Production resource determination method, electronic equipment and computer readable storage medium

Abstract

The invention provides a production resource determination method, electronic equipment and a computer readable storage medium, and solves the problem that standby materials are inflexible to find when the material inventory is insufficient in the prior art by introducing a dynamic production resource selection strategy. The order data is received, whether the current associated production resources meet the manufacturing requirements or not is judged, and when the inventory is insufficient, the adaptive target replacement production resources are flexibly determined from the production resource library according to the production objects and the preset production resource selection strategy. The method avoids the limitation of dependence on static rules or manual intervention, can adjust the selection of standby materials in real time, improves the flexibility and response speed of resource scheduling, reduces the delay of production scheduling, and improves the production efficiency and the material utilization rate.

Description

Technical Field

[0001] The present invention relates to the technical field of production data processing, and in particular to a method for determining production resources, an electronic device, and a computer-readable storage medium. Background Art

[0002] Sheet metal fabrication involves the processing of sheet metal (e.g., steel or aluminum) into parts or products of desired shapes and sizes through processes such as cutting, stamping, bending, welding, and painting. Production scheduling involves the rational arrangement of production tasks based on factors such as order demand, equipment capacity, and material inventory.

[0003] In the prior art, when an order is received and production scheduling is performed for the materials in the order, and when the corresponding inventory materials are insufficient, there is a technical problem of insufficient flexibility in finding spare materials. Summary of the Invention

[0004] The purpose of the present invention is to overcome the above-mentioned technical deficiencies and provide a method for determining production resources, an electronic device and a computer-readable storage medium to solve the technical problem in the related art that when an order is received and production scheduling is executed for the materials in the order, and when the inventory materials corresponding to the materials are insufficient, it is not flexible enough to find spare materials.

[0005] In order to achieve the above technical objectives, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a method for determining production resources, comprising: receiving order data including at least one production object; Determining whether current associated production resources satisfy the manufacturing requirements of the production object in the order data; wherein the associated production resources represent preset production resources that are adapted to the production object; In the case that the current associated production resources do not meet the manufacturing requirements, based on the production object and a preset production resource selection strategy, a target replacement production resource adapted to the production object is determined from the current production resource library.

[0006] In a second aspect, the present invention provides an electronic device comprising: a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors to enable the one or more processors to implement the above-mentioned method.

[0007] In a third aspect, the present invention provides a computer-readable storage medium, wherein the computer program is stored in the computer-readable storage medium, and the computer program implements the above method when executed by a processor.

[0008] Beneficial effects: This invention addresses the existing issue of inflexible search for backup materials when inventory is insufficient by introducing a dynamic production resource selection strategy. By receiving order data and determining whether the currently associated production resources meet manufacturing needs, when inventory is insufficient, the system flexibly determines suitable target replacement production resources from the production resource library based on the production target and a preset production resource selection strategy. This method avoids the limitations of relying on static rules or manual intervention, enabling real-time adjustments to backup material selection, improving resource scheduling flexibility and responsiveness, thereby reducing production scheduling delays and increasing production efficiency and material utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 This is an architectural diagram of a method for determining production resources provided by an embodiment of the present invention; Figure 2 This is a flow chart of a method for determining production resources provided by an embodiment of the present invention; Figure 3 This is a flow chart of a method for determining production resources provided by an embodiment of the present invention; Figure 4 This is a flow chart of a method for determining production resources provided by an embodiment of the present invention; Figure 5 This is a block diagram of an electronic device used in an embodiment of the present invention. DETAILED DESCRIPTION

[0010] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings 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 in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0011] In modern manufacturing, especially in large-scale and customized production, production scheduling and material management are crucial components. To ensure smooth production, manufacturers typically schedule materials based on order requirements, including allocating and scheduling materials based on the inventory status of the materials required for the order. Current production scheduling systems typically consist of a material management system, a production planning system, and an inventory management system. These interconnected systems ensure smooth production execution through data sharing and collaborative work. Specifically, upon receiving a production order, the material management system schedules production based on the materials required. The production planning system compares material requirements with available inventory. If inventory is insufficient, the system typically issues an automatic alert, requesting the search for backup materials. However, existing systems often rely on fixed rules or manual intervention to select backup materials, often failing to consider the diversity of production processes and actual production needs.

[0012] While it's understandable that pre-configured static rule bases can be used to schedule material preparation, maintaining them is often expensive. Each new material requires manual configuration of all associated rules. For example, when a sheet metal manufacturer introduces a new aluminum alloy, it must develop separate substitution rules for each part that might use it, and the number of rules increases exponentially with the type of material. Furthermore, static rule bases lack adaptability. When the pre-set backup material inventory runs low, the system cannot automatically find a suboptimal solution. For example, a sheet metal manufacturer presets Baosteel steel coils as the only backup resource. When these materials are out of stock, even if other qualified materials (such as Ansteel steel coils of the same specification) are available, the system will still report an error and shut down the line. Therefore, when the system cannot automatically match a suitable backup material based on inventory, manual intervention is often required to identify a suitable alternative. This not only increases operational complexity and time costs but also easily leads to errors and omissions.

[0013] It's understandable that different production targets may have varying requirements for backup materials. For example, some may prioritize cost and quality, while others may prioritize production time. Existing systems often lack the flexibility to adjust the priority of backup material selection, resulting in a lack of flexibility in selecting backup materials for different production targets. More specifically, in sheet metal manufacturing, the priority assigned to backup material selection by the production scheduling system directly impacts production efficiency. For example, in a typical scenario, a sheet metal factory may produce refrigerator casings, air conditioner panels, and washing machine drums. For this refrigerator casing production target, if inventory of the primary material, cold-rolled galvanized steel sheet, is insufficient, the system can select an alternative material based on a preset "lowest unit price first" rule. For example, an alternative steel sheet with similar specifications but higher surface roughness may be selected. While this can reduce direct procurement costs, the differences in material surface properties necessitate additional pretreatment steps in the spray coating process, increasing unit processing costs and ultimately increasing the actual total cost compared to the standard solution. For the air-conditioning panel, for example, during the peak sales season of air conditioners, when the inventory of the main material aluminum alloy plate is insufficient, the system can lock in the alternative material with a 3-day procurement cycle according to the "same specification inventory first" rule, and ignore the slightly thicker plates existing in the workshop (which can be put into production immediately by adjusting the stamping parameters). In this case, the system may lack the ability to perceive the urgency of delivery, resulting in a delayed start of the production plan and missed opportunities to adopt quick response solutions.

