Industrial production scheduling method and system, intelligent terminal and storage medium

Abstract

The invention relates to an industrial production scheduling method and system, an intelligent terminal and a storage medium, and relates to the technical field of large models, and the method comprises the steps: collecting production data, related to a first product, of each factory; performing preprocessing and feature extraction operation on the production data to obtain a production data feature set of the production data; obtaining a first industrial production rule of the first product, wherein the first industrial production rule is used as a constraint condition for producing the first product; performing feature extraction operation on the first industrial production rule to obtain a production rule feature set of the first industrial production rule; and calling a production scheduling plan model, performing production scheduling on the production data feature set and the production rule feature set, and obtaining a total production scheduling plan of the first product, the total production scheduling plan including the production scheduling plan of each factory. The method has the effect of improving the accuracy of the industrial production scheduling plan.

Description

Technical Field

[0001] The present application relates to the technical field of large models, and in particular to an industrial production scheduling method, system, intelligent terminal, and storage medium. Background Art

[0002] Planning and scheduling in industrial production manufacturing are the core links to ensure production efficiency and optimal utilization of resources. Reasonable planning and scheduling can not only improve the working efficiency of the production line, reduce production costs, but also ensure on-time delivery, meet customer needs, and ultimately enhance the market competitiveness of the enterprise.

[0003] Related technologies need to first obtain the priority and delivery deadline of the product, and obtain the production capacity of the factory to produce the product. Taking the priority and delivery deadline as the goal and the production capacity as the constraint condition, a linear optimization algorithm is used to calculate the quantity of products produced by the factory every day, and the scheduling plan is set according to the aforementioned quantity.

[0004] In view of the above related technologies, the formulation of the scheduling plan is affected by many factors, and the scheduling plan obtained only by the linear optimization method is difficult to adapt to complex scenarios, resulting in the scheduling plan deviating from the actual scenario. Summary of the Invention

[0005] In order to improve the accuracy of the industrial production scheduling plan, the present application provides an industrial production scheduling method, system, intelligent terminal, and storage medium.

[0006] In a first aspect, the present application provides an industrial production scheduling method, adopting the following technical solution: An industrial production scheduling method includes: Collect production data related to a first product from each factory, where the production data includes at least one of the collected order requirements, production resources, equipment status, and raw material inventory of the first product; Perform preprocessing and feature extraction operations on the production data to obtain a production data feature set of the production data; Obtain a first industrial production rule of the first product, where the first industrial production rule is used as a constraint condition for producing the first product, and the first industrial production rule includes at least one of product production objectives, product order priorities, production cycle constraints, and equipment maintenance plans; Perform feature extraction operations on the first industrial production rule to obtain a production rule feature set of the first industrial production rule; Call a scheduling plan model to perform a scheduling plan on the production data feature set and the production rule feature set to obtain a total production scheduling plan of the first product, where the total production scheduling plan includes the production scheduling plans of each factory.

[0007] By adopting the above technical solution, the production data feature set and the production rule feature set are respectively obtained through the production data related to the first product and the first industrial production rule of the first product, and the total production scheduling plan of the first product is obtained through the production data feature set and the production rule feature set. Through the language understanding and reasoning ability of the scheduling plan model, the efficiency and flexibility of industrial production planning and scheduling are significantly optimized.

[0008] Optionally, the production conditions of each factory are monitored in real time to obtain the actual production conditions of each factory; For the target factory among the various factories, the target production scheduling plan of the target factory is determined in the total production scheduling plan, and the target actual production conditions of the target factory are determined in the actual production conditions; In the case where the similarity between the target production scheduling plan and the target actual production conditions is less than the preset similarity, the production abnormality cause of the target factory is obtained according to the target production scheduling plan and the target actual production conditions; The production data feature set is updated according to the production abnormality cause, and the total production scheduling plan is adjusted by using the updated production data feature set.

[0009] By adopting the above technical solution, the actual production conditions of each factory are monitored in real time, the production abnormality cause is deduced according to the actual production conditions, and then the total production scheduling plan is adjusted according to the production abnormality cause. Problems occurring in the factory can be addressed by adjusting the total production scheduling plan to ensure the manufacturing efficiency of the first product.

[0010] Optionally, the historical market demand in the similar time period of the first product in the historical period is statistically analyzed; The current market demand change of the first product in the current time period is statistically analyzed, and the current time period corresponds to the similar time period; The historical market demand and the current market demand change are integrally processed to obtain the theoretical market demand of the first product; The first industrial production rule is updated by using the theoretical market demand.

[0011] By adopting the above technical solution, the first industrial production rule is updated according to the historical market demand and the current market demand change, ensuring that the first industrial production rule can match the actual situation and improving the accuracy of the total production scheduling plan.

