Order production scheduling method and system, electronic equipment and storage medium

Abstract

The invention relates to intelligent manufacturing, in particular to an order production scheduling method and system, electronic equipment and a storage medium, and the method comprises the steps: collecting and processing production associated data of a to-be-scheduled order according to a preset evaluation index to obtain an evaluation result, and determining a main target rule of the to-be-scheduled order according to the evaluation result; sorting the to-be-scheduled orders based on the main target rule and the production associated data, and dividing the orders according to production processes; selecting a secondary target rule of each process in combination with the primary target rule and the production associated data corresponding to each process; and for each production process, on the basis of the primary target rule, the secondary target rule and the production associated data, performing local search optimization on the to-be-scheduled order to obtain a scheduling sequence. Compared with the prior art, the main target rule is determined according to the production associated data of the to-be-scheduled order and the preset evaluation index, and the optimal scheduling sequence can be effectively determined based on the production associated data of the current to-be-scheduled order, so that the production efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing, and more specifically, to an order scheduling method, system, electronic device, and storage medium. Background Technology

[0002] Order scheduling refers to the process of rationally allocating each process step in a manufacturing order to specific equipment and time slots based on logical dependencies and resource availability, thereby determining the order's execution sequence on the production line. This sequence directly determines the smoothness of production, the efficiency of resource utilization, and the on-time delivery rate of orders. A scientific scheduling sequence can effectively shorten the manufacturing cycle, reduce waiting and changeover losses, and improve overall production responsiveness while meeting process constraints.

[0003] However, in existing order scheduling technologies, the optimization guidelines used for scheduling are usually set by planners based on experience. Although this approach can meet the planners' subjective intentions to some extent, planners often struggle to capture the correlations within order data. Consequently, the optimization guidelines set by planners may not yield the optimal order scheduling sequence, making it difficult to fully utilize key elements of industrial production equipment and resources. This ultimately hinders the improvement of overall production efficiency and fails to meet the requirements of intelligent industrial production. Summary of the Invention

[0004] This invention provides an order scheduling method, system, electronic device, and storage medium for obtaining the optimal order scheduling sequence, thereby effectively improving the efficiency of industrial production.

[0005] According to a first aspect of this application, an order scheduling method is provided, the method comprising: Collect production-related data for orders awaiting production scheduling; The production-related data is processed according to preset evaluation indicators to obtain evaluation results, and the main target rules of the production orders to be scheduled are determined based on the evaluation results. The orders to be scheduled are sorted according to the main target rules and the production-related data; The sorted orders to be scheduled are divided according to the production process; Based on the main target rules and the production association data corresponding to the orders to be scheduled, select the secondary target rules corresponding to each production process from the preset production scheduling rule library; For each production process, based on the primary objective rule and according to the corresponding secondary objective rule and the production association data, a local search optimization is performed on the production orders to be scheduled in the production process to obtain the production scheduling sequence of the production orders to be scheduled.

[0006] Optionally, the evaluation indicators include the rule evaluation indicators corresponding to the main preset candidate rules; The process of processing the production-related data according to preset evaluation indicators to obtain evaluation results, and determining the main target rules for the orders to be scheduled for production based on the evaluation results, includes: Based on the rule evaluation index corresponding to the main preset candidate rule, extract the corresponding evaluation data from the production-related data; The evaluation score of the main preset candidate rule is obtained based on the rule evaluation index and the corresponding evaluation data as the evaluation result; The primary target rule for the production order to be scheduled is determined from the primary preset candidate rules based on the evaluation score of the primary preset candidate rules.

[0007] Optionally, the main target rule is configured with several triggering conditions; The step of selecting secondary target rules corresponding to each production process from a preset production scheduling rule library, based on the production association data corresponding to the primary target rules and the production orders to be scheduled, includes: Based on the division of the pending production orders, obtain the process association data corresponding to each production process from the production association data; Select the triggering condition that matches the data associated with the process as the target triggering condition; Based on the primary target rule and the target triggering condition, the secondary target rule corresponding to each production process is selected from the preset production scheduling rule library.

[0008] Optionally, the production scheduling rule base contains several production scheduling rules, and each production scheduling rule has a corresponding applicable text preset; The step of selecting the secondary target rule corresponding to the production process from a preset production scheduling rule base according to the primary target rule and the target triggering condition includes: The main target rule and the target triggering condition are semantically concatenated to obtain the business scenario corpus; Calculate the semantic similarity between the business scenario corpus and the applicable text of each scheduling rule; Based on the semantic similarity, a secondary target rule is selected from the production scheduling rule base.