[0014] In summary, in the prior art, when an order is received and production scheduling is performed for the materials in the order, and when the corresponding inventory materials are insufficient, there is a technical problem of insufficient flexibility in finding spare materials.

[0015] like Figure 1 and Figure 2 As shown, this embodiment provides a method for determining production resources. The execution subject of the method may be a production management server. The method may include: Step S12: Receive order data containing at least one production object.

[0016] In this embodiment, the receiving action can be represented by the production management server receiving order data containing at least one production object from an external system via a wired or wireless method. Specifically, data exchange with the external system can be carried out via a preset network communication protocol (e.g., HTTP, MQTT, SOAP). The external system can be a customer relationship management server. After detecting that a dealer has placed an order, the customer relationship management server can automatically trigger the generation of an order data packet and send it to the production management server. The external system can also be a factory terminal device, which can be deployed in a workshop office or control room and can run order management software. Planners can manually enter or import data, or order data updates can be triggered by scanning material codes in the warehouse or production line. The external system can also be a mobile terminal. For example, a sales representative or customer can submit customized order data through a mobile app.

[0017] In this embodiment, the production object is represented as an entity to be processed with certain process requirements and physical form during the manufacturing process. Specifically, the production object can be a specific product, or a component or part of a product.

[0018] In a specific scenario example, the production management server may be a production management server deployed in a sheet metal factory, which can produce structures of products such as air conditioners and refrigerators. Therefore, in the scenario example, the production objects may be refrigerator side panels, air conditioner brackets, oven doors, etc.

[0019] In this embodiment, the order data may be text data, image data (eg, an image of the order), or structured data (eg, structured data in JSON or XML format).

[0020] In this embodiment, the order data may include one production object or multiple production objects.

[0021] In this embodiment, in the order data, the production object may correspond to identification information and attribute information. Specifically, the identification information is the identity identification information of the production object, such as a product code, component code, or material code, etc. The attribute information may further include first attribute information and second attribute information. The first attribute information may be directly included in the order data. The first attribute information may be personalized parameter data for the production object proposed by the customer (for example, personalized material specifications, quantity information, order time and delivery time, etc.). The second attribute information may be included in the order data or not, and may be configured in the production management server (for example, the second attribute information can be directly queried through the identity identification information). The second attribute information may be the conventional material specifications (standard material grades, dimensions, etc.), production processes (bending angle tolerance, laser cutting speed, etc.), quality standards, and equipment constraints of the production object.

[0022] In a specific scenario example, a data table (which can be a relational database structure) can be configured in the production management server. The data table can use the identification information of the production object as the primary key. In addition to the identification information field, the data table can also have an attribute information field (for example, a second attribute information field). The second attribute information field can be a standard material brand, a standard thickness range, a standard surface roughness requirement, a standard process route, etc.

[0023] Step S14: Determine whether the current associated production resources meet the manufacturing requirements of the production object in the order data; wherein the associated production resources represent preset production resources that are adapted to the production object.

[0024] In this embodiment, the determination process can be represented as follows: the production management server first determines the identification information and attribute information corresponding to the production object based on the order data. Then, based on the identification information, it determines the corresponding associated production resources from a preset data table. Finally, based on the attribute information (the first attribute information and the second attribute information), it determines whether the current associated production resources meet the manufacturing requirements of the production object.

[0025] Specifically, the production management server can directly parse out the identification information and attribute information from the order data. For example, when the order data is image data, the production management server can first identify the text information in the image data through a preset text recognition model, and then further parse out the identification information and attribute information from the text information, especially the first attribute information (such as delivery date or quantity information, etc.). When the order data is structured data, the production management server can directly parse out the identification information and attribute information. Specifically, structured data often contains fielded information, such as product codes, component codes, or material codes, etc. These coding information can be directly mapped to the identification information of the production object. In addition, structured data can also contain the first attribute information of the production object, such as quantity information, delivery date, personalized production process requirements, etc. Furthermore, based on the identification information, the production management server can query a preset data table (for example, a production object attribute information table) or a database (for example, a production object attribute information database) to find attribute information associated with the production object (second attribute information), for example, conventional material specifications (standard material grades, sizes, etc.), production processes (bending angle tolerance, laser cutting speed, etc.), quality benchmarks, and equipment constraints, etc.

[0026] After the production management server determines the identification information of the production object, it can query a pre-defined data table (e.g., a production resource table) or database (e.g., a production resource database) based on the identification information to find the production resources associated with the production object. It will be appreciated that corresponding production resources can be pre-defined for each production object, such as raw materials, processes, and equipment for each product, part, or component.

[0027] In this embodiment, the associated production resources can be represented as production resources that have been preset in the production management server and are adaptable to the production object. Therefore, the production management server can directly query the associated production resources preset in the data table or database based on the identity of the production object.

[0028] In a specific embodiment, the associated production resources may include: Raw material resources may further include standard material grades, specifications (thickness) and supplier codes.

[0029] Process route resources can further include cutting parameters (laser power), bending process sequence (bend A first and then bend B), and surface treatment process (electroplating).

[0030] Equipment resources may further include equipment model, processing capacity and real-time status.

[0031] Quality inspection standard resources may further include appearance inspection items, performance test thresholds, and sampling rules.

[0032] Human resources can further include operator skill levels (senior press brake), qualification certificates (ISO certification) and shift scheduling.

[0033] In this embodiment, based on the attribute information (first attribute information and second attribute information), the step of judging whether the current associated production resources meet the manufacturing requirements of the production object may be: judging whether the raw material resources are sufficient based on the quantity information in the first attribute information. Judging whether the equipment resources are idle based on the production process and equipment in the second attribute information. Judging whether the human resources are sufficient based on the production process and equipment in the second attribute information. It is understandable that when the raw material resources are sufficient, the equipment resources are idle, and the human resources are sufficient, the production management server may judge that the associated production resources meet the manufacturing requirements of the production object in the order data. It is understandable that when any of the above conditions is not met, for example, the raw material resources are insufficient, the production management server may judge that the associated production resources do not meet the manufacturing requirements of the production object in the order data.

