Furniture production task automatic matching method and system based on intelligent manufacturing

Abstract

The invention relates to the technical field of production task decision making, in particular to a furniture production task automatic matching method and system based on intelligent manufacturing. And extracting personalized demand information corresponding to the production task, converting the personalized demand information into standard design parameters, and generating a customized task. The production task is disassembled into a plurality of sub-tasks, and each sub-task has independent attributes including process requirements, resource requirements and time requirements; and performing one-to-one mapping on the customized tasks and the subtasks to generate an execution plan. Performing resource matching by using a constraint algorithm based on the execution plan and the existing production resource information to obtain a production plan; and obtaining an optimal scheduling plan by using a constraint algorithm according to the production plan. And based on the real-time production data and the burst information, adjusting the optimal scheduling plan through the data analysis model to obtain a final scheduling plan. The method can cope with emergencies or real-time data changes, and manual decisions are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of production task decision making, and in particular to an automatic matching method and system for furniture production tasks based on intelligent manufacturing. Background Art

[0002] With the continuous development of intelligent manufacturing technology, the furniture production industry is gradually transforming towards automation, flexibility and intelligence. Traditional furniture production relies on manual scheduling and management. The production process is complex and easily affected by external uncertainties such as equipment failure, material shortages and order changes. This traditional production method is not only inefficient, but also difficult to respond quickly to changes in market demand and fluctuations in the production environment, which can easily lead to production plan delays, resource waste and high management costs. Therefore, how to improve production efficiency, optimize resource allocation and enhance production flexibility has become an urgent problem that furniture manufacturers need to solve.

[0003] At present, intelligent manufacturing technology in the field of furniture production has made certain progress. For example, customized production can be achieved through digital design and 3D modeling technology; the production scheduling system introduces constraint optimization algorithms such as mixed integer linear programming (MILP) and constraint programming (CP) to improve the efficiency of production task allocation; the real-time monitoring system collects production data through the Internet of Things technology to assist in production process management. However, there are still some shortcomings in the existing technology. The generation process of personalized tasks still lacks sufficient intelligence, usually relying on manual input or semi-automatic operation, and the production scheduling system has poor flexibility and is difficult to cope with dynamic changes and emergencies in production.

[0004] Therefore, an automatic matching method and system for furniture production tasks based on intelligent manufacturing is proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for automatic matching of furniture production tasks based on intelligent manufacturing, which is used to respond to emergencies or real-time data changes and reduce manual decision-making. The personalized demand information corresponding to the production task is extracted, converted into standard design parameters, and customized tasks are generated. The production task is broken down into multiple subtasks, each subtask has independent attributes, including process requirements, resource requirements, and time requirements; customized tasks are mapped one by one with subtasks to generate an execution plan. Based on the execution plan and existing production resource information, a constraint algorithm is used to match resources to obtain a production plan; based on the production plan, a constraint algorithm is used to obtain the optimal scheduling plan. Based on real-time production data and emergency information, the optimal scheduling plan is adjusted through a data analysis model to obtain a final scheduling plan.

[0006] To achieve the above object, the present invention provides the following technical solutions: A method and system for automatically matching furniture production tasks based on intelligent manufacturing, comprising: Personalized task generation: extract the personalized demand information corresponding to the production task, convert it into standard design parameters, and generate customized tasks; Task granularity decomposition: the production task is decomposed into multiple subtasks, each of which has independent attributes, including process requirements, resource requirements and time requirements; the customized task is mapped to the subtasks one by one to generate an execution plan; Intelligent plan matching: Based on the execution plan and existing production resource information, a constraint algorithm is used to match resources and obtain a production plan; based on the production plan, a constraint algorithm is used to obtain an optimal scheduling plan; Real-time monitoring and dynamic adjustment: collect real-time production data and emergency information, the real-time production data includes equipment status, worker operation status, material inventory, production line capacity and production progress; the emergency information includes sudden changes in the supply chain, logistics delays and order changes; based on the real-time production data and emergency information, adjust the optimal scheduling plan through the data analysis model to obtain the final scheduling plan.

[0007] Furthermore, the production task includes order and customer communication information; the personalized demand information is extracted from the order and customer communication information using NLP technology, including furniture type, size, color, function and delivery time; Performing parametric modeling on the personalized demand information and converting it into calculable standard design parameters; The customized task is generated based on the standard design parameters, including a task ID, a design parameter list, production requirements and a priority.

