Blank processing method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a blank processing method and device, electronic equipment and storage medium, relates to the field of intelligent manufacturing, in particular to the layout scene of a blank, so as to at least solve the technical problem of low layout efficiency of the blank in the related art. The specific implementation scheme is: obtaining a target blank set to be laid out; determining at least one initial layout mode of the target blank set on a target plate and a target utilization rate corresponding to the at least one initial layout mode by using a first function model, wherein the target utilization rate is used to represent the ratio of the total area of the blank obtained after the target blank set is laid out according to the at least one initial layout mode to the area of the target plate; determining a target layout mode corresponding to the target blank set based on the target utilization rate corresponding to the at least one initial layout mode.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent manufacturing, specifically to the layout of blanks, and particularly to a blank processing method, apparatus, electronic device, and storage medium. Background Technology

[0002] Blank layout refers to the rational geometric combination of small blank parts on large raw materials to reduce raw material consumption while meeting order blank requirements. Currently, blank layout can be calculated using algorithms; however, the computational efficiency of these algorithms is low when the amount of blank data is large. Summary of the Invention

[0003] This disclosure provides a blank processing method, apparatus, electronic device, and storage medium to at least solve the technical problem of low blank typesetting efficiency in the related art.

[0004] According to one aspect of this disclosure, a method for processing raw blanks is provided, comprising: obtaining a set of target raw blanks to be laid out; determining at least one initial layout method of the target raw blanks on a target board and a target utilization rate corresponding to the at least one initial layout method using a first function model, wherein the target utilization rate is used to represent the ratio of the total area of ​​the raw blanks obtained after the target raw blanks are laid out according to at least one initial layout method to the area of ​​the target board; and determining a target layout method corresponding to the target raw blanks based on the target utilization rate corresponding to the at least one initial layout method.

[0005] According to another aspect of this disclosure, a blank processing apparatus is provided, comprising: an acquisition module for acquiring a set of target blanks to be laid out; a utilization rate determination module for determining at least one initial layout method of the target blank set on a target board and a target utilization rate corresponding to the at least one initial layout method using a first function model, wherein the target utilization rate is used to represent the ratio of the total area of ​​the blanks obtained after the target blank set is laid out according to at least one initial layout method to the area of ​​the target board; and a layout method determination module for determining a target layout method corresponding to the target blank set based on the target utilization rate corresponding to the at least one initial layout method.

[0006] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the blank processing method proposed in this disclosure.

[0007] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause a computer to perform the blank processing method proposed in this disclosure.

[0008] According to another aspect of this disclosure, a computer program product is provided, including a computer program that is executed by a processor using the blank processing method proposed in this disclosure.

[0009] In this disclosure, a set of target blanks to be laid out is first obtained; then, a first function model is used to determine at least one initial layout method for the target blank set on the target board and the target utilization rate corresponding to the at least one initial layout method, wherein the target utilization rate is used to represent the ratio of the total area of ​​the blanks obtained after the target blank set is laid out according to at least one initial layout method to the area of ​​the target board; finally, based on the target utilization rate corresponding to at least one initial layout method, the target layout method corresponding to the target blank set can be determined, thereby achieving the purpose of improving the layout efficiency of the target blank set; the first function model can improve the computational efficiency of the layout method, and the target utilization rate obtained through the first function model can reduce the material consumption of the target blank set layout, thereby reducing the layout cost of the blanks, and thus solving the technical problem of low layout efficiency of blanks in related technologies.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0011] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0012] Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) for implementing a blank processing method according to an embodiment of the present disclosure;

[0013] Figure 2 This is a hardware structure block diagram of a computer terminal (or mobile device) implementing a blank processing method according to an embodiment of the present disclosure;

[0014] Figure 3 This is a flowchart of a tabu search according to an embodiment of the present disclosure;

[0015] Figure 4 This is an architectural diagram of a blank processing method according to an embodiment of the present disclosure;

[0016] Figure 5 This is a structural block diagram of a blank processing apparatus according to an embodiment of the present disclosure. Detailed Implementation

[0017] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0018] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0019] According to an embodiment of this disclosure, a method for processing a blank is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0020] The method embodiments provided in this disclosure can be performed in a mobile terminal, computer terminal, or similar electronic device. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the disclosure described and / or claimed herein. Figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing a blank processing method is shown.

