Palletizing method and device

Abstract

The present invention discloses a palletizing method and device, and relates to the field of computer technology. The method comprises: i) selecting a current stacking item from all the items to be stacked, and then constructing a candidate stacking corner point set of the current stacking item; ii) evaluating the stacking effect of each candidate stacking corner point in the candidate stacking corner point set, so as to determine the stacking corner point of the current stacking item according to the evaluation result; iii) repeatedly executing steps i) to ii) until the stacking corner points of all items are obtained; iv) after the stacking corner points of all items are obtained, generating a palletizing type. Through the above steps, the pallet type of mixed palletizing can be automatically generated, and the effect of mixed palletizing can be improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a palletizing method and device. Background Art

[0002] Palletizing is widely used in manufacturing, warehousing and logistics industries. It usually refers to stacking containers on pallets in a certain stacking pattern. Due to business needs, sometimes containers of different types need to be stacked on the same pallet, which is called mixed palletizing.

[0003] In the existing mixed palletizing methods, most of them first determine the mixed palletizing type based on manual experience, and then stack the goods according to the pallet type.

[0004] In the process of realizing the present invention, the inventors found that there are at least the following problems in the prior art: the existing mixed palletizing method requires high palletizing experience of the operators, and the effect of mixed palletizing often depends on the amount of manual experience. Summary of the invention

[0005] In view of this, the present invention provides a palletizing method and device, which can automatically generate a mixed palletizing shape and improve the effect of mixed palletizing.

[0006] To achieve the above objective, according to a first aspect of the present invention, a palletizing method is provided.

[0007] The stacking method of the present invention comprises: i) selecting a current stacking item from all the items to be stacked, and then constructing a candidate stacking corner point set of the current stacking item; ii) evaluating the stacking effect of each candidate stacking corner point in the candidate stacking corner point set, so as to determine the stacking corner point of the current stacking item according to the evaluation result; iii) repeatedly executing step i) to step ii) until the stacking corner points of all the items are obtained; iv) after the stacking corner points of all the items are obtained, generating a stacking type.

[0008] Optionally, the step of constructing the candidate stacking corner point set of the currently stacked items includes: selecting candidate stacking corner points of the currently stacked items from an available corner point set of the container according to a preset placement rule to obtain the candidate stacking corner point set.

[0009] Optionally, the preset placement rule includes at least one of the following: after the current stacked item is placed at an available corner point of the container, the current stacked item cannot interfere with the stacked items on the current container; after the current stacked item is placed at an available corner point of the container, the current stacked item cannot exceed the boundary of the container; after the current stacked item is placed at an available corner point of the container, the bottom support area ratio of the current stacked item is greater than or equal to a preset threshold.

[0010] Optionally, the method further includes: when the candidate stacking corner point set is empty, opening a new empty container, and using a designated position of the empty container as a stacking corner point of the currently stacked item.

[0011] Optionally, the method further comprises: after determining the stacking corner points of the currently stacked items and before repeatedly executing step i) to step ii), updating the available corner point set of the container.

[0012] Optionally, the step of updating the available corner point set of the container includes: deleting the stacking corner points of the current stacked items from the available corner point set; deleting the corner points covered by the current stacked items from the available corner point set; adding new corner points generated after placing the current stacked items to the available corner point set; and deleting duplicate corner points in the available corner point set.

[0013] Optionally, the method further comprises: determining a stacking order of the objects according to a preset sorting rule, so as to select a currently stacked object from all the objects to be stacked according to the stacking order.

[0014] Optionally, the preset sorting rules include: arranging in descending order according to the volume of the items, and arranging in descending order according to the height of the items when the volumes are the same; or, arranging in descending order according to the bottom area of ​​the items, and arranging in descending order according to the height of the items when the bottom areas are the same; or, arranging in descending order according to the maximum dimensions of the three sides of the items.

[0015] Optionally, the palletizing pattern includes: a correspondence between items and containers; the method further includes: changing the correspondence between the items and containers according to a neighborhood generation strategy to obtain a new set of items corresponding to each container; after obtaining the stacking corner points of each item in the new set of items, generating a new palletizing pattern; evaluating the quality of the new palletizing pattern, and determining whether to update the current optimized palletizing pattern based on the evaluation result; and when the optimization stop condition is reached, using the current optimized palletizing pattern as the final palletizing pattern.

[0016] To achieve the above objective, according to a second aspect of the present invention, another palletizing method is provided.

[0017] The stacking method of the present invention comprises: i) constructing a candidate stacking corner point set of all items to be stacked; ii) evaluating the stacking effect of each candidate stacking corner point in the candidate stacking corner point set, so as to determine the current stacking item and the stacking corner point of the current stacking item according to the evaluation result; iii) repeatedly executing step i) to step ii) until the stacking corner points of all items are obtained; iv) after the stacking corner points of all items are obtained, generating a stacking type.

[0018] To achieve the above objective, according to a third aspect of the present invention, a palletizing device is provided.

[0019] The stacking device of the present invention comprises: a construction module, which is used to select the current stacking item from all the items to be stacked, and then construct a candidate stacking corner point set of the current stacking item; a determination module, which is used to evaluate the stacking effect of each candidate stacking corner point in the candidate stacking corner point set, so as to determine the stacking corner point of the current stacking item according to the evaluation result; repeatedly calling the construction module and the determination module until the stacking corner points of all the items are obtained; and a generation module, which is used to generate a stacking type after the stacking corner points of all the items are obtained.

[0020] Optionally, the constructing module constructing the candidate stacking corner point set of the currently stacked items includes: the constructing module selecting the candidate stacking corner points of the currently stacked items from the available corner point set of the container according to a preset placement rule to obtain the candidate stacking corner point set.

[0021] Optionally, the determination module is further configured to: when the candidate stacking corner point set is empty, the determination module opens a new empty container and uses a designated position of the empty container as a stacking corner point of the currently stacked item.

[0022] Optionally, the device further comprises: an updating module, configured to update an available corner point set of a container after the determining module determines the stacking corner points of the currently stacked items and before repeatedly calling the building module and the determining module.

