodity correlation matrix is constructed with order names and commodity SKUs in historical orders, as shown in Figure 14 .

[0095] Step 92, calculating the out-of-warehouse frequency vector corresponding to the order commodity correlation matrix, and detecting the out-of-warehouse frequency vector value of the third SKU corresponding to the first SKU and the second SKU in the out-of-warehouse frequency vector to obtain the corresponding commodity out-of-warehouse frequency parameter.

[0096] In the embodiment, based on the commodity outbound frequency vector F=(f i ) 1×K , the corresponding outbound frequency is determined, wherein K is the total number of commodity SKUs, and the element f i is the outbound frequency of commodity i in all customer orders, and the greater the value is, the higher the outbound frequency is, and the value of f i is achieved by calculating the order and commodity relationship matrix R, and the calculation formula is: , r i is a commodity vector, that is, a column vector r i in the order and commodity relationship matrix R, which indicates which orders demand the commodity; the unit vector 1 D is a Dx1 all-1 vector.

[0097] In step 93, based on the order commodity association matrix, a commodity co-occurrence matrix is generated, and a corresponding commodity association network is generated by using the commodity co-occurrence matrix, wherein the commodity co-occurrence matrix includes a plurality of commodity association degrees, and the commodity association degree is used to represent the co-occurrence frequency of the corresponding two commodities in all historical order data, and a network graph node of the commodity association network is used to represent a corresponding SKU, and a node path of the commodity association network is used to represent the association relationship between two corresponding SKUs.

[0098] In the embodiment, in order to analyze and quantify the association relationship between commodities, a commodity combination co-occurrence matrix is constructed by counting the co-occurrence number of each two commodities in all customer orders, and a commodity association network is generated by using the co-occurrence matrix. The commodity association network is a kind of undirected weighted network, a single node in the network represents a single commodity SKU, and the total number of commodity SKUs determines the number of network nodes, the edges between nodes represent the association relationship between commodities, and the weight of the edge is the co-occurrence number of each two commodities in all orders, which means the strength of the association.

[0099] In the embodiment, based on the order and commodity relationship matrix R shown in Figure 14 , a commodity association matrix C=(c ij ) K×K is further constructed, wherein K is the total number of commodity SKUs, and the element c ij is the co-occurrence number of commodity i and commodity j in all customer orders, which represents the association degree between the two commodities, and the greater the value is, the stronger the association is, and the value of c ij is obtained by calculating the order and commodity relationship matrix R, and the calculation formula is: , r i and r j are not order vectors, but commodity vectors, that is, column vectors r i and r j, all represent which orders the goods are required; the constructed commodity correlation matrix C is as shown in reference Figure 15 In this embodiment, based on the commodity correlation matrix, a corresponding commodity correlation network can be constructed, as shown in reference Figure 16 In this embodiment, based on the commodity correlation matrix, a corresponding commodity correlation network can be constructed, as shown in reference ij In this embodiment, in order to avoid the subsequent constructed location allocation mathematical model after introducing the correlation matrix (co-occurrence matrix), the objective function is difficult to converge due to the order of magnitude difference of the co-occurrence times, and the co-occurrence times also need to be normalized to fall within the interval [0, 1], and the calculation formula of the correlation degree between commodities is obtained. , wherein the co-occurrence times directly correspond to the c ij value of the commodity correlation matrix C, and max is the co-occurrence times, which is the largest element value in the matrix C.

[0100] Step 94, detecting the node path corresponding to all first SKUs and all second SKUs in the commodity correlation network to obtain the commodity correlation degree parameters corresponding to the first SKUs and the second SKUs.

[0101] The embodiment also provides a picking path planning device for a small and medium-sized planar warehouse in a full-channel mode, which is used to implement the above-mentioned embodiments and preferred embodiments, and details have been described.