[0021] like Figure 1As shown, the computer terminal 100 includes a computing unit 101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 102 or a computer program loaded from a storage unit 108 into a random access memory (RAM) 103. The RAM 103 may also store various programs and data required for the operation of the computer terminal 100. The computing unit 101, ROM 102, and RAM 103 are interconnected via a bus 104. An input / output (I / O) interface 105 is also connected to the bus 104.

[0022] Multiple components in the computer terminal 100 are connected to the I / O interface 105, including: an input unit 106, such as a keyboard and mouse; an output unit 107, such as various types of displays and speakers; a storage unit 108, such as a hard disk and optical disk; and a communication unit 109, such as a network interface card (NIC), a modem, or a wireless transceiver. The communication unit 109 allows the computer terminal 100 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0023] The computing unit 101 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 101 executes the blanking process described herein. For example, in some embodiments, the blanking process may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 108. In some embodiments, part or all of the computer program may be loaded and / or installed on the computer terminal 100 via ROM 102 and / or communication unit 109. When the computer program is loaded into RAM 103 and executed by the computing unit 101, one or more steps of the blanking process described herein may be performed. Alternatively, in other embodiments, the computing unit 101 may be configured to execute the blanking process by any other suitable means (e.g., by means of firmware).

[0024] Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0025] It should be noted here that, in some optional embodiments, the above... Figure 1 The illustrated electronic device may include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that... Figure 1 This is only one instance of a specific particular example, and is intended to illustrate the types of components that may exist in the aforementioned electronic devices.

[0026] Under the aforementioned operating environment, this disclosure provides, for example... Figure 2 The blank processing method shown can be performed by... Figure 1 The computer terminal or similar electronic device shown is used for execution. Figure 2 This is a flowchart of a blank processing method provided according to an embodiment of this disclosure. Figure 2 As shown, the method may include the following steps:

[0027] Step S202: Obtain the target blank set to be typed.

[0028] The aforementioned set of target blanks to be typed can be sets of blanks from different fields. In the metal cutting process of machinery manufacturing, the target set of blanks can be metal blanks to be cut after typesetting; in the wood cutting process of the furniture industry, the target set of blanks can be wood to be cut after typesetting; in the glass cutting process of the construction industry, the target set of blanks can be glass to be cut after typesetting; the target set of blanks can also be text content to be typed in the printing industry; the target set of blanks can also be plastic to be typed in the plastic processing process of the chemical industry; and the target set of blanks can also be fabric to be typed and cut in the fabric cutting process of the clothing industry.

[0029] In one optional embodiment, during the cutting and processing of the target blank set, a reasonable layout method can reduce material waste, reduce material costs, and simplify processing operations to reduce manufacturing costs. Therefore, the target blank set to be layoutd can be obtained first, and then the target blank set can be layoutd using deep learning calculations to obtain the target layout method corresponding to the target blank set.

[0030] Step S204: Use the first function model to determine at least one initial layout method of the target blank set on the target board and the target utilization rate corresponding to the at least one initial layout method.

[0031] The target utilization rate is used to represent the ratio of the total area of ​​the blanks obtained after the target blank set is arranged according to at least one initial layout method to the area of ​​the target board.

[0032] The first function model mentioned above can be a utilization calculation function model, which is used to determine multiple initial layout methods corresponding to the target blank set and the utilization rate corresponding to each initial layout method. The first function model can be a convolutional neural network.

[0033] The target board material mentioned above can be a pre-set specific model board material, which can be a specific size board material, and the material of the board material can be set according to the material of the target blank set.

[0034] The aforementioned target utilization rate indicates how much area of ​​the target sheet can be used by the blanks in the target blank set. A higher utilization rate means less wasted area in the target sheet, allowing for greater utilization of space and thus reducing material costs. Conversely, a lower utilization rate indicates more wasted area, meaning a large portion of the target sheet's area is not being used effectively, leading to higher material costs.