[0023] Optionally, the update module updates the available corner point set of the container, including: the update module deleting the stacking corner points of the current stacked items from the available corner point set; the update module deleting the corner points covered by the current stacked items from the available corner point set; the update module adding new corner points generated after placing the current stacked items to the available corner point set; the update module deleting duplicate corner points in the available corner point set.

[0024] Optionally, the device further comprises: a sorting module, configured to determine a stacking order of the objects according to a preset sorting rule, so that the construction module selects a currently stacked object from all the objects to be stacked according to the stacking order.

[0025] Optionally, the palletizing pattern includes: a correspondence between items and containers; the device also includes: an optimization module, used to change the correspondence between the items and containers according to a neighborhood generation strategy to obtain a new set of items corresponding to each container; and also used to generate a new palletizing pattern after obtaining the stacking corner points of each item in the new set of items; and also used to evaluate the quality of the new palletizing pattern and determine whether to update the current optimized palletizing pattern based on the evaluation result; and also used to use the current optimized palletizing pattern as the final palletizing pattern when the optimization stop condition is reached.

[0026] To achieve the above objective, according to a fourth aspect of the present invention, another palletizing device is provided.

[0027] The stacking device of the present invention comprises: a construction module, which is used to construct a candidate stacking corner point set of all items to be stacked; a determination module, which is used to evaluate the stacking effect of each candidate stacking corner point in the candidate stacking corner point set, so as to determine the current stacking item and the stacking corner point of the current stacking item according to the evaluation result; repeatedly calling the construction module and the determination module to obtain the stacking corner points of all items; and a generation module, which is used to generate a stacking type after obtaining the stacking corner points of all items.

[0028] To achieve the above objective, according to a fifth aspect of the present invention, an electronic device is provided.

[0029] The electronic device of the present invention comprises: one or more processors; and a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the palletizing method of the present invention.

[0030] To achieve the above objective, according to a sixth aspect of the present invention, a computer readable medium is provided.

[0031] The computer readable medium of the present invention stores a computer program thereon, and when the program is executed by a processor, the palletizing method of the present invention is implemented.

[0032] An embodiment of the above invention has the following advantages or beneficial effects: by repeatedly executing step i) to step ii), specifically including: selecting the current stacked item from all the items to be stacked, and then constructing a set of candidate stacking corner points of the current stacked item; evaluating the stacking effect of each candidate stacking corner point in the set of candidate stacking corner points, so as to determine the stacking corner point of the current stacked item according to the evaluation result, and being able to automatically generate a mixed stacking type and improve the mixed stacking effect.

[0033] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0035] Figure 1 is a schematic diagram of the main process of a palletizing method according to an embodiment of the present invention;

[0036] Figure 2 is a schematic diagram of the main process of a palletizing method according to another embodiment of the present invention;

[0037] Figure 3 is a schematic diagram of spatial expression of mixed palletizing according to an embodiment of the present invention;

[0038] Figure 4 is a two-dimensional schematic diagram of the remaining space of the corner point according to an embodiment of the present invention;

[0039] Figure 5 is a schematic diagram of the main process of a palletizing method according to yet another embodiment of the present invention;

[0040] Figure 6 is a schematic diagram of main modules of a palletizing device according to one embodiment of the present invention;

[0041] Figure 7 is a schematic diagram of main modules of a palletizing device according to another embodiment of the present invention;

[0042] Figure 8 is a schematic diagram of main modules of a palletizing device according to yet another embodiment of the present invention;

[0043] Fig. 9 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0044] Fig.10 It is a schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0046] It should be pointed out that the embodiments of the present invention and the features in the embodiments may be combined with each other if there is no conflict.

[0047] Figure 1Schematic diagram of the main process of a palletizing method according to an embodiment of the present invention. Figure 1 As shown, the palletizing method of the embodiment of the present invention includes:

[0048] Step S101: Select a currently stacked object from all the objects to be stacked, and then construct a candidate stacking corner point set of the currently stacked object.

[0049] The candidate stacking corner point set can be understood as a set of position points in a container where items can be placed. For example, assuming that there are 20 boxes in total, 5 boxes have been stacked on the pallet, and the remaining 15 boxes are items to be stacked, and box A is selected from the remaining 15 boxes as the current stacking item. Further, the candidate stacking corner point set of box A can be {candidate stacking corner point 1, candidate stacking corner point 2, candidate stacking corner point 3}.

[0050] Step S102: Evaluate the stacking effect of each candidate stacking corner point in the candidate stacking corner point set to determine the stacking corner point of the current stacked item according to the evaluation result.

[0051] Step S103, determine whether the stacking corner points of all items are obtained. If yes, execute step S104; if not, repeat step S101 to step S102 until the stacking corner points of all items are obtained.

[0052] Step S104, generating a palletizing pattern. The palletizing pattern may include: the correspondence between items and containers, and the stacking corners of items. Exemplarily, the correspondence between items and containers includes: pallet 1 corresponds to items A, B, C, D, E; pallet 2 corresponds to items F, G, H, I; the stacking corners of items include: the stacking corner of item A (0, 0, 0), the stacking corner of item B (3, 4, 5), etc.

[0053] In the embodiment of the present invention, the above steps can automatically generate the mixed palletizing type, reduce the requirements for manual experience in mixed palletizing, improve the efficiency of mixed palletizing, and improve the effect of mixed palletizing. Furthermore, the palletizing method of the embodiment of the present invention can also be applied to the scenarios of manual palletizing palletizing type recommendation and palletizing guidance, or to the scenarios of machine palletizing palletizing type generation and cargo box positioning, so as to improve the intelligence and automation level of mixed palletizing.

[0054] Figure 2 FIG. 1 is a schematic diagram of the main process of a palletizing method according to another embodiment of the present invention. Figure 2 As shown, the palletizing method of the embodiment of the present invention includes:

[0055] Step S201, determine the stacking order of the items according to a preset sorting rule. The preset sorting rule is to determine the stacking order of the items according to a certain standard. For example, Table 1 shows several optional sorting rules.