[0102] Figure 17 The structure block diagram of the picking path planning device for a small and medium-sized planar warehouse in a full-channel mode according to the embodiment of the application is as shown in reference Figure 17 The device comprises an acquisition module 171, a selection module 172, a planning module 173 and a processing module 174, wherein

[0103] ​The acquisition module 171 is configured to acquire the planned storage location allocation information before the current time after receiving a picking request for picking a plurality of picking orders, wherein the picking request comprises a picking order type and a picking SKU of the picking order, and the storage location allocation information is generated by using a genetic algorithm to plan storage location allocation of replenishment SKUs in consideration of a product shipment frequency parameter, a product correlation parameter and a relocation cost of the replenishment SKUs corresponding to the replenishment order; the selection module 172 is coupled to the acquisition module 171 and configured to select a current picking order and a corresponding target picking object from the plurality of picking orders allocated to the plurality of picking objects, and detect a plurality of target picking channels in the storage location allocation information in which the replenishment SKUs corresponding to the picking SKU associated with the current picking order are stored; the planning module 173 is coupled to the selection module 172 and configured to determine an order of entering the plurality of target picking channels based on a picking waiting time required by the target picking object to enter the target picking channel for picking, and generate a target picking path corresponding to the current picking order based on the order and a path strategy determined according to the picking order type; and the processing module 174 is coupled to the planning module 173 and configured to sequentially plan the target picking paths corresponding to the plurality of picking orders to obtain a path planning result.

[0104] The embodiment also provides an electronic device including a memory and a processor, the memory storing a computer program, and the processor being configured to execute the computer program to perform the steps in any of the above method embodiments.

[0105] Optionally, the electronic device described above can further include a transmission device connected to the processor and an input / output device connected to the processor.

[0106] Optionally, in the embodiment, the processor can be configured to execute the following steps through the computer program: S1, selecting a current picking order and a corresponding target picking object from the plurality of picking orders allocated to the plurality of picking objects, and detecting a plurality of target picking channels in the storage location allocation information in which the replenishment SKUs corresponding to the picking SKU associated with the current picking order are stored; S2, selecting a current picking order and a corresponding target picking object from the plurality of picking orders allocated to the plurality of picking objects, and detecting a plurality of target picking channels in the storage location allocation information in which the replenishment SKUs corresponding to the picking SKU associated with the current picking order are stored; S3, determining an order of entering the plurality of target picking channels based on a picking waiting time required by the target picking object to enter the target picking channel for picking, and generating a target picking path corresponding to the current picking order based on the order and a path strategy determined according to the picking order type; and S4, sequentially planning the target picking paths corresponding to the plurality of picking orders to obtain a path planning result.

[0107] In addition, in combination with the picking path planning method of the small and medium-sized flat warehouse in the full-channel mode in the above-embodiment, an embodiment of the present application can provide a storage medium for implementation. The storage medium has a computer program stored thereon; and the computer program is executed by a processor to implement any one of the picking path planning methods of the small and medium-sized flat warehouse in the full-channel mode in the above-embodiments.

[0108] The above embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it cannot be understood as a limitation on the scope of the patent application.

Claims

1. A picking route planning method for small and medium-sized planar warehouses under an omnichannel model, characterized in that, include: After receiving a picking request for picking multiple picking orders, the system obtains the planned storage location information previously available. The picking request includes the picking order type and picking SKU of the picking order. The storage location information is generated by considering the product outbound frequency parameter, product correlation parameter, and transfer cost corresponding to the replenishment SKU of the replenishment order, and by using a genetic algorithm to plan the storage location allocation for the replenishment SKU. From the multiple picking orders assigned to multiple picking objects, select the current picking order and the corresponding target picking object, and in the location allocation information, detect multiple target picking channels that store the replenishment SKU corresponding to the picking SKU associated with the current picking order; Based on the picking waiting time required for the target picking object to enter the target picking channel, the order of entering multiple target picking channels is determined sequentially, and based on the order and the path strategy determined according to the picking order type, a target picking path corresponding to the current picking order is generated. The target picking paths corresponding to multiple picking orders are planned sequentially to obtain path planning results. Specifically, based on the picking wait time required for the target picking object to enter the target picking channel, the order in which the objects enter the multiple target picking channels is determined sequentially. Based on this order and the path strategy determined according to the picking order type, a target picking path corresponding to the current picking order is generated, including: A spatiotemporal network is generated by sequentially picking multiple picking orders. The spatiotemporal network includes multiple spatiotemporal arcs corresponding to the multiple picking orders. Each spatiotemporal arc includes at least one spatiotemporal sub-arc corresponding to a corresponding spatiotemporal state. The spatiotemporal sub-arcs include picking spatiotemporal sub-arcs, waiting spatiotemporal sub-arcs, and walking spatiotemporal sub-arcs. The spatiotemporal states include walking, waiting, and picking. Based on the spatiotemporal network and the greedy strategy, the target waiting spatiotemporal sub-arcs generated when entering each of the target picking channels are determined respectively, and the target picking channel with the shortest waiting time corresponding to the target waiting spatiotemporal sub-arcs is selected to obtain the intended picking channel to be entered. The target waiting spatiotemporal sub-arcs are used to represent the spatiotemporal arc generated when the target picking object walks from the current position to the intersection channel node that serves as the target entrance and waits at the intersection channel node. The target entrance includes the channel opening closest to the current position in the corresponding entrance and exit of the intended picking channel. After generating multiple picking time-space sub-arcs and multiple walking time-space sub-arcs corresponding to picking within the designated picking channel according to the path strategy corresponding to the picking order type, the current position is taken as the end node of the last walking time-space sub-arc corresponding to the current designated picking channel. The repeated operation of selecting the next designated picking channel to be entered and the corresponding target entrance is performed to determine the next target picking channel to be entered in sequence, and to determine the order of entering multiple target picking channels. For the target picking channels determined in the aforementioned order, multiple picking time-space sub-arcs and multiple walking time-space sub-arcs located within the corresponding target picking channels are generated sequentially. The target waiting time-space sub-arcs, multiple picking time-space sub-arcs, and multiple walking time-space sub-arcs corresponding to the corresponding target picking channels are combined into the target time-space arc corresponding to the corresponding target picking channel. The picking links corresponding to the multiple target time-space arcs are synthesized into the target picking path corresponding to the current picking order.