[0012] Optionally, in the case where the abnormal production cause belongs to an irresistible abnormal production cause, the affected area is determined according to the abnormal production cause; The affected factories located near the affected area are determined; Statistically analyze the production data affecting the factory; Use the production data affecting the factory to update the overall production scheduling plan.

[0013] By adopting the above technical solution, when the abnormal production reason belongs to an irresistible abnormal production reason, the affected factories near the affected area will be determined, and the overall production scheduling plan will be updated according to the production data of the affected factories.

[0014] Optionally, calculate the correlation degree between the first product and the abnormal production reason; When the correlation degree is greater than the preset correlation degree, adjust the current product production target of the affected factory according to the distance from the affected factory to the affected area and the demand degree of the first product in the affected area; Collect the first traffic status of the affected factory and the second traffic status in the affected area; Collect the product demand locations in the affected area; Call the path planning model to perform path planning on the location of the affected factory, the current product production target, the location of the product demand location, the first traffic status, and the second traffic status, and obtain the transportation route from the affected factory to the product demand location and the corresponding first product carrying capacity of each transportation route.

[0015] By adopting the above technical solution, the transportation route of the affected factory and the corresponding first product carrying capacity of each transportation route can be adjusted to ensure that the first product produced by each affected factory can be transported to the affected area in time. This not only ensures the product production efficiency of each affected factory but also ensures that the first product can be transported to the affected area.

[0016] Optionally, when the correlation degree is less than the preset correlation degree, obtain the feasibility result of the affected factory producing the second product according to the equipment information of the affected factory; When the feasibility result is that production is feasible, determine the method for updating the production line of the affected factory and predict the longest time for the affected factory to update the production line; Use the longest time and the relevant information of the second product to update the production data affecting the factory and update the production data feature set based on the production data affecting the factory; Obtain the second industrial production rule of the second product; Use the second industrial production rule to update the production rule feature set; Update the production scheduling plan of the affected factory through the production data feature set and the production rule feature set.

[0017] By adopting the above technical solution, the products affecting the factory production can be turned into second products, ensuring that the second products can meet the needs of the people in the affected area, and updating the production scheduling plan according to the actual situation of the factory affecting production to ensure the production volume of the second products.

[0018] Optionally, generate a skill portrait according to the update method; Search for target personnel in each of the factories according to the skill portrait and determine the locations of the target personnel; For the target affected factory among the affected factories, determine the actual number of the target personnel in the target affected factory and the theoretical required number of the target personnel by the target affected factory; In the case where the actual number is less than the theoretical required number, determine the flow mode of the target personnel according to the location of the target affected factory and the difference in the number between the actual number and the theoretical required number.

[0019] By adopting the above technical solution, adjust the personnel flow in the factory so that the target personnel can reach the target affected factory in time and provide an update method for the target affected factory to ensure the normal operation of the target affected factory.

[0020] In a second aspect, the present application provides an industrial production scheduling system, adopting the following technical solution: An industrial production scheduling system includes: An acquisition module, configured to acquire production data, a first industrial production rule, a scheduling plan model, actual production conditions, historical market demands, current market demand change conditions, affected areas, preset correlation degrees, product demand locations, theoretical required numbers, and skill portraits; A memory, configured to store a program of the industrial production scheduling method of any one of the above; A processor, and the program in the memory can be loaded and executed by the processor and implement the industrial production scheduling method of any one of the above.

[0021] By adopting the above technical solution, respectively obtain a production data feature set and a production rule feature set through the production data related to the first product and the first industrial production rule of the first product, and obtain the total production scheduling plan of the first product through the production data feature set and the production rule feature set. This method significantly optimizes the efficiency and flexibility of industrial production planning and scheduling through the language understanding and reasoning capabilities of the scheduling plan model.

[0022] In a third aspect, the present application provides an intelligent terminal, adopting the following technical solution: An intelligent terminal includes a memory and a processor, and a computer program capable of being loaded and executed by the processor for any of the above-mentioned methods is stored on the memory.

[0023] In a fourth aspect, the present application provides a computer-readable storage medium that can store a corresponding program and has the characteristic of facilitating the improvement of the accuracy of industrial production scheduling plans. The following technical solution is adopted: A computer-readable storage medium stores a computer program capable of being loaded and executed by a processor for any of the above industrial production scheduling methods.

