A profile production scheduling method, device, electronic equipment and storage medium

Abstract

The present invention discloses a method, device, electronic device and storage medium for scheduling production of profiles. The method includes: obtaining initial production environment information and external production information, and updating the initial production environment information according to the external production information to obtain online production environment information; analyzing the online production environment information to obtain environmental characteristics of the online production environment information; inputting the environmental characteristics into the online production scheduling model to obtain a scheduling strategy corresponding to the online production environment information; and executing the scheduling strategy based on the online production environment information to generate a production scheduling plan. That is, in an embodiment of the present invention, environmental characteristics are obtained by analyzing the online production environment information, a scheduling strategy corresponding to the online production environment information is obtained based on the environmental characteristics and the online production scheduling model, and a production scheduling plan is scheduled according to the scheduling strategy, so as to realize intelligent scheduling of production tasks, improve production efficiency, shorten production time, and reduce production scheduling costs.

Description

Technical Field

[0001] The embodiments of the present invention relate to computer technology, and in particular to a profile production scheduling method, device, electronic equipment and storage medium. Background Art

[0002] With the increasing personalization of profile factory production plans and the increasing uncertainty of market demand, the core competitiveness of the factory is no longer just the actual capacity and inventory of manufacturing resources, but also requires adjustments to the dynamic changes in production progress to optimize and monitor production scheduling during the manufacturing process. Traditional manual scheduling methods can no longer meet the needs, so solvers and genetic algorithms are used to solve production scheduling problems, but they have problems such as long calculation cycles, untimely delivery, high costs, and time-consuming production task switching. With the continuous development of artificial intelligence technology, how to face the situation where profile factories have many production links, complex collaborative relationships, strong production continuity, and fast changes in production conditions, and adopt corresponding production scheduling plans according to different situations. Summary of the invention

[0003] The present invention provides a profile production scheduling method, device, electronic equipment and storage medium to realize intelligent production scheduling of production tasks, improve production efficiency, shorten production time and reduce production scheduling costs.

[0004] In a first aspect, an embodiment of the present invention provides a profile production scheduling method, the method comprising:

[0005] Acquire initial production environment information and external production information, and update the initial production environment information according to the external production information to obtain online production environment information;

[0006] Analyze the online production environment information to obtain environmental characteristics of the online production environment information;

[0007] Inputting the environmental characteristics into an online production scheduling model to obtain a scheduling strategy corresponding to the online production environment information;

[0008] The scheduling strategy is executed based on the online production environment information to generate a production scheduling plan.

[0009] Furthermore, the online production scheduling model is obtained in the following manner:

[0010] Acquire a training data set according to the initial production environment information;

[0011] Inputting the training data set into a training network to obtain a scheduling strategy for each environmental feature in the training data set;

[0012] Based on the initial production environment information, the scheduling strategies of the environmental characteristics are respectively executed to obtain the reward values ​​of the scheduling strategies of the environmental characteristics;

[0013] The online production scheduling model is determined according to the reward value of the scheduling strategy of each environmental feature.

[0014] Further, the scheduling strategies of the environmental characteristics are respectively executed based on the initial production environment information to obtain the reward values ​​of the scheduling strategies of the environmental characteristics, including:

[0015] Based on the initial production environment information, the environmental characteristics and the scheduling strategies of the environmental characteristics, a production plan corresponding to each scheduling strategy is generated, and the production plan corresponding to each scheduling strategy is respectively executed to obtain the production execution environment information corresponding to each scheduling strategy;

[0016] The production initial environment information is compared with the production execution environment information corresponding to each scheduling strategy to determine the reward value of the scheduling strategy of each environmental feature.

[0017] Furthermore, the production initial environment information is compared with the production execution environment information to determine the reward value of the scheduling strategy of each environment feature, including:

[0018] Determine the initial environment characteristics of the production initial environment information and the execution environment characteristics of each production execution environment information, and respectively determine the change value between the initial characteristics and each execution environment characteristic;

[0019] The reward value of the scheduling strategy for each of the environmental characteristics is determined according to the change value between the initial characteristics and the characteristics of each of the execution environments and a preset reward rule.

[0020] Furthermore, the online production scheduling model is determined according to the reward value of each environmental feature scheduling strategy, including:

[0021] Accumulating the reward values ​​of the environmental features to obtain the total reward value of the training data set;

[0022] Determining whether the total reward value is greater than a preset reward threshold;

[0023] When the total reward value is greater than a preset reward threshold, the training parameters corresponding to the training data set are updated to the training network to obtain the online production scheduling model.

[0024] Further, after determining whether the total reward value is greater than a preset reward threshold, the method further includes:

[0025] When the total reward value is less than a preset reward threshold, searching for new training data corresponding to the production initial environment information, and updating the new training data into the training data set to obtain a new training data set;

[0026] The training network is trained according to the new training data set until the total reward value of the new training data set is greater than the preset reward threshold, thereby obtaining the online production scheduling model.

[0027] Further, the online production environment information is analyzed to obtain the environmental characteristics of the online production environment information, including:

[0028] Acquire the indicator types of the online production environment information, wherein the indicator types include utilization rate, delivery rate and mold conversion rate;

[0029] The online production environment information is statistically analyzed according to the indicator type to obtain environmental characteristics of the online production environment information.