2. The method according to claim 1, characterized in that, Selecting the current picking order and the corresponding target picking object from multiple picking orders assigned to multiple picking objects includes: after assigning multiple picking orders to multiple picking objects, determining the order in which each picking object receives the picking order, selecting the picking order with the earliest assignment order to obtain the current picking order, and taking the picking object with the earliest assignment order as the target picking object.

3. The method according to claim 1, characterized in that, The location allocation information detects multiple target picking channels that store the replenishment SKU corresponding to the picking SKU associated with the current picking order, including: The planar warehouse grid corresponding to the location allocation information is gridded into a node network, wherein the node network includes picking lanes, picking lane nodes and cross lane nodes. One picking lane node is associated with two replenishment SKUs allocated in the same picking lane. The cross lane node is used to characterize one of the entrance and exit of each picking lane. Among the replenishment SKUs associated with the picking channel nodes of all the picking channels, the replenishment SKU that is one of the picking SKUs associated with the current picking order is retrieved, and the picking channel node associated with the retrieved replenishment SKU is determined. The picking channel having at least one picking channel node is designated as the target picking channel.

4. The method according to claim 1, characterized in that, Based on the aforementioned spatiotemporal network and greedy strategy, the target waiting spatiotemporal sub-arcs generated when entering each of the target picking channels are determined, including: Based on the spatiotemporal network, determine whether each target picking channel is currently associated with the corresponding spatiotemporal arc; If it is determined that the target picking channel is not currently associated with the corresponding spatiotemporal arc, the first walking spatiotemporal sub-arc corresponding to the target picking channel that is not associated with the spatiotemporal arc is determined, and the first walking spatiotemporal sub-arc is used as the target waiting spatiotemporal sub-arc. The first walking spatiotemporal sub-arc is used to characterize that the target picking object is on the first picking link during the first walking time. The first picking link is used to characterize the physical path of the target picking object from the current position to the cross channel node corresponding to the entrance of the picking channel. The waiting time corresponding to the target waiting spatiotemporal sub-arc includes the first walking time. When it is determined that the corresponding spatiotemporal arc is currently associated with the target picking channel, the first walking spatiotemporal sub-arc and the first waiting spatiotemporal sub-arc corresponding to the target picking channel are determined, and the first walking spatiotemporal sub-arc and the first waiting spatiotemporal sub-arc are used as the target waiting spatiotemporal sub-arc. The first waiting spatiotemporal sub-arc is used to represent the target picking object waiting at the cross channel node corresponding to the entrance of the picking channel. The waiting time corresponding to the target waiting spatiotemporal sub-arc includes the corresponding first walking time and the waiting time corresponding to the first waiting spatiotemporal sub-arc.

