Scheduling method and device for garment production line

Abstract

The invention relates to the field of production line scheduling, in particular to a garment production line scheduling method and device, and the method comprises the steps: obtaining a plurality of garment orders, distributing the same garment processing tasks in each garment order to a corresponding target edge calculation node which is used for sequentially processing the same garment processing tasks, if the processing time of the target edge computing node exceeds the preset time, obtaining the remaining clothing processing tasks corresponding to the target edge computing node, obtaining the distribution relation value between the remaining clothing processing tasks and other target edge computing nodes, and determining the target edge computing node based on the distribution relation value. And determining the optimal target edge computing node allocated to the remaining garment processing tasks. By detecting the calculation delay of the edge calculation nodes and based on the distribution relation value, the calculation power of all the edge calculation nodes of the production system is automatically rescheduled, and the problems that in the prior art, the calculation power is spare, and the load of individual equipment is too high are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of production line scheduling, and in particular to a scheduling method and device for a clothing production line. Background Art

[0002] At present, there are already many technologies on the market that can meet this demand. Among them, the common one is the data analysis and visualization technology based on edge computing. This technology installs edge computing devices and data sensors at each processing link of each production line, and summarizes the processed analysis results to the total control device for visual display. However, for clothing production, this process is significantly different from other industries. The reason is that an order may involve the production of multiple types of clothing, and different types of clothing require different processing techniques, and various techniques need to be completed by different production lines. Usually, different production lines are responsible for different production techniques. Therefore, in the actual production process, the workloads of different production lines will vary. When there is a serious deviation in the load of the production line, the computing power of some edge computing devices may be idle. Summary of the Invention

[0003] To solve the above-mentioned problems of the prior art, the present invention provides a scheduling method and device for a clothing production line, which solves the problem that the computing power of some edge computing devices may be idle when there is a serious deviation in the load of the production line.

[0004] According to one aspect of the present invention, there is provided a scheduling method for a clothing production line, including: Obtaining a plurality of clothing orders; Allocating the same clothing processing tasks in each clothing order to corresponding target edge computing nodes; wherein the target edge computing nodes are used to sequentially process the same clothing processing tasks; If the processing time of the target edge computing node exceeds a preset time, obtaining the remaining clothing processing tasks corresponding to the target edge computing node; wherein the remaining clothing processing tasks are the tasks that the target edge computing node has not completed within the processing time; Obtaining the allocation relationship value between the remaining clothing processing tasks and other target edge computing nodes; Based on the allocation relationship value, determining the optimal target edge computing node to which the remaining clothing processing tasks are allocated.

[0005] In an embodiment, the obtaining the allocation relationship value between the remaining clothing processing tasks and other target edge computing nodes includes: Determining the execution time corresponding to the remaining clothing processing tasks; Determining the computing power value of the remaining clothing processing tasks allocated to other target edge computing nodes; Determine the allocation relationship value between the remaining garment processing tasks and other target edge computing nodes according to the execution time corresponding to the remaining garment processing tasks and the computing power value allocated to other target edge computing nodes for the remaining garment processing tasks.

[0006] In one embodiment, the determining the optimal target edge computing node to which the remaining garment processing tasks are allocated based on the allocation relationship value includes: Obtain the current delay time of the target edge computing node whose processing time exceeds the preset time; Obtain the average delay time of multiple target edge computing nodes; Determine the optimal target edge computing node to which the remaining garment processing tasks are allocated according to the current delay time of the target edge computing node whose processing time exceeds the preset time, the average delay time of the multiple target edge computing nodes, and the allocation relationship value.

[0007] In one embodiment, the determining the optimal target edge computing node to which the remaining garment processing tasks are allocated according to the current delay time of the target edge computing node whose processing time exceeds the preset time, the average delay time of the multiple target edge computing nodes, and the allocation relationship value includes: Update the allocation cost according to the current delay time of the target edge computing node whose processing time exceeds the preset time, the average delay time of the multiple target edge computing nodes, and the allocation relationship value; If the allocation cost is less than the preset cost threshold, then based on the allocation cost, obtain the optimal target edge computing node to which the remaining garment processing tasks are allocated.

[0008] In one embodiment, the updating the allocation cost according to the current delay time of the target edge computing node whose processing time exceeds the preset time, the average delay time of the multiple target edge computing nodes, and the allocation relationship value includes: Obtain the number of iterations; Calculate the partial derivative of the allocation cost with respect to the allocation relationship value; Update the allocation relationship value according to the number of iterations and the partial derivative; Calculate the allocation cost according to the current delay time of the target edge computing node whose processing time exceeds the preset time, the average delay time of the multiple target edge computing nodes, and the updated allocation relationship value.