[0030] In a second aspect, an embodiment of the present invention further provides a profile production scheduling device, the device comprising:

[0031] An information acquisition module is used to acquire initial production environment information and external production information, and update the initial production environment information according to the external production information to obtain online production environment information;

[0032] A feature analysis module, used to analyze the online production environment information to obtain environmental features of the online production environment information;

[0033] A strategy determination module, used to input the environmental characteristics into an online production scheduling model to obtain a scheduling strategy corresponding to the online production environment information;

[0034] A strategy execution module is used to execute the scheduling strategy based on the online production environment information to generate a production scheduling plan.

[0035] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0036] one or more processors;

[0037] a storage device for storing one or more programs,

[0038] When the one or more programs are executed by the one or more processors, the one or more processors implement the profile production scheduling method.

[0039] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the profile production scheduling method as described in any one of claims 1 to 7.

[0040] In the embodiment of the present invention, the online production environment information is obtained by obtaining the initial production environment information and the external production information, and the initial production environment information is updated according to the external production information; the online production environment information is analyzed to obtain the environmental characteristics of the online production environment information; the environmental characteristics are input into the online production scheduling model to obtain the scheduling strategy corresponding to the online production environment information; the scheduling strategy is executed based on the online production environment information to generate a production scheduling plan. That is, in the embodiment of the present invention, real-time online production environment information is obtained by updating the production environment information; the environmental characteristics are obtained by analyzing the online production environment information, and the scheduling strategy corresponding to the online production environment information can be obtained based on the indicators according to the environmental characteristics and the online production scheduling model, and the production tasks can be intelligently scheduled, so as to improve production efficiency, shorten production time, and reduce production scheduling costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flow chart of a profile production scheduling method provided by an embodiment of the present invention;

[0042] Figure 2 It is a flow chart of online production scheduling model training in the profile production scheduling method provided by an embodiment of the present invention;

[0043] Figure 3 It is a schematic diagram of the principle of determining the reward value of the scheduling strategy of each environmental feature in the profile production scheduling method provided by an embodiment of the present invention;

[0044] Figure 4 is another flow chart of the profile production scheduling method provided by an embodiment of the present invention;

[0045] Figure 5 It is a structural schematic diagram of a profile production scheduling device provided by an embodiment of the present invention;

[0046] Figure 6 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0048] Figure 1 A flow chart of a profile production scheduling method provided in an embodiment of the present invention is provided. The method can be executed by a profile production scheduling device provided in an embodiment of the present invention. The device can be implemented in software and / or hardware. In a specific embodiment, the device can be integrated in an electronic device, such as a server. The following embodiments will be described by taking the device integrated in an electronic device as an example. Figure 1 , the method may specifically include the following steps:

[0049] S110, obtaining initial production environment information and external production information, and updating the initial production environment information according to the external production information to obtain online production environment information;

[0050] For example, the initial production environment information may be the initial production plan, molds, equipment, materials, finished product information, and environmental interface for the enterprise factory to carry out production quantitative information, wherein the initial production plan may be production information such as production batches, product quantity, startup sequence of running equipment, and order completion time of different orders determined according to each order and product quantity, such as: how many batches are 10 orders completed, the orders corresponding to each batch, the number of products produced in each batch, the number of molds prepared for each batch, the type of molds for each batch, the production line started for each batch, the production time corresponding to each batch, the order completion time, the number of equipment and the operating status, and the inventory information of materials and finished products; the mold may be a solid model of the profile that needs to be provided on the production line of different products; the equipment may be the factory equipment or production line machinery that needs to be started to produce different products; the material may be the raw materials used by the factory to produce different products; the finished product information may be the appearance design information and functions of different products produced by the factory, such as: when the profile is a steel bar, the appearance design information may be the cross-sectional area, length, and density of the steel bar; the product function may be the load-bearing capacity per unit length and the unit area that can be reinforced; the environmental interface may be the process interface used to monitor the production process and the electronic device that can view the process interface. The external production information may be the production environment information generated based on the unentered production orders, production failures of factory equipment and order changes. The online production environment information may be the production environment information after the initial production environment information is updated based on the production environment information corresponding to the external production information.

[0051] In the specific implementation, the initial production environment information of the enterprise factory is obtained through the initial production plan, mold, equipment, material, finished product information and production quantity information corresponding to the environment configuration surface entered by the factory, and the external production information of the enterprise factory is obtained at the same time, and the initial production environment information is updated through the production orders, production failures of factory equipment and order changes that are not entered in the external production information, and the online production environment information is obtained, that is, the production orders, production failures of factory equipment and order changes that are not entered in the external production information are entered into the initial production environment information, and the input information of the enterprise factory is updated, so as to formulate the best production efficiency according to the online production ring tightening information. Among them, updating the input information of the enterprise factory can be to add production orders in the initial production environment information, for example, to enter the production orders that have not been entered, or to determine the maintenance time for the production failure of the factory equipment and adjust the production batch, order completion time and mold preparation time of the order corresponding to the failure, or to delete the production quantity in the initial production environment information according to the order changes, adjust the orders of different batches, delete the order quantity, etc.