[0008] Furthermore, the plurality of subtasks correspond to design, processing, assembly and inspection links, and each of the subtasks has independent attributes, including process requirements, resource requirements and time requirements; Based on the independent attributes of the subtask, the correlation value between the custom task and the subtask is calculated, and the custom task and the subtask are mapped based on the correlation value to generate the execution plan, including the subtask ID, required resources, required process, required time, priority and constraints.

[0009] Further, the existing production resource information includes resource ID, resource type, current status, available quantity and available time; using a constraint algorithm, analyzing the execution plan, matching it with the existing production resource information, and obtaining a production plan, including resource ID and start time; The resource IDs are preliminarily sorted in time according to the priority and constraints of the execution plan, and a time window is specified according to the start time to constrain scheduling and obtain an initial scheduling plan; based on the initial scheduling plan, the sorting is further adjusted through a genetic algorithm to find the optimal scheduling plan.

[0010] Furthermore, the real-time production data includes equipment status, worker operation status, material inventory, production line capacity and production progress; the sudden information includes sudden changes in the supply chain, logistics delays and order changes; The real-time production data and the emergency information are input into the data analysis model to predict future production data, and to identify deviations and abnormal situations, including equipment failures, material shortages, production process delays, and task changes; and the optimal scheduling plan is adjusted based on the deviations and abnormal situations.

[0011] An automatic matching system for furniture production tasks based on intelligent manufacturing, comprising: The personalized task generation unit extracts the personalized demand information corresponding to the production task, converts it into standard design parameters, and generates customized tasks; A task granularity decomposition unit is used to decompose the production task into multiple subtasks, each of which has independent attributes, including process requirements, resource requirements, and time requirements; the customized task is mapped to the subtasks one by one to generate an execution plan; An intelligent plan matching unit uses a constraint algorithm to match resources based on the execution plan and existing production resource information to obtain a production plan; and uses a constraint algorithm to obtain an optimal scheduling plan based on the production plan; The real-time monitoring and dynamic adjustment unit collects real-time production data and emergency information, wherein the real-time production data includes equipment status, worker operation status, material inventory, production line capacity and production progress; the emergency information includes sudden changes in the supply chain, logistics delays and order changes; based on the real-time production data and emergency information, the optimal scheduling plan is adjusted through a data analysis model to obtain a final scheduling plan.

[0012] Furthermore, the production task includes order and customer communication information; the personalized demand information is extracted from the order and customer communication information using NLP technology, including furniture type, size, color, function and delivery time; Performing parametric modeling on the personalized demand information and converting it into calculable standard design parameters; The customized task is generated based on the standard design parameters, including a task ID, a design parameter list, production requirements and a priority.

[0013] Furthermore, the plurality of subtasks correspond to design, processing, assembly and inspection links, and each of the subtasks has independent attributes, including process requirements, resource requirements and time requirements; Based on the independent attributes of the subtask, the correlation value between the custom task and the subtask is calculated, and the custom task and the subtask are mapped based on the correlation value to generate the execution plan, including the subtask ID, required resources, required process, required time, priority and constraints.

[0014] Further, the existing production resource information includes resource ID, resource type, current status, available quantity and available time; using a constraint algorithm, analyzing the execution plan, matching it with the existing production resource information, and obtaining a production plan, including resource ID and start time; The resource IDs are preliminarily sorted in time according to the priority and constraints of the execution plan, and a time window is specified according to the start time to constrain scheduling and obtain an initial scheduling plan; based on the initial scheduling plan, the sorting is further adjusted through a genetic algorithm to find the optimal scheduling plan.

[0015] Furthermore, the real-time production data includes equipment status, worker operation status, material inventory, production line capacity and production progress; the sudden information includes sudden changes in the supply chain, logistics delays and order changes; The real-time production data and the emergency information are input into the data analysis model to predict future production data, and to identify deviations and abnormal situations, including equipment failures, material shortages, production process delays, and task changes; and the optimal scheduling plan is adjusted based on the deviations and abnormal situations.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. The personalized task generation of the present invention can accurately capture the specific needs of customers by extracting personalized needs from production tasks and converting them into standard design parameters. This not only improves production flexibility, but also reduces manual intervention and errors and improves production efficiency while ensuring the quality of customized products. By automatically generating customized tasks, market demand can be better met, customer satisfaction can be improved, and production delays and errors caused by manual decision-making can be reduced.