[0035] It should be noted that the target utilization rate corresponding to the initial layout method may be 0. When the target utilization rate is 0, it means that the area of ​​the target board cannot accommodate all the blanks in the target blank set. For example, there may be stacking or edge loss of blanks in the target blank set on the target board. In this case, multiple target boards are needed to lay out the target blank set.

[0036] In one alternative embodiment, a first function model can be used to determine at least one initial layout of the target blank set on the target sheet and the target utilization rate corresponding to the at least one initial layout, so as to determine the layout when the utilization rate of the target blank set on the target sheet is maximized, thereby reducing the cost of the material used in the target blank set.

[0037] In another optional embodiment, the first function model described above can be trained using historical layout methods and their corresponding utilization rate labels. It should be noted that historical layout methods generally do not contain layouts with a utilization rate of 0. Therefore, additional blanks can be manually added to historical layout methods to obtain layouts that violate constraints, and the first function model described above can be trained based on these historical layout methods and the layouts that violate constraints.

[0038] Step S206: Based on the target utilization rate corresponding to at least one initial layout method, determine the target layout method corresponding to the target blank set.

[0039] The above-mentioned target layout method can be the final layout method of the target blank set.

[0040] In one optional embodiment, the layout method with the highest target utilization rate can be determined based on the target utilization rate corresponding to at least one initial layout method, and the layout method with the highest utilization rate can be used as the target layout method.

[0041] Furthermore, to further improve layout efficiency, it is necessary to combine the cutting efficiency corresponding to the layout method to obtain the final layout method. Therefore, we can first determine multiple first layout methods with relatively high target utilization rates based on the target utilization rate corresponding to at least one initial layout method. Then, we obtain the cutting efficiency corresponding to the multiple first layout methods and determine the layout method with the highest cutting efficiency as the target layout method. Optionally, the layout method with the highest cutting efficiency among the multiple first layout methods can be determined by a cutting efficiency calculation function. To further improve the calculation speed, the layout method with the highest cutting efficiency among the multiple first layout methods can also be determined by a cutting efficiency function model. This cutting efficiency function model can be trained by the corresponding cutting efficiency in historical layout methods.

[0042] Through the above steps, the target blank set to be laid out is first obtained; then, the first function model is used to determine at least one initial layout method for the target blank set on the target board and the target utilization rate corresponding to the at least one initial layout method. The target utilization rate represents the ratio of the total area of ​​the blanks obtained after the target blank set is laid out according to at least one initial layout method to the area of ​​the target board. Finally, based on the target utilization rate corresponding to at least one initial layout method, the target layout method corresponding to the target blank set can be determined, thus achieving the goal of improving the layout efficiency of the target blank set. The first function model can improve the computational efficiency of the layout method, and the target utilization rate obtained through the first function model can reduce the material consumption for the layout of the target blank set, thereby reducing the layout cost of the blanks and solving the technical problem of low layout efficiency of blanks in related technologies.

[0043] Optionally, based on the target utilization rate corresponding to at least one initial layout method, the target layout method corresponding to the target blank set is determined, including: determining at least one first layout method with a target utilization rate greater than a first preset value from at least one initial layout method; and determining the target layout method from at least one first layout method using a second function model.

[0044] The aforementioned second function model can be a cutting efficiency calculation function model, which is used to determine the cutting efficiency of multiple initial layout methods corresponding to the target blank set. The second function model can be a convolutional neural network.

[0045] The first preset value mentioned above can be 0.

[0046] In one alternative embodiment, at least one first layout method with a target utilization rate greater than 0 can be determined from at least one initial layout method. In order to reduce the time for cutting the target blank set on the target board, the first layout method with the highest cutting efficiency can be determined from at least one first layout method as the target layout method.

[0047] In another alternative embodiment, the second function model described above can be obtained by training the historical layout method and the corresponding cutting efficiency of the historical layout method.

[0048] Optionally, the target layout method is determined from at least one first layout method using a second function model, including: determining the target cutting efficiency of at least one first layout method using the second function model, wherein the target cutting efficiency is used to characterize the efficiency of cutting the target blank set according to at least one first layout method; and determining the first layout method corresponding to the maximum cutting efficiency as the target layout method.