[0024] In summary, the present application includes at least one of the following beneficial technical effects: By using the production data related to the first product and the first industrial production rule of the first product, a production data feature set and a production rule feature set are respectively obtained, and the overall production scheduling plan of the first product is obtained through the production data feature set and the production rule feature set. This method significantly optimizes the efficiency and flexibility of industrial production planning and scheduling through the language understanding and reasoning ability of the scheduling plan model; The actual production situation of each factory is monitored in real time, the reasons for production anomalies are deduced based on the actual production situation, and then the overall production scheduling plan is adjusted according to the reasons for production anomalies. The problems that occur in the factory can be addressed by adjusting the overall production scheduling plan to ensure the manufacturing efficiency of the first product; According to the historical market demand and the current changes in market demand, the first industrial production rule is updated to ensure that the first industrial production rule can match the actual situation and improve the accuracy of the overall production scheduling plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 is a flowchart showing an industrial production scheduling method provided by an embodiment of the present application.

[0026] Figure 2 is a flowchart showing a method for adjusting an overall production scheduling plan provided by an embodiment of the present application.

[0027] Figure 3 is a flowchart showing a method for updating a first industrial production rule provided by an embodiment of the present application.

[0028] Figure 4 is a flowchart showing a method for updating a scheduling plan based on irresistible abnormal production reasons provided by an embodiment of the present application.

[0029] Figure 5 is a flowchart showing a method for planning a product transportation route provided by an embodiment of the present application.

[0030] Figure 6It is a schematic flowchart of a production scheduling method for a second product provided by an embodiment of the present application.

[0031] Figure 7 It is a schematic flowchart of a personnel flow method provided by an embodiment of the present application.

[0032] Figure 8 It is a schematic structural diagram of an industrial production scheduling system provided by an embodiment of the present application. Detailed implementation manners

[0033] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the Figures 1 to 8 accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0034] An embodiment of the present application discloses an industrial production scheduling method. Referring to Figure 1 , the method includes: Step S101: Collect production data related to the first product for each factory. The production data includes at least one of the collected order requirements, production resources, equipment status, and raw material inventory of the first product.

[0035] The collected order requirements are used to represent the demand for the first product in the market or by customers. The collected order requirements include at least one of order information, shipping time, quantity, and specifications.

[0036] The production resources refer to the resources that support the production of the first product. The production resources include at least one of human resources, equipment resources, and time.

[0037] The equipment status is used to represent the condition of the equipment for producing the first product during operation. The equipment status includes at least one of whether the equipment is operating normally, whether it needs repair, and the workload.

[0038] The raw material inventory refers to the existing inventory situation of the raw materials and components required in the process of producing the first product.

[0039] Optionally, each factory can upload its own production data to the cloud server, and when production data is needed, it can download the production data from the cloud server.

[0040] Step S102: Perform preprocessing and feature extraction operations on the production data to obtain a production data feature set of the production data.

[0041] The preprocessing includes processing missing values, outliers, and duplicate data. Exemplarily, the interpolation method is used to supplement the missing values in the production data. Exemplarily, the outliers and duplicate data in the production data are deleted.

[0042] Exemplarily, the feature extraction operation is a normalization operation.

[0043] Optionally, the production data feature set is in matrix form. Exemplarily, when the production data feature set is a feature matrix, the first row of the production data feature set corresponds to the vector of the acquisition order, and the second row of the production data feature set corresponds to the vector of the production resources.

[0044] Step S103: Obtain the first industrial production rule of the first product, where the first industrial production rule is used as a constraint condition for producing the first product, and the first industrial production rule includes at least one of a product production target, a product order priority, a production cycle constraint, and an equipment maintenance plan.

[0045] The product production target refers to the product output or delivery quantity of the first product that each factory needs to achieve in total within a specific time. Optionally, the product production target is set according to market demand, customer orders, inventory levels, or custom targets.

[0046] The product order priority refers to the priority order for processing different products.

[0047] The production cycle constraint refers to the time limit or conditions during the process of producing the first product. The production cycle constraint is affected by equipment capabilities, operation processes, process requirements, inventory levels, etc.

[0048] The equipment maintenance plan refers to the equipment maintenance and servicing for the equipment used to produce the first product. Optionally, the equipment maintenance plan includes at least one of regular maintenance, preventive maintenance, and fault repair.

[0049] Step S104: Perform a feature extraction operation on the first industrial production rule to obtain the production rule feature set of the first industrial production rule.

[0050] Exemplarily, the feature extraction operation is a normalization operation.

[0051] Optionally, the production rule feature set is in matrix form. Exemplarily, when the production rule feature set is a feature matrix, the first row of the production rule feature set corresponds to the vector of the product production target, and the second row of the production rule feature set corresponds to the vector of the product order priority.

[0052] Step S105: Invoke the production scheduling model to perform production scheduling on the production data feature set and the production rule feature set to obtain the total production scheduling plan of the first product, where the total production scheduling plan includes the production scheduling plans of each factory.