[0017] 2. The intelligent plan matching of the present invention can efficiently and accurately optimize resource allocation by using constraint algorithms, combining execution plans with existing production resources. This process reduces the subjectivity of manual decision-making, improves resource utilization efficiency, and avoids resource conflicts or overuse. By accurately matching production resources, it is possible to reduce costs, increase production capacity, and improve the predictability and stability of production while ensuring production quality.

[0018] 3. The real-time monitoring and dynamic adjustment of the present invention can quickly respond to sudden information in the production process through data analysis models, and can promptly discover and solve bottlenecks or problems in production, reducing the risk of production interruptions or delays. This mechanism ensures the flexibility and adaptability of production plans, can adjust the optimal schedule according to real-time changes, improve production efficiency and flexibility, ensure on-time delivery of products, and improve the resilience and reliability of the entire production system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A method flow chart of an automatic matching method for furniture production tasks based on intelligent manufacturing of the present invention; Figure 2 A schematic diagram of the data flow for real-time monitoring and dynamic adjustment of the present invention; Figure 3 This is a flow system structure diagram of an automatic matching system for furniture production tasks based on intelligent manufacturing of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] In order to cope with emergencies or real-time data changes and reduce manual decision-making, the present invention provides a method and system for automatically matching furniture production tasks based on intelligent manufacturing. In order to illustrate the role of the present invention, the effectiveness of the present invention will be illustrated from the following examples.

[0022] Embodiment 1 A Furniture Co., Ltd. is involved in multiple businesses, including woodworking, spraying, assembly and packaging of various furniture. Different processes require different resources and time arrangements. In order to coordinate different tasks in the production plan among multiple processes, A Furniture Co., Ltd. uses an automatic matching method for furniture production tasks based on intelligent manufacturing. Figure 1 , which is a flow chart of a method for automatic matching of furniture production tasks based on intelligent manufacturing.

[0023] Reference Figure 1 Step S01 in the process is to generate personalized tasks: extract personalized demand information corresponding to the production tasks, convert it into standard design parameters, and generate customized tasks.

[0024] Specifically, the production task includes order and customer communication information; the personalized demand information, including furniture type, is extracted from the order and customer communication information using NLP technology. ,size ,color ,Function and delivery time .

[0025] The personalized demand information is parametrically modeled and converted into calculable standard design parameters. Converted into a discrete variable, in this embodiment, includes but is not limited to: Represents sofa; Represents the dining table; Represents sideboards, etc. Dimensions Expressed as ,in The unit is cm. Color Using the RGB model, it is expressed as ,in, It is represented by multiple binary numbers (0 or 1), including whether the component can be adjusted, whether there is a storage function, whether it is manually set, etc. The specific function depends on the specific situation, that is, ,in Indicates the number of functions, Features The value of is either 0 or 1. Delivery time Convert to .

[0026] Generate the customized task based on the standard design parameters , including task ID, design parameter list, production requirements and priority. Task ID is a unique identifier assigned to each custom task to distinguish different tasks. The design parameter list is the core content of each custom task, which contains specific design parameters generated according to customer needs, from furniture type to ,size ,color ,Function Get the specific design parameters of the furniture. Production requirements refer to the specific production conditions and constraints related to the customization task, including production process, resource requirements and quality standards. Priority indicates the urgency of the current customization task among all tasks. Specifically, the factors affecting the priority are the number of days for delivery, the importance of the order, the availability of production resources and the complexity of the functional requirements. The remaining delivery time is determined by the delivery time. Subtract today's date to get; the importance of an order is usually determined by the level of the customer and the size of the order; the availability of production resources takes into account the degree of resource tension. If the resources required for production are tight, the priority of the task will be higher; if the functional requirements are more complex, the priority of the task will be higher. The remaining delivery time, order importance, availability of production resources, and complexity of functional requirements are scored, as shown in Table 1, which shows an example of scoring factors affecting priority.

[0027] Table 1 Example of scoring of priority influencing factors

[0028] The scoring results of remaining delivery time, order importance, availability of production resources, and complexity of functional requirements are weighted with weights of 0.3, 0.25, 0.2, and 0.25 respectively, and the weighted sum is the priority.

[0029] By extracting personalized demand information from production tasks and converting it into standard design parameters to generate customized tasks, this process can ensure that each production task accurately reflects the specific needs of customers. It avoids the "one-size-fits-all" production in the traditional model and improves production efficiency and flexibility. At the same time, by standardizing design parameters, the task transfer and understanding process can be simplified, and the efficiency of cross-departmental collaboration can be improved.