[0056] Table 1

[0057]

[0058] For example, suppose item A has a height of 0.5m and a volume of 0.01m 3 , the height of object B is 0.4m and the volume is 0.024m 3 , the height of object C is 0.3m and the volume is 0.006m 3 According to the sorting rule Volume-Height in Table 1, the order of stacking items is: stack item B first, then item A, and finally item C.

[0059] Step S202: selecting a currently stacked item from all the items to be stacked according to the stacking order.

[0060] For example, assume that the stacking order of items is: first stack item B, then stack item A, and finally stack item C. In the first stacking, the items to be stacked are item A, item B, and item C, and the current stacking item is item B; in the second stacking, the items to be stacked are item A and item C, and the current stacking item is item A; in the third stacking, the item to be stacked is item C, and the current stacking item is item C.

[0061] Step S203: selecting candidate stacking corner points for the currently stacked items from the available corner point set of the container according to a preset placement rule to obtain a candidate stacking corner point set.

[0062] Exemplarily, the container may be a tray.

[0063] Exemplarily, the preset placement rule includes at least one of the following: a) after the current stacked item is placed at an available corner point of the container, the current stacked item cannot interfere with the stacked items on the current container; b) after the current stacked item is placed at an available corner point of the container, the current stacked item cannot exceed the boundary of the container; c) after the current stacked item is placed at an available corner point of the container, the bottom support area ratio of the current stacked item is greater than or equal to a preset threshold. The bottom support area ratio can be understood as "the ratio of the support area provided by the container or other stacked items for the current stacked item to the bottom area of ​​the current stacked item". In specific implementation, the preset threshold can be flexibly set according to demand. For example, the preset threshold can be set to 0.8.

[0064] It should be noted that step S203 is mainly for the second to the last stacking of items. When stacking items for the first time, the first item can be stacked at a designated position on the pallet, such as Figure 3 The coordinate origin is shown in FIG. 1 . In addition, in the specific implementation, the following constraints can be made: the currently stacked items are allowed to rotate at right angles in the horizontal plane (XY plane), and the height plane of the currently stacked items is not allowed to change. For example, the three-sided dimensions of the cargo box are: length 0.4m (X direction), width 0.3m (Y direction), and height 0.5m (Z direction). By rotating the cargo box in the horizontal plane, the three-sided dimensions of the cargo box can be changed to: length 0.3m (X direction), width 0.4m (Y direction), and height 0.5m (Z direction).

[0065] Step S204: Determine whether the candidate stacking corner point set is empty. If not, execute step S205; if yes, execute step S206.

[0066] Step S205: Evaluate the stacking effect of each candidate stacking corner point in the candidate stacking corner point set to determine the stacking corner point of the current stacked item according to the evaluation result.

[0067] In an optional implementation, the stacking effect of each candidate stacking corner point can be evaluated according to the first effect function. The first effect function reflects the impact of the current stacking items placed at a candidate stacking corner point on the overall stacking shape. In specific implementation, the first effect function can be in the following form:

[0068]

[0069] Among them, epX and epY represent the horizontal and vertical coordinates of the candidate stacking corner points; itemX and itemY represent the length and width of the current stacked item; envW and envD represent the length and width of the smallest cuboid that can accommodate all the stacked items in the container (excluding the current stacked item); W represents the length of the container; D represents the width of the container; Max(0,epX+itemX-envW) means taking the maximum value from 0 and epX+itemX-envW; Max(0,epY+itemY-envD) means taking the maximum value from 0 and epY+itemY-envD.

[0070] in, and It reflects the degree of expansion of the envelope of the minimum cuboid after the current stacked item is placed at a certain candidate stacking corner point. After calculating the function value corresponding to each candidate stacking corner point through the first effect function, the candidate stacking corner point with the smallest function value can be used as the stacking corner point of the current stacked item. That is, try to select the candidate stacking corner point with the smallest expansion degree of the envelope of the minimum cuboid.

[0071] In another optional implementation, the stacking effect of each candidate stacking corner point can be evaluated according to the second effect function, and then the corner point with the largest function value can be selected. The second effect function reflects the degree of utilization of the remaining space of a candidate stacking corner point when the current stacked items are placed at the candidate stacking corner point. In specific implementation, the second effect function can be in the following form:

[0072] SUM(rsX-itemX,rsY-itemY,rsZ-itemZ)

[0073] Among them, rsX, rsY, and rsZ represent the three-sided dimensions of the remaining space of a candidate stacking corner point; itemX, itemY, and itemZ represent the three-sided dimensions of the current stacked items; SUM(rsX-itemX,rsY-itemY,rsZ-itemZ) represents the sum of rsX-itemX, rsY-itemY, and rsZ-itemZ.

[0074] After calculating the function value corresponding to each candidate stacking corner point through the second effect function, the candidate stacking corner point with the largest function value can be used as the stacking corner point for the current stacked items. That is, try to select the candidate stacking corner point with the highest utilization rate of the remaining space.

[0075] Step S206: opening a new empty container, and using the designated position of the empty container as the stacking corner point of the currently stacked items.

[0076] The specified location may be Figure 3 After step S205 or step S206, step S207 may be performed.

[0077] Step S207: Determine whether the stacking corners of all items are obtained. If yes, execute step S208; if not, execute step S209.

[0078] Step S208: Generate a palletizing pattern.

[0079] The stacking pattern may include: the correspondence between items and containers, and the stacking corners of items. For example, the correspondence between items and containers includes: pallet 1 corresponds to items A, B, C, D, E; pallet 2 corresponds to items F, G, H, I; the stacking corners of items include: the stacking corner of item A (0, 0, 0), the stacking corner of item B (3, 4, 5), etc.

[0080] Step S209: Update the available corner point set of the container.

[0081] This step specifically includes: 1) deleting the stacking corner points of the current stacked items from the available corner point set of the container; 2) deleting the corner points covered by the current stacked items from the available corner point set; 3) adding new corner points generated after placing the current stacked items to the available corner point set; 4) deleting duplicate corner points in the available corner point set.

[0082] After step S209, steps S201 to S207 are repeatedly executed until the stacking corner points of all the objects are obtained.