[0034] In a specific implementation, the production management server can determine whether the current associated production resources meet the manufacturing requirements of the production object in the following manner: The production management server can prioritize and overwrite the customized parameters in the first attribute information with the standard parameters in the second attribute information to generate a comprehensive set of process requirements. For example, a customer-specified thickness of 2.5mm (first attribute information) in the order data overrides the standard range of 1.2-3.0mm (second attribute information). Unspecified parameters (e.g., surface roughness Ra ≤ 1.6) are inherited from the second attribute information. Based on this comprehensive set of process requirements, the production management server can then verify whether the corresponding associated production resources meet the manufacturing requirements of the production object. The server can also check whether the inventory of the preset associated raw materials meets the order quantity and verify whether the material performance parameters (tensile strength, elongation) meet the comprehensive process requirements. For example, if an order requires the production of 500 stainless steel casings with a thickness of 2.5mm, the preset standard thickness range of the associated raw material S is 1.2-3.0mm, and the inventory is 600 pieces, then the inventory is determined to be sufficient and the thickness is in compliance, marking it as meeting the requirements.

[0035] Step S16: When the current associated production resources do not meet the manufacturing requirements, based on the production object and a preset production resource selection strategy, a target replacement production resource adapted to the production object is determined from the current production resource library.

[0036] In this embodiment, the production resource selection strategy may be a production resource selection strategy that is expressed as having at least a screening condition. The screening condition may be a screening condition for screening out a set of candidate production resources from a production resource library based on the attribute information of the production object. The candidate production resource set may be expressed as a set of alternative resources that are preliminarily selected from the production resource library through the screening condition and partially meet the manufacturing requirements of the production object. After the candidate production resource set is determined, the target alternative production resource may be further determined from the candidate production resource set. The further determination may be a random selection method or may be determined based on an optimization algorithm that carries at least one optimization objective.

[0037] It is understandable that although the candidate production resource set does not fully conform to the ideal state of the preset associated resources, it meets the core constraints of manufacturing requirements and can be used as the input set for subsequent multi-objective optimization.

[0038] Therefore, in this embodiment, the production resource selection strategy can also be a production resource selection strategy that has both screening conditions and optimization objectives. For example, after determining a set of candidate production resources based on the screening conditions, the candidate production resource set can be optimized based on a preset optimization algorithm with at least one optimization objective to obtain a target replacement production resource.

[0039] In this embodiment, the candidate production resource set may be a set of production resources that at least meet the hard conditions (screening conditions). Specifically, the hard conditions may be key physical / chemical properties (for example, tensile strength ≥ threshold value, corrosion resistance level meets standards, etc., and those that do not meet the requirements will be directly excluded), and the hard conditions may be process feasibility (for example, equipment processing accuracy must meet part tolerance requirements). For example, the tensile strength requirement for refrigerator shells is ≥400MPa, and steel coils with tensile strength <360MPa in the candidate resources will be eliminated. The candidate production resource set may not meet the elastic conditions. The elastic condition may be dimensional adaptability (allowing deviations within a certain range). The elastic condition may be inventory availability (the current inventory must cover the minimum production demand).

[0040] Therefore, it is understandable that candidate conditions can be constructed in advance based on the attribute information (second attribute information) of the production object to filter out a set of candidate production resources that meet the screening conditions (ie, meet the hard conditions).

[0041] Therefore, it is also understandable that candidate conditions can be generated in real time based on the attribute information (first attribute information) of the production object in advance to screen out a set of candidate production resources that meet the screening conditions (ie, meet the hard conditions).

[0042] This implementation addresses the existing issue of inflexible backup material selection when inventory is insufficient by introducing a dynamic production resource selection strategy. By receiving order data and determining whether the currently associated production resources meet manufacturing needs, when inventory is insufficient, a flexible selection of suitable target replacement production resources is determined from the production resource library based on the production target and the preset production resource selection strategy. This approach avoids the limitations of relying on static rules or manual intervention, enabling real-time adjustments to backup material selection, improving resource scheduling flexibility and responsiveness, thereby reducing production scheduling delays and increasing production efficiency and material utilization.

[0043] like Figure 3 As shown, in some embodiments, the step of determining whether the current associated production resources meet the manufacturing requirements of the production object in the order data includes: Step S142: Parse the order data to extract identification information and attribute information of the at least one production object.

[0044] In this embodiment, when the order data is text data, the step of parsing the order data to extract the identification information and attribute information of the at least one production object may be: parsing the order data through keyword matching and context analysis methods to extract the identification information and attribute information of the at least one production object.

[0045] Specifically, the production management server can preset a set of keywords (product code, component number, material code) and use regular expressions or text matching algorithms to identify identification information from the text. For example, order data may contain "Product Code: ABC123." The production management server can match "Product Code" and extract the subsequent code "ABC123" as identification information. In cases where the order data is more complex, the production management server can analyze the context to identify identification information. For example, the text may contain "Order Number: 12345, Production Object: Refrigerator Shell, Quantity: 100." The production management server can extract "Refrigerator Shell" as the production object identifier. Similarly, the production management server can extract keywords representing attribute information. For example, if the order data contains "Dimensions: 50cm*30cm*0.75cm, Delivery Date: December 15, 2023," the production management server can extract "Dimensions" and "Delivery Date" as attribute information.

[0046] In this embodiment, when the order data is image data, the step of parsing the order data to extract the identification information and attribute information of the at least one production object may be: parsing the order data through text recognition technology to extract the identification information and attribute information of the at least one production object.

[0047] Specifically, the production management server can be pre-installed with an OCR text recognition model. By using the OCR text recognition model to identify the production object identification information (product code, component number) in the order, the production management server can extract the relevant identification information from the image. For example, "Product Code: DEF456" may be displayed in the order image, and the OCR text recognition model can recognize "DEF456" and use it as identification information. For complex form images, the production management server can also use layout analysis technology, combined with the text recognized by the OCR text recognition model, to determine the location of the identification information. For example, in the order form, the product code is usually located in a fixed position, and the production management server can extract the corresponding identification information based on the position.

[0048] In this embodiment, when the order data is structured data, the step of parsing the order data to extract the identification information and attribute information of the at least one production object may be: parsing the order data by directly accessing preset fields to extract the identification information and attribute information of the at least one production object.

