Object making scheduling method and device, medium and computer equipment

Abstract

An object production scheduling method and apparatus, a medium and a computer device, the method comprising: acquiring a plurality of orders, each of the plurality of orders comprising at least one category of to-be-produced objects that are not produced completely, and at least two orders comprising the same category of to-be-produced objects; obtaining an initial scheduling scheme of each type of to-be-made object in the plurality of orders; the initial scheduling scheme is used for representing a making sequence of to-be-made objects of various categories in the plurality of orders; and optimizing the initial scheduling scheme based on a preset optimization target to obtain an optimized scheduling scheme, the optimization target being determined based on the total delay delivery duration of the plurality of orders and the total production duration of the to-be-produced objects of each category in the plurality of orders, the optimization comprises the step of performing combined production on the to-be-produced objects with the same category in the at least two orders; the optimized scheduling scheme comprises a sorting scheme for the to-be-made objects.

Description

Technical Field

[0001] The present disclosure relates to the technical field of data processing, and in particular, to an object production scheduling method and apparatus, a medium, and a computer device. Background Art

[0002] In the related art, when a producer produces an object to be produced, the producer often produces in units of orders. That is, the producer will first produce the objects to be produced in a certain order, and after all the objects to be produced in that order are produced, then produce the objects to be produced in the next order. However, the production efficiency of the above production method in units of orders is relatively low. Summary of the Invention

[0003] In a first aspect, an embodiment of the present disclosure provides an object production scheduling method, the method including: obtaining a plurality of orders, each order of the plurality of orders including at least one category of objects to be produced that are not completed, and at least two orders including objects to be produced of the same category; obtaining an initial scheduling plan for the objects to be produced of each category in the plurality of orders; the initial scheduling plan being used to represent the production order of the objects to be produced of each category in the plurality of orders; optimizing the initial scheduling plan based on a preset optimization goal, the optimization goal being determined based on the total late delivery duration of the plurality of orders and the total production duration of the objects to be produced of each category in the plurality of orders, the optimization including jointly producing the objects to be produced of the same category in at least two orders; the optimized scheduling plan including a sorting plan for the objects to be produced.

[0004] In some embodiments, obtaining the initial scheduling plan for the objects to be produced of each category in the plurality of orders includes: obtaining the order entry order of the plurality of orders; sorting the objects to be produced of each category in the plurality of orders in sequence according to the order entry order of the plurality of orders, to obtain the initial scheduling plan.

[0005] In some embodiments, optimizing the initial scheduling plan based on a preset optimization goal includes: adjusting the production order represented by the initial scheduling plan to obtain an adjusted production order; if the objects to be produced corresponding to adjacent positions in the adjusted production order belong to the same category, jointly producing the objects to be produced corresponding to the adjacent positions to obtain an optimized scheduling plan; if the optimized scheduling plan does not meet a preset iteration termination condition, determining the optimized scheduling plan as the initial scheduling plan, and returning to the step of adjusting the production order represented by the initial scheduling plan.

[0006] In some embodiments, adjusting the production sequence represented by the initial scheduling plan includes: adjusting the production sequence represented by the initial scheduling plan based on at least one of the following methods: randomly selecting two positions in the initial scheduling plan and reversing each position between the two positions; randomly selecting two positions in the initial scheduling plan and swapping the two positions; randomly selecting one position in the initial scheduling plan and inserting the randomly selected position into a new position in the initial scheduling plan; randomly selecting one position in the initial scheduling plan and swapping the randomly selected position with its adjacent position.

[0007] In some embodiments, the iteration termination condition includes at least one of the following: the number of iterations reaches a first number threshold; the number of consecutive occurrences of the same objective value corresponding to the optimization objective reaches a second number threshold.

[0008] In some embodiments, the optimization objective includes: minimizing the total late delivery duration and minimizing the sum of the total production durations.

[0009] In some embodiments, the total late delivery duration is obtained by weighting the late delivery durations of the multiple orders respectively by using the weights corresponding to the multiple orders, and the weights corresponding to the multiple orders are determined based on the delivery priorities corresponding to the multiple orders.

[0010] In some embodiments, the delivery priority corresponding to the order is determined based on at least one of the following: whether the order is a VIP order; whether the order is an inserted order.

[0011] In some embodiments, the late delivery duration of the order is determined based on the time difference between the latest delivery time of the order and the order completion time of the order estimated based on the optimized scheduling plan; wherein, the latest delivery time is determined based on the sum of the order placement time of the order and a preset duration; or the latest delivery time is determined based on the number of orders that have been received and not completed up to the order placement moment of the order.

[0012] In some embodiments, the total production duration is determined based on the maximum value of the production durations of the objects to be produced of each category, and the production duration of the object to be produced is determined based on the number of producers of the object to be produced.

[0013] In some embodiments, the number of objects to be produced of each category is greater than or equal to 1, and in the optimized scheduling plan, the objects to be produced of the same category in the same order are combined for production.

[0014] Second aspect, embodiments of the present disclosure provide an object production scheduling device, the device includes: a first acquisition module, configured to acquire a plurality of orders, each order in the plurality of orders includes at least one category of to-be-produced objects that have not been completed, and at least two orders include to-be-produced objects of the same category; a second acquisition module, configured to acquire an initial scheduling plan for the to-be-produced objects of each category in the plurality of orders; the initial scheduling plan is used to represent the production order of the to-be-produced objects of each category in the plurality of orders; an optimization module, configured to optimize the initial scheduling plan based on a preset optimization goal to obtain an optimized scheduling plan, the optimization goal is determined based on the total late delivery duration of the plurality of orders and the total production duration of the to-be-produced objects of each category in the plurality of orders, the optimization includes jointly producing the to-be-produced objects of the same category in at least two orders; the optimized scheduling plan includes a sorting plan for the to-be-produced objects.

[0015] In some embodiments, the second acquisition module is configured to: acquire the order entry sequence of the plurality of orders; sort the to-be-produced objects of each category in the plurality of orders in sequence according to the order entry sequence of the plurality of orders to obtain the initial scheduling plan.

