Product production scheduling method and device, equipment and storage medium

Abstract

The invention provides a product scheduling method and device, equipment and a storage medium. The method comprises the following steps: obtaining production line configuration information, production change cost information between to-be-produced products and production demand information; based on the production line configuration information, the production change cost information and the production demand information, obtaining different level constraints of a to-be-produced product; obtaining a weight value of each constraint condition contained in each hierarchical constraint; determining a production scheduling scheme of the to-be-produced product through a planning engine according to each constraint condition and the weight value of each constraint condition; wherein the deduction score of the production scheduling scheme under each constraint condition meets a preset condition. According to the method, on the basis of the industrial internet platform, the reliability and the production scheduling efficiency of product production scheduling are improved, and the production efficiency is further improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a product scheduling method, device, equipment and storage medium. Background Art

[0002] With the development of science and technology and artificial intelligence, the management and operation mode of factories has undergone major changes. Lean and information-based production management modes have gradually replaced traditional business models. In addition, with the expansion of the scale of manufacturing production, the increase in equipment and the huge amount of processed raw materials, the reliability of production scheduling based on manual experience is insufficient, which affects production efficiency. Therefore, how to schedule products more intelligently has become a technical problem that technicians in this field need to solve urgently. Summary of the invention

[0003] The present application provides a product scheduling method, device, equipment and storage medium, which can improve the reliability and efficiency of scheduling, thereby improving product production efficiency.

[0004] In a first aspect, the present application provides a product scheduling method, comprising:

[0005] Obtain production line configuration information, changeover cost information between products to be produced, and production demand information;

[0006] Based on the production line configuration information, the production change cost information and the production demand information, different levels of constraints on the products to be produced are obtained;

[0007] Get the weight value of each constraint condition contained in each level constraint;

[0008] The planning engine determines the production schedule of the products to be produced according to each constraint condition and the weight value of each constraint condition; wherein the deduction score of the production schedule under each constraint condition meets the preset conditions.

[0009] In one embodiment, the different levels of constraints include at least hard constraints, medium constraints and soft constraints;

[0010] The hard constraints include at least one of the following: the production schedule of the product to be produced is not within the downtime of the production line, and the product to be produced is not in the product blacklist of the production line;

[0011] The constraints include at least one of the following: the production completion time of the product to be produced does not exceed the delivery time, the production line with the highest product capacity is selected first, and the total time consumption of each production line is less than a specified threshold;

[0012] The soft constraints include at least one of the following: minimum production change time and minimum number of production change times.

[0013] In one embodiment, obtaining the weight value of each constraint condition included in each level constraint includes:

[0014] Determine the deduction of each level of constraints when generating historical production scheduling plans, and obtain the constraint score groups corresponding to each level of constraints;

[0015] For each target level constraint, N groups of weight values ​​are randomly generated, and each group of weight values ​​is correspondingly multiplied by the score in the constraint score group corresponding to the target level constraint to obtain N groups of new constraint scores; wherein N is a natural number greater than 1;

[0016] Determine a new constraint score group belonging to positive samples among the N groups of new constraint scores by using a pre-trained single-classification model corresponding to the target level constraint;

[0017] The weight value of each constraint condition in the target level constraint is determined according to the weight value group used when generating each new constraint score group.

[0018] In one embodiment, the step of determining the deduction of each level of constraints when generating a historical production scheduling plan to obtain a constraint score group corresponding to each level of constraints includes:

[0019] Obtain historical production scheduling plans;

[0020] The historical production scheduling plan is input into the planning engine, and the planning engine is used to determine the deduction of each level of constraints when generating the historical production scheduling plan, and obtain the constraint score group corresponding to each level of constraints.

[0021] In one of the embodiments, before determining the new constraint score group belonging to the positive sample in the N groups of new constraint scores by using the pre-trained single classification model corresponding to the target level constraint, the method further includes:

[0022] The single-class model is trained using a constraint score group corresponding to the target level constraint.

[0023] In one embodiment, determining the weight value of each constraint condition in the target level constraint according to the weight value group used when generating each new constraint score group includes:

[0024] The weight values ​​corresponding to the same constraint condition in the weight value group used when generating each new constraint score group are averaged, and the obtained average value is determined as the target weight value of the corresponding constraint condition in the target level constraint.