[0009] In one embodiment, the determining the execution time corresponding to the remaining garment processing tasks includes: If the task type of the remaining garment processing tasks is the cutting type, then obtain the operation image corresponding to the remaining garment processing tasks; Determine the execution time corresponding to the remaining garment processing tasks based on the processing frequency of the worker operations in the operation image.

[0010] In one embodiment, the obtaining the current delay time of the target edge computing node whose processing time exceeds the preset time includes: Determine the garment category of the garment processing task corresponding to the target edge computing node whose processing time exceeds the preset time; Determine the historical garment category that is the same as the garment category; Obtain the historical garment processing tasks corresponding to the historical garment category; Determine the target historical garment processing task whose task type is the same as that of the garment processing task corresponding to the target edge computing node whose processing time exceeds the preset time among the historical garment processing tasks; Calculate the average processing time corresponding to multiple target historical garment processing tasks; wherein, the average processing time is the total required time of the garment processing tasks with the same task type as the target historical garment processing tasks; Based on the multiple average processing times, determine the current delay time of the target edge computing node whose processing time exceeds the preset time.

[0011] In one embodiment, the based on the multiple average processing times, determining the current delay time of the target edge computing node whose processing time exceeds the preset time includes: Calculate the sum of the multiple average processing times as the total required time of the target edge computing node whose processing time exceeds the preset time; Obtain the total execution time of the target edge computing node whose processing time exceeds the preset time; Based on the total required time of the target edge computing node whose processing time exceeds the preset time and the total execution time of the target edge computing node whose processing time exceeds the preset time, determine the current delay time of the target edge computing node whose processing time exceeds the preset time.

[0012] In one embodiment, after determining the optimal target edge computing node to which the remaining garment processing tasks are allocated based on the assignment relation value, the scheduling method of the garment production line further includes: Obtain the execution time of the process type of the garment processing tasks corresponding to each garment order; Obtain the execution time of the cutting type of the garment processing tasks corresponding to each garment order; Display the ratio of the execution time of the process type to the execution time of the cutting type corresponding to each garment order in the form of a progress bar.

[0013] According to another aspect of the present invention, there is provided a scheduling device for a clothing production line, including: An acquisition module, configured to acquire a plurality of clothing orders; An allocation module, configured to allocate the same clothing processing tasks in each clothing order to corresponding target edge computing nodes; wherein, the target edge computing nodes are used to sequentially process the same clothing processing tasks; A scheduling module, configured to, if the processing time of the target edge computing node exceeds a preset time, acquire the remaining clothing processing tasks corresponding to the target edge computing node; wherein, the remaining clothing processing tasks are the tasks that the target edge computing node has not completed within the processing time; acquire the allocation relationship value between the remaining clothing processing tasks and other target edge computing nodes; and determine the optimal target edge computing node to which the remaining clothing processing tasks are allocated based on the allocation relationship value.

[0014] The beneficial effects of the present invention are reflected in that the present invention provides a scheduling method and device for a clothing production line, including: acquiring a plurality of clothing orders, allocating the same clothing processing tasks in each clothing order to corresponding target edge computing nodes, wherein the target edge computing nodes are used to sequentially process the same clothing processing tasks, if the processing time of the target edge computing node exceeds a preset time, acquire the remaining clothing processing tasks corresponding to the target edge computing node; wherein the remaining clothing processing tasks are the tasks that the target edge computing node has not completed within the processing time, acquire the allocation relationship value between the remaining clothing processing tasks and other target edge computing nodes, and determine the optimal target edge computing node to which the remaining clothing processing tasks are allocated based on the allocation relationship value. By detecting the computing delay of the edge computing node and based on the allocation relationship value, the computing power of all edge computing nodes in the production system is automatically rescheduled, avoiding the problems of idle computing power and excessive load on individual devices in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a schematic flowchart of a scheduling method for a clothing production line provided by an exemplary embodiment of the present invention.

[0016] Figure 2 is a schematic structural diagram of task allocation provided by an exemplary embodiment of the present invention.

[0017] Figure 3 is a schematic flowchart of determining an optimal target edge computing node provided by an exemplary embodiment of the present invention.

[0018] Figure 4 is a schematic structural diagram of a scheduling device for a clothing production line provided by an exemplary embodiment of the present invention.

[0019] Figure 5It is a schematic structural diagram of a scheduling device for a clothing production line provided by another exemplary embodiment of the present invention.