[0016] In some embodiments, the optimization module is configured to: adjust the production order represented by the initial scheduling plan to obtain an adjusted production order; if the to-be-produced objects corresponding to adjacent positions in the adjusted production order belong to the same category, jointly produce the to-be-produced objects corresponding to the adjacent positions to obtain an optimized scheduling plan; if the optimized scheduling plan does not meet the preset iteration termination condition, determine the optimized scheduling plan as the initial scheduling plan, and return to execute the function of adjusting the production order represented by the initial scheduling plan.

[0017] In some embodiments, the optimization module is configured to: adjust the production order represented by the initial scheduling plan based on at least one of the following methods: randomly select two positions in the initial scheduling plan and reverse each position between the two positions; randomly select two positions in the initial scheduling plan and exchange the two positions; randomly select one position in the initial scheduling plan and insert the randomly selected position into a new position in the initial scheduling plan; randomly select one position in the initial scheduling plan and exchange the randomly selected position with its adjacent position.

[0018] In some embodiments, the iteration termination condition includes at least one of the following: the number of iterations reaches the first number threshold; the number of consecutive occurrences of the same target value corresponding to the optimization goal reaches the second number threshold.

[0019] In some embodiments, the optimization objectives include minimizing the total late delivery duration and minimizing the sum of the total production durations.

[0020] In some embodiments, the total late delivery duration is obtained by weighting the late delivery durations of the multiple orders respectively by using the weights corresponding to the multiple orders, and the weights corresponding to the multiple orders are determined based on the delivery priorities corresponding to the multiple orders respectively.

[0021] In some embodiments, the delivery priority corresponding to the order is determined based on at least one of the following: whether the order is a VIP order; whether the order is an inserted order.

[0022] In some embodiments, the late delivery duration of the order is determined based on the time difference between the latest delivery time of the order and the order completion time of the order estimated based on the optimized scheduling plan; wherein, the latest delivery time is determined based on the sum of the order placement time of the order and a preset duration; or the latest delivery time is determined based on the number of orders that have been received and not completed up to the order placement moment of the order.

[0023] In some embodiments, the total production duration is determined based on the maximum value of the production durations of the objects to be produced of each category, and the production duration of the object to be produced is determined based on the number of producers of the object to be produced.

[0024] In some embodiments, the number of objects to be produced of each category is greater than or equal to 1, and in the optimized scheduling plan, the objects to be produced of the same category in the same order are combined for production.

[0025] In a third aspect, an embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method described in any embodiment of the present disclosure is implemented.

[0026] In a fourth aspect, an embodiment of the present disclosure provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the method described in any embodiment of the present disclosure is implemented.

[0027] In the embodiments of the present disclosure, an initial scheduling plan is first determined, and then an optimization objective is determined based on the total delayed delivery duration of multiple orders and the total production duration of the objects to be produced in each category of the multiple orders. The initial scheduling plan is optimized, including combined production, based on the optimization objective, so as to obtain an optimized scheduling plan. On the one hand, taking the total production duration of the objects to be produced in each category of the multiple orders as the optimization objective for combined production reduces the average production duration and production frequency of the objects to be produced, thereby effectively improving the production efficiency of the objects to be produced. On the other hand, taking the total delayed delivery duration of the multiple orders as the optimization objective reduces the order delivery delay caused by combined production and reduces the waiting duration of users.

[0028] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings herein are incorporated into the specification and constitute a part of the present disclosure. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to explain the technical solutions of the present disclosure.

[0030] Figure 1 is a schematic diagram of an object production scheduling method in the related art.

[0031] Figure 2 is a flowchart of an object production scheduling method according to an embodiment of the present disclosure.

[0032] Figure 3 is an overall flowchart of an embodiment of the present disclosure.

[0033] Figure 4 is a schematic diagram of an evolution process based on a simulated annealing algorithm according to an embodiment of the present disclosure.

[0034] Figure 5A and Figure 5B is a comparative schematic diagram of an object production process in the related art and an embodiment of the present disclosure.

[0035] Figure 6 is a block diagram of an object production scheduling device according to an embodiment of the present disclosure.

[0036] Figure 7 is a schematic diagram of a computer device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0038] The terms used in the present disclosure are for the purpose of describing particular embodiments only and are not intended to limit the present disclosure. The singular forms "a", "the", and "said" used in the present disclosure and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. Additionally, the term "at least one" as used herein represents any one of a plurality or any combination of at least two of a plurality.

[0039] It should be understood that although the terms first, second, third, etc. may be used in the present disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0040] In order for those skilled in the art to better understand the technical solutions in the embodiments of the present disclosure and to make the above-mentioned objects, features, and advantages of the embodiments of the present disclosure more apparent and understandable, the technical solutions in the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.

[0041] In the related art, when a producer manufactures an object to be manufactured, the production is often carried out on an order-by-order basis. Taking the application scenario of the catering industry as an example and combining Figure 1 , an example will be given of the production method on an order-by-order basis. Refer to Figure 1, the producer receives two different orders at different times, denoted as Order A and Order B respectively. The order receipt time of Order A is 10:25:20, and the order receipt time of Order B is 10:25:30, that is, the order receipt time of Order A is earlier than that of Order B. Order A includes 1 serving of fried chicken drumsticks, 1 serving of French fries and 1 serving of hamburger, and Order B includes 1 serving of French fries and 1 serving of orange juice. In the related art, the producer makes food items in units of orders, that is, the producer will first make each food item in Order A. After all the food items in Order A are made, then make each food item in Order B. Therefore, the production order of each food item is as follows: 1 serving of fried chicken drumsticks, 1 serving of French fries, 1 serving of hamburger, 1 serving of French fries, 1 serving of orange juice. However, when some food items are made one by one and when made in multiple portions together, the average production time is often quite different. For example, for French fries, assuming that one serving of French fries is made each time, the production time for one serving of French fries is 30 seconds, so it takes a total of 60 seconds to make the two servings of French fries in Order A and Order B. If it is assumed that two servings of French fries are made each time, the total production time for these two servings of French fries is only 38 seconds, that is, the average production time for each serving of French fries is only 19 seconds. Therefore, if the two servings of French fries in Order A and Order B are combined for production, the production efficiency can be effectively improved.