[0030] Further, refer to Figure 1 Step S02 in the process, task granularity decomposition: decomposing the production task into multiple subtasks, each of which has independent attributes, including process requirements, resource requirements and time requirements; mapping the customized task to the subtasks one by one to generate an execution plan.

[0031] Specifically, the plurality of subtasks correspond to design, processing, assembly and inspection links, and each of the subtasks has independent attributes, including process requirements, resource requirements and time requirements; Calculate a correlation value between the custom task and the subtask based on the independent attribute of the subtask , the calculation formula is: ,in, Indicates a custom task and subtasks The relevance value of Indicates a custom task and subtasks The resource matching between them; Indicates a custom task and subtasks The matching degree between the process requirements; Indicates a custom task and subtasks The time requirements between them are matching; , and represents the weight of each factor, and .

[0032] Specifically, custom tasks and subtasks The resource matching between The calculation formula is: ,in, and Represents custom tasks and subtasks The required resource set, Indicates the size of the collection; Custom tasks and subtasks The matching degree between the process requirements The calculation formula is ,in, and Represents custom tasks and subtasks The process steps involved, Indicates process steps and The similarity between Custom tasks and subtasks Time requirements match The calculation formula is , where min means taking the minimum value operation; max means taking the maximum value operation; and Represents custom tasks The earliest and latest completion times, and Represents subtasks The earliest and latest completion times of the .

[0033] Based on the relevance value Customize tasks and subtasks Mapping is performed and the most appropriate subtask is selected based on the relevance value. The mapping rule is that for custom tasks Select the value associated with it The largest subtask To assign tasks: ; in, Representation and Customization Tasks The best matching subtask; Indicates the maximum value operation.

[0034] According to the mapping rules, multiple subtasks with top correlation values ​​are obtained, and the execution plan is generated from these subtasks, including the subtask ID, required resources, required processes, required time, priority and constraints. In order to generate a reasonable execution plan, the priority must be determined according to the urgency and importance of each subtask, and the execution order of the tasks must be further constrained according to the constraints. The priority calculation formula is: ; in, Represents a subtask Corresponding customized tasks Priority; Indicates a custom task and subtasks The relevance value of Represents a subtask the time required; Represents a subtask resource requirements; , and Represents the weight coefficient.

[0035] For each subtask , if there are resource, process or time constraints, they can be expressed through constraints: ; in, represents the decision variable; Indicates The constraint function of each subtask.

[0036] Decomposing production tasks into multiple subtasks and ensuring that each subtask has independent attributes makes task management more refined, which can help optimize resource allocation and scheduling and improve the operability and flexibility of task execution. By managing each subtask independently, potential bottlenecks or resource conflicts can be better discovered, so that production plans can be adjusted in a timely manner to reduce risks and uncertainties in the production process. In addition, granular decomposition can also improve the transparency and traceability of production tasks, which helps optimize the production process.

[0037] Further, refer to Figure 1 Step S03 in the process is intelligent plan matching: based on the execution plan and the existing production resource information, a constraint algorithm is used to match resources to obtain a production plan; based on the production plan, an optimal scheduling plan is obtained using a constraint algorithm.

[0038] Specifically, the existing production resource information includes resource ID, resource type, current status, available quantity and available time; the constraint algorithm is used to analyze the execution plan and match it with the existing production resource information to obtain a production plan, including resource ID and start time. The following variables are defined as shown in Table 2.

[0039] Table 2 Variable definition table

[0040] Determine each subtask in the execution plan Resource requirements for each subtask Corresponding resources The task's process requirements, time requirements and other constraints must be met. Construct the following constraint equation: ; in, Indicates Subtasks Use Resources , otherwise ; Indicates the total number of resources. Indicates the total number of subtasks in the execution plan.

[0041] For each resource , requiring that the total demand in all tasks cannot exceed its available quantity , and must comply with the time window constraint. The specific expression is: ; This means that in all subtasks, resources The total demand cannot exceed the available quantity .

[0042] Each subtask Start time and end time It is also necessary to meet the resource availability time constraints, namely: ; in, Indicates the maximum duration that a resource can be used.

[0043] According to the subtasks in the execution plan The urgency, resource requirements and complexity of the task are used to obtain the priority. . The subtasks in the execution plan are sorted according to their priority Sort and determine the start time and end time : ; in, Represents a subtask In Resources Execution time on .

[0044] According to priority , resource constraints, time window constraints and other constraints to obtain an initial scheduling plan; based on the initial scheduling plan, the sorting is further adjusted through a genetic algorithm, and new possible solutions are introduced in combination with mutation operations to find the optimal scheduling plan.