[0083] Furthermore, after step S208, the palletizing method of the embodiment of the present invention may further include the following steps: optimizing the palletizing type.

[0084] Specifically, the optimization of the palletizing type includes:

[0085] Step A: changing the correspondence between the items and containers according to the neighborhood generation strategy to obtain a new set of items corresponding to each container.

[0086] In this step, a neighborhood generation strategy such as a genetic algorithm and a taboo search may be used to perform operations such as exchanging, adding, and subtracting items stacked on multiple containers (such as pallets) to obtain a new set of items corresponding to each container.

[0087] Step B: after obtaining the stacking corner point of each item in the new item set, a new stacking pattern is generated.

[0088] In this step, the new items can be centrally executed Figure 2 The steps shown are used to obtain the stacking corner points of each item and then generate a new stacking pattern.

[0089] Step C, evaluating the quality of the new palletizing pattern, and determining whether to update the current optimized palletizing pattern according to the evaluation result;

[0090] In this step, the quality of the palletizing pattern can be calculated by quantitative indicators. If the quality of the new palletizing pattern is higher than the quality of the original palletizing pattern, the current optimized palletizing pattern is updated; if the quality of the new palletizing pattern is less than or equal to the quality of the original palletizing pattern, the current optimized palletizing pattern is not updated. Repeat steps A to C until the optimization stop condition is reached.

[0091] Step D: when the optimization stop condition is reached, the current optimized pallet type is used as the final palletizing type.

[0092] The optimization stop condition may be a calculation time or a lower limit value of an acceptable stack quality.

[0093] In the embodiment of the present invention, the above steps can automatically generate the mixed palletizing type, reduce the requirements for manual experience in mixed palletizing, improve the efficiency of mixed palletizing, and improve the effect of mixed palletizing. Furthermore, the palletizing method of the embodiment of the present invention can also be applied to the scenarios of manual palletizing palletizing type recommendation and palletizing guidance, or to the scenarios of machine palletizing palletizing type generation and cargo box positioning, so as to improve the intelligence and automation level of mixed palletizing.

[0094] Combine the following Figure 3 right Figure 2 Step S209 in the illustrated embodiment is further explained. Figure 3 Schematic diagram of the spatial expression of mixed palletizing according to an embodiment of the present invention. Figure 3 As shown, assuming that the pallet is placed flat on the bottom surface, a three-dimensional rectangular coordinate system is established with the left-rear point on the upper surface of the pallet as the origin. Rays are emitted from the origin to the X-axis, Y-axis, and Z-axis until the boundaries of the pallet, and the enclosed space is the initial available volume of the pallet.

[0095] Among them, "available corner points" can be understood as points in the pallet space that can be used to place new boxes. When placing the first box on the pallet, place the first box at a specified location, such as the origin. After the first box is placed on the pallet, the corner point (0, 0, 0) is occupied, but three new corner points are generated, namely Figure 3 The left part shows corner points 1, 2, and 3. Therefore, when the second box is placed on the pallet, the set of available corner points of the pallet is updated to {corner point 1, corner point 2, corner point 3}.

[0096] More generally, if Figure 3 As shown in the right part, suppose the Kth box is placed at a corner point C on the pallet. At this time, a new corner point can be generated as follows:

[0097] 1) Zup point is a newly generated corner point.

[0098] 2) Emit rays from the Zdown point in the negative direction of the Z axis until it reaches the surface of the pallet or contacts the upper surface of the nearest container. If the contact point does not coincide with the Zdown point, then this contact point is a newly generated corner point.

[0099] 3) Emit rays from three points of the current stacked container (the left-rear-upper point, left-front-lower point, and right-rear-lower point of the current stacked container), namely Zx, Zy, Yx, Yz, Xy, and Xz. Among them, Xz and Yz are rays emitted in the negative direction of the Z axis until they contact the edge of the pallet or the nearest container surface. The two contact points generated are newly generated corner points. Zx, Zy, Yx, and Xy are rays emitted horizontally in the corresponding directions until they contact the edge of the pallet or the nearest container surface. If the contact point generated by this has support in the height direction (that is, the contact point is located on the bottom surface of the pallet or the top surface of the container), then the contact point is a newly generated corner point; otherwise, the contact point needs to be moved vertically to the negative direction of the Z axis until the condition of "the contact point has support in the height direction" is met. The contact point after vertical movement is the newly generated corner point.

[0100] According to steps 1), 2), and 3) Figure 3 Analyzing the special case on the left, we can get: Figure 3 Point 3 on the left is equivalent to Zup, which is a newly generated corner point. The contact point generated by emitting rays from point Zdown to the negative direction of the Z axis coincides with point Zdown, so it cannot be used as a new corner point. The contact points generated by rays Xy, Xz, Yx, Yz, Zx, and Zy from point 1, point 2, and point 3 are point 1, point 2, and point 3 themselves. Therefore, after deleting the duplicate corner points, Figure 3 The available corner points of the left portion shown are point 1, point 2, and point 3.

[0101] Combine the following Figure 4 right Figure 2 The concept of "remaining space" in the illustrated embodiment is further explained. Figure 4 is a two-dimensional schematic diagram of the remaining space of the corner points according to an embodiment of the present invention. Figure 4 As shown in the figure, the gray area on the left is the current remaining space of corner point 2. When a box is placed, the remaining space of corner point 2 after update is as follows: Figure 4 The right part is shown in the gray area.

[0102] More generally, the remaining space of the corner point can be defined as follows: starting from the corner point, emitting rays along the X-axis, Y-axis, and Z-axis until reaching the pallet boundary or the container surface, the rectangular space enclosed by these three rays is the remaining space of the corner point. When using the second effect function for evaluation, since the new container will interfere with the remaining space of the existing corner point after being stacked, it is necessary to update not only the set of available corner points but also the remaining space of the corner point after placing the new container.

[0103] Figure 5 FIG. 1 is a schematic diagram of the main process of a palletizing method according to another embodiment of the present invention. Figure 5As shown, the palletizing method of the embodiment of the present invention includes:

[0104] Step S501: construct a candidate stacking corner point set for all objects to be stacked.