[0042] It can be understood that the application scenarios in the above embodiments are only for illustrative purposes and are not used to limit the present disclosure. For example, in the application scenario of material processing, when processing multiple materials simultaneously (such as cutting, heating, etc.), the average time-consuming for material processing may be shorter than the average time-consuming when processing one material each time.

[0043] In summary, in the production method in units of orders, the characteristic that the average production time is shorter when combined production is carried out cannot be utilized, resulting in lower production efficiency.

[0044] Based on this, the present disclosure provides an object production scheduling method, see Figure 2 , the method includes:

[0045] Step S1: Obtain multiple orders, each order in the multiple orders includes at least one category of to-be-produced objects that are not yet produced, and at least two orders include to-be-produced objects of the same category;

[0046] Step S2: Obtain an initial scheduling plan for the to-be-produced objects of each category in the multiple orders; the initial scheduling plan is used to represent the production order of the to-be-produced objects of each category in the multiple orders;

[0047] Step S3: Optimize the initial scheduling plan based on a preset optimization objective to obtain an optimized scheduling plan. The optimization objective is determined based on the total overdue delivery duration of multiple orders and the total production duration of the objects to be produced in each category among the multiple orders. The optimization includes jointly producing the objects to be produced with the same category in at least two orders; the optimized scheduling plan includes the sorting plan of the objects to be produced.

[0048] In the embodiment of the present disclosure, after obtaining multiple orders, production scheduling is carried out in units of the objects to be produced in each category among the multiple orders. First, an initial scheduling plan is determined, and then an optimization objective is determined based on the total overdue delivery duration of multiple orders and the total production duration of the objects to be produced in each category among the multiple orders, and the initial scheduling plan is optimized including joint production based on the optimization objective, so as to obtain an optimized scheduling plan. On the one hand, the above solution takes the total production duration of the objects to be produced in each category among the multiple orders as an optimization objective for joint production, reducing the average production duration and production frequency of the objects to be produced, and thus can effectively improve the production efficiency of the objects to be produced; on the other hand, the total overdue delivery duration of multiple orders is also taken as an optimization objective, thereby reducing the order delivery delay caused by joint production and reducing the waiting duration of users.

[0049] The following takes Figure 1 the application scenario shown as an example to illustrate the solution of the embodiment of the present disclosure.

[0050] In step S1, multiple orders participating in scheduling can be obtained. The above multiple orders may include at least two orders that have been received at the current moment and have not been completed for delivery. Among them, the order not being completed for delivery means that at least one category of the objects to be produced in the order has not been produced. For example, at time T1, order A is obtained. Order A includes 1 serving of fried chicken legs, 1 serving of French fries, and 1 serving of hamburger, and each category of food in order A has not been produced. Then, at time T1, order A can be included in the multiple orders, and the objects to be produced in order A that have not been produced (i.e., participating in scheduling) include 1 serving of fried chicken legs, 1 serving of French fries, and 1 serving of hamburger.

[0051] Orders can be refreshed at preset time intervals or when new orders are received, and the categories of to-be-produced objects that are not yet completed in the refreshed orders are updated. Specifically, if, at the time of refreshing, all to-be-produced objects of each category in a certain order have been produced, then that order is deleted from the multiple orders participating in the scheduling, and based on the categories and quantities of the to-be-produced objects in that order, to-be-produced objects that have been completed in corresponding categories and quantities are obtained, and the obtained to-be-produced objects are delivered. If, at the time of refreshing, a to-be-produced object of a certain category in a certain order participating in the scheduling has been produced, then the produced to-be-produced object is deleted from the to-be-produced objects participating in the scheduling. If a new order is detected at the time of refreshing, then the new order is added to the multiple orders participating in the scheduling, and the categories of the to-be-produced objects included in the new order are added to the categories of the to-be-produced objects participating in the scheduling.

[0052] Continuing with the above example, at time T2 after time T1, the order can be refreshed. Assume that order B is received between time T1 and time T2, and this order B includes 1 serving of French fries and 1 serving of orange juice. Also, assume that the fried chicken in order A is produced between time T1 and time T2. Then, at time T2, the multiple orders can include order A and order B. The to-be-produced objects that are not yet completed (i.e., participating in the scheduling) in order A include 1 serving of French fries and 1 serving of hamburger, and the to-be-produced objects that are not yet completed (i.e., participating in the scheduling) in order B include 1 serving of French fries and 1 serving of orange juice. According to business requirements, the to-be-produced objects that are not yet completed can be scheduled for the next optimization together with the produced objects in the newly received order, or they can be not scheduled for the next optimization together with the produced objects in the newly received order, but instead be continued to be produced by the production personnel or equipment. Taking the former case as an example, assume that at time T3, all the food items in order A and the French fries in order B have been produced, and an order C including 1 serving of ice cream is received between time T2 and time T3. Then, at time T3, the multiple orders can include order B and order C. The to-be-produced objects that are not yet completed (i.e., participating in the scheduling) in order B include 1 serving of orange juice, and the to-be-produced objects that are not yet completed (i.e., participating in the scheduling) in order C include 1 serving of ice cream.