[0052] S120, analyzing the online production environment information to obtain the environmental characteristics of the online production environment information;

[0053] In a specific implementation, the environmental characteristics of the online production environment information may be the corresponding indicator value of the online production environment information determined according to the indicator type corresponding to the online production environment information, wherein the indicator type corresponding to the online production environment information may be the quantitative indicator of the production information of the online production environment information during the operation process, and may be the utilization rate of the enterprise factory equipment, the order delivery rate, and the mold change rate, etc. during the operation of the online production environment information. According to the indicator type corresponding to the online production environment information, the production information in the running online production environment information is statistically analyzed to obtain the environmental characteristics of the online production environment information. For example: there are a total of 10 production equipment in the enterprise factory in the running online production environment information, and the total number of production equipment used in each batch is accumulated to obtain the total number of production equipment used in the online production environment information, and the total number of production equipment used is divided by the number of production equipment in the enterprise factory and the number of batches to obtain the total number of available equipment to obtain the corresponding equipment utilization rate. Among them, the order delivery rate can be determined based on the probability of not exceeding the completion time specified in the order contract according to the completion time of the order in the online production environment information. It can be the ratio of the number of orders that do not exceed the completion time specified in the order contract and the total number of orders in the online production environment information, and the delivery rate of the orders in the online production environment information is calculated; the mold change rate can be the probability of mold replacement between different batches, which is used to determine the mold utilization rate in the online production environment information. Among them, the lower the mold change rate, the higher the timeliness of production and the faster the efficiency. It can be calculated based on the number of batches in the online environment information and the number of mold changes in the online environment information.

[0054] S130, inputting the environmental characteristics into the online production scheduling model to obtain a scheduling strategy corresponding to the online production environment information;

[0055] In a specific implementation, environmental characteristics can be input into an online production scheduling model, and the output of the online production scheduling model can be a scheduling strategy for the online production environment information. A production plan corresponding to the online production environment information can be formulated based on the scheduling strategy for the online production environment information, and the index value corresponding to the online production environment information can be optimized. For example: the optimization of the index value corresponding to the online production environment information can be determined based on the reward rules set corresponding to the environmental characteristics of the production environment information in the training data set during the training of the online production scheduling model. In addition, the online production scheduling model can be a deep neural network model, and the online production scheduling model can be pre-trained. The scheduling strategy corresponding to the online production environment information can be an adjustment rule or adjustment basis for adjusting the production plan corresponding to the online production environment information, wherein the adjustment strategy can come from a pre-set adjustment strategy library, wherein the adjustment strategy library can be an adjustment rule for adjusting the production plan in advance according to the indicator type in the online production environment information.

[0056] For example: when the indicator types corresponding to the online production environment information are delivery rate, equipment utilization rate and mold conversion rate, the adjustment strategies in the adjustment strategy library can be pre-set as the following 11 items: 1. You can select the non-timed order that is farthest from the delivery deadline or the order with the largest estimated timeout, and select the equipment and mold corresponding to the smallest completion time point; 2. You can select the non-timed order that is farthest from the delivery deadline or the order with the largest estimated timeout, and select the equipment and mold corresponding to the largest completion time point; 3. You can select the non-timed order that is closest to the delivery deadline or the order with the smallest estimated timeout, and select the equipment and mold corresponding to the smallest completion time point; 4. You can select the non-timed order that is closest to the delivery deadline or the order with the smallest estimated timeout, and select the equipment and mold corresponding to the largest completion time point; 5. Select the non-timed order or the estimated timeout with the smallest remaining time / execution time (the least estimated free time). 1. For the largest order, select the machine and mold with the smallest order completion time; 2. Select the unfinished order with the longest estimated timeout, and choose the machine and mold with the smallest utilization rate with a half probability, and choose the machine and mold with the shortest total execution time with a half probability; 3. Randomly select an unfinished order and take the candidate machine and mold with the shortest execution time; 4. Select the order with the closest delivery time or the longest possible delay, and take the candidate machine with the shortest execution time; 5. Select the order with the longest estimated timeout and the farthest delivery deadline, and select the equipment and mold with the least mold change times; 6. Select the unfinished order with the longest estimated timeout and the smallest remaining time / execution time (the least estimated free time), and select the equipment and mold with the least mold change times; 7. Select the order with the closest delivery time or the longest possible delay, and select the equipment and mold with the least mold change times.

[0057] S140. Execute a scheduling strategy based on the online production environment information to generate a production scheduling plan.

[0058] In a specific implementation, the production scheduling plan can be a production plan obtained by adjusting the production plan in the online production environment information according to the adjustment strategy. For example, the scheduling strategy based on the online production environment information can be to select the non-timed order farthest from the delivery deadline or the order with the largest estimated timeout, and select the equipment and mold corresponding to the smallest completion time point. The non-timed orders in the online production environment information can be rearranged from far to near in time, and the equipment model with the smallest completion time corresponding to each non-timed order can be determined and executed in the order of the non-timed orders.