[0049] The aforementioned target cutting efficiency is used to represent the efficiency of cutting the target blank assembly on the target sheet according to the first layout method. A higher cutting efficiency indicates a shorter cutting time corresponding to the first layout method, meaning a lower cutting time cost; conversely, a lower cutting efficiency indicates a longer cutting time corresponding to the first layout method, meaning a higher cutting time cost.

[0050] In one alternative embodiment, a second function model can be used to determine the target cutting efficiency of at least one first layout method in order to improve the efficiency of calculation; the first layout method corresponding to the maximum cutting efficiency can be determined in order to reduce the time cost of cutting, thereby quickly obtaining a target layout method with high utilization and cutting efficiency.

[0051] Optionally, based on the target utilization rate corresponding to at least one initial layout method, the target layout method corresponding to the target blank set is determined, including: in response to the target utilization rate being equal to a first preset value, calling a target algorithm to determine at least one second layout method for the target blank set on multiple target boards; using a first function model to determine a first utilization rate for the target blank set on each target board in the at least one second layout method; using a second function model to determine a first cutting efficiency corresponding to the at least one second layout method; and determining the target layout method from the at least one second layout method based on the first utilization rate and the first cutting efficiency.

[0052] The aforementioned objective algorithm can be a heuristic algorithm, defined as searching for the best solution within an acceptable computational cost. Specifically, the objective algorithm can be a nearest neighbor search algorithm and / or a greedy algorithm within the heuristic algorithm family.

[0053] In an optional embodiment, when the target utilization rate is 0, it indicates that multiple target boards are needed to arrange the target blank set, meaning the number of target boards in the target arrangement is greater than 1. In this case, a greedy algorithm can be used to obtain at least one second arrangement method for the target blank set on multiple target boards, i.e., the initial solution of the greedy algorithm. Then, a neighborhood search algorithm in heuristic algorithms can be used to iteratively update the initial solution. Each update finds the optimal solution in the neighborhood space of the current solution. The optimal solution can be calculated based on the first utilization rate obtained from the first function model and the second utilization rate obtained from the second function model. Specifically, the average first utilization rate and average first cutting efficiency of at least one second arrangement method can be obtained, and the optimal solution is obtained by the maximum weighted sum of the average first utilization rate and average first cutting efficiency.

[0054] In the process of iteratively updating the initial solution using the nearest neighbor search algorithm, iterative updates can be performed using tabu search. Tabu search can start from an initial solution and select a series of specific search methods as trials. It can compare the current node with its surrounding neighbor nodes. If the current node is the largest, then the current node is returned as the maximum value. Otherwise, the current node is replaced with the highest neighbor node, thereby achieving the goal of climbing to the higher peak and obtaining the optimal solution.

[0055] Furthermore, to avoid getting trapped in local optima during the tabu search process, a flexible "memory" technique can be used to record and select the optimization processes that have already been performed, guiding the next search direction. Optionally, this can be achieved by creating a tabu list.

[0056] In another optional embodiment, the tabu search process can combine the utilization rate and cutting efficiency corresponding to the layout method. First, a greedy algorithm can be used to obtain at least one second layout method. Then, based on the first function model and the second function model, the first utilization rate and the first cutting efficiency corresponding to at least one second layout method can be obtained. The target board in the second layout method with the smallest first utilization rate can be determined. Then, blanks are grabbed and exchanged from other boards through neighborhood search. The grabbed and exchanged blanks are recorded in the tabu table, and the grabbed and exchanged blanks are restricted from returning to the original board.

[0057] Furthermore, during the neighborhood search process, the determined second layout method can be updated. Optionally, a weighted calculation can be performed based on the average value of the first utilization rate corresponding to at least one second layout method and the average value of the first cutting efficiency corresponding to at least one second layout method to obtain the weighted sum corresponding to each second layout method. When the iteration number is reached, the second layout method corresponding to the maximum weighted sum can be updated as the target layout method.