[0053] It should be noted that Figure 1It shows a case where the number of objects to be made in each category is 1. It can be understood that this is only an exemplary illustration here. In practical applications, the number of objects to be made in each category can be greater than or equal to 1. For example, in order A, the number of fried chicken legs can be 2 servings, and in orders A and B, the number of French fries can be 2 or 3 servings, etc. The number of objects to be made in other categories can also be greater than 1, which will not be elaborated here. When the number of objects to be made in a certain category in the same order is greater than 1, multiple objects to be made in this category can be combined and made as a whole without splitting them. For example, assume that in Figure 1 In the illustrated embodiment, the number of fried chicken legs in order A is 2, and the number of orange juices in order B is 3. Then, the two fried chicken legs are taken as a whole, and the 3 orange juices are taken as a whole. Thus, the production sequence can be: 2 fried chicken legs, 1 serving of French fries, 1 hamburger, 1 serving of French fries, 3 orange juices. The overall production completion time of the combined production of objects to be made is the production completion time of all objects to be made in the combined production. For example, when 2 fried chicken legs are combined and made, the production duration is 60 seconds. Then, when the production duration reaches 60 seconds, both fried chicken legs are made. If the production duration is shorter than 60 seconds, neither of the two fried chicken legs is made.

[0054] In step S2, an initial scheduling plan can be obtained. The initial scheduling plan is used to represent the production sequence of objects to be made in each category in multiple orders (referred to as the initial production sequence). This initial production sequence is the production sequence in units of the categories of objects to be made. The initial production sequence includes multiple positions, which are sequentially recorded as position 1, position 2, position 3, and so on. Each position corresponds to an object to be made in a category. The earlier the position of an object to be made in a certain category, the earlier the start production time of this category of objects to be made; conversely, the later the position of an object to be made in a certain category, the later the start production time of this category of objects to be made. Still taking Figure 1 Orders A and B shown as an example, the initial production sequence can be: 1 fried chicken leg, 1 serving of French fries, 1 hamburger, 1 serving of French fries, 1 orange juice. Then, the position of the fried chicken leg is 1, the position of the French fries is 2, the position of the hamburger is 3, the position of the other serving of French fries is 4, and the position of the orange juice is 5. During production, first make 1 fried chicken leg, then make 1 serving of French fries, then make 1 hamburger, then make the other serving of French fries, and finally make 1 orange juice.

[0055] In some embodiments, the to-be-produced objects of each category in multiple orders may be sorted in the order of order receipt to obtain an initial scheduling plan. That is to say, the to-be-produced objects of each category in the order with an earlier order receipt time may be ranked before the to-be-produced objects of each category in the order with a later order receipt time. Further, if a certain order includes to-be-produced objects of multiple categories, the ranks may be randomly assigned to the to-be-produced objects of each category in this order, or the ranks may be assigned to the to-be-produced objects of each category in this order according to the order in which the to-be-produced objects of each category are added to the order. For example, in Figure 1 the order receipt time of order A is earlier than that of order B. Therefore, in the initial scheduling plan, the ranks of the to-be-produced objects of each category in order A are ranked before the ranks of the to-be-produced objects of each category in order B.

[0056] In other embodiments, the to-be-produced objects of each category in multiple orders may also be randomly sorted to obtain an initial scheduling plan. Other methods may also be used to obtain the initial scheduling plan, which will not be enumerated here one by one.

[0057] For the convenience of sorting and optimization, the to-be-produced objects of each category may be encoded. The encodings of the to-be-produced objects of different categories in the same order may be different, so as to facilitate the distinction of the to-be-produced objects of different categories in different orders. The encodings of the to-be-produced objects of the same category in different orders may be the same or different. Assuming that multiple orders include order A, order B, and order C in the foregoing embodiments, in an example where the encodings of the to-be-produced objects of the same category in different orders are different, one encoding method is as follows:

[0058] The fried chicken legs, French fries, and hamburgers in order A are encoded as 1, 2, and 3 respectively;

[0059] The French fries and orange juice in order B are encoded as 4 and 5 respectively;

[0060] The ice cream in order C is encoded as 6.

[0061] In an example where the encodings of the to-be-produced objects of the same category in different orders are the same, one encoding method is as follows:

[0062] The fried chicken legs, French fries, and hamburgers in order A are encoded as 1, 2, and 3 respectively;

[0063] The French fries and orange juice in order B are encoded as 2 and 4 respectively;

[0064] The ice cream in order C is encoded as 5.

[0065] In some embodiments, the encoding may include bits for representing the order and bits for representing the category of the to-be-produced object. For example, one encoding method is as follows:

[0066] The fried chicken drumsticks, French fries, and hamburgers in Order A are coded as 11, 12, and 13 respectively;

[0067] The French fries and orange juice in Order B are coded as 22 and 24 respectively;

[0068] The ice cream in Order C is coded as 35.

[0069] The high digits in the above codes are used to identify the orders. "1" corresponds to Order A, "2" corresponds to Order B, and "3" corresponds to Order C. The low digits in the above codes are used to identify the categories of the objects to be made. "1", "2", "3", "4", and "5" correspond to fried chicken drumsticks, French fries, hamburgers, orange juice, and ice cream respectively. In this way, different categories can be distinguished, and it can also be known which order the object to be made comes from.

[0070] In addition to the above-listed coding methods, other methods can also be used to code the objects to be made, which will not be elaborated here. For the convenience of description, when describing the production sequence of the objects to be made of each category below, a sequence composed of the codes of the objects to be made of each category will be used for illustration.

[0071] After the coding is completed, the codes of the objects to be made of each category in multiple orders can be sorted to obtain the initial scheduling plan for the objects to be made of each category in multiple orders. Taking the first coding method above as an example, the codes of the objects to be made of each category can be sorted. Assuming the sorting of each code is "1→2→3→4→5→6", it means the order of the objects to be made of each category is as follows: 1 portion of fried chicken drumsticks, 1 portion of French fries, 1 portion of hamburger, 1 portion of French fries, 1 portion of orange juice, 1 portion of ice cream.