[0059] In the embodiment of the present invention, the online production environment information is obtained by obtaining the initial production environment information and the external production information, and the initial production environment information is updated according to the external production information; the online production environment information is analyzed to obtain the environmental characteristics of the online production environment information; the environmental characteristics are input into the online production scheduling model to obtain the scheduling strategy corresponding to the online production environment information; the scheduling strategy is executed based on the online production environment information to generate a production scheduling plan. That is, in the embodiment of the present invention, real-time online production environment information is obtained by updating the production environment information; the environmental characteristics are obtained by analyzing the online production environment information, and the scheduling strategy corresponding to the online production environment information can be obtained based on the indicators according to the environmental characteristics and the online production scheduling model, and the production tasks can be intelligently scheduled, so as to improve production efficiency, shorten production time, and reduce production scheduling costs.

[0060] The following further describes the training process of the online production scheduling model in the profile production scheduling method provided by the embodiment of the present invention. Figure 2 As shown, the method may specifically include the following steps:

[0061] S210, obtaining a training data set according to the initial production environment information;

[0062] In a specific implementation, the training data set may be data for training the training network, and may be a data set for training parameters in the training network determined based on the initial production environment information, customer needs, and the production needs of the enterprise factory, wherein the training data set includes various environmental features of the initial production environment information and the scheduling strategies corresponding to the various environmental features. Among them, the scheduling strategies in the initial production environment information belong to the preset scheduling strategy library. The training data set is determined based on the initial production environment information, customer needs, and the production needs of the enterprise factory, so as to determine the corresponding weights for the indicator types corresponding to the initial production environment information based on the customer needs and the production needs of the enterprise factory, and then calculate the reward values ​​of each scheduling strategy.

[0063] S220, inputting the training data set into the training network to obtain a scheduling strategy for each environmental feature in the training data set;

[0064] In a specific implementation, the training network can be a neural network constructed by multiple deep learning neural network modules, and parameter training can be performed through the training data set to obtain an online production scheduling model. The scheduling strategy for each environmental feature in the training data set can be obtained by interacting the environmental features of each initial production environment information with the preset scheduling strategy library to obtain a scheduling strategy corresponding to each environmental feature, or by randomly assigning scheduling strategies to each environmental feature during the training process of the training network, or by matching each environmental feature with all strategies in the preset scheduling strategy library during the training process of the training network to determine the scheduling strategy corresponding to the maximum reward value of the scheduling strategy as the scheduling strategy corresponding to each environmental feature.

[0065] In an embodiment of the present invention, the environmental characteristics of each initial production environment information in the training data set can be interactively associated with the preset scheduling strategy library, so that each environmental characteristic has a one-to-one correspondence with the preset scheduling strategy library, and the training data in the training data set is obtained. The training data is input into the training network to train the training network, and a scheduling model corresponding to the training network is obtained. Each environmental characteristic in the training data is input into the scheduling model in turn to obtain a scheduling strategy for each environmental characteristic in the training data set. Among them, the scheduling model can be a model after the training network is trained with the training data in the training data set, but it has not been converged to determine whether it meets the production scheduling needs of the enterprise factory.

[0066] S230, executing the scheduling strategies of each environmental feature respectively based on the initial production environment information, and obtaining the reward value of the scheduling strategy of each environmental feature;

[0067] In a specific implementation, the scheduling strategies of each environmental feature are executed in turn in the initial production environment, that is, the production plan corresponding to each scheduling strategy is generated based on the initial production environment information, each environmental feature and the scheduling strategy of each environmental feature, and the production execution environment information corresponding to each scheduling strategy is determined according to the production plan corresponding to each scheduling strategy. The reward value of the scheduling strategy of each environmental feature is determined using the initial production environment information and the production execution environment information corresponding to each scheduling strategy. Among them, the reward value of the scheduling strategy of each environmental feature can be determined by comparing the environmental features corresponding to each indicator type of the initial production environment information with the environmental features corresponding to each indicator type of the production execution environment information.

[0068] Furthermore, the scheduling strategies of each environmental feature are respectively executed based on the initial production environment information to obtain the reward value of the scheduling strategy of each environmental feature, including:

[0069] Based on the initial production environment information, each environment feature and the scheduling strategy of each environment feature, a production plan corresponding to each scheduling strategy is generated, and the production plan corresponding to each scheduling strategy is executed respectively to obtain the production execution environment information corresponding to each scheduling strategy;

[0070] The initial production environment information is compared with the production execution environment information corresponding to each scheduling strategy to determine the reward value of the scheduling strategy for each environmental feature.

[0071] In a specific implementation, the production plan corresponding to each scheduling strategy can be a production plan generated by each scheduling strategy using the initial production environment information, and the production plan is updated in the initial production environment information to obtain the production execution environment information corresponding to each scheduling strategy. The production plan corresponding to each scheduling strategy is generated based on the initial production environment information, each environmental feature, and the scheduling strategy of each environmental feature, and the production plan corresponding to each scheduling strategy is executed based on the initial production environment information, and the production plan corresponding to each scheduling strategy is updated in the initial production environment information to obtain the production execution environment information corresponding to each scheduling strategy. The environmental features corresponding to each indicator type of the initial production environment information and the environmental features corresponding to each indicator type of the production execution environment information are compared to determine the reward value of the scheduling strategy of each environmental feature.