[0009] Optionally, the collection of production-related data for orders awaiting production scheduling includes: Retrieve incomplete orders and collect production-related data for those incomplete orders; According to the preset production conflict rules, unfinished orders without production conflicts are selected from the production association data of the unfinished orders and designated as the orders to be scheduled for production.

[0010] Optionally, collecting the production-related data of the uncompleted orders includes: Collect associated data of the incomplete orders based on preset data keywords; The associated data collected from the incomplete orders are associated with the corresponding data keywords to construct a structured data table of data keywords and associated data as the production associated data of the incomplete orders.

[0011] Optionally, for each production process, the step of performing local search optimization on the pending production orders in the production process based on the primary objective rule and according to the corresponding secondary objective rule and the production association data includes: If the number of pending production orders included in the production process exceeds a preset threshold, then based on the main target rule, and according to the corresponding secondary target rule and the production association data, a local search optimization is performed on the pending production orders in the production process. If the number of pending production orders included in the production process does not exceed a preset threshold, then based on the main target rule and the production association data, a local search optimization is performed on the pending production orders in the production process.

[0012] According to a second aspect of this application, an order scheduling system is provided, the system comprising: The data acquisition module is used to collect production-related data for orders awaiting production scheduling. The main target determination module is used to process the production-related data according to preset evaluation indicators to obtain evaluation results, and to determine the main target rules of the production order to be scheduled based on the evaluation results; The order sorting module is used to sort the orders to be scheduled for production according to the main target rules and the production-related data; The process division module is used to divide the sorted orders to be scheduled into production processes. The secondary target determination module is used to select the secondary target rules corresponding to each production process from the preset production scheduling rule library based on the main target rules and the production association data corresponding to the orders to be scheduled. The production sequence acquisition module is used to perform local search optimization on the orders to be scheduled in the production process for each production process based on the main target rule and according to the corresponding secondary target rule and the production association data, so as to obtain the production sequence of the orders to be scheduled.

[0013] According to a third aspect of this application, an electronic device is provided, comprising: Memory, used to store one or more computer programs; A processor, when the one or more computer programs are executed by the processor, implements the order scheduling method described in the first aspect above.

[0014] According to a fourth aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the order scheduling method described in the first aspect above.

[0015] Based on any of the above aspects, the order scheduling method, system, electronic device, and computer storage medium provided in this application determine the main target rule based on the production association data of the orders to be scheduled and preset evaluation indicators. This allows for dynamic adaptation to the actual characteristics of the current order set without relying on manual specification, avoiding situations where manual specification cannot match the actual production situation. It can effectively determine the optimal scheduling order based on the production association data of the current orders to be scheduled, thereby improving production efficiency. At the same time, after performing global sorting under the guidance of the main target rule, this application further divides orders according to production processes and independently selects secondary target rules for each production process for local search optimization. This ensures that the scheduling results not only meet the overall production orientation but also allow for fine-tuning at the specific process level, effectively optimizing the scheduling results and thus improving production efficiency. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the steps of the order scheduling method provided in this embodiment.

[0018] Figure 2 This is a flowchart illustrating the steps involved in determining the primary target rule in this embodiment.

[0019] Figure 3 This is a flowchart illustrating the steps involved in selecting the sub-target rule in this embodiment.

[0020] Figure 4 This is a flowchart illustrating one implementation method for selecting the sub-target rule provided in this embodiment.

[0021] Figure 5 This is a schematic diagram of the functional modules of the order scheduling system provided in this embodiment.

[0022] Figure 6This is a schematic diagram of the device structure of the electronic device provided in this embodiment. Detailed Implementation

[0023] The accompanying drawings are for illustrative purposes only and should not be construed as limiting the scope of this application. To better illustrate the following embodiments, some components in the drawings may be omitted, enlarged, or reduced, and do not represent the actual dimensions of the product; it is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] Order scheduling refers to the process of rationally allocating each process step in a manufacturing order to specific equipment and time slots based on logical dependencies and resource availability, thereby determining the order's execution sequence on the production line. This sequence directly determines the smoothness of production, the efficiency of resource utilization, and the on-time delivery rate of orders. A scientific scheduling sequence can effectively shorten the manufacturing cycle, reduce waiting and changeover losses, and improve overall production responsiveness while meeting process constraints.

[0027] However, in existing order scheduling technologies, the optimization guidelines used for scheduling are usually set by planners based on experience. Although this approach can meet the planners' subjective intentions to some extent, planners often struggle to capture the correlations within order data. Consequently, the optimization guidelines set by planners may not yield the optimal order scheduling sequence, making it difficult to fully utilize key elements of industrial production equipment and resources. This ultimately hinders the improvement of overall production efficiency and fails to meet the requirements of intelligent industrial production.