[0025] In one embodiment, it also includes:

[0026] Visually display the production schedule of the product to be produced.

[0027] In a second aspect, the present application provides a product scheduling device, comprising:

[0028] An acquisition module is used to obtain production line configuration information, changeover cost information between products to be produced, and production demand information;

[0029] The acquisition module is further used to obtain different levels of constraints on the products to be produced based on the production line configuration information, the production change cost information and the production demand information;

[0030] The acquisition module is further used to obtain the weight value of each constraint condition contained in each level constraint;

[0031] The planning module is used to determine the production schedule of the products to be produced according to each constraint condition and the weight value of each constraint condition through the planning engine; wherein the deduction score of the production schedule under each constraint condition meets the preset conditions.

[0032] In a third aspect, the present application provides an electronic device comprising: a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the product scheduling method provided in the first aspect of the present application are implemented.

[0033] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the product scheduling method provided in the first aspect of the present application are implemented.

[0034] The technical solution provided in the present application obtains the different levels of constraints of the products to be produced and the weight values ​​of each constraint condition contained in each level of constraints, and determines the production scheduling plan for the products to be produced according to each constraint condition and the weight value of each constraint condition through a planning engine. Compared with manual scheduling, this can improve the reliability and efficiency of product scheduling, thereby improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A schematic diagram of a process flow of a product scheduling method provided in an embodiment of the present application;

[0036] Figure 2 A schematic diagram of a process for obtaining weight values ​​of constraint conditions provided in an embodiment of the present application;

[0037] Figure 3 A schematic diagram of the structure of a product scheduling device provided in an embodiment of the present application;

[0038] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of this application more clear, the technical solution in this application is further described in detail through the following embodiments and in combination with the accompanying drawings. It should be understood that the specific embodiments described here are only used to explain this application and are not used to limit this application.

[0040] The product scheduling method provided in the embodiment of the present application can be applied to one or more electronic devices. The electronic device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. Optionally, the electronic device can be a portable electronic device (such as a mobile phone, a tablet computer), a desktop computer, a server, etc.

[0041] Figure 1 A flow chart of a product scheduling method provided in an embodiment of the present application. Figure 1 As shown, the method may include:

[0042] S101, obtaining production line configuration information, changeover cost information between products to be produced, and production demand information.

[0043] Among them, the production line configuration information is information related to the production line, which may include the maintenance start time, maintenance end time, downtime, production line capacity, product capacity and product blacklist of the production line. The above-mentioned production line capacity refers to the number of all products produced by the production line per hour, and the above-mentioned product capacity refers to the number of a certain product produced by the production line per hour. The above-mentioned product blacklist includes identification information of products that cannot be produced by the production line. In specific implementation, the production line capacity and product capacity of the production line can be counted based on the historical machine log data of the production line. When counting the production line capacity of the production line, there is no need to consider the production change time of the production line. When counting the product capacity of the production line, the production change time of the production line needs to be considered.

[0044] The products to be produced may include products and parts that the factory needs to produce, and the products to be produced are referred to as products hereinafter. The products may be various parts of household appliances or products of other equipment, which are not limited in the embodiments of the present application.

[0045] In actual applications, a production line can produce multiple products. When the production line switches between multiple products, it will generate production change cost information. Among them, the production change cost information may include the production change time and the number of production changes. In specific implementation, the production change time when each production line switches to different products can be counted based on the historical machine log data of the production line. For example, for production line 1, the production end time of product A and the production start time of product B are obtained from the historical log data. Using the production start time of product B and the production end time of product A, the production change time from product A to product B can be obtained.

[0046] The production demand information may include information such as product identification, product demand quantity, and product delivery time.

[0047] In some embodiments, the electronic device may provide a visual interface, in which corresponding controls are provided, through which the user may import the above-mentioned production line configuration information, production changeover cost information and production demand information into the electronic device, and the electronic device receives the production line configuration information, production changeover cost information and production demand information input by the user through the visual interface.

[0048] In other embodiments, the above-mentioned production line configuration information, production change cost information and production demand information may also be pre-stored in the memory, and the electronic device directly retrieves this information from the storage device.

[0049] S102: Obtain different levels of constraints on the products to be produced based on the production line configuration information, the production change cost information, and the production demand information.