[0045] Based on the execution plan and existing production resource information, the constraint algorithm is used to match resources, thereby optimizing the configuration of production resources. This method can achieve accurate matching of production tasks with existing resources, avoid resource waste, and improve production efficiency. At the same time, the generation of the optimal scheduling plan based on the constraint algorithm helps to improve the rationality of production scheduling and reduce the risk of production delays. This intelligent production scheduling can effectively improve the flexibility and responsiveness of the production process, reduce human intervention, and achieve automated and efficient production.

[0046] Further, refer to Figure 1 Step S04 in real-time monitoring and dynamic adjustment: collect real-time production data and emergency information, the real-time production data includes equipment status, worker operation status, material inventory, production line capacity and production progress; the emergency information includes sudden changes in the supply chain, logistics delays and order changes; based on the real-time production data and emergency information, adjust the optimal scheduling plan through the data analysis model to obtain the final scheduling plan. Figure 2 , showing a data flow diagram for real-time monitoring and dynamic adjustment.

[0047] Specifically, the real-time production data includes equipment status, worker operation status, material inventory, production line capacity and production progress; the emergency information includes sudden changes in the supply chain, logistics delays and order changes; The real-time production data and the emergency information are input into the data analysis model to predict future production data: ; in, express The predicted value at the moment, i.e., future production data; express The production status at the moment; represents the lag order of the model; Represents external factors that affect production status, including worker operation, material inventory, production line capacity, and production progress; Represents a time series forecasting model.

[0048] After predicting the future production data, it is necessary to identify whether there is a problem through deviation and anomaly detection. In this embodiment, an anomaly detection model is defined to calculate the deviation between the predicted value and the actual value, and to determine whether it exceeds the threshold through statistical methods, so as to identify anomalies. For actual production data, For the predicted future production data, the deviation for: . Set the threshold To determine whether the deviation exceeds the standard, and thus determine whether there is an abnormal situation. , it is considered abnormal.

[0049] Deviations and abnormal situations are detected, including equipment failure, material shortage, production process delays and task changes, and the optimal schedule is adjusted based on these situations. The optimal schedule is used as the original schedule , set an objective function to minimize the total cost of the adjusted schedule. The objective function is as follows: ; in, Indicates the original schedule Middle The unit delay cost of a task, Indicates The delay time of each task; Indicates The idle cost of a resource, Indicates The idle time of a resource; Indicates Inventory adjustment cost of each material, Indicates Inventory change of each material; , and Represents the original schedule plan In addition, under the constraints of the order of tasks, resource limitations, and production line capacity, the constrained optimization problem is solved to obtain the final scheduling plan.

[0050] By collecting production data and emergency information in real time and adjusting production plans with the help of data analysis models, uncertainties in the production process can be dealt with in a timely manner. Emergency situations such as machine failures and raw material shortages can be quickly discovered through real-time monitoring and dynamically adjusted in the system to ensure that the production process is not greatly disturbed. This flexibility not only reduces downtime and resource waste, but also improves the adaptability of production plans. With the help of data analysis, potential risks can be predicted and responded to in advance, which helps to improve overall production efficiency and on-time delivery of products.

[0051] Through personalized task generation, task granularity decomposition, intelligent plan matching and real-time monitoring and dynamic adjustment, the production process is automated and optimized. By accurately disassembling tasks, reasonably matching resources and adjusting schedules, production efficiency can be greatly improved and the risk of manual decision-making errors and delays can be reduced. At the same time, real-time data feedback and adjustment mechanisms ensure the flexibility and response speed of production plans, enhance the system's ability to respond to emergencies, improve the intelligence and refinement of furniture production, and improve the efficiency of furniture production.

[0052] Embodiment 2 A furniture customization company B customizes products according to the design or needs provided by customers. Reference Figure 3 , showing the system structure diagram of an automatic matching system for furniture production tasks based on intelligent manufacturing.

[0053] The system includes a personalized task generation unit, which extracts personalized demand information corresponding to the production task, converts it into standard design parameters, and generates customized tasks.

[0054] Specifically, the production task includes order and customer communication information; the personalized demand information, including furniture type, is extracted from the order and customer communication information using NLP technology. ,size ,color ,Function and delivery time .