[0028] This embodiment provides a technical solution that can solve the above problems. The specific implementation of this application will be described in detail below with reference to the accompanying drawings.

[0029] like Figure 1 As shown, this embodiment provides an order scheduling method, which may include the following steps: S1: Collect production-related data for orders awaiting production scheduling; In this embodiment, the production-related data can be understood as various types of information directly related to order production execution, mainly used to determine order characteristics, evaluate constraints, and serve as the basis for production scheduling optimization.

[0030] In one implementation, the production-related data may include at least the order code, the product code in the order, the quantity of the product to be processed, the customer's required delivery date, the number of production processes required for the order, the number of production processes already executed, the number of remaining production processes, the process number of each production process required for the order, the standard working hours for processing one product per process, the interval time between previous processes, the interval time between subsequent processes, whether equipment needs to be changed between processes, and the change events for the corresponding processes, etc.

[0031] In some implementations, the production-related data may also include production resource data such as the number of workstations, workstation codes, number of production lines, production line codes, number of technical personnel, and technical personnel codes.

[0032] By using the production-related data to analyze the corresponding order information, the production sequence of orders for each production process can be arranged to obtain the optimal order production sequence while avoiding production conflicts.

[0033] It is understood that the production-related data can be set according to the actual production environment and the products being produced, and there are no further restrictions here.

[0034] In this embodiment, the collection of production relationship data may include the following steps: Obtain unfinished orders and collect production-related data for the unfinished orders; based on preset production conflict rules, filter out unfinished orders without production conflicts from the production-related data of the unfinished orders as the orders to be scheduled for production.

[0035] In this embodiment, the production conflict refers to a situation where multiple orders cannot be executed simultaneously as planned during the scheduling or production process due to competition for the same production resources. The production conflict may include situations such as the same technician being simultaneously needed by multiple processes, overlapping production equipment schedules, delays in material availability, and unmet dependencies between processes. Therefore, the production conflict rules may include rules for determining whether the technician schedules for the unfinished orders conflict, whether the production equipment schedules for the unfinished orders conflict, and whether the materials for the unfinished orders are readily available.

[0036] Understandably, in order to ensure the continuity of the production process and improve the efficiency and utilization of production equipment and resources, it is necessary to first screen the unfinished orders through the production conflict rules. By screening, it is possible to identify unfinished orders that do not have production conflicts under the current production environment and can be scheduled for production, thus avoiding production conflicts during scheduling or actual production.

[0037] In this embodiment, collecting the production-related data of the unfinished orders may include: Collect associated data of the unfinished orders according to preset data keywords; associate the associated data of the unfinished orders with the corresponding data keywords to construct a structured data table of data keywords-associated data as the production associated data of the unfinished orders.

[0038] By constructing a structured data table as the production-related data for the unfinished orders, a unified and complete input basis can be provided for subsequent production scheduling.

[0039] Table 1 below shows an example of the production-related data: Table 1 It is understood that Table 1 above only provides one structural example and some data examples of the production-related data, and does not represent the actual setting of the production-related data. The production-related data can be adaptively set based on the data keywords and the collected related data. For example, the production-related data can be represented by multiple structured data tables. In some embodiments, the production-related data can also be represented as a structured data combination. No further restrictions are imposed here.

[0040] S2: Process the production-related data according to the preset evaluation indicators to obtain the evaluation results, and determine the main target rules of the production orders to be scheduled based on the evaluation results; In this embodiment, the evaluation index includes the rule evaluation index corresponding to the main preset candidate rule. The main preset candidate rule is a predefined production scheduling strategy option. Each main preset candidate rule corresponds to a core production target. The rule evaluation index is the quantitative score corresponding to the core production target. In one implementation, the main preset candidate rules include at least delivery date guarantee rules, efficiency guarantee rules, equipment guarantee rules, and production process guarantee rules. It can be understood that the delivery date guarantee rule ensures that the pending production orders, after being scheduled, meet the delivery date specified by the customer; the efficiency guarantee rule ensures that the pending production orders, after being scheduled, maximize the throughput efficiency of the production process; the equipment guarantee rule ensures that the pending production orders, after being scheduled, reduce equipment wear and tear; and the production process guarantee rule ensures that the pending production orders can be completed stably and continuously after being scheduled.

[0041] It is understood that the main preset candidate rules can be set according to the actual core production objectives, or can be added based on the implementation methods shown above.