[0020] Figure 6 It is a structural diagram of an electronic device provided by an exemplary embodiment of the present invention.

[0021] Reference numerals: 201, acquisition module; 202, allocation module; 203, scheduling module; 2031, first determination unit; 2032, time acquisition unit; 2033, second determination unit; 10, electronic device; 11, processor; 12, memory; 13, input device; 14, output device. Detailed implementation manners

[0022] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0023] Embodiment 1: Figure 1 It is a schematic flowchart of a scheduling method for a clothing production line provided by an exemplary embodiment of the present invention. Figure 2 It is a schematic structural diagram of task allocation provided by an exemplary embodiment of the present invention. Refer to Figure 1-2 As shown, the scheduling method for the clothing production line includes: S110: Obtain multiple clothing orders.

[0024] S120: Allocate the same clothing processing tasks in each clothing order to corresponding target edge computing nodes, where the target edge computing nodes are used to sequentially process the same clothing processing tasks.

[0025] In the embodiment of the present invention, there are clothes of different clothing categories in each clothing order, and the clothing processing tasks required for clothes of different clothing categories are different. For example, the clothing categories may include trousers, skirts, short sleeves, etc. The clothing processing tasks include design tasks, process tasks, cutting tasks, etc. Among them, the process tasks include ironing, rinsing, etc., and the cutting tasks include cutting, machine sewing, embroidery, etc. Determine the same clothing processing tasks from multiple clothing orders, and allocate the same clothing processing tasks to the corresponding target edge computing nodes. The target edge computing nodes process according to the sequentially uploaded clothing processing tasks.

[0026] As Figure 2As shown, the purple circles represent embroidery process tasks, and the red circles represent washing process tasks. The squares corresponding to the purple circles represent edge computing nodes responsible for analyzing embroidery process tasks, and the squares corresponding to the red circles represent edge computing nodes responsible for washing process tasks.

[0027] S130: If the processing time of the target edge computing node exceeds the preset time, obtain the remaining garment processing tasks corresponding to the target edge computing node, where the remaining garment processing tasks are the tasks that the target edge computing node has not completed within the processing time.

[0028] In the embodiments of the present invention, if the processing time of the target edge computing node exceeds the preset time, it means that the target edge computing node has a delay. Then, it is necessary to schedule the remaining garment processing tasks in the target edge computing node to prevent other edge computing nodes from being idle and the target edge computing node from having a congestion in task processing.

[0029] S140: Obtain the distribution relationship value between the remaining garment processing tasks and other target edge computing nodes.

[0030] S150: Based on the distribution relationship value, determine the optimal target edge computing node to which the remaining garment processing tasks are assigned.

[0031] Embodiment 2: In an embodiment, S140 can be specifically implemented as follows: Determine the execution time corresponding to the remaining garment processing tasks; Determine the computing power value of the remaining garment processing tasks assigned to other target edge computing nodes; According to the execution time corresponding to the remaining garment processing tasks and the computing power value of the remaining garment processing tasks assigned to other target edge computing nodes, determine the distribution relationship value between the remaining garment processing tasks and other target edge computing nodes.

[0032] In the embodiments of the present invention, determining the execution time corresponding to the remaining garment processing tasks may include the following steps: If the task type of the remaining garment processing tasks is the cutting type, obtain the operation image corresponding to the remaining garment processing tasks; Based on the processing frequency of the workers' operations in the operation image, determine the execution time corresponding to the remaining garment processing tasks.

[0033] In the present invention, due to different processing means corresponding to the garment processing tasks, the execution times corresponding to the garment processing tasks are different. If the task type of the remaining garment processing tasks is the cutting type, obtain the operation image corresponding to the remaining garment processing tasks. The operation image is the image captured by the camera when the workers are processing. By analyzing the processing frequency of each worker, the execution time corresponding to the remaining garment processing tasks can be determined. It should be understood that the cutting type tasks mainly rely on workers for operation, and the operation model is relatively fixed. Specific tools are mainly used to process fabrics or garments, only the processing positions are different. For example, the specific tool is scissors.

[0034] Specifically, the tool taken by the worker is determined by operating the image, and the type of the tool is identified. For example, the tool can be scissors, needles, etc. According to the type of the tool, the processing frequency of the worker is determined. For example, if the tool is scissors, the closing to opening of the scissors on the clothing is counted as one processing time. Until the worker finishes cutting, the number of times the scissors close to open is counted as the processing frequency of the worker during cutting.