[0105] The candidate stacking corner point set can be understood as a set of position points in a container where items can be placed. For example, assuming that there are 10 boxes in total, 5 boxes have been stacked on the pallet, and the remaining 5 boxes are the items to be stacked, namely box A, box B, box C, box D, and box E. Further, the candidate stacking corner point set of the five boxes A to E can be: {candidate stacking corner point 1, candidate stacking corner point 2, candidate stacking corner point 3}.

[0106] Step S502: Evaluate the stacking effect of each candidate stacking corner point in the candidate stacking corner point set to determine the current stacked item and the stacking corner point of the current stacked item according to the evaluation result.

[0107] Step S503: determine whether the stacking corners of all items are obtained. If yes, execute step S504; if no, repeat steps S501 to S502 until the stacking corners of all items are obtained.

[0108] Step S504: Generate a palletizing pattern.

[0109] Figure 5 The embodiment shown and Figure 1 The main differences of the shown embodiments are: Figure 5 The embodiment shown adopts "dynamic sorting", that is, all combinations of candidate stacking corner points are compared for all items to be stacked, and the best combination is selected by calculating the effect function to determine the stacking corner points of the current stacking item and the current stacking item; Figure 1 The illustrated embodiment adopts "static sorting", that is, first determining the current stacked items, and then selecting the optimal candidate stacking corner points corresponding thereto through the effect function to determine the stacking corner points of the current stacked items.

[0110] In the embodiment of the present invention, the above steps can automatically generate the mixed palletizing type, reduce the mixed palletizing requirements for manual experience, improve the efficiency of mixed palletizing, and improve the effect of mixed palletizing. Compared with the palletizing method using "static sorting", the use of "dynamic sorting" can further improve the effect of mixed palletizing.

[0111] Figure 6 Schematic diagram of the main modules of a palletizing device according to one embodiment of the present invention. Figure 6 As shown, the palletizing device 600 of the embodiment of the present invention includes: a construction module 601 , a determination module 602 , and a generation module 603 .

[0112] The construction module 601 is used to select a current stacking object from all the objects to be stacked, and then construct a candidate stacking corner point set of the current stacking object.

[0113] The candidate stacking corner point set can be understood as a set of position points in a container where items can be placed. For example, assuming that there are 20 boxes in total, 5 boxes have been stacked on the pallet, and the remaining 15 boxes are items to be stacked, and box A is selected from the remaining 15 boxes as the current stacking item. Further, the candidate stacking corner point set of box A can be {candidate stacking corner point 1, candidate stacking corner point 2, candidate stacking corner point 3}.

[0114] The determination module 602 is used to evaluate the stacking effect of each candidate stacking corner point in the candidate stacking corner point set, so as to determine the stacking corner point of the current stacked item according to the evaluation result.

[0115] When mixed palletizing is performed, it is necessary to repeatedly call the construction module 601 and the determination module 602 until the stacking corner points of all items are obtained.

[0116] The generation module 603 is used to generate a palletizing pattern after obtaining the stacking corner points of all items.

[0117] The stacking pattern may include: the correspondence between items and containers, and the stacking corners of items. For example, the correspondence between items and containers includes: pallet 1 corresponds to items A, B, C, D, E; pallet 2 corresponds to items F, G, H, I; the stacking corners of items include: the stacking corner of item A (0, 0, 0), the stacking corner of item B (3, 4, 5), etc.

[0118] In the embodiment of the present invention, the above palletizing device can automatically generate the pallet type of mixed palletizing, reduce the requirements for manual experience in mixed palletizing, improve the efficiency of mixed palletizing, and improve the effect of mixed palletizing. Furthermore, the palletizing device of the embodiment of the present invention can also be applied to the scenarios of pallet type recommendation and palletizing guidance in manual palletizing, or to the scenarios of pallet type generation and cargo box positioning in machine palletizing, so as to improve the intelligence and automation level of mixed palletizing.

[0119] Figure 7 Schematic diagram of the main modules of a palletizing device according to another embodiment of the present invention. Figure 7 As shown, the palletizing device 700 of the embodiment of the present invention includes: a sorting module 701 , a building module 702 , a determining module 703 , an updating module 704 , and a generating module 705 .

[0120] The sorting module 701 is used to determine the stacking order of the items according to a preset sorting rule.

[0121] The preset sorting rules are used to determine the stacking order of items according to certain standards. Table 1 shows several optional sorting rules. For example, assuming that the height of item A is 0.5m and the volume is 0.01m 3 , the height of object B is 0.4m and the volume is 0.024m 3 , the height of object C is 0.3m and the volume is 0.006m 3 According to the sorting rule Volume-Height in Table 1, the order of stacking items is: stack item B first, then item A, and finally item C.

[0122] The construction module 702 is used to select the current stacking object from all the to-be-stacked objects according to the stacking order, and then select the candidate stacking corner points of the current stacking object from the available corner point set of the container according to a preset placement rule to obtain a candidate stacking corner point set.

[0123] For example, assume that the stacking order of items is: first stack item B, then stack item A, and finally stack item C. In the first stacking, the items to be stacked are item A, item B, and item C, and the current stacking item is item B; in the second stacking, the items to be stacked are item A and item C, and the current stacking item is item A; in the third stacking, the item to be stacked is item C, and the current stacking item is item C.

[0124] Exemplarily, the preset placement rule includes at least one of the following: a) after the current stacked item is placed at an available corner point of the container, the current stacked item cannot interfere with the stacked items on the current container; b) after the current stacked item is placed at an available corner point of the container, the current stacked item cannot exceed the boundary of the container; c) after the current stacked item is placed at an available corner point of the container, the bottom support area ratio of the current stacked item is greater than or equal to a preset threshold. The bottom support area ratio can be understood as "the ratio of the support area provided by the container or other stacked items for the current stacked item to the bottom area of ​​the current stacked item". In specific implementation, the preset threshold can be flexibly set according to demand. For example, the preset threshold can be set to 0.8.