[0042] In this embodiment, as Figure 2 As shown, step S2 may include the following sub-steps: S21: Extract the corresponding evaluation data from the production-related data according to the rule evaluation index corresponding to the main preset candidate rule; S22: Based on the rule evaluation index and the corresponding evaluation data, obtain the evaluation score of the main preset candidate rule as the evaluation result; S23: Determine the main target rule for the production order to be scheduled from the main preset candidate rules based on the evaluation score of the main preset candidate rules.

[0043] In this embodiment, each of the primary preset candidate rules is associated with a rule evaluation index. The rule evaluation index can be set according to the core production target corresponding to the primary preset candidate rule. The rule evaluation index calculates the evaluation score of the primary preset candidate rule based on the required data, which can be extracted from the production-related data of all pending production orders. In one implementation, each rule evaluation index is set with a corresponding keyword. Data can be extracted from the production-related data using the keyword in the rule evaluation index. The keyword can be set based on the corresponding primary preset candidate rule.

[0044] In one example, for the primary preset candidate rule for the guaranteed delivery date rule, the number of orders to be scheduled, the number of production processes required, and the customer's required delivery date can be collected. The production time for each production process can be calculated, and then the latest completion time for each order to be scheduled can be calculated. The evaluation score of the guaranteed delivery date rule is obtained based on the difference between the latest completion time of all orders to be scheduled and the customer's required delivery date for the corresponding order. It can be understood that the evaluation score calculated by the rule evaluation index of the guaranteed delivery date rule represents the urgency of the order to be scheduled. If the evaluation score of the guaranteed delivery date rule is higher than the evaluation scores of other primary preset candidate rules, it indicates that the current order to be scheduled is more urgent. In this case, the overall scheduling goal of the order to be scheduled is to guarantee the customer's delivery date, and the guaranteed delivery date rule is selected as the primary target rule for the order to be scheduled.

[0045] The evaluation score of the rule evaluation index for the equipment protection rule can be calculated based on whether the process between each process in the production order needs to be changed and the changeover time between the corresponding processes, so as to reduce equipment loss caused by changeover and changeover time.

[0046] The evaluation score for the production process rule can be calculated based on the ratio of unexecuted processes to total processes in the pending production orders, as well as the difference between the start time and the current time of the pending production orders, to ensure that all orders can be effectively scheduled.

[0047] For the efficiency guarantee rule, a fixed default evaluation score can be set for the efficiency guarantee rule as the default strategy of the main preset candidate rule. When the evaluation scores of other main preset candidate rules are low and lower than the default evaluation score set for the efficiency guarantee rule, the efficiency guarantee rule is selected as the main target rule, so that the production orders to be scheduled are scheduled with the goal of maximizing overall efficiency.

[0048] In one implementation, a corresponding candidate rule library can be set for each of the main preset candidate rules. After the main preset candidate rule to be selected is determined according to the evaluation score, a candidate rule can be selected from the candidate rule library corresponding to the main preset candidate rule through heuristic selection. The selected candidate rule is used as the main preset candidate rule, and the main target rule is constructed according to the main preset candidate rule.

[0049] Taking the guaranteed delivery date rule as an example, assuming that the candidate rule base corresponding to the guaranteed delivery date rule contains two candidate rules: the earliest delivery date rule (EDD) and the slack time remaining rule (STR), then the earliest delivery date rule is selected as the guaranteed delivery date rule through heuristic selection, and the main target rule is constructed based on the guaranteed delivery date rule.

[0050] Understandably, the primary target rule is the main constraint rule for production scheduling. Besides the primary preset candidate rule, it also includes several basic restriction rules. These basic restriction rules are used to limit the orders to be scheduled, ensuring their normal execution after scheduling. These basic restriction rules may include process execution rules and resource allocation rules. The process execution rule stipulates that the next process cannot begin until the previous process of the order to be scheduled is completed. The resource allocation rule stipulates that the order to be scheduled needs the support of corresponding idle equipment and technical personnel in each process. Therefore, the primary target rule contains the primary preset candidate rule for the core production target and the basic restriction rules for limitation, enabling this embodiment to ensure both the normal execution of production scheduling and the satisfaction of the core production target when scheduling based on the primary target rule.

[0051] S3: Sort the production orders to be scheduled according to the main target rules and the production association data; In one example of this embodiment, taking the guaranteed delivery date rule as an example, sorting the orders to be scheduled for production based on the main target rule and the production-related data can be done by sorting the orders to be scheduled for production according to the customer's required delivery date in the production-related data. By sorting according to the main target rule first, the overall production scheduling target of the orders to be scheduled can be determined, while reducing the number of adjustments required for subsequent fine-tuning of each process.