[0058] like Figure 3 The diagram shows the flowchart of tabu search. First, the tabu list is initialized, and the tabu length is determined, where the tabu length is the number of prohibited operations. An initial solution (at least one second layout method) can be generated, and the fitness function value (first utilization and first cutting efficiency) can be calculated. During the neighborhood search, candidate solutions (candidate second layout methods) can be generated. It is determined whether the best solution among the candidate solutions is the current global best solution. If so, the best solution among the candidate solutions can be selected, and the current solution is updated, while the tabu list is updated. If not, the best solution among the candidate solutions that is not tabulated can be selected, and the current solution is updated according to the best solution, while the tabu list is updated. It is determined whether the number of iterations to terminate has been reached. If so, the process ends. If not, the search continues in the neighborhood to generate candidate solutions. The final current solution is the optimal solution (target layout method).

[0059] For a furniture set that needs to be stored in a cabinet, the furniture set can be input into the first function model. If the output target utilization rate is equal to 0, it means that multiple boards need to be arranged, that is, it is necessary to enter the multi-board scene for arrangement.

[0060] Optionally, the method further includes: obtaining at least one historical layout method and a preset blank, wherein the at least one historical layout method includes a historical utilization rate; generating first training data based on the at least one historical layout method and the preset blank; and training a first preset model using the first training data to generate a first function model.

[0061] At least one of the above-mentioned historical layout methods can be the layout method corresponding to the set of blanks that are placed in the same board during the historical layout process. The historical layout method can include blank feature information, historical utilization rate and historical cutting efficiency.

[0062] Among them, the blank feature information can be x=[x_1,…,x_n], where x_i is a triple (l,w,m) representing the length, width and quantity of the blank respectively; the historical utilization rate can be p, the piece can be a real number in the interval [0,1], and the historical utilization rate can be the ratio of the total area of ​​the blanks on the target board to the area of ​​the target board in the blank set. When the historical utilization rate is 0, it indicates that there is a violation of the layout constraints, such as the occurrence of stacked parts or insufficient edge trimming loss. The historical cutting efficiency can be the actual cutting time of the historical layout method.

[0063] The aforementioned preset blanks can be any number and any shape of blanks.

[0064] In one optional embodiment, since only layout methods with utilization greater than 0 are used in the historical layout process, there are no layout methods with utilization equal to 0 in the historical layout methods. However, in the process of training the first function model, layout methods with utilization greater than 0 and layout methods with utilization equal to 0 are required for training. Therefore, layout methods with utilization of 0 can be artificially generated. Optionally, additional blanks can be added to the historical layout methods with high utilization to generate layout methods that violate constraints, that is, layout methods with utilization of 0, so as to obtain the first training data for training the model.

[0065] In another alternative embodiment, first training data corresponding to the historical layout method can be generated through historical layout method. After obtaining the first training data, the first preset model can be trained through the first training data by machine learning algorithm or deep learning algorithm to generate a first function model. The blank set can be solved by the first function model, which can reduce the solution time.

[0066] Optionally, generating first training data based on at least one historical layout method and a preset blank includes: determining a layout method to be adjusted from at least one historical layout method, wherein the historical utilization rate of the layout method to be adjusted is greater than a second preset value; adding a preset blank to the set of historical blanks corresponding to the layout method to be adjusted to generate an adjusted layout method, wherein the adjusted layout method includes a second utilization rate; and generating first training data based on at least one historical layout method and the adjusted layout method.

[0067] The above-mentioned layout adjustment method can be the layout method for adding additional blanks.

[0068] The second preset value mentioned above can be set by the user.

[0069] In an optional embodiment, in order to obtain a layout with a utilization rate of 0, a layout with a historical utilization rate greater than a second preset value can be determined from at least one historical layout, that is, the aforementioned layout to be adjusted. Since the remaining usable area of ​​the target board is small in the layout to be adjusted with a higher utilization rate, when an additional preset blank is added to the layout to be adjusted, the probability that the second utilization rate corresponding to the adjusted layout is equal to 0 is relatively high. Therefore, first training data can be generated based on the historical layout and the adjusted layout.