[0072] In step S3, the initial scheduling plan can be optimized to obtain an optimized scheduling plan. Specifically, the production order represented by the initial scheduling plan can be adjusted to obtain an adjusted production order, so as to determine whether there is a scheduling plan that is better than the initial scheduling plan. For example, assume that the order of the objects to be produced in each category is as follows: 1 serving of fried chicken drumsticks, 1 serving of French fries, 1 serving of hamburger, 1 serving of French fries, 1 serving of orange juice, 1 serving of ice cream, and its coding is represented as "1→2→3→4→5→6". The above order can be adjusted. For example, the production order of the fried chicken drumsticks and the orange juice can be swapped, so as to obtain the adjusted production order as "5→2→3→4→1→6", and the production order of each object to be produced is in turn: 1 serving of orange juice, 1 serving of French fries, 1 serving of hamburger, 1 serving of French fries, 1 serving of fried chicken drumsticks, 1 serving of ice cream. Or, the production order of the French fries in order A and the hamburger in order A can also be swapped, so as to obtain the adjusted production order as "1→3→2→4→5→6", and the production order of each object to be produced is in turn: 1 serving of fried chicken drumsticks, 1 serving of hamburger, 1 serving of French fries, 1 serving of French fries, 1 serving of orange juice, 1 serving of ice cream.

[0073] After obtaining the adjusted production order, if the objects to be produced corresponding to adjacent positions in the adjusted production order belong to the same category, the objects to be produced corresponding to the adjacent positions are combined for production to obtain an optimized scheduling plan. Continuing with the previous example, assume that the adjusted production order is "1→3→2→4→5→6", then the categories of the objects to be produced corresponding to the third position and the fourth position in the above production order are both French fries, and the third position and the fourth position are adjacent positions. Therefore, the objects to be produced corresponding to the third position and the fourth position can be combined for production, that is, the two servings of French fries are combined for production, and the obtained optimized scheduling plan is "1→3→2+4→5→6", and the production order of each object to be produced is in turn: 1 serving of fried chicken drumsticks, 1 serving of hamburger, 2 servings of French fries, 1 serving of orange juice, 1 serving of ice cream.

[0074] The above iterative optimization can be performed multiple times. Specifically, it can be determined whether the above optimized scheduling plan meets the preset iteration termination condition. If not, the optimized scheduling plan is re-determined as the initial scheduling plan, and the step of adjusting the production order represented by the initial scheduling plan is returned. If the preset iteration termination condition is met, the iteration is stopped, and the above optimized scheduling plan is determined as the final scheduling plan.

[0075] Taking the initial scheduling plan as "1→2→3→4→5→6" as an example, the method of adjusting the production order is illustrated as follows. The production order represented by the initial scheduling plan can be adjusted based on at least one of the following methods:

[0076] Method 1: Randomly select two positions in the initial scheduling plan and reverse each position between these two positions. Suppose the two randomly selected positions are the 1st position (i.e., the production position corresponding to the object to be produced of the category numbered "1") and the 5th position (i.e., the production position corresponding to the object to be produced of the category numbered "5"). Then each position between these two positions includes "2→3→4", reverse it to get "4→3→2", so the adjusted production order obtained is "1→4→3→2→5→6".

[0077] Method 2: Randomly select two positions in the initial scheduling plan and swap these two positions. Still suppose the two randomly selected positions are the 1st position and the 5th position. Then the adjusted production order obtained after swapping these two positions is "5→2→3→4→1→6".

[0078] Method 3: Randomly select one position in the initial scheduling plan and insert the randomly selected position into a new position in the initial scheduling plan. Among them, the new position can also be randomly selected. For example, suppose the randomly selected position is the 2nd position (i.e., the production position corresponding to the object to be produced of the category numbered "2"), then the code corresponding to the 2nd position can be inserted between the 5th position and the 6th position, and the adjusted production order obtained is "1→3→4→5→2→6".

[0079] Method 4: Randomly select one position in the initial scheduling plan and swap the randomly selected position with its adjacent position. Among them, the adjacent position can be the previous position or the next position of this position. Taking the adjacent position as the previous position of this position as an example, suppose the randomly selected position is the 2nd position, then the adjacent position is the 1st position, and the code corresponding to the 2nd position can be swapped with the code corresponding to the 1st position, and the adjusted production order obtained is "2→1→3→4→5→6".

[0080] In each iteration, one of the above four methods can be randomly selected to adjust the order of the initial scheduling plan in the current iteration process to obtain an optimized scheduling plan, and then it is judged whether this iteration meets the iteration termination condition. If not, continue the iteration, otherwise terminate the iteration. By selecting the order adjustment method from multiple methods, the situation that the obtained optimized scheduling plan falls into a local optimal solution can be reduced, thereby improving the accuracy of the optimized scheduling plan.

[0081] Among them, the iteration termination condition may include that the number of iterations reaches the first number threshold, and / or the number of consecutive occurrences of the same objective value corresponding to the optimization objective reaches the second number threshold. The first number threshold and the second number threshold can be preset according to actual needs. By setting the number of iterations reaching the first number threshold as the iteration termination condition, the total number of iterations can be constrained, thereby improving the optimization efficiency. When the number of consecutive occurrences of the same objective value corresponding to the optimization objective reaches the second number threshold, it indicates that the iteration result may have converged, so the iteration can be stopped.

[0082] In the above embodiment, the optimization objective may include minimizing the total delayed delivery duration and minimizing the sum of the total production durations. Among them, minimizing the total delayed delivery duration means that the sum of the delivery delays of all orders is the shortest. The latest delivery time of the order can be preset. If the order completion time is earlier than or equal to the latest delivery time, the delivery delay of this order is 0; if the order completion time is later than the latest delivery time, the delivery delay of this order is the difference between the order completion time and the latest delivery time. Therefore, for order j, its delayed delivery duration can be recorded as max(c j -d j ,0), where d j is the latest delivery time of order j, and c j is the order completion time of order j.