[0052] S4: Divide the sorted pending production orders according to the production process; In this embodiment, step S4 may include the following steps: Based on the production processes that the pending production orders still need to be executed, obtain the process dependencies of the pending production orders, such as process 1 → process 2 → … → process N; obtain the process components of the pending production orders for each production process according to the process dependencies, such as pending production order A_OP1, pending production order A_OP2, …, pending production order A_OPN; then classify each process component of all the pending production orders based on the corresponding production processes to realize the division of pending production orders.

[0053] The results of the order allocation are shown in Table 2 below: Table 2 In Table 2 above, "..." indicates omission, and "-" indicates an empty set, meaning that the corresponding order to be scheduled for production has no corresponding process component for that process and does not need to be executed. Since the process component is part of the order to be scheduled for production, it can be seen from Table 2 above that process 1 contains two orders to be scheduled for production, process 2 contains three orders to be scheduled for production, and process 3 contains two orders to be scheduled for production.

[0054] S5: Based on the main target rule and the production association data corresponding to the orders to be scheduled, select the secondary target rule corresponding to each production process from the preset production scheduling rule library; In this embodiment, the main objective rule includes core production rules. However, if production is scheduled solely based on the main objective rule, the optimal production sequence based on the current production environment may not be obtained. For example, if the main objective rule is used as the delivery date guarantee rule, the final sorting result may meet the customer's delivery date requirements, but it may not maximize production efficiency.

[0055] Therefore, after determining the primary target rule, it is necessary to determine the secondary target rule for adjusting the production schedule. In this embodiment, the secondary target rule and the primary target rule have a corresponding relationship to avoid conflict between the secondary target rule and the primary target rule.

[0056] Meanwhile, in order to accurately match suitable secondary target rules to the primary target rule, this embodiment pre-sets several triggering conditions for the primary target rule. When any triggering condition is met, the corresponding secondary target rule can be extracted based on that met triggering condition. In this embodiment, the triggering conditions can be set for the corresponding secondary target rule, thereby enabling the accurate acquisition of the corresponding secondary target rule based on the primary target rule and the met triggering conditions.

[0057] In this embodiment, as Figure 3 As shown, step S5 may include the following sub-steps: S51: Based on the division of the orders to be scheduled for production, obtain the process association data corresponding to each of the production processes from the production association data; S52: Select the triggering condition that matches the process-related data as the target triggering condition; S53: Based on the main target rule and the target triggering condition, select the secondary target rule corresponding to each production process from the preset production scheduling rule library.

[0058] In this embodiment, since the process component is the result of dividing the production order into production processes, the process association data corresponding to the process component can be obtained from the production association data based on the process component obtained from the production order. It is understood that the process association data can include all relevant data required for scheduling the production order in the production process. The extraction of the process association data can be based on the actual production process settings. For example, if the production process is parts processing, the process association data can include the number of parts that the production order can process in the production process, the processing time for a single part, the process preparation time, and the process changeover time, etc.

[0059] After obtaining the process association data, the process association data corresponding to each production process can be matched with several triggering conditions in the main target rule to determine the triggering conditions satisfied by the process association data of each production process, and the satisfied triggering conditions can be used as the target triggering conditions of the production process.

[0060] In this embodiment, the triggering condition can be understood as a judgment criterion based on various scenarios preset by the main target rule, used to determine whether the preconditions for applying a certain secondary target rule are met in a specific production process. For example, the triggering condition may include whether there is a change in type between adjacent orders to be scheduled in the production process (after sorting), and whether the customer delivery time requirements of the corresponding orders to be scheduled in the production process are the same. It can be understood that if there is a change in type between adjacent orders to be scheduled in the production process, the change time between the orders to be scheduled needs to be considered when scheduling production to ensure that the time occupied by the change is minimized. Therefore, based on the main target rule, the scheduling rule that can ensure the minimum change time can be selected from the scheduling rule library as the secondary target rule. If the customer delivery time requirements of the corresponding orders to be scheduled in the production process are the same, all orders with the same customer delivery time requirements need to be completed on time when scheduling production. Therefore, based on the main target rule, the scheduling rule that prioritizes the scheduling of orders with large processing quantities and can compress the total production cycle can be selected from the scheduling rule library as the secondary target rule.

[0061] It is understandable that for a single production process, there may be multiple triggering conditions. For example, in the production process, there may be a change in product type between adjacent orders awaiting production, and there may be orders awaiting production with the same customer delivery date requirement within the same production process. Furthermore, for different production processes, the triggering conditions satisfied by their corresponding process-related data may be different. Therefore, in this embodiment, for each production process, matching is performed independently based on the main target rule and the triggering conditions.