5. The method according to claim 1, characterized in that, Generating multiple picking spatiotemporal sub-arcs and multiple walking spatiotemporal sub-arcs located within the corresponding target picking channel, including: Based on the path strategy corresponding to the picking order type, the cross-channel nodes that the target picking object passes through when entering and exiting the target picking channel are determined respectively, and the first cross-channel node and the second cross-channel node are obtained. Among all the picking channel nodes corresponding to the target picking channel, the picking channel nodes storing the picking SKU to be picked are retrieved sequentially to obtain the first channel node. After determining the node paths between the first intersecting channel node and the first first channel node, the two adjacent first channel nodes, and the last first channel node and the second intersecting channel node, the walking time of the target picking object in the corresponding node path and the corresponding node path are converted into the corresponding walking spatiotemporal sub-arcs. The node position of each first channel node and the picking time corresponding to the target picking object are converted into the corresponding picking spatiotemporal sub-arcs. According to the order, it is determined whether the target picking channel is the last target picking channel. If it is determined that the target picking channel is the last target picking channel, the walking path and corresponding walking time between the second cross channel node corresponding to the last target picking channel and the flat warehouse entrance are converted into end-point walking time-space sub-arcs, and the end-point walking time-space sub-arcs are used as one of the walking time-space sub-arcs corresponding to the last target picking channel.

6. The method according to claim 5, characterized in that, The picking order types include online picking and offline picking. Based on the path strategy corresponding to the picking order type, the cross-channel nodes traversed by the target picking object when entering and exiting the target picking channel are determined, resulting in a first cross-channel node and a second cross-channel node, including: When the picking order type is offline picking type, the path strategy is determined to be a return path strategy, and the cross channel node corresponding to the entrance of the target picking channel is respectively designated as the first cross channel node and the second cross channel node; When the picking order type is online picking, the path strategy is determined to be a combined path strategy consisting of an S-shaped path strategy and a return path strategy. After taking the entrance of the target picking channel as the first cross-channel node, the walking distance corresponding to the target picking object exiting the target picking channel from the last first channel node of the target picking channel and walking to the first first channel node of the next target picking channel is determined. The alternative exit corresponding to the shortest walking distance is taken as the second cross-channel node. The alternative exit includes one of the entrance and exit of the target picking channel.

7. The method according to claim 1, characterized in that, Before determining the order of entry into the multiple target picking channels, the method further includes: Each picking order is associated with multiple target picking channels and the order of access to those channels. Based on the order of access to those channels and the path strategy corresponding to the type of picking order, the first path for picking the corresponding object within the multiple target picking channels is determined. Based on the picking order determined by the allocation order of multiple picking orders to multiple picking objects, the order in which the picking objects corresponding to multiple picking orders enter the same target picking channel at intervals is determined, wherein multiple picking objects are not allowed to enter a target picking channel at the same time; According to the sequence, the congestion waiting time required for the picking objects to enter the corresponding target picking channel at intervals is determined. Based on the first path and the congestion waiting time corresponding to each target picking channel, the picking time and walking time required for the picking objects to be picked in the corresponding target picking channel, a spatiotemporal state association mapping is performed to generate at least an initial spatiotemporal sub-arc for picking in each target picking channel. The congestion waiting time is determined based on the picking time and walking time required for the picking objects of the previous picking order to be picked in the corresponding target picking channel. Based on the initial spatiotemporal sub-arcs corresponding to the multiple target picking channels associated with the picking order, an initial spatiotemporal arc corresponding to the picking order is generated, and based on the initial spatiotemporal arcs corresponding to the multiple picking orders respectively, the spatiotemporal network is generated.