[0053] The production scheduling model uses a general large model. The general large model is a model integrated with multiple functions. Exemplarily, the production scheduling model is integrated with functions such as natural language processing, reasoning and decision support, and multi-modal capabilities.

[0054] By adopting the above technical solution, the production data feature set and the production rule feature set are respectively obtained through the production data related to the first product and the first industrial production rule of the first product, and the total production scheduling plan of the first product is obtained through the production data feature set and the production rule feature set. Through the language understanding and reasoning ability of the scheduling plan model, the method significantly optimizes the efficiency and flexibility of industrial production planning and scheduling.

[0055] In the following embodiments, in the actual production activities of the factory, it is necessary to monitor the production process of the factory in real time so as to adjust the production scheduling plan of the factory in time, so as to follow up the changes in the actual situation. Therefore, an embodiment of the present application discloses a method for adjusting the total production scheduling plan. Referring to Figure 2 , the method includes: Step S201: Monitor the production conditions of each factory in real time to obtain the actual production conditions of each factory.

[0056] Optionally, the production conditions refer to the quantity and quality of the first product produced by the factory within the production cycle. The duration of the production cycle can be adjusted according to the actual situation. For example, the production cycle is one day, one week or one month. For example, the production conditions refer to the quantity of the first product produced by the factory within one day.

[0057] Step S202: For the target factory among each factory, determine the target production scheduling plan of the target factory in the total production scheduling plan, and determine the target actual production conditions of the target factory in the actual production conditions.

[0058] The target factory is any one of each factory.

[0059] The target production scheduling plan refers to the quantity and quality of the first product planned to be produced by the target factory within the production cycle. Similarly, the target actual production conditions refer to the quantity and quality of the first product actually produced by the target factory within the production cycle. Among them, the target production scheduling plan and the target actual production conditions correspond to the same production cycle.

[0060] Step S203: In the case where the similarity between the target production scheduling plan and the target actual production conditions is less than the preset similarity, obtain the production abnormality cause of the target factory according to the target production scheduling plan and the target actual production conditions.

[0061] The abnormal production causes include equipment damage, equipment aging, insufficient human resources, insufficient raw materials, unqualified raw material quality, and irresistible production abnormal causes, etc.

[0062] The preset similarity is a preset empirical value, and relevant personnel can adjust the value of the preset similarity according to the actual situation.

[0063] Optionally, perform feature extraction operations on the target production scheduling plan to obtain the first comparison feature. Perform feature extraction operations on the target actual production situation to obtain the second comparison feature. Call the error correction model to perform error correction processing on the first comparison feature and the second comparison feature to obtain candidate production anomaly causes. After obtaining the candidate production anomaly causes, relevant personnel can conduct investigations according to the candidate production anomaly causes to obtain the actual production anomaly causes. The error correction model uses a general large model.

[0064] In some other embodiments, a classifier can also be used to score the candidate production anomaly causes to obtain the score of each candidate production anomaly cause. Take the candidate production anomaly cause corresponding to the maximum value in the score as the production anomaly cause. Thus, the automatic search for the production anomaly cause is realized, liberating manpower.

[0065] In another aspect of this embodiment, when the similarity between the target production scheduling plan and the target actual production situation is greater than the preset similarity, it indicates that the target production scheduling plan is close to the target actual production situation, and the target factory has completed the production scheduling plan, and there is no need to execute the subsequent steps.

[0066] Step S204: Update the production data feature set according to the production anomaly cause, and use the updated production data feature set to adjust the total production scheduling plan.

[0067] Call the production scheduling plan model to perform production scheduling on the updated production data feature set and the production rule feature set to obtain the total production scheduling plan of the updated first product.

[0068] By adopting the above technical solutions, the actual production situation of each factory is monitored in real time, the production anomaly cause is deduced according to the actual production situation, and then the total production scheduling plan is adjusted according to the production anomaly cause. The problems that occur in the factory can be addressed by adjusting the total production scheduling plan, ensuring the manufacturing efficiency of the first product.

[0069] In the following embodiments, the market demand for the first product will change continuously over time. To cope with the continuous changes in market demand, the quantity and efficiency of the factory producing the first product also need to make adaptive adjustments. Therefore, the embodiments of the present application disclose a method for updating the first industrial production rules. Refer to Figure 3 , the method includes: Step S301: Statistically analyze the historical market demand for the first product during similar periods in the historical period.

[0070] The historical market demand is the total demand for the first product in the market.

[0071] The similar period is located in the historical period. The similar period is a proper subset of the historical period. Exemplarily, the historical market demand refers to the total quantity of the first product purchased in the market on March 1st of last year.

[0072] Step S302: Statistically analyze the current market demand change of the first product in the current period, where the current period corresponds to the similar period.