[0050] If the electronic device receives the production line configuration information, the production change cost information and the production demand information from the visualization interface, it can generate different levels of constraints based on the production line configuration information, the production change cost information and the production demand information. For example, the production line configuration information, the production change cost information and the production demand information are assigned to the corresponding variables in the constraint conditions contained in each level of constraint, so as to facilitate the subsequent planning of the product scheduling plan.

[0051] Optionally, different levels of constraints include at least hard constraints, medium constraints and soft constraints, and the priority relationship between the three in the production scheduling execution process is: hard constraints> medium constraints> soft constraints, that is, hard constraints have the highest priority and soft constraints have the lowest priority. Hard constraints refer to constraints that must not be violated during the production scheduling execution process, medium constraints refer to constraints that can be violated but are violated as little as possible during the production scheduling execution process, and soft constraints refer to constraints that can be violated but are violated as little as possible during the production scheduling execution process. During the production scheduling execution process, the priority relationship between the three can be understood as first ensuring that hard constraints do not deduct points, secondly ensuring that medium constraints deduct points as little as possible, and thirdly ensuring that soft constraints deduct points as little as possible.

[0052] In actual applications, hard constraints, medium constraints, and soft constraints can be set based on business needs. Optionally, hard constraints include at least one of the following: 1) The production schedule of the product to be produced is not within the downtime of the production line; 2) The product to be produced is not in the product blacklist of the production line. Medium constraints include at least one of the following: 1) The production completion time of the product to be produced does not exceed the delivery time; 2) The production line with the highest product capacity is given priority; 3) The total time consumption of each production line is less than the specified threshold. Soft constraints include at least one of the following: 1) The production change time is minimal; 2) The number of production changes is minimal.

[0053] S103: Obtain the weight value of each constraint condition included in each level of constraints.

[0054] For each level constraint, you can also set corresponding weight values ​​for the multiple constraints contained in each level constraint based on business needs. The weight value can be set based on experience, or you can obtain the setting rules of each constraint from the historical scheduling plan. The weight value can reflect the importance level of each constraint. The more important the constraint is, the more points will be deducted when it is violated. Conversely, the smaller the weight value is, the less points will be deducted when it is violated. For example, taking the multiple constraints contained in the medium constraint as an example, if the weight value of constraint 1 is higher than constraint 2 and higher than constraint 3, that is, during the scheduling execution process, constraint 1 will be prioritized to ensure that it is met.

[0055] S104. Determine the production schedule for the products to be produced according to the constraints and the weights of the constraints through the planning engine.

[0056] Among them, the deduction scores of the production scheduling plan under each constraint condition meet the preset conditions.

[0057] The above-mentioned planning engine may be OptaPlanner, which uses meta-inspiration or taboo search algorithm to find a production scheduling scheme that satisfies preset conditions by deducting scores under each constraint condition according to the constraints in the above-mentioned different levels of constraints and the weight values ​​of each constraint condition, that is, to obtain which product is produced by which production line in which time period. The preset conditions may be that no deduction is made for hard constraints, and the deduction scores for medium constraints and soft constraints are the smallest.

[0058] Exemplarily, according to the above constraint rules, when scheduling products, if the product assigned to the production line is in the production line blacklist of the production line, the hard score corresponding to the hard constraint condition is deducted; if the production completion time of the product is less than the expected delivery date of the product, the medium score corresponding to the medium constraint condition is deducted, wherein the medium score can be the ratio between the production completion time of the product and the expected delivery date, and the product of the weight value corresponding to the medium constraint condition; if there is a production change time, the soft score corresponding to the soft constraint condition is deducted, wherein the soft score can be the product of the production change time of the product and the weight value corresponding to the soft constraint condition. By summing up the deduction scores and combining the meta-inspiration and taboo search algorithms, the production scheduling plan with the smallest deduction score is determined as the final production scheduling plan for the product.

[0059] When obtaining the production schedule of the products to be produced, the production schedule of the products to be produced can also be visualized to facilitate users to view and improve the intelligence of production scheduling. For example, the products to be produced by each production line and the production time of the products can be displayed in a graphical manner.

[0060] The product scheduling method provided in the embodiment of the present application obtains different levels of constraints on the products to be produced and the weight values ​​of each constraint condition contained in each level of constraints, and determines the scheduling plan for the products to be produced according to each constraint condition and the weight value of each constraint condition through a planning engine. Compared with manual scheduling, the reliability and scheduling efficiency of product scheduling can be improved, thereby improving production efficiency.