[0049] Specifically, it's understood that in structured data, identification information is often stored in predefined fields, such as "product_code" or "item_id." The production management server can directly access these fields to extract the identification information of production objects. In structured data, attribute information also often corresponds to predefined fields or subfields. For example, information such as "quantity," "delivery date," and "customization requirements" in an order can be directly extracted from corresponding fields (e.g., "quantity," "delivery_date").

[0050] Step S144: determining associated production resources from the current production resource library based at least on the identification information.

[0051] In this embodiment, the associated production resources may be determined from the current production resource library based on the identification information.

[0052] In this case, the production management server can rely solely on the identification information (product code, component code, or material code) extracted from the order data to retrieve the production resources associated with the identification information from the production resource library.

[0053] In this embodiment, the associated production resources may also be determined from the current production resource library based on both the identification information and the attribute information.

[0054] In this case, the production management server not only relies on identification information, but also combines attribute information (size of the production object, material specifications, and production process requirements) to determine the associated production resources from the production resource library. By combining this information, the production management server can more accurately match the most suitable production resources. It can be understood that identification information provides a unique identity for the production object and is the basis for the query. Attribute information provides the specific requirements of the production object, such as customer-customized size, material requirements, delivery time, etc., to help the production management server determine whether specific resources or process support are required. For example, the production of a standard product may only require identification information to match resources, but if it is a customized product, it is necessary to combine attribute information to determine which resources can meet the customization requirements.

[0055] Step S146: Based on the attribute information, determine whether the current associated production resources meet the manufacturing requirements of the production object.

[0056] In this embodiment, first, the production management server can perform data fusion processing on the first attribute information and the second attribute information to obtain fused attribute information. Specifically, the production management server can overwrite the customized parameters in the first attribute information with the standard values of the second attribute information to generate a comprehensive process requirement table (fused attribute information). For example, a customer specifies a thickness of 2.5mm (first attribute), covering the standard range of 1.2-3.0mm (second attribute), and generating a new thickness requirement of 2.5±0.1mm. Then, based on the fused attribute information, the production management server traverses the parameters in the associated production resources to verify whether each associated production resource meets the manufacturing requirements of the production object. For example, the real-time inventory of raw materials in the associated production resources can be queried to determine whether the order requirements are met. The physical / chemical properties of the raw materials can be compared to see if they match the fused attribute information.

[0057] This embodiment can effectively improve the flexibility and response speed of the production management system through accurate analysis of order data and intelligent matching of associated resources. By extracting the production object identification information and attribute information in the order data in step S142, the specific requirements of the production object can be quickly identified, and the associated resources can be accurately matched from the production resource library in step S144. Furthermore, in step S146, based on the attribute information of the production object, it is judged whether the current associated production resources meet the manufacturing needs. This process can identify in real time whether the resources are sufficient or appropriate, avoiding the shortcomings of traditional methods that rely on manual judgment or static rules. This embodiment reduces manual intervention through automated and intelligent resource matching and judgment, improves the scheduling efficiency of production resources and the accuracy of production plans, thereby effectively reducing the risk of production delays and improving the degree of optimization of production processes.

[0058] like Figure 4 As shown, in some embodiments, the production resource selection strategy includes at least a screening condition; the step of determining a target replacement production resource suitable for the production object from the current production resource library based on the production object and the preset production resource selection strategy includes: Step S162: Based on the production object, determine a screening condition corresponding to the production object.

[0059] In this embodiment, the step of determining the filtering condition corresponding to the production object based on the production object may be that the production management server determines the first filtering condition corresponding to the production object from a preset filtering condition library based on the identification information of the production object; wherein the filtering condition library is configured with at least one first filtering condition corresponding to multiple production objects.

[0060] In this embodiment, the step of determining the screening condition corresponding to the production object based on the production object may also be that the production management server directly generates the second screening condition corresponding to the production object in real time based on the attribute information of the production object.

[0061] In this embodiment, the step of determining the screening conditions corresponding to the production object based on the production object may also involve the production management server combining the identification information and attribute information of the production object to generate the screening conditions through the synergy of preset rules and real-time calculation. Specifically, the identification information can trigger basic rules (such as material type and industry standards) in a preset screening condition library, while the attribute information can dynamically adjust the threshold range (for example, relaxing the delivery tolerance by ±5% based on the urgency of the order).

[0062] In this embodiment, the step of determining the screening conditions corresponding to the production object based on the production object can also be the production management server predicting the optimal screening conditions based on the historical production data of the production object. Specifically, the historical production data can include the identification information and attribute information of the production object, as well as information during the production process (processing time, efficiency, processing speed, etc.) and information after the end of production (product quality control standards, inspection results, quality pass rate, various types of cost data related to production, such as material costs, labor costs, equipment usage costs, etc.). The production management server can use machine learning models such as regression analysis, classification algorithms, neural networks, etc., to train based on historical production data and establish a prediction model. Through this prediction model, the production management server can predict the screening conditions for a given production object. For example, based on historical production data, the production management server can predict the optimal material specifications (tensile strength, corrosion resistance, etc.) suitable for a certain type of product.

[0063] Step S164: Based on the screening conditions, the current production resource library is screened to obtain a set of candidate production resources.

[0064] Step S166: Determine a target replacement production resource from the candidate production resource set.

[0065] In this embodiment, the step of determining the target replacement production resource from the set of candidate production resources may involve the production management server randomly determining the target replacement production resource from the set of candidate production resources. Specifically, the production management server may randomly select a production resource from the set of candidate production resources and then check whether the available inventory of the production resource meets the order requirements. If so, the production resource is directly selected. If not, the system enters a multi-resource combination selection mode.

[0066] In this embodiment, the step of determining the target replacement production resource from the candidate production resource set may be that the production management server traverses the candidate production resource set based on at least one preset optimization goal to determine the target replacement production resource from the candidate production resource set.

[0067] In this embodiment, the step of determining the target replacement production resource from the set of candidate production resources may involve the production management server determining the target replacement production resource from the set of candidate production resources based on preset priority rules. Specifically, the candidate production resources are prioritized according to preset priority rules (e.g., inventory adequacy, supplier reliability, historical yield rate, etc.), and are then sorted by priority. The highest-priority production resource is selected, and its inventory is verified to meet demand. If not, the next-best production resource is selected in descending order of priority until demand is met.