[0125] It should be noted that the operation of "selecting candidate stacking corner points for the current stacked items from the available corner points of the container according to the preset placement rules" performed by the construction module is mainly for the second to the last stacking of items. When stacking items for the first time, the construction module can stack the first item at the specified position of the pallet, such as Figure 3 The coordinate origin is shown.

[0126] The determination module 703 is used to evaluate the stacking effect of each candidate stacking corner point in the candidate stacking corner point set when the candidate stacking corner point set is not empty, so as to determine the stacking corner point of the current stacked item according to the evaluation result.

[0127] In an optional implementation, the determination module 703 may evaluate the stacking effect of each candidate stacking corner point according to the first effect function. The first effect function reflects the effect of the current stacked items placed at a candidate stacking corner point on the overall stacking shape. In specific implementation, the first effect function may be in the following form:

[0128]

[0129] Among them, epX and epY represent the horizontal and vertical coordinates of the candidate stacking corner points; itemX and itemY represent the length and width of the current stacked item; envW and envD represent the length and width of the smallest cuboid that can accommodate all the stacked items in the container (excluding the current stacked item); W represents the length of the container; D represents the width of the container; Max(0,epX+itemX-envW) means taking the maximum value from 0 and epX+itemX-envW; Max(0,epY+itemY-envD) means taking the maximum value from 0 and epY+itemY-envD.

[0130] in, and It reflects the degree of expansion of the envelope of the minimum cuboid after the current stacked item is placed at a certain candidate stacking corner point. After calculating the function value corresponding to each candidate stacking corner point through the first effect function, the candidate stacking corner point with the smallest function value can be used as the stacking corner point of the current stacked item. That is, try to select the candidate stacking corner point with the smallest expansion degree of the envelope of the minimum cuboid.

[0131] In another optional implementation, the determination module 703 may evaluate the stacking effect of each candidate stacking corner point according to the second effect function, and then select the corner point with the largest function value. The second effect function reflects the degree of utilization of the remaining space of a candidate stacking corner point when the current stacked items are placed at the candidate stacking corner point. In specific implementation, the second effect function may be in the following form:

[0132] SUM(rsX-itemX,rsY-itemY,rsZ-itemZ)

[0133] Among them, rsX, rsY, and rsZ represent the three-sided dimensions of the remaining space of a candidate stacking corner point; itemX, itemY, and itemZ represent the three-sided dimensions of the current stacked items; SUM(rsX-itemX,rsY-itemY,rsZ-itemZ) represents the sum of rsX-itemX, rsY-itemY, and rsZ-itemZ.

[0134] After calculating the function value corresponding to each candidate stacking corner point through the second effect function, the candidate stacking corner point with the largest function value can be used as the stacking corner point for the current stacked items. That is, try to select the candidate stacking corner point with the highest utilization rate of the remaining space.

[0135] The determination module 703 is further configured to, when the candidate stacking corner point set is empty, create a new empty container and use the designated position of the empty container as the stacking corner point of the current stacked item. The designated position may be Figure 3 The coordinate origin is shown.

[0136] The updating module 704 is used to update the available corner point set of the container when it is confirmed that the stacking corner points of all the items have not been obtained.

[0137] Among them, the updating module 704 updates the available corner point set of the container specifically including: 1) the updating module 704 deletes the stacking corner points of the current stacked items from the available corner point set of the container; 2) the updating module 704 deletes the corner points covered by the current stacked items from the available corner point set; 3) the updating module 704 adds the new corner points generated after the current stacked items are placed to the available corner point set; 4) the updating module 704 deletes the duplicate corner points in the available corner point set.

[0138] After the updating module 704 updates the available corner point set of the container, the building module 702 and the determining module 703 may be repeatedly called until the stacking corner points of all items are obtained.

[0139] The generation module 705 is used to generate a palletizing pattern after confirming the stacking corner points of all the items.

[0140] The stacking pattern may include: the correspondence between items and containers, and the stacking corners of items. For example, the correspondence between items and containers includes: pallet 1 corresponds to items A, B, C, D, E; pallet 2 corresponds to items F, G, H, I; the stacking corners of items include: the stacking corner of item A (0, 0, 0), the stacking corner of item B (3, 4, 5), etc.

[0141] Furthermore, the palletizing device 700 of the embodiment of the present invention may further include the following modules: an optimization module, used for optimizing the palletizing type.

[0142] Specifically, the optimization module optimizes the stacking type including: changing the correspondence between the items and containers according to the neighborhood generation strategy to obtain a new set of items corresponding to each container; generating a new stacking type after obtaining the stacking corner points of each item in the new set of items; evaluating the quality of the new stacking type, and judging whether to update the current optimized type according to the evaluation result; and using the current optimized type as the final stacking type when the optimization stop condition is reached. The optimization stop condition may be the lower limit of the calculation time or the acceptable quality of the stacking type.

[0143] In the embodiment of the present invention, the above device can automatically generate the stacking type of mixed palletizing, which reduces the requirements for manual experience in mixed palletizing, improves the efficiency of mixed palletizing, and improves the effect of mixed palletizing. Furthermore, the palletizing device of the embodiment of the present invention can also be applied to the scenarios of stacking type recommendation and stacking guidance of manual palletizing, or to the scenarios of stacking type generation and cargo box positioning of machine palletizing, so as to improve the intelligence and automation level of mixed palletizing.

[0144] Figure 8 Schematic diagram of the main modules of a palletizing device according to another embodiment of the present invention. Figure 8 As shown, the palletizing device 800 of the embodiment of the present invention includes: a construction module 801 , a determination module 802 , and a generation module 803 .

[0145] The construction module 801 is used to construct a candidate stacking corner point set for all the items to be stacked.

[0146] The candidate stacking corner point set can be understood as a set of position points in a container where items can be placed. For example, assuming that there are 10 boxes in total, 5 boxes have been stacked on the pallet, and the remaining 5 boxes are the items to be stacked, namely box A, box B, box C, box D, and box E. Further, the candidate stacking corner point set of the five boxes A to E can be: {candidate stacking corner point 1, candidate stacking corner point 2, candidate stacking corner point 3}.

[0147] The determination module 802 is used to evaluate the stacking effect of each candidate stacking corner point in the candidate stacking corner point set, so as to determine the current stacked item and the stacking corner point of the current stacked item according to the evaluation result.