[0061] In one embodiment, the weight value setting rules of each constraint condition contained in each level constraint can also be obtained based on the historical order scheduling plan. Based on this, on the basis of the above embodiment, optionally, as Figure 2 As shown, the above S103 may include:

[0062] S201. Determine the deduction of each level of constraints when generating a historical production scheduling plan, and obtain a constraint score group corresponding to each level of constraints.

[0063] The historical production schedule includes the production line and production time assigned to the product in the specified historical time period, as well as the production line configuration information, production change cost information, and production demand information in the specified historical time period. Specifically, the deduction of each level of constraints when generating the historical production schedule can be inferred from the historical production schedule to obtain the constraint score group corresponding to each level of constraints, such as a group of constraint scores corresponding to hard constraints, a group of constraint scores corresponding to medium constraints, and a group of constraint scores corresponding to soft constraints.

[0064] Optionally, the above S201 process can be: obtaining historical production scheduling plans, inputting the historical production scheduling plans into the planning engine, determining the deduction of each level of constraints when generating the historical production scheduling plans through the planning engine, and obtaining the constraint score group corresponding to each level of constraints.

[0065] Specifically, the historical production schedule is input into the planning engine, which infers the historical production schedule. During this calculation process, the planning engine does not add weights to the constraints contained in each level of constraints, but only uses the deduction points corresponding to each constraint to perform optimal calculations. After the planning engine runs, the constraint score groups corresponding to each level of constraints are recorded.

[0066] S202. For each target level constraint, randomly generate N groups of weight values, and multiply each group of weight values ​​by the score in the constraint score group corresponding to the target level constraint to obtain N groups of new constraint scores.

[0067] Wherein, N is a natural number greater than 1.

[0068] For example, if the soft constraint contains 10 constraints, then the constraint score group corresponding to the soft constraint contains 10 scores, and N groups of weight values ​​are randomly generated, each group of weight values ​​contains 10 weight values, and these 10 weight values ​​correspond to the 10 constraints in the soft constraint one by one; then, each group of weight values ​​is multiplied by the scores corresponding to the 10 constraints in the constraint score group, so as to obtain N groups of new constraint scores. Among them, each group of new constraint scores also includes 10 scores.

[0069] S203. Determine a new constraint score group belonging to positive samples among the N groups of new constraint scores through a pre-trained single-classification model corresponding to the target level constraint.

[0070] Among them, the single classification model can predict whether a group of data is positive sample data. Continuing with the example in S202 above, 10 groups of new constraint scores are input into the single classification model, and the single classification model is used to predict whether the 10 groups of new constraint scores are positive sample data, the new constraint score group of the positive sample is retained, the new constraint score group of the negative sample is deleted, and the new constraint score group belonging to the positive sample data is extracted from the 10 groups of new constraint scores based on the prediction results.

[0071] Optionally, before the above S203, the single classification model can also be trained using the constraint score group corresponding to the target level constraint. The single classification model can be a support vector data description (SVDD) model, a support vector machine, a single class neural network or an isolation forest, etc., which is not limited in this embodiment.

[0072] S204: Determine the weight value of each constraint condition in the target level constraint according to the weight value group used when generating each new constraint score group.

[0073] In one embodiment, optionally, the above S204 process can be: averaging the weight values ​​corresponding to the same constraint condition in the weight value group used when generating each new constraint score group, and determining the obtained average value as the target weight value of the corresponding constraint condition in the target level constraint.

[0074] Exemplarily, taking constraint 1 in the soft constraint as an example, assuming that the 1st to 5th groups of new constraint scores are new constraint score groups of positive samples, the weight values ​​corresponding to constraint 1 in the 1st to 5th groups of new constraint score groups can be averaged, and the obtained average value is determined as the target weight value of constraint 1 in the soft constraint. For the target weight values ​​of the remaining 9 constraints in the soft constraint, they can be calculated by referring to the target weight value acquisition process of constraint 1, which will not be repeated in this embodiment.

[0075] Of course, in some other embodiments, the weight values ​​corresponding to the same constraint condition in the weight value group used when generating each new constraint score group may be median-operated, and the obtained median may be used to determine the target weight value of the corresponding constraint condition in the target level constraint.