[0035] If the task type of the remaining clothing processing task is a process type, the operation time corresponding to the process type task can be directly obtained as its execution time. Specifically, the process data unit is responsible for collecting process processing progress data, such as ironing, rinsing, etc. These processes usually have clear operation times, so the execution time can be determined by calculating the operation time of the target process.

[0036] If the task type of the remaining clothing processing task is a design type, the operation time uploaded by the designer or pattern maker is obtained as the execution time of the remaining clothing processing task.

[0037] Furthermore, after obtaining the execution time of the remaining clothing processing task, the computing power value of the remaining clothing processing task assigned to other target edge computing nodes is obtained. The computing power value refers to the ability of each edge computing node to execute tasks per unit time. When the remaining clothing processing tasks cannot be continued to be processed on the original node, these tasks need to be transferred to other target edge computing nodes. In order to reasonably allocate tasks, it is necessary to evaluate the "computing power value" of the target nodes. The computing power value of the node determines its task processing speed, efficiency or possible delay, which in turn affects the task allocation decision. For example, there are multiple target edge computing nodes, and the computing power of each node is different. Specifically, the computing power value of node A is 15 (which means it can process 15 tasks per second). The computing power value of node B is 10 (it can process 10 tasks per second). The computing power value of node C is 5 (it can process 5 tasks per second). If the remaining tasks need to be processed within the unit time and the current node cannot process all tasks, the tasks can be allocated according to the computing power values of these target nodes. For example, more tasks are preferentially allocated to the node with stronger computing power (node A), followed by node B and node C.

[0038] Embodiment 3: Figure 3 It is a schematic flowchart of determining the optimal target edge computing node provided by an exemplary embodiment of the present invention. Refer to Figure 3 , S150 may include: S151: Obtain the current delay time of the target edge computing node whose processing time exceeds the preset time.

[0039] S152: Obtain the average latency of multiple target edge computing nodes.

[0040] S153: Determine the optimal target edge computing node for allocating the remaining garment processing tasks according to the current latency of the target edge computing nodes whose processing time exceeds the preset time, the average latency of multiple target edge computing nodes, and the allocation relationship value.

[0041] In the embodiment of the present invention, according to the current latency of the target edge computing nodes whose processing time exceeds the preset time and the average latency of multiple target edge computing nodes, the current latency of the target edge computing nodes whose processing time exceeds the preset time is updated.

[0042] Specifically, the calculation formula for the updated current latency of the target edge computing node is: , where is the learning rate, k represents the number of iterations, represents the current latency of the target edge computing node whose processing time exceeds the preset time, represents the average latency of multiple target edge computing nodes, represents the second weight. Among them, multiple target edge computing nodes represent all target edge computing nodes.

[0043] It can be understood that the latency of the current node i has a gap with the average latency of all nodes . The gap indicates whether the latency of node i is higher or lower than the average value. If the gap is positive, it means that the latency of node i is higher than the average value; if the gap is negative, it means that the latency of node i is lower than the average value. The gap is multiplied by a second weight to obtain the adjustment amount of the latency of node i. If the latency of node i is higher than the average value, then is positive, and the formula will decrease , making it tend to the average value . If the latency of node i is lower than the average value, then is negative, and the formula will increase , making it tend to the average value.

[0044] The parameter controls the step size of the adjustment. If takes a larger value, the adjustment amplitude per iteration is larger, but it may cause oscillation or instability; if The value is relatively small, and the adjustment amplitude for each iteration is small, so the adjustment process will be smoother and more stable. In this way, through successive updates, the latency of each node gradually approaches the average latency, achieving the overall load balancing of the system. By executing the formula multiple times, the of each node will be continuously adjusted and finally tend to the average latency of the system. This adjustment process can effectively balance the workload of each node in the system, prevent some nodes from being overloaded while other nodes are idle, thus achieving the goal of load balancing.

[0045] Embodiment 4: In one embodiment, S153 may be specifically implemented as follows: Update the allocation cost according to the current latency of the target edge computing node whose processing time exceeds the preset time, the average latency of multiple target edge computing nodes, and the allocation relationship value; if the allocation cost is less than the preset cost threshold, then based on the allocation cost, obtain the optimal target edge computing node for allocating the remaining clothing processing tasks.

[0046] In the embodiments of the present invention, the current latency of other target edge computing nodes after update can be obtained according to the current latency of the target edge computing node whose processing time exceeds the preset time and the average latency of multiple target edge computing nodes, and then the allocation cost can be calculated in combination with the allocation relationship value.