[0055] The personalized demand information is parametrically modeled and converted into calculable standard design parameters. Converted into a discrete variable, in this embodiment, includes but is not limited to: Represents sofa; Represents the dining table; Represents sideboards, etc. Dimensions Expressed as ,in The unit is cm. Color Using the RGB model, it is expressed as ,in, It is represented by multiple binary numbers (0 or 1), including whether the component can be adjusted, whether there is a storage function, whether it is manually set, etc. The specific function depends on the specific situation, that is, ,in Indicates the number of functions, Features The value of is either 0 or 1. Delivery time Convert to .

[0056] Generate the customized task based on the standard design parameters , including task ID, design parameter list, production requirements and priority. Task ID is a unique identifier assigned to each custom task to distinguish different tasks. The design parameter list is the core content of each custom task, which contains specific design parameters generated according to customer needs, from furniture type to ,size ,color ,Function Get the specific design parameters of the furniture. Production requirements refer to the specific production conditions and constraints related to the customization task, including production process, resource requirements and quality standards. Priority indicates the urgency of the current customization task among all tasks. Specifically, the factors affecting the priority are the number of days for delivery, the importance of the order, the availability of production resources and the complexity of the functional requirements. The remaining delivery time is determined by the delivery time. Subtract today's date to get; The importance of an order is usually determined by the level of the customer and the size of the order; The availability of production resources takes into account the degree of resource tension. If the resources required for production are tight, the priority of the task will be higher; If the functional requirements are more complex, the priority of the task will be higher. Score the remaining delivery time, order importance, availability of production resources, and complexity of functional requirements.

[0057] Furthermore, the system also includes a task granularity decomposition unit, which breaks down the production task into multiple subtasks, each of which has independent attributes, including process requirements, resource requirements and time requirements; maps the customized task to the subtask one by one to generate an execution plan.

[0058] Specifically, the plurality of subtasks correspond to design, processing, assembly and inspection links, and each of the subtasks has independent attributes, including process requirements, resource requirements and time requirements; Calculate a correlation value between the custom task and the subtask based on the independent attribute of the subtask , the calculation formula is: ,in, Indicates a custom task and subtasks The relevance value of Indicates a custom task and subtasks The resource matching between them; Indicates a custom task and subtasks The matching degree between the process requirements; Indicates a custom task and subtasks The time requirements between them are matching; , and represents the weight of each factor, and .

[0059] Specifically, custom tasks and subtasks The resource matching between The calculation formula is: ,in, and Represents custom tasks and subtasks The required resource set, Indicates the size of the collection; Custom tasks and subtasks The matching degree between the process requirements The calculation formula is ,in, and Represents custom tasks and subtasks The process steps involved, Indicates process steps and The similarity between Custom tasks and subtasks Time requirements match The calculation formula is , where min means taking the minimum value operation; max means taking the maximum value operation; and Represents custom tasks The earliest and latest completion times, and Represents subtasks The earliest and latest completion times of the .

[0060] Based on the relevance value Customize tasks and subtasks Mapping is performed and the most appropriate subtask is selected based on the relevance value. The mapping rule is that for custom tasks , select the value associated with it The largest subtask To assign tasks: ; in, Representation and Customization Tasks The best matching subtask; Indicates the maximum value operation.

[0061] According to the mapping rules, multiple subtasks with top correlation values ​​are obtained, and the execution plan is generated from these subtasks, including the subtask ID, required resources, required processes, required time, priority and constraints. In order to generate a reasonable execution plan, the priority must be determined according to the urgency and importance of each subtask, and the execution order of the tasks must be further constrained according to the constraints. The priority calculation formula is: ; in, Represents a subtask Corresponding customized tasks Priority; Indicates a custom task and subtasks The relevance value of Represents a subtask the time required; Represents a subtask resource requirements; , and Represents the weight coefficient.

[0062] For each subtask , if there are resource, process or time constraints, they can be expressed through constraints: ; in, represents the decision variable; Indicates The constraint function of each subtask.

[0063] Furthermore, the system also includes an intelligent plan matching unit, which uses a constraint algorithm to match resources based on the execution plan and existing production resource information to obtain a production plan; based on the production plan, uses a constraint algorithm to obtain an optimal scheduling plan.

[0064] Specifically, the existing production resource information includes resource ID, resource type, current status, available quantity and available time; using a constraint algorithm, the execution plan is analyzed and matched with the existing production resource information to obtain a production plan, including resource ID and start time.

[0065] Determine the execution plan Subtasks Resource requirements, Subtasks The corresponding Resources The task's process requirements, time requirements and other constraints must be met. Construct the following constraint equation: ; in, Indicates Subtasks Use Resources , otherwise ; Indicates the total number of resources. Indicates the total number of subtasks in the execution plan.