[0076] In this embodiment, a single classification model is used to obtain the weight setting rules of each constraint condition in the product scheduling process from historical scheduling plans, guide the weight setting of each constraint condition in the subsequent scheduling process, and realize adaptive adjustment of the weight value of the constraint condition, which is more adapted to the actual production situation of the factory, further improving the intelligence and reliability of scheduling.

[0077] Figure 3 A schematic diagram of the structure of a product scheduling device provided in an embodiment of the present application. Figure 3 As shown, the device may include: an acquisition module 301 and a planning module 302.

[0078] Specifically, the acquisition module 301 is used to acquire production line configuration information, production change cost information between products to be produced, and production demand information;

[0079] The acquisition module 301 is also used to obtain different levels of constraints on the products to be produced based on the production line configuration information, the production change cost information and the production demand information;

[0080] The acquisition module 301 is also used to obtain the weight value of each constraint condition included in each level constraint;

[0081] The planning module 302 is used to determine the production schedule of the products to be produced according to each constraint condition and the weight value of each constraint condition through the planning engine; wherein the deduction score of the production schedule under each constraint condition meets the preset conditions.

[0082] In one of the embodiments, optionally, the different levels of constraints include at least hard constraints, medium constraints and soft constraints;

[0083] The hard constraints include at least one of the following: the production schedule of the product to be produced is not within the downtime of the production line, and the product to be produced is not in the product blacklist of the production line;

[0084] The constraints include at least one of the following: the production completion time of the product to be produced does not exceed the delivery time, the production line with the highest product capacity is selected first, and the total time consumption of each production line is less than a specified threshold;

[0085] The soft constraints include at least one of the following: minimum production change time and minimum number of production change times.

[0086] In one of the embodiments, optionally, the acquisition module 301 is specifically used to determine the deduction of each level of constraints when generating a historical production schedule, and obtain a constraint score group corresponding to each level of constraints; for each target level constraint, randomly generate N groups of weight values, and multiply each group of weight values ​​by the score in the constraint score group corresponding to the target level constraint, to obtain N groups of new constraint scores; wherein, N is a natural number greater than 1; determine the new constraint score group belonging to the positive sample in the N groups of new constraint scores through the pre-trained single classification model corresponding to the target level constraint; and determine the weight value of each constraint condition in the target level constraint according to the weight value group used when generating each new constraint score group.

[0087] In one of the embodiments, optionally, the acquisition module 301 is also specifically used to obtain historical production scheduling plans; input the historical production scheduling plans into the planning engine, and determine the deduction of each level of constraints when generating the historical production scheduling plans through the planning engine to obtain the constraint score group corresponding to each level of constraints.

[0088] In one of the embodiments, optionally, the acquisition module 301 is further specifically used to train the single classification model using the constraint score group corresponding to the target level constraint before determining the new constraint score group belonging to the positive samples in the N groups of new constraint scores through the single classification model corresponding to the pre-trained target level constraint.

[0089] In one of the embodiments, optionally, the acquisition module 301 is also specifically used to average the weight values ​​corresponding to the same constraint condition in the weight value group used when generating each new constraint score group, and determine the obtained average value as the target weight value of the corresponding constraint condition in the target level constraint.

[0090] In one of the embodiments, optionally, the device further includes: a display module.

[0091] Specifically, the display module is used to visually display the production schedule of the product to be produced.

[0092] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 4 As shown, the electronic device includes a processor 40, a memory 41, an input device 42 and an output device 43; the number of the processor 40 in the electronic device can be one or more. Figure 4 A processor 40 is taken as an example; the processor 40, the memory 41, the input device 42 and the output device 43 in the electronic device can be connected by a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0093] The memory 41 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the product scheduling method in the embodiment of the present application (for example, the acquisition module 301 and the planning module 302 in the product scheduling device). The processor 40 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 41, that is, realizing the above-mentioned product scheduling method.

[0094] The memory 41 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created during product scheduling, etc. In addition, the memory 41 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 41 may further include a memory remotely arranged relative to the processor 40, and these remote memories may be connected to the device / terminal / server via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0095] The input device 42 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the electronic device. The output device 43 may include a display device such as a display screen.