[0047] Among them, the calculation formula of the allocation cost is: where, is the first weight, M is 0, 1…, M, M represents the total computing power of other target edge computing nodes allocated to the remaining clothing processing tasks , N is 0, 1…, N, N represents the total number of nodes of the target edge computing node whose processing time exceeds the preset time, represents the current latency of the target edge computing node whose processing time exceeds the preset time, represents the average latency of multiple target edge computing nodes, represents the second weight, represents the remaining clothing processing tasks corresponding execution time, represents the computing power of other target edge computing nodes allocated to the remaining clothing processing tasks .

[0048] If the allocation cost value is the smallest, determine the optimal target edge computing node for allocating the remaining clothing processing tasks through the allocation relationship value in the allocation cost value.

[0049] Embodiment 5: In one embodiment, S153 may be specifically implemented as follows: obtain the number of iterations; calculate the partial derivative of the allocation cost with respect to the allocation relationship value; update the allocation relationship value according to the number of iterations and the partial derivative; calculate the allocation cost according to the current delay time of the target edge computing node whose processing time exceeds the preset time, the average delay time of multiple target edge computing nodes, and the updated allocation relationship value. The present invention realizes the reasonable allocation of tasks and the load balancing of the system by minimizing the objective function C.

[0050] In the embodiment of the present invention, the remaining clothing processing tasks with other target edge computing nodes of the allocation relationship uses binary decision variables to represent. When is 1, it means that the remaining clothing processing tasks are allocated to other target edge computing nodes . When is 0, it means that the allocation is not completed.

[0051] Specifically, by using the linear relaxation method to convert the calculation formula of the allocation cost into continuous variable optimization, the calculation formula of the allocation relationship value can be obtained as: ; where is the learning rate, is the partial derivative of the allocation cost with respect to , and k represents the number of iterations.

[0052] According to formula it can be obtained that in each iteration, it is necessary to calculate the gradient of the objective function C with respect to each allocation coefficient in the current situation. Then multiply by the learning rate to control the step size of each update. Selecting a suitable can not only converge quickly but also not oscillate. Finally, subtract the gradient adjustment amount from the current allocation coefficient to obtain the allocation coefficient for the next iteration step.

[0053] In one embodiment, before S130, the scheduling method of the clothing production line can be specifically implemented as follows: determining the clothing category of the clothing processing task corresponding to the target edge computing node whose processing time exceeds the preset time; determining the historical clothing category that is the same as the clothing category; obtaining the historical clothing processing task corresponding to the historical clothing category; wherein, the historical clothing processing task and the clothing processing task have the same task type; calculating the average processing time corresponding to multiple historical clothing processing tasks; wherein, the average processing time is the total required time of the clothing processing task corresponding to the target edge computing node whose processing time exceeds the preset time; based on multiple average processing times, determining the current delay time of the target edge computing node whose processing time exceeds the preset time.

[0054] In the embodiment of the present invention, after receiving an order, the category of the order (such as tops / trousers / skirts, etc.) and the process complexity (such as embroidery / printing / washing, etc.) will be automatically parsed first. Subsequently, according to different production lines, the productivity requirements for the target production volume in the order are calculated. The productivity requirements calculation can be obtained by calculating the average processing time of a single piece of clothing under a single process (the average processing time can be obtained from historical data). Therefore, for a single order, the total production requirements for each category of clothing in the order at different processing links are obtained.

[0055] For the clothing processing tasks corresponding to the target edge computing nodes whose processing time exceeds the preset time, there are different categories of clothing. Therefore, it is necessary to determine the clothing category corresponding to the clothing processing task, such as trousers, clothes, skirts, etc. Then determine the historical clothing category that is the same as the clothing category, then obtain the historical clothing processing task of the historical clothing category, and determine the target historical clothing processing task with the same task type as the clothing processing task corresponding to other target edge computing nodes from the historical clothing processing tasks. Then calculate the average processing time corresponding to multiple target historical clothing processing tasks. For example, the clothing category of the clothing processing task A of the target edge computing node whose processing time exceeds the preset time is trousers. Determine the historical clothing processing task B of trousers, and select the target historical clothing processing task C with the same task type as the clothing processing task A from the historical clothing processing task B. Obtain the task execution times of multiple target historical clothing processing tasks C, and calculate their average processing time. This average processing time is the total required time of the clothing processing task A. Since the clothing categories of the clothing processing tasks corresponding to the target edge computing nodes whose processing time exceeds the preset time are different, there are multiple average processing times. Calculating multiple average processing times is the total required time of the target edge nodes whose processing time exceeds the preset time.