[0070] Optionally, the method further includes: determining second training data based on at least one historical layout method, wherein the at least one historical layout method further includes historical cutting efficiency; and training a second preset model using the second training data to generate a second function model.

[0071] In one optional embodiment, at least one historical layout method also includes the cutting time required by the historical layout method, that is, the historical cutting efficiency mentioned above. The longer the cutting time corresponding to the layout method, the lower the cutting efficiency. The shorter the cutting time corresponding to the layout method, the higher the cutting efficiency. The second preset model can be trained using the second training data through a deep learning algorithm to obtain a second function model with higher computational speed.

[0072] In another alternative embodiment, a fitting function with high accuracy and strong generalization ability can be found by trying various deep learning algorithms, namely the second function model mentioned above.

[0073] like Figure 4 The diagram illustrates an architecture for a raw material processing method. First, training data is uploaded, and then the model is trained using this data. After training, the model is tested, and upon successful testing, it is deployed to the application layer. The application layer can then use the model to arrange the target raw material set. In the actual processing, the data management layer manages data access, data analysis, data preprocessing, raw material parameters, constraints, and historical layout methods. Then, the utilization function model and the cutting efficiency function model can be optimized through a combination of basic algorithms and mechanistic knowledge. The basic algorithms can include heuristic algorithms and deep learning algorithms, while the mechanistic knowledge can be operations research knowledge.

[0074] Through the above-described content of this disclosure, automatic layout of the target blank set can be achieved. Compared with traditional algorithms, the layout method obtained by the first function model of this disclosure improves the target utilization rate of the target material by 5%. Compared with traditional algorithms, the layout method obtained by the second function model of this disclosure reduces the average cutting time by 10%. In this disclosure, deep learning algorithms are used to replace manually designed grouping algorithms and value correction algorithms, which can effectively utilize historical layout methods to uncover the hidden logic behind efficient cutting schemes.

[0075] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0076] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this disclosure.

[0077] This disclosure also provides a blank processing apparatus for implementing the above embodiments and preferred embodiments, which will not be repeated hereafter. As used below, the term "module" can be a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0078] Figure 5 This is a structural block diagram of a blank processing apparatus according to one embodiment of the present disclosure, such as... Figure 5 As shown, a blank processing device 500 includes: an acquisition module 502, a utilization rate determination module 504, and a layout method determination module 506.

[0079] The acquisition module is used to acquire the target blank set to be laid out; the utilization rate determination module is used to determine at least one initial layout method of the target blank set on the target board and the target utilization rate corresponding to the at least one initial layout method using the first function model, wherein the target utilization rate is used to represent the ratio of the total area of ​​the blanks obtained after the target blank set is laid out according to at least one initial layout method to the area of ​​the target board; the layout method determination module is used to determine the target layout method corresponding to the target blank set based on the target utilization rate corresponding to at least one initial layout method.

[0080] Optionally, the layout method determination module includes: a first determination unit, used to determine at least one first layout method with a target utilization rate greater than a first preset value from at least one initial layout method; and a second determination unit, used to determine the target layout method from at least one first layout method using a second function model.

[0081] Optionally, the second determining unit includes: a first determining subunit, used to determine the target cutting efficiency of at least one first layout method using a second function model, wherein the target cutting efficiency is used to characterize the efficiency of cutting the target blank set according to at least one first layout method; and a second determining subunit, used to determine the first layout method corresponding to the maximum cutting efficiency as the target layout method.

[0082] Optionally, the layout method determination module further includes: a calling unit, used to call a target algorithm to determine at least one second layout method of the target blank set on multiple target boards in response to the target utilization rate being equal to a first preset value; a third determining unit, used to determine a first utilization rate of the target blank set on each target board in the at least one second layout method using a first function model; the third determining unit is also used to determine a first cutting efficiency corresponding to the at least one second layout method using a second function model; the third determining unit is also used to determine a target layout method from the at least one second layout method based on the first utilization rate and the first cutting efficiency.

[0083] Optionally, the device further includes: an acquisition module for acquiring at least one historical layout method and a preset blank, wherein the at least one historical layout method includes a historical utilization rate; a generation module for generating first training data based on at least one historical layout method and the preset blank; and the generation module for training a first preset model using the first training data to generate a first function model.