[0062] In one implementation, the production scheduling rule base contains several production scheduling rules, and each production scheduling rule has a corresponding rule application text preset. It can be understood that the rule application text is used to describe the business scenario to which the corresponding sorting rule applies. Therefore, the rule application text can be used as the basis for determining the selection of the secondary target rule, and can be matched with the primary target rule and the target triggering condition through the rule application text.

[0063] like Figure 4 As shown, step S53, which involves selecting the secondary target rule corresponding to the production process from a preset production scheduling rule library based on the primary target rule and the target triggering condition, may include the following sub-steps: A1: The main target rule and the target triggering condition are concatenated semantically to obtain the business scenario corpus; A2: Calculate the semantic similarity between the business scenario corpus and the applicable text of each scheduling rule; A3: Select a secondary target rule from the production scheduling rule base based on the semantic similarity.

[0064] In this embodiment, after obtaining the similarity of the text to which the rule applies, the scheduling rule corresponding to the text to which the rule applies with the highest similarity can be used as the secondary target rule.

[0065] As described above, the applicable text of the rule contains the business scenario to which the corresponding sorting rule applies. Therefore, in this embodiment, by semantically concatenating the main target rule and the target triggering condition, the main target rule and multiple target triggering conditions can be combined. At the same time, by semantically matching the obtained business scenario corpus with the applicable text of the rule, the main target rule and the target triggering condition can be matched with the scheduling rules in the scheduling rule base by adjusting the semantic description. It does not require complete matching in content, and has higher versatility and robustness than structured condition matching.

[0066] When a new production scheduling rule needs to be added, simply add the production scheduling rule and its corresponding applicable text to the production scheduling rule library. At the same time, for different production scheduling rules, only the applicable text of the corresponding rule needs to be adjusted to adjust the applicable business scenario of the production scheduling rule, thereby adjusting the semantic matching relationship between the business scenario corpus and the production scheduling rule, which facilitates the addition of the production scheduling rule.

[0067] Table 3 below provides examples of some production scheduling rules in the aforementioned production scheduling rule base: Table 3 S6: For each production process, based on the main target rule and according to the corresponding secondary target rule and the production association data, perform local search optimization on the production orders to be scheduled in the production process to obtain the production scheduling sequence of the production orders to be scheduled.

[0068] In this embodiment, step S6 may include the following sub-steps: If the number of pending production orders included in the production process exceeds a preset threshold, then based on the main target rule, and according to the corresponding secondary target rule and the production association data, a local search optimization is performed on the pending production orders in the production process. If the number of pending production orders included in the production process does not exceed a preset threshold, then based on the main target rule and the production association data, a local search optimization is performed on the pending production orders in the production process.

[0069] In a preferred embodiment, the preset threshold can be set to 1. It is understood that by adjusting the number of orders to be scheduled in each production process, the complexity of the local optimization strategy can be dynamically adjusted. This ensures scheduling quality in high-load processes while improving processing efficiency in low-load scenarios, achieving an adaptive balance between optimization accuracy and computational performance.

[0070] In this embodiment, by determining the main target rule based on the production-related data of the orders to be scheduled and preset evaluation indicators, it can dynamically adapt to the actual characteristics of the current order set without relying on manual specification. This avoids situations where manual specification cannot match the actual production situation. It can effectively determine the optimal production scheduling order based on the production-related data of the current orders to be scheduled, thereby improving production efficiency. At the same time, after global sorting under the guidance of the main target rule, this embodiment further divides the orders according to the production process and independently selects secondary target rules for each production process for local search optimization. This makes the scheduling result not only meet the overall production orientation, but also achieve fine-grained adjustments at the specific process level, effectively optimizing the scheduling result and thus improving production efficiency.

[0071] like Figure 5 As shown in the illustration, this application also provides an order scheduling system. Optionally, the order scheduling system may include: Data acquisition module 11 is used to collect production-related data of orders to be scheduled for production; In this embodiment, the data acquisition module 11 can be used to perform... Figure 1 For a detailed description of the data acquisition module 11 shown in step S1, please refer to the description of step S1.

[0072] The main target determination module 12 is used to process the production-related data according to preset evaluation indicators to obtain evaluation results, and to determine the main target rules of the production order to be scheduled according to the evaluation results. In this embodiment, the main target determination module 12 can be used to perform... Figure 1 For a detailed description of the main target determination module 12 shown in step S2, please refer to the description of step S2.