[0148] When mixed palletizing is performed, it is necessary to repeatedly call the construction module 801 and the determination module 802 until the stacking corner points of all items are obtained.

[0149] The generation module 803 is used to generate a palletizing pattern after obtaining the stacking corner points of all items.

[0150] The stacking pattern may include: the correspondence between items and containers, and the stacking corners of items. For example, the correspondence between items and containers includes: pallet 1 corresponds to items A, B, C, D, E; pallet 2 corresponds to items F, G, H, I; the stacking corners of items include: the stacking corner of item A (0, 0, 0), the stacking corner of item B (3, 4, 5), etc.

[0151] Figure 8 The embodiment shown and Figure 6 The main differences of the shown embodiments are: Figure 8 The embodiment shown adopts "dynamic sorting", that is, all combinations of candidate stacking corner points are compared for all items to be stacked, and the best combination is selected by calculating the effect function to determine the stacking corner points of the current stacking item and the current stacking item; Figure 6 The illustrated embodiment adopts "static sorting", that is, first determining the current stacked items, and then selecting the optimal candidate stacking corner points corresponding thereto through the effect function to determine the stacking corner points of the current stacked items.

[0152] In the embodiment of the present invention, the above device can automatically generate the mixed palletizing type, which reduces the requirements for manual experience in mixed palletizing, improves the efficiency of mixed palletizing, and improves the effect of mixed palletizing. Compared with the palletizing device using "static sorting", the use of "dynamic sorting" can further improve the effect of mixed palletizing.

[0153] Fig. 9 An exemplary system architecture 900 is shown to which a palletizing method or a palletizing device according to an embodiment of the present invention may be applied.

[0154] like Fig. 9 As shown, system architecture 900 may include terminal devices 901, 902, 903, network 904 and server 905. Network 904 is used to provide a medium for communication links between terminal devices 901, 902, 903 and server 905. Network 904 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0155] Users can use terminal devices 901, 902, 903 to interact with server 905 through network 904 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 901, 902, 903, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0156] The terminal devices 901 , 902 , and 903 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0157] The server 905 may be a server that provides various services, such as a background management server that provides support for the pallet type recommendation website browsed by the user using the terminal devices 901, 902, and 903. The background management server may analyze and process the received data such as the pallet type query request, and feed back the processing result (such as the generated pallet type) to the terminal device.

[0158] It should be noted that the palletizing method provided in the embodiment of the present invention is generally executed by the server 905 , and accordingly, the palletizing device is generally disposed in the server 905 .

[0159] It should be understood that Fig. 9 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0160] Fig.10 A schematic diagram of the structure of a computer system 1000 suitable for implementing an electronic device of an embodiment of the present invention is shown. Fig.10 The computer system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0161] like Fig.10 As shown, the computer system 1000 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage part 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the system 1000 are also stored. The CPU 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0162] The following components are connected to the I / O interface 1005: an input section 1006 including a keyboard, a mouse, etc.; an output section 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, a modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed, so that a computer program read therefrom is installed into the storage section 1008 as needed.

[0163] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1009, and / or installed from the removable medium 1011. When the computer program is executed by the central processing unit (CPU) 1001, the above-mentioned functions defined in the system of the present invention are executed.

[0164] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0165] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0166] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor, for example, it may be described as: a processor includes a construction module, a determination module and a generation module. The names of these modules do not constitute a limitation on the modules themselves in some cases, for example, the construction module may also be described as "a module for constructing a set of candidate stacking corner points for the currently stacked items".

[0167] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device executes the following process: i) select the current stacked item from all the items to be stacked, and then construct a candidate stacking corner point set of the current stacked item; ii) evaluate the stacking effect of each candidate stacking corner point in the candidate stacking corner point set, and determine the stacking corner point of the current stacked item according to the evaluation result; iii) repeat step i) to step ii) until the stacking corner points of all items are obtained; iv) after the stacking corner points of all items are obtained, generate a stacking type.

[0168] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A palletizing method, characterized in that: The method comprises: i) selecting a current stacking object from all the objects to be stacked, and then constructing a candidate stacking corner point set of the current stacking object; ii) evaluating the stacking effect of each candidate stacking corner point in the candidate stacking corner point set, so as to determine the stacking corner point of the current stacked item according to the evaluation result; wherein the stacking effect is evaluated according to the degree of expansion of the envelope of the minimum cuboid and / or the degree of utilization of the remaining space after the current stacked item is placed at the candidate stacking corner point; the minimum cuboid is the minimum cuboid that can accommodate all the stacked items on the container; iii) Repeating steps i) to ii) until the stacking corner points of all items are obtained; iv) after obtaining the stacking corner points of all the items, generating a stacking pattern; the stacking pattern includes: a corresponding relationship between the items and the containers; The corresponding relationship between the items and containers is changed according to the neighborhood generation strategy to obtain a new set of items corresponding to each container; after obtaining the stacking corner point of each item in the new set of items, a new stacking shape is generated; the quality of the new stacking shape is evaluated, and it is determined whether to update the current optimized shape according to the evaluation result; when the optimization stop condition is reached, the current optimized shape is used as the final stacking shape; The step of constructing a candidate stacking corner point set for the currently stacked items includes: According to a preset placement rule, candidate stacking corner points of the current stacked items are selected from the available corner point set of the container to obtain the candidate stacking corner point set; the preset placement rule includes: after the current stacked items are placed at the available corner points of the container, the proportion of the bottom support area of ​​the current stacked items is greater than or equal to a preset threshold.

2. The method according to claim 1, characterized in that The preset placement rule also includes at least one of the following: After placing the currently stacked items at the available corner points of the container, the currently stacked items cannot interfere with the stacked items on the current container; After the currently stacked items are placed at the available corner points of the container, the currently stacked items cannot exceed the boundaries of the container.

3. The method according to claim 1, characterized in that The method further comprises: When the candidate stacking corner point set is empty, a new empty container is opened, and the designated position of the empty container is used as the stacking corner point of the current stacked item.