[0073] Optionally, taking the current time point as the midpoint of the current period, and taking the preset time length as the interval length of the current period, the current period is obtained. Then, the current period includes a left endpoint and a right endpoint. Statistically analyze the first market sales volume of the first product from the left endpoint to the current time point. Invoke the market sales volume prediction model to process the data of the first market sales volume to obtain the second market sales volume from the current time point to the right endpoint. Combine the first market sales volume and the second market sales volume to obtain the current market demand change. The current market demand change describes the quantity of the market's demand for the first product during the current period corresponding to the left endpoint to the right endpoint.

[0074] Specifically, the current period is from March 1st to March 7th, and the similar period is from March 1st to March 7th of last year.

[0075] Step S303: Integrate and process the historical market demand and the current market demand change to obtain the theoretical market demand of the first product.

[0076] The theoretical market demand refers to the quantity of the market's demand for the first product in the future period.

[0077] Optionally, calculate the mean value of the current market demand change to obtain the current market demand. Calculate the weighted value of the historical market demand and the current market demand to obtain the theoretical market demand of the first product.

[0078] Optionally, according to the similar period of the historical market demand, determine the target current market data corresponding to the similar period in the current market demand change. Calculate the mean value of the historical market demand and the target current market data, and use the aforementioned mean value to replace the target current market data in the current market demand change to obtain the theoretical market demand of the first product.

[0079] Step S304: Update the first industrial production rule using the theoretical market demand.

[0080] After updating the first industrial production rule using the theoretical market demand, generate an updated production rule feature set using the updated first industrial production rule. Invoke the production scheduling plan model to perform production scheduling on the production data feature set and the updated production rule feature set to obtain the total production scheduling plan of the updated first product.

[0081] By adopting the above technical solution, the first industrial production rules are updated according to the historical market demand and the changes in the current market demand, ensuring that the first industrial production rules can match the actual situation and improving the accuracy of the overall production scheduling plan.

[0082] In the following embodiments, in the actual production scenario, various inevitable accidents may sometimes occur. At this time, the factory needs to flexibly adjust the production scheduling plan according to the actual situation. While ensuring the rights and interests of the factory, it can cope with the damage caused by the accidents. Therefore, the embodiments of the present application disclose a method for updating the production scheduling plan based on irresistible abnormal production reasons. Referring to Figure 4 , the method includes: Step S401: When the abnormal production reason belongs to an irresistible abnormal production reason, determine the affected area according to the abnormal production reason.

[0083] In the present application, the irresistible abnormal production reason refers to sudden public events, natural disasters, social security events or accident disasters, etc.

[0084] Exemplarily, when the abnormal production reason is a natural disaster, the affected area can be obtained through the scope of the natural disaster.

[0085] Step S402: Determine the affected factories located near the affected area.

[0086] Optionally, set the boundary line of the warning area outside the affected area, and the shortest distance from the boundary line to the affected area is greater than the preset distance. Set the factories within the warning area as affected factories.

[0087] Step S403: Statistically analyze the affected production data of the affected factories.

[0088] The affected production data includes production data and the first industrial production rules.

[0089] In some embodiments, after the relevant personnel statistically analyze the affected production data, the affected production data is uploaded to the computer system, so that the production scheduling plan model can process the affected production data.

[0090] Step S404: Update the overall production scheduling plan using the affected production data.

[0091] Perform feature extraction operations on the production data in the affected production data to obtain the affected production data feature set. Perform feature extraction operations on the first industrial production rules in the affected production data to obtain the affected production rule feature set. Call the production scheduling plan model to schedule the production for the affected production data feature set and the affected production rule feature set, and obtain the updated overall production scheduling plan.

[0092] By adopting the above technical solution, when the abnormal production cause belongs to an irresistible abnormal production cause, the affected factory near the affected area will be determined, and the total production scheduling plan will be updated according to the production data of the affected factory.

[0093] In the following embodiments, when the factory is affected by an irresistible abnormal production cause, it is necessary to reconsider the production quantity of the first product. On the one hand, the factory itself will be affected, and on the other hand, the market demand in the affected area will also change. Moreover, it is also necessary to consider the impact of traffic changes in the affected area on the transportation of the first product. Therefore, an embodiment of the present application discloses a method for planning a product transportation route. Referring to Figure 5 , the method includes: Step S501: Calculate the correlation degree between the first product and the abnormal production cause.

[0094] Optionally, obtain the type parameter of the first product. Convert the type parameter into a type feature vector. Determine the product required parameter corresponding to the abnormal production cause in the preset mapping relationship according to the abnormal production cause. Convert the product required parameter into a product required vector. Calculate the distance between the type feature vector and the product required vector to obtain a vector distance. Convert the vector distance into a correlation degree, where the correlation degree is negatively correlated with the vector distance.