[0083] Among them, the latest delivery time d j can be determined based on the sum of the order placement time of order j and the preset waiting duration. To reduce the waiting time of users, usually an upper limit of the user waiting duration (i.e., the above preset duration) is set. For example, "This restaurant promises to complete the production of food within 10 minutes after the user places an order". Assume that the order placement time of order j is t and the preset waiting duration is Δt, then the latest delivery time can be recorded as t + Δt. Taking the catering industry as an example, in the case where the user places an order online and picks up the food in the store, it is usually assumed that the pick-up time of the user is 10 minutes after the user places an order. To reduce the user waiting, Δt can be set to 10 minutes. The purpose is to possibly complete the production of the user's order before the user arrives at the store so that the user can pick up the order immediately when arriving at the store. Or, the latest delivery time can be determined based on the number of orders that have actually not been completed at the moment when order j is placed. For example, assume that the order placement time of order j is t. By time t, the number of received and uncompleted orders is Nt, and the average production duration of the order is t0, then the latest delivery time can be recorded as Nt * t0; or another timing model estimates the production duration Δt of all to-be-produced objects that have been in the production scheduling plan and have not been completed before time t. The order completion time c jIt can be the completion time of order j estimated based on the scheduling plan obtained in the current iteration, that is, the time when all the objects to be manufactured in order j estimated based on the scheduling plan obtained in the current iteration are completely manufactured.

[0084] In other examples, the total late delivery duration can also be calculated in other ways. For example, if the order completion time is earlier than or equal to the latest delivery time, the delivery delay of this order is a negative value or a small value (referred to as a reward value); if the order completion time is later than the latest delivery time, the delivery delay of this order is a positive value or a large value (referred to as a penalty value). The total late delivery duration is the sum of the reward value and the penalty value. When there are multiple categories of objects to be manufactured in an order, the order completion time is the completion time of the last category of objects to be manufactured in the order.

[0085] By summing up the delivery durations of each order, the total late delivery duration can be obtained. By setting the optimization goal of minimizing the total late delivery duration, the late delivery of orders caused by the combined manufacturing of objects to be manufactured can be reduced, thereby reducing the waiting time of users.

[0086] Minimizing the sum of the total manufacturing durations means that the completion time of the last order is the shortest, that is, the maximum value of the manufacturing durations of various categories of objects to be manufactured is the shortest. Therefore, the total manufacturing duration can be denoted as max({c 1 ,c 2 ,…,c n}). By setting the optimization goal of minimizing the sum of the total manufacturing durations, the manufacturing efficiency of the objects to be manufactured can be improved. The manufacturing duration of the objects to be manufactured can be determined based on the number of manufacturers of the objects to be manufactured. Assuming that the manufacturing duration of the objects to be manufactured is X, then based on the number of manufacturers, the manufacturing duration of the objects to be manufactured can be converted into human efficiency. Assuming that the number of manufacturers is K, the converted manufacturing duration is X / K.

[0087] In some embodiments, the total late delivery duration and the total manufacturing duration can be summed up to obtain an objective function. The optimization goal is to minimize the value of the objective function (i.e., the objective value).

[0088] Furthermore, the total late delivery duration can be obtained by weighting the late delivery durations of the multiple orders respectively by using the weights corresponding to the multiple orders, and can be specifically denoted as:

[0089]

[0090] Among them, the weight corresponding to an order is determined based on the delivery priority corresponding to the order. The delivery priority corresponding to an order can be determined based on at least one of the following: whether the order is a VIP order and whether the order is an inserted order. Among them, a VIP order can be an order of a VIP user, and a non-VIP order can be an order of a non-VIP user. The delivery priority of a VIP order is higher than that of a non-VIP order, and the delivery priority of an inserted order is higher than that of a non-inserted order. An inserted order can be an order that is temporarily added. The delivery priority of an inserted order can be higher than that of a non-inserted order. The weight corresponding to an order can be positively correlated with the delivery priority of the order. In this way, the penalty for the late delivery duration of orders with different priorities can be imposed through the weight. The greater the weight, the higher the penalty ratio caused by the late delivery of the order, so as to effectively reduce the late delivery of orders with higher priorities such as VIP orders and inserted orders.

[0091] After adding the weight, the optimization objective can be denoted as:

[0092]

[0093] Among them, n represents the number of orders, c j is the order completion time of order j, the model time starting point is defaulted to 0, d j is the latest delivery time of order j, w j is the weight of order j.

[0094] Next, taking the catering industry as an example and referring to Figure 3 , the overall process of the embodiments of the present disclosure will be illustrated by examples. First, the food items can be encoded, and the initial simulated annealing parameters can be determined. Then, an initial scheduling plan can be generated. Then, it is determined whether the initial scheduling plan meets the iteration termination condition. If it meets, the initial scheduling plan is used as the optimal scheduling plan and output. If it does not meet, the initial scheduling plan is optimized to generate an optimized scheduling plan, the temperature parameter is updated, the optimal scheduling plan is retained, and it is re-determined whether the optimal scheduling plan meets the iteration termination condition.

[0095] During iteration, in the case of knowing the initial scheduling plan, a Markov chain can be formed by several consecutive searches to optimize the scheduling plan. The final result of this Markov chain is used as the initial scheduling plan for the next Markov chain for the next round of search until the optimal scheduling plan is obtained. In some embodiments, the simulated annealing algorithm can be used for iterative optimization. According to the production time required for different quantities of each type of object to be produced and considering the following constraints, the production completion time of each type of object to be produced within each order can be calculated:

[0096] The overall production completion time of the objects to be produced after merging is the production completion time of all the objects to be produced in the merged production;

[0097] For objects to be produced of the same category, the time difference between the average production duration for producing one such object each time and the average production duration for producing multiple such objects each time is relatively large. The more the production quantity, the shorter the average production duration;

[0098] Convert the production duration of the objects to be produced into human efficiency according to the number of producers.

[0099] Furthermore, based on the production completion time of the objects to be produced in the last category of each order as the production completion time of the order, the production completion time of each order can be calculated. According to the optimization objectives in the foregoing embodiments, the objective value of the optimized scheduling plan obtained after each iterative optimization can be calculated.

[0100] Taking the catering industry as an example and taking the order intake data of a certain store during a certain lunch peak as an example for illustration. Assume that at 11:00:00, 6 orders enter the food production workstation. The priorities of each order are the same. The order intake time, latest delivery time, and food information of each order are shown in Table 1, and the production time of each food under different production quantities is shown in Table 2. The production time unit is seconds. In the following table, it is assumed that the foods of the same category in each order use the same coding.