[0056] In one embodiment, the scheduling method of the clothing production line can be specifically implemented as follows: calculate the sum of multiple average processing times as the total required time of the target edge computing node whose processing time exceeds the preset time; obtain the total execution time of the target edge computing node whose processing time exceeds the preset time; based on the total required time of the target edge computing node whose processing time exceeds the preset time and the total execution time of the target edge computing node whose processing time exceeds the preset time, determine the current delay time of the target edge computing node whose processing time exceeds the preset time.

[0057] In an embodiment of the present invention, if the total required time of the target edge computing node whose processing time exceeds the preset time is lower than the total execution time of the target edge computing node whose processing time exceeds the preset time, it indicates that the target edge computing node whose processing time exceeds the preset time has a delay. The difference between the total execution time and the total required time is the current delay time of the target edge computing node whose processing time exceeds the preset time.

[0058] In one embodiment, S150 can be specifically implemented as follows: obtain the execution time of the clothing processing task corresponding to each clothing order with the type of process type; obtain the execution time of the clothing processing task corresponding to each clothing order with the type of cutting type; display the ratio between the execution time of the process type and the execution time of the cutting type corresponding to each clothing order in the form of a progress bar.

[0059] In an embodiment of the present invention, calculate the ratio between the execution time of the clothing processing task corresponding to each clothing order with the type of process type and the execution time of the clothing processing task corresponding to each clothing order with the type of cutting type, and then display it in categories according to each order in the form of a progress bar. For the clothing processing task corresponding to each clothing order with the type of design type, display it according to the values reported by several personnel.

[0060] In an embodiment of the present invention, relevant staff upload and visualize the design or pattern-making progress they are responsible for. The uploaded data includes the order number and progress (in the form of a percentage). For process-type processing tasks, the present invention uses a barcode scanner to scan the production barcode of the processed clothing or fabric to obtain the identity information. When the process-related equipment starts, the working data of the equipment and the identity information will be uploaded to the associated edge computing device. The equipment working data includes: equipment startup time, equipment planned working duration. The cutting-type processing task captures image data through a camera and uploads it to the edge computing device.

[0061] Figure 4 It is a schematic structural diagram of a scheduling device for a clothing production line provided by an exemplary embodiment of the present invention. Refer to Figure 4, the scheduling device of the clothing production line includes: an obtaining module 201 for obtaining multiple clothing orders; an allocating module 202 for allocating the same clothing processing tasks in each clothing order to corresponding target edge computing nodes, where the target edge computing nodes are used to process the same clothing processing tasks in sequence; a scheduling module 203 for, if the processing time of a target edge computing node exceeds a preset time, obtaining the remaining clothing processing tasks corresponding to the target edge computing node, where the remaining clothing processing tasks are the tasks that the target edge computing node has not completed within the processing time; obtaining the allocation relationship value between the remaining clothing processing tasks and other target edge computing nodes; and determining the optimal target edge computing node for allocating the remaining clothing processing tasks based on the allocation relationship value. Figure 5 FIG. is a schematic structural diagram of a scheduling device for a clothing production line provided by another exemplary embodiment of the present invention. Refer to Figure 5 , the scheduling module 203 may include: a first determining unit 2031 for determining the execution time corresponding to the remaining clothing processing tasks; determining the computing power value of allocating the remaining clothing processing tasks to other target edge computing nodes; and determining the allocation relationship value between the remaining clothing processing tasks and other target edge computing nodes according to the execution time corresponding to the remaining clothing processing tasks and the computing power value of allocating the remaining clothing processing tasks to other target edge computing nodes.

[0062] In one embodiment, the scheduling module 203 may include: a time obtaining unit 2032 for obtaining the current delay time of other target edge computing nodes; obtaining the average delay time of multiple target edge computing nodes; and a second determining unit 2033 for determining the optimal target edge computing node for allocating the remaining clothing processing tasks according to the current delay time of other target edge computing nodes, the average delay time of multiple target edge computing nodes, and the allocation relationship value.

[0063] In one embodiment, the second determining unit 2033 may be specifically configured to: update the allocation cost according to the current delay time of other target edge computing nodes, the average delay time of multiple target edge computing nodes, and the allocation relationship value; and if the allocation cost is less than a preset cost threshold, obtain the optimal target edge computing node for allocating the remaining clothing processing tasks based on the allocation cost.

[0064] In one embodiment, the second determining unit 2033 may be specifically configured to: obtain the number of iterations; calculate the partial derivative of the allocation cost with respect to the allocation relationship value; update the allocation relationship value according to the number of iterations and the partial derivative; and calculate the allocation cost according to the current delay time of other target edge computing nodes, the average delay time of multiple target edge computing nodes, and the updated allocation relationship value.