[0095] Step S502: When the correlation degree is greater than the preset correlation degree, adjust the current product production target of the affected factory according to the distance from the affected factory to the affected area and the demand degree of the first product in the affected area.

[0096] The preset correlation degree is a preset empirical value, and relevant personnel can adjust the specific value of the preset correlation degree according to actual needs.

[0097] The demand degree includes the demand quantity and the demand quality.

[0098] Exemplarily, according to the distance from the affected factory to the affected area and the demand degree of the first product in the affected area, adjust the first industrial production rule. Update the production rule feature set with the adjusted first industrial production rule to obtain an updated production rule feature set. Call the production scheduling model to perform production scheduling on the production data feature set and the updated production rule feature set to obtain the current product production target of the affected factory.

[0099] In another aspect of this embodiment, when the correlation degree is less than the preset correlation degree, it means that the market demand for the first product in the affected area is small, so there is no need to perform subsequent steps.

[0100] Step S503: Collect the first traffic status of the affected factory and the second traffic conditions in the affected area.

[0101] Traffic status represents the operation of a traffic network, and traffic status can reflect information such as traffic mobility, speed, density, congestion, etc. on the road.

[0102] The first traffic status refers to the traffic status affecting the area near the factory.

[0103] The second traffic status refers to the traffic status affecting the area within the region.

[0104] In some embodiments, the first traffic status and the second traffic status can be obtained through a positioning server.

[0105] Step S504: Collect the product demand locations within the affected area.

[0106] The product demand location refers to the area within the affected area where the demand quantity for the first product is greater than a preset quantity threshold.

[0107] Optionally, collect the demand quantities for the first product at different locations within the affected area. Select the areas within the affected area where the demand quantity is greater than the preset demand quantity threshold to obtain the product demand areas. Take the central location of the product demand areas to obtain the product demand locations.

[0108] Step S505: Invoke the path planning model to perform path planning on the location of the factory under influence, the current product production target, the location of the product demand location, the first traffic status, and the second traffic status, to obtain the transportation routes from the factory under influence to the product demand locations and the corresponding first product carrying capacities for each transportation route.

[0109] The path planning model adopts any one of a convolutional neural network, a recurrent neural network, a long short-term memory neural network, and a hybrid neural network. Exemplarily, perform feature extraction on the location of the factory under influence, the current product production target, the location of the product demand location, the first traffic status, and the second traffic status to obtain a feature vector matrix. Invoke the path planning model to perform path planning on the feature vector matrix to obtain the transportation routes from the factory under influence to the product demand locations and the corresponding first product carrying capacities for each transportation route.

[0110] By adopting the above technical solution, the transportation routes from the factory under influence and the corresponding first product carrying capacities for each transportation route can be adjusted to ensure that each first product produced by the factory under influence can be transported to the affected area in a timely manner. This not only ensures the product production efficiency of each factory under influence but also ensures that the first product can be delivered to the affected area.

[0111] In the following embodiments, in a special scenario, it is necessary for the factory under influence to temporarily produce a specific second product. Therefore, the embodiments of the present application disclose a production scheduling planning method for the second product. Refer to Figure 6 , the method includes: Step S601: When the correlation degree is less than the preset correlation degree, obtain the feasibility result of affecting the factory's production of the second product according to the equipment information of the factory.

[0112] The equipment information includes at least one of equipment type, equipment use, life cycle, operating status, and equipment performance.

[0113] Optionally, call the feasibility judgment model to perform a feasibility judgment on the equipment information of the factory to obtain the feasibility result.

[0114] The feasibility result includes production feasibility and production infeasibility.

[0115] Step S602: When the feasibility result is production feasible, determine the method for the factory to update the production line and predict the longest time for the factory to update the production line.

[0116] In some other embodiments, when the feasibility result is production infeasible, there is no need to execute the subsequent steps and the process ends.

[0117] Step S603: Use the longest time and the relevant information of the second product to update the influencing production data, and update the production data feature set based on the influencing production data.

[0118] Optionally, the updated influencing production data includes at least one of the acquisition order requirements, production resources, equipment status, and raw material inventory of the second product.

[0119] Step S604: Obtain the second industrial production rule of the second product.

[0120] The second industrial production rule is used as a constraint condition for producing the second product, and the second industrial production rule includes at least one of product production objectives, product order priorities, production cycle constraints, and equipment maintenance plans.

[0121] Step S605: Update the production rule feature set using the second industrial production rule.

[0122] In some embodiments, replace the first industrial production rule with the second industrial production rule to update the production rule feature set.

[0123] In some embodiments, combine the first industrial production rule and the second industrial production rule to update the production rule feature set.

[0124] Step S606: Update the production scheduling plan of the factory through the production data feature set and the production rule feature set.