[0072] Furthermore, the initial production environment information is compared with the production execution environment information to determine the reward value of the scheduling strategy for each environmental feature, including:

[0073] Determine the initial environment characteristics of the production initial environment information and the execution environment characteristics of each production execution environment information, and respectively determine the change value between the initial characteristics and each execution environment characteristic;

[0074] The reward value of the scheduling strategy for each environment feature is determined according to the change value between the initial feature and each execution environment feature and the preset reward rule.

[0075] For example, the preset reward rule may be a rule for the change between the initial production environment information and each production execution environment information determined according to the initial production environment information, customer demand, and the production demand of the enterprise factory, and used to determine the change value between the initial production environment information and each production execution environment information. The calculation of the change value between the initial production environment information and each production execution environment information actually compares the initial environment characteristics of the initial production environment information with the execution environment characteristics of each production execution environment information, and determines the change value between the initial characteristics and each execution environment characteristic.

[0076] In a specific implementation, the initial environment characteristics of the initial environment information of the production and the execution environment characteristics of each production execution environment information are determined respectively according to the initial environment information of the production and the execution environment characteristics of each production execution environment information, that is, the specific values ​​of each indicator type of the initial environment information of the production and each production execution environment information are determined. The initial environment characteristics of the initial environment information of the production and the execution environment characteristics of each production execution environment information are compared to determine the change value between the initial characteristics and the execution environment characteristics. Among them, the change value between the initial characteristics and the execution environment characteristics can be determined by making a difference between the initial characteristics and the execution environment characteristics to obtain the difference between the initial characteristics and the execution environment characteristics (that is, the change value between the initial environment information of the production and the execution environment information of each production), and the reward value of the scheduling strategy of each environment characteristic is determined according to the change value between the initial characteristics and the execution environment characteristics and the preset reward rule. Among them, the reward value of the scheduling strategy of each environment characteristic can be determined based on the preset reward rule and the difference between the initial characteristics and the execution environment characteristics. In fact, the positive or negative or size of the difference between the initial characteristics and the execution environment characteristics and the preset reward rule are used to determine the reward value of the scheduling strategy of each environment characteristic. For example, when the difference in utilization between the initial feature and each execution environment feature is positive, the utilization reward value is increased according to the preset reward rules. For example, the reward for increased equipment utilization is +1, and for decreased equipment utilization is -1. The reward for increased timely delivery rate is +1, and for decreased timely delivery rate is -1. The reward for decreased mold change rate is +1, and for increased mold change rate is -1.

[0077] Figure 3 : is a schematic diagram of the principle of determining the reward value of the scheduling strategy of each environmental feature in the profile production scheduling method provided by an embodiment of the present invention, such as Figure 3 As shown in the figure, the indicator types corresponding to the initial production environment information are four indicator types: expedited order postponement rate, ordinary order postponement rate, average machine mold change rate and average machine utilization rate. Among them, the preset reward rule can be that the expedited order postponement rate decreases, the return reward value increases by 1, the expedited order postponement rate increases, the return reward value decreases by 1, the expedited order postponement rate remains unchanged, and the return reward value is 0; the ordinary order postponement rate decreases, the return reward value increases by 1, the ordinary order postponement rate increases, the return reward value decreases by 1, the ordinary order postponement rate remains unchanged, and the return reward value is 0; the average machine mold change rate decreases, the return reward value increases by 1, the average machine mold change rate increases, the return reward value decreases by 1, the average machine mold change rate remains unchanged, and the return reward value is 0; the average machine utilization rate decreases, the return reward value increases by 1, the average machine utilization rate increases, the return reward value decreases by 1, the average machine utilization rate remains unchanged, and the return reward value is 0. Reward value of the scheduling strategy based on the preset reward rule, initial environment characteristics and each environment characteristic.

[0078] S240. Determine an online production scheduling model based on the reward value of the scheduling strategy of each environmental characteristic.

[0079] In the specific implementation, the reward value of the scheduling strategy of each environmental feature is used for calculation to obtain a judgment value for judging whether the scheduling model has converged. Based on the judgment of the scheduling model and the preset reward threshold, it is determined whether the scheduling model can be used as an online scheduling model for scheduling work.

[0080] Furthermore, the online production scheduling model is determined based on the reward value of each environmental characteristic scheduling strategy, including:

[0081] Accumulate the reward value of each environmental feature to get the total reward value of the training data set;

[0082] Determine whether the total reward value is greater than a preset reward threshold;

[0083] When the total reward value is greater than the preset reward threshold, the training parameters corresponding to the training data set are updated to the training network to obtain the online production scheduling model.

[0084] In a specific implementation, the preset reward threshold may be a reward threshold pre-designed according to actual demand or implementation data, which is used to judge whether the scheduling model has converged or meets the production scheduling requirements of the enterprise factory. The total reward value of the training data set may be obtained by accumulating the reward values ​​of the scheduling strategies of various environmental features obtained by inputting the training data in the training data set into the scheduling model, wherein the total reward value of the training data set is used to judge with the preset reward threshold whether the scheduling model trained by the training network has converged or meets the production scheduling requirements of the enterprise factory. When the total reward value is greater than the preset reward threshold, it means that the scheduling model trained by the training network has converged or met the production scheduling requirements of the enterprise factory, and the training parameters corresponding to the training data set are updated to the training network, that is, the training parameters in the scheduling model trained by the training network are updated to the training network to obtain the online production scheduling model. Among them, the training parameters corresponding to the training data set may be the training parameters of the network obtained by training the training network according to the training data in the training data set, that is, the training parameters of the scheduling model.