[0066] For Resources , requiring that the total demand in all tasks cannot exceed its available quantity , and must comply with the time window constraint. The specific expression is: ; This means that in all subtasks, resources The total demand cannot exceed the available quantity .

[0067] Each subtask Start time and end time It is also necessary to meet the resource availability time constraints, namely: ; in, Indicates the maximum duration that a resource can be used.

[0068] According to the subtasks in the execution plan The urgency, resource requirements and complexity of the task are used to obtain the priority. . The subtasks in the execution plan are sorted according to their priority Sort and determine the start time and end time : ; in, Represents a subtask In Resources Execution time on .

[0069] According to priority , resource constraints, time window constraints and other constraints to obtain an initial scheduling plan; based on the initial scheduling plan, the sorting is further adjusted through a genetic algorithm, and new possible solutions are introduced in combination with mutation operations to find the optimal scheduling plan.

[0070] Furthermore, the system also includes a real-time monitoring and dynamic adjustment unit to collect real-time production data and emergency information, wherein the real-time production data includes equipment status, worker operation status, material inventory, production line capacity and production progress; the emergency information includes sudden changes in the supply chain, logistics delays and order changes; based on the real-time production data and emergency information, the optimal scheduling plan is adjusted through a data analysis model to obtain a final scheduling plan.

[0071] Specifically, the real-time production data includes equipment status, worker operation status, material inventory, production line capacity and production progress; the emergency information includes sudden changes in the supply chain, logistics delays and order changes; The real-time production data and the emergency information are input into the data analysis model to predict future production data: ; in, express The predicted value at the moment, i.e., future production data; express The production status at the moment; represents the lag order of the model; Represents external factors that affect production status, including worker operation, material inventory, production line capacity, and production progress; Represents a time series forecasting model.

[0072] After predicting the future production data, it is necessary to identify whether there is a problem through deviation and anomaly detection. In this embodiment, an anomaly detection model is defined to calculate the deviation between the predicted value and the actual value, and to determine whether it exceeds the threshold through statistical methods, so as to identify anomalies. For actual production data, For the predicted future production data, the deviation for: . Set the threshold To determine whether the deviation exceeds the standard, and thus determine whether there is an abnormal situation. , it is considered abnormal.

[0073] Deviations and abnormal situations are detected, including equipment failure, material shortage, production process delays and task changes, and the optimal schedule is adjusted based on these situations. The optimal schedule is used as the original schedule , set an objective function to minimize the total cost of the adjusted schedule. The objective function is as follows: ; in, Indicates the original schedule Middle The unit delay cost of a task, Indicates The delay time of each task; Indicates The idle cost of a resource, Indicates The idle time of a resource; Indicates Inventory adjustment cost of each material, Indicates Inventory change of each material; , and Represents the original schedule plan In addition, under the constraints of the order of tasks, resource limitations, and production line capacity, the constrained optimization problem is solved to obtain the final scheduling plan.

[0074] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A furniture production task automatic matching method based on intelligent manufacturing, characterized in that: include: Personalized task generation: extract the personalized demand information corresponding to the production task, convert it into standard design parameters, and generate customized tasks; Task granularity decomposition: the production task is decomposed into multiple subtasks, each of which has independent attributes, including process requirements, resource requirements and time requirements; Mapping the customized tasks to the subtasks one by one to generate an execution plan; Intelligent plan matching: Based on the execution plan and existing production resource information, a constraint algorithm is used to match resources and obtain a production plan; According to the production plan, an optimal scheduling plan is obtained using a constraint algorithm; Real-time monitoring and dynamic adjustment: collect real-time production data and emergency information, the real-time production data includes equipment status, worker operation status, material inventory, production line capacity and production progress; the emergency information includes sudden changes in the supply chain, logistics delays and order changes; based on the real-time production data and emergency information, adjust the optimal scheduling plan through the data analysis model to obtain the final scheduling plan.

2. According to the method of automatic matching of furniture production tasks based on intelligent manufacturing according to claim 1, it is characterized in that: The production task includes order and customer communication information; using NLP technology to extract the personalized demand information from the order and customer communication information, including furniture type, size, color, function and delivery time; Performing parametric modeling on the personalized demand information and converting it into calculable standard design parameters; The customized task is generated based on the standard design parameters, including a task ID, a design parameter list, production requirements and a priority.