[0068] In this embodiment, the step of determining a target replacement production resource from the set of candidate production resources may involve the production management server determining the target replacement production resource from the set of candidate production resources based on historical success cases. Specifically, the production management server recommends the optimal resource by analyzing the success rate of alternative solutions for similar production objects in historical orders, calculating the similarity between the current production object and historical cases (e.g., attribute vector cosine similarity), and selecting the resource or combination with the highest historical success rate as the target.

[0069] This embodiment effectively improves the efficiency and accuracy of production resource scheduling through a clear production resource selection strategy, combined with screening conditions and a set of candidate production resources. Through steps S162 and S164, the production management server can dynamically generate screening conditions based on the specific needs of the production object and accurately screen the production resource library to obtain a set of candidate resources that meet the production requirements. Subsequently, step S166 selects the most appropriate target replacement production resource based on the candidate resource set to ensure that resource scheduling in the production process is more flexible and efficient. This process not only reduces the error rate of resource matching, but also greatly improves the ability of the production management server to cope with dynamic changes in production demand, ensuring the smooth execution of the production plan and maximization of resource utilization.

[0070] In some embodiments, the screening condition includes a first screening condition, which is a preset screening condition; and the step of determining the screening condition corresponding to the production object based on the production object includes: Step S1662: Based on the production object, determine a first screening condition corresponding to the production object from a preset screening condition library; wherein the screening condition library is configured with at least one first screening condition corresponding to a plurality of production objects.

[0071] In this embodiment, the preset screening condition library can be a data set that stores and manages the preset screening conditions corresponding to various production objects. The screening condition library can help the production management server quickly and accurately determine the appropriate screening conditions for each production object, thereby making effective decisions when selecting production resources.

[0072] In this embodiment, the first screening condition may be a screening condition related to the physical parameters of the material (type and specification of the material), or a screening condition related to the processing technology requirements, etc.

[0073] In a specific scenario example, in the preset filtering condition library, the following filtering condition table is preset for the production object of refrigerator shell.

[0074] This embodiment configures corresponding screening conditions for different production objects through a preset screening condition library, thereby improving the efficiency and accuracy of decision-making in the production resource selection process. Through step S1662, the production management server can quickly find the preset screening conditions that match the production object from the screening condition library based on the identification information of the production object. In this way, there is no need to redefine the screening conditions each time, reducing manual intervention and errors, while ensuring the consistency and standardization of resource selection. This method greatly improves the automation and flexibility of production resource scheduling, can quickly respond to different production needs, optimize the production process, reduce the risk of production delays and resource waste, and ensure the smooth execution of the production plan.

[0075] In some embodiments, the screening condition includes a second screening condition, where the second screening condition represents a real-time generated screening condition; the production object corresponds to attribute information; and the step of determining the screening condition corresponding to the production object based on the production object includes: Step S1664: Input the attribute information corresponding to the production object into the dynamic rule generation engine to generate a second screening rule.

[0076] In this embodiment, the dynamic rule generation engine may be a rule inference engine, which may at least include: A business rule template library stores standard filtering criteria (e.g., material strength thresholds, dimensional tolerance ranges). Specifically, this library can include universal rule templates for different production object types. Universal rule templates can be categorized by production object type (e.g., "refrigerator housing" or "air conditioner panel") or attribute category (e.g., "material strength" or "surface treatment") to support rapid retrieval.

[0077] A dynamic constraint calculator, based on real-time attribute information (primary attribute information) of production objects, parametrically adjusts pre-set rule templates or adds new constraints. Specifically, it can bind production object attributes (such as "delivery date" or "custom thickness") to variable parameters in a common rule template. It can also dynamically calculate constraint thresholds using pre-set mathematical formulas or logical rules.

[0078] A rule mapping table defines the correspondence between production object attributes and rule parameters, ensuring that dynamic rules accurately match actual requirements. Specifically, this rule mapping table can record the corresponding rule parameters (e.g., "spraying process requirements") for each production object attribute (e.g., "surface roughness"). Priority weights can also be set for different attributes, such as giving "tensile strength" a higher weight than "color preference" to ensure that key constraints take precedence.

[0079] The rule integration and output module integrates dynamically generated constraints with template rules and outputs a structured rule file. Specifically, the rule integration and output module converts the calculated constraints into executable rule expressions (e.g., SQL query conditions, JSON-formatted rule descriptions).

[0080] This implementation significantly improves the flexibility and adaptability of production resource selection by inputting production object attribute information into a dynamic rule generation engine to generate secondary screening rules in real time. This dynamic rule generation engine allows the production management server to generate secondary screening criteria in real time based on the customized requirements of each production object (customized size, material, process, etc.), rather than relying solely on a pre-set rule base. This approach enables rapid response to changes in orders or production conditions, ensuring that production resources are promptly and accurately matched to the actual needs of production objects. This optimizes production scheduling, improves resource utilization efficiency, and reduces the inaccurate resource selection caused by fixed rules.

[0081] In some embodiments, the production resource selection strategy includes an optimization goal set, wherein the optimization goal set includes an optimization goal of minimizing material waste, minimizing production cost, minimizing production time, minimizing quality risk, or minimizing delivery delay; The step of determining a target replacement production resource from the set of candidate production resources comprises: Step S1662: Based on at least one optimization objective in the optimization objective set, traverse the candidate production resource set and calculate an evaluation index of each candidate production resource in the candidate production resource set.

[0082] In this embodiment, based on one optimization objective or multiple optimization objectives in the optimization objective set, the candidate production resource set may be traversed to calculate the evaluation index of each candidate production resource in the candidate production resource set.

[0083] In this embodiment, the optimization goal may be to minimize material waste. It is understandable that in sheet metal processing, raw materials (e.g., steel plates, aluminum plates) are usually supplied in the form of fixed-size coils or plates. By selecting cutting equipment with intelligent nesting capabilities (e.g., laser cutting machines or CNC punching machines), the cutting path can be dynamically adjusted to maximize sheet utilization. For example, it is preferred to select equipment that can automatically plan cutting layouts through "nesting software" to reduce waste of scraps caused by unreasonable cutting paths. For sheet metal parts of different shapes, select a more compatible processing technology. For example, for parts with complex contours, laser cutting (which can flexibly cut special-shaped parts and reduce excess material) is preferred rather than fixed mold stamping (which may produce more waste due to mold design limitations).