[0101] Table 1 Order Information

[0102] Order Food Code Quantity of Food Order Entry Time Latest Delivery Time 1 1001 1 10:48:07 10:58:07 2 1002 1 10:52:50 11:02:50 3 1001 1 10:53:29 11:03:29 4 1003 1 10:55:37 11:05:37 5 1002 1 10:56:22 11:06:22 6 1003 1 11:00:00 11:10:00

[0103] Table 2 Food Production Time

[0104]

[0105]

[0106] Sort the foods in order of the order intake time from earliest to latest. The detailed food production time is shown in Table 3. The column of time difference represents the first item in formula (1) (i.e., the total late delivery duration). Assume that each order has only one food, then the food production completion time is the order production completion time.

[0107] Table 3 By Order Intake Time

[0108]

[0109] Sort the food items according to the order entry time. The initial solution is 1001→1002→1001→1003→1002→1003. Set the initial parameters of simulated annealing: the initial temperature is 10, the stopping iteration temperature is 1e-8, the cooling rate is 0.99, the chain length is 10, the number of iterations is 500, and the number of convergent iterations is 300. Call the simulated annealing algorithm, and the optimal solution is 1001→1001→1002→1003→1003→1002. The target value convergence iteration graph is as shown in Figure 4 shown. The production information of the food items sorted according to the optimal solution is shown in Table 4. The food item 1001 of Order 1 and Order 3 is combined for production, and the food item 1003 of Order 4 and Order 6 is combined for production. According to the order entry time food item sequence of the order in Table 3, the sum of the time differences of the objective function is 206s, and the overall production time is 372s; according to the production sequence of the optimal solution in Table 4, the sum of the time differences of the objective function is 207s, and the overall production time is 291s.

[0110] Table 4 The optimal scheduling scheme of the simulated annealing algorithm

[0111]

[0112] Figure 5A and Figure 5B respectively compare the production processes in the related art and the production process of the embodiment of the present disclosure. Assume that the received orders include Order A, Order B, and Order C in the foregoing embodiments, the order time of Order A is earlier than that of Order B, and the order time of Order B is earlier than that of Order C. For the sake of convenience of description, the number of food items of each category in each order is assumed to be 1.

[0113] As Figure 5A shown, in the related art, food items are produced by order granularity, and the production order of each food item is in turn: 1 fried chicken leg, 1 serving of French fries, 1 hamburger, 1 serving of French fries, 1 serving of orange juice, 1 serving of ice cream. That is to say, in the related art, the food items in the order placed earlier will be produced first. After all the food items of each category in an order are produced, the food items of each category in the next order will be produced. In the related art, each order will be displayed on the display screen in the back kitchen in the order of placement, and the chef will sequentially obtain the objects to be produced in the order and produce them according to the order arrangement.

[0114] As Figure 5BAs shown in the figure, the production sequence of each meal item is as follows: 1 fried chicken leg, 2 servings of French fries, 1 hamburger, 1 serving of orange juice, and 1 ice cream. That is to say, in the embodiments of the present disclosure, production is not carried out at the order granularity, but at the meal item granularity. Meal items of each category can be displayed on the display screen in the back kitchen according to the production sequence in the optimized scheduling plan. The chef only needs to produce according to the production sequence of each meal item displayed on the display screen without caring about which order the meal item comes from.

[0115] See Figure 6 , the embodiments of the present disclosure also provide an object production scheduling device, and the device includes:

[0116] A first acquisition module 11, configured to acquire a plurality of orders, where each order in the plurality of orders includes at least one category of to-be-produced objects that have not been completed, and at least two orders include to-be-produced objects of the same category;

[0117] A second acquisition module 12, configured to acquire an initial scheduling plan for to-be-produced objects of each category in the plurality of orders; the initial scheduling plan is used to represent the production sequence of to-be-produced objects of each category in the plurality of orders;

[0118] An optimization module 13, configured to optimize the initial scheduling plan based on a preset optimization goal to obtain an optimized scheduling plan. The optimization goal is determined based on the total delayed delivery duration of the plurality of orders and the total production duration of to-be-produced objects of each category in the plurality of orders. The optimization includes combining the production of to-be-produced objects of the same category in at least two orders; the optimized scheduling plan includes a sorting plan for the to-be-produced objects.

[0119] In some embodiments, the functions or modules included in the device provided in the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0120] The embodiments of the present disclosure also provide a computer device, which at least includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the method described in any of the foregoing embodiments.

[0121] Figure 7 FIG. shows a more specific schematic diagram of the hardware structure of a computing device provided in the embodiments of the present disclosure. The device may include: a processor 21, a memory 22, an input / output interface 23, a communication interface 24, and a bus 25. Among them, the processor 21, the memory 22, the input / output interface 23, and the communication interface 24 are communicatively connected to each other inside the device through the bus 25.

[0122] The processor 21 can be implemented in the form of a general-purpose central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present disclosure. The processor 21 may further include a graphics card, and the graphics card may be an Nvidia titan X graphics card or a 1080Ti graphics card, etc.

[0123] The memory 22 can be implemented in the form of a read-only memory (ROM), a random access memory (RAM), a static storage device, a dynamic storage device, etc. The memory 22 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of the present disclosure through software or firmware, the relevant program codes are stored in the memory 22 and called and executed by the processor 21.

[0124] The input / output interface 23 is used to connect to an input / output module to implement information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0125] The communication interface 24 is used to connect to a communication module (not shown in the figure) to implement communication interaction between this device and other devices. Among them, the communication module can implement communication in a wired manner (such as USB, network cable, etc.) or in a wireless manner (such as mobile network, WIFI, Bluetooth, etc.).

[0126] The bus 25 includes a path for transmitting information between various components of the device (such as the processor 21, the memory 22, the input / output interface 23, and the communication interface 24).