[0065] In one embodiment, the first determination unit 2031 may be specifically configured to: if the task type of the remaining garment processing task is the cutting type, obtain the operation image corresponding to the remaining garment processing task; and determine the execution time corresponding to the remaining garment processing task based on the processing frequency of the worker operation in the operation image.

[0066] In one embodiment, the time acquisition unit 2032 may be specifically configured to: determine the garment category of the garment processing task corresponding to other target edge computing nodes; determine the historical garment category that is the same as the garment category; obtain the historical garment processing task corresponding to the historical garment category; determine the target historical garment processing task whose task type is the same as that of the garment processing task corresponding to other target edge computing nodes among the historical garment processing tasks; calculate the average processing time corresponding to multiple target historical garment processing tasks; where the average processing time is the total required time of the garment processing tasks with the same task type as the target historical garment processing task; and determine the current latency time of other target edge computing nodes based on the multiple average processing times. In one embodiment, the time acquisition unit 2032 may be specifically configured to: calculate the sum of multiple average processing times as the total required time of other target edge computing nodes; obtain the total execution time of other target edge computing nodes; and determine the current latency time of other target edge computing nodes based on the total required time of other target edge computing nodes and the total execution time of other target edge computing nodes.

[0067] In one embodiment, after the scheduling module 203, the scheduling device of the garment production line may be specifically configured to: obtain the execution time of the garment processing task corresponding to each garment order whose task type is the process type; obtain the execution time of the garment processing task corresponding to each garment order whose task type is the cutting type; and display the ratio of the execution time of the process type to the execution time of the cutting type corresponding to each garment order in the form of a progress bar.

[0068] [[ID=!1]] Figure 6 The block diagram of an electronic device according to an embodiment of the present application is illustrated.

[0069] As Figure 6 shown, the electronic device 10 includes one or more processors 11 and a memory 12.

[0070] The processor 11 may be a central processing unit (CPU) or other form of processing unit having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0071] The memory 12 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage media, and the processor 11 may run the program instructions to implement the scheduling method of the clothing production line in the various embodiments of the present application above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage media.

[0072] In one example, the electronic device 10 may further include: an input device 13 and an output device 14, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0073] When the electronic device 10 is a stand-alone device, the input device 13 may be a communication network connector for receiving the collected input signals from the first device and the second device.

[0074] In addition, the input device 13 may further include, for example, a keyboard, a mouse, and so on.

[0075] The output device 14 may output various information to the outside, including the determined distance information, direction information, etc. The output device 14 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0076] Of course, for simplicity, Figure 6 only some of the components related to the present application in the electronic device 10 are shown, and components such as buses, input / output interfaces, etc. are omitted. In addition, according to specific application scenarios, the electronic device 10 may further include any other appropriate components.

[0077] The computer program products may be written in any combination of one or more programming languages to write program codes for performing the operations of the embodiments of the present application. The programming languages include object-oriented programming languages, such as Java, C++, etc., and also include conventional procedural programming languages, such as the "C" language or similar programming languages. The program codes may be executed entirely on the user computing device, partially on the user device, executed as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0078] A computer-readable storage medium may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable 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.

[0079] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A scheduling method for a clothing production line, characterized in that Including: Obtain multiple clothing orders; Assign the same clothing processing tasks in each clothing order to corresponding target edge computing nodes; wherein, the target edge computing nodes are used to sequentially process the same clothing processing tasks; If the processing time of the target edge computing node exceeds the preset time, obtain the remaining clothing processing tasks corresponding to the target edge computing node; wherein, the remaining clothing processing tasks are the tasks not completed by the target edge computing node within the processing time; Obtain the allocation relationship value between the remaining clothing processing tasks and other target edge computing nodes; Based on the allocation relationship value, determine the optimal target edge computing node for allocating the remaining clothing processing tasks.

2. The scheduling method of the clothing production line according to claim 1, wherein, The obtaining the allocation relationship value between the remaining clothing processing tasks and other target edge computing nodes includes: Determine the execution time corresponding to the remaining clothing processing tasks; Determine the computing power value of allocating the remaining clothing processing tasks to other target edge computing nodes; According to the execution time corresponding to the remaining clothing processing tasks and the computing power value of allocating the remaining clothing processing tasks to other target edge computing nodes, determine the allocation relationship value between the remaining clothing processing tasks and other target edge computing nodes.