[0073] Order sorting module 13 is used to sort the orders to be scheduled for production according to the main target rules and the production association data; In this embodiment, the order sorting module 13 can be used to perform... Figure 1 For a detailed description of the order sorting module 13 shown in step S3, please refer to the description of step S3.

[0074] The process division module 14 is used to divide the sorted orders to be scheduled into production processes. In this embodiment, the process division module 14 can be used to execute... Figure 1 For a detailed description of the process division module 14 shown in step S4, please refer to the description of step S4.

[0075] The secondary target determination module 15 is used to select the secondary target rules corresponding to each production process from the preset production scheduling rule library based on the main target rules and the production association data corresponding to the orders to be scheduled after division. In this embodiment, the secondary target determination module 15 can be used to perform... Figure 1 For a detailed description of the sub-target determination module 15, please refer to the description of step S5 shown in step S5.

[0076] The production sequence acquisition module 16 is used to perform local search optimization on the orders to be scheduled in the production process for each production process based on the main target rule and according to the corresponding secondary target rule and the production association data, so as to obtain the production sequence of the orders to be scheduled.

[0077] In this embodiment, the production sequence acquisition module 16 can be used to perform... Figure 1 For a detailed description of the production sequence acquisition module 16 shown in step S6, please refer to the description of step S6.

[0078] This application provides an electronic device with the following structure: Figure 6 As shown.

[0079] The electronic device includes a memory 21, a processor 22, a communication module 23, and an input / output interface 24, etc. Optionally, the memory 21, the processor 22, the communication module 23, and the input / output interface 24 can be connected and communicate with each other through a bus 25.

[0080] The memory 21 is used to store one or more computer programs and to transfer the code of the computer programs to the processor 22; when the one or more computer programs are executed by the processor 22, an order scheduling method in this embodiment of the application is implemented.

[0081] Optionally, the electronic device can be connected to a network via communication module 23 to communicate with other devices, such as terminals or servers, to achieve data interaction. The electronic device can be various forms of digital computers, exemplarily such as desktop computers, servers, workbenches, mainframes, or other types of computers. The electronic device can also be various forms of mobile terminals, exemplarily such as smartphones, tablets, wearable devices (such as helmets, glasses, watches, etc.), and other similar mobile terminals.

[0082] Optionally, the electronic device can connect to required input / output devices, such as a keyboard or display device, via the input / output interface 24. The electronic device itself may have a display device, and other display devices can also be connected externally via the input / output interface 24. Optionally, a storage device, such as a hard disk, can also be connected via the input / output interface 24 to store data from the electronic device, read data from the storage device, or store data from the storage device in the memory 21. It is understood that the input / output interface 24 can be a wired interface or a wireless interface. Depending on the actual application scenario, the device connected to the input / output interface 24 can be a component of the electronic device or an external device connected to the electronic device when needed.

[0083] Optionally, the memory 21 may be a volatile memory and / or a non-volatile memory. The volatile memory may be a random access memory, etc., and the non-volatile memory may be a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, or a flash memory, etc.

[0084] Optionally, the computer program stored in the processor 22 can be divided into one or more modules, which are stored in the memory 21 and executed by the processor 22 to perform the method provided in this embodiment. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the electronic device.

[0085] Optionally, the processor 22 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 22 include, but are not limited to, a central processing unit, a graphics processing unit, a digital signal processor, various special-purpose artificial intelligence computing chips, various processors running machine learning model algorithms, and can also be any suitable controller, microcontroller, processor, etc. The processor 22 executes the various methods and processes of this embodiment, exemplarily, such as an order scheduling method according to an embodiment of this application.

[0086] Optionally, the bus 25 may include a path for transmitting information. Depending on its function, the bus 25 may be divided into an address bus, a data bus, a control bus, etc.

[0087] In an optional implementation, this application embodiment also provides a computer storage medium storing a computer program thereon. When the computer program is executed by a computer, it enables the computer to perform the methods described in the above-described method embodiments. Part or all of the computer program can be loaded and / or installed on the memory 21 of an electronic device. When the computer program is executed by the processor 22, one or more steps of an order scheduling method according to an embodiment of this application can be performed.

[0088] Optionally, the computer-readable storage medium may be a random access memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, etc.

[0089] Obviously, the above embodiments of this application are merely examples for clearly illustrating the technical solution of this application, and are not intended to limit the specific implementation of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the claims of this application should be included within the protection scope of the claims of this application.