8. The method according to claim 1, characterized in that, Before obtaining the previously planned storage location allocation information, the method further includes: Obtain multiple first SKUs associated with the first replenishment order currently awaiting replenishment and multiple second SKUs associated with the second replenishment order, and determine the target information corresponding to the first SKU and the second SKU respectively. The target information includes at least the product outbound frequency parameter and product correlation parameter determined by a preset statistical method. The target information of the second SKU also includes the original storage location information corresponding to the second SKU. Based on the target information and the corresponding target SKU, perform two-layer coding and initialization for cargo location allocation, and generate multiple two-layer coded individuals; Using a preset genetic algorithm and a target fitness function, a preset genetic evolution operation and evolution iteration are performed on the location sub-code body of the double-layer coded individual. Based on the location sub-code body that has completed the corresponding genetic evolution operation, the transfer code of the corresponding transfer sub-code body of the double-layer coded individual is updated until a target double-layer coded body corresponding to the current replenishment order is obtained. The location allocation information is then decoded from the location sub-code body corresponding to the target double-layer coded body. The target fitness function is constructed based on the commodity outbound frequency parameter and commodity correlation parameter associated with the location code of the corresponding location sub-code body, as well as the transfer cost associated with the corresponding transfer code. The location code is used to represent the location arrangement for a target SKU, and the transfer code is used to represent a change in location arrangement.

9. The method according to claim 8, characterized in that, After generating multiple two-layer coded individuals, the method includes: A tournament selection operation is performed on multiple dual-layer encoded individuals to obtain multiple candidate dual-layer encoded individuals; From the multiple candidate double-layer coding individuals' location sub-code bodies, randomly select any two candidate location sub-code bodies as the intended location sub-code body group. Then, from all the location codes corresponding to the two candidate location sub-code bodies in the intended location sub-code body group, select the location codes corresponding to at least two target SKUs. Then, perform cross-checking and location conflict correction on the location codes selected from the corresponding two candidate location sub-code bodies to generate two corresponding first location sub-code bodies. Update the transfer code corresponding to the location code that has been moved during the location conflict correction. From all the location codes of all the first location sub-code bodies, a set number of location codes are randomly selected, and each set of location codes is subjected to exchange mutation to generate a second location sub-code body corresponding to each first location sub-code body. The location codes corresponding to the location codes that have moved during the exchange mutation are updated to obtain the location sub-code bodies of the two-layer coding individuals that have completed the current genetic evolution iteration. The set number of groups is calculated based on the dynamic mutation probability corresponding to the adaptive local mutation strategy.

10. The method according to claim 9, characterized in that, The location codes selected from the two corresponding candidate location sub-code bodies are cross-referenced and location conflict corrections are performed to generate two corresponding first location sub-code bodies, including: The location codes selected from the two candidate location sub-code bodies are determined respectively to obtain the first cross location code and the second cross location code, and the code bits in each candidate location sub-code body that do not have the location code are determined. Among all the location codes in the candidate location sub-code body corresponding to the first cross location code, the location code that has the same coding position as the second cross location code is determined, and all the second cross location codes are replaced with the determined location codes. The second cross location codes that are not in the coding position corresponding to the first cross location code and the coding position that do not have the location code are corrected to the coding position that does not have the location code, so as to obtain the first location sub-code body corresponding to the candidate location sub-code body corresponding to the first cross location code. Among all the location codes in the candidate location sub-code body corresponding to the second cross location code, the location code that has the same coding position as the first cross location code is determined, and all the first cross location codes are replaced with the determined location codes. The first cross location codes that are not in the coding position corresponding to the second cross location code or do not have the location code are corrected to the coding position that does not have the location code, so as to obtain the first location sub-code body corresponding to the candidate location sub-code body corresponding to the second cross location code.

11. The method according to claim 8, characterized in that, According to a preset statistical method, determine the product outbound frequency parameters and product correlation parameters corresponding to the first SKU and the second SKU, including: One-hot encoding is used to construct a matrix of multiple historical order data and the third SKU required by the historical order data, generating an order product association matrix with historical order data as rows and SKU as columns; Calculate the outbound frequency vector corresponding to the order product association matrix, and detect the outbound frequency vector value of the third SKU corresponding to the first SKU and the second SKU in the outbound frequency vector to obtain the corresponding product outbound frequency parameter; Based on the order product association matrix, a product co-occurrence matrix is ​​generated, and a corresponding product association network is generated using the product co-occurrence matrix. The product co-occurrence matrix includes multiple product association degrees, which are used to characterize the co-occurrence frequency of two corresponding products in all historical order data. A network graph node of the product association network is used to characterize a corresponding SKU, and a node path of the product association network is used to characterize the association relationship between two corresponding SKUs. In the product association network, the node paths corresponding to all first SKUs and all second SKUs are detected to obtain the product association parameters corresponding to the first SKUs and the second SKUs.

Images