[0084] In this embodiment, the optimization goal can be minimizing production costs. It is understood that lower-cost sheet materials can be prioritized (provided they meet process requirements). In sheet metal processing, sheet materials from different suppliers or with different specifications may have the same properties (such as material thickness, strength, and surface treatment), but differ in price. In this case, prioritization can be achieved through direct cost comparison or comprehensive cost considerations. Sheets with less residual material after cutting can also be prioritized. It is understood that in the sheet metal cutting process, the size of the sheet material directly affects the degree of residual material waste. By optimizing the sheet material specifications, material waste can be reduced and unit costs can be lowered.

[0085] In this embodiment, the optimization goal can be minimizing production time. It is understood that in sheet metal stamping or bending processes, it is preferred to select equipment with high-speed processing capabilities (e.g., a high-speed punch press or press brake equipped with a servo drive) to shorten single-piece processing time. Furthermore, by optimizing the process path (e.g., combining the stamping and bending steps into a composite process), equipment switching and material handling time can be reduced.

[0086] In this embodiment, the optimization goal may be to minimize quality risk.

[0087] In this embodiment, the optimization goal may be to minimize delivery delays.

[0088] In some embodiments, the optimization goal can also be to minimize the number of mold changes. It is understood that frequent mold changes in sheet metal stamping or forming processes can lead to equipment downtime, increased commissioning time, and increased costs. The optimization goal can be set to reduce the number of mold changes required within a production batch. For example, by prioritizing candidate resources that can be directly processed using existing molds (punch press molds, bending molds), this can reduce equipment conversion losses.

[0089] In some embodiments, the optimization objective can also be to maximize equipment compatibility. It is understood that for the diverse types of equipment used in sheet metal processing (such as laser cutters, CNC punch presses, and shearing machines), the optimization objective may include evaluating the compatibility of candidate equipment with the sheet metal material thickness, shape, and processing accuracy. For example, preference is given to equipment that can directly adapt to the material thickness (e.g., 1.5mm galvanized sheet) without requiring additional adapter tools, thus avoiding rework or accuracy deviations caused by equipment parameter mismatches.

[0090] In some embodiments, the optimization goal can also be to minimize process complexity. It is understood that sheet metal processing often involves multiple steps (e.g., blanking, bending, welding, and surface treatment). The optimization goal can be set to reduce the number of steps or the difficulty of the process. For example, resources that can complete multiple steps using integrated equipment (e.g., a compound punch press) or processing solutions with the shortest process paths can be prioritized to reduce the risk of human error and equipment usage time.

[0091] In this embodiment, a corresponding evaluation function may be pre-set for each optimization objective. The evaluation function can reflect the optimization objective, and thus, the evaluation index of the corresponding optimization objective for different production resources can be calculated through the evaluation function.

[0092] In a specific implementation scheme, for the optimization goal of minimizing production costs, a corresponding evaluation function can be constructed by integrating raw material procurement costs, process adjustment costs (such as adding new processes), and equipment energy consumption costs. For the optimization goal of minimizing production time, a corresponding evaluation function can be constructed by calculating the total working hours of the process path (including processing time, equipment switching time, and logistics waiting time). For the optimization goal of minimizing quality risks, a corresponding evaluation function can be constructed by evaluating the compatibility of alternative resources with standard processes (material strength deviation, tolerance range adaptability), and historical yield data. For the optimization goal of minimizing delivery delays, a corresponding evaluation function can be constructed by combining the supplier's delivery cycle, the total time of the alternative process path, and the matching degree of the order delivery deadline. For the optimization goal of minimizing material waste, a corresponding evaluation function can be constructed by calculating the theoretical excess material rate based on the matching degree between the standard size of the sheet / coil and the unfolded area of the part.

[0093] In this embodiment, the evaluation function may be a linear model or a nonlinear model.

[0094] In this embodiment, a comprehensive evaluation function may also be set for multiple optimization objectives.

[0095] In a specific embodiment, the comprehensive evaluation function may be: In the formula, Represented as the i-th production resource, Expressed as the weight coefficient of the kth optimization objective, It is represented as the normalized evaluation value of the kth optimization objective, and n represents that there are n optimization objectives.

[0096] In a specific embodiment, the comprehensive evaluation function may be: In the formula, Represented as the i-th production resource, Expressed as the weight coefficient of the kth optimization objective, is the normalized evaluation value of the kth optimization objective, n represents the number of optimization objectives, p represents the total number of hard constraints (for example, the lower limit of material strength, process accuracy requirements, etc.), λ is the penalty coefficient, which represents the penalty intensity for violation of the control constraint. is represented by the actual value of the jth constraint (e.g., material strength, delivery cycle), It is expressed as the lower threshold of the j-th constraint, indicating the minimum standard that must be met. Indicates over-limit calculation. ≥ , this item is 0, no penalty is triggered; if < , exceeding the limit - , the penalty value increases with the amount of excess.

[0097] In this evaluation function, a minor violation results in an exponentially increasing penalty, ensuring that the server automatically excludes solutions that severely violate the constraints. If multiple constraints are violated simultaneously, the penalty term is the cumulative value of all violations.

[0098] In a specific embodiment, the comprehensive evaluation function may also be a piecewise function model.

[0099] In a specific embodiment, the comprehensive evaluation function can also be based on a multiplicative interaction model.

[0100] In this embodiment, the evaluation function under the above-mentioned single optimization objective or the comprehensive evaluation function can be solved by a heuristic algorithm.

[0101] In this embodiment, the evaluation function under the above-mentioned single optimization objective or the comprehensive evaluation function can be solved by a genetic algorithm.

[0102] In this embodiment, the evaluation function under the above-mentioned single optimization objective or the comprehensive evaluation function can be solved by a particle swarm optimization algorithm.

[0103] In this embodiment, the evaluation function under the above-mentioned single optimization objective or the comprehensive evaluation function can be solved by a simulated annealing algorithm.

[0104] In this embodiment, the evaluation function under the above-mentioned single optimization objective or the comprehensive evaluation function can be solved by a mixed integer linear programming algorithm.