3. The scheduling method of the clothing production line according to claim 1, wherein The determining the optimal target edge computing node for allocating the remaining clothing processing tasks based on the allocation relationship value includes: Obtain the current delay time of the target edge computing node whose processing time exceeds the preset time; Obtain the average delay time of multiple target edge computing nodes; According to the current delay time of the target edge computing node whose processing time exceeds the preset time, the average delay time of the multiple target edge computing nodes, and the allocation relationship value, determine the optimal target edge computing node for allocating the remaining clothing processing tasks.

4. The scheduling method of the clothing production line according to claim 3, characterized in that, The according to the current delay time of the target edge computing node whose processing time exceeds the preset time, the average delay time of the multiple target edge computing nodes, and the allocation relationship value, determining the optimal target edge computing node for allocating the remaining clothing processing tasks includes: According to the current delay time of the target edge computing node whose processing time exceeds the preset time, the average delay time of the multiple target edge computing nodes, and the allocation relationship value, update the allocation cost; If the allocation cost is less than the preset cost threshold, based on the allocation cost, obtain the optimal target edge computing node for allocating the remaining clothing processing tasks.

5. The scheduling method of the clothing production line according to claim 4, characterized in that, The according to the current delay time of the target edge computing node whose processing time exceeds the preset time, the average delay time of the multiple target edge computing nodes, and the allocation relationship value, updating the allocation cost includes: Obtain the number of iterations; Calculate the partial derivative of the allocation cost with respect to the allocation relationship value; According to the number of iterations and the partial derivative, update the allocation relationship value; According to the current delay time of the target edge computing node whose processing time exceeds the preset time, the average delay time of the multiple target edge computing nodes, and the updated allocation relationship value, calculate the allocation cost.

6. The scheduling method of the clothing production line according to claim 2, characterized in that, The determining the execution time corresponding to the remaining clothing processing tasks includes: If the task type of the remaining garment processing task is a cutting type, obtain the operation image corresponding to the remaining garment processing task; Based on the processing frequency of the worker's operation in the operation image, determine the execution time corresponding to the remaining garment processing task.

7. The scheduling method of the clothing production line according to claim 3, characterized in that, The obtaining of the current delay time of the target edge computing node whose processing time exceeds the preset time includes: Determine the garment category of the garment processing task corresponding to the target edge computing node whose processing time exceeds the preset time; Determine the historical garment category that is the same as the garment category; Obtain the historical garment processing task corresponding to the historical garment category; Determine the target historical garment processing task whose task type is the same as that of the garment processing task corresponding to the target edge computing node whose processing time exceeds the preset time among the historical garment processing tasks; Calculate the average processing time corresponding to multiple target historical garment processing tasks; wherein, the average processing time is the total required time of the garment processing tasks with the same task type as the target historical garment processing task; Based on multiple average processing times, determine the current delay time of the target edge computing node whose processing time exceeds the preset time.

8. The scheduling method of the clothing production line according to claim 7, characterized in that, The determining of the current delay time of the target edge computing node whose processing time exceeds the preset time based on multiple average processing times includes: Calculate the sum of the multiple average processing times as the total required time of the target edge computing node whose processing time exceeds the preset time; Obtain the total execution time of the target edge computing node whose processing time exceeds the preset time; Based on the total required time of the target edge computing node whose processing time exceeds the preset time and the total execution time of the target edge computing node whose processing time exceeds the preset time, determine the current delay time of the target edge computing node whose processing time exceeds the preset time.

9. The scheduling method of the clothing production line according to claim 1, characterized in that, After determining the optimal target edge computing node to which the remaining garment processing task is allocated based on the allocation relationship value, it further includes: Obtain the execution time of the garment processing task of each garment order whose task type is a process type; Obtain the execution time of the garment processing task of each garment order whose task type is a cutting type; Display the ratio between the execution time of the process type and the execution time of the cutting type corresponding to each garment order in the form of a progress bar.

10. A scheduling device for a clothing production line, characterized in that, Includes: An obtaining module, configured to obtain multiple garment orders; An allocation module, configured to allocate the same garment processing tasks in each garment order to the corresponding target edge computing nodes; wherein, the target edge computing nodes are used to sequentially process the same garment processing tasks; A scheduling module, configured to, if the processing time of the target edge computing node exceeds the preset time, obtain the remaining garment processing tasks corresponding to the target edge computing node; wherein, the remaining garment processing tasks are the tasks that the target edge computing node has not completed within the processing time; obtain the allocation relationship value between the remaining garment processing tasks and other target edge computing nodes; and based on the allocation relationship value, determine the optimal target edge computing node to which the remaining garment processing tasks are allocated.

Images