[0096] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0097] Obtain production line configuration information, changeover cost information between products to be produced, and production demand information;

[0098] Based on the production line configuration information, the production change cost information and the production demand information, different levels of constraints on the products to be produced are obtained;

[0099] Get the weight value of each constraint condition contained in each level constraint;

[0100] The planning engine determines the production schedule of the products to be produced according to each constraint condition and the weight value of each constraint condition; wherein the deduction score of the production schedule under each constraint condition meets the preset conditions.

[0101] The product scheduling device, electronic device, and storage medium provided in the above embodiments can execute the product scheduling method provided in any of the above embodiments, and have the corresponding functional modules and beneficial effects of executing the method. For technical details not described in detail in the above embodiments, please refer to the product scheduling method provided in any of the above embodiments.

[0102] Through the above description of the implementation method, the technicians in the relevant field can clearly understand that the present application can be implemented with the help of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0103] It is worth noting that in the embodiment of the above-mentioned search device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application.

[0104] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0105] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A product scheduling method, characterized in that: include: Obtain production line configuration information, changeover cost information between products to be produced, and production demand information; Based on the production line configuration information, the production change cost information and the production demand information, different levels of constraints on the products to be produced are obtained; Get the weight value of each constraint condition contained in each level constraint; The planning engine determines the production schedule of the products to be produced according to each constraint condition and the weight value of each constraint condition; wherein the deduction score of the production schedule under each constraint condition meets the preset conditions.

2. The method according to claim 1, characterized in that The different levels of constraints include at least hard constraints, medium constraints and soft constraints; The hard constraints include at least one of the following: the production schedule of the product to be produced is not within the downtime of the production line, and the product to be produced is not in the product blacklist of the production line; The constraints include at least one of the following: the production completion time of the product to be produced does not exceed the delivery time, the production line with the highest product capacity is selected first, and the total time consumption of each production line is less than a specified threshold; The soft constraints include at least one of the following: minimum production change time and minimum number of production change times.

3. The method according to claim 1, characterized in that The step of obtaining the weight value of each constraint condition contained in each level of constraint includes: Determine the deduction of each level of constraints when generating historical production scheduling plans, and obtain the constraint score groups corresponding to each level of constraints; For each target level constraint, N groups of weight values ​​are randomly generated, and each group of weight values ​​is correspondingly multiplied by the score in the constraint score group corresponding to the target level constraint to obtain N groups of new constraint scores; wherein N is a natural number greater than 1; Determine a new constraint score group belonging to positive samples among the N groups of new constraint scores by using a pre-trained single-classification model corresponding to the target level constraint; The weight value of each constraint condition in the target level constraint is determined according to the weight value group used when generating each new constraint score group.

4. The method according to claim 3, characterized in that The step of determining the deduction of each level of constraints when generating a historical production scheduling plan, and obtaining a constraint score group corresponding to each level of constraints, includes: Obtain historical production scheduling plans; The historical production scheduling plan is input into the planning engine, and the planning engine is used to determine the deduction of each level of constraints when generating the historical production scheduling plan, and obtain the constraint score group corresponding to each level of constraints.

5. The method according to claim 3, characterized in that: Before determining the new constraint score group belonging to the positive samples in the N groups of new constraint scores by using the pre-trained single classification model corresponding to the target level constraint, the method further includes: The single-class model is trained using a constraint score group corresponding to the target level constraint.

6. The method according to claim 3, characterized in that Determining the weight value of each constraint condition in the target level constraint according to the weight value group used when generating each new constraint score group includes: The weight values ​​corresponding to the same constraint condition in the weight value group used when generating each new constraint score group are averaged, and the obtained average value is determined as the target weight value of the corresponding constraint condition in the target level constraint.

7. The method according to any one of claims 1 to 6, characterized in that Also includes: Visually display the production schedule of the product to be produced.

8. A product scheduling device, characterized in that: include: An acquisition module is used to obtain production line configuration information, changeover cost information between products to be produced, and production demand information; The acquisition module is further used to obtain different levels of constraints on the products to be produced based on the production line configuration information, the production change cost information and the production demand information; The acquisition module is further used to obtain the weight value of each constraint condition contained in each level constraint; The planning module is used to determine the production schedule of the products to be produced according to various constraints and the weight values ​​of each constraint through the planning engine; wherein the deduction score of the production schedule under each constraint meets the preset conditions.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images