[0085] Further, after determining whether the total reward value is greater than the preset reward threshold, it also includes:

[0086] When the total reward value is less than the preset reward threshold, new training data corresponding to the production initial environment information is searched, and the new training data is updated to the training data set to obtain a new training data set;

[0087] The training network is trained according to the new training data set until the total reward value of the new training data set is greater than the preset reward threshold, and the online scheduling model is obtained.

[0088] In the specific implementation, the new training data set can search the scheduling strategy and environmental characteristics corresponding to the indicator type of the initial production environment information in the online database according to the initial production environment information, and form new training data to update the training data set to obtain the data set. Determine whether the total reward value of the training data set is greater than the preset reward threshold. When the total reward value of the training data set is greater than the preset reward threshold, it means that the scheduling model trained by the training network has converged or meets the production scheduling requirements of the enterprise factory. The training parameters corresponding to the training data set are updated to the training network, that is, the training parameters in the scheduling model trained by the training network are updated to the training network to obtain the online production scheduling model; when the total reward value of the training data set is less than the preset reward threshold, it means that the training of the training network by the training data set has not reached convergence or the production scheduling requirements of the enterprise factory, and it is necessary to re-expand the training data set to obtain a new training data set to train the training network, and calculate the total reward value corresponding to the new training data set. The total reward value corresponding to the new training data set is used to determine whether the new training data set has converged the training network to obtain an online production scheduling model. When the total reward value of the new training data set and the preset reward threshold determine that the model has not converged or has not met the production scheduling needs of the enterprise factory, the new training data set continues to be expanded until the total reward value of the new training data set is greater than the preset reward threshold to obtain an online production scheduling model.

[0089] In the embodiment of the present invention, the online production environment information is obtained by obtaining the initial production environment information and the external production information, and the initial production environment information is updated according to the external production information; the online production environment information is analyzed to obtain the environmental characteristics of the online production environment information; the environmental characteristics are input into the online production scheduling model to obtain the scheduling strategy corresponding to the online production environment information; the scheduling strategy is executed based on the online production environment information to generate a production scheduling plan. That is, in the embodiment of the present invention, real-time online production environment information is obtained by updating the production environment information; the environmental characteristics are obtained by analyzing the online production environment information, and the scheduling strategy corresponding to the online production environment information can be obtained based on the indicators according to the environmental characteristics and the online production scheduling model, and the production tasks can be intelligently scheduled, so as to improve production efficiency, shorten production time, and reduce production scheduling costs.

[0090] The following further describes the profile production scheduling method provided by the embodiment of the present invention. Figure 4 As shown, the method may specifically include the following steps:

[0091] S410, obtaining initial production environment information and external production information, and updating the initial production environment information according to the external production information to obtain online production environment information;

[0092] S420, obtaining indicator types of online production environment information, wherein the indicator types include utilization rate, delivery rate, and mold conversion rate;

[0093] In specific implementation, the indicator type corresponding to the online production environment information can be a quantitative indicator of the production information of the online production environment information during the operation process, and can be the utilization rate of the enterprise factory equipment, order delivery rate and mold change rate during the operation of the online production environment information.

[0094] S430, statistically analyzing the online production environment information according to the indicator type to obtain the environmental characteristics of the online production environment information;

[0095] In the specific implementation, the production information in the running online production environment information is statistically analyzed according to the indicator type corresponding to the online production environment information to obtain the environmental characteristics of the online production environment information. For example: there are 10 production equipment in the enterprise factory in the running online production environment information, and the total number of production equipment used in each batch is accumulated to obtain the total number of production equipment used in the online production environment information. The total number of production equipment used is divided by the number of production equipment in the enterprise factory and the number of batches to obtain the total number of available equipment to obtain the corresponding equipment utilization rate. Among them, the delivery rate of the order can be determined based on the probability of not exceeding the completion time specified in the order contract according to the completion time of the order in the online production environment information, which can be the ratio of the number of orders that do not exceed the completion time specified in the order contract and the total number of orders in the online production environment information, and the delivery rate of the order in the online production environment information is calculated; the mold change rate can be the probability of mold replacement between different batches, which is used to determine the mold utilization rate in the online production environment information, wherein the lower the mold change rate, the higher the timeliness of production and the faster the efficiency, which can be calculated based on the number of batches in the online environment information and the number of mold changes in the online environment information.

[0096] S440, inputting the environmental characteristics into the online production scheduling model to obtain a scheduling strategy corresponding to the online production environment information;

[0097] S450: Execute a scheduling strategy based on the online production environment information to generate a production scheduling plan.

[0098] In the embodiment of the present invention, the online production environment information is obtained by obtaining the initial production environment information and the external production information, and the initial production environment information is updated according to the external production information; the online production environment information is analyzed to obtain the environmental characteristics of the online production environment information; the environmental characteristics are input into the online production scheduling model to obtain the scheduling strategy corresponding to the online production environment information; the scheduling strategy is executed based on the online production environment information to generate a production scheduling plan. That is, in the embodiment of the present invention, real-time online production environment information is obtained by updating the production environment information; the environmental characteristics are obtained by analyzing the online production environment information, and the scheduling strategy corresponding to the online production environment information can be obtained based on the indicators according to the environmental characteristics and the online production scheduling model, and the production tasks can be intelligently scheduled, so as to improve production efficiency, shorten production time, and reduce production scheduling costs.