4. The method according to claim 1, characterized in that: The method further comprises: After determining the stacking corner points of the currently stacked items and before repeatedly executing step i) to step ii), the available corner point set of the container is updated.

5. The method according to claim 4, characterized in that The step of updating the available corner point set of the container comprises: Deleting the stacking corner points of the currently stacked items from the available corner point set; Deleting the corner points covered by the currently stacked items from the available corner point set; Adding new corner points generated after placing the currently stacked items to the set of available corner points; The duplicate corner points in the available corner point set are deleted.

6. The method according to claim 1, characterized in that The method further comprises: The stacking order of the objects is determined according to a preset sorting rule, so that the current stacking object is selected from all the objects to be stacked according to the stacking order.

7. The method according to claim 6, characterized in that The preset sorting rules include: Sort the items in descending order by volume, and if the volumes are the same, sort them in descending order by height; or, Sort the items in descending order by their base area, and if the base areas are the same, sort them in descending order by their height; or, Sort items in descending order based on their three largest dimensions.

8. A palletizing method, characterized in that: The method comprises: i) constructing a set of candidate stacking corner points for all items to be stacked; ii) evaluating the stacking effect of each candidate stacking corner point in the candidate stacking corner point set, so as to determine the current stacked item and the stacking corner point of the current stacked item according to the evaluation result; wherein the stacking effect is evaluated according to the degree of expansion of the envelope of the minimum cuboid and / or the degree of utilization of the remaining space after the current stacked item is placed at the candidate stacking corner point; the minimum cuboid is the minimum cuboid that can accommodate all the stacked items on the container; iii) Repeating steps i) to ii) until the stacking corner points of all items are obtained; iv) after obtaining the stacking corner points of all the items, generating a stacking pattern; the stacking pattern includes: a corresponding relationship between the items and the containers; The corresponding relationship between the items and containers is changed according to the neighborhood generation strategy to obtain a new set of items corresponding to each container; after obtaining the stacking corner points of each item in the new set of items, a new stacking pattern is generated; the quality of the new stacking pattern is evaluated, and it is determined whether to update the current optimized stacking pattern according to the evaluation result; when the optimization stop condition is reached, the current optimized stacking pattern is used as the final stacking pattern.

9. A palletizing device, characterized in that: The device comprises: A construction module, used for selecting a current stacking object from all the objects to be stacked, and then constructing a candidate stacking corner point set of the current stacking object; A determination module is used to evaluate the stacking effect of each candidate stacking corner point in the candidate stacking corner point set, so as to determine the stacking corner point of the current stacked item according to the evaluation result; wherein the stacking effect is evaluated according to the degree of expansion of the envelope of the minimum cuboid and / or the degree of utilization of the remaining space after the current stacked item is placed at the candidate stacking corner point; the minimum cuboid is the minimum cuboid that can accommodate all the stacked items on the container; Repeatedly calling the construction module and the determination module until the stacking corner points of all items are obtained; A generating module, for generating a stacking pattern after obtaining the stacking corner points of all the articles, wherein the stacking pattern includes: a corresponding relationship between the articles and the containers; An optimization module, used to change the correspondence between the items and containers according to the neighborhood generation strategy to obtain a new set of items corresponding to each container; also used to generate a new stacking pattern after obtaining the stacking corner point of each item in the new set of items; also used to evaluate the quality of the new stacking pattern and determine whether to update the current optimized pattern according to the evaluation result; and also used to use the current optimized pattern as the final stacking pattern when the optimization stop condition is reached; The construction module constructs the candidate stacking corner point set of the current stacked items, including: The construction module selects candidate stacking corner points of the current stacked items from the available corner point set of the container according to a preset placement rule to obtain the candidate stacking corner point set; the preset placement rule includes: after the current stacked items are placed at the available corner points of the container, the proportion of the bottom support area of ​​the current stacked items is greater than or equal to a preset threshold.

10. The device according to claim 9, characterized in that The determining module is also used for: In the case that the candidate stacking corner point set is empty, the determination module opens a new empty container and uses the designated position of the empty container as the stacking corner point of the currently stacked item.

11. The device according to claim 9, characterized in that The device also includes: An updating module is used to update the available corner point set of the container after the determining module determines the stacking corner points of the currently stacked items and before repeatedly calling the building module and the determining module.

12. The device according to claim 11, characterized in that The updating module updates the available corner point set of the container including: The updating module deletes the stacking corner points of the current stacked items from the available corner point set; the updating module deletes the corner points covered by the current stacked items from the available corner point set; the updating module adds new corner points generated after the current stacked items are placed to the available corner point set; the updating module deletes duplicate corner points in the available corner point set.

13. The device according to claim 9, characterized in that The device also includes: The sorting module is used to determine the stacking order of the objects according to a preset sorting rule, so that the construction module selects the current stacking object from all the objects to be stacked according to the stacking order.

14. A palletizing device, characterized in that: The device comprises: A construction module is used to construct a candidate stacking corner point set for all items to be stacked; A determination module is used to evaluate the stacking effect of each candidate stacking corner point in the candidate stacking corner point set, so as to determine the current stacked item and the stacking corner point of the current stacked item according to the evaluation result; wherein the stacking effect is evaluated according to the degree of expansion of the envelope of the minimum cuboid and / or the degree of utilization of the remaining space after the current stacked item is placed at the candidate stacking corner point; the minimum cuboid is the minimum cuboid that can accommodate all the stacked items on the container; Repeatedly calling the construction module and the determination module until the stacking corner points of all items are obtained; A generating module, used to generate a stacking pattern after obtaining the stacking corner points of all the items; the stacking pattern includes: a corresponding relationship between the items and the containers; The optimization module is used to change the correspondence between the items and containers according to the neighborhood generation strategy to obtain a new set of items corresponding to each container; it is also used to generate a new stacking pattern after obtaining the stacking corner points of each item in the new set of items; it is also used to evaluate the quality of the new stacking pattern and determine whether to update the current optimized pattern according to the evaluation result; it is also used to use the current optimized pattern as the final stacking pattern when the optimization stop condition is reached.

15. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

16. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images