[0084] Optionally, the generation module includes: a fourth determining unit, configured to determine a typesetting method to be adjusted from at least one historical typesetting method, wherein the historical utilization rate of the typesetting method to be adjusted is greater than a second preset value; a generation unit, configured to add a preset blank to the historical blank set corresponding to the typesetting method to be adjusted, and generate an adjusted typesetting method, wherein the adjusted typesetting method includes the second utilization rate; the generation unit is further configured to generate first training data based on at least one historical typesetting method and the adjusted typesetting method.

[0085] Optionally, the device further includes: a training data determination module, configured to determine second training data based on at least one historical layout method, wherein the at least one historical layout method further includes historical cutting efficiency; and a generation module, configured to train a second preset model using the second training data to generate a second function model.

[0086] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0087] According to embodiments of this disclosure, this disclosure also provides an electronic device including a memory and at least one processor, the memory storing computer instructions, the processor being configured to execute the computer instructions to perform the steps in any of the above method embodiments.

[0088] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0089] Optionally, in this disclosure, the processor described above can be configured to perform the following steps via a computer program:

[0090] S1, obtain the target blank set to be typed;

[0091] S2, using the first function model to determine at least one initial layout method of the target blank set on the target board and the target utilization rate corresponding to the at least one initial layout method, wherein the target utilization rate is used to represent the ratio of the total area of ​​the blanks obtained after the target blank set is laid out according to at least one initial layout method to the area of ​​the target board.

[0092] S3, based on the target utilization rate corresponding to at least one initial layout method, determine the target layout method corresponding to the target blank set.

[0093] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0094] According to embodiments of the present disclosure, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are configured to perform the steps in any of the above method embodiments at runtime.

[0095] Optionally, in this embodiment, the non-volatile storage medium described above can be configured to store a computer program for performing the following steps:

[0096] S1, obtain the target blank set to be typed;

[0097] S2, using the first function model to determine at least one initial layout method of the target blank set on the target board and the target utilization rate corresponding to the at least one initial layout method, wherein the target utilization rate is used to represent the ratio of the total area of ​​the blanks obtained after the target blank set is laid out according to at least one initial layout method to the area of ​​the target board.

[0098] S3, based on the target utilization rate corresponding to at least one initial layout method, determine the target layout method corresponding to the target blank set.

[0099] Optionally, in this embodiment, the aforementioned non-transitory computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. More specific examples of readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0100] According to embodiments of this disclosure, a computer program product is also provided. Program code for implementing the methods described above can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0101] In the above embodiments of this disclosure, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0102] In the several embodiments provided in this disclosure, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0103] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0104] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0105] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0106] The above description is only a preferred embodiment of this disclosure. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principles of this disclosure, and these improvements and modifications should also be considered within the scope of protection of this disclosure.

Claims

1. A method of processing a blank, wherein, The method comprises the following steps: acquiring a target blank set to be arranged; determining at least one initial arrangement mode of the target blank set on a target plate and a target utilization rate corresponding to the at least one initial arrangement mode by using a first function model, wherein the target utilization rate represents a ratio of a total area of the target blank set arranged according to the at least one initial arrangement mode to an area of the target plate; determining at least one first arrangement mode with a target utilization rate greater than zero from the at least one initial arrangement mode; determining a target arrangement mode from the at least one first arrangement mode by using a second function model, wherein the second function model is a cutting efficiency calculation function model, the target arrangement mode is a first arrangement mode corresponding to a maximum cutting efficiency, and the first arrangement mode is the target arrangement mode; in response to the target utilization rate being equal to zero, calling a target algorithm to determine at least one second arrangement mode of the target blank set on a plurality of target plates; determining a first utilization rate of each target plate in the at least one second arrangement mode of the target blank set by using the first function model; determining a first cutting efficiency corresponding to each target plate in the at least one second arrangement mode by using the second function model; performing weighted calculation on an average value of the first utilization rates corresponding to the at least one second arrangement mode and an average value of the first cutting efficiencies corresponding to the at least one second arrangement mode to obtain a weighted sum corresponding to each second arrangement mode; determining a second arrangement mode corresponding to a maximum weighted sum as the target arrangement mode; acquiring at least one historical arrangement mode and a preset blank, wherein the at least one historical arrangement mode comprises a historical utilization rate; determining a to-be-adjusted arrangement mode from the at least one historical arrangement mode, wherein the historical utilization rate of the to-be-adjusted arrangement mode is greater than a second preset value; adding the preset blank to a historical blank set corresponding to the to-be-adjusted arrangement mode to generate an adjusted arrangement mode, wherein the adjusted arrangement mode comprises a second utilization rate; generating first training data based on the at least one historical arrangement mode and the adjusted arrangement mode; training a first preset model by using the first training data to generate the first function model.