[0099] Figure 5 is a schematic diagram of the structure of the profile production scheduling device provided by an embodiment of the present invention, such as Figure 5 As shown, the profile production scheduling device includes:

[0100] The information acquisition module 510 is used to acquire the initial production environment information and the external production information, and update the initial production environment information according to the external production information to obtain the online production environment information;

[0101] A feature analysis module 520 is used to analyze the online production environment information to obtain the environmental features of the online production environment information;

[0102] A strategy determination module 530, configured to input the environmental characteristics into an online production scheduling model to obtain a scheduling strategy corresponding to the online production environment information;

[0103] The strategy execution module 540 is used to execute the scheduling strategy based on the online production environment information to generate a production scheduling plan.

[0104] In one embodiment, the online production scheduling model in the strategy determination module 530 is obtained as follows:

[0105] Acquire a training data set according to the initial production environment information;

[0106] Inputting the training data set into a training network to obtain a scheduling strategy for each environmental feature in the training data set;

[0107] Based on the initial production environment information, the scheduling strategies of the environmental characteristics are respectively executed to obtain the reward values ​​of the scheduling strategies of the environmental characteristics;

[0108] The online production scheduling model is determined according to the reward value of the scheduling strategy of each environmental feature.

[0109] In one embodiment, the strategy determination module 530 executes the scheduling strategies of the environmental characteristics respectively based on the initial production environment information to obtain the reward value of the scheduling strategies of the environmental characteristics, including:

[0110] Based on the initial production environment information, the environmental characteristics and the scheduling strategies of the environmental characteristics, a production plan corresponding to each scheduling strategy is generated, and the production plan corresponding to each scheduling strategy is respectively executed to obtain the production execution environment information corresponding to each scheduling strategy;

[0111] The production initial environment information is compared with the production execution environment information corresponding to each scheduling strategy to determine the reward value of the scheduling strategy of each environmental feature.

[0112] In one embodiment, the strategy determination module 530 compares the production initial environment information with the production execution environment information to determine the reward value of the scheduling strategy for each environment feature, including:

[0113] Determine the initial environment characteristics of the production initial environment information and the execution environment characteristics of each production execution environment information, and respectively determine the change value between the initial characteristics and each execution environment characteristic;

[0114] The reward value of the scheduling strategy for each of the environmental characteristics is determined according to the change value between the initial characteristics and the characteristics of each of the execution environments and a preset reward rule.

[0115] In one embodiment, the strategy determination module 530 determines the online production scheduling model according to the reward value of each environmental feature scheduling strategy, including:

[0116] Accumulating the reward values ​​of the environmental features to obtain the total reward value of the training data set;

[0117] Determining whether the total reward value is greater than a preset reward threshold;

[0118] When the total reward value is greater than a preset reward threshold, the training parameters corresponding to the training data set are updated to the training network to obtain the online production scheduling model.

[0119] In one embodiment, after the strategy determination module 530 determines whether the total reward value is greater than a preset reward threshold, it further includes:

[0120] When the total reward value is less than a preset reward threshold, searching for new training data corresponding to the production initial environment information, and updating the new training data into the training data set to obtain a new training data set;

[0121] The training network is trained according to the new training data set until the total reward value of the new training data set is greater than the preset reward threshold, thereby obtaining the online production scheduling model.

[0122] In one embodiment, the feature analysis module 520 analyzes the online production environment information to obtain the environmental features of the online production environment information, including:

[0123] Acquire the indicator types of the online production environment information, wherein the indicator types include utilization rate, delivery rate and mold conversion rate;

[0124] The online production environment information is statistically analyzed according to the indicator type to obtain environmental characteristics of the online production environment information.

[0125] In the embodiment of the present invention, the online production environment information is obtained by obtaining the initial production environment information and the external production information, and the initial production environment information is updated according to the external production information; the online production environment information is analyzed to obtain the environmental characteristics of the online production environment information; the environmental characteristics are input into the online production scheduling model to obtain the scheduling strategy corresponding to the online production environment information; the scheduling strategy is executed based on the online production environment information to generate a production scheduling plan. That is, in the embodiment of the present invention, real-time online production environment information is obtained by updating the production environment information; the environmental characteristics are obtained by analyzing the online production environment information, and the scheduling strategy corresponding to the online production environment information can be obtained based on the indicators according to the environmental characteristics and the online production scheduling model, and the production tasks can be intelligently scheduled, so as to improve production efficiency, shorten production time, and reduce production scheduling costs.

[0126] Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 6 A block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 6 The electronic device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0127] like Figure 6 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0128] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0129] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0130] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 6 not shown, usually called a "hard drive"). Although Figure 6 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0131] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0132] The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 12, and / or may communicate with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0133] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing the profile production scheduling method provided in the embodiment of the present invention, which includes:

[0134] Acquire initial production environment information and external production information, and update the initial production environment information according to the external production information to obtain online production environment information;

[0135] Analyze the online production environment information to obtain environmental characteristics of the online production environment information;

[0136] Inputting the environmental characteristics into an online production scheduling model to obtain a scheduling strategy corresponding to the online production environment information;

[0137] The scheduling strategy is executed based on the online production environment information to generate a production scheduling plan.