[0125] Optionally, call the production scheduling model to schedule the production data feature set and the production rule feature set, and obtain the overall production schedule of the first product and / or the second product.

[0126] By adopting the above technical solution, the product affecting the factory production can be changed into the second product, ensuring that the second product can meet the needs of the people in the affected area, and updating the production schedule according to the actual situation of the affected factory to ensure the production volume of the second product.

[0127] In the following embodiments, when producing the second product, it is necessary to consider transforming the production equipment of the factory so that the equipment can meet the production requirements of the second product. Therefore, the embodiments of the present application disclose a personnel flow method. Refer to Figure 7 , the method includes: Step S701: Generate a skill portrait according to the update method.

[0128] In this step, first, a detailed skill portrait needs to be generated for each employee according to the update method (such as data collection, artificial intelligence algorithms, historical record analysis, etc.).

[0129] Among them, the skill portrait is a comprehensive description of each employee's skills, experience, work ability, etc. The skill portrait includes the employee's professional skills, work experience, educational background, project experience, certificate certifications, etc.

[0130] The skill portrait can be generated in various ways. Exemplarily, combine information such as internal training records, job performance, employee self-evaluation, and colleague evaluation to generate the skill portrait. Exemplarily, extract the employee skill characteristics from the historical data through a machine learning model to generate the skill portrait.

[0131] Step S702: Search for target personnel in each factory according to the skill portrait and determine the location of the target personnel.

[0132] Exemplarily, calculate the similarity between the employee skill portrait of each employee in each factory and the skill portrait. Select the employees with a similarity greater than the preset similarity threshold as the target personnel. Take the factory location corresponding to the target personnel as the location of the target personnel.

[0133] Step S703: For the target affected factory among the affected factories, determine the actual number of target personnel in the target affected factory and the theoretical required number of target personnel in the target affected factory.

[0134] Optionally, based on historical data, production plans, and actual working conditions, determine the theoretical required number of target personnel for the target-influencing factory. The theoretical required number is the ideal personnel allocation obtained by predicting multiple factors such as the factory's production tasks, equipment requirements, and order volume. However, due to possible fluctuations in the actual production process, the actual number often differs from the theoretical required number. Therefore, a deviation number needs to be added to the theoretical required number.

[0135] Step S704: When the actual number is less than the theoretical required number, determine the movement mode of the target personnel according to the location of the target-influencing factory and the difference in the number between the actual number and the theoretical required number.

[0136] The theoretical required number is a preset empirical value, and relevant personnel can adjust it according to actual needs.

[0137] By adopting the above technical solution, the personnel flow within the factory is adjusted so that the target personnel can reach the target-influencing factory in a timely manner, and an update method is provided for the target-influencing factory to ensure the normal operation of the target-influencing factory.

[0138] Based on the same inventive concept, an embodiment of the present application provides an industrial production scheduling system. Please refer to Figure 8 , including: An acquisition module 801, configured to acquire production data, a first industrial production rule, a scheduling plan model, actual production conditions, historical market demands, current market demand change conditions, influencing regions, preset correlation degrees, product demand locations, theoretical required numbers, and skill portraits; A memory 802, configured to store the program of the industrial production scheduling method of any one of the above; A processor 803, the program in the memory can be loaded and executed by the processor and implement the industrial production scheduling method of any one of the above.

[0139] By adopting the above technical solution, a production data feature set and a production rule feature set are respectively obtained through the production data related to the first product and the first industrial production rule of the first product, and the total production scheduling plan of the first product is obtained through the production data feature set and the production rule feature set. This method significantly optimizes the efficiency and flexibility of industrial production planning and scheduling through the language understanding and reasoning ability of the scheduling plan model.

[0140] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be allocated to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working processes of the above-mentioned system, device, and unit can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0141] An embodiment of the present application provides a computer-readable storage medium storing a computer program that can be loaded and executed by a processor to implement an industrial production scheduling method.

[0142] The computer-readable storage medium includes, for example, various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs.

[0143] Based on the same inventive concept, an embodiment of the present application provides an intelligent terminal, including a memory and a processor, where the memory stores a computer program that can be loaded and executed by the processor to implement an industrial production scheduling method.

[0144] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be allocated to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working processes of the above-mentioned system, device, and unit can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0145] The above are all preferred embodiments of the present application. Without limiting the protection scope of the present application accordingly, any feature disclosed in this specification (including the abstract and drawings), unless specifically described, can be replaced by other equivalent or features with similar purposes. That is, unless specifically described, each feature is only an example of a series of equivalent or similar features.