[0105] Step S1664: Based on the evaluation index, determine a target replacement production resource or a combination of multiple target replacement production resources from the candidate production resource set.

[0106] In this embodiment, a candidate production resource with the best evaluation index may be selected as a target replacement production resource.

[0107] In this embodiment, when the candidate production resource with the best evaluation index still cannot meet the manufacturing demand, the candidate production resource with the best evaluation index and the second best evaluation index can be selected as the target replacement production resource.

[0108] This implementation effectively addresses the rigid resource selection problem inherent in existing material preparation scheduling techniques, resulting from the lack of a dynamic trade-off mechanism, by introducing a production resource selection strategy encompassing multi-dimensional optimization objectives. Specifically, the optimization objective set (including minimizing material waste, production costs, production time, quality risks, and delivery delays) can be intelligently selected based on the real-time needs and dynamic constraints of the production target. This is achieved by traversing the set of candidate production resources and calculating comprehensive evaluation metrics for each resource. This approach overcomes the limitations of static rule bases that rely solely on fixed priorities. By dynamically balancing requirements with different priorities through a multi-objective optimization algorithm, it significantly enhances resource scheduling flexibility and decision-making rationality. Furthermore, a selection mechanism that supports combined resources further expands the solution's scope of application. When a single resource cannot fully meet demand, the optimal solution to production constraints can be achieved through the collaborative optimization of multiple resources. Ultimately, this effectively reduces manual intervention costs, mitigates the risk of abnormal production downtime, and improves the resource utilization and responsiveness of the overall production system.

[0109] In some embodiments, the step of traversing the set of candidate production resources based on at least one optimization objective in the optimization objective set and calculating an evaluation index for each candidate production resource in the set of candidate production resources includes: Step S16622: Based on the production object, determine a plurality of associated optimization objectives and corresponding fusion weights from the optimization objective set.

[0110] In this embodiment, a plurality of associated optimization objectives and corresponding fusion weights may be pre-configured for different production objects in the optimization objective set.

[0111] In this embodiment, multiple associated optimization objectives and corresponding fusion weights may be directly queried from the optimization objective set based on the identification information of the production object.

[0112] In this embodiment, weights can also be dynamically adjusted based on the first attribute information (user-customized parameters, such as delivery time and other customized requirements). For example, if the order delivery date is less than three days from the current time, the delivery weight will be increased from the default 30% to 50%. If the customer requests "quality first," the quality risk weight will be increased from 30% to 50%.

[0113] In this implementation, association refers to the existence of technical coupling between multiple optimization objectives. For example, if each optimization objective shares the same set of production resource constraints (equipment capacity, material inventory, and so on), optimizing any one optimization objective will alter the resource state, thereby affecting the achievement of other optimization objectives. For example, shortening delivery time (optimization objective 1) may require the use of high-cost equipment (which deteriorates optimization objective 2), and the two are linked through capacity constraints.

[0114] Step S16624: Based on multiple optimization objectives, traverse the candidate production resource set and calculate the evaluation index of each candidate production resource under each optimization objective.

[0115] In this embodiment, a corresponding evaluation function may be pre-set for each optimization objective. The evaluation function can reflect the optimization objective, and thus, the evaluation index of the corresponding optimization objective for different production resources can be calculated through the evaluation function.

[0116] In a specific embodiment, if the optimization goal is to minimize the expected delivery delay time of an order, the corresponding evaluation function can be: In the formula, It can be expressed as the corresponding benchmark production cycle when using production resource r, It can be expressed as the delay caused by using production resource r, It can be expressed as the delay in transporting to the predetermined location when using production resource r.

[0117] Step S16626: Based on the fusion weights, the evaluation indicators of the candidate production resources under different optimization objectives are weightedly integrated to obtain the final evaluation indicator of each candidate production resource.

[0118] In a specific embodiment, the final evaluation indicator may be: In the formula, Can be represented as candidate production resources The final evaluation indicator, It can be expressed as: when the optimization goal is to minimize the expected delivery delay time of the order, the candidate production resources The normalized value of the evaluation index, It can be expressed as when the optimization goal is to minimize the production cost, the candidate production resources The normalized value of the evaluation index, It can be expressed as when the optimization goal is to minimize the quality risk, the candidate production resources The normalized values of the evaluation indicators, w1, and is represented as fusion weight.

[0119] This implementation method dynamically associates multiple optimization objectives (such as cost, efficiency, resource utilization, etc.) with production demand through multi-objective association modeling and dynamic weight fusion, and generates comprehensive evaluation indicators based on weight fusion. It avoids the one-sidedness of single indicator evaluation and can flexibly adapt to the priority requirements of different scenarios, thereby achieving global optimization of resource selection, significantly improving production efficiency, reducing cost waste, and providing scientific and explainable decision support for complex manufacturing scenarios.

[0120] In some embodiments, the production object corresponds to identification information and attribute information; wherein the attribute information includes a quantity attribute indicating quantity scale, a time attribute indicating urgency, and a quality attribute indicating quality standard level; the step of determining a plurality of associated optimization objectives and corresponding fusion weights from the optimization objective set based on the production object includes: Based on the identification information of the production object, a plurality of associated optimization objectives are determined from a preset optimization objective set.

[0121] Based on the attribute information of the production object and the preset dynamic weight optimization model, the fusion weight of each optimization target is determined; wherein, the dynamic weight optimization model is used to increase the weight ratio of minimizing material waste when the quantity attribute exceeds the preset economic batch threshold, increase the weight ratio of minimizing production time when the time attribute is lower than the preset delivery safety margin, and increase the weight ratio of minimizing quality risk when the quality attribute reaches the preset high-precision standard.

[0122] In this embodiment, the dynamic weight optimization model may be a model that can automatically adjust the weights of different optimization objectives according to attribute information of the production object (such as quantity scale, urgency and quality standard).

[0123] When the quantity attribute (production scale or batch size) of a production object exceeds the preset economic batch threshold, the server will prioritize the goal of minimizing material waste. Because material waste has a more significant impact on overall production costs in large-scale production, the optimization goal of reducing material waste should be given a higher weight.

[0124] When the time attribute of the production object (the urgency of the delivery date) is lower than the preset delivery safety margin, the server will increase the weight of minimizing the production time to ensure that the production task can be completed on time and avoid delivery delays.