[0138] The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, characterized in that when the program is executed by a processor, the profile production scheduling method is implemented, and the method includes:

[0139] Acquire initial production environment information and external production information, and update the initial production environment information according to the external production information to obtain online production environment information;

[0140] Analyze the online production environment information to obtain environmental characteristics of the online production environment information;

[0141] Inputting the environmental characteristics into an online production scheduling model to obtain a scheduling strategy corresponding to the online production environment information;

[0142] The scheduling strategy is executed based on the online production environment information to generate a production scheduling plan.

[0143] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0144] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0145] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0146] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0147] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A profile production scheduling method, characterized in that: include: Acquire initial production environment information and external production information, and update the initial production environment information according to the external production information to obtain online production environment information, wherein the initial production environment information includes production quantitative information, and the production quantitative information includes initial production plan, mold, equipment, materials, finished product information and environmental configuration, and the external production information is the production environment information generated according to the unentered production orders, production failures of factory equipment and order changes; Analyze the online production environment information to obtain environmental characteristics of the online production environment information; Inputting the environmental characteristics into an online production scheduling model to obtain a scheduling strategy corresponding to the online production environment information; Executing the scheduling strategy based on the online production environment information to generate a production scheduling plan; Wherein, analyzing the online production environment information to obtain the environmental characteristics of the online production environment information includes: Acquire the indicator types of the online production environment information, wherein the indicator types include utilization rate, delivery rate and mold conversion rate; The online production environment information is statistically analyzed according to the indicator type to obtain environmental characteristics of the online production environment information.

2. The method according to claim 1, characterized in that The online production scheduling model is obtained as follows: Acquire a training data set according to the initial production environment information; Inputting the training data set into a training network to obtain a scheduling strategy for each environmental feature in the training data set; Based on the initial production environment information, the scheduling strategies of the environmental characteristics are respectively executed to obtain the reward values ​​of the scheduling strategies of the environmental characteristics; The online production scheduling model is determined according to the reward value of the scheduling strategy of each environmental feature.

3. The method according to claim 2, characterized in that The scheduling strategies of the environmental characteristics are respectively executed based on the initial production environment information to obtain the reward values ​​of the scheduling strategies of the environmental characteristics, including: Based on the initial production environment information, the environmental characteristics and the scheduling strategies of the environmental characteristics, a production plan corresponding to each scheduling strategy is generated, and the production plan corresponding to each scheduling strategy is respectively executed to obtain the production execution environment information corresponding to each scheduling strategy; The production initial environment information is compared with the production execution environment information corresponding to each scheduling strategy to determine the reward value of the scheduling strategy of each environmental feature.

4. The method according to claim 3, characterized in that: Comparing the initial production environment information with the production execution environment information to determine the reward value of the scheduling strategy of each environmental feature, including: Determine the initial environment characteristics of the production initial environment information and the execution environment characteristics of each production execution environment information, and respectively determine the change value between the initial characteristics and each execution environment characteristic; The reward value of the scheduling strategy for each of the environmental characteristics is determined according to the change value between the initial characteristics and each of the execution environment characteristics and a preset reward rule.

5. The method according to claim 2, characterized in that: Determining the online production scheduling model according to the reward value of each environmental feature scheduling strategy includes: Accumulating the reward values ​​of the environmental features to obtain the total reward value of the training data set; Determining whether the total reward value is greater than a preset reward threshold; When the total reward value is greater than a preset reward threshold, the training parameters corresponding to the training data set are updated to the training network to obtain the online production scheduling model.

6. The method according to claim 5, characterized in that After determining whether the total reward value is greater than a preset reward threshold, the method further includes: When the total reward value is less than a preset reward threshold, searching for new training data corresponding to the production initial environment information, and updating the new training data into the training data set to obtain a new training data set; The training network is trained according to the new training data set until the total reward value of the new training data set is greater than the preset reward threshold, thereby obtaining the online production scheduling model.

7. A profile production scheduling device, characterized in that: include: An information acquisition module is used to acquire initial production environment information and external production information, and update the initial production environment information according to the external production information to obtain online production environment information, wherein the initial production environment information includes production quantitative information, and the production quantitative information includes initial production plan, mold, equipment, materials, finished product information and environmental configuration, and the external production information is the production environment information generated according to the unentered production orders, production failures of factory equipment and order changes; A feature analysis module, used to analyze the online production environment information to obtain environmental features of the online production environment information; A strategy determination module, used to input the environmental characteristics into an online production scheduling model to obtain a scheduling strategy corresponding to the online production environment information; A strategy execution module, used to execute the scheduling strategy based on the online production environment information to generate a production scheduling plan; Wherein, the feature analysis module is used to: Acquire the indicator types of the online production environment information, wherein the indicator types include utilization rate, delivery rate and mold conversion rate; The online production environment information is statistically analyzed according to the indicator type to obtain environmental characteristics of the online production environment information.

8. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the profile production scheduling method as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the profile production scheduling method as described in any one of claims 1 to 6 is implemented.

Images