Claims

1. An order scheduling method, characterized in that, The method includes: Collect production-related data for orders awaiting production scheduling; The production-related data is processed according to preset evaluation indicators to obtain evaluation results, and the main target rules of the production orders to be scheduled are determined based on the evaluation results. The orders to be scheduled are sorted according to the main target rules and the production-related data; The sorted orders to be scheduled are divided according to the production process; Based on the main target rules and the production association data corresponding to the orders to be scheduled, select the secondary target rules corresponding to each production process from the preset production scheduling rule library; For each production process, based on the primary objective rule and according to the corresponding secondary objective rule and the production association data, a local search optimization is performed on the production orders to be scheduled in the production process to obtain the production scheduling sequence of the production orders to be scheduled.

2. The order scheduling method according to claim 1, characterized in that, The evaluation indicators include the rule evaluation indicators corresponding to the main preset candidate rules; The process of processing the production-related data according to preset evaluation indicators to obtain evaluation results, and determining the main target rules for the orders to be scheduled for production based on the evaluation results, includes: Based on the rule evaluation index corresponding to the main preset candidate rule, extract the corresponding evaluation data from the production-related data; The evaluation score of the main preset candidate rule is obtained based on the rule evaluation index and the corresponding evaluation data as the evaluation result; The primary target rule for the production order to be scheduled is determined from the primary preset candidate rules based on the evaluation score of the primary preset candidate rules.

3. The order scheduling method according to claim 1, characterized in that, The main target rule is configured with several triggering conditions; The step of selecting secondary target rules corresponding to each production process from a preset production scheduling rule library, based on the production association data corresponding to the primary target rules and the production orders to be scheduled, includes: Based on the division of the pending production orders, obtain the process association data corresponding to each production process from the production association data; Select the triggering condition that matches the data associated with the process as the target triggering condition; Based on the primary target rule and the target triggering condition, the secondary target rule corresponding to each production process is selected from the preset production scheduling rule library.

4. The order scheduling method according to claim 3, characterized in that, The production scheduling rule library contains several production scheduling rules, and each production scheduling rule has a corresponding applicable text preset; The step of selecting the secondary target rule corresponding to the production process from a preset production scheduling rule base according to the primary target rule and the target triggering condition includes: The main target rule and the target triggering condition are semantically concatenated to obtain the business scenario corpus; Calculate the semantic similarity between the business scenario corpus and the applicable text of each scheduling rule; Based on the semantic similarity, a secondary target rule is selected from the production scheduling rule base.

5. An order scheduling method according to any one of claims 1-4, characterized in that, The collection of production-related data for pending orders includes: Retrieve incomplete orders and collect production-related data for those incomplete orders; According to the preset production conflict rules, unfinished orders without production conflicts are selected from the production association data of the unfinished orders and designated as the orders to be scheduled for production.

6. The order scheduling method according to claim 5, characterized in that, The collection of production-related data for the unfinished orders includes: Collect associated data of the incomplete orders based on preset data keywords; The associated data collected from the incomplete orders are associated with the corresponding data keywords to construct a structured data table of data keywords and associated data as the production associated data of the incomplete orders.

7. An order scheduling method according to any one of claims 1-4, characterized in that, For each production process, based on the primary objective rule and according to the corresponding secondary objective rule and the production association data, a local search optimization is performed on the pending production orders in the production process, including: If the number of pending production orders included in the production process exceeds a preset threshold, then based on the main target rule, and according to the corresponding secondary target rule and the production association data, a local search optimization is performed on the pending production orders in the production process. If the number of pending production orders included in the production process does not exceed a preset threshold, then based on the main target rule and the production association data, a local search optimization is performed on the pending production orders in the production process.

8. An order scheduling system, characterized in that, The system includes: The data acquisition module is used to collect production-related data for orders awaiting production scheduling. The main target determination module is used to process the production-related data according to preset evaluation indicators to obtain evaluation results, and to determine the main target rules of the production order to be scheduled based on the evaluation results; The order sorting module is used to sort the orders to be scheduled for production according to the main target rules and the production-related data; The process division module is used to divide the sorted orders to be scheduled into production processes. The secondary target determination module is used to select the secondary target rules corresponding to each production process from the preset production scheduling rule library based on the main target rules and the production association data corresponding to the orders to be scheduled. The production sequence acquisition module is used to perform local search optimization on the orders to be scheduled in the production process for each production process based on the main target rule and according to the corresponding secondary target rule and the production association data, so as to obtain the production sequence of the orders to be scheduled.

9. An electronic device, characterized in that, include: Memory, used to store one or more computer programs; A processor, when the one or more computer programs are executed by the processor, implements an order scheduling method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute an order scheduling method as described in any one of claims 1-7.

Images