[0125] When the quality attributes (quality standards or precision requirements) of a production object meet the preset high-precision standards, the server will increase the weight of minimizing quality risk. Because high-precision production tasks often have more stringent quality requirements, the optimization goal of reducing quality risk should be given a higher weight.

[0126] In this embodiment, the dynamic weight optimization model may be: In the formula, It can be expressed as the basic weight, Represented as the current attribute information value (which can be a real-time value extracted from the production object attribute to determine whether to trigger weight adjustment), It can be expressed as the attribute threshold that triggers weight adjustment. When this value is exceeded or reached, the weight adjustment is triggered. Expressed as the theoretical or actual maximum value that can be achieved, used for normalized calculations. Expressed as the adjustment coefficient, It is represented as the fusion weight of the i-th optimization objective.

[0127] This implementation method flexibly adjusts the fusion weight of the optimization objectives based on the identification information and attribute information of the production objects, combined with a preset dynamic weight optimization model, and can automatically adjust the production scheduling strategy according to actual production needs. Specifically, when the order quantity exceeds the economic batch threshold, the server prioritizes minimizing material waste; when the delivery date is urgent, the server increases the weight of production time optimization; when quality requirements are high, the server strengthens the optimization goal of quality control. This dynamic adjustment mechanism not only improves the efficiency of resource utilization in the production process, but also effectively responds to the specific needs of different production tasks, reduces unnecessary resource waste, improves production efficiency, and ensures product quality, ultimately achieving a more intelligent and efficient production process.

[0128] According to an embodiment of the present invention, an electronic device is provided. Figure 5 The electronic device in this embodiment may include one or more of the following components: a processor, a network interface, a memory, a non-volatile memory, and one or more applications, wherein the one or more applications may be stored in the non-volatile memory and configured to be executed by one or more processors, and the one or more programs are configured to execute the method described in the aforementioned method embodiment.

[0129] According to an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a computer, the computer executes the method described in any one of the above embodiments.

[0130] According to an embodiment of the present invention, a computer program product comprising instructions is further provided. When the instructions are executed by a computer, the computer is enabled to perform a method in any one of the above embodiments.

[0131] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0132] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0133] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0134] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0135] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining production resources, characterized in that: include: receiving order data including at least one production object; Determining whether current associated production resources satisfy the manufacturing requirements of the production object in the order data; wherein the associated production resources represent preset production resources that are adapted to the production object; In the case that the current associated production resources do not meet the manufacturing requirements, based on the production object and a preset production resource selection strategy, a target replacement production resource adapted to the production object is determined from the current production resource library.

2. The method according to claim 1, characterized in that The step of determining whether the current associated production resources meet the manufacturing requirements of the production object in the order data includes: Parsing the order data to extract identification information and attribute information of the at least one production object; determining associated production resources from a current production resource library based at least on the identification information; Based on the attribute information, it is determined whether the current associated production resources meet the manufacturing requirements of the production object.

3. The method according to claim 1, characterized in that The production resource selection strategy includes at least a screening condition; the step of determining a target replacement production resource suitable for the production object from the current production resource library based on the production object and the preset production resource selection strategy includes: Based on the production object, determining a screening condition corresponding to the production object; Based on the screening conditions, the current production resource library is screened to obtain a set of candidate production resources; A target replacement production resource is determined from the set of candidate production resources.

4. The method according to claim 3, characterized in that The screening condition includes a first screening condition, which is a pre-set screening condition. The step of determining the screening condition corresponding to the production object based on the production object includes: Based on the production object, a first screening condition corresponding to the production object is determined from a preset screening condition library; wherein the screening condition library is configured with at least one first screening condition corresponding to a plurality of production objects.

5. The method according to claim 3, characterized in that The screening condition includes a second screening condition, wherein the second screening condition is a screening condition generated in real time; The production object corresponds to attribute information; the step of determining a screening condition corresponding to the production object based on the production object includes: The attribute information corresponding to the production object is input into the dynamic rule generation engine to generate a second screening rule.

6. The method according to claim 3, characterized in that The production resource selection strategy includes an optimization target set, wherein the optimization target set includes an optimization target representing minimizing material waste, minimizing production cost, minimizing production time, minimizing quality risk, or minimizing delivery delay; The step of determining a target replacement production resource from the set of candidate production resources comprises: Based on at least one optimization objective in the optimization objective set, traverse the candidate production resource set and calculate an evaluation index for each candidate production resource in the candidate production resource set; Based on the evaluation index, a target replacement production resource or a combination of multiple target replacement production resources is determined from the candidate production resource set.

7. The method according to claim 6, characterized in that The step of traversing the set of candidate production resources based on at least one optimization objective in the optimization objective set and calculating an evaluation index of each candidate production resource in the set of candidate production resources includes: Based on the production object, determining a plurality of associated optimization objectives and corresponding fusion weights from the optimization objective set; Based on multiple optimization objectives, traverse the set of candidate production resources and calculate the evaluation index of each candidate production resource under each optimization objective; According to the fusion weights, the evaluation indicators of each candidate production resource under different optimization objectives are weightedly fused to obtain the final evaluation indicator of each candidate production resource.

8. The method according to claim 7, characterized in that The production object corresponds to identification information and attribute information; wherein the attribute information includes a quantity attribute indicating quantity scale, a time attribute indicating urgency, and a quality attribute indicating quality standard level; the step of determining a plurality of associated optimization objectives and corresponding fusion weights from the optimization objective set based on the production object includes: Based on the identification information of the production object, determining a plurality of associated optimization objectives from a preset optimization objective set; Based on the attribute information of the production object and the preset dynamic weight optimization model, the fusion weight of each optimization target is determined; wherein, the dynamic weight optimization model is used to increase the weight ratio of minimizing material waste when the quantity attribute exceeds the preset economic batch threshold, increase the weight ratio of minimizing production time when the time attribute is lower than the preset delivery safety margin, and increase the weight ratio of minimizing quality risk when the quality attribute reaches the preset high-precision standard.

9. An electronic device, characterized in that: include: a memory, and one or more processors communicatively coupled to the memory; Instructions executable by the one or more processors are stored in the memory. The instructions are executed by the one or more processors to enable the one or more processors to implement the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that The readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images