3. According to the method of automatic matching of furniture production tasks based on intelligent manufacturing in claim 1, it is characterized in that: The multiple subtasks correspond to the design, processing, assembly and inspection links, and each of the subtasks has independent attributes, including process requirements, resource requirements and time requirements; Based on the independent attributes of the subtask, the correlation value between the custom task and the subtask is calculated, and the custom task and the subtask are mapped based on the correlation value to generate the execution plan, including the subtask ID, required resources, required process, required time, priority and constraints.

4. The automatic matching method for furniture production tasks based on intelligent manufacturing according to claim 1 is characterized in that: The existing production resource information includes resource ID, resource type, current status, available quantity and available time; Using a constraint algorithm, analyzing the execution plan, matching it with the existing production resource information, and obtaining a production plan, including a resource ID and a start time; Preliminarily sort the resource IDs in time according to the priority and constraint conditions of the execution plan, and specify a time window according to the start time to constrain the scheduling and obtain an initial scheduling plan; Based on the initial scheduling plan, the sorting is further adjusted through a genetic algorithm to find the optimal scheduling plan.

5. The method for automatically matching furniture production tasks based on intelligent manufacturing according to claim 1 is characterized in that: The real-time production data includes equipment status, worker operation status, material inventory, production line capacity and production progress; the emergency information includes sudden changes in the supply chain, logistics delays and order changes; The real-time production data and the emergency information are input into the data analysis model to predict future production data, and to identify deviations and abnormal situations, including equipment failures, material shortages, production process delays, and task changes; and the optimal scheduling plan is adjusted based on the deviations and abnormal situations.

6. An automatic matching system for furniture production tasks based on intelligent manufacturing, characterized in that: include: The personalized task generation unit extracts the personalized demand information corresponding to the production task, converts it into standard design parameters, and generates customized tasks; A task granularity decomposition unit, which decomposes the production task into multiple subtasks, each of which has independent attributes, including process requirements, resource requirements and time requirements; Mapping the customized tasks to the subtasks one by one to generate an execution plan; An intelligent plan matching unit, based on the execution plan and existing production resource information, uses a constraint algorithm to perform resource matching to obtain a production plan; According to the production plan, an optimal scheduling plan is obtained using a constraint algorithm; The real-time monitoring and dynamic adjustment unit collects real-time production data and emergency information, wherein the real-time production data includes equipment status, worker operation status, material inventory, production line capacity and production progress; the emergency information includes sudden changes in the supply chain, logistics delays and order changes; based on the real-time production data and emergency information, the optimal scheduling plan is adjusted through a data analysis model to obtain a final scheduling plan.

7. The furniture production task automatic matching system based on intelligent manufacturing according to claim 6 is characterized in that: The production task includes order and customer communication information; using NLP technology to extract the personalized demand information from the order and customer communication information, including furniture type, size, color, function and delivery time; Performing parametric modeling on the personalized demand information and converting it into calculable standard design parameters; The customized task is generated based on the standard design parameters, including a task ID, a design parameter list, production requirements and a priority.

8. The furniture production task automatic matching system based on intelligent manufacturing according to claim 6 is characterized in that: The multiple subtasks correspond to the design, processing, assembly and inspection links, and each of the subtasks has independent attributes, including process requirements, resource requirements and time requirements; Based on the independent attributes of the subtask, the correlation value between the custom task and the subtask is calculated, and the custom task and the subtask are mapped based on the correlation value to generate the execution plan, including the subtask ID, required resources, required process, required time, priority and constraints.

9. The furniture production task automatic matching system based on intelligent manufacturing according to claim 6 is characterized in that: The existing production resource information includes resource ID, resource type, current status, available quantity and available time; Using a constraint algorithm, analyzing the execution plan, matching it with the existing production resource information, and obtaining a production plan, including a resource ID and a start time; Preliminarily sort the resource IDs in time according to the priority and constraint conditions of the execution plan, and specify a time window according to the start time to constrain the scheduling and obtain an initial scheduling plan; Based on the initial scheduling plan, the sorting is further adjusted through a genetic algorithm to find the optimal scheduling plan.

10. The furniture production task automatic matching system based on intelligent manufacturing according to claim 6 is characterized in that: The real-time production data includes equipment status, worker operation status, material inventory, production line capacity and production progress; the emergency information includes sudden changes in the supply chain, logistics delays and order changes; The real-time production data and the emergency information are input into the data analysis model to predict future production data, and to identify deviations and abnormal situations, including equipment failures, material shortages, production process delays, and task changes; and the optimal scheduling plan is adjusted based on the deviations and abnormal situations.

Images