[0127] It should be noted that although the above device only shows the processor 21, the memory 22, the input / output interface 23, the communication interface 24, and the bus 25, in the specific implementation process, the device may further include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary to implement the solutions of the embodiments of the present disclosure, and do not necessarily include all the components shown in the figure.

[0128] Embodiments of the present disclosure also provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method described in any of the foregoing embodiments is implemented.

[0129] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology for storing information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0130] From the description of the above embodiments, those skilled in the art can clearly understand that the embodiments of the present disclosure can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solutions of the embodiments of the present disclosure, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, magnetic disk, optical disc, etc., including several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present disclosure.

[0131] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by a computer device or entity, or by a product with certain functions. A typical implementation device is a computer, and the specific form of the computer can be a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email transceiver, game console, tablet computer, wearable device, or a combination of any several of these devices.

[0132] Each embodiment in the present disclosure is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the apparatus embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the description of the method embodiments. The apparatus embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separated. When implementing the solutions of the embodiments of the present disclosure, the functions of the modules can be implemented in the same or multiple software and / or hardware. It is also possible to select some or all of the modules according to actual needs to achieve the purpose of the solutions of this embodiment. A person of ordinary skill in the art can understand and implement it without creative efforts.

[0133] The above is only the specific implementation manner of the embodiments of the present disclosure. It should be noted that for those of ordinary skill in the art, without departing from the principles of the embodiments of the present disclosure, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the embodiments of the present disclosure.

Claims

1. An object production scheduling method, the method comprises: obtaining a plurality of orders, each order of the plurality of orders includes at least one category of objects to be produced that are not yet completed, and at least two orders include objects to be produced of the same category; obtaining an initial scheduling plan for the objects to be produced in each category in the plurality of orders; the initial scheduling plan is used to represent the production order of the objects to be produced in each category in the plurality of orders; optimizing the initial scheduling plan based on a preset optimization goal to obtain an optimized scheduling plan, the optimization goal is determined based on the total delayed delivery duration of the plurality of orders and the total production duration of the objects to be produced in each category in the plurality of orders, the optimization includes combining the production of the objects to be produced of the same category in at least two orders; the optimized scheduling plan includes a sorting plan for the objects to be produced.

2. The method according to claim 1, wherein the obtaining an initial scheduling plan for the objects to be produced in each category in the plurality of orders, comprises: obtaining the order entry sequence of the plurality of orders; sequentially sorting the objects to be produced in each category in the plurality of orders according to the order entry sequence of the plurality of orders to obtain the initial scheduling plan.

3. The method according to claim 1 or 2, wherein the optimizing the initial scheduling plan based on a preset optimization goal, comprises: adjusting the production order represented by the initial scheduling plan to obtain an adjusted production order; if the objects to be produced corresponding to adjacent positions in the adjusted production order belong to the same category, combining the production of the objects to be produced corresponding to the adjacent positions to obtain an optimized scheduling plan; if the optimized scheduling plan does not meet the preset iteration termination condition, determining the optimized scheduling plan as the initial scheduling plan, and returning to the step of adjusting the production order represented by the initial scheduling plan.

4. The method according to claim 3, wherein the adjusting the production order represented by the initial scheduling plan, comprises: adjusting the production order represented by the initial scheduling plan based on at least one of the following methods: randomly selecting two positions in the initial scheduling plan and reversing the positions between the two positions; randomly selecting two positions in the initial scheduling plan and swapping the two positions; randomly selecting one position in the initial scheduling plan and inserting the randomly selected position into a new position in the initial scheduling plan; randomly selecting one position in the initial scheduling plan and swapping the randomly selected position with its adjacent position.

5. The method according to claim 3, wherein the iteration termination condition includes at least one of the following: the number of iterations reaches a first threshold; the number of consecutive occurrences of the same target value corresponding to the optimization goal reaches a second threshold.

6. The method according to claim 1, wherein the optimization goal comprises: minimizing the total delayed delivery duration, and minimizing the sum of the total production durations.

7. The method according to claim 1, wherein the total deferred delivery duration is obtained by weighting the deferred delivery durations of the multiple orders respectively by using the weights corresponding to the multiple orders, and the weights corresponding to the multiple orders are determined based on the delivery priorities corresponding to the multiple orders respectively.

8. The method according to claim 7, wherein the delivery priority corresponding to the order is determined based on at least one of the following: whether the order is a VIP order; whether the order is an inserted order.

9. The method according to claim 7, wherein the deferred delivery duration of the order is determined based on the time difference between the latest delivery time of the order and the order completion time of the order estimated based on the optimized scheduling plan; wherein, the latest delivery time is determined based on the sum of the order placement time of the order and a preset duration; or the latest delivery time is determined based on the number of orders that have been received and not completed up to the order placement moment of the order.

10. The method according to claim 1, wherein the total production duration is determined based on the maximum value of the production durations of the production objects to be produced of each category, and the production duration of the production object to be produced is determined based on the number of producers of the production object to be produced.

11. The method according to claim 1, wherein the number of production objects to be produced of each category is greater than or equal to 1, and in the optimized scheduling plan, the production objects to be produced of the same category in the same order are combined for production.

12. An object production scheduling device, the device comprises: a first acquisition module, configured to acquire multiple orders, each order in the multiple orders includes at least one category of production object to be produced that has not been completed, and at least two orders include production objects to be produced of the same category; a second acquisition module, configured to acquire an initial scheduling plan for the production objects to be produced of each category in the multiple orders; the initial scheduling plan is used to represent the production order of the production objects to be produced of each category in the multiple orders; an optimization module, configured to optimize the initial scheduling plan based on a preset optimization goal to obtain an optimized scheduling plan, the optimization goal is determined based on the total deferred delivery duration of the multiple orders and the total production duration of the production objects to be produced of each category in the multiple orders, and the optimization includes combining the production objects to be produced of the same category in at least two orders for production; the optimized scheduling plan includes a sorting plan for the production objects to be produced.

13. A computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

14. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the method according to any one of claims 1 to 11 is implemented.

Images