Claims

1. An industrial production scheduling method, characterized in that, The method includes: Collecting production data related to the first product from each factory, where the production data includes at least one of the collection order requirements, production resources, equipment status, and raw material inventory of the first product; Performing preprocessing and feature extraction operations on the production data to obtain a production data feature set of the production data; Obtaining a first industrial production rule for the first product, where the first industrial production rule is used as a constraint condition for producing the first product, and the first industrial production rule includes at least one of product production goals, product order priorities, production cycle constraints, and equipment maintenance plans; Performing a feature extraction operation on the first industrial production rule to obtain a production rule feature set of the first industrial production rule; Invoking a production scheduling model to perform production scheduling on the production data feature set and the production rule feature set to obtain a total production scheduling plan for the first product, where the total production scheduling plan includes the production scheduling plans of each factory.

2. The industrial production scheduling method according to claim 1, characterized in that The method further includes: Real-time monitoring of the production situation of each factory to obtain the actual production situation of each factory; For a target factory among the various factories, determining the target production scheduling plan of the target factory in the total production scheduling plan, and determining the target actual production situation of the target factory in the actual production situation; In the case where the similarity between the target production scheduling plan and the target actual production situation is less than a preset similarity, obtaining the production anomaly cause of the target factory according to the target production scheduling plan and the target actual production situation; Updating the production data feature set according to the production anomaly cause, and using the updated production data feature set to adjust the total production scheduling plan.

3. The industrial production scheduling method according to claim 2, characterized in that The method further includes: Statistically analyzing the historical market demand in similar periods during the historical period of the first product; Statistically analyzing the current market demand change situation of the first product in the current period, where the current period corresponds to the similar period; Performing an integration process on the historical market demand and the current market demand change situation to obtain the theoretical market demand of the first product; Updating the first industrial production rule using the theoretical market demand.

4. The industrial production scheduling method according to claim 2, wherein, The method further includes: In the case where the abnormal production cause belongs to an irresistible abnormal production cause, determining the affected area according to the abnormal production cause; Determining the affected factories located near the affected area; Statistically analyzing the affected production data of the affected factories; Updating the total production scheduling plan using the affected production data.

5. The industrial production scheduling method according to claim 4, characterized in that The method further includes: Calculating the correlation degree between the first product and the abnormal production cause; In the case where the correlation degree is greater than a preset correlation degree, adjusting the current product production goal of the affected factory according to the distance from the affected factory to the affected area and the demand degree of the affected area for the first product; Collecting the first traffic status of the affected factory and the second traffic status within the affected area; Collecting the product demand locations within the affected area; Invoke the path planning model to perform path planning on the location of the influencing factory, the current product production target, the location of the product demand area, the first traffic condition, and the second traffic condition, so as to obtain the transportation route from the influencing factory to the product demand area and the corresponding first product carrying capacity of each transportation route.

6. The industrial production scheduling method according to claim 5, characterized in that, The method further includes: In the case where the correlation degree is less than the preset correlation degree, according to the equipment information of the influencing factory, obtain the feasibility result of the influencing factory producing the second product; In the case where the feasibility result is that production is feasible, determine the method for updating the production line of the influencing factory and predict the longest time for the influencing factory to update the production line; Use the longest time and the relevant information of the second product to update the influencing production data, and update the production data feature set based on the influencing production data; Obtain the second industrial production rule of the second product; Use the second industrial production rule to update the production rule feature set; Update the production scheduling plan of the influencing factory through the production data feature set and the production rule feature set.

7. The industrial production scheduling method according to claim 6, wherein The method further includes: Generate a skill portrait according to the update method; Search for target personnel in each factory according to the skill portrait and determine the location of the target personnel; For the target influencing factory among the influencing factories, determine the actual number of the target personnel in the target influencing factory and the theoretical required number of the target personnel by the target influencing factory; In the case where the actual number is less than the theoretical required number, determine the flow mode of the target personnel according to the location of the target influencing factory and the difference in the number between the actual number and the theoretical required number.

8. An industrial production scheduling system, characterized in that, The system includes: An acquisition module, configured to acquire production data, the first industrial production rule, a scheduling plan model, the actual production situation, historical market demand, the current market demand change situation, the influencing area, the preset correlation degree, the product demand area, the theoretical required number, and the skill portrait; A memory, configured to store the program of the industrial production scheduling method according to any one of claims 1 to 7; A processor, the program in the memory can be loaded and executed by the processor and implement the industrial production scheduling method according to any one of claims 1 to 7.

9. An intelligent terminal, characterized in that, It includes a memory and a processor, and a computer program capable of being loaded and executed by the processor as described in any one of claims 1 to 7 is stored on the memory.

10. A computer-readable storage medium, characterized in that, A computer program capable of being loaded and executed by the processor as described in any one of claims 1 to 7 is stored.

Images