2. The method of claim 1, wherein, The method further comprises the following steps: determining a target cutting efficiency of the at least one first arrangement mode by using the second function model, wherein the target cutting efficiency represents an efficiency of cutting the target blank set according to the at least one first arrangement mode; determining a first arrangement mode corresponding to a maximum cutting efficiency as the target arrangement mode.

3. The method of claim 1, wherein, The method further comprises the following steps: determining second training data based on the at least one historical arrangement mode, wherein the at least one historical arrangement mode further comprises a historical cutting efficiency; training a second preset model by using the second training data to generate the second function model.

4. A blank handling apparatus wherein, The method comprises the following steps: an acquiring module configured to acquire a target blank set to be arranged; The utilization rate determination module is configured to determine, by using a first function model, at least one initial layout mode of the target blank set on a target plate and a target utilization rate corresponding to the at least one initial layout mode, where the target utilization rate represents a ratio of a total area of the target blank set after the target blank set is laid out according to the at least one initial layout mode to an area of the target plate. The device further includes a first determination unit configured to determine, from the at least one initial layout mode, at least one first layout mode in which the target utilization rate is greater than zero, and a second determination unit configured to determine, by using a second function model, a target layout mode from the at least one first layout mode. The device further includes a calling unit configured to, in response to the target utilization rate being equal to zero, call a target algorithm to determine at least one second layout mode of the target blank set on a plurality of target plates, a third determination unit configured to determine, by using the first function model, a first utilization rate of each target plate in the at least one second layout mode of the target blank set, determine, by using the second function model, a first cutting efficiency corresponding to each target plate in the at least one second layout mode, and perform weighted calculation on an average value of the first utilization rates corresponding to the at least one second layout mode and an average value of the first cutting efficiencies corresponding to the at least one second layout mode to obtain a weighted sum corresponding to each second layout mode, and a second layout mode corresponding to a maximum weighted sum is the target layout mode. The acquisition module is further configured to acquire at least one historical layout mode and a preset blank, where the at least one historical layout mode includes a historical utilization rate. The generation module includes a fourth determination unit configured to determine, from the at least one historical layout mode, a layout mode to be adjusted, where the historical utilization rate of the layout mode to be adjusted is greater than a second preset value, and a generation unit configured to add the preset blank to a historical blank set corresponding to the layout mode to be adjusted to generate an adjusted layout mode, where the adjusted layout mode includes a second utilization rate, and the generation unit is further configured to generate first training data based on the at least one historical layout mode and the adjusted layout mode. The generation module is further configured to train a first preset model by using the first training data to generate the first function model.

5. The apparatus of claim 4, wherein, The second determination unit includes: A first determination subunit configured to determine, by using the second function model, a target cutting efficiency of the at least one first layout mode, where the target cutting efficiency represents an efficiency of cutting the target blank set according to the at least one first layout mode. A second determination subunit configured to determine that a first layout mode corresponding to a maximum cutting efficiency is the target layout mode.

6. The apparatus of claim 4, wherein, The device further includes: A training data determination module configured to determine second training data based on the at least one historical layout mode, where the at least one historical layout mode further includes a historical cutting efficiency. The generating module is further configured to train a second preset model using the second training data to generate the second function model. 7.An electronic device, comprising: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-3.

8. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are configured to cause the computer to perform the method of any one of claims 1-3. 9